rename: edge deployment -> on-device deployment (#4196)

.github/ISSUE_TEMPLATE/3_deploy.md

@@ -33,7 +33,7 @@ assignees: ''
     * 如果是多语言调用的问题，请给出调用示例子。
 
 3. 端侧部署
-    * 您是否完全按照[端侧部署文档教程](https://paddlepaddle.github.io/PaddleX/main/pipeline_deploy/edge_deploy.html)跑通了流程？
+    * 您是否完全按照[端侧部署文档教程](https://paddlepaddle.github.io/PaddleX/main/pipeline_deploy/on_device_deployment.html)跑通了流程？
 
     * 您使用的端侧设备是？对应的PaddlePaddle版本和PaddleLite版本分别是什么？
 

README.md

@@ -68,7 +68,7 @@ PaddleX 3.0 是基于飞桨框架构建的低代码开发工具，它集成了
  ## 📊 能力支持
 
 
-PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI Studio星河社区](https://aistudio.baidu.com/overview)上进行**在线体验**，您可以快速体验各个产线的预训练模型效果，如果您对产线的预训练模型效果满意，可以直接对产线进行[高性能推理](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/high_performance_inference.html)/[服务化部署](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/serving.html)/[端侧部署](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/edge_deploy.html)，如果不满意，您也可以使用产线的**二次开发**能力，提升效果。完整的产线开发流程请参考[PaddleX产线使用概览](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/pipeline_develop_guide.html)或各产线使用[教程](#-文档)。
+PaddleX的各个产线均支持本地**快速推理**，部分模型支持在[AI Studio星河社区](https://aistudio.baidu.com/overview)上进行**在线体验**，您可以快速体验各个产线的预训练模型效果，如果您对产线的预训练模型效果满意，可以直接对产线进行[高性能推理](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/high_performance_inference.html)/[服务化部署](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/serving.html)/[端侧部署](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/on_device_deployment.html)，如果不满意，您也可以使用产线的**二次开发**能力，提升效果。完整的产线开发流程请参考[PaddleX产线使用概览](https://paddlepaddle.github.io/PaddleX/latest/pipeline_usage/pipeline_develop_guide.html)或各产线使用[教程](#-文档)。
 
 
 此外，PaddleX在[AI Studio星河社区](https://aistudio.baidu.com/overview)为开发者提供了基于[云端图形化开发界面](https://aistudio.baidu.com/pipeline/mine)的全流程开发工具, 点击【创建产线】，选择对应的任务场景和模型产线，就可以开启全流程开发。详细请参考[教程《零门槛开发产业级AI模型》](https://aistudio.baidu.com/practical/introduce/546656605663301)
@@ -985,7 +985,7 @@ for res in output:
 
   * [🚀 PaddleX 高性能推理指南](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/high_performance_inference.html)
   * [🖥️ PaddleX 服务化部署指南](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/serving.html)
-  * [📱 PaddleX 端侧部署指南](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/edge_deploy.html)
+  * [📱 PaddleX 端侧部署指南](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/on_device_deployment.html)
   * [🌐 获取 ONNX 模型](https://paddlepaddle.github.io/PaddleX/latest/pipeline_deploy/paddle2onnx.html)
 
 </details>

README_en.md

@@ -74,7 +74,7 @@ PaddleX is dedicated to achieving pipeline-level model training, inference, and
 ## 📊 What can PaddleX do？
 
 
-All pipelines of PaddleX support **online experience** on [AI Studio]((https://aistudio.baidu.com/overview)) and local **fast inference**. You can quickly experience the effects of each pre-trained pipeline. If you are satisfied with the effects of the pre-trained pipeline, you can directly perform [high-performance inference](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/high_performance_inference.html) / [serving](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/serving.html) / [edge deployment](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/edge_deploy.html) on the pipeline. If not satisfied, you can also **Custom Development** to improve the pipeline effect. For the complete pipeline development process, please refer to the [PaddleX pipeline Development Tool Local Use Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/pipeline_develop_guide.html).
+All pipelines of PaddleX support **online experience** on [AI Studio]((https://aistudio.baidu.com/overview)) and local **fast inference**. You can quickly experience the effects of each pre-trained pipeline. If you are satisfied with the effects of the pre-trained pipeline, you can directly perform [high-performance inference](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/high_performance_inference.html) / [serving](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/serving.html) / [edge deployment](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/on_device_deployment.html) on the pipeline. If not satisfied, you can also **Custom Development** to improve the pipeline effect. For the complete pipeline development process, please refer to the [PaddleX pipeline Development Tool Local Use Tutorial](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_usage/pipeline_develop_guide.html).
 
 In addition, PaddleX provides developers with a full-process efficient model training and deployment tool based on a [cloud-based GUI](https://aistudio.baidu.com/pipeline/mine). Developers **do not need code development**, just need to prepare a dataset that meets the pipeline requirements to **quickly start model training**. For details, please refer to the tutorial ["Developing Industrial-level AI Models with Zero Barrier"](https://aistudio.baidu.com/practical/introduce/546656605663301).
 
@@ -85,7 +85,7 @@ In addition, PaddleX provides developers with a full-process efficient model tra
         <th>Local Inference</th>
         <th>High-Performance Inference</th>
         <th>Serving</th>
-        <th>Edge Deployment</th>
+        <th>On-Device Deployment</th>
         <th>Custom Development</th>
         <th><a href="https://aistudio.baidu.com/pipeline/mine">Zero-Code Development On AI Studio</a></td>
     </tr>
@@ -924,7 +924,7 @@ To use the Python script for other pipelines, simply adjust the `pipeline` param
 
   * [🚀 PaddleX High-Performance Inference Guide](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/high_performance_inference.html)
   * [🖥️ PaddleX Serving Guide](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/serving.html)
-  * [📱 PaddleX Edge Deployment Guide](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/edge_deploy.html)
+  * [📱 PaddleX On-Device Deployment Guide](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/on_device_deployment.html)
   * [🌐 Installation and Usage of the Paddle2ONNX Plugin](https://paddlepaddle.github.io/PaddleX/latest/en/pipeline_deploy/paddle2onnx.html)
 
 </details>

docs/pipeline_deploy/edge_deploy.en.md → docs/pipeline_deploy/on_device_deployment.en.md

@@ -2,9 +2,9 @@
 comments: true
 ---
 
-# PaddleX Edge Deployment Demo Usage Guide
+# PaddleX On-Device Deployment Demo Usage Guide
 
-- [PaddleX Edge Deployment Demo Usage Guide](#paddlex-edge-deployment-demo-usage-guide)
+- [PaddleX On-Device Deployment Demo Usage Guide](#paddlex-on-device-deployment-demo-usage-guide)
   - [Installation Process and Usage](#installation-process-and-usage)
     - [Environment Preparation](#environment-preparation)
     - [Material Preparation](#material-preparation)

docs/pipeline_usage/pipeline_develop_guide.en.md

@@ -170,7 +170,7 @@ In addition, PaddleX also provides three other deployment methods, with detailed
 
 ☁️ <b>Serving</b>: Serving is a common deployment strategy in real-world production environments. By encapsulating inference functions into services, clients can access these services via network requests to obtain inference results. PaddleX supports various solutions for serving pipelines. For detailed pipeline serving procedures, please refer to the [PaddleX Pipeline Serving Guide](../pipeline_deploy/serving.md).
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method that places computing and data processing capabilities on user devices themselves, allowing devices to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. Refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md) for detailed edge deployment procedures.
+📱 <b>On-Device Deployment</b>: Edge deployment is a method that places computing and data processing capabilities on user devices themselves, allowing devices to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. Refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md) for detailed edge deployment procedures.
 
 Choose the appropriate deployment method for your model pipeline based on your needs, and proceed with subsequent AI application integration.
 

docs/pipeline_usage/pipeline_develop_guide.md

@@ -172,7 +172,7 @@ PaddleX 也提供了其他三种部署方式，详细说明如下：
 
 ☁️ <b>服务化部署</b>：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持多种产线服务化部署方案，详细的产线服务化部署流程请参考[PaddleX服务化部署指南](../pipeline_deploy/serving.md)。
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 PaddleX 提供了将 Paddle 模型转换为 ONNX 模型的能力，详细说明请参考[Paddle2ONNX 插件的安装与使用](../pipeline_deploy/paddle2onnx.md)

docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.en.md

@@ -498,7 +498,7 @@ print(result["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing functions on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing functions on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.md).
 
 You can choose an appropriate deployment method for your model pipeline based on your needs, and then proceed with subsequent AI application integration.
 

docs/pipeline_usage/tutorials/cv_pipelines/3d_bev_detection.md

@@ -490,7 +490,7 @@ print(result["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 

docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.en.md

@@ -1100,7 +1100,7 @@ pprint.pp(result_infer["faces"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs, and then proceed with subsequent AI application integration.
 
 

docs/pipeline_usage/tutorials/cv_pipelines/face_recognition.md

@@ -1098,7 +1098,7 @@ pprint.pp(result_infer["faces"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.en.md

@@ -1060,7 +1060,7 @@ pprint.pp(result_infer["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline based on your needs for subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/general_image_recognition.md

@@ -1059,7 +1059,7 @@ pprint.pp(result_infer["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.en.md

@@ -753,7 +753,7 @@ print(result["persons"])
 </details>
 <br />
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the AI application subsequently.
 
 

docs/pipeline_usage/tutorials/cv_pipelines/human_keypoint_detection.md

@@ -744,7 +744,7 @@ print(result["persons"])
 </details>
 <br />
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.en.md

@@ -809,7 +809,7 @@ echo "Output image saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/image_anomaly_detection.md

@@ -812,7 +812,7 @@ echo "Output image saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.en.md

@@ -1703,7 +1703,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method that places computing and data processing capabilities directly on the user's device, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method that places computing and data processing capabilities directly on the user's device, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method according to your needs to integrate the model pipeline into subsequent AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/image_classification.md

@@ -1510,7 +1510,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.en.md

@@ -899,7 +899,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline based on your needs for subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/image_multi_label_classification.md

@@ -897,7 +897,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.en.md

@@ -1045,7 +1045,7 @@ print_r($result['instances']);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs and proceed with the integration of AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/instance_segmentation.md

@@ -1045,7 +1045,7 @@ print_r($result["instances"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.en.md

@@ -1293,7 +1293,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method where computation and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline based on your needs for subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/object_detection.md

@@ -1231,7 +1231,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_detection.en.md

@@ -912,7 +912,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs, and then proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_detection.md

@@ -583,7 +583,7 @@ print(result["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_segmentation.en.md

@@ -579,7 +579,7 @@ print(f"Output image saved at {output_image_path}")
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs, and then proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/open_vocabulary_segmentation.md

@@ -575,7 +575,7 @@ print(f"Output image saved at {output_image_path}")
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.en.md

@@ -617,7 +617,7 @@ print(result["pedestrians"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md). You can choose the appropriate deployment method based on your needs to integrate the model pipeline into your AI applications.
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md). You can choose the appropriate deployment method based on your needs to integrate the model pipeline into your AI applications.
 
 ## 4. Custom Development
 If the default model weights provided by the pedestrian attribute recognition pipeline are not satisfactory in terms of accuracy or speed for your specific scenario, you can attempt to further <b>fine-tune</b> the existing models using <b>your own domain-specific or application data</b> to improve the recognition performance of the pipeline in your scenario.

docs/pipeline_usage/tutorials/cv_pipelines/pedestrian_attribute_recognition.md

@@ -613,7 +613,7 @@ print(result["pedestrians"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.en.md

@@ -914,7 +914,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/rotated_object_detection.md

@@ -579,7 +579,7 @@ print(result["detectedObjects"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.en.md

@@ -996,7 +996,7 @@ echo "Output image saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy your model based on your needs and proceed with the integration of AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/semantic_segmentation.md

@@ -1001,7 +1001,7 @@ echo "Output image saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.en.md

@@ -904,7 +904,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method that places computing and data processing functions on the user's device itself. The device can process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method that places computing and data processing functions on the user's device itself. The device can process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model into your AI application.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/small_object_detection.md

@@ -906,7 +906,7 @@ print_r($result["detectedObjects"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.en.md

@@ -598,7 +598,7 @@ print(result["vehicles"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into your AI application.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/cv_pipelines/vehicle_attribute_recognition.md

@@ -610,7 +610,7 @@ print(result["vehicles"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.en.md

@@ -1759,7 +1759,7 @@ print(result_chat["chatResult"])
 </details>
 <br/>
 
-📱 **Edge Deployment**: Edge deployment is a method where computing and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).
+📱 **On-Device Deployment**: Edge deployment is a method where computing and data processing functions are placed on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.md).
 You can choose the appropriate deployment method for your pipeline based on your needs, and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v3.md

@@ -1764,7 +1764,7 @@ print(result_chat["chatResult"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.en.md

@@ -1985,7 +1985,7 @@ print(result_chat["chatResult"])
 </details>
 <br/>
 
-📱 **Edge Deployment**: Edge deployment is a method where computing and data processing functions are placed on the user's device itself. The device can directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).
+📱 **On-Device Deployment**: Edge deployment is a method where computing and data processing functions are placed on the user's device itself. The device can directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.md).
 You can choose an appropriate deployment method for your pipeline based on your needs and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/information_extraction_pipelines/document_scene_information_extraction_v4.md

@@ -2190,7 +2190,7 @@ print(result_chat["chatResult"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.en.md

@@ -1198,7 +1198,7 @@ for i, res in enumerate(result["ocrResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into your AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/ocr_pipelines/OCR.md

@@ -1193,7 +1193,7 @@ for i, res in enumerate(result["ocrResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.en.md

@@ -1915,7 +1915,7 @@ for i, res in enumerate(result["layoutParsingResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model into your pipeline and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/ocr_pipelines/PP-StructureV3.md

@@ -1867,7 +1867,7 @@ for i, res in enumerate(result["layoutParsingResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/ocr_pipelines/doc_preprocessor.md

@@ -602,7 +602,7 @@ for i, res in enumerate(result["docPreprocessingResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.en.md

@@ -996,7 +996,7 @@ for i, res in enumerate(result["formulaRecResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 

docs/pipeline_usage/tutorials/ocr_pipelines/formula_recognition.md

@@ -996,7 +996,7 @@ for i, res in enumerate(result["formulaRecResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.en.md

@@ -1514,7 +1514,7 @@ for i, res in enumerate(result["layoutParsingResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment refers to placing computational and data processing capabilities directly on user devices, enabling them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment refers to placing computational and data processing capabilities directly on user devices, enabling them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 
 You can choose an appropriate method to deploy your model pipeline based on your needs, and proceed with subsequent AI application integration.
 

docs/pipeline_usage/tutorials/ocr_pipelines/layout_parsing.md

@@ -1549,7 +1549,7 @@ for i, res in enumerate(result["layoutParsingResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.en.md

@@ -1345,7 +1345,7 @@ for i, res in enumerate(result["sealRecResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/ocr_pipelines/seal_recognition.md

@@ -1363,7 +1363,7 @@ for i, res in enumerate(result["sealRecResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.en.md

@@ -1384,7 +1384,7 @@ for i, res in enumerate(result["tableRecResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method for your model pipeline according to your needs, and then proceed with the subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition.md

@@ -1303,7 +1303,7 @@ for i, res in enumerate(result["tableRecResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.en.md

@@ -1559,7 +1559,7 @@ for i, res in enumerate(result["tableRecResults"]):
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing the devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing the devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method according to your needs to integrate the model into your AI application.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/ocr_pipelines/table_recognition_v2.md

@@ -1545,7 +1545,7 @@ for i, res in enumerate(result["tableRecResults"]):
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/speech_pipelines/multilingual_speech_recognition.en.md

@@ -311,7 +311,7 @@ print(result)
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs and proceed with subsequent AI application integration.
 
 ## 3. Development Integration/Deployment
@@ -541,7 +541,7 @@ print(result)
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method that places computational and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method that places computational and data processing capabilities directly on user devices, allowing them to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model into your pipeline and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/speech_pipelines/multilingual_speech_recognition.md

@@ -511,5 +511,5 @@ print(result)
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.en.md

@@ -821,7 +821,7 @@ echo "Output time-series data saved at " . $output_csv_path . "\n";
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities on the user's device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs, and then proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_anomaly_detection.md

@@ -902,7 +902,7 @@ echo "Output time-series data saved at " . $output_csv_path . "\n";
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.en.md

@@ -817,7 +817,7 @@ echo "Output image data saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on user devices, allowing them to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_classification.md

@@ -817,7 +817,7 @@ echo "Output image data saved at " . $output_image_path . "\n";
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.en.md

@@ -919,7 +919,7 @@ echo "Output time-series data saved at " . $output_csv_path . "\n";
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md). You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing the device to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed instructions, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md). You can choose the appropriate deployment method based on your needs to integrate the model pipeline into subsequent AI applications.
 
 ## 4. Custom Development
 If the default model weights provided by the time-series forecasting pipeline are not satisfactory in terms of accuracy or speed for your specific scenario, you can attempt to further <b>fine-tune</b> the existing models using <b>your own domain-specific or application data</b> to improve the performance of the time-series forecasting pipeline in your scenario.

docs/pipeline_usage/tutorials/time_series_pipelines/time_series_forecasting.md

@@ -933,7 +933,7 @@ echo "Output time-series data saved at " . $output_csv_path . "\n";
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/video_pipelines/video_classification.en.md

@@ -808,7 +808,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/video_pipelines/video_classification.md

@@ -810,7 +810,7 @@ print_r($result["categories"]);
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/video_pipelines/video_detection.en.md

@@ -523,7 +523,7 @@ print(result["frames"])
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.en.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a method of placing computing and data processing capabilities directly on the user's device, allowing it to process data locally without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed procedures on edge deployment, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.en.md).
 You can choose the appropriate method to deploy the model pipeline according to your needs and proceed with subsequent AI application integration.
 
 ## 4. Custom Development

docs/pipeline_usage/tutorials/video_pipelines/video_detection.md

@@ -526,7 +526,7 @@ print(result["frames"])
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 ## 4. 二次开发

docs/pipeline_usage/tutorials/vlm_pipelines/doc_understanding.en.md

@@ -724,7 +724,7 @@ print('Reply:', content)
 </details>
 <br/>
 
-📱 <b>Edge Deployment</b>: Edge deployment is a way of placing computing and data processing functions on the user device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX Edge Deployment Guide](../../../pipeline_deploy/edge_deploy.md).
+📱 <b>On-Device Deployment</b>: Edge deployment is a way of placing computing and data processing functions on the user device itself, allowing the device to process data directly without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to the [PaddleX On-Device Deployment Guide](../../../pipeline_deploy/on_device_deployment.md).
 You can choose the appropriate deployment method for your needs and proceed with subsequent AI application integration.
 
 

docs/pipeline_usage/tutorials/vlm_pipelines/doc_understanding.md

@@ -725,7 +725,7 @@ print('Reply:', content)
 </details>
 <br/>
 
-📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/edge_deploy.md)。
+📱 <b>端侧部署</b>：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考[PaddleX端侧部署指南](../../../pipeline_deploy/on_device_deployment.md)。
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。
 
 

docs/practical_tutorials/anomaly_detection_tutorial.en.md

@@ -302,6 +302,6 @@ For more parameters, please refer to [Anomaly Detection Pipeline Usage Tutorial]
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/anomaly_detection_tutorial.md

@@ -299,6 +299,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/deployment_tutorial.en.md

@@ -10,7 +10,7 @@ The three deployment methods of PaddleX are detailed below:
 
 * High-Performance Inference: In actual production environments, many applications have stringent performance standards for deployment strategies, especially in terms of response speed, to ensure efficient system operation and smooth user experience. To this end, PaddleX provides a high-performance inference plugin aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end speedups. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functionality as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving low-cost serving deployment in pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method where computing and data processing functions are placed on the user's device itself, allowing the device to directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method where computing and data processing functions are placed on the user's device itself, allowing the device to directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 This tutorial will introduce the three deployment methods of PaddleX through three practical application examples.
 
@@ -322,7 +322,7 @@ Running Results:
 
   The operations for other pipelines are similar to the above two. For more details, refer to the pipeline usage tutorials.
 
-## 3 Edge Deployment Example
+## 3 On-Device Deployment Example
 
 ### 3.1 Environment Preparation
 

docs/practical_tutorials/deployment_tutorial.md

@@ -12,7 +12,7 @@ PaddleX 的三种部署方式详细说明如下：
 
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
 
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 本教程将举三个实际应用例子，来依次介绍 PaddleX 的三种部署方式。
 

docs/practical_tutorials/document_scene_information_extraction(layout_detection)_tutorial.en.md

@@ -637,6 +637,6 @@ For more parameters, please refer to the [Document Scene Information Extraction
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugin aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/document_scene_information_extraction(layout_detection)_tutorial.md

@@ -663,6 +663,6 @@ chat_result = pipeline.chat(key_list=["页眉", "表格标题"], visual_info=vis
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/document_scene_information_extraction(seal_recognition)_tutorial.en.md

@@ -474,6 +474,6 @@ For more parameters, please refer to the [Document Scene Information Extraction
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugin aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/document_scene_information_extraction(seal_recognition)_tutorial.md

@@ -489,6 +489,6 @@ chat_result = pipeline.chat(key_list=["印章名称"], visual_info=visual_info_l
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能部署指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/formula_recognition_tutorial.md

@@ -648,6 +648,6 @@ python -m pip install paddlex_hps_client-*.whl
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 基础服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/image_classification_garbage_tutorial.en.md

@@ -419,6 +419,6 @@ For more parameters, please refer to the [General Image Classification Pipeline
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugin aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/image_classification_garbage_tutorial.md

@@ -417,6 +417,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/instance_segmentation_remote_sensing_tutorial.en.md

@@ -368,6 +368,6 @@ For more parameters, please refer to the [General Instance Segmentation Pipeline
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/instance_segmentation_remote_sensing_tutorial.md

@@ -387,6 +387,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/layout_detection.en.md

@@ -619,6 +619,6 @@ The `client.py` script in the `client` directory contains examples of service ca
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Service-Oriented Deployment: Service-oriented deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective service-oriented deployment of production lines. For detailed service-oriented deployment procedures, please refer to the [PaddleX Service-Oriented Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can choose the appropriate method to deploy the model pipeline based on your needs, and then proceed with the subsequent integration of AI applications.

docs/practical_tutorials/layout_detection.md

@@ -622,6 +622,6 @@ python -m pip install paddlex_hps_client-*.whl
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 基础服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/object_detection_fall_tutorial.en.md

@@ -391,6 +391,6 @@ For more parameters, please refer to [General Object Detection Pipeline Usage Tu
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/object_detection_fall_tutorial.md

@@ -389,6 +389,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/object_detection_fashion_pedia_tutorial.en.md

@@ -397,6 +397,6 @@ For more parameters, please refer to [General Object Detection Pipeline Usage Tu
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/object_detection_fashion_pedia_tutorial.md

@@ -397,6 +397,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/ocr_det_license_tutorial.en.md

@@ -377,6 +377,6 @@ For more parameters, please refer to the [General OCR Pipeline Usage Tutorial](.
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/ocr_det_license_tutorial.md

@@ -376,6 +376,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/ocr_rec_chinese_tutorial.en.md

@@ -379,6 +379,6 @@ For more parameters, please refer to the [General OCR Pipeline Usage Tutorial](.
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/ocr_rec_chinese_tutorial.md

@@ -377,6 +377,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/semantic_segmentation_road_tutorial.en.md

@@ -370,6 +370,6 @@ For more parameters, please refer to [General Semantic Segmentation Pipeline Usa
 
 * high-performance inference: In actual production environments, many applications have stringent standards for deployment strategy performance metrics (especially response speed) to ensure efficient system operation and smooth user experience. To this end, PaddleX provides high-performance inference plugins aimed at deeply optimizing model inference and pre/post-processing for significant end-to-end process acceleration. For detailed high-performance inference procedures, please refer to the [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Serving Deployment: Serving Deployment is a common deployment form in actual production environments. By encapsulating inference functions as services, clients can access these services through network requests to obtain inference results. PaddleX supports users in achieving cost-effective serving deployment of pipelines. For detailed serving deployment procedures, please refer to the [PaddleX Serving Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* On-Device Deployment: Edge deployment is a method that places computing and data processing capabilities directly on user devices, allowing devices to process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment procedures, please refer to the [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can select the appropriate deployment method for your model pipeline according to your needs, and proceed with subsequent AI application integration.

docs/practical_tutorials/semantic_segmentation_road_tutorial.md

@@ -366,6 +366,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/small_object_detection_tutorial.en.md

@@ -320,6 +320,6 @@ For more parameters, please refer to [Small Object Detection Pipeline Usage Tuto
 
 * High-performance deployment: In actual production environments, many applications have strict standards for the performance indicators of deployment strategies (especially response speed) to ensure the efficient operation of the system and the smooth user experience. For this reason, PaddleX provides a high-performance inference plugin, aiming to deeply optimize the performance of model inference and pre/post-processing, achieving significant acceleration of the end-to-end process. For detailed high-performance deployment processes, please refer to [PaddleX High-Performance Inference Guide](../pipeline_deploy/high_performance_inference.en.md).
 * Service deployment: Service deployment is a common deployment form in actual production environments. By encapsulating inference functions into services, clients can access these services through network requests to obtain inference results. PaddleX supports users to achieve service deployment of the pipeline at a low cost. For detailed service deployment processes, please refer to [PaddleX Service Deployment Guide](../pipeline_deploy/serving.en.md).
-* Edge deployment: Edge deployment is a way of placing computing and data processing functions on user devices themselves, where devices can directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to [PaddleX Edge Deployment Guide](../pipeline_deploy/edge_deploy.en.md).
+* Edge deployment: Edge deployment is a way of placing computing and data processing functions on user devices themselves, where devices can directly process data without relying on remote servers. PaddleX supports deploying models on edge devices such as Android. For detailed edge deployment processes, please refer to [PaddleX On-Device Deployment Guide](../pipeline_deploy/on_device_deployment.en.md).
 
 You can choose an appropriate method to deploy the model pipeline according to your needs and proceed with subsequent AI application integration.

docs/practical_tutorials/small_object_detection_tutorial.md

@@ -326,6 +326,6 @@ for res in output:
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。

docs/practical_tutorials/table_recognition_v2_tutorial.md

@@ -1014,6 +1014,6 @@ python -m pip install paddlex_hps_client-*.whl
 
 * 高性能部署：在实际生产环境中，许多应用对部署策略的性能指标（尤其是响应速度）有着较严苛的标准，以确保系统的高效运行与用户体验的流畅性。为此，PaddleX 提供高性能推理插件，旨在对模型推理及前后处理进行深度性能优化，实现端到端流程的显著提速，详细的高性能部署流程请参考 [PaddleX 高性能推理指南](../pipeline_deploy/high_performance_inference.md)。
 * 基础服务化部署：服务化部署是实际生产环境中常见的一种部署形式。通过将推理功能封装为服务，客户端可以通过网络请求来访问这些服务，以获取推理结果。PaddleX 支持用户以低成本实现产线的服务化部署，详细的服务化部署流程请参考 [PaddleX 服务化部署指南](../pipeline_deploy/serving.md)。
-* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/edge_deploy.md)。
+* 端侧部署：端侧部署是一种将计算和数据处理功能放在用户设备本身上的方式，设备可以直接处理数据，而不需要依赖远程的服务器。PaddleX 支持将模型部署在 Android 等端侧设备上，详细的端侧部署流程请参考 [PaddleX端侧部署指南](../pipeline_deploy/on_device_deployment.md)。
 
 您可以根据需要选择合适的方式部署模型产线，进而进行后续的 AI 应用集成。