4 Angajamente 6db2bb35e7 ... f91a88eb03

Autor SHA1 Permisiunea de a trimite mesaje. Dacă este dezactivată, utilizatorul nu va putea trimite nici un fel de mesaj Data
  zhch158_admin f91a88eb03 fix(config): 更新最小匹配字符长度为1,并添加多个数据源配置 2 săptămâni în urmă
  zhch158_admin 90c5adad77 并添加多个银行文档配置 2 săptămâni în urmă
  zhch158_admin 78706b705c fix(vl_recognition): 更新VLM表格识别配置,切换为MinerU模块并修正服务地址 2 săptămâni în urmă
  zhch158_admin 5e6956c1a1 feat(yusys_mineru): 添加新的处理器配置,支持多参数输入和调试日志 2 săptămâni în urmă

+ 18 - 0
ocr_tools/ocr_batch/processor_configs.yaml

@@ -26,6 +26,24 @@ processors:
     venv: "conda activate mineru2"
     description: "YUSYS Wired UNET OCR 框架"
 
+  yusys_mineru:
+    script: "/Users/zhch158/workspace/repository.git/ocr_platform/ocr_tools/universal_doc_parser/main_v2.py"
+    input_arg: "--input"
+    output_arg: "--output_dir"
+    extra_args:
+      - "--config=/Users/zhch158/workspace/repository.git/ocr_platform/ocr_tools/universal_doc_parser/config/bank_statement_mineru_vl.yaml"
+      # - "--config=/Users/zhch158/workspace/repository.git/ocr_platform/ocr_tools/universal_doc_parser/config/bank_statement_yusys_v2.yaml"
+      - "--pages=1-35"
+      - "--streaming"
+      - "--debug"
+      - "--log_level=DEBUG"
+    output_subdir: "bank_statement_mineru_vl"
+    log_subdir: "logs/bank_statement_mineru_vl"
+    # output_subdir: "bank_statement_yusys_v2"
+    # log_subdir: "logs/bank_statement_yusys_v2"
+    venv: "conda activate mineru2"
+    description: "YUSYS MinerU OCR 框架"
+
   # -------------------------------------------------------------------------
   # PaddleOCR-VL 处理器
   # -------------------------------------------------------------------------

+ 6 - 3
ocr_tools/universal_doc_parser/config/bank_statement_yusys_v3.yaml

@@ -111,12 +111,15 @@ table_recognition_wired:
 # VLM 表格识别配置(当分类为 'wireless' 时使用)
 vl_recognition:
   # 可选: "mineru" (MinerU VLM) 或 "paddle" (PaddleOCR-VL)
-  module: "paddle"
-  model_name: "PaddleOCR-VL-0.9B"
+  module: "mineru"
+  # model_name: "PaddleOCR-VL-0.9B"
+  # module: "paddle"
+  # model_name: "PaddleOCR-VL-0.9B"
   
   # 后端配置
   backend: "http-client"  # 可选: "http-client", "vllm-engine", "transformers"
-  server_url: "http://10.192.72.11:20016"  # PaddleOCR-VL 服务地址
+  server_url: "http://10.192.72.11:20006"  # MinerU-VL 服务地址
+  # server_url: "http://10.192.72.11:20016"  # PaddleOCR-VL 服务地址
   
   # 图片尺寸限制(避免序列长度超限)
   max_image_size: 4096

+ 8 - 1
ocr_validator/config/global.yaml

@@ -28,7 +28,7 @@ ui:
   
 # OCR数据配置
 ocr:
-  min_text_length: 2
+  min_text_length: 1 # 最小匹配字符长度,过滤过短文本
   default_confidence: 1.0
   exclude_texts: ["Picture", ""]
   
@@ -154,4 +154,11 @@ data_sources:
   - 山西云集科技有限公司.yaml
   - 至远彩色_2023年报.yaml
   - 提取自赤峰黄金2023年报.yaml
+  - 乔_建设银行图.yaml
+  - 湛_平安银行图.yaml
+  - 朱_中信银行图.yaml
+  - 张_微信图.yaml
+  - 付_工商银行943825图.yaml
+  - 许_民生银行图.yaml
+
 

+ 68 - 0
ocr_validator/config/乔_建设银行图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "乔_建设银行图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/乔_建设银行图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # # bank_statement_yusys_v2
+    # - tool: "mineru"
+    #   result_dir: "bank_statement_yusys_v2"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "YUSYS统一OCR框架"
+    #   enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true

+ 68 - 0
ocr_validator/config/付_工商银行943825图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "付_工商银行943825图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/付_工商银行943825图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # bank_statement_mineru_vl
+    - tool: "mineru"
+      result_dir: "bank_statement_mineru_vl"
+      image_dir: "bank_statement_mineru_vl/{{name}}"
+      description: "YUSYS统一OCR框架mineru_vl"
+      enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true

+ 68 - 0
ocr_validator/config/张_微信图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "张_微信图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/张_微信图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # bank_statement_mineru_vl
+    - tool: "mineru"
+      result_dir: "bank_statement_mineru_vl"
+      image_dir: "bank_statement_mineru_vl/{{name}}"
+      description: "YUSYS统一OCR框架mineru_vl"
+      enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true

+ 68 - 0
ocr_validator/config/朱_中信银行图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "朱_中信银行图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/朱_中信银行图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # # bank_statement_yusys_v2
+    # - tool: "mineru"
+    #   result_dir: "bank_statement_yusys_v2"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "YUSYS统一OCR框架"
+    #   enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true

+ 68 - 0
ocr_validator/config/湛_平安银行图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "湛_平安银行图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/湛_平安银行图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # # bank_statement_yusys_v2
+    # - tool: "mineru"
+    #   result_dir: "bank_statement_yusys_v2"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "YUSYS统一OCR框架"
+    #   enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true

+ 68 - 0
ocr_validator/config/许_民生银行图.yaml

@@ -0,0 +1,68 @@
+document:
+  name: "许_民生银行图"
+  base_dir: "/Users/zhch158/workspace/data/流水分析/许_民生银行图"
+  
+  # 🎯 关键改进:定义该文档使用的 OCR 工具及其结果目录
+  ocr_results:
+    # bank_statement_yusys_v3
+    - tool: "mineru"
+      result_dir: "bank_statement_yusys_v3"
+      image_dir: "bank_statement_yusys_v3/{{name}}"
+      description: "YUSYS-OCR框架 v3.0"
+      enabled: true
+
+    # bank_statement_mineru_vl
+    - tool: "mineru"
+      result_dir: "bank_statement_mineru_vl"
+      image_dir: "bank_statement_mineru_vl/{{name}}"
+      description: "YUSYS统一OCR框架mineru_vl"
+      enabled: true
+
+    #  # MinerU
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU 图片合成结果"
+    #   enabled: true
+    
+    # # MinerU (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "mineru_vllm_results_cell_bbox"
+    #   image_dir: "mineru_vllm_results/{{name}}"
+    #   description: "MinerU + PaddleOCR 坐标"
+    #   enabled: true
+   
+    # # PaddleOCR-VL
+    # - tool: "paddleocr_vl"
+    #   result_dir: "paddleocr_vl_results"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM 图片合成结果"
+    #   enabled: true
+    
+    # # PaddleOCR-VL (带 cell bbox)
+    # - tool: "mineru"  # 格式同 MinerU
+    #   result_dir: "paddleocr_vl_results_cell_bbox"
+    #   image_dir: "paddleocr_vl_results/{{name}}"
+    #   description: "PaddleOCR VLM + PaddleOCR 坐标"
+    #   enabled: true
+    
+    # # DotsOCR
+    # - tool: "dots_ocr"
+    #   result_dir: "dotsocr_vllm_results"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR 图片合成结果"
+    #   enabled: true
+  
+    # # DotsOCR (带 cell bbox)
+    # - tool: "mineru"
+    #   result_dir: "dotsocr_vllm_results_cell_bbox"
+    #   image_dir: "dotsocr_vllm_results/{{name}}"
+    #   description: "Dots OCR + PaddleOCR 坐标"
+    #   enabled: true
+
+    # # PPStructV3
+    # - tool: "ppstructv3"
+    #   result_dir: "ppstructurev3_client_results"
+    #   image_dir: "ppstructurev3_client_results/{{name}}"
+    #   description: "PPStructV3 图片合成结果"
+    #   enabled: true