ocr_platform/ocr_validator/config/杨万益_福建农信.yaml

# 文档: 德_内蒙古银行照
document:
  name: "杨万益_福建农信"
  base_dir: "/Users/zhch158/workspace/data/流水分析/杨万益_福建农信"
  
  # 🎯 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_v4
    # - tool: "mineru"
    #   result_dir: "bank_statement_yusys_v4"
    #   image_dir: "bank_statement_yusys_v4/{{name}}"
    #   description: "YUSYS-OCR框架 v4.0 GLM-OCR"
    #   enabled: true

    # # 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_local glm-ocr
    - tool: "mineru"
      result_dir: "bank_statement_yusys_local"
      image_dir: "bank_statement_yusys_local/{{name}}"
      description: "YUSYS-OCR框架(local) GLM-OCR"
      enabled: true

    # bank_statement_yusys_local paddleocr_vl
    - tool: "mineru"
      result_dir: "bank_statement_paddle_vl_local"
      image_dir: "bank_statement_paddle_vl_local/{{name}}"
      description: "YUSYS-OCR框架(local) PaddleOCR-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