用大模型投票提升复杂文档识别准确率
LMV-RPA: Large Model Voting-based Robotic Process Automation
- 多个OCR+大模型输出通过投票机制融合
- 99%准确率，处理速度提升80%
- 适合大规模文档自动化场景
自动化高吞吐量非结构化数据处理对运营效率至关重要。光学字符识别（OCR）虽关键，但在复杂版式和模糊文本中常面临准确率与效率难题，尤其在大规模任务中更为突出。本文提出基于大模型投票的机器人流程自动化系统LMV-RPA，整合Paddle OCR、Tesseract OCR、EasyOCR和DocTR等OCR引擎，以及LLaMA 3和Gemini-1.5-pro等大语言模型（LLMs）的输出。通过多数投票机制，将OCR结果转化为结构化JSON格式，显著提升复杂版式下的识别准确率。多阶段流水线将OCR提取的文本经由大模型处理并融合结果，确保最优输出。实验表明，LMV-RPA在OCR任务中达到99%准确率，超越基线模型的94%，同时处理时间减少80%。基准测试验证其可扩展性，证明该系统为大规模文档处理提供了更快速、可靠且高效的解决方案。
原文摘要 · Abstract (English)
Automating high-volume unstructured data processing is essential for operational efficiency. Optical Character Recognition (OCR) is critical but often struggles with accuracy and efficiency in complex layouts and ambiguous text. These challenges are especially pronounced in large-scale tasks requiring both speed and precision. This paper introduces LMV-RPA, a Large Model Voting-based Robotic Process Automation system to enhance OCR workflows. LMV-RPA integrates outputs from OCR engines such as Paddle OCR, Tesseract OCR, Easy OCR, and DocTR with Large Language Models (LLMs) like LLaMA 3 and Gemini-1.5-pro. Using a majority voting mechanism, it processes OCR outputs into structured JSON formats, improving accuracy, particularly in complex layouts. The multi-phase pipeline processes text extracted by OCR engines through LLMs, combining results to ensure the most accurate outputs. LMV-RPA achieves 99 percent accuracy in OCR tasks, surpassing baseline models with 94 percent, while reducing processing time by 80 percent. Benchmark evaluations confirm its scalability and demonstrate that LMV-RPA offers a faster, more reliable, and efficient solution for automating large-scale document processing tasks.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。