LMV-RPA: Large Model Voting-based Robotic Process Automation
This addresses the need for faster and more reliable document automation in operational settings, though it appears incremental as it combines existing methods.
The paper tackled the problem of low accuracy and efficiency in Optical Character Recognition (OCR) for high-volume unstructured data processing by introducing LMV-RPA, a system that integrates multiple OCR engines and Large Language Models with a majority voting mechanism, achieving 99% accuracy and an 80% reduction in processing time compared to baselines.
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.