LMV-RPA: Large Model Voting-based Robotic Process Automation

Bewaard in:

Bibliografische gegevens
Gepubliceerd in:	arXiv.org (Dec 23, 2024), p. n/a
Hoofdauteur:	Abdellatif, Osama
Andere auteurs:	Ahmed, Ayman, Hamdi, Ali
Gepubliceerd in:	Cornell University Library, arXiv.org
Onderwerpen:	Accuracy Layouts Data processing Unstructured data Large language models Automation Engines Optical character recognition Task complexity
Online toegang:	Citation/Abstract Full text outside of ProQuest
Tags:	Voeg label toe Geen labels, Wees de eerste die dit record labelt!

Omschrijving
Samenvatting:	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.
ISSN:	2331-8422
Bron:	Engineering Database