Intelligent document processing: AI-powered RPA for multilingual OCR of receipts

Abstract

This paper explores the integration of Artificial Intelligence (AI) in Robotic Process Automation (RPA) for document processing, specifically focusing on Optical Character Recognition (OCR) of image receipts in multiple languages. By leveraging a hybrid Convolutional Neural Network (CNN) and Recurrent Neural Network (RNN) model, the system is capable of accurately extracting textual information from receipts. Furthermore, the model classifies these receipts into distinct categories, enabling efficient data management and analysis.