Maheen SohailFollow

Degree

Master of Science in Computer Science

Department

Department of Computer Science

School

School of Mathematics and Computer Science (SMCS)

Date of Submission

Spring 2024

Supervisor

Saiyed Shahab Ahmed

Keywords

Invoice Processing, Robotic Process Automation, Optical Character Recognition, Data Extraction, AI Builder

Abstract

This project aims to develop an automated invoice processing system leveraging Robotic Process Automation (RPA) and Optical Character Recognition (OCR) technologies to streamline invoice management, reduce manual effort, and minimize errors. The system captures invoice images via a mobile application and validates the vendor against a predefined vendor list. Recognized vendor’s invoices are uploaded to SharePoint and sent for further processing with OCR to extract data, while others are routed for approval before being processed further. This dual-path workflow ensures both speed and accuracy in handling invoices.

Developed with Microsoft Power Apps and automated using Microsoft Power Automate, the system integrates AI Builder for OCR capabilities. Testing showed significant reductions in processing time and errors. The potential industry impact includes increased productivity, cost savings, and enhanced compliance.

Future work will focus on enhancing the system's capabilities, including expanding the range of supported invoice formats, improving the accuracy of OCR, and integrating advanced machine learning algorithms to handle more complex validation tasks.

This project demonstrates a practical application of RPA and OCR technologies in automating and improving business processes, highlighting its potential for widespread adoption and contributing to the digital transformation of invoice management.

Document Type

Open Access

Submission Type

Research Project

Loading...

Media is loading
 
Download

The full text of this document is only accessible to authorized users.

Share

COinS