Artificial intelligence optimization strategies for invoice management : a preliminary study

Abstract

It is very common for companies to receive invoices (and other semistructured documents) in paper and PDF files and someone has to manually enter that data into a digital structure like a database or comma-separated values (CSV) file. This type of work is very time-consuming (making it expensive) and exhaustive (making it prone to errors). Data entry activities also force high-paying specialized workers to do repetitive tasks or to outsource that work, making it hard to manage the data workflow. There is a need to automate this type of process. In this context, the following paper presents a preliminary study and review of technologies, tools and recent research strategies for invoice management mainly in the scope of robotic process automation tools.