Robotic Process Automation and Machine Learning: a Systematic Review

Abstract

The need for companies to seek new techniques that generate productivity gains made them carry out the mapping of their processes using Business Process Management (BPM). Well-mapped processes make it possible to identify repetitive tasks, which can be automated using Robotic Process Automation (RPA), where a computer program mimics the actions of an employee. Furthermore, recent advances in Artificial Intelligence have brought new possibilities to RPA. The systematic review developed aims to raise information on Robotic Process Automation (RPA) integrated with Artificial Intelligence (AI) for autonomously automating work processes.

AI Based Assistive Maintenance of Machines via Querix Expert-System

“…While neural networks may seem as the only solution due to their popularity and accessible tool-chains, alternative AI methods like expert systems offer the advantage of backtracking the decision processes, an inherent feature of their design (Zhang, 2019;Bloecher and Alt, 2021;Valerio de Moraes et al, 2022). This capability is even more suited in industrial contexts where the hidden process behind each decisions is as crucial as the decisions themselves.…”

The design of Bayesian diagnostic expert system Querix and it’s engineering application

“…However, it has lost attraction in favor of artificial neural networks in recent years, which is mostly influenced by the availability of data to train neural network models and the availability of various frameworks to achieve fast time-to-market applications for given solutions. 2022)), this creates a space for other AI methods, such as expert systems, and brings the possibility of explaining their decisions (Korb and Nicholson (2004); Thrun et al (2005)), as it is naturally implemented inside the system itself.…”