Dipartimento di Ingegneria informatica, automatica e gestionale

Robotic Process Automation (RPA) is an automation technology that sits between the fields of Business Process Management (BPM) and Artificial Intelligence (AI) that creates software (SW) robots to partially or fully automate rule-based and repetitive tasks (or simply routines) performed by human users in their applications’ user interfaces (UIs). RPA tools are able to capture in dedicated UI logs the execution of many routines of interest. A UI log consists of user actions that are mixed in some order that reflects the particular order of their execution by the user, thus potentially belonging to different routines. When considering state-of-the-art RPA technology in the BPM domain, it becomes apparent that the current generation of RPA tools is driven by predefined rules and manual configurations made by expert users rather than intelligent techniques. In this paper, we discuss our research targeted at injecting intelligence into RPA practices. Specifically, we present an approach to: (i) automatically understand which user actions contribute to which routines inside a UI log (this issue is known as segmentation) and (ii) automatically generate executable RPA scripts directly from the UI logs that record the user interactions with the SW applications involved in a routine execution, thus skipping completely the (manual) modeling activity of the flowchart diagrams.