A probabilistic BPMN normal form to model and advise human activities

Abstract

Agent-based technologies, originally proposed with the aim of assisting human activities, have been recently adopted in industry for automating business processes. Business Process Model and Notation (BPMN) is a standard notation for modeling business processes, that provides a rich graphical representation that can be used for common understanding of processes but also for automation purposes.We propose a normal form of Business Process Diagrams based on Activity Theory that can be transformed to a Causal Bayesian Network, which in turn can be used to model the behavior of activity participants and assess human decision through user agents. We illustrate our approach on an Elderly health care scenario obtained from an actual contextual study.