Process-Oriented Modelling, Creation, and Interpretation of Multi-Agent Systems
Abstract
In the past, different ways of integrating business processes and multi-agent systems have been proposed. Often, those approaches use restricted process models or target only single agents, and are thus not making full use of the expressive power of modern process modelling notations. Nevertheless, business processes have many notions in common with agents, giving them great potential for modelling complex multi-agent systems. In this article, we combine concepts from several existing approaches to a mapping from business process diagrams to readily executable agent components. That mapping has been implemented in two ways: As a transformation, producing well-structured and extensible agent code, and as an interpreter, accounting for nearly the entire expressiveness of the process modelling notation.