Multi-instance Mining: Discovering Synchronisation in Artifact-Centric Processes.

In complex systems one can often identify various entities or artifacts. The lifecycles of these artifacts and the loosely coupled interactions between them define the system behavior. The analysis of such artifact system behavior with traditional process discovery techniques is often problematic due to the existence of many-to-many relationships between artifacts, resulting in models that are difficult to understand and statistics that are inaccurate. The aim of this work is to address these issues and enable the calculation of statistics regarding the synchronisation of behaviour between artifact instances. By using a Petri net formalisation with step sequence execution semantics to support true concurrency, we create state-based artifact lifecycle models that support many-to-many relations between artifacts. The approach has been implemented as an interactive visualisation in ProM and evaluated using real-life public data.