Search

A business process model represents the expected behavior of a set of process instances (cases). The process instances may be executed in parallel and may affect each other through data or resources. In particular, changes in values of data shared by process instances may affect a set of process instances and require some operations in response. Such potential effects do not explicitly appear in the process model. This paper addresses possible impacts that may be affected through shared data across process instances and suggests how to analyze them at design time (when the actual process instances do not yet exist). The suggested method uses both a process model and a (relational) data model in order to identify potential inter-instance data impact sets. These sets may guide process users in tracking the impacts of data changes and supporting their handling at runtime. They can also assist process designers in exploring possible constraints over data. The applicability of the method was evaluated using three different realistic processes. Using a process expert, we further assessed the usefulness of the method, revealing some useful insights for coping with unexpected data-related changes suggested by our approach., Comment: 34 pages, 2 figures and 6 tables