Enhancing the Quality of Merged Process Models by Addressing Invisible Task

Abstract

Model merging is a key approach for integrating multiple process model variants into a unified representation. Existing automated merging methods face challenges in handling invisible tasks, which are intentionally inserted in the process model to depict certain conditions, including stacked branching relationships. The inability to handle invisible tasks reduces the quality of the merged process models. A proposed graph-merging method explicitly addresses sequence, branching relationships, and invisible tasks. The proposed method first identifies common activities across model variants. Furthermore, the method applies the proposed graph rules grounded in behavioral and structural aspects to combine those common activities as well as their related relationships and generate the graph-based merged process model. Behavioral rules govern the integration of sequence and branching relationships, while structural rules handle branching and invisible tasks. An evaluation against two existing approaches by Derguech and Yohanes demonstrates that the proposed graph-merging method achieves higher precision. The graph-merging method substantially improves the quality of merged process models.