On Measuring Semantic Similarity of Business Process Models

Identifying and integrating similar business processes within different organizations is an important task in construction of virtual enterprise. However, the same business process may be represented in different ways by different modelers even when they using the same modeling language. This is because that different organization using different terminologies and the problem of semantic heterogeneity makes it a tedious job to compare business processes. Therefore, the technologies of semantic similarity computing are employed to resolve ambiguity issues caused by the use of synonyms or homonyms. In particular, the idea of similarity propagation is introduced to pick out a mapping between corresponding activities and data, and Hungarian algorithm is expanded to reduce its time complexity. Then the similarity of whole models is measured based on Jaccard coefficient. Finally, an experiment is given to evaluate the method.