Associating Event Logs with Ontologies for Semantic Process Mining and Analysis

Abstract

Process mining uses various forms of event logs to extract process-related information, in order to discover, analyze conformance, or to enhance (business) processes. The vast majority of process mining applications are based on event logs with flat, keyword-based activity and resource descriptions. Many human-designed processes, however, are based on explicit workflow or lifecycle models with associated product models, both of which can be described using taxonomies or more complicated ontologies. This additional information can be used to analyze and visualize the processes with better insight of and improved formal access to the data. In this paper, we introduce a generic approach for enriching process mining using events logs with associated ontology structures. The main contribution and benefit of this approach lies in the ability to analyze the models in different abstraction levels, which greatly helps understanding complicated processes. Our main application areas are related to engineering and documentation processes.