Matching events and activities by integrating behavioral aspects and label analysis.

Area of Science:

• Computer Science
• Information Systems
• Business Process Management

Background:

• Business processes increasingly rely on IT services, generating vast event data.
• Process mining techniques analyze event data for process discovery, conformance checking, and performance enhancement.
• Accurate mapping of events to model activities is crucial for effective process mining.

Purpose of the Study:

• To develop a semi-automatic approach for mapping events to activities with minimal manual effort.
• To improve the efficiency and accuracy of process mining by enhancing event-to-activity mapping.
• To reduce the manual workload associated with analyzing large event logs.

Main Methods:

• Implemented a semi-automatic event-to-activity mapping approach.
• Utilized behavioral analysis and label analysis for mapping insights.
• Extracted Declare constraints from event logs and process models to build matching constraints.
• Applied natural language processing techniques for label-based matching and integration with external knowledge sources.

Main Results:

• Successfully developed and evaluated a semi-automatic event-to-activity mapping method.
• Demonstrated effectiveness using both synthetic and real-life process execution data.
• Showcased robustness of the approach even with non-conforming execution logs.

Conclusions:

• The proposed semi-automatic approach significantly aids in mapping events to activities for process mining.
• The method effectively reduces manual effort and enhances the accuracy of process analysis.
• The approach is robust and applicable to diverse datasets, including those with deviations.