Checking Wrong Pattern in Process Model Containing Invisible Task by Using Declarative Miner

摘要

Event log records all events of performed business process on the system. Analysts used the event log to detect occurred anomalies, one of which is wrong pattern, in the process. However, there are conditions, i.e. skip condition, redo condition, and switch condition, which can be misinterpreted as wrong pattern. Uniquely, those conditions cannot be depicted in the reference model without utilizing additional tasks, namely invisible tasks. This research proposes rules which can check the wrong pattern in the process model containing those conditions. This research automatically formed declarative miner rules carrying invisible tasks based on a process model. The form of the used process model in this research is a graph model. Then, the rules are used to checking the wrong pattern. The experiment uses real data, i.e. port-container handling processes, and several simulation data. The analysis explains that declarative miners have 100% accuracy to check the wrong pattern in the process model that contains each invisible task including skip condition, redo condition, and switch condition.