An approach to repair Petri net-based process models with choice structures

Model repair is regarded as a new process mining technique. It can repair process models of information systems according to the generated event logs. The existing approaches focus on eliminating deviations between the activities performed by a process model and those observed in event logs. However, they cannot efficiently enhance other conformance dimensions, such as precision and simplicity. In order to obtain a repaired model with higher conformance, this work designs a new model repair approach. It builds process models via Petri nets (PNs) and investigates how to repair a PN-based process model with choice structures. An extended alignment is defined to be added to reachable markings of a Petri net. Then we can compute the deviations in the Petri net and repair the process model accordingly. The correctness and effectiveness of the proposed approach is illustrated by some examples.