A method of mining low frequency behavior of business process based on Petri net

Abstract

A new method of mining low-frequency behavior of business processes based on Petri nets is proposed, which involves the discovery and optimization of low-frequency behavior based on process tree cutting and the optimization of Petri net model based on communication behavior contour. Firstly, the initial flow model is established according to the communication behavior contour, and the behavior relationship of the log is represented by the direct flow graph cut from the flow tree, which is matched with the initial model, and all the low frequency sequences are found. Then, the behavior distancevector between the log and the model is calculated, the effective low frequency log and the noise log are distinguished based on the behavior compactness, and the noise log is filtered. Secondly, according to the filtered optimization log, the module net and the feature net are established, and the module net and the feature net are fused to obtain the optimized business process Petri net model.The invention provides the new method for mining low-frequency behavior, which effectively solves the problem of distinguishing low-frequency behavior and noise behavior in the business process by using behavior attributes among different modules, and avoids the structure of influencing the business process due to ignoring the low-frequency behavior in the process mining.

Description

technical field [0001] The invention belongs to the field of e-commerce information technology, and relates to a method for mining and optimizing low-frequency behaviors in business process mining, including a method for mining and optimizing low-frequency behaviors based on process tree cuts and an optimization method for business process Petri net models based on communication behavior profiles. Background technique [0002] At present, business process management plays a vital role in many fields. It not only ensures the normal operation of the enterprise, but also provides guarantee for the accurate and efficient operation of the enterprise. The study of low-frequency behavior is one of the important contents of business process management. In real life, most of the research is based on the complete behavior of the business process recorded in the event log, and then the business process model is mined. The business process model inevitably contains low-frequency behavio...

AI Technical Summary

Problems solved by technology

However, although some low-frequency behaviors appear less frequently, they are also very important to process management. Directly deleting low-frequency behaviors will cause the business process model to lose some regular behaviors, which cannot fully meet the needs of the demander and affect the structure of the business process.

Images