基于Petri网行为紧密度的有效低频行为模式分析

Analysis of Effective Low-frequency Behavioral Patterns Based on Petri Net Behavior Closeness

低频行为模式分析是流程管理的重要内容之一,有效区分低频日志和噪音日志在业务流程过程挖掘中显得尤为重要。目前已有的研究大部分是将流程模型中的低频行为当作噪音直接过滤,但有些低频行为对模型是有效的。文中提出了基于Petri网行为紧密度的有效低频模式分析方法。首先,根据给定的事件日志建立合理的流程模型;然后,通过迭代扩展初始模式来发现流程模型中的所有低频日志序列,并在此基础上计算日志与模型的行为距离向量,利用日志与模型的行为紧密度找出有效的低频行为模式;最后,通过实例分析验证了所提方法的可行性。

Low-frequency behavior pattern analysis is one of the important contents of process management.It is very important to distinguish low-frequency logs and noise logs effectively in business process mining.At present,most of the researches have dealt with the direct filtering of low-frequency behavior in the process model as noise,but some low frequency behavior are valid for the model.This paper presented an effective low-frequency pattern analysis method based on Petri nets’behavioral closeness.Firstly,a reasonable process model is established according to the given event log.Then,all low-frequency log sequences in the process model are found by iteratively expanding the initial patterns.Based on this,the behavioral distance vectors of the log and the model are calculated,and the behavior closeness of log and model is used to find the effective low-frequency behavioral pattern.Finally,an example is given to verify the feasibility of this method.