摘要
过程挖掘是业务流程管理的核心内容之一。现有的方法多是基于控制流观点进行过程挖掘的,但是在挖掘存在时延的业务流程时,此方法存在一定的局限性。目前基于队列观点进行过程挖掘的方法,为挖掘存在时延的流程提供了定量分析的技术支持,但是在多类别队列挖掘方面存在不足。笔者针对G/M/s+M,D/M/c+M和M/M/1三种不同的队列类型提出不同的时延预测方法,并且将服务流程中不同的顾客类别对时延预测产生的影响考虑在内,对特定顾客进行基于队列长度的时延预测。同时提出了通过总结时延数据得到事件的行为信息,以此优化初始流程模型的方法。文章提出的多类别队列挖掘方法,针对目前队列挖掘方法在考虑多队列类型方面的不足进行了完善,同时能运用在优化流程模型方面。最后通过实例验证方法的有效性。
The process mining is one of the core content of business process management .The existing methods are most based on the view of control‐flow .However ,there are some limitations in the existing methods for the execution of the business processes which hold delay .At present ,the method of process mining based on queue view provides quantitative analysis for the process of time delay ,but it is insufficient in multi class queue mining .This paper put forward different delay prediction algorithm according to G/M/s+ M ,D/M/c+ M and M/M/1 three different type of queue system .In addition ,in consideration of the effect of different customer categories in the service process ,predict the time delay based on the delay of the queue length for target‐customer at the instant .At the same time ,the method of optimizing the initial process model is introduced by summarizing the behavior information which mined by the data of delay prediction of the event .Multi‐class queue mining method is proposed in this paper ,which not only can accurately mining the business process with time delay ,but also but also improve the problem of queue mining in the case of multi‐class queue system .At the same time ,the proposed multi class queue mining method can be used in the optimization process model ,and finally through an example to verify the effectiveness of the method .
出处
《皖西学院学报》
2016年第2期55-61,共7页
Journal of West Anhui University
基金
国家自然科学基金项目(61572035
61402011
61272153)
安徽省自然科学基金(1508085MF111)
安徽省高校自然科学基金重点项目(KJ2014A067)
安徽省优秀青年基金项目(ZY290)资助
