基于重复任务的复杂结构挖掘  

Mining Complex Structure Based on the Repetitive Task

作　　者：叶小虎[1] 刘芳妤[2] 薛岗[2] 

机构地区：[1]云南大学信息科学与工程学院,昆明650091 [2]云南大学国家示范性软件学院,昆明650091

出　　处：《计算机科学》2011年第B10期209-211,224,共4页Computer Science

基　　金：云南省教育厅科学研究基础基金项目(2010Y252)资助

摘　　要：过程挖掘对于部署新的商业流程以及审计、分析和改进已有的流程是非常有帮助的。在商业流程系统日志中,同名任务和重复任务是大量存在的。现有的挖掘算法都不能很好地区分,这导致在过程挖掘的结果中往往会产生不准确的流程模型。为了提高过程挖掘的准确性,提出了一种改进方法,它不仅能够挖掘日志中的循环结构、非自由选择结构等复杂结构,还能够挖掘日志中的同名任务和重复任务。Process mining is helpful for deploying new business processes as well as auditing,analyzing and improving the already enacted ones.The namesake task and a repetitive task exist in the business process of system log of a large number.The existing alpha algorithm of the mining algorithm can distinguish them very well.It leads to the results of the process mining will often produce inaccurate flow model.In order to improve the accuracy of the process mining,it put forward an improved method.The new method not only can dig the complex structure,such as circulation structure,free choice structure and so on,but also can dig the eponymous task and repeat task in the log.

关 键 词：过程挖掘 同名任务 重复任务 复杂结构 

分 类 号：TP311.5[自动化与计算机技术—计算机软件与理论]