摘要
变化挖掘是业务流程管理的核心,从事件日志中挖掘出业务流程的变化尤为重要。已有对变化挖掘的分析方法大多集中在源模型或目标模型已知的基础上。文中从系统日志的角度提出了一种基于成本最优对齐的业务流程变化挖掘方法。首先,根据事件日志提取出有效的高频形态学发生片段,计算出各迹对齐时的最高成本函数值,并在此基础上发现最优迹对齐;然后,通过度量最优对齐时变化日志与源日志间的相似性度,快速且高效地挖掘出变化集。最后通过实例分析显示了该方法的有效性。
Change mining is the core of business process management,and it is particularly important to mine the changes of business processes from the event log.Most of the existing analysis methods of change mining focus on the source model or target model.From the point of view of system log,this paper proposes a business process change mining method based on cost optimal alignment.Firstly,according to the event log,the effective high frequency morphological occurrence segment is extracted,the highest cost function value of each trace alignment is calculated,and on this basis,the optimal trace alignment is found,and then the similarity between the change log and the source log is measured to mine the change set quickly and efficiently.Finally,an example is given to show the effectiveness of the method.
作者
刘静
方贤文
LIU Jing;FANG Xian-wen(College of Mathematics and Big Data,Anhui University of Science and Technology,Huainan,Auhui232001,China)
出处
《计算机科学》
CSCD
北大核心
2020年第7期78-83,共6页
Computer Science
基金
国家自然科学基金(61272153,61402011)
安徽省自然科学基金(1508085MF111,1608085QF149)
安徽省高校自然科学基金重点项目(KJ2016A208)。
关键词
变化挖掘
最优对齐
成本函数
相似性度
高频片段
Change mining
Optimal alignment
Cost function
Similarity degree
High frequency segment
