计算机集成制造系统 ›› 2018, Vol. 24 ›› Issue (第3): 591-601.DOI: 10.13196/j.cims.2018.03.006

• 当期目次 • 上一篇    下一篇

一种挖掘二度循环的扩展Alpha算法

林雷蕾1,3,周华2,代飞2,3+,闻立杰4,莫启1,3   

  1. 1.云南大学软件学院
    2.西南林业大学大数据与智能工程学院
    3.云南大学云南省软件工程重点实验室
    4.清华大学软件学院
  • 出版日期:2018-03-31 发布日期:2018-03-31
  • 基金资助:
    国家自然科学基金资助项目(61462095,61702442,61662085);云南省科技厅后备人才培养计划资助项目(C6143002);云南省高新技术产业发展资助项目(20121956);云南省教育厅研究生资助项目(2017YJS107,2017ZZX227);云南大学研究生创新资助项目(YDY17095)。

Extending α-algorithm to mine simplest 2-Loops

  • Online:2018-03-31 Published:2018-03-31
  • Supported by:
    Project supported by the National Natural Science Foundation,China(No.61462095,61702442,61662085),the Talent Fund of Yunnan Provincial Science and Technology Department,China(No.C6143002),the Yunnan High-Tech.Industry Development Program,China(No.20121956),the Yunnan Education Foundation for Graduate,China(No.2017YJS107,2017ZZX227),and the Graduate Innovation Program of Yunnan University,China(No.YDY17095).

摘要: 为解决现有挖掘算法无法从不具有显式行为特征“aba”的局部完备性的日志文件中挖掘最简2度循环的问题,对经典的alpha算法进行了扩展,提出了αL算法,用于从具有行为特征或不具有行为特征的局部完备性日志中挖掘出最简2度循环。给出了最简2度循环的形式化定义。从全局角度根据不同结构具有不同行为轨迹来区分最简2度循环与并发结构。通过紧邻关系的强弱,来有效识别并发分支上同类型的最简2度循环结构。通过大量模型实验表明了所提算法的有效性,并将算法集成在开源框架ProM中。

关键词: 业务流程管理, 流程挖掘, 紧邻度, 日志完备性, Petri网

Abstract: To solve the problem that the existing mining algorithm could not mine simplest 2-loops from local complete log traces without a fixed behavior pattern like “aba”,an αL -algorithm by extending classic α-algorithm was presented.The definition of simplest 2-loop was given by petri nets.The 2-loop and concurrency structure were distinguished according to the principle that different structures had different behaviors in event logs.After that,the same type of 2-loops structure was accurately divided by following degrees of tasks.The real data was used for extensive experiments sets to show the effectiveness and correctness of proposed method.In addition,the αL -algorithm was implemented in ProM tool.

Key words: business process management, process mining, following degrees, log completeness, Petri nets

中图分类号: