ISSN 1000-1239 CN 11-1777/TP

计算机研究与发展 ›› 2018, Vol. 55 ›› Issue (3): 585-601.doi: 10.7544/issn1000-1239.2018.20160838

• 人工智能 • 上一篇    下一篇

基于引发序列的流程模型修正

王路,杜玉越,祁宏达   

  1. (山东科技大学计算机科学与工程学院 山东青岛 266590) (wanglu253@126.com)
  • 出版日期: 2018-03-01
  • 基金资助: 
    国家自然科学基金项目(61170078,61472228);山东省泰山学者建设工程专项基金项目;山东省自然科学基金项目(ZR2014FM009);山东科技大学科技创新项目(SDKDYC170222);山东省重点研发计划项目(2016GGX101031)

Process Model Repair Based on Firing Sequences

Wang Lu, Du Yuyue, Qi Hongda   

  1. (College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao, Shandong 266590)
  • Online: 2018-03-01

摘要: 随着信息系统在业务流程中的广泛应用,对事件日志与业务流程的需求也随之增加.由于事件日志的爆炸式增长,有些事件日志不能被流程模型正确地重演.通过合规性检查可以检测与诊断模型与日志之间存在的差异.但是,合规性检查技术不能对流程模型做出正确的修正.基于事件日志中的引发序列,从移除活动、增加活动及改变模型子流程3个方面解决了流程模型的修正问题.在进行模型修正时,需要确定移除的活动在模型中所在的结构、增加的活动与相邻活动的关系以及需要改变的子流程.流程模型修正的目的在于使修正的流程模型可以重演(大多数)的事件日志,并且使得到的修正模型尽可能与原模型相似.通过仿真模拟提出的修正方法,实验验证了该方法的正确性与实用性.

关键词: 流程挖掘, 合规性检查, 引发序列, 模型修正, 重演

Abstract: When business processes are mostly supported by information systems, the availability of event logs generated from these systems and the requirements of appropriate process models are increasing. However, some events cannot be correctly identified because of the explosion of the amount of event logs. Conformance checking techniques can be used to detect and diagnose the differences between observed and modeled behavior, but they cannot repair the actual model. The information from conformance checking can be used for model repair. By means of the firing sequences of event logs, process models can be repaired from three aspects: removing behavior, adding behavior and changing behavior. The structure with deleted activity in process model, the relationship between additional activities and adjoin activities, and the nonconformance sub-process in process model should be identified when the process model need repairing. It is obtained that the repaired model can replay (most of) event logs based on the proposed techniques, and it is as similar to the original model as possible. The methods in this paper are simulated manually. A real-world process model of hospitalization in a hospital and the corresponding event logs are employed to evaluate the proposed approaches. The correctness and effectiveness of the proposed methods are illustrated through experiments.

Key words: process mining, conformance checking, firing sequence, model repair, replay

中图分类号: