基于流程切的过程模型挖掘方法
|
摘要
在业务流程挖掘过程中,过程挖掘的目的是从事件日志中挖掘出满足人们需要的模型,以此来改善和优化过程模型。以往的研究都是从频繁日志中挖掘模型,将低频日志直接删除,该类方法使得挖掘的模型不完整,且在行为上会引发死锁或其他异常情况。文中提出基于流程切的过程模型挖掘方法,该方法从事件日志中挖掘过程模型,对事件日志采用流程切的形式进行分割,不仅考虑到频繁行为,还考虑了低频模式下的行为;尤其针对异常的环状结构会引起流程图的边缘结构发生异常的问题,流程切可以很好地进行处理。利用这种方法得到的模型比较全面完善,能够提高有效性和精确度。利用评价指标对构建的模型进行优化,从而得出最优模型。最后,通过具体事例验证了所提方法的有效性。
The purpose of process mining is to mine the model that meets people's needs from the event log in the mi-ning process of business process,so as to improve and optimize the process model.In previous studies,models were mined from frequent log,and low-frequency log was deleted directly,which makes the mined model incomplete and may cause a deadlock or other abnormalities.This paper proposed a process model mining method based on process cutting.The method mines the process model from the event log and segments the event log in the form of a process cutting,not only taking into account the frequent behaviors,but also the behaviors in the low-frequency mode.In particular,aiming at the proplem that the abnormal circular structure will cause abnormality for edge structure of the flow chart,the process cutting can handle it well.The model obtained by proposed method is more comprehensive and perfect,and the validity and accuracy of the model can be improved.The evaluation index was used to optimize the constructed model and the optimal model was obtained.Finally,the effectiveness of the method was verified by concrete examples.
The purpose of process mining is to mine the model that meets people's needs from the event log in the mi-ning process of business process,so as to improve and optimize the process model.In previous studies,models were mined from frequent log,and low-frequency log was deleted directly,which makes the mined model incomplete and may cause a deadlock or other abnormalities.This paper proposed a process model mining method based on process cutting.The method mines the process model from the event log and segments the event log in the form of a process cutting,not only taking into account the frequent behaviors,but also the behaviors in the low-frequency mode.In particular,aiming at the proplem that the abnormal circular structure will cause abnormality for edge structure of the flow chart,the process cutting can handle it well.The model obtained by proposed method is more comprehensive and perfect,and the validity and accuracy of the model can be improved.The evaluation index was used to optimize the constructed model and the optimal model was obtained.Finally,the effectiveness of the method was verified by concrete examples.
引文
[1] VAN DER AALST W,WEIJTERS T,MARUSTER L.Workflow mining:discovering process models from event logs[J].IEEE Transactions on Knowledge & Data Engineering,2004,16(9):1128-1142.
[2] VAN DER AALST W M P.Process Mining:Discovery,Con- formance and Enhancement of Business Processes[M].Springer Publishing Company,Incorporated,2011.
[3] VAN DER AALST W M P,VAN DONGEN B F,HERBST J,et al.Workflow mining:a survey of issues and approaches[J].Data & Knowledge Engineering,2003,47(2):237-267.
[4] VAN DER AALST W M P,WEIJTERS A.Process mining:a research agenda[J].Computers in Industry,2004,53(3):231-244.
[5] CONFORTI R,ROSA M L,HOFSTEDE A H M T.Filtering Out Infrequent Behavior from Business Process Event Logs[J].IEEE Transactions on Knowledge & Data Engineering,2017,29(2):300-314.
[6] EICHST?DT S,LINK A,HARRIS P,et al.Efficient implementation of a Monte Carlo method for uncertainty evaluation in dynamic measurements[J].Metrologia,2012,49(3):401.
[7] POURMASOUMI A,KAHANI M,BAGHERI E.Mining variable fragments from process event logs[J].Information Systems Frontiers,2017,19(6):1423-1443.
[8] WEN L,VAN DER AALST W M P,WANG J,et al.Mining process models with non-free-choice constructs[J].Data Mining and Knowledge Discovery,2007,15(2):145-180.
[9] BUSI N,PINNA G,VAN DER AALST W.An Iterative Algorithm for Applying the Theory of Regions in Process Mining[R].Department of Technology Management,Eindhoven University of Technology,2007:16-38.
[10] YZQUIERDO-HERRERA R,SILVERIO-CASTRO R,LAZO- CORTéS M.Sub-process discovery:opportunities for process diagnotics[M]∥Enterprise Information Systems of the Future.Berlin Heidelberg:Springer,2013:48-57.
[11] BOUSHABA S,KABBAJ M I,BAKKOURY Z.Process disco- very:Automated approach for block discovery[C]//2014 International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE).IEEE,2014:1-8.
[12] CHAPELA-CAMPA D,MUCIENTES M,LAMA M.Discovering Infrequent Behavioral Patterns in Process Models[C]//International Conference on Business Process Management.Springer,Cham,2017:324-340.
[13] 吴哲辉.Petri网理论[M].北京:机械工业出版社,2006:6-22.
[14] WEIDLICH M,POLYVYANYY A,DESAI N,et al.Process Compliance Measurement Based On Behavioral Profiles [J].Advanced Information Systems Engineering,2010,6051:499-514.
[15] KUNZE M,WEIDLICH M,WESKEM.Querying process mo- dels by behavior inclusion[J].Software & Systems Modeling,2015,14(3):1105-1125.
[16] WEIDLICH M,MENDLING J,WESKE M.Efficient Consistency Measurement Based on Behavioural Profiles of Process Mo-dels[J].IEEE Transactions on Software Engineering,2011,37(3):410-429.
[2] VAN DER AALST W M P.Process Mining:Discovery,Con- formance and Enhancement of Business Processes[M].Springer Publishing Company,Incorporated,2011.
[3] VAN DER AALST W M P,VAN DONGEN B F,HERBST J,et al.Workflow mining:a survey of issues and approaches[J].Data & Knowledge Engineering,2003,47(2):237-267.
[4] VAN DER AALST W M P,WEIJTERS A.Process mining:a research agenda[J].Computers in Industry,2004,53(3):231-244.
[5] CONFORTI R,ROSA M L,HOFSTEDE A H M T.Filtering Out Infrequent Behavior from Business Process Event Logs[J].IEEE Transactions on Knowledge & Data Engineering,2017,29(2):300-314.
[6] EICHST?DT S,LINK A,HARRIS P,et al.Efficient implementation of a Monte Carlo method for uncertainty evaluation in dynamic measurements[J].Metrologia,2012,49(3):401.
[7] POURMASOUMI A,KAHANI M,BAGHERI E.Mining variable fragments from process event logs[J].Information Systems Frontiers,2017,19(6):1423-1443.
[8] WEN L,VAN DER AALST W M P,WANG J,et al.Mining process models with non-free-choice constructs[J].Data Mining and Knowledge Discovery,2007,15(2):145-180.
[9] BUSI N,PINNA G,VAN DER AALST W.An Iterative Algorithm for Applying the Theory of Regions in Process Mining[R].Department of Technology Management,Eindhoven University of Technology,2007:16-38.
[10] YZQUIERDO-HERRERA R,SILVERIO-CASTRO R,LAZO- CORTéS M.Sub-process discovery:opportunities for process diagnotics[M]∥Enterprise Information Systems of the Future.Berlin Heidelberg:Springer,2013:48-57.
[11] BOUSHABA S,KABBAJ M I,BAKKOURY Z.Process disco- very:Automated approach for block discovery[C]//2014 International Conference on Evaluation of Novel Approaches to Software Engineering (ENASE).IEEE,2014:1-8.
[12] CHAPELA-CAMPA D,MUCIENTES M,LAMA M.Discovering Infrequent Behavioral Patterns in Process Models[C]//International Conference on Business Process Management.Springer,Cham,2017:324-340.
[13] 吴哲辉.Petri网理论[M].北京:机械工业出版社,2006:6-22.
[14] WEIDLICH M,POLYVYANYY A,DESAI N,et al.Process Compliance Measurement Based On Behavioral Profiles [J].Advanced Information Systems Engineering,2010,6051:499-514.
[15] KUNZE M,WEIDLICH M,WESKEM.Querying process mo- dels by behavior inclusion[J].Software & Systems Modeling,2015,14(3):1105-1125.
[16] WEIDLICH M,MENDLING J,WESKE M.Efficient Consistency Measurement Based on Behavioural Profiles of Process Mo-dels[J].IEEE Transactions on Software Engineering,2011,37(3):410-429.