面向业务过程的时间预测方法
|
摘要
为了在充满竞争的社会环境中生存,企业必须实现高效的工作流程.为此,时间作为业务流程中的重要因素,在近几年得到了越来越多的关注.准确的时间预测对提高企业服务效率、降低运行成本,预防违规活动发生等具有重要意义.时间预测根据应用的场景分为业务过程的剩余时间预测,业务过程中某一个活动执行时间预测以及业务过程的违规预测三种类型.本文综述了近年来有关时间预测的研究成果,总结了时间预测技术面临的挑战,并在此基础上给出了未来的研究方向.
In order to survive in a competitive social environment,companies must implement efficient process management. For this reason,time,as an important factor in business processes,has received more and more attentions in recent years. Accurate time prediction is of great significance to the improvement of the efficiency of business services,reduction of operating costs,and prevention of the occurrence of illegal activities. The time prediction problem can be divided into three types,i. e.,the prediction of the remaining time of the business process,the prediction of the execution time of an activity in the business process,and the violation prediction of the business process according to the application scenario. This paper reviews the recent research results on the topic of time prediction for business process,summarizes the challenges faced by this research,and points out some future research directions.
In order to survive in a competitive social environment,companies must implement efficient process management. For this reason,time,as an important factor in business processes,has received more and more attentions in recent years. Accurate time prediction is of great significance to the improvement of the efficiency of business services,reduction of operating costs,and prevention of the occurrence of illegal activities. The time prediction problem can be divided into three types,i. e.,the prediction of the remaining time of the business process,the prediction of the execution time of an activity in the business process,and the violation prediction of the business process according to the application scenario. This paper reviews the recent research results on the topic of time prediction for business process,summarizes the challenges faced by this research,and points out some future research directions.
引文
[1]Schellekens B.Cycle time prediction in staffware[D].Technisch Universiteit Eindhoven,2009.
[2]Vander Aalst W M P,van Dongen B F,Herbst J,et al.Workflow mining:a survey of issues and approaches[J].Data&Know ledge Engineering,2003,47(2):237-267.
[3]Wang Yan-bing,Peng Dun-lu.Frequent process pattern supported recommendation of cross-enterprise business processes[J].Journal of Chinese Computer Systems,2016,37(2):275-280.
[4]Verbeek H M W,Buijs J C A M,Dongen B F V,et al.XES,XE-Same,and ProM 6[M].Springer Berlin Heidelberg:Information Systems Evolution,2011.
[5]Scheer A W,Nüttgens M.ARIS architecture and reference models for business process management[C].Proceedings of Business Process Management,Models,and Empirical Studies,2000:376-389.
[6]Scheer A W.ARIS toolset:a software product is born[J].Speech Communication,1994,11(1):51-69.
[7]Burattin A.Process mining techniques in business environments[M].Springer International Publishing,2015.
[8]Meng Xiao-feng,Ci Xiang.Big data management:concepts,techniques and challenges[J].Journal of Computer Research and Development,2013,50(1):146-169.
[9]Aalst W M P V D,Schonenberg M H,Song M.Time prediction based on process mining[J].Information Systems,2011,36(2):450-475.
[10]Rogge-Solti A,Weske M.Prediction of business process durations using non-M arkovian stochastic petri nets[J].Information Systems,2015,54(C):1-14.
[11]Rogge-Solti A,Weske M.Prediction of remaining service execution time using stochastic petri nets with arbitrary firing delays[M].Springer Berlin Heidelberg:Service-Oriented Computing,2013.
[12]Bolt A,Sepulveda M.Process remaining time prediction using query catalogs[M].Springer International Publishing,2013.
[13]Polato M,Sperduti A,Burattin A,et al.Time and activity sequence prediction of business process instances[J].Computing,2016,45(10):1-27.
[14]Ceci M,Lanotte P F,Fumarola F,et al.Completion time and next activity prediction of processes using sequential pattern mining[M].Springer International Publishing,2014.
[15]Navarin N,Vincenzi B,Polato M,et al.LSTM networks for dataaw are remaining time prediction of business process instances[J].IEEE Symposium on Deep Learning,2017,1109(8):1-7.
[16]Graves A.Long short-term memory[M].Springer Berlin Heidelberg,2012.
[17]Dongen B F V,Crooy R A,Aalst W M P V D.Cycle time prediction:w hen w ill this case finally be finished?[C].Otm 2008 Confederated International Conferences,2008:319-336.
[18]Mitchell T M.Machine learning[M].China Machine Press,2003.
[19]Drucker H,Burges C J C,Kaufman L,et al.Support vector regression machines[J].Advances in Neural Information Processing Systems,1997,28(7):779-784.
[20]Pandey S,Nepal S,Chen S.A test-bed for the evaluation of business process prediction techniques[C].International Conference on Collaborative Computing:Netw orking,Applications and Worksharing,2012:382-391.
[21]Tax N,Verenich I,Rosa M L,et al.Predictive business process monitoring w ith LSTM neural netw orks[J].Advanced Information Systems Engineering,2017,10253(30):477-492.
[22]Verenich I,Nguyen H,La Rosa M,et al.White-box prediction of process performance indicators via flow analysis[C].International Conference on Softw are and System Processes(ICSSP),2017.
[23]Nazerfard E,Cook D J.Using bayesian networks for daily activity prediction[C].Proceedings of AAAI Conference on Plan,Activity,and Intent Recognition,2013:32-38.
[24]Minor B,Doppa J R,Cook D J.Data-driven activity prediction:algorithms,evaluation methodology,and applications[C].ACMSIGKDD International Conference on Know ledge Discovery and Data M ining,2015:805-814.
[25]Maleshkova M,Weller T.Activity duration prediction of workflows by using a data science approach:unveiling the advantage of semantics[J].SWIT@ISWC,2017,42(1):25-37.
[26]Chirkin A M,Kovalchuk S V.Towards better workflow execution time estimation[J].Ieri Procedia,2014,10(10):216-223.
[27]Wombacher A,Iacob M.Estimating the processing time of process instances in semi-structured processes-a case study[C].IEEE Ninth International Conference on Services Computing,2017:368-375.
[28]Zhi Li,Jian Cao,Qi Gu.Temporal-aware QoS-based service recommendation using tensor decomposition[J].International Journal of Web Service Research,2015,12(1):62-74.
[29]Evermann J,Rehse J R,Fettke P.A deep learning approach for predicting process behaviour at runtime[C].International Conference on Business Process M anagement,2016:327-338.
[30]Houston M B,Bettencourt L A,Wenger S.The relationship betw een w aiting in a service queue and evaluations of service quality:a field theory perspective[J].Psychology&M arketing,1998,15(8):735-753.
[31]Menasc D A.QoS issues in Web services[J].IEEE Internet Computing,2002,6(6):72-75.
[32]Folino F,Guarascio M,Pontieri L.Discovering context-aware models for predicting business process performances[C].Proceedings of Otm Conferences,2012:287-304.
[33]Pika A,Aalst W M P,Fidge C J,et al.Predicting deadline transgressions using event logs[J].Lecture Notes in Business Information Processing,2013,132(21):211-216.
[34]Conforti R,Fortino G,Rosa M L,et al.History-aware,real-time risk detection in business processes[M].Springer Berlin Heidelberg,2011.
[35]Leitner P,Wetzstein B,Rosenberg F,et al.Runtime prediction of service level agreement violations for composite services[J].Lecture Notes in Computer Science,2010,6275(12):176-186.
[36]Conforti R,Leoni M D,Rosa M L,et al.Supporting risk-informed decisions during business process execution[C].International Conference on Advanced Information Systems Engineering,Springer-Verlag,2013:116-132.
[37]Suriadi S,Ouyang C,Aalst W M P V D,et al.Root cause analysis with enriched process logs[M].Springer Berlin Heidelberg,2012.
[38]Song M,Günther C W,Aalst W M P V D.Trace clustering in process mining[M].Springer Berlin Heidelberg,2008.
[39]Folino F,Greco G,Guzzo A,et al.Editorial:mining usage scenarios in business processes:outlier-aware discovery and run-time prediction[J].Data&Knowledge Engineering,2011,70(12):1005-1029.
[40]Blockeel H,De R L.Top-down induction of first order logical decision trees[J].Artificial Intelligence,1998,101(1-2):285-297.
[41]Folino F,Guarascio M,Pontieri L.Context-aware predictions on business processes:an ensemble-based solution[M].Springer Berlin Heidelberg,2012.
[42]Kang B,Kim D,Kang S.Periodic performance prediction for realtime business process monitoring[J].Industrial M anagement&Data Systems,2012,112(1):4-23.
[43]Hompes B,Buijs J,van der Aalst W,et al.Discovering deviating cases and process variants using trace clustering[C].In:Proceedings of the27th Benelux Conference on Artificial Intelligence,2015.
[44]Ferreira D,Zacarias M.Approaching process mining with sequence clustering:experiments and findings[C].Proceedings of Business Process M anagement International Conference,2007:360-374.
[45]Wang Yan,Wang Feng-tong,Wang Jun-lu,et al.Missing data imputation approach based on generalized centroids clustering algorithm[J].Journal of Chinese Computer Systems,2017,38(9):2017-2021.
[46]Zhao Wei,He Pi-lian,Chen Xia,et al.Research on data preprocessing technology in Web log mining[J].Journal of Computer Applications,2003,23(5):62-64.
[47]Harrington P.Machine learning in action[M].Manning Publications Co,2012.
[48]Kohavi R.A study of cross-validation and bootstrap for accuracy estimation and model selection[C].Proceedings of International Joint Conference on Artificial Intelligenc,1995:1137-1143.
[49]Seni G,Elder J.Ensemble methods in data mining:improving accuracy through combining predictions[M].M organ and Claypool Publishers,2010.
[3]王艳冰,彭敦陆.频繁过程模式支持下的跨企业业务过程推荐[J].小型微型计算机系统,2016,37(2):275-280.
[8]孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,50(1):146-169.
[45]王妍,王凤桐,王俊陆,等.基于泛化中心聚类的不完备数据集填补方法[J].小型微型计算机系统,2017,38(9):2017-2021.
[46]赵伟,何丕廉,陈霞,等.Web日志挖掘中的数据预处理技术研究[J].计算机应用,2003,23(5):62-64.
[2]Vander Aalst W M P,van Dongen B F,Herbst J,et al.Workflow mining:a survey of issues and approaches[J].Data&Know ledge Engineering,2003,47(2):237-267.
[3]Wang Yan-bing,Peng Dun-lu.Frequent process pattern supported recommendation of cross-enterprise business processes[J].Journal of Chinese Computer Systems,2016,37(2):275-280.
[4]Verbeek H M W,Buijs J C A M,Dongen B F V,et al.XES,XE-Same,and ProM 6[M].Springer Berlin Heidelberg:Information Systems Evolution,2011.
[5]Scheer A W,Nüttgens M.ARIS architecture and reference models for business process management[C].Proceedings of Business Process Management,Models,and Empirical Studies,2000:376-389.
[6]Scheer A W.ARIS toolset:a software product is born[J].Speech Communication,1994,11(1):51-69.
[7]Burattin A.Process mining techniques in business environments[M].Springer International Publishing,2015.
[8]Meng Xiao-feng,Ci Xiang.Big data management:concepts,techniques and challenges[J].Journal of Computer Research and Development,2013,50(1):146-169.
[9]Aalst W M P V D,Schonenberg M H,Song M.Time prediction based on process mining[J].Information Systems,2011,36(2):450-475.
[10]Rogge-Solti A,Weske M.Prediction of business process durations using non-M arkovian stochastic petri nets[J].Information Systems,2015,54(C):1-14.
[11]Rogge-Solti A,Weske M.Prediction of remaining service execution time using stochastic petri nets with arbitrary firing delays[M].Springer Berlin Heidelberg:Service-Oriented Computing,2013.
[12]Bolt A,Sepulveda M.Process remaining time prediction using query catalogs[M].Springer International Publishing,2013.
[13]Polato M,Sperduti A,Burattin A,et al.Time and activity sequence prediction of business process instances[J].Computing,2016,45(10):1-27.
[14]Ceci M,Lanotte P F,Fumarola F,et al.Completion time and next activity prediction of processes using sequential pattern mining[M].Springer International Publishing,2014.
[15]Navarin N,Vincenzi B,Polato M,et al.LSTM networks for dataaw are remaining time prediction of business process instances[J].IEEE Symposium on Deep Learning,2017,1109(8):1-7.
[16]Graves A.Long short-term memory[M].Springer Berlin Heidelberg,2012.
[17]Dongen B F V,Crooy R A,Aalst W M P V D.Cycle time prediction:w hen w ill this case finally be finished?[C].Otm 2008 Confederated International Conferences,2008:319-336.
[18]Mitchell T M.Machine learning[M].China Machine Press,2003.
[19]Drucker H,Burges C J C,Kaufman L,et al.Support vector regression machines[J].Advances in Neural Information Processing Systems,1997,28(7):779-784.
[20]Pandey S,Nepal S,Chen S.A test-bed for the evaluation of business process prediction techniques[C].International Conference on Collaborative Computing:Netw orking,Applications and Worksharing,2012:382-391.
[21]Tax N,Verenich I,Rosa M L,et al.Predictive business process monitoring w ith LSTM neural netw orks[J].Advanced Information Systems Engineering,2017,10253(30):477-492.
[22]Verenich I,Nguyen H,La Rosa M,et al.White-box prediction of process performance indicators via flow analysis[C].International Conference on Softw are and System Processes(ICSSP),2017.
[23]Nazerfard E,Cook D J.Using bayesian networks for daily activity prediction[C].Proceedings of AAAI Conference on Plan,Activity,and Intent Recognition,2013:32-38.
[24]Minor B,Doppa J R,Cook D J.Data-driven activity prediction:algorithms,evaluation methodology,and applications[C].ACMSIGKDD International Conference on Know ledge Discovery and Data M ining,2015:805-814.
[25]Maleshkova M,Weller T.Activity duration prediction of workflows by using a data science approach:unveiling the advantage of semantics[J].SWIT@ISWC,2017,42(1):25-37.
[26]Chirkin A M,Kovalchuk S V.Towards better workflow execution time estimation[J].Ieri Procedia,2014,10(10):216-223.
[27]Wombacher A,Iacob M.Estimating the processing time of process instances in semi-structured processes-a case study[C].IEEE Ninth International Conference on Services Computing,2017:368-375.
[28]Zhi Li,Jian Cao,Qi Gu.Temporal-aware QoS-based service recommendation using tensor decomposition[J].International Journal of Web Service Research,2015,12(1):62-74.
[29]Evermann J,Rehse J R,Fettke P.A deep learning approach for predicting process behaviour at runtime[C].International Conference on Business Process M anagement,2016:327-338.
[30]Houston M B,Bettencourt L A,Wenger S.The relationship betw een w aiting in a service queue and evaluations of service quality:a field theory perspective[J].Psychology&M arketing,1998,15(8):735-753.
[31]Menasc D A.QoS issues in Web services[J].IEEE Internet Computing,2002,6(6):72-75.
[32]Folino F,Guarascio M,Pontieri L.Discovering context-aware models for predicting business process performances[C].Proceedings of Otm Conferences,2012:287-304.
[33]Pika A,Aalst W M P,Fidge C J,et al.Predicting deadline transgressions using event logs[J].Lecture Notes in Business Information Processing,2013,132(21):211-216.
[34]Conforti R,Fortino G,Rosa M L,et al.History-aware,real-time risk detection in business processes[M].Springer Berlin Heidelberg,2011.
[35]Leitner P,Wetzstein B,Rosenberg F,et al.Runtime prediction of service level agreement violations for composite services[J].Lecture Notes in Computer Science,2010,6275(12):176-186.
[36]Conforti R,Leoni M D,Rosa M L,et al.Supporting risk-informed decisions during business process execution[C].International Conference on Advanced Information Systems Engineering,Springer-Verlag,2013:116-132.
[37]Suriadi S,Ouyang C,Aalst W M P V D,et al.Root cause analysis with enriched process logs[M].Springer Berlin Heidelberg,2012.
[38]Song M,Günther C W,Aalst W M P V D.Trace clustering in process mining[M].Springer Berlin Heidelberg,2008.
[39]Folino F,Greco G,Guzzo A,et al.Editorial:mining usage scenarios in business processes:outlier-aware discovery and run-time prediction[J].Data&Knowledge Engineering,2011,70(12):1005-1029.
[40]Blockeel H,De R L.Top-down induction of first order logical decision trees[J].Artificial Intelligence,1998,101(1-2):285-297.
[41]Folino F,Guarascio M,Pontieri L.Context-aware predictions on business processes:an ensemble-based solution[M].Springer Berlin Heidelberg,2012.
[42]Kang B,Kim D,Kang S.Periodic performance prediction for realtime business process monitoring[J].Industrial M anagement&Data Systems,2012,112(1):4-23.
[43]Hompes B,Buijs J,van der Aalst W,et al.Discovering deviating cases and process variants using trace clustering[C].In:Proceedings of the27th Benelux Conference on Artificial Intelligence,2015.
[44]Ferreira D,Zacarias M.Approaching process mining with sequence clustering:experiments and findings[C].Proceedings of Business Process M anagement International Conference,2007:360-374.
[45]Wang Yan,Wang Feng-tong,Wang Jun-lu,et al.Missing data imputation approach based on generalized centroids clustering algorithm[J].Journal of Chinese Computer Systems,2017,38(9):2017-2021.
[46]Zhao Wei,He Pi-lian,Chen Xia,et al.Research on data preprocessing technology in Web log mining[J].Journal of Computer Applications,2003,23(5):62-64.
[47]Harrington P.Machine learning in action[M].Manning Publications Co,2012.
[48]Kohavi R.A study of cross-validation and bootstrap for accuracy estimation and model selection[C].Proceedings of International Joint Conference on Artificial Intelligenc,1995:1137-1143.
[49]Seni G,Elder J.Ensemble methods in data mining:improving accuracy through combining predictions[M].M organ and Claypool Publishers,2010.
[3]王艳冰,彭敦陆.频繁过程模式支持下的跨企业业务过程推荐[J].小型微型计算机系统,2016,37(2):275-280.
[8]孟小峰,慈祥.大数据管理:概念、技术与挑战[J].计算机研究与发展,2013,50(1):146-169.
[45]王妍,王凤桐,王俊陆,等.基于泛化中心聚类的不完备数据集填补方法[J].小型微型计算机系统,2017,38(9):2017-2021.
[46]赵伟,何丕廉,陈霞,等.Web日志挖掘中的数据预处理技术研究[J].计算机应用,2003,23(5):62-64.