范濤 方賢文



摘 要:提出一種基于Petri網和因果關系矩陣的事件日志過程挖掘方法.基于Petri網和因果關系矩陣的事件日志過程挖掘算法,利用因果關系矩陣進行過程挖掘,其過程模型可以更好地匹配系統產生的事件日志集.
關鍵詞:Petri網;因果關系矩陣;事件日志;過程挖掘
[中圖分類號]TP391.9 ? [文獻標志碼]A
Abstract:An event log process mining method based on Petri net and causality matrix is proposed.The process mining algorithm based on the idea of mutual transformation between Petri nets and causal relationship matrix uses the causal relationship matrix for process mining,and the resulting process model can better match the event log set generated by the system.
Key words:Petri net;causality matrix;event log;process mining
隨著信息時代的到來,過程挖掘[1]技術得到了飛速發展,取得了重要成果.Alast等人提出的α算法[2]是最早的過程挖掘算法,它不僅被廣泛使用,而且對后來的算法有著廣泛而又深遠的影響.清華大學聞立杰團隊利用改進的α算法——α*算法[3]——從事件日志中挖掘出了不可見任務[4],使其具備了挖掘不可見任務即隱變遷的能力.筆者針對過程挖掘中由于模型和事件日志的復雜性,很難將此過程數字化表示并與計算機相結合提高工作效率這一問題,提出了一種基于Petri網和因果關系矩陣的事件日志過程挖掘方法.
1 基本概念
3 總結
本文提出一種基于Petri網和因果關系矩陣的事件日志過程挖掘方法,利用因果關系矩陣進行過程挖掘,得到的過程模型可以更好地匹配系統產生的事件日志集.計算機直接處理過程模型很棘手,特別是處理復雜的過程模型對計算機的相關性能有很高的要求,將過程模型轉化成因果關系矩陣可以大大減少計算機的工作量,只需要能夠處理簡單數字矩陣的計算機就可以完成此項工作.Petri網圖形和因果關系矩陣的相互轉化對于促進業務流程的數字化發展也有很大的幫助.在未來的工作中,還要對此方法的代碼實現做進一步研究,爭取早日上傳此系統框架并應用于實際.
參考文獻
[1]Cook J E,Wolf A L.Automating process discovery through event-data analysis[J].Software Engineering,1995:73-82.
[2]Agrawal R,Gunopulos D,Leyman F.Mining process models from workflow logs[M].Springer Berlin Heidelberg,1998.
[3]Greco G,Guzzo A,Pontieri L.Mining hierarchies of models:From abstract views to concrete specifications[M].Business Process Management Springer Berlin Heidelberg,2005:32-47.
[4]Herbst J,Karagiannis D.Workflow mining with InWoLvE[J].Computers in Industry,2004,53(3):245-264.
[5]羅海濱,范玉順,吳澄.工作流技術綜述[J].軟件學報,2000,11(7):899-907.
[6]Wang J,Jin T,Wong R K,et al.Querying business process model repositories:A survey of current approaches and issues[J].World wide web,2014,17(3):427-454.
[7]Mashinchi M H,Orgun M A,et al.A tabu-harmony search-based approach to fuzzy linear regression[J].Fuzzy Systems,IEEE Transactions on,2011,19(3):432-448.
[8]Meeran S,S.Morshed M.A hybird genetic tabu search algorithm for solving job shop scheduling problems:a case study[J].Joural of Intelligent Manufacturing,2012,23(4):1063-1078.
[9]Li J,Pan Y.A hybrid discrete particle swarm optimization algorithm for solving fuzzy job shop scheduling problem[J].The International Journal of Advanced Manufacturing Technology,2013,66(1-4):583-596.
[10]陳志剛,文一憑,康國勝.成批處理工作流動態分組調度優化方法[J].計算機集成制造系統,2012,18(8):1693
編輯:琳莉