计算机科学 ›› 2026, Vol. 53 ›› Issue (2): 207-215.doi: 10.11896/jsjkx.241200037
刘芙洁, 方贤文
LIU Fujie, FANG Xianwen
摘要： 在数字化转型浪潮中,业务流程的异常检测与修复对保障企业运营效率和决策质量至关重要,同时也对其检测与修复技术提出了更高的要求。传统的异常检测方法已无法满足当前业务流程实时监控和适应性调整的需要,而现有方法多侧重于静态分析,没有充分考虑业务环境的复杂性与多变性,难以适应流程动态变化的需求。基于此,创新性地提出了一种自适应异常处理方法(Adaptive Anomaly Handling Method,AAHM)。该方法通过动态参数调整和实时数据反馈,提高异常检测的准确性和修复的有效性。为验证该方法的有效性,实验采用了4组真实事件日志进行仿真。结果表明,该方法通过特征向量补全和行为修复策略,能够有效识别并对异常行为进行修复,恢复业务流程的正常执行。此外,通过对实验结果进行事后检验分析,进一步验证了所提方法的有效性和合理性。
中图分类号:
| [1]SARNO R,SINAGA F,SUNGKONO K R.Anomaly detection in business processes using process mining and fuzzy association rule learning[J].Journal of Big Data,2020,7(1):5. [2]VAN ZELST S J,SANI M F,OSTOVAR A,et al.Detection and removal of infrequent behavior from event streams of business processes[J].Information Systems,2020,90:101451. [3]KRAJSIC P,FRANCZYK B.Catch me if you can:online classification for near real-time anomaly detection in business process event streams[J].Procedia Computer Science,2022,207:235-244. [4]GUAN W,CAO J,GU Y,et al.GAMA:A multi-graph-based anomaly detection framework for business processes via graph neural networks[J].Information Systems,2024,124:102405. [5]NOLLE T,LUETTGEN S,SEELIGER A,et al.Binet:Multi-perspective business process anomaly classification[J].Information Systems,2022,103:101458. [6]KO J,COMUZZI M.Keeping our rivers clean:Information-theoretic online anomaly detection for streaming business process events[J].Information Systems,2022,104:101894. [7]BÖHMER K,RINDERLE-MA S.Multi-perspective anomaly detection in business process execution events[C]//On the Move to Meaningful Internet Systems:OTM 2016 Conferences.Springer,2016:80-98. [8]NOLLE T,LUETTGEN S,SEELIGER A,et al.Analyzing business process anomalies using autoencoders[J].Machine Lear-ning,2018,107:1875-1893. [9]KRAJSIC P,FRANCZYK B.Variational Autoencoder forAnomaly Detection in Event Data in Online Process Mining[C]//ICEIS.2021:567-574. [10]KRAJSIC P,FRANCZYK B.Semi-supervised anomaly detection in business process event data using self-attention based classification[J].Procedia Computer Science,2021,192:39-48. [11]NGUYEN H T C,LEE S,KIM J,et al.Autoencoders for improving quality of process event logs[J].Expert Systems with Applications,2019,131:132-147. [12]TAVARES G M,JUNIOR S B.Process miningencoding via meta-learning for an enhanced anomaly detection[C]//Proceedings of European Conference on Advances in Databases and Information Systems.Cham:Springer,2021:157-168. [13]BÖHMER K,RINDERLE-MA S.Mining association rules foranomaly detection indynamic process runtime behavior and explaining the root cause to users[J].Information Systems,2020,90:101438. [14]FANI SANI M,VAN ZELST S J,VAN DER AALST W M P.Repairing outlier behaviour in event logs[C]//Business Information Systems:21st International Conference,BIS 2018.Cham:Springer,2018:115-131. [15]FANI SANI M,VAN ZELST S J,VAN DER AALST W M P.Applying sequence mining for outlier detection in process mining[C]//On the Move to Meaningful Internet Systems.OTM 2018 Conferences.Cham:Springer,2018:98-116. [16]GUO H C,GUO Y H,YANG J,et al.Loglg:Weakly supervised log anomaly detection via log-event graph construction[C]//Proceedings of International Conference on Database Systems for Advanced Applications.Cham:Springer,2023:490-501. [17]MEHR A S M,DE CARVALHO R M,VAN DONGEN B.Explainable conformance checking:understanding patterns of anomalous behavior[J].Engineering Applications of Artificial Intelligence,2023,126:106827. [18]LEE S,LU X,REIJERS H A.The analysis of online eventstreams:Predicting the next activity for anomaly detection[C]//Proceedings of International Conference on Research Challenges in Information Science.Cham:Springer,2022:248-264. [19]ZAVATTERI M,BRESOLIN D,DE LEONI M.Repair of unsound data-aware process models[C]//Proceedings of International Conference on Business Process Management.Cham:Springer,2023:383-395. [20]CONFORTI R,LA ROSA M,TER HOFSTEDE A H M,et al.Automatic repair of same-timestamp errors in business process event logs[C]//Business Process Management:18th International Conference,BPM 2020.Cham:Springer,2020:327-345. [21]GUAN W,CAO J,GU Y,et al.AIMED:An automatic and incremental approach for business process model repair under concept drift[J].Information Systems,2023,119:102285. [22]FANG H,LIU W C G,WANG W S,et al.Discovery of process variants based on trace context tree[J].Connection Science,2023,35(1):2190499. [23]MASUYAMA N,AMAKO N,YAMADA Y,et al.Adaptiveresonance theory-based topological clustering with a divisive hierarchical structure capable of continual learning[J].IEEE Access,2022,10:68042-68056. [24]LEI S.A feature selection method based on information gain and genetic algorithm[C]//International Conference on Computer Science and Electronics Engineering.IEEE,2012:355-358. |
|
||
首页