Process next event prediction method based on event log sampling

被引：0

作者：

Dong, Lele ^{[1
]}

Liu, Cong ^{[1
,2
]}

Zhang, Shuaipeng ^{[1
]}

Ni, Weijian ^{[2
]}

Ren, Chongguang ^{[1
]}

Zeng, Qingtian ^{[2
]}

机构：

[1] School of Computer Science and Technology, Shandong University of Technology, Zibo

[2] College of Computer Science and Engineering, Shandong University of Science and Technology, Qingdao

来源：

Jisuanji Jicheng Zhizao Xitong/Computer Integrated Manufacturing Systems, CIMS | 2024年 / 30卷 / 10期

基金：

中国国家自然科学基金;

关键词：

business process; deep learning; event log sampling; long short term memory network; prediction of next event;

D O I：

10.13196/j.cims.2023.0086

中图分类号：

学科分类号：

摘要：

The next event prediction task is one of the research focuses of predictive process monitoring, and the ex-isting deep learning-based prediction methods suffer from long training time, large amount of parameters and high hardware requirements to meet the dynamic nature of business processes. To address these problems, a Sampling-based Next Event Prediction (SNEP) method based on log sampling was proposed. Specifically, the importance of traces was measured by calculating event importance and direct-following activity relationship importance, and some important traces were extracted to represent the original event log. The prefixes of trace were recoded using the One-hot coding approach and a three-layer Long Short Term Memory(LSTM) network prediction model applicable to the next event prediction task was designed. Experiments were conducted in six real event logs to investigate the effec-tiveness of the proposed method and the effect of different sampling rates on the prediction results of the model. The results showed that the pre-sampled next event prediction method had improved prediction accuracy and efficiency in each event log, which could help practitioners to achieve next event prediction tasks efficiently. © 2024 CIMS. All rights reserved.

引用

页码：3621 / 3632

页数：11

共 31 条

[1] AALST W V D., Processmining: Data science in action, pp. 3-23, (2016)
[2] POURMASOUMI A, KAHANI M, BAGHERI E., The evolutionary composition ofdesirable execution traces from event logs, Future Generation Computer Systems, 98, pp. 78-103, (2019)
[3] DUMAS M, LA ROSA M, MENDLING J, Et al., Introduction to Business proeess management [_ M J//Fundamentals of Business Process Management, pp. 1-33, (2018)
[4] VAN DER AALST W M P, ROSEMANN M, DUMAS M., Deadline-based escalationin process-aware information systems, Decision Support Systems, 43, 2, pp. 492-511, (2007)
[5] EDER J, PICHLER H, VIELGUT S., A technique for the predietion of deadline-violations in inter-organizational Business processes, Proceedings of the Conference on Databases and Information Systems, pp. 57-71, (2007)
[6] JALAYER A, KAHANI M, BEHESHTI A, Et al., Attention mechanism in predictive business process monitoring, Proceeding.s of the 24th IEEE International Enterprise Distrib-uted Object Computing Conference, pp. 181-186, (2020)
[7] MARQUEZ-CHAMORRO AE, RESINAS M, RUIZ-CORTES A., Predictive monitoring of business processes
[8] A survey, IEEE Transactions on Services Computing, 11, 6, pp. 962-977, (2017)
[9] MAGGIEM, DI FRANCESCOMARIN, DUMAS M, Et al., Predictive monitoring of business processes, Proceedings of International Conference on Advanced Information Systems Engineering, pp. 457-472, (2014)
[10] BECKER J, BREUKER D, DELFMANN P, Et al., Designing and implementing aframework for event-based predictive mod-elling of business processes, Proceedings of the 6th International Workshop on Enterprise Modelling and Information-Systems Architectures, pp. 71-84, (2014)

← 1 2 3 4 →