1. NCCU Academic Hub
  2. Publications
  3. College of Informatics
  4. Theses
  5. Item

Publications-Theses

Article View/Open

Publication Export

Google ScholarTM

NCCU Library

Citation Infomation

Related Publications in TAIR

題名 應用深度學習於流程模型一致性檢驗之研究
A Deep Learning Approach for Conformance Checking of Process Models
作者 林秉謙
LIN, PING-CHIEN
貢獻者 沈錳坤
Shan, Man-Kwan
林秉謙
LIN, PING-CHIEN
關鍵詞 流程探勘
一致性檢驗
深度學習
Process Mining
Conformance Checking
Deep Learning
日期 2025
上傳時間 1-Sep-2025 16:18:07 (UTC+8)
摘要 流程探勘結合資料科學與流程管理，透過流程發掘、一致性檢驗與優化分析，協助組織探索與改善流程。其中，一致性檢驗的目標在於比較模型與事件紀錄間的相符程度，以診斷流程偏差。一致性檢驗可應用在資訊系統與企業實際流程之間的對齊、稽核組織的運作與執行是否遵循政府或企業規範的流程，也可應用在流程的優化。然而，現有一致性檢驗方法多為離線處理，對大型事件紀錄分析耗時甚鉅。為解決此問題，本研究提出以深度學習取代一般一致性檢驗的模型比對的新方法，由事件紀錄訓練分類模型，辨識合法與不合法的流程案例。本論文研究重點包括：如何產生合法與不合法軌跡、深度學習模型的檢驗效率、模型分類的效果，以及模型訓練所需案例數量。實驗顯示本研究提出的方法於一致性檢驗的可行性，為大型流程資料的快速分析提供新方向。
Process Mining, which integrates data science and process management, supports this objective through three main functionalities: process discovery, conformance checking, and enhancement. Among these, conformance checking compares observed event logs with reference process models to detect deviations, supporting business alignment, auditing, compliance, and process improvement. However, existing methods are mostly offline and become computationally expensive when applied to large-scale event logs, limiting their applicability in practice. To address this challenge, this study explores a deep learning-based alternative for conformance checking. Instead of relying on predefined process models, the proposed approach trains classification models directly on event logs to distinguish between legal and illegal traces. The research focuses on four key issues: how to generate legal and illegal traces, whether deep learning can improve efficiency compared to traditional methods, how effectively models can classify traces, and the case volume required for effective training. Experimental results demonstrate the feasibility of applying deep learning to accelerate conformance checking, providing a promising direction for large-scale process data analysis.
參考文獻 [1] W. M. P., van der Aalst, Process Mining: Data Science in Action, 2nd Ed., Springer, 2016. [2] J., Carmona, B., van Dongen, & M., Weidlich, Conformance Checking: Foundations, Milestones and Challenges, Process Mining Handbook, pp. 155–190, 2022. [3] A., Rozinat, & W. M. P., van der Aalst, Conformance Checking of Processes Based on Monitoring Real Behavior, Information Systems, 33(1), pp. 64–95, 2008. [4] A., Adriansyah, J., Munoz-Gama, J., Carmona, B. F., van Dongen, & W. M. P., van der Aalst, Alignment Based Precision Checking, Business Process Management Workshops, pp. 137–149, 2013. [5] A., Adriansyah, N., Sidorova, & B. F., van Dongen, Cost-based Fitness in Conformance Checking, 2011 Eleventh International Conference on Application of Concurrency to System Design, pp. 57–66, 2011. [6] M., Weidlich, A., Polyvyanyy, N., Desai, J., Mendling, & M., Weske, Process Compliance Analysis Based on Behavioural Profiles. Information Systems, 36(7), pp. 1009–1025, 2011. [7] A., Burattin, S. J., van Zelst, A., Armas-Cervantes, B. F., van Dongen, & J., Carmona, Online Conformance Checking Using Behavioural Patterns, Business Process Management, pp. 250–267, 2018. [8] M., Camargo, M., Dumas, & O, González-Rojas., Learning Accurate LSTM Models of Business Processes, Business Process Management, pp. 286–302, 2019 [9] M., Pourbafrani, S., Vasudevan, F., Zafar, Y., Xingran, R., Singh, & W. M. P., van der Aalst, A Python Extension to Simulate Petri Nets in Process Mining, arXiv preprint arXiv:2102.08774, 2021. [10] J., Peeperkorn, S., vanden Broucke, & J., De Weerdt, Supervised Conformance Checking Using Recurrent Neural Network Classifiers, Process Mining Workshops, pp. 175–187, 2021. [11] J., Wang, D., Yu, X., Ma, C., Liu, V., Chang, & X., Shen, Online Predicting Conformance of Business Process with Recurrent Neural Networks, IoTBDS 2020 - Proceedings of The 5th International Conference on Internet of Things, Big Data and Security, pp. 88–100, 2020. [12] J., Lahann, P., Pfeiffer, & P., Fettke, LSTM-Based Anomaly Detection of Process Instances: Benchmark and Tweaks, Process Mining Workshops, pp. 229–241, 2023. [13] W. M. P., van der Aalst, Process Mining: Discovery, Conformance and Enhancement of Business Processes, Springer, 2011. [14] W. M. P., van der Aalst, A. H. M., ter Hofstede, B., Kiepuszewski, & A. P., Barros, Workflow Patterns, Distributed and Parallel Databases, 14(1), pp. 5–51, 2003. [15] W. M. P., van der Aalst, The Application of Petri Nets to Workflow Management, Journal of Circuits, Systems and Computers, 8(1), pp. 21–66, 1998. [16] N., Lohmann, E., Verbeek, & R., Dijkman, Petri Net Transformations for Business Processes – A Survey, Transactions on Petri Nets and Other Models of Concurrency II: Special Issue on Concurrency in Process-Aware Information Systems, pp. 49-63, 2009. [17] S. J. J., Leemans, D., Fahland, & W. M. P., van der Aalst, Discovering Block-Structured Process Models from Event Logs – A Constructive Approach, Application and Theory of Petri Nets and Concurrency, pp. 311–329, 2013. [18] W. M. P., van der Aalst, Process Discovery from Event Data: Relating Models and Logs Through Abstractions, WIREs Data Mining and Knowledge Discovery, 8(3), 2018. [19] K., Cho, B., van Merrienboer, Ç., Gülçehre, D., Bahdanau, F., Bougares, H., Schwenk, & Y., Bengio, Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation, arXiv preprint arXiv:1406.1078, 2014. [20] M., Abadi, P., Barham, J., Chen, Z., Chen, A., Davis, J., Dean, M., Devin, S., Ghemawat, G., Irving, M., Isard, M., Kudlur, J., Levenberg, R., Monga, S., Moore, D. G., Murray, B., Steiner, P., Tucker, V., Vasudevan, P., Warden, M., Wicke, Y, Yu, X., Zheng, TensorFlow: A System for Large-Scale Machine Learning, arXiv preprint arXiv:1605.08695, 2016. [21] A., Berti, S., van Zelst, & D., Schuster, PM4Py: A Process Mining Library for Python, Software Impacts, 17, 2023.
描述 碩士
國立政治大學
資訊科學系碩士在職專班
110971017
資料來源 http://thesis.lib.nccu.edu.tw/record/#G0110971017
資料類型 thesis
dc.contributor.advisor 沈錳坤zh_TW
dc.contributor.advisor Shan, Man-Kwanen_US
dc.contributor.author (Authors) 林秉謙zh_TW
dc.contributor.author (Authors) LIN, PING-CHIENen_US
dc.creator (作者) 林秉謙zh_TW
dc.creator (作者) LIN, PING-CHIENen_US
dc.date (日期) 2025en_US
dc.date.accessioned 1-Sep-2025 16:18:07 (UTC+8)-
dc.date.available 1-Sep-2025 16:18:07 (UTC+8)-
dc.date.issued (上傳時間) 1-Sep-2025 16:18:07 (UTC+8)-
dc.identifier (Other Identifiers) G0110971017en_US
dc.identifier.uri (URI) https://nccur.lib.nccu.edu.tw/handle/140.119/159291-
dc.description (描述) 碩士zh_TW
dc.description (描述) 國立政治大學zh_TW
dc.description (描述) 資訊科學系碩士在職專班zh_TW
dc.description (描述) 110971017zh_TW
dc.description.abstract (摘要) 流程探勘結合資料科學與流程管理，透過流程發掘、一致性檢驗與優化分析，協助組織探索與改善流程。其中，一致性檢驗的目標在於比較模型與事件紀錄間的相符程度，以診斷流程偏差。一致性檢驗可應用在資訊系統與企業實際流程之間的對齊、稽核組織的運作與執行是否遵循政府或企業規範的流程，也可應用在流程的優化。然而，現有一致性檢驗方法多為離線處理，對大型事件紀錄分析耗時甚鉅。為解決此問題，本研究提出以深度學習取代一般一致性檢驗的模型比對的新方法，由事件紀錄訓練分類模型，辨識合法與不合法的流程案例。本論文研究重點包括：如何產生合法與不合法軌跡、深度學習模型的檢驗效率、模型分類的效果，以及模型訓練所需案例數量。實驗顯示本研究提出的方法於一致性檢驗的可行性，為大型流程資料的快速分析提供新方向。zh_TW
dc.description.abstract (摘要) Process Mining, which integrates data science and process management, supports this objective through three main functionalities: process discovery, conformance checking, and enhancement. Among these, conformance checking compares observed event logs with reference process models to detect deviations, supporting business alignment, auditing, compliance, and process improvement. However, existing methods are mostly offline and become computationally expensive when applied to large-scale event logs, limiting their applicability in practice. To address this challenge, this study explores a deep learning-based alternative for conformance checking. Instead of relying on predefined process models, the proposed approach trains classification models directly on event logs to distinguish between legal and illegal traces. The research focuses on four key issues: how to generate legal and illegal traces, whether deep learning can improve efficiency compared to traditional methods, how effectively models can classify traces, and the case volume required for effective training. Experimental results demonstrate the feasibility of applying deep learning to accelerate conformance checking, providing a promising direction for large-scale process data analysis.en_US
dc.description.tableofcontents 第一章 緒論及前言 1 1.1 研究動機 1 1.2 研究目的 2 第二章 相關研究 3 2.1 Conformance Checking 3 2.2 Conformance Checking with Deep Learning 5 第三章 研究方法 6 3.1 研究架構 6 3.2 名詞解釋與定義 7 3.3 Play-in建構Process Model 10 3.4 產生樣本資料 11 3.4.1 Legal Trace 11 3.4.2 Illegal Trace 13 3.5 訓練模型 14 3.5.1 資料前處理 14 3.5.2 模型架構 15 第四章 實驗與成果 17 4.1 實驗目的 17 4.2 實驗設計 19 4.2.1 Data Collection 19 4.2.2 實驗指標 21 4.2.3 GRU 模型訓練 21 4.3 實驗步驟 22 4.4 實驗結果 23 第五章 總結與未來工作 46 參考文獻 47zh_TW
dc.format.extent 3384465 bytes-
dc.format.mimetype application/pdf-
dc.source.uri (資料來源) http://thesis.lib.nccu.edu.tw/record/#G0110971017en_US
dc.subject (關鍵詞) 流程探勘zh_TW
dc.subject (關鍵詞) 一致性檢驗zh_TW
dc.subject (關鍵詞) 深度學習zh_TW
dc.subject (關鍵詞) Process Miningen_US
dc.subject (關鍵詞) Conformance Checkingen_US
dc.subject (關鍵詞) Deep Learningen_US
dc.title (題名) 應用深度學習於流程模型一致性檢驗之研究zh_TW
dc.title (題名) A Deep Learning Approach for Conformance Checking of Process Modelsen_US
dc.type (資料類型) thesisen_US
dc.relation.reference (參考文獻) [1] W. M. P., van der Aalst, Process Mining: Data Science in Action, 2nd Ed., Springer, 2016. [2] J., Carmona, B., van Dongen, & M., Weidlich, Conformance Checking: Foundations, Milestones and Challenges, Process Mining Handbook, pp. 155–190, 2022. [3] A., Rozinat, & W. M. P., van der Aalst, Conformance Checking of Processes Based on Monitoring Real Behavior, Information Systems, 33(1), pp. 64–95, 2008. [4] A., Adriansyah, J., Munoz-Gama, J., Carmona, B. F., van Dongen, & W. M. P., van der Aalst, Alignment Based Precision Checking, Business Process Management Workshops, pp. 137–149, 2013. [5] A., Adriansyah, N., Sidorova, & B. F., van Dongen, Cost-based Fitness in Conformance Checking, 2011 Eleventh International Conference on Application of Concurrency to System Design, pp. 57–66, 2011. [6] M., Weidlich, A., Polyvyanyy, N., Desai, J., Mendling, & M., Weske, Process Compliance Analysis Based on Behavioural Profiles. Information Systems, 36(7), pp. 1009–1025, 2011. [7] A., Burattin, S. J., van Zelst, A., Armas-Cervantes, B. F., van Dongen, & J., Carmona, Online Conformance Checking Using Behavioural Patterns, Business Process Management, pp. 250–267, 2018. [8] M., Camargo, M., Dumas, & O, González-Rojas., Learning Accurate LSTM Models of Business Processes, Business Process Management, pp. 286–302, 2019 [9] M., Pourbafrani, S., Vasudevan, F., Zafar, Y., Xingran, R., Singh, & W. M. P., van der Aalst, A Python Extension to Simulate Petri Nets in Process Mining, arXiv preprint arXiv:2102.08774, 2021. [10] J., Peeperkorn, S., vanden Broucke, & J., De Weerdt, Supervised Conformance Checking Using Recurrent Neural Network Classifiers, Process Mining Workshops, pp. 175–187, 2021. [11] J., Wang, D., Yu, X., Ma, C., Liu, V., Chang, & X., Shen, Online Predicting Conformance of Business Process with Recurrent Neural Networks, IoTBDS 2020 - Proceedings of The 5th International Conference on Internet of Things, Big Data and Security, pp. 88–100, 2020. [12] J., Lahann, P., Pfeiffer, & P., Fettke, LSTM-Based Anomaly Detection of Process Instances: Benchmark and Tweaks, Process Mining Workshops, pp. 229–241, 2023. [13] W. M. P., van der Aalst, Process Mining: Discovery, Conformance and Enhancement of Business Processes, Springer, 2011. [14] W. M. P., van der Aalst, A. H. M., ter Hofstede, B., Kiepuszewski, & A. P., Barros, Workflow Patterns, Distributed and Parallel Databases, 14(1), pp. 5–51, 2003. [15] W. M. P., van der Aalst, The Application of Petri Nets to Workflow Management, Journal of Circuits, Systems and Computers, 8(1), pp. 21–66, 1998. [16] N., Lohmann, E., Verbeek, & R., Dijkman, Petri Net Transformations for Business Processes – A Survey, Transactions on Petri Nets and Other Models of Concurrency II: Special Issue on Concurrency in Process-Aware Information Systems, pp. 49-63, 2009. [17] S. J. J., Leemans, D., Fahland, & W. M. P., van der Aalst, Discovering Block-Structured Process Models from Event Logs – A Constructive Approach, Application and Theory of Petri Nets and Concurrency, pp. 311–329, 2013. [18] W. M. P., van der Aalst, Process Discovery from Event Data: Relating Models and Logs Through Abstractions, WIREs Data Mining and Knowledge Discovery, 8(3), 2018. [19] K., Cho, B., van Merrienboer, Ç., Gülçehre, D., Bahdanau, F., Bougares, H., Schwenk, & Y., Bengio, Learning Phrase Representations Using RNN Encoder–Decoder for Statistical Machine Translation, arXiv preprint arXiv:1406.1078, 2014. [20] M., Abadi, P., Barham, J., Chen, Z., Chen, A., Davis, J., Dean, M., Devin, S., Ghemawat, G., Irving, M., Isard, M., Kudlur, J., Levenberg, R., Monga, S., Moore, D. G., Murray, B., Steiner, P., Tucker, V., Vasudevan, P., Warden, M., Wicke, Y, Yu, X., Zheng, TensorFlow: A System for Large-Scale Machine Learning, arXiv preprint arXiv:1605.08695, 2016. [21] A., Berti, S., van Zelst, & D., Schuster, PM4Py: A Process Mining Library for Python, Software Impacts, 17, 2023.zh_TW