Developing a Method for Building Business Process Models Based on Graph Neural Networks in the Absence of Task Identifier Data
DOI:
https://doi.org/10.58429/qaj.v4n1a333Abstract
The contemporary methodology of business process modeling is closely tied to process mining. The aim of the study is to develop a method of creating business process models through the restoration of links between events recorded in logs in the absence of CaseID data based on graph neural networks. The problem is solved by applying the graph convolutional networks architecture. The study employs a combination of a weighted adjacency matrix and an adjacency matric accounting for the graph data structure. Textual information about the tasks involved in the business process is considered when implementing the feature matrix using embeddings. The Navec embedding model is chosen to represent task titles as numerical vectors. The study was based on parsing the technological log of the 1C:Enterprise system. The obtained solutions make it possible to restore the required connection (Sequence flow) in the model of the "Approval of a commercial offer" business process in the absence of Case ID data in the event log as part of the "Reset request" task.
Downloads
References
Bagratuni, K.; Kashina, E.; Kletskova, E.; Kapustina, D.; Ivashkin, M.; Sinyukov, V.; Karshalova, A.; Hajiyev, H.; and Hajiyev, E. Impact of socially responsible business behavior on implementing the principles of sustainable development (experience of large business). Int. J. Sustain. Dev. Plan. 2023, 18(8), 2481-2488. https://doi.org/10.18280/ijsdp.180819
Borodina, M.; Idrisov, H.; Kapustina, D.; Zhildikbayeva, A.; Fedorov, A.; Denisova, D.; Gerasimova, E.; and Solovyanenko, N. State regulation of digital technologies for sustainable development and territorial planning. Int. J. Sustain. Dev. Plan. 2023, 18(5), 1615-1624. http://dx.doi.org/10.18280/ijsdp.180533
Hamilton, W.L.; Ying, R.; and Leskovec, J. Inductive representation learning on large graphs, in Proceedings of the 31st Conference on Neural Information Processing Systems (NIPS 2017); Long Beach, CA, USA, 2017. https://doi.org/10.48550/arXiv.1706.02216
Abdullaev, I.S. and Khamraev, K.I. Modeling factors affecting net assets of investment funds using autoregressive distributed lag (ARDL) model. J. Crit. Rev. 2020, 7(12), 987-990. http://dx.doi.org/10.31838/jcr.07.12.174
Ilyushin, Y. and Afanaseva, O. Modeling of a spatial distributed management system of a preliminary hydro-cleaning gasoline steam column, in 20th International Multidisciplinary Scientific GeoConference SGEM 2020, Vol. 2.1; STEF92 Technology: Sofia, Bulgaria, 2020; pp. 531-538. http://dx.doi.org/10.5593/sgem2020/2.1/s08.068
Velickovic, P.; Cucurull, G.; Casanova, A.; Romero, A.; Lio, P.; and Bengio, Y. Graph attention networks, in Proceedings of the 6th International Conference on Learning Representations (ICLR 2018); Vancouver Convention Center: Vancouver, Canada, 2018. https://doi.org/10.48550/arXiv.1710.10903
Wu, Z.; Pan, S.; Chen, F.; Long, G.; Zhang, C.; and Yu, P.S. A comprehensive survey on graph neural networks. IEEE Trans. Neural Netw. Learn. Syst. 2021, 32(1), 4-24. https://doi.org/10.1109/TNNLS.2020.2978386
Rozinat, A.; and van der Aalst, W.M.P. Conformance checking of processes based on monitoring real behavior. Inf. Syst. 2006, 33(1), 64-95. https://doi.org/10.1016/j.is.2007.07.001
van der Aalst, W.M.P. Process mining: Discovery, conformance and enhancement of business processes; Springer-Verlag: Berlin; Heidelberg, Germany, 2011.
Rybakov, A.V.; Shichkin, I.A.; Tolmachev, O.M.; and Magomaeva, L. The impact of a progressive personal income tax scale on reducing income inequality: Comparative analysis. Relacoes Internacionais no Mundo Atual 2022, 1(34), 371-395.
Weijters, A.J.M.M.; Ribeiro, J.T.; and van der Aalst, W.M.P. Process mining with the heuristics miner algorithm, BETA publicatie: Working papers, Vol. 166; Technische Universiteit Eindhoven: Eindhoven, Netherlands, 2011.
Di Francescomarino, C.; Ghidini, C.; Rospocher, M.; and Sperduti, A. Automated discovery of process models from knowledge-intensive processes, 2015.
Kipf, T.N. Graph convolutional networks; 2016. https://tkipf.github.io/graph-convolutional-networks/
Kipf, T.N. and Welling, M. Semi-supervised classification with graph convolutional networks. arXiv preprint 2016. https://doi.org/10.48550/arXiv.1609.02907
Zhou, J.; Cui, G.; Hu, S.; Zhang, Z.; Yang, C.; Liu, Z.; Wang, L.; Li, C.; and Sun, M. Graph neural networks: A review of methods and applications. AI Open, 2020, 1, 57-81. https://doi.org/10.1016/j.aiopen.2021.01.001
Gao, С.; Zheng, Y.; Li, N.; Li, Y.; Qin, Y.; Piao, J.; Quan, Y.; Chang, J.; Jin, D.; He, X.; and Li, Y. Graph neural networks for recommender systems: Challenges, methods, and directions. ACM Trans. Inf. Syst. 2021, 1(1), 1-46. https://arxiv.org/pdf/2109.12843v1.pdf
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2024 Qubahan Academic Journal
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.