Abstract
Advocating a convergence between generative AI and BPMN-based process analysis, this study reports on experiments with multi-modal business process representations. By leveraging the capabilities of the Bee-Up modeling tool for RDF serialization and the standard XML export of SAP Signavio, the report probes into the generative AI ability of BPMN interpretation according to these different serializations. In addition, the deployment of multi-modal AI – that directly processes image inputs – transcends traditional constraints of machine readability of BPMN diagrams. For prompt engineering, we employ a combined strategy utilizing semantic processing offered by Ontotext GraphDB integrated with LLM services from OpenAI, which, applied on RDF representations of BPMN, can push the boundaries of natural language interactions with visual process models. The investigation experiments with the interpretation of BPMN process models through such AI-based user interactions, highlighting possibilities of integrating conversational AI with the Business Process Management lifecycle. Assessments of outcomes are based on the RAGAs framework.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Similar content being viewed by others
References
Camunda: What is BPMN? business process model and notation. https://camunda.com/bpmn/. Accessed 16 Dec 2023
Cinpoeru, M., Ghiran, A.-M., Harkai, A., Buchmann, R.A., Karagiannis, D.: Model-driven context configuration in business process management systems: an approach based on knowledge graphs. In: Pańkowska, M., Sandkuhl, K. (eds.) Perspectives in Business Informatics Research: 18th International Conference, BIR 2019, Katowice, Poland, September 23–25, 2019, Proceedings, pp. 189–203. Springer International Publishing, Cham (2019). https://doi.org/10.1007/978-3-030-31143-8_14
OMILAB NPO: Bee-up for education. https://bee-up.omilab.org/activities/bee-up/. Accessed 30 Dec 2023
Bachhofner, S., Kiesling, E., Revoredo, K., Waibel, P., Polleres, A.: Automated process knowledge graph construction from BPMN models. In: Strauss, C., Cuzzocrea, A., Gabriele Kotsis, A., Tjoa, M., Khalil, I. (eds.) Database and Expert Systems Applications: 33rd International Conference, DEXA 2022, Vienna, Austria, August 22–24, 2022, Proceedings, Part I, pp. 32–47. Springer International Publishing, Cham (2022). https://doi.org/10.1007/978-3-031-12423-5_3
Buchmann, R.A., Ussenbayeva, M., Utz, W., Karagiannis, D: Leveraging RDF graphs, similarity metrics and network analysis for business process management. In: Martin A., et al. (eds.) Proceedings of the AAAI 2023 Spring Symposium on Challenges Requiring the Combination of Machine Learning and Knowledge Engineering (AAAI-MAKE 2023). Hyatt Regency, San Francisco Airport, California, USA (2023). https://ceur-ws.org/Vol-3433/paper14.pdf
Uifălean, Ș, Ghiran, A.-M., Buchmann, R.A.: Employing graph databases for business process management and representation. In: Silaghi, G.C., Buchmann, R.A., Niculescu, V., Czibula, G., Barry, C., Lang, M., Linger, H., Schneider, C. (eds.) Advances in Information Systems Development: AI for IS Development and Operations, pp. 73–92. Springer International Publishing, Cham (2023). https://doi.org/10.1007/978-3-031-32418-5_5
Fill, H., Fettke, P., Köpke, J.: Conceptual modeling and large language models: Impressions from first experiments with ChatGPT. EMISAJ 18(3), 1–15 (2023). https://doi.org/10.18417/emisa.18.3
Dolha, D.N., Buchmann, R.A.: Comparative analysis of natural language query responses on BPMN model serializations: RDF graphs vs. BPMN XML. In: Presented at: The 23rd International Conference on Informatics in Economy. IE 2024. Timişoara (2024)
Dolha, D.N., Buchmann, R.A.: Experiments with natural language queries on RDF vs. XML-serialized BPMN diagrams. In: 28th International Conference on Knowledge-Based and Intelligent Information & Engineering Systems. KES (2024). In press
Guntur, B.H.: Automating data flow diagram generation from user stories using large language models. In: 7th Workshop on Natural Language Processing for Requirements Engineering, Winterthur, Switzerland (2024). https://hal.science/hal-04525925/
AQL query language: ADOxx documentation. https://www.adoxx.org/live/adoxx-query-language-aql/. Accessed 12 Jan 2024
Grohs, M., Abb, L., Elsayed, N., Rehse, JR.: Large language models can accomplish business process management tasks. In: De Weerdt, J., Pufahl, L. (eds.) Business Process Management Workshops. BPM 2023. Lecture Notes in Business Information Processing, vol. 492. Springer, Cham (2024). https://doi.org/10.48550/arXiv.2307.09923
Vidgof, M., Bachhofner, S., Mendling, J.: Large language models for business process management: opportunities and challenges. In: Di Francescomarino, C., Burattin, A., Janiesch, C., Sadiq, S. (eds.) Business Process Management Forum. BPM 2023. Lecture Notes in Business Information Processing, vol. 490. Springer, Cham (2023). https://doi.org/10.48550/arXiv.2304.04309
Jalali, A.: Graph-based process mining. In: Leemans, S., Leopold, H. (eds.) Process Mining Workshops: ICPM 2020 International Workshops, Padua, Italy, October 5–8, 2020, Revised Selected Papers, pp. 273–285. Springer International Publishing, Cham (2021). https://doi.org/10.1007/978-3-030-72693-5_21
OpenAI: GPT-4. https://openai.com/research/gpt-4. Accessed 15 Apr 2024
Polyvyanyy, A.: Process querying: methods, techniques, and applications. In: Polyvyanyy, A. (ed.) Process Querying Methods, pp. 511–524. Springer International Publishing, Cham (2022). https://doi.org/10.1007/978-3-030-92875-9_18
Busch, K., Rochlitzer, A., Sola, D., Leopold, H.: Just tell me: prompt engineering in business process management. In: van der Aa, H., Bork, D., Proper, H.A., Schmidt, R. (eds.) Enterprise, Business-Process and Information Systems Modeling. BPMDS EMMSAD 2023 2023. Lecture Notes in Business Information Processing, vol. 479. Springer, Cham (2023). https://doi.org/10.48550/arXiv.2304.07183
Shahin, M., Chen, F.F., Hosseinzadeh, A., Maghanaki, M., Eghbalian, A.: A novel approach to voice of customer extraction using GPT-3.5 turbo: linking advanced NLP and lean six sigma 4.0. Int. J. Adv. Manuf. Technol. 131, 3615–3630 (2024). https://doi.org/10.21203/rs.3.rs-3246823/v1
Jasińska, K., Lewicz, M., Rostalski, M.: Digitization of the enterprise - prospects for process automation with using RPA and GPT integration. Procedia Comput. Sci. 225, 3243–3254 (2023). https://doi.org/10.1016/j.procs.2023.10.318
Yang, L.F., Chen, H., Li, Z., Ding, X., Wu, X.: Give us the facts: enhancing large language models with knowledge graphs for fact-aware language modeling. IEEE Transactions on Knowledge and Data Engineering (2023). https://doi.org/10.48550/arXiv.2306.11489
Karagiannis, D., Buchmann, R.A., Utz, W.: The OMiLAB digital innovation environment: agile conceptual models to bridge business value with digital and physical twins for product-service systems development. Comput. Ind. 138, 103631 (2022). https://doi.org/10.1016/j.compind.2022.103631
Buchmann, R. A., Burzynski, P., Utz, W: ER2023 tutorials: semantic enrichment & digital twins based on conceptual modeling: the bee-up tool. https://er2023.inesc-id.pt/program/tutorials/#tutorial3/. Accessed 30 Dec 2023
SAP Signavio: SAP signavio process transformation suite, academic edition. https://www.signavio.com/academic-and-research-alliances/. Accessed 15 Apr 2024
Buchmann, R.A., Karagiannis, D.: Pattern-based transformation of diagrammatic conceptual models for semantic enrichment in the web of data. Procedia Comput. Sci. 60, 150–159 (2015). https://doi.org/10.1016/j.procs.2015.08.114
Ontotext, What is GraphDB? – GraphDB 10.5 documentation. https://graphdb.ontotext.com/documentation/10.5/. Accessed 15 Apr 2024
Ontotext: Querying OpenAI GPT Models. https://graphdb.ontotext.com/documentation/10.5/gpt-queries.html#configuring. Accessed 15 Apr 2024
OpenAI: Introducing ChatGPT Plus. https://openai.com/blog/chatgpt-plus. Accessed 15 Apr 2024
Es, S., James, J., Espinosa-Anke, L., Schockaert, S.: RAGAS: automated evaluation of retrieval augmented generation. In: Proceedings of the 18th Conference of the European Chapter of the Association for Computational Linguistics: System Demonstrations. Association for Computational Linguistics (2024). https://aclanthology.org/2024.eacl-demo.16
Ragas: Metrics. https://docs.ragas.io/en/v0.0.17/concepts/metrics/index.html. Accessed 15 Apr 2024
Acknowledgement
This work was supported through the student research scholarship no. 36300/2024, granted to Damaris Dolha by Babeș-Bolyai University.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2024 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Dolha, D.N., Buchmann, R.A. (2024). Generative AI for BPMN Process Analysis: Experiments with Multi-modal Process Representations. In: Řepa, V., Matulevičius, R., Laurenzi, E. (eds) Perspectives in Business Informatics Research. BIR 2024. Lecture Notes in Business Information Processing, vol 529. Springer, Cham. https://doi.org/10.1007/978-3-031-71333-0_2
Download citation
DOI: https://doi.org/10.1007/978-3-031-71333-0_2
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-71332-3
Online ISBN: 978-3-031-71333-0
eBook Packages: Computer ScienceComputer Science (R0)