Abstract
Process compliance aims to ensure that processes adhere to requirements imposed by natural language texts such as regulatory documents. Existing approaches assume that requirements are available in a formalized manner using, e.g., linear temporal logic, leaving the question open of how to automatically extract and formalize them for verification. Especially with the constantly growing amount of regulatory documents and their frequent updates, it can be preferable to provide an approach that enables the verification of processes with requirements in natural language text instead of formalized requirements. To this end, this paper presents an approach that copes with the verification of resource compliance requirements, e.g., which resource shall perform which activity, in natural language over event logs. The approach relies on a comprehensive literature analysis to identify resource compliance patterns. It then contrasts these patterns with resource patterns reflecting the process perspective, while considering the natural language perspective. We combine the state-of-the-art GPT-4 technology for pre-processing the natural language text with a customized compliance verification component to identify and verify resource compliance requirements. Thereby, the approach distinguishes different resource patterns including multiple organizational perspectives. The approach is evaluated based on a set of well-established process descriptions and synthesized event logs generated by a process execution engine as well as the BPIC 2020 dataset.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
https://dblp.org/, last access: 2023-06-19.
- 2.
https://scikit-learn.org/stable/install.html, last access: 2023-06-19.
- 3.
https://www.sbert.net, last access: 2023-06-19.
- 4.
https://spacy.io/usage/linguistic-features, last access: 2023-06-19.
- 5.
https://cpee.org, last access: 2023-06-19.
- 6.
https://doi.org/10.4121/uuid:52fb97d4-4588-43c9-9d04-3604d4613b51 last access: 2023-06-19.
References
IEEE standard for eXtensible event stream (XES) for achieving interoperability in event logs and event streams. IEEE Std 1849–2016, pp. 1–50 (2016). https://doi.org/10.1109/IEEESTD.2016.7740858
van der Aalst, W.M.P., de Beer, H.T., van Dongen, B.F.: Process mining and verification of properties: an approach based on temporal logic. In: On the Move to Meaningful Internet Systems, pp. 130–147 (2005). https://doi.org/10.1007/11575771_11
van der Aalst, W.M.P., van Hee, K.M., van der Werf, J.M.E.M., Kumar, A., Verdonk, M.: Conceptual model for online auditing. Decis. Support Syst. 50(3), 636–647 (2011). https://doi.org/10.1016/j.dss.2010.08.014
Barrientos, M., Winter, K., Mangler, J., Rinderle-Ma, S.: Verification of quantitative temporal compliance requirements in process descriptions over event logs. In: Indulska, M., Reinhartz-Berger, I., Cetina, C., Pastor, O. (eds.) CAiSE 2023. LNCS, vol. 13901, pp. 417–433. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-34560-9_25
Bellan, P., Dragoni, M., Ghidini, C.: Extracting business process entities and relations from text using pre-trained language models and in-context learning. In: Enterprise Design, Operations, and Computing, pp. 182–199 (2022). https://doi.org/10.1007/978-3-031-17604-3_11
Bellan, P., Ghidini, C., Dragoni, M., Ponzetto, S.P., van der Aa, H.: Process extraction from natural language text: the PET dataset and annotation guidelines. In: Proceedings of the Sixth Workshop on Natural Language for Artificial Intelligence (NL4AI 2022), vol. 3287, pp. 177–191. CEUR-WS.org (2022). http://ceur-ws.org/Vol-3287/paper18.pdf
Berti, A., van Zelst, S.J., van der Aalst, W.M.P.: Process mining for python (PM4Py): bridging the gap between process- and data science. CoRR abs/1905.06169 (2019). http://arxiv.org/abs/1905.06169
Brown, T.B., et al.: Language models are few-shot learners. In: Annual Conference on Neural Information Processing Systems (2020). https://proceedings.neurips.cc/paper/2020/hash/1457c0d6bfcb4967418bfb8ac142f64a-Abstract.html
Brunello, A., Montanari, A., Reynolds, M.: Synthesis of LTL formulas from natural language texts: state of the art and research directions. In: 26th International Symposium on Temporal Representation and Reasoning, TIME, LIPIcs, vol. 147, pp. 17:1–17:19 (2019). https://doi.org/10.4230/LIPIcs.TIME.2019.17
Cabanillas, C., Ackermann, L., Schönig, S., Sturm, C., Mendling, J.: The RALph miner for automated discovery and verification of resource-aware process models. Softw. Syst. Model. 19(6), 1415–1441 (2020). https://doi.org/10.1007/s10270-020-00820-7
Friedrich, F., Mendling, J., Puhlmann, F.: Process model generation from natural language text. In: Mouratidis, H., Rolland, C. (eds.) CAiSE 2011. LNCS, vol. 6741, pp. 482–496. Springer, Heidelberg (2011). https://doi.org/10.1007/978-3-642-21640-4_36
Hashmi, M., Governatori, G., Lam, H.-P., Wynn, M.T.: Are we done with business process compliance: state of the art and challenges ahead. Knowl. Inf. Syst. 57(1), 79–133 (2018). https://doi.org/10.1007/s10115-017-1142-1
Ji, Z., et al.: Survey of hallucination in natural language generation. ACM Comput. Surv. 55(12), 248:1–248:38 (2023). https://doi.org/10.1145/3571730
Köpf, A., et al.: Openassistant conversations - democratizing large language model alignment. CoRR abs/2304.07327 (2023). https://doi.org/10.48550/arXiv.2304.07327
Ly, L.T., Maggi, F.M., Montali, M., Rinderle-Ma, S., van der Aalst, W.M.P.: Compliance monitoring in business processes: functionalities, application, and tool-support. Inf. Syst. 54, 209–234 (2015). https://doi.org/10.1016/j.is.2015.02.007
Mangler, J., Rinderle-Ma, S.: Cloud process execution engine: architecture and interfaces (2022). https://doi.org/10.48550/ARXIV.2208.12214
Narouei, M., Takabi, H., Nielsen, R.: Automatic extraction of access control policies from natural language documents. IEEE Trans. Dependable Secur. Comput. 17(3), 506–517 (2020). https://doi.org/10.1109/TDSC.2018.2818708
Neuberger, J., Ackermann, L., Jablonski, S.: Beyond rule-based named entity recognition and relation extraction for process model generation from natural language text. CoRR abs/2305.03960 (2023). https://doi.org/10.48550/arXiv.2305.03960
OpenAI: GPT-4 technical report (2023)
Quishpi, L., Carmona, J., Padró, L.: Extracting decision models from textual descriptions of processes. In: Business Process Management, pp. 85–102 (2021). https://doi.org/10.1007/978-3-030-85469-0_8
Russell, N., van der Aalst, W.M.P., ter Hofstede, A.H.M., Edmond, D.: Workflow resource patterns: identification, representation and tool support. In: Pastor, O., Falcão e Cunha, J. (eds.) CAiSE 2005. LNCS, vol. 3520, pp. 216–232. Springer, Heidelberg (2005). https://doi.org/10.1007/11431855_16
Sai, C., Winter, K., Fernanda, E., Rinderle-Ma, S.: Detecting deviations between external and internal regulatory requirements for improved process compliance assessment. In: Indulska, M., Reinhartz-Berger, I., Cetina, C., Pastor, O. (eds.) CAiSE 2023. LNCS, vol. 13901, pp. 401–416. Springer, Cham (2023). https://doi.org/10.1007/978-3-031-34560-9_24
Semmelrodt, F., Knuplesch, D., Reichert, M.: Modeling the resource perspective of business process compliance rules with the extended compliance rule graph. In: Bider, I., et al. (eds.) BPMDS/EMMSAD -2014. LNBIP, vol. 175, pp. 48–63. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-43745-2_4
Taghiabadi, E.R., Gromov, V., Fahland, D., van der Aalst, W.M.P.: Compliance checking of data-aware and resource-aware compliance requirements. In: Meersman, R., et al. (eds.) OTM 2014. LNCS, vol. 8841, pp. 237–257. Springer, Heidelberg (2014). https://doi.org/10.1007/978-3-662-45563-0_14
Türetken, O., Elgammal, A., van den Heuvel, W., Papazoglou, M.P.: Capturing compliance requirements: a pattern-based approach. IEEE Softw. 29(3), 28–36 (2012). https://doi.org/10.1109/MS.2012.45
Voglhofer, T., Rinderle-Ma, S.: Collection and elicitation of business process compliance patterns with focus on data aspects. Bus. Inf. Syst. Eng. 62(4), 361–377 (2019). https://doi.org/10.1007/s12599-019-00594-3
Winter, K., van der Aa, H., Rinderle-Ma, S., Weidlich, M.: Assessing the compliance of business process models with regulatory documents. In: Dobbie, G., Frank, U., Kappel, G., Liddle, S.W., Mayr, H.C. (eds.) ER 2020. LNCS, vol. 12400, pp. 189–203. Springer, Cham (2020). https://doi.org/10.1007/978-3-030-62522-1_14
Wolter, C., Schaad, A.: Modeling of task-based authorization constraints in BPMN. In: Alonso, G., Dadam, P., Rosemann, M. (eds.) BPM 2007. LNCS, vol. 4714, pp. 64–79. Springer, Heidelberg (2007). https://doi.org/10.1007/978-3-540-75183-0_5
Acknowledgements
This work has been partly funded by SAP SE in the context of the research project “Building Semantic Models for the Process Mining Pipeline” and by the Deutsche Forschungsgemeinschaft (DFG, German Research Foundation) – project number 277991500.
Author information
Authors and Affiliations
Corresponding author
Editor information
Editors and Affiliations
Rights and permissions
Copyright information
© 2023 The Author(s), under exclusive license to Springer Nature Switzerland AG
About this paper
Cite this paper
Mustroph, H., Barrientos, M., Winter, K., Rinderle-Ma, S. (2023). Verifying Resource Compliance Requirements from Natural Language Text over Event Logs. In: Di Francescomarino, C., Burattin, A., Janiesch, C., Sadiq, S. (eds) Business Process Management. BPM 2023. Lecture Notes in Computer Science, vol 14159. Springer, Cham. https://doi.org/10.1007/978-3-031-41620-0_15
Download citation
DOI: https://doi.org/10.1007/978-3-031-41620-0_15
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-41619-4
Online ISBN: 978-3-031-41620-0
eBook Packages: Computer ScienceComputer Science (R0)