Abstract
User interaction events can give an accurate picture of tasks executed in a process, since they capture work performed across applications in a detailed manner. However, such data is too low level to be used for process analysis directly, since the underlying tasks are typically not apparent from individual events. Therefore, several task-recognition techniques were recently proposed that are able to abstract user interaction data to a higher level. However, these techniques work in an offline manner, requiring user interaction data to be stored in event logs. Such storage is often infeasible, though, due to the data’s sheer volume and its privacy-sensitive nature. While this can be avoided by analyzing user interaction data in a streaming manner, existing task-recognition techniques cannot be applied to such settings, since they require multiple, post-hoc passes over the entire data collection. To overcome this, we propose the first approach for unsupervised task recognition from user interaction streams. For a given stream, our approach continuously identifies task instances, groups them according to their type, and emits task-level events to an output stream. Our evaluation demonstrates our approach’s efficacy and shows that it outperforms two baseline approaches.
This is a preview of subscription content, log in via an institution to check access.
Access this chapter
Tax calculation will be finalised at checkout
Purchases are for personal use only
Notes
- 1.
We refer to our repository for the full list of keywords, though \(K_A\) can naturally be extended with, e.g., self-defined keywords or other languages.
- 2.
t is configurable, yet, we set it to 0.1 as done by the authors of the offline approach [23].
- 3.
Given that the final number of event classes is unknown, \(s_v\) should be set sufficiently large. We set 1,000 as the default for \(s_v\), which already covers more than 6 times the total number of event classes in our evaluation data.
- 4.
- 5.
See our repository for detailed experiments regarding BL2’s parameter configurations.
References
van der Aalst, W.M.P.: Process Mining: Data Science in Action. Springer, Berlin (2016). https://doi.org/10.1007/978-3-662-49851-4
Abb, L., Bormann, C., van der Aa, H., Rehse, J.R.: Trace clustering for user behavior mining. In: ECIS 2022 Research Papers, vol. 34 (2022)
Abb, L., Rehse, J.R.: A reference data model for process-related user interaction logs. In: Di Ciccio, C., Dijkman, R., del Río Ortega, A., Rinderle-Ma, S. (eds.) Business Process Management. BPM 2022. LNCS, vol. 13420, pp. 57–74. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-16103-2_7
Agostinelli, S.: Automated segmentation of user interface logs using trace alignment techniques. In: ICPM Doctoral Consortium/Tools, pp. 13–14 (2020)
Agostinelli, S., Marrella, A., Mecella, M.: Automated segmentation of user interface logs. In: Robotic Process Automation, pp. 201–222. De Gruyter Oldenbourg (2021)
Awad, A., Weidlich, M., Sakr, S.: Process mining over unordered event streams. In: ICPM, pp. 81–88. IEEE (2020)
Bernard, G., Senderovich, A., Andritsos, P.: Cut to the trace! process-aware partitioning of long-running cases in customer journey logs. In: La Rosa, M., Sadiq, S., Teniente, E. (eds.) CAiSE 2021. LNCS, vol. 12751, pp. 519–535. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79382-1_31
Bifet, A., Gavalda, R., Holmes, G., Pfahringer, B.: Machine learning for data streams: with practical examples in MOA. MIT Press (2018)
Burattin, A.: Streaming process mining. In: van der Aalst, W.M.P., Carmona, J. (eds.) Process Mining Handbook. LNBIP, vol. 448, pp. 349–372. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-08848-3_11
Cao, F., Ester, M., Qian, W., Zhou, A.: Density-based clustering over an evolving data stream with noise. In: International Conference on Data Mining, pp. 328–339. SIAM (2006)
Chen, L., Hoey, J., Nugent, C.D., Cook, D.J., Yu, Z.: Sensor-based activity recognition. IEEE Trans. Syst. Man Cybern. 42(6), 790–808 (2012)
Dev, H., Liu, Z.: Identifying frequent user tasks from application logs. In: Proceedings of the 22nd International Conference on Intelligent User Interfaces, pp. 263–273 (2017)
Diba, K., Batoulis, K., Weidlich, M., Weske, M.: Extraction, correlation, and abstraction of event data for process mining. WIRES 10(3), 1–31 (2020)
Engelberg, G., Hadad, M., Soffer, P.: from network traffic data to business activities: a process mining driven conceptualization. In: Augusto, A., et al. (eds.) BPMDS/EMMSAD -2021. LNBIP, vol. 421, pp. 3–18. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-79186-5_1
Ester, M., Kriegel, H.P., Sander, J., Xu, X.: A density-based algorithm for discovering clusters in large spatial databases with noise. In: KDD. p. 226–231. AAAI Press (1996)
Hassani, M., Siccha, S., Richter, F., Seidl, T.: Efficient process discovery from event streams using sequential pattern mining. In: SSCI, pp. 1366–1373. IEEE (2015)
IBM: Carbon Design System - Action Labels (2022). https://carbondesignsystem.com/guidelines/content/action-labels/
Leno, V., Augusto, A., Dumas, M., La Rosa, M., Maggi, F.M., Polyvyanyy, A.: Identifying candidate routines for robotic process automation from unsegmented UI logs. In: ICPM, pp. 153–160. IEEE (2020)
Leno, V., Polyvyanyy, A., Dumas, M., La Rosa, M., Maggi, F.M.: Robotic process mining: vision and challenges. Bus. Inf. Syst. Eng. 63(3), 301–314 (2021)
Linn, C., Zimmermann, P., Werth, D.: Desktop activity mining-a new level of detail in mining business processes. In: Workshops der INFORMATIK 2018-Architekturen, Prozesse, Sicherheit und Nachhaltigkeit. Köllen Druck+ Verlag GmbH (2018)
Rebmann, A., Emrich, A., Fettke, P.: Enabling the discovery of manual processes using a multi-modal activity recognition approach. In: Di Francescomarino, C., Dijkman, R., Zdun, U. (eds.) BPM 2019. LNBIP, vol. 362, pp. 130–141. Springer, Cham (2019). https://doi.org/10.1007/978-3-030-37453-2_12
Rebmann, A., Pfeiffer, P., Fettke, P., van der Aa, H.: Multi-perspective identification of event groups for event abstraction. In: Montali, M., Senderovich, A., Weidlich, M. (eds.) Process Mining Workshops. ICPM 2022. LNBIP, vol. 468, pp. 31–43. Springer, Cham (2022). https://doi.org/10.1007/978-3-031-27815-0_3
Urabe, Y., Yagi, S., Tsuchikawa, K., Oishi, H.: Task clustering method using user interaction logs to plan RPA introduction. In: Polyvyanyy, A., Wynn, M.T., Van Looy, A., Reichert, M. (eds.) BPM 2021. LNCS, vol. 12875, pp. 273–288. Springer, Cham (2021). https://doi.org/10.1007/978-3-030-85469-0_18
van Zelst, S.J., Fani Sani, M., Ostovar, A., Conforti, R., La Rosa, M.: Filtering spurious events from event streams of business processes. In: Krogstie, J., Reijers, H.A. (eds.) CAiSE 2018. LNCS, vol. 10816, pp. 35–52. Springer, Cham (2018). https://doi.org/10.1007/978-3-319-91563-0_3
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
Rebmann, A., van der Aa, H. (2023). Unsupervised Task Recognition from User Interaction Streams. In: Indulska, M., Reinhartz-Berger, I., Cetina, C., Pastor, O. (eds) Advanced Information Systems Engineering. CAiSE 2023. Lecture Notes in Computer Science, vol 13901. Springer, Cham. https://doi.org/10.1007/978-3-031-34560-9_9
Download citation
DOI: https://doi.org/10.1007/978-3-031-34560-9_9
Published:
Publisher Name: Springer, Cham
Print ISBN: 978-3-031-34559-3
Online ISBN: 978-3-031-34560-9
eBook Packages: Computer ScienceComputer Science (R0)