Skip to main content
SpringerLink
Log in

D3BA: A Tool for Optimizing Business Processes Using Non-deterministic Planning

  • Conference paper
  • First Online:
Business Process Management Workshops (BPM 2020)

Part of the book series: Lecture Notes in Business Information Processing ((LNBIP,volume 397))

Included in the following conference series:

Abstract

This paper builds on recent work in the declarative design of dialogue agents and proposes an exciting new tool – D3BA (Declarative Design for Digital Business Automation) – to optimize business processes using AI planning. The tool provides a powerful framework to build, optimize, and maintain complex business processes and optimize them by composing with services that automate one or more subtasks. We illustrate salient features of this composition technique, compare with other philosophies of composition, and highlight exciting opportunities for research in this emerging field of business process automation.

This is a preview of subscription content, log in via an institution to check access.

Access this chapter

Log in via an institution
Chapter
USD 29.95
Price excludes VAT (USA)
  • Available as PDF
  • Read on any device
  • Instant download
  • Own it forever
eBook
USD 79.99
Price excludes VAT (USA)
  • Available as EPUB and PDF
  • Read on any device
  • Instant download
  • Own it forever
Softcover Book
USD 99.99
Price excludes VAT (USA)
  • Compact, lightweight edition
  • Dispatched in 3 to 5 business days
  • Free shipping worldwide - see info

Tax calculation will be finalised at checkout

Purchases are for personal use only

Institutional subscriptions

Similar content being viewed by others

Notes

  1. 1.

    Interestingly, as we discuss in more detail in [21], the declarative specification also allows for imperative patterns (e.g. “forced followups”) to be brought in wherever deemed necessary by the process author – to enforce more control over the eventual process. The actual goal of the process itself can be quite open-ended: e.g. in the specification linked above in [21], the process ends when the user says that they are done, and this abstract goal can materialize in many ways. For most processes, the ability to model such abstract goals is imperative [1] – in general these manifest as conditions that can be planned with but whose exact values need to be sensed or “determined” at execution time [23] – either by interacting with the user, such as in the case of finding out if they are done, or by monitoring the system state.

  2. 2.

    Similar to “skills” in Watson Assistant and Amazon Alexa.

References

  1. Adamo, G., Borgo, S., Di Francescomarino, C., Ghidini, C., Guarino, N.: On the notion of goal in business process models. In: AI*IA (2018)

    Google Scholar 

  2. Araghi, S.S.: Customizing the Composition of Web Services and Beyond. Ph.D. thesis, University of Toronto (2012)

    Google Scholar 

  3. Au, T.C., Kuter, U., Nau, D.: Planning for interactions among autonomous agents. In: International Workshop on Programming Multi-Agent Systems (2008)

    Google Scholar 

  4. Botea, A., et al.: Generating Dialogue Agents via Automated Planning. Technical Report (2019)

    Google Scholar 

  5. Bucchiarone, A., Pistore, M., Raik, H., Kazhamiakin, R.: Adaptation of service-based business processes by context-aware replanning. In: SOCA (2011)

    Google Scholar 

  6. Carman, M., Serafini, L., Traverso, P.: Web service composition as planning. In: ICAPS Workshop on Planning for Web Services (2003)

    Google Scholar 

  7. Chakraborti, T., Muise, C., Agarwal, S., Lastras, L.: D3WA: an intelligent model acquisition interface for interactive specification of dialog agents. In: AAAI Demo (2019)

    Google Scholar 

  8. Dong, X., Halevy, A., Madhavan, J., Nemes, E., Zhang, J.: Similarity search for web services. In: VLDB (2004)

    Google Scholar 

  9. Hoffmann, J., Bertoli, P., Pistore, M.: Web Service Composition as Planning. AAAI, Revisited. In Between Background Theories and Initial State Uncertainty. In (2007)

    MATH  Google Scholar 

  10. Hoffmann, J., Brafman, R.I.: Conformant Planning via Heuristic Forward Search: A New Approach. AIJ (2006)

    Google Scholar 

  11. Hull, R., Nezhad, H.R.M.: Rethinking BPM in a cognitive world: transforming how we learn and perform business processes. In: BPM (2016)

    Google Scholar 

  12. Jarvis, P., Moore, J., Stader, J., Macintosh, A., Casson-du Mont, A., Chung, P.: Exploiting AI technologies to realise adaptive workflow systems. In: AAAI Workshop on Agent-Based Systems in the Business Context (1999)

    Google Scholar 

  13. Kambhampati, S.: Model-Lite planning for the web age masses: the challenges of planning with incomplete and evolving domain models. In: AAAI Senior Member Track (2007)

    Google Scholar 

  14. de Leoni, M., Lanciano, G., Marrella, A.: Aligning partially-ordered process-execution traces and models using automated planning. In: ICAPS (2018)

    Google Scholar 

  15. Little, I., Thiebaux, S.: Probabilistic planning vs replanning. In: ICAPS Workshop on IPC: Past, Present and Future (2007)

    Google Scholar 

  16. Marrella, A.: Automated planning for business process management. J. Data Sem. 8(2), 79–98 (2018). https://doi.org/10.1007/s13740-018-0096-0

    Article  Google Scholar 

  17. Marrella, A., Lespérance, Y.: A planning approach to the automated synthesis of template-based process models. Serv. Orient. Comput. Appl. 11(4), 367–392 (2017). https://doi.org/10.1007/s11761-017-0215-z

    Article  Google Scholar 

  18. Marrella, A., Mecella, M., Sardina, S.: Intelligent process adaptation in the smartpm system. TIST 8(2), 1–43 (2017)

    Article  Google Scholar 

  19. Marrella, A., Mecella, M., Sardina, S.: Supporting adaptiveness of cyber-physical processes through action-based formalisms. AI Communications 31(1), 47–74 (2018)

    Article  MathSciNet  Google Scholar 

  20. Metz, R.: Microsoft’s Neo-Nazi Sexbot was a Great Lesson for Makers of AI Assistants, MIT Tech. Review (2018)

    Google Scholar 

  21. Muise, C., et al.: Planning for Goal-Oriented Dialogue Systems. Technical Report (2020)

    Google Scholar 

  22. Muise, C., McIlraith, S., Beck, C.: Improved non-deterministic planning by exploiting state relevance. In: ICAPS (2012)

    Google Scholar 

  23. Muise, C., Vodolan, M., Agarwal, S., Bajgar, O., Lastras, L.: Executing contingent plans: challenges in deploying artificial agents. In: AAAI Fall Symposium (2019)

    Google Scholar 

  24. Nau, D.S., et al.: SHOP2: An HTN planning system. JAIR 20, 379–404 (2003)

    Article  Google Scholar 

  25. Nguyen, T., Sreedharan, S., Kambhampati, S.: Robust planning with incomplete domain models. AIJ 245, 134–161 (2017)

    MathSciNet  MATH  Google Scholar 

  26. Papazoglou, M.P., Georgakopoulos, D.: Service-oriented computing. Commun. ACM 46(10), 24–89 (2003)

    Article  Google Scholar 

  27. Pesic, M., Van der Aalst, W.M.: A declarative approach for flexible business processes management. In: BPM (2006)

    Google Scholar 

  28. Pistore, M., Traverso, P., Bertoli, P.: Automated composition of web services by planning in asynchronous domains. In: ICAPS (2005)

    Google Scholar 

  29. R-moreno, M.D., Borrajo, D., Cesta, A., Oddi, A.: integrating planning and scheduling in workflow domains. Expert Syst. Appl. 33(2), 389–406 (2007)

    Article  Google Scholar 

  30. Rao, J., Su, X.: A survey of automated web service composition methods. In: Cardoso, J., Sheth, A. (eds.) SWSWPC 2004. LNCS, vol. 3387, pp. 43–54. Springer, Heidelberg (2005). https://doi.org/10.1007/978-3-540-30581-1_5

    Chapter  Google Scholar 

  31. Rizk, Y., et al.: A unified conversational assistant framework for business process automation. In: AAAI Worskhop on Intelligent Process Automation (IPA) (2020)

    Google Scholar 

  32. Sirin, E., Parsia, B., Wu, D., Hendler, J., Nau, D.: HTN Planning for Web Service Composition Using SHOP2. Science, Services and Agents on the World Wide Web, Web Semantics (2004)

    Book  Google Scholar 

  33. Sohrabi, S.: Customizing the composition of actions, programs, and web services with user preferences. In: ISWC (2010)

    Google Scholar 

  34. Sohrabi, S., McIlraith, S.A.: Preference-Based web service composition: a middle ground between execution and search. In: ISWC (2010)

    Google Scholar 

  35. Sohrabi, S., Prokoshyna, N., McIlraith, S.: Web service composition via the customization of golog programs with user preferences. In: Conceptual Modeling (2009)

    Google Scholar 

  36. Sohrabi, S., Riabov, A.V., Katz, M., Udrea, O.: An AI planning solution to scenario generation for enterprise risk management. In: AAAI (2018)

    Google Scholar 

  37. Sreedhar, K.: What it Takes to Build Enterprise-Class Chatbots (2018)

    Google Scholar 

  38. Srivastava, B.: A decision-support framework for component reuse and maintenance in software project management. In: CSMR (2004)

    Google Scholar 

  39. Srivastava, B., Koehler, J.: Web service composition - current solutions and open problems. In: ICAPS Workshop on Planning for Web Services (2003)

    Google Scholar 

  40. Talamadupula, K., Smith, D.E., Cushing, W., Kambhampati, S.: A theory of intra-agent replanning. In: ICAPS Workshop on Distributed and Multi-Agent Planning (2013)

    Google Scholar 

  41. Yoon, S.W., Fern, A., Givan, R.: FF-Replan: a baseline for probabilistic planning. In: ICAPS (2007)

    Google Scholar 

Download references

Acknowledgements

We thank IBM’s digital business automation team and the research team including Scott Boag, Falk Pollok, Vinod Muthusamy, Sampath Dechu, Merve Unuvar, and Rania Khalaf for their support and ideas throughout the project. A special word of thanks to Christian Muise and the rest of the D3WA team [21] on whose work we built our D3BA extension. Finally, many thanks to Shirin Sohrabi and Michael Katz, also from IBM Research, who helped us navigate the fascinating world of planning, business processes, and web service composition.

Author information

Authors and Affiliations

  1. IBM Research AI, Cambridge, MA, USA

    Tathagata Chakraborti, Shubham Agarwal, Yasaman Khazaeni, Yara Rizk & Vatche Isahagian

Authors
  1. Tathagata Chakraborti
    View author publications

    You can also search for this author in PubMed Google Scholar

  2. Shubham Agarwal
    View author publications

    You can also search for this author in PubMed Google Scholar

  3. Yasaman Khazaeni
    View author publications

    You can also search for this author in PubMed Google Scholar

  4. Yara Rizk
    View author publications

    You can also search for this author in PubMed Google Scholar

  5. Vatche Isahagian
    View author publications

    You can also search for this author in PubMed Google Scholar

Editor information

Editors and Affiliations

  1. Universidad de Sevilla, Seville, Spain

    Adela Del Río Ortega

  2. Kühne Logistics University, Hamburg, Germany

    Henrik Leopold

  3. Universidade do Estado do Rio de Janeiro – UERJ, Rio de Janeiro, Brazil

    Flávia Maria Santoro

Rights and permissions

Reprints and permissions

Copyright information

© 2020 Springer Nature Switzerland AG

About this paper

Check for updates. Verify currency and authenticity via CrossMark

Cite this paper

Chakraborti, T., Agarwal, S., Khazaeni, Y., Rizk, Y., Isahagian, V. (2020). D3BA: A Tool for Optimizing Business Processes Using Non-deterministic Planning. In: Del Río Ortega, A., Leopold, H., Santoro, F.M. (eds) Business Process Management Workshops. BPM 2020. Lecture Notes in Business Information Processing, vol 397. Springer, Cham. https://doi.org/10.1007/978-3-030-66498-5_14

Download citation

  • DOI: https://doi.org/10.1007/978-3-030-66498-5_14

  • Published:

  • Publisher Name: Springer, Cham

  • Print ISBN: 978-3-030-66497-8

  • Online ISBN: 978-3-030-66498-5

  • eBook Packages: Computer ScienceComputer Science (R0)

Publish with us

Policies and ethics

Search

Navigation