Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

Bridging Domain Knowledge and Process Discovery Using Large Language Models

Ali Norouzifar, Humam Kourani, Marcus Dees, Wil van der Aalst

TL;DR

This paper leverages Large Language Models to integrate such knowledge directly into process discovery, using rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions.

Abstract

Discovering good process models is essential for different process analysis tasks such as conformance checking and process improvements. Automated process discovery methods often overlook valuable domain knowledge. This knowledge, including insights from domain experts and detailed process documentation, remains largely untapped during process discovery. This paper leverages Large Language Models (LLMs) to integrate such knowledge directly into process discovery. We use rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions. By integrating LLMs, we create a bridge between process knowledge expressed in natural language and the discovery of robust process models, advancing process discovery methodologies significantly. To showcase the usability of our framework, we conducted a case study with the UWV employee insurance agency, demonstrating its practical benefits and effectiveness.

Bridging Domain Knowledge and Process Discovery Using Large Language Models

TL;DR

This paper leverages Large Language Models to integrate such knowledge directly into process discovery, using rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions.

Abstract

Discovering good process models is essential for different process analysis tasks such as conformance checking and process improvements. Automated process discovery methods often overlook valuable domain knowledge. This knowledge, including insights from domain experts and detailed process documentation, remains largely untapped during process discovery. This paper leverages Large Language Models (LLMs) to integrate such knowledge directly into process discovery. We use rules derived from LLMs to guide model construction, ensuring alignment with both domain knowledge and actual process executions. By integrating LLMs, we create a bridge between process knowledge expressed in natural language and the discovery of robust process models, advancing process discovery methodologies significantly. To showcase the usability of our framework, we conducted a case study with the UWV employee insurance agency, demonstrating its practical benefits and effectiveness.
Paper Structure (15 sections, 5 figures, 1 table)

This paper contains 15 sections, 5 figures, 1 table.

Table of Contents

  1. Introduction
  2. Related Work
  3. Background
  4. Motivating Example
  5. Domain-Enhanced Process Discovery with LLMs
  6. Task Definition
  7. Rule Extraction
  8. Business Context
  9. Feedback integration
  10. Interactive Refinement
  11. Rule Validation
  12. Case Study
  13. Process Discovery Without Including Process Knowledge
  14. Employing ChatGPT to Extract the Rules
  15. Conclusion

Figures (5)

  • Figure 1: Our proposed framework to integrate process knowledge in the IMr framework employing LLMs.
  • Figure 2: Discovered models from the motivating example event log using different techniques.
  • Figure 3: Different components of the designed framework to bridge domain knowledge and process discovery using LLMs.
  • Figure 4: Normative model of the UWV claim handling process, extracted manually in collaboration with domain experts RCIS-TBP.
  • Figure 5: Discovered models from UWV event log using different strategies.