Leveraging Machine Learning and Enhanced Parallelism Detection for BPMN Model Generation from Text

2025-07-11

AI Summary

Existing approaches for automatically converting natural-language business process descriptions into BPMN models suffer from low efficiency, poor generalization, and difficulty in identifying parallel structures. This paper proposes an end-to-end generative framework integrating machine learning and large language models. Its core contributions are threefold: (1) an enhanced parallel-structure identification mechanism that significantly improves modeling of concurrent logic; (2) the first high-quality, parallel-gateway–focused annotated dataset (15 documents, 32 parallel gateways), addressing a critical gap in the field; and (3) joint extraction of process elements and control flows trained on an extended PET dataset, achieving high accuracy. Experimental results demonstrate that our method outperforms state-of-the-art techniques in BPMN model reconstruction accuracy. It provides a practical, scalable pathway toward automated and standardized business process modeling.

Technology Category

• Natural Language Processing: Generation
• Machine Learning: Structured Learning
• Planning, Routing, and Scheduling: Planning with Language Models

Application Category

• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• Economics, Online Markets and Human Computation: Architectures and workflows that use LLMs for crowd work
• Semantics and Knowledge: Methods to enhance, augment, integrate or synergize semantic models such as knowledge graphs and LLMs

Abstract

Efficient planning, resource management, and consistent operations often rely on converting textual process documents into formal Business Process Model and Notation (BPMN) models. However, this conversion process remains time-intensive and costly. Existing approaches, whether rule-based or machine-learning-based, still struggle with writing styles and often fail to identify parallel structures in process descriptions. This paper introduces an automated pipeline for extracting BPMN models from text, leveraging the use of machine learning and large language models. A key contribution of this work is the introduction of a newly annotated dataset, which significantly enhances the training process. Specifically, we augment the PET dataset with 15 newly annotated documents containing 32 parallel gateways for model training, a critical feature often overlooked in existing datasets. This addition enables models to better capture parallel structures, a common but complex aspect of process descriptions. The proposed approach demonstrates adequate performance in terms of reconstruction accuracy, offering a promising foundation for organizations to accelerate BPMN model creation.

Problem

• Automating BPMN model generation from text using machine learning
• Improving parallel structure detection in process descriptions
• Enhancing dataset with annotated parallel gateways for better training

Innovation

• Machine learning for BPMN model generation
• Enhanced parallelism detection in text
• New annotated dataset for training