An LLM-Based Generation and Visualization Method for Cross-Organizational Emergency Response Process Models in Coal–Power Joint Operation Enterprises

View at publisher Summarise with VIRAT
Authors: Jianling Zang, Suiling Wang, Weijun Zhang, Ning Li
Cited by: 0
References: 6

Summary

No summary yet. VIRAT can read this paper and write a plain-language summary of its aim, methods, key findings and limitations.

Summarise with VIRAT Free to try with your Science Catalogs account.

Abstract

Emergency response in coal-power enterprises requires multi-organizational collaboration, yet existing emergency plans are typically documented in natural language with implicit process structures, hindering efficient cross-organizational coordination. To address the high cost and low automation in transforming textual plans into executable models, this paper proposes an automatic generation and visualization method based on large language models (LLMs) and the Flowable platform. The method extracts key process elements (activities, roles, conditions, temporal relationships) from emergency plan texts through structured preprocessing and LLM analysis, generates BPMN 2.0compliant cross-organizational process models, and deploys them to Flowable for visualization and execution. Validated through a whole-plant power outage case study, the method demonstrates significant modeling cost reduction, improved process clarity and standardization, offering a practical pathway for informatizing emergency management in coal-power enterprises.

Fields of Study & Subjects

Business Process Modeling and Analysis Safety and Risk Management Model-Driven Software Engineering Techniques

Publication details

Journal / source
International Conference on Electrical Automation and Artificial Intelligence (ICEAAI)
Pages
718–721
Publication date
16 January 2026
Language
EN