Intelligent Mining and Reasoning for Shipbuilding Process Rules Based on LLM-KG
TL;DR
This paper introduces RCKG—a knowledge graph structure tailored for process reasoning—and develops its ontology schema and an RCKG-based dynamic reasoning base approach is adopted, which retrieves similar rule chains via retrieval-augmented generation and applies multi-level weight-based conflict resolution, enabling dynamic organization and rapid reasoning.
Abstract
To address three key challenges in the knowledge-based process of domain process design—heavy manual dependence, the difficulty of updating traditional knowledge rules, and the reliance of knowledge graph construction on manual effort with limited contextual understanding—this paper proposes an LLM-KG-based domain rule reasoning framework termed RCKG-DRB. First, this paper introduces RCKG—a knowledge graph structure tailored for process reasoning—and develops its ontology schema. Subsequently, integrating Prompt Engineering with Workflow techniques, an LLM-based automatic RCKG rule chain construction method is proposed for efficient rule mining. Finally, an RCKG-based dynamic reasoning base approach is adopted, which retrieves similar rule chains via retrieval-augmented generation (RAG) and applies multi-level weight-based conflict resolution, enabling dynamic organization and rapid reasoning. Experiments demonstrate that RCKG-DRB achieves an F1 score of 87.31% in domain-specific knowledge graph construction, showing promising improvements on the evaluated dataset in both reasoning accuracy and explainability, thereby enhancing rule-based knowledge management.