LAI Zan-you, HUANG Zheng-hao, CHEN Chong, WANG Tao, CHENG Liang-lun
To address the problems of scattered knowledge systems in ship assembly and ineffective mining and utilization of massive process data, this paper proposes an automatic knowledge graph construction technology for the shipbuilding domain based on large language models. This method uses large language models to convert unstructured and semi-structured ship data into structured data to build a ship process corpus. It models ship ontology knowledge structure with the assistance of large language models, designs an instruction prompting framework for ship assembly domain, and achieves efficient entity-relationship extraction, to complete the automatic construction of knowledge graphs. Additionally, the method uses triple sets constructed by general large language model instruction prompts as fine-tuning training sets to further fine-tune specialized small language models, ensuring the security of specific private ship data while reducing computational resources. Experimental results show that this method outperforms traditional baseline models in key metrics such as accuracy, providing a new technical approach for knowledge management and intelligent upgrading in the shipbuilding domain.