A Large Language Model-Enhanced Knowledge Graph Multi-hop Reasoning Method for Assembly Process Question-Answering

Abstract In the assembly process design, knowledge question-answering is a crucial scenario for promoting the sharing of knowledge resources and enhancing the process design accuracy and efficiency. Simultaneously, knowledge graph technology enables efficient semantic modeling of knowledge, to capture the semantics and intentions of users more accurately, thereby improving the accuracy and flexibility of knowledge question-answering. However, due to the high complexity and specialization of assembly processes, current knowledge graph question-answering for assembly processes still faces challenges such as difficulty in understanding complex queries. In response to this, this paper proposes a large language model (LLM)-enhanced knowledge graph multi-hop reasoning method for assembly process question-answering. This method decomposes the multi-hop knowledge graph question-answering task into a series of subtasks: LLM-tuning-based question-answering chain generation task, which transform the question into one or more question-answering chains, multi-hop question-answering chain reasoning task, and LLM-based natural language answer generation task. For the multi-hop question-answering chain reasoning task, a multi-hop reasoning model for assembly processes based on graph paths is constructed, employing a reasoning strategy of “core multi-hop question-answering chain reasoning + attribute constraints” and a task-oriented negative sample setting method to achieve rapid and precise reasoning between the knowledge graph and question-answering chains. The effectiveness of the proposed method is validated through the comparative experiments with existing mature knowledge graph question-answering models.