故障运维是当前工业生产领域的一个重要研究主题.基于故障知识图谱的故障预测、故障诊断、智能问答等研究都已经得到了较大的发展和应用,然而,高质量的故障知识图谱是这些方法开展的基础.考虑到传统的知识图谱构建技术需要对原始数据进行数据预处理、实体识别、关系抽取以及实体对齐,为了提高知识图谱构建效率,本文的工作聚焦于利用大语言模型(Large Language Model,LLM)对故障运维数据进行无监督知识抽取,设计并实现一种基于大模型的大型故障知识图谱的自动构建方法.该方法主要包含2个部分:1)2种面向故障知识图谱构建的zero-shot Prompt,这些Prompt能够引导大语言模型对故障知识图谱进行概念层的生成和元素层的知识抽取,以RDF语法进行表征和输出;2)一种基于大语言模型的知识图谱构建方法,该方法可以通过zero-shot Prompt引导大语言模型对故障运维数据进行知识抽取,并以迭代的形式完成大型故障知识图谱的构建.实验结果表明本文提出的方法具有一定的科学性和有效性.
An LLM-based Method for Automatic Construction of Equipment Failure Knowledge Graphs
Fault operation and maintenance is an important research topic in the field of industrial production.The research of fault prediction,fault diagnosis,question-answering systems based on the fault knowledge graph have been greatly developed and applied.However,a high-quality fault operation and maintenance knowledge graph is the foundation for these methods.Con-sidering that traditional knowledge graph construction techniques require data preprocessing,entity recognition,relationship ex-traction and entity alignment of raw data,to improve the efficiency of knowledge graphs,this paper focuses on using large lan-guage models for unsupervised knowledge extraction from fault operation and maintenance data to achieve automatic construction of large-scale fault operation and maintenance knowledge graphs.This method mainly includes two parts:1)Two zero-shot Prompts oriented towards the construction of fault operation and maintenance knowledge graphs are proposed.These Prompts can guide large language models to generate conceptual layers and extract elemental knowledge for the fault operation and mainte-nance knowledge graph represented and output in RDF syntax;2)A method based on large language models for constructing knowledge graphs is proposed.This method can guide large language models to extract knowledge from fault operation and mainte-nance data through zero-shot Prompts and complete the construction of large-scale fault operation and maintenance knowledge graphs iteratively.Experimental results show that the proposed method is scientific and effective.
prompt learningknowledge extractionknowledge graph constructionfault operation and maintenancelarge lan-guage model
万方数据
维普
