地质通报2026，Vol.45Issue(2)：549-560,12.DOI:10.12097/gbc.2025.07.001
基于GeoGPT与LightRAG的地质找矿知识图谱及知识问答模型构建方法研究
The methodology for constructing a geological prospecting knowledge graph and question answering model based on GeoGPT and LightRAG
摘要
Abstract
[Objective]The integration of massive geological text data into mineral prospecting is challenged by difficulties in semantic recognition and synthesis.While Large Language Models(LLMs)offer new possibilities,they face significant bottlenecks in understanding domain-specific terminology and constructing knowledge graphs.[Methods]This paper proposes a methodology for constructing a geological prospecting knowledge graph and a question-answering(QA)model by integrating GeoGPT with the LightRAG framework.Leveraging GeoGPT's domain-specific prior knowledge,the approach enables autonomous ontology definition,entity recognition,and relation extraction.A post-processing module for association enhancement and degradation is employed to refine the knowledge graph.Furthermore,a QA model is developed using LightRAG's distinctive dual-layer retrieval and incremental update mechanisms to achieve contextual knowledge completion from external geological databases.[Results]In key entity recognition(e.g.,minerals,ore deposits),GeoGPT's F1-score outperformed general LLMs(DeepSeek-V3,Qwen2.5-72B)by 17%-28%.Compared to GraphRAG,LightRAG significantly improved retrieval efficiency by bypassing high-cost community summarization and global reconstruction.The GeoGPT-based QA model achieved win rates 8%-28%higher in geochemistry and 52%-78%higher in remote sensing geology compared to the general models.[Conclusions]This study provides an efficient method for constructing geological knowledge graphs and lightweight QA models.By substantially improving retrieval efficiency and incremental updating,this methodology offers a robust new paradigm for the intelligent utilization of geological text data.关键词
地质知识图谱/LightRAG/GeoGPT/知识问答模型Key words
geological knowledge graph/LightRAG/GeoGPT/knowledge question-answering model分类
天文与地球科学引用本文复制引用
周波,李珂..基于GeoGPT与LightRAG的地质找矿知识图谱及知识问答模型构建方法研究[J].地质通报,2026,45(2):549-560,12.基金项目
重庆市地质矿产勘查开发局项目《重庆地区萤石共伴生矿成矿远景区 AI 找矿模型研究》(编号:DKJ-2024-DKC-B-006) Supported by Project of Chongqing Bureau of Geology and Minerals Exploration(No.DKJ-2024-DKC-B-006) （编号:DKJ-2024-DKC-B-006）
