关键金属作为未来新兴产业的核心资源保障，近年来逐渐成为国内外学者研究的热点，其研究存在难示踪、难辨识、难分离等瓶颈。知识图谱作为大数据和人工智能的重要基础构建，能够为这些科学问题的解决提供新思路。与关键金属矿床相关的矿物学、年代学、地球化学等研究成果大多以文献的形式发表在国内外期刊杂志上，这类文献通常以自然语言的形式进行描述，难于为机器所理解和直接利用。文章以铌钽矿床为例，对铌钽矿床重要的概念和描述性属性进行了整理，构建了铌钽矿床知识图谱的本体层，并从大量文献资料中提取相关信息，建立了铌钽矿床知识图谱的数据层，初步完成了Nb-Ta矿床知识图谱的建设。在此基础上，从大数据分析的角度对中国铌钽矿床空间—时间—构造背景—成因类型多维分布特征以及矿石矿物共生组合特征与铌钽矿床多维分布之间的关联进行了分析，为进一步揭示中国铌钽矿床时空演化规律提供了新的视角。

As an important resource for emerging industries, critical metals have gradually gain attention both domestically and overseas in recent years. However there are still some bottlenecks existing in the critical metal research due to its low abundance, difficulty to trace, identify and separate. As an important infrastructure of big data and artificial intelligence, knowledge graph provides new insights to tackle these issues. Most of the research achievements related to critical metal deposits are published in academic journals, which are written in natural language and is difficult to be understood and directly used by machines. In this paper, the ontology layer of Nb-Ta deposit knowledge graph was constructed and data extracted from literatures consists of the fact layer of the Nb-Ta deposit knowledge graph. Based on the Nb-Ta deposit knowledge graph, the features and relationships among the metallogenic periods, types of Nb-Ta deposits and the co-occurrence of niobium and tantalum related minerals were analyzed. It will help to further reveal the spatio-temporal distribution and evolution characteristics of China Nb-Ta deposits.