多模态知识图谱构建技术及其在军事领域的应用综述  

Survey of Multimodal Knowledge Graph Construction Technology and Its Application in Military Field

作　　者：姚奕 陈朝阳 杜晓明 姚天磊 李青尚 孙鸣蔚 YAO Yi;CHEN Zhaoyang;DU Xiaoming;YAO Tianlei;LI Qingshang;SUN Mingwei(College of Command&Control Engineering,Army Engineering University of PLA,Nanjing 210007,China)

机构地区：[1]中国人民解放军陆军工程大学指挥控制工程学院,南京210007

出　　处：《计算机工程与应用》2024年第22期18-37,共20页Computer Engineering and Applications

基　　金：国家自然科学基金(62273356,61806221);高层次科技创新人才自主科研项目(KYZYJKKC0024001)。

摘　　要：随着数据资源类型的丰富与大模型技术的发展,能够处理多源异构数据的多模态知识图谱(multimodal knowledge graph,MMKG)以出色的数据处理与管理能力而被广泛关注。结合领域需求与特性,对多模态知识图谱构建技术及其在军事领域的应用展开总体概述。基于传统文本知识图谱的相关概念,对多模态知识图谱的基本概念、研究现状进行梳理,分析总结了多模态信息抽取、多模态实体链接、多模态表示学习三个多模态知识图谱构建的关键技术,以及大模型技术在多模态知识图谱构建过程中的应用,探讨了多模态知识图谱在军事领域中的应用场景。最后结合大模型热点和军事需求,对多模态知识图谱构建技术的发展前景及军事应用进行总结与展望。With the rich types of data resources and the development of large language model technology,the multimodal knowledge graph(MMKG)that can handle multi-source heterogeneous data has been widely concerned because of its excellent data processing and management capabilities.Combined with the requirements and characteristics of the field,this paper gives a general survey of the construction technology of multimodal knowledge graph and its application in mil-itary field.Based on the relevant concepts of traditional text knowledge graph,this paper summarizes the basic concepts and research status of multimodal knowledge graph,analyzes and summarizes the key technologies of multimodal knowl-edge graph construction,which are multimodal information extraction,multimodal entity link and multimodal representation learning,and the application of large language model technology in the process of multimodal knowledge graph construc-tion,discusses the application scenarios of multimodal knowledge graph in military field.Finally,combined with the hot topics of large language model and military requirements,the development prospect and military application of multimodal knowledge graph construction technology are summarized.

关 键 词：多模态知识图谱 构建技术 大语言模型 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]