数据与计算发展前沿 ›› 2026, Vol. 8 ›› Issue (4): 234-245.

CSTR: 32002.14.jfdc.CN10-1649/TP.2026.04.018

doi: 10.11871/jfdc.issn.2096-742X.2026.04.018

• • 上一篇    下一篇

基于多智能体协作和复杂网络理论的贸易事件知识图谱构建

周晓芳1(),鲍彦荣2,顾荣杰1,*(),王昕1   

  1. 1 公安部第三研究所， 上海 201204
    2 上海理工大学， 管理学院， 上海 200093
  • 收稿日期:2026-01-05 出版日期:2026-08-20 发布日期:2026-08-21
  • 通讯作者: 顾荣杰（E-mail: grj1116@163.com）
  • 作者简介:周晓芳，博士，公安部第三研究所，副研究员，从事特种技术、人工智能、卫星通讯等方面的研究和项目工作。参与和主持“十三五”、“十四五”重点研究计划、公安部应用创新计划、公安部技术革新、上海市科技创新计划等科研项目9项，发表学术论文6篇，主编《智慧社区大数据》专著1部。获得知识产权8项，包括发明专利1项、实用新型专利3项、软件著作权4项。
    本文负责确定论文总体思路、编制修改、数据收集和测试验证工作。
    ZHOU Xiaofang, Ph.D., is an associate researcher at the Third Research Institute of the Ministry of Public Security. She is engaged in research and project work related to special technologies, artificial intelligence, and satellite communications. She has participated in and led nine research projects, including the “13th Five-Year Plan” and “14th Five-Year Plan” key research programs, the Ministry of Public Security’s Application Innovation Plan, the Ministry of Public Security’s Technological Innovation, and the Shanghai Science and Technology Innovation Plan. She has published six academic papers and served as the chief editor of the monograph “Big Data for Smart Communities.” She holds eight intellectual property rights, including one invention patent, three utility model patents, and four software copyrights.
    In this paper, she is responsible for determining the overall research idea and framework, drafting and revising the manuscrip, data collection, testing and verification.
    E-mail: fw339zxf@126.com|顾荣杰，博士、研究员，警务技术三级警监，现任公安部第三研究所特种技术中心主任，公安部警务保障专家，公安部十二局教官、装备专家，国家移动信息产业技术创新战略联盟网络特种技术专业委员会主任委员，上海市通信学会理事。长期从事公安装备、信息与网络安全的理论研究与技术应用，主持国家重点研发计划项目1项，课题1项，发表专业学术论文10余篇及多项专利；多次主持完成国家重大工程规划和全国公安信息化建设总体规划，制订公共安全领域和行业标准10余项。获得公安部科学技术三等奖2次、荣立个人三等功3次和个人嘉奖3次。
    本文负责制定论文框架，论文修改、审定。
    GU Rongjie, Ph.D., is a research fellow and Third-Class Police Commissioner. He currently serves as the Director of the Special Technology Center at the Third Research Institute of the Ministry of Public Security. He is an expert in police support for the Ministry of Public Security, an instructor and equipment specialist for the 12th Bureau of the Ministry of Public Security, Chairman of the Network Special Technology Professional Committee of the National Mobile Information Industry Technology Innovation Strategic Alliance, and a council member of the Shanghai Communication Society. Dr. Gu has long been engaged in theoretical research and technological applications in public security equipment, information, and network security. He has led one national key R&D program and one research project, published over 10 professional academic papers, and holds multiple patents. He has also spearheaded the planning of several major national projects and the overall design of national public security informatization, formulating more than 10 standards in the field of public safety and related industries. He has been awarded the Third Prize for Science and Technology by the Ministry of Public Security twice, received three individual Third-Class Merits, and three individual commendations.
    In this paper, he is responsible for developing the paper framework, revising the manuscript, and finalizing the manuscript.
    E-mail: grj1116@163.com
  • 基金资助:
    四川省科技厅重大科技专项揭榜挂帅项目(2025ZDZX0059);国家重点研发计划301项目(C22501);公安部技术革新计划项目(C25246)

Construction of Trade Event Knowledge Graph Based on Multi-Agent Collaboration and Complex Network Theory

ZHOU Xiaofang1(),BAO Yanrong2,GU Rongjie1,*(),WANG Xin1   

  1. 1 The Third Research Institute of the Ministry of Public Security, Shanghai 201204, China
    2 Business School, University of Shanghai for Science and Technology, Shanghai 200093, China
  • Received:2026-01-05 Online:2026-08-20 Published:2026-08-21

RichHTML

4

PDF

16

摘要：

【目的】 在大数据时代，重大网络事件治理难度增大，通过构建知识图谱并分析可以有效支持智能决策。【方法】 本文采用改进的多智能体协作框架，以某贸易事件为研究对象，先通过 Python 采集了多源异构数据，再基于改进的多智能体框架构建了知识图谱，最后结合复杂网络理论解析了图谱的网络结构特征。【结果】 结果显示，该多智能体知识图谱构建框架能够高效地从非结构化数据中提取三元组，构建的知识图谱呈现“经济为基、政治为纲、多维延伸”特征，网络分析发现其具有典型的幂律分布特征。【结论】 本文有效提升了知识图谱的构建效率，缓解了传统网络事件研究痛点，为其结构化与量化分析提供支撑。

关键词: 公共治理, 知识图谱, 智能体, 大语言模型

Abstract:

[Objective] In the era of big data, the governance of major cyber events has become increasingly challenging. Constructing knowledge graphs and conducting analysis can effectively support intelligent decision-making. [Method] This paper employs an improved multi-agent collaboration framework, taking a trade event as the research subject. First, multi-source heterogeneous data was collected using Python, followed by the construction of a knowledge graph based on the enhanced multi-agent framework. Finally, the network structural characteristics of the graph are analyzed using complex network theory. [Results] The results demonstrate that this multi-agent knowledge graph construction framework can efficiently extract triples from unstructured data. The constructed knowledge graph exhibits the characteristics of “economy as the foundation, politics as the framework, and multi-dimensional extension.” Network analysis reveals that it has typical power-law distribution features. [Conclusion] This study effectively improves the efficiency of knowledge graph construction, alleviates the limitations of traditional cyber event research, and provides support for its structured and quantitative analysis.

Key words: public opinion governance, knowledge graph, intelligent agent, large language model