Computer Engineering and Applications ›› 2022, Vol. 58 ›› Issue (19): 37-52.DOI: 10.3778/j.issn.1002-8331.2204-0243

• Research Hotspots and Reviews • Previous Articles     Next Articles

Summary of Research and Application of Knowledge Graphs in Risk Management Field of Commercial Banks

YUAN Jun, LIU Guozhu, LIANG Hongtao, LUO Qingcai   

  1. 1.Institute of Information Science and Technology, Qingdao University of Science and Technology, Qingdao, Shandong 266061, China
    2.Shandong Inspur Science Research Institute Co., Ltd., Jinan 250101, China
  • Online:2022-10-01 Published:2022-10-01

知识图谱在商业银行风控领域的研究与应用综述

袁俊,刘国柱,梁宏涛,罗清彩   

  1. 1.青岛科技大学 信息科学技术学院,山东 青岛 266061 
    2.山东浪潮科学研究院有限公司,济南 250101

Abstract: With the tide of financial innovation, commercial banks begin to apply intelligent technology to solve problems in the field of risk management. With increasingly diversified financial risks, especially the credit risks of bank customers, it is urgent to improve the risk management ability of commercial banks. In view of the chain reaction characteristics of risk communication, knowledge graph technology can be used to identify and monitor risks. Knowledge graph uses graph data structure to describe things and their relationship, which is easy for the management and application of large-scale knowledge. Based on the limitations of the traditional risk management model, the paper firstly introduces the concept and architecture of the knowledge graph in the field of risk management, then summarizes the research status of the key construction technologies of knowledge graph in the field of risk management, such as knowledge extraction, knowledge fusion and knowledge reasoning, finally introduces the specific application of the knowledge graph in the field of risk management, at last summarizes and analyzes the future development trend.

Key words: commercial banks, risk management, knowledge graph, knowledge extraction, knowledge fusion, knowledge reasoning

摘要: 伴随金融创新大潮,商业银行开始应用智能技术解决风控领域问题。在金融风险尤其是银行客户信用风险日益多样化的背景下,提升商业银行的风险管理能力已是刻不容缓。针对风险传播具有连锁反应的特点,可选择利用知识图谱技术鉴别和监控风险。知识图谱使用图数据结构描述客观事物及其相互之间的关系,对于大规模知识的管理和应用表现得游刃有余。以传统风控模式存在的局限性为引,介绍了风控领域知识图谱的概念与架构,归纳了知识抽取、知识融合、知识推理这几种风控领域知识图谱关键构建技术的研究现状,最后介绍风控领域知识图谱的具体应用,并总结和分析未来发展趋势。

关键词: 商业银行, 风控, 知识图谱, 知识抽取, 知识融合, 知识推理