期刊文献+

基于图数据库的人物关系知识图谱推理方法研究 被引量:15

Interpersonal Relationship Reasoning Based on Knowledge Graph in Graph Database
原文传递
导出
摘要 【目的/意义】人物关系数据中隐含着丰富的信息,是组织进行特定管理决策的重要依据。人物关系知识图谱推理研究能够发现隐含人物关系并检测人物关系数据中存在的不一致,从而支持组织基于人物关系的管理决策。【方法/过程】首先依据已有人物关系数据构建人物关系知识图谱,存储至图数据库中;然后基于自定义规则推理发现并添加隐含的人物关系;通过检测补全后的人物关系知识图谱是否存在属性值异常或关系不一致,来修正原有人物关系数据或判断新增数据的正确性。【结果/结论】隐含人物关系的发现和添加提高了人物关系自动推理与数据异常检测的准确性。并且,将人物关系数据的存储由二维表结构转变为图数据结构,能够大幅提升人物关系自动推理的效率。 【Purpose/significance】There is abundant information in interpersonal relationship data,which is the vital base for organizations when making certain management decisions.Reasoning with the interpersonal relationship knowledge graph can discover implicit interpersonal relationships and detect inconsistent relationships for supporting decision making with interpersonal relationship data.【Method/process】Firstly,an interpersonal relationship knowledge graph is built based on existing interpersonal relationship data and stored into the graph database.Then,implicit interpersonal relationships are automantically discovered and embeded into the knowledge graph through rule-based reasoning using user-defined rules.Thus,the original interpersonal relationship data can be corrected and the accuracy of new data can be detected through checking the extended knowledge graph.【Result/conclusion】The reasoning effect of interpersonal relationship detection is improved due to the addition of implicit interpersonal relationships.Meanwhile,the reasoning efficiency is significantly improved by transforming the storage of interpersonal relationship data from the two-dimensional table structure to the graph data structure.
作者 于娟 黄恒琪 席运江 朱正祥 YU Juan;HUANG Heng-qi;XI Yun-jiang;ZHU Zheng-xiang(School of Economics and Management,Fuzhou University,Fuzhou350116,China;School of Business Administration,South China University of Technology,Guangzhou510641,China;Institute for FinTech Research,Haier Consumer Finance Co.,Shanghai200120,China)
出处 《情报科学》 CSSCI 北大核心 2019年第10期8-12,共5页 Information Science
基金 国家自然科学基金项目“基于本体学习与本体映射的组织异构数据融合方法研究”(71771054)
关键词 知识图谱 人物关系 规则推理 图数据库 knowledge graph interpersonal relationship rule-based reasoning graph database
  • 相关文献

参考文献2

二级参考文献12

  • 1RAVI K, JASMINE N, ANDREW T. Structureand Evolution of Online Social Networks [C]//Proceedings of the 12th ACM SIGKDDInternational Conference on KnowledgeDiscovery and Data Mining(KDD), August2006, New York, NY, USA: ACM, 2006:935-940.
  • 2ALBERT L, RICARD G. Applying trust metricsbased on user interactions torecommendation in social networks [C]//Proceedings of the 2012 IEEE/ACMInternational Conference on Advances inSocial Networks Analysis and Mining(ASONAM), 2012, Washington, DC, USA.2012:1159-1164. doi:10.1109/ASONAM.2012.200.
  • 3GIRVAN M, NEWMAN M E J. CommunityStructure in Social and Biological Networks[J]. PNAS, 2001,99(12):7821-7826. doi:10.1073/pnas.122653799.
  • 4NEWMAN M E J. Fast Algorithm forDetecting Community Structure in Networks[J]. Phys. Rev. E, 2004, 69(6): 066133-066138. doi:10.1103/PhysRevE.69.066133.
  • 5CLAUSET A, NEWMAN M E J, MOORE C.Finding Community Structure in Very LargeNetworks [J]. Phys. Rev. E, 2004, 70(6):066111-066117. doi:10.1103/PhysRevE.70.066111.
  • 6NEWMAN M E J, GIRVAN M. Finding andEvaluating Community Structure in Networks[J]. Phys. Rev. E, 2004, 69(2): 026113-026128. doi:10.1103/PhysRevE.69.026113.
  • 7ICTCLAS 汉语分词系统:ICTCLAS 简介[EB/OL]. [2009-05-18]. http://ictclas.org/sub_1_1.html.
  • 8VIEGAS F B, WATTENBERG M, FEINBERGJ. Participatory visualization with Wordle [J].IEEE transactions on visualization andcomputer graphics, 2009, 15(6): 1137-1144. doi:10.1109/TVCG.2009.171.
  • 9GRAHAM R L, HELL P. On the history of theminimum spanning tree problem [J]. Annalsof the History of Computing, 1985,7(1): 43-57. doi:10.1109/MAHC.1985.10011.
  • 10JOSEPH B K. On the shortest spanningsubtree of a graph and the travelingsalesman Problem [J]. American.

共引文献4

同被引文献261

引证文献15

二级引证文献125

相关作者

内容加载中请稍等...

相关机构

内容加载中请稍等...

相关主题

内容加载中请稍等...

浏览历史

内容加载中请稍等...
;
使用帮助 返回顶部