[1]田萍芳,张冰,黄涛,等.基于全局和历史对比的时序知识图谱推理模型[J].计算机技术与发展,2025,(07):84-92.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0051]
　TIAN Ping-fang,ZHANG Bing,HUANG Tao,et al.A Temporal Knowledge Graph Reasoning Model Based on Global and Historical Comparisons[J].,2025,(07):84-92.[doi:10.20165/j.cnki.ISSN1673-629X.2025.0051]
点击复制

基于全局和历史对比的时序知识图谱推理模型()

《计算机技术与发展》[ISSN:1006-6977/CN:61-1281/TN]

卷:
期数:
2025年07期
页码:
84-92
栏目:
人工智能
出版日期:
2025-07-10

文章信息/Info

Title:
A Temporal Knowledge Graph Reasoning Model Based on Global and Historical Comparisons
文章编号:
1673-629X(2025)07-0084-09
作者:
田萍芳1; 2; 张冰1; 2; 黄涛1; 2; 齐凤亮1; 3; 光晓俐1; 3; 顾进广1; 2
1. 武汉科技大学 计算机科学与技术学院,湖北 武汉 430065;
2. 湖北智能信息处理与实时计算重点实验室,湖北 武汉 430065;
3. 公安部鉴定中心,北京 100038
Author(s):
TIAN Ping-fang1; 2; ZHANG Bing1; 2; HUANG Tao1; 2; QI Feng-liang1; 3; GUANG Xiao-li1; 3; GU Jin-guang1; 2
1. School of Computer Science and Technology,Wuhan University of Science and Technology,Wuhan 430065,China;
2. Hubei Province Key Laboratory of Intelligent Information Processing and Real-time Industrial System,Wuhan 430065,China;
3. Institute of Forensic Sciences,Ministry of Public Security of the People’s Republic of China,Beijing 100038,China
关键词:
知识图谱; 知识图谱推理; 注意力机制; 对比学习; 多层感知机
Keywords:
knowledge graph; knowledge graph reasoning; attention mechanism; contrastive learning; multilayer perceptron
分类号:
TP311
DOI:
10.20165/j.cnki.ISSN1673-629X.2025.0051
摘要:
时序知识图谱推理旨在借助时序信息,捕捉知识图谱演化过程,并补充知识图谱中的缺失链路。 针对大多数模型缺乏对新实体的考虑或未考虑不同数据集中重复事件的比例,该文提出了一种基于全局与历史对比的时序知识图谱推理模型。 为增强对新实体的识别与适应能力,设计了全局生成编码器,高效提取全局静态实体信息,并利用多头注意力机制精确聚焦相关实体。 同时,引入历史线索编码器,从直接历史线索和关联历史线索两个维度提取历史事实。 为准确区分全局信息与历史信息的差异,模型还集成了对比学习模块,促使模型关注全局依赖信息与历史依赖信息的不同。 模型在ICEWS14、GDELT、YAGO 以及 WIKI 等多个数据集上进行了链路预测实验,结果表明模型在 MRR、Hits@ 1、Hits@ 3、Hits@ 10 等评价指标上较次优模型获得了 2 百分点至 6 百分点的提升,有效提升了时序知识图谱的推理能力。
Abstract:
Time-series knowledge graph inference aims to capture the knowledge graph evolution process and supplement the missing links in the knowledge graph with the help of time-series information. In response to the fact that most models lack the consideration of new entities or do not consider the proportion of duplicate events in different datasets,we propose a temporal knowledge graph inference model based on the comparison between global and historical. To enhance the recognition and adaptation of new entities,we design a global generative encoder to efficiently extract global static entity information and accurately focus on relevant entities using a multi-head attention mechanism. Meanwhile,a history cue encoder is introduced to extract historical facts from two dimensions:direct history cues and associated history cues. In order to accurately distinguish the difference between global and historical information,the model also in-tegrates a comparative learning module,which prompts the model to focus on the difference between globally dependent information and historically dependent information. The model is subjected to link prediction experiments on several datasets, including ICEWS14,GDELT, YAGO, and WIKI, etc. The results show that the model obtains an improvement of two percentage points to six percentage points over the suboptimal model in the evaluation metrics,such as MRR,Hits@ 1,Hits@ 3,and Hits@ 10,which effectively enhances the inference ability of the time-series knowledge graph.

相似文献/References:

[1]孙艳,田丽梅. 基于多维尺度分析的舆情研究主题词知识图谱[J].计算机技术与发展,2016,26(04):187.
　SUN Yan,TIAN Li-mei. Mapping Knowledge Domain on Subject Headings of Public Sentiment Research Based on Multi-dimensional Scaling[J].,2016,26(07):187.
[2]刘申凯,周霁婷,朱永华,等.融合知识图谱和 ESA 方法的网络新词识别[J].计算机技术与发展,2019,29(03):12.[doi:10.3969/ j. issn.1673-629X.2019.03.003]
　LIU Shen-kai,ZHOU Ji-ting,ZHU Yong-hua,et al.Network New Word Recognition Based on Fusion of Knowledge Graph and ESA[J].,2019,29(07):12.[doi:10.3969/ j. issn.1673-629X.2019.03.003]
[3]戈其平,钟艳如.基于数学教学的知识图谱构建[J].计算机技术与发展,2019,29(03):187.[doi:10.3969/ j. issn.1673-629X.2019.03.039]
　GE Qi-ping,ZHONG Yan-ru.Construction of Knowledge Atlas Based on Mathematics Teaching[J].,2019,29(07):187.[doi:10.3969/ j. issn.1673-629X.2019.03.039]
[4]魏 瑾,李伟华,潘 炜.基于知识图谱的智能决策支持技术及应用研究[J].计算机技术与发展,2020,30(01):1.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 001]
　WEI Jin,LI Wei-hua,PAN Wei.Research on Intelligent Decision Support Technology and Application Based on Knowledge Graph[J].,2020,30(07):1.[doi:10. 3969 / j. issn. 1673-629X. 2020. 01. 001]
[5]项 威,王 邦.中文事件抽取研究综述[J].计算机技术与发展,2020,30(02):1.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 001]
　XIANG Wei,WANG Bang.Survey of Chinese Event Extraction Research[J].,2020,30(07):1.[doi:10. 3969 / j. issn. 1673-629X. 2020. 02. 001]
[6]刘家祝,郭 强,吴碧伟,等.基于子图相交的社交账号与知识图谱实体对齐[J].计算机技术与发展,2020,30(05):10.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 003]
　LIU Jia-zhu,GUO Qiang,WU Bi-wei,et al.Subgraph Intersection Based Alignment between Social Media Account and Knowledge Graph Entity[J].,2020,30(07):10.[doi:10. 3969 / j. issn. 1673-629X. 2020. 05. 003]
[7]陆菁宇,张绍阳,黄文旎.学科发展状态的知识图谱构建[J].计算机技术与发展,2020,30(06):145.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 028]
　LU Jing-yu,ZHANG Shao-yang,HUANG Wen-ni.Analysis of Development Status of Discipline Based on Knowledge Graph[J].,2020,30(07):145.[doi:10. 3969 / j. issn. 1673-629X. 2020. 06. 028]
[8]黄东晋,秦 汉,郭 昊.基于 BERT-CNN 的电影原声智能问答系统[J].计算机技术与发展,2020,30(11):158.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 029]
　HUANG Dong-jin,QIN Han,GUO Hao.Movie Soundtrack Intelligent Question and Answer System Based on BERT-CNN[J].,2020,30(07):158.[doi:10. 3969 / j. issn. 1673-629X. 2020. 11. 029]
[9]任佳妮,杨 阳.全球医疗机器人技术领域创新态势分析[J].计算机技术与发展,2021,31(04):158.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 027]
　REN Jia-ni,YANG Yang.Analysis of Innovation Situation in Field of Global MedicalRobot Technology[J].,2021,31(07):158.[doi:10. 3969 / j. issn. 1673-629X. 2021. 04. 027]
[10]卢 琪,谢艺菲,谢 钧,等.知识图谱在智能问答中的应用研究[J].计算机技术与发展,2021,31(07):13.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 003]
　LU Qi,XIE Yi-fei,XIE Jun,et al.Research on Application of Knowledge Graphs in Intelligent Question Answering[J].,2021,31(07):13.[doi:10. 3969 / j. issn. 1673-629X. 2021. 07. 003]

更新日期/Last Update: 2025-07-10