计算机科学

计算机科学 ›› 2023, Vol. 50 ›› Issue (10): 146-155.doi: 10.11896/jsjkx.221000063

• 人工智能 • 上一篇    下一篇

基于知识增强的企业实体关系预测模型

王家祺1, 李文根1, 关佶红1, 邢婷2, 魏小敏2, 邵冰清2, 付宠洁2   

  1. 1 同济大学电子与信息工程学院 上海201804
    2 北京上奇数字科技有限公司 北京100084
  • 收稿日期:2022-10-10 修回日期:2023-02-20 出版日期:2023-10-10 发布日期:2023-10-10
  • 通讯作者: 关佶红(jhguan@tongji.edu.cn)
  • 作者简介:(wangjq@tongji.edu.cn)
  • 基金资助:
    国家自然科学基金(U1936205,62202336);上海“科技创新行动计划”软科学研究项目(22692194100)

Knowledge Enhanced Relationship Prediction Model for Enterprise Entities

WANG Jiaqi1, LI Wengen1, GUAN Jihong1, XING Ting2, WEI Xiaomin2, SHAO Bingqing2, FU Chongjie2   

  1. 1 College of Electronic and Information Engineering,Tongji University,Shanghai 201804,China
    2 Beijing Shangqi Digital Technology Co.,Ltd.,Beijing 100084,China
  • Received:2022-10-10 Revised:2023-02-20 Online:2023-10-10 Published:2023-10-10
  • About author:WANG Jiaqi,born in 2000,doctoral student,is a member of China Compu-ter Federation.His main research intere-sts include knowledge graph and data mining.GUAN Jihong,born in 1969,Ph.D,professor,Ph.D supervisor,is a member of China Computer Federation.Her main research interests include machine learning and bioinformatics.
  • Supported by:
    National Natural Science Foundation of China(U1936205,62202336) and Shanghai Soft Science Research Program(22692194100).

PDF (PC)

1880

摘要： 随着知识图谱的不断发展,大量应用于工业界的产业知识图谱应运而生。然而,这些产业知识图谱经常缺乏充足的企业关联关系,如上下游关系、供应关系、合作关系、竞争关系等,导致其应用范围受到极大限制。现有企业关系预测研究大多仅关注知识图谱中三元组本身的结构信息,未能充分利用企业文本描述和企业关联实体的描述等多视角信息。为解决该问题,提出了一种基于知识增强的企业实体关系预测模型KERP。模型首先通过多视角实体特征三元组学习,完善企业实体特征表示;其次,利用图注意力网络获取实体的高阶语义表示,并与TransR模型学习的实体关系低阶语义表示进行融合,进一步增强企业实体及其关系的特征表示;最后,通过二维卷积解码器ConvE实现对企业实体关系的预测。在新能源汽车产业知识图谱数据上的实验分析表明,与现有主流实体关系预测模型相比,KERP在预测企业关系上具有更好的效果,在F1值上有6.7%的提升。此外,在多个公开实体关系预测数据集上的实验结果表明,KERP模型在一般化的实体关系预测任务上也具有较好的通用性。

关键词: 产业知识图谱, 企业实体关系, 知识补全, 链路预测, 知识增强

Abstract: With the development of knowledge graphs,a variety of industrial knowledge graphs have come into being.However,these industrial knowledge graphs lack sufficient relationships among enterprises,such as up-down stream relationship,supply relationship,cooperation and competition relationship,which greatly affects their applications.Most existing methods for predicting the enterprise entity relationships focus on the fact triples and cannot fully utilize multiple perspectives such as enterprise descriptions and associated entity descriptions.To solve this problem,KERP,a knowledge enhanced relationship prediction model for enterprise entities is proposed.The model first improves enterprise features representations using a multi-view entity feature lear-ning module,then uses graph attention network to obtain higher-order semantic representations of entities and fuses lower-order semantic representations learned by TransR for knowledge enhancement,and finally predicts enterprise entity relationships by a convolutional decoder ConvE.Experimental results on the new energy automobile industrial knowledge graph show that KERP has better results in predicting the relationships between enterprises with a improvement of 6.7%in terms of F1 value compared with the existing models.Generalization is also evaluated on multiple datasets,and the experimental results demonstrate that KERP has good generality for generalized entity relationship prediction tasks.

Key words: Industrial knowledge graph, Enterprise entity relationship, Knowledge completion, Link prediction, Knowledge enhancement

中图分类号: 

  • TP391
[1]CHEN Z,WANG Y,ZHAO B,et al.Knowledge Graph Completion:A Review[J].IEEE Access,2020,8:192435-192456.
[2]LI F L,CHEN H,XU G,et al.AliMeKG:Domain knowledge graph construction and application in e-commerce[C]//Procee-dings of the 29th ACM International Conference on Information &Knowledge Management.2020:2581-2588.
[3]MOON C,JONES P,SAMATOVA N F.Learning Entity Type Embeddings for Knowledge Graph Completion[C]//Proceedings of the 2017 ACM on Conference on Information and Knowledge Management.2017:2215-2218.
[4]WANG J J,LIU J G,LI Z K.Research on Partnership of SupplyChain Based on Complex Network[J].Chinese Journal of Systems Science,2021,29(3):110-115130.
[5]LU Z Z,CHEN Q.Link Prediction of Enterprise Cooperation Relationship in Dynamic Supply Chain Network[J].Computer Engineering and Applications,2022,58(2):265-273.
[6]LIN Y,LIU Z,SUN M,et al.Learning entity and relation embeddings for knowledge graph completion[C]//Twenty-ninth AAAI Conference on Artificial Intelligence.2015.
[7]DETTMERS T,MINERVINI P,STENETORP P,et al.Convolutional 2d knowledge graph embeddings[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2018.
[8]ZHANG J Z,HU Y M.Uncovering the Mechanism of Co-Authorship Network Evolution by Link Prediction[J].Information Science,2017,35(7):75-81.
[9]LU Z G,CHEN Q.Discovering Potential Partners via Projec-tion-Based Link Prediction in the Supply Chain Network[J].International Journal of Computational Intelligence Systems,2020,13(1):1253-1264.
[10]XIE M,WANG T,JIANG Q,et al.Higher-Order NetworkStructure Embedding in Supply Chain Partner Link Prediction[C]//CCF Conference on Computer Supported Cooperative Work and Social Computing.Singapore:Springer,2019:3-17.
[11]KERSTING K,RAEDT L D.Adaptive Bayesian logic programs[C]//International Conference on Inductive Logic Programming.Berlin:Springer,2001:104-117.
[12]LAO N,COHEN W W.Relational retrieval using a combination of path-constrained random walks[J].Machine Learning,2010,81(1):53-67.
[13]WANG Q,MAO Z,WANG B,et al.Knowledge graph embedding:A survey of approaches and applications[J].IEEE Tran-sactions on Knowledge and Data Engineering,2017,29(12):2724-2743.
[14]BORDES A,USUNIER N,GARCIA-DURAN A,et al.Translating embeddings for modeling multi-relational data[C]//Proceedings of the 26th International Conference on Neural Information Processing Systems-Volume 2.2013:2787-2795.
[15]JI G,HE S,XU L,et al.Knowledge graph embedding via dy-namic mapping matrix[C]//Proceedings of the 53rd Annual Meeting of the Association for Computational Linguistics and the 7th International Joint Conference on Natural Language Processing(volume 1:Long papers).2015:687-696.
[16]NICKEL M,TRESP V,KRIEGEL H P.A three-way model for collective learning on multi-relational data[C]//ICML.2011.
[17]TROUILLON T,WELBL J,RIEDEL S,et al.Complex embeddings for simple link prediction[C]//International Conference on Machine Learning.PMLR,2016:2071-2080.
[18]GU J,WANG Z,KUEN J,et al.Recent advances in convolu-tional neural networks[J].Pattern Recognition,2018,77:354-377.
[19]NGUYEN D Q,NGUYEN T D,NGUYEN D Q,et al.A novel embedding model for knowledge base completion based on con-volutional neural network[J].arXiv:1712.02121,2017.
[20]SCHLICHTKRULL M,KIPF T N,BLOEM P,et al.Modeling relational data with graph convolutional networks[C]//Euro-pean Semantic Web Conference.Cham:Springer,2018:593-607.
[21]SHANG C,TANG Y,HUANG J,et al.End-to-end structure-aware convolutional networks for knowledge base completion[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2019:3060-3067.
[22]NATHANI D,CHAUHAN J,SHARMA C,et al.Learning attention-based embeddings for relation prediction in knowledge graphs[J].arXiv:1906.01195,2019.
[23]XIAO H,HUANG M,MENG L,et al.SSP:semantic space projection for knowledge graph embedding with text descriptions[C]//Thirty-First AAAI Conference on Artificial Intelligence.2017.
[24]XIE R,LIU Z,JIA J,et al.Representation learning of knowledge graphs with entity descriptions[C]//Proceedings of the AAAI Conference on Artificial Intelligence.2016.
[25]ZHANG Z,CAO L,CHEN X,et al.Representation learning of knowledge graphs with entity attributes[J].IEEE Access,2020,8:7435-7441.
[26]LIN Z F,OU S Y.Research on Relation Prediction in Know-ledge Graphs by Fusing Structure and Text Features[J].Libraryand Information Service,2020,64(21):99-110.
[27]ZHAI S P,WANG S H,SHANG D R,etal.An adaptive model for knowledge representation with entity description[J].Journal of Chinese Information Processing,2021,35(01):43-53.
[28]BLEI D M,NG A Y,JORDAN M I.Latent dirichlet allocation[J].Journal of Machine Learning Research,2003,3(Jan):993-1022.
[29]SUN X L,ZHUANG W H,LI B,et al.Research on Characteristics and Cooperation Prediction of Industry-University-Research lnstitute Collaboration Based on Patents inRegional Equipment Manufacturing Industry[J].Science and Management,2020,40(1):31-40.
[30]MIKOLOV T,CHEN K,CORRADO G,et al.Efficient estimation of word representations in vector space[J].arXiv:1301.3781,2013.
[31]VELICKOVIC P,CUCURULL G,CASANOVA A,et al.Graph Attention Networks[J].arXiv:1710.10903,2017.
[32]SUN Z,VASHISHTH S,SANYAL S,et al.A Re-evaluation of Knowledge Graph Completion Methods[C]//Proceedings of the 58th Annual Meeting of the Association for Computational Linguistics.2020:5516-5522.
[33]XU B,XU Y,LIANG J,et al.CN-DBpedia:A never-ending Chinese knowledge extraction system[C]//International Confe-rence on Industrial,Engineering and Other Applications of Applied Intelligent Systems.Springer,2017:428-438.
[34]KINGMA D P,BA J.Adam:A method for stochastic optimization[J].arXiv:1412.6980,2014.
Viewed
Full text


Abstract

Cited
  Shared   
  Discussed   
No Suggested Reading articles found!
渝ICP备16013121号-4
地址：重庆市渝北区洪湖西路18号    邮编：401121  
电话：023-63500828（编辑部） 023-67039612（会议/专题） 023-67039623（财务/发票）
E-mail：jsjkx12@163.com
本系统由北京玛格泰克科技发展有限公司设计开发