基于知识增强的企业实体关系预测模型  

Knowledge Enhanced Relationship Prediction Model for Enterprise Entities

作　　者：王家祺 李文根 关佶红[1] 邢婷 魏小敏 邵冰清 付宠洁 WANG Jiaqi;LI Wengen;GUAN Jihong;XING Ting;WEI Xiaomin;SHAO Bingqing;FU Chongjie(College of Electronic and Information Engineering,Tongji University,Shanghai 201804,China;Beijing Shangqi Digital Technology Co.,Ltd.,Beijing 100084,China)

机构地区：[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

出　　处：《计算机科学》2023年第10期146-155,共10页Computer Science

基　　金：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)。

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。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.

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 

分 类 号：TP391[自动化与计算机技术—计算机应用技术]