摘要
为解决和缓解甲骨学研究难度大、周期长、知识关联性弱、知识共享程度低等问题。基于多源异构数据源,融合基于文献计量学的科学知识图谱(MKD)和基于知识库的知识图谱(KG),构建了甲骨学融合知识图谱。通过融合两类知识图谱,并基于知识推理进行语义扩展,形成最终的甲骨学知识图谱。其中包含实体148 305个,关系434032条,可满足甲骨学研究的基本需求。融合MKD和KG两类知识图谱,优势互补,实现甲骨学知识图谱构建,可为其他古籍类知识图谱构建提供借鉴。
In order to solve or alleviate the problems such as great difficulty, long period, weak knowledge linking and low sharing regarding the oracle bone studies, we construct the oracle bone studies knowledge graph by combining two kinds of knowledge graphs MKD and KG.These two kinds of knowledge graphs are fused and semantic extension is carried out based on knowledge reasoning. The constructed oracle bone studies knowledge graph contains 148 305 entities and 434 032 relations, which can meet the basic needs of oracle bone studies research. It also provides reference for other ancient books knowledge graph construction.
作者
熊晶
焦清局
刘运通
XIONG Jing;JIAO Qingju;LIU Yuntong(School of Computer&Information Engineering,Anyang Normal University,Anyang 455000,Henan Province,China;Key Laboratory of Oracle Bone Inscriptions Information Processing,Ministry of Education,Anyang 455000,Henan Province,China)
出处
《浙江大学学报（理学版）》
CAS
CSCD
北大核心
2020年第2期131-141,150,共12页
Journal of Zhejiang University（Science Edition）
基金
国家自然科学基金资助项目(U1504612,61806007)
教育部、国家语委甲骨文等古文字研究与应用专项(YWZ-J023,YWZJ010)
河南省科技发展计划项目(182102310039)
河南省高校重点科研项目(17A520002,18A520002).
关键词
甲骨学
知识图谱
知识推理
知识融合
oracle bone studies
knowledge graph
knowledge reasoning
knowledge fusion
