首页 | 本学科首页   官方微博 | 高级检索  
     

领域知识图谱快速构建和应用框架
引用本文:于皓,张杰,吴明辉,吴信东.领域知识图谱快速构建和应用框架[J].智能系统学报,2021,16(5):871-884.
作者姓名:于皓  张杰  吴明辉  吴信东
作者单位:明略科技集团,北京 110000
摘    要:快速构建和应用领域知识图谱(domain knowledge graphs, DKG)已成为企业的迫切需求。然而,领域知识图谱的快速构建和应用仍然存在问题:1)构建前,复杂领域场景涉及知识维度广,业务专家短时间内难以构建完备的领域schema;2)构建中,业务和技术专家深度耦合,图谱构建缓慢,难以适应业务快速发展需求;3)构建后,图谱应用严重依赖技术人员开发,业务专家无法自主基于领域知识图谱探索问题解决方案。为解决上述问题,本文提出了领域知识图谱的快速构建和应用框架,其中包括:多人协作构建领域schema解决领域知识的复杂性问题,将业务和技术专家解耦合,提高领域知识图谱的构建效率,最后通过建立基于行业schema的auto-KBQA((knowledge base question answering)解决领域知识图谱在知识问答应用的快速落地。通过实际项目的应用落地,验证了该框架可有效加快领域知识图谱的落地应用,期望该框架给领域知识图谱的快速构建和应用带来一定的启发和帮助。

关 键 词:领域知识图谱  schema  实体链指  知识补全  KBQA  多人协作  业务专家  技术专家

A framework for rapid construction and application of domain knowledge graphs
YU Hao,ZHANG Jie,WU Minghui,WU Xindong.A framework for rapid construction and application of domain knowledge graphs[J].CAAL Transactions on Intelligent Systems,2021,16(5):871-884.
Authors:YU Hao  ZHANG Jie  WU Minghui  WU Xindong
Affiliation:Mininglamp Technology, Beijing 110000, China
Abstract:There is an urgent need for enterprises to rapidly construct and apply domain knowledge graphs (DKG). However, there are still problems in meeting this need: firstly, extensive knowledge is required to deal with complex domain scenarios and it is difficult for business experts to rapidly construct a complete domain schema; secondly, the construction process is so slow that it’s difficult to meet the needs of rapid business development, because information exchanges are ambiguous between business experts and technical experts; thirdly, after their construction, the heavy dependence of the applications of graphs on technical personnel refrains business experts from exploring approaches to solving business problems. In order to solve the above problems, this paper proposes a framework for the rapid construction and applications of DKG. It builds a domain schema through multiple-person cooperation to solve complex problems and improves the construction efficiency by decoupling business experts and technical experts in the construction and applications of DKG. Finally, it builds the schema-based auto-KBQA((knowledge base question answering) for fast applications of DKG in question and answering mode. Through real-world applications, it is verified that the framework can effectively accelerate the construction and applications of DKG. The framework is expected to bring insights and extend assistance to the rapid construction and application of DKG.
Keywords:domain knowledge graph  schema  entity linking  knowledge completion  KBQA  multiple-person cooperation  business experts  technical experts
点击此处可从《智能系统学报》浏览原始摘要信息
点击此处可从《智能系统学报》下载全文
设为首页 | 免责声明 | 关于勤云 | 加入收藏

Copyright©北京勤云科技发展有限公司  京ICP备09084417号