计算机工程与应用 ›› 2021, Vol. 57 ›› Issue (1): 261-270.DOI: 10.3778/j.issn.1002-8331.1910-0342

• 工程与应用 • 上一篇    下一篇

自定义SWRL知识图谱推理补全插件的实现

陈光,蒋同海,王蒙,唐新余,季文飞   

  1. 1.中国科学院 新疆理化技术研究所,乌鲁木齐 830011
    2.中国科学院大学,北京 100049
    3.新疆民族语音语言信息处理实验室,乌鲁木齐 830011
    4.江苏中科西北星信息科技有限公司,江苏 无锡 214135
  • 出版日期:2021-01-01 发布日期:2020-12-31

Custom SWRL Knowledge Graph Completion Reasoning Built-ins Implementation Method

CHEN Guang, JIANG Tonghai, WANG Meng, TANG Xinyu, JI Wenfei   

  1. 1.Xinjiang Technical Institute of Physics & Chemistry, Chinese Academic of Sciences, Urumqi 830011, China
    2.University of Chinese Academy of Sciences, Beijing 100049, China
    3.Xinjiang Laboratory of Minority Speech & Language Information Processing, Urumqi 830011, China
    4.Jiangsu CAS Nor-West Star Information Technology Co., Ltd., Wuxi, Jiangsu 214135, China
  • Online:2021-01-01 Published:2020-12-31

摘要:

知识图谱是人工智能应用的基石,基于规则进行推理是知识图谱知识补全的重要方式。SWRL推理插件的局限性成为了知识推理补全的瓶颈。打破了SWRL有限的推理能力,论述了在SWRL规则中编写自定义知识推理插件,并在知识图谱建模和推理工具中实现对自定义插件推理支持的方法。介绍了知识图谱知识建模和推理的方法与工具,结合一个具体的知识补全需求建模了包含自定义知识推理插件的SWRL推理规则;在Pellet推理机中实现和注入了此自定义推理插件的推理支持源码,并通过与Protégé知识建模工具进行集成从而完成知识补全需求;应用包含自定义插件的SWRL推理规则完成了老人健康小屋物联网系统资源组成和资源故障诊断的知识补全。以此论述了使用SWRL自定义知识推理插件进行知识图谱知识补全的方法和实践。

关键词: 知识图谱, 知识补全, 推理, SWRL语言, Proté, gé, 知识建模型工具, Pellet推理机, 自定义插件

Abstract:

Knowledge Graph(KG) is the cornerstone of AI application, and rule-based reasoning is still an important way to complete knowledge in KG. The limitation of SWRL reasoning built-ins has become the bottleneck of knowledge reasoning and complete. This paper breaks the limited reasoning ability of SWRL, and discusses the method of compiling custom knowledge reasoning built-ins in SWRL rules, and realizing reasoning support for these plug-ins in knowledge graph modeling and reasoning tools. Firstly, the paper introduces the methods and tools of knowledge modeling and reasoning in KG, and establishes SWRL reasoning rules including custom reasoning built-in with a specific knowledge completion requirement. Then, the reasoning support source code of this custom reasoning built-in is implemented and injected into Pellet reasoner, and is integrated with Protégé knowledge modeling tool to fulfill the requirement. Finally, the SWRL inference rules including the custom plug-ins are applied to complete the knowledge completion of the resource composition and resource fault diagnosis of the Internet of things system in the elderly healthy cabin. In this way, it discusses the method and practice of using SWRL custom reasoning built-ins to complete knowledge graph.

Key words: knowledge graph, knowledge complete, reasoning, Semantic Web Rule Language(SWRL), Protégé, knowledge modeling tool, Pellet reasoner, custom built-ins