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