基于知识图谱的语义融合模型构建方法研究  

Research on Construction Method of Semantic Fusion Model Based on Knowledge Map

作　　者：柴雁欣 李学龄 萧展辉 耿豫杰 张晓光 CHAI Yanxin;LI Xueing;XIAO Zhanhui;GENG Yujie;ZHANG Xiaoguang(China Southern Power Grid Digital Power Grid Research Institute Co.,Ltd.,Guangzhou 510000,China)

机构地区：[1]南方电网数字电网研究院有限公司,广东广州510000

出　　处：《自动化仪表》2024年第6期83-87,共5页Process Automation Instrumentation

基　　金：广东电网有限责任公司数字电网关键技术(国重配套)基金资助项目(JY-KF-03-GX-21-016)。

摘　　要：知识图谱具有良好的指标描述性能与解释能力。为了有效分析数字电网的业务全生命周期数据、形成以知识为导向的新型电网运维管理模式,开展了基于知识图谱的语义融合模型构建方法的研究。首先,构建基于物联网的电网数字模型,汇总数字电网信息。其次,针对数字电网,采用Protégé软件,通过七步法构建数字电网本体。最后,基于本体,采用自顶向下的方式生成知识图谱。基于上述建模方法,将知识图谱与模式识别相结合,设计一套语义提取框架。根据数字电网模型信息(图像、声音、文本等)提取的原子概念检测本体,推理出更高层次的复合语义特征。基于所获取的语义特征,结合知识图谱,试点数字电网信息语义融合,为推动统一模型的构建提供实践参考。Knowledge map has good indicator description performance and interpretation ability.To effectively analyze the business full life cycle data of the digital grid and form a new knowledge-oriented grid operation and maintenance management mode,the research on semantic fusion model construction method based on knowledge map is carried out.Firstly,a digital model of the grid based on the Internet of Things is constructed to summarize the information of the digital grid.Secondly,for the digital grid,Protégésoftware is used to construct an ontology of the digital grid through a seven-step approach.Finally,based on the ontology,a top-down approach is used to generate a knowledge map.Based on the above modeling method,a set of semantic extraction framework is designed by combining the knowledge map with pattern recognition.Based on the atomic concept detection ontology extracted from the digital grid model information(image,sound,text,etc.),higher-level composite semantic features are inferred.Based on the acquired semantic features,combined with knowledge map,pilot the semantic fusion of digital grid information to provide a practical reference to promote the construction of a unified model.

关 键 词：数字电网 知识图谱 语义融合 信息本体 语义提取 物联网 

分 类 号：TH-39[机械工程]