Abstract: To solve the problems that the business data in state grid corporation cannot be crossed professionally, and the data resources cannot be intelligently analyzed and managed, this paper proposes a knowledge graph construction method based on the full-service unified data center. On the basis of multi-source data in the full-service unified data center collected by the big data technology, the semantic annotation method is used to extract the knowledge entities, attributions and relations from the structured, semi-structured and unstructured data. The knowledge graph is constructed through the knowledge fusion technology. The accurate result and related information can be returned intelligently according to the user’s search. Experiments show that this method improves the precision and recall rate, and has better intelligent search and analysis ability.

Key words: knowledge graph, full-service data center, knowledge fusion, big data, multi-source data

摘要： 针对国网公司的业务数据无法跨专业贯通，数据资源无法被智能分析与管理等问题，提出基于全业务统一数据中心的知识图谱构建方法。在全业务统一数据中心使用大数据技术采集电网多源数据的基础上，使用语义标注方法对结构化、半结构化、非结构化数据进行知识抽取获得知识实体、属性和关系，通过知识融合技术构建知识图谱，根据用户搜索内容智能推荐结果和相关信息。实验表明该方法提高了查准率和召回率，具有更好的智能搜索和分析能力。

关键词: 知识图谱, 全业务统一数据中心, 知识融合, 大数据, 多源数据