输变电设备运维知识图谱的构建及应用

针对电网公司在开展输变电设备运维检修过程中存在的非结构化文本数据难以利用、全口径数据难以深度融合、数据应用手段仍处于简单统计状态等难题,本文研究设计了基于知识图谱的输变电设备运维知识问答系统的总体框架,以打破传统信息获取方式的局限性。首先,从多源输变电设备数据中提取出实体、关系、属性等元素,涵盖的数据既有结构化也有非结构化的数据。在此过程中,使用不同的技术和方法来提取这些元素。其次,利用图形数据库Neo4j将这些元素组合在一起,构建一个完整的输电变电设备运维知识图谱,从而将不同类型和业务数据整合并形成一个连贯统一的知识网络。最后,基于Neo4j +Python平台搭建输变电设备运维知识问答系统,为运维人员提供一种新的方法。

Construction and application of power transmission and transformation equipment operation and maintenance knowledge graph

In response to the challenges faced by the power grid company in utilizing unstructured text data, deep integration of all-caliber data, and employing simple statistical methods for data analysis during the operation and maintenance of transmission and transformation equipment, this paper presents a comprehensive framework for a knowledge-based question-answering system for transmission equipment operation and maintenance based on a knowledge graph. The system breaks free from the limitations of traditional methods of information retrieval. Firstly, entities, relationships, attributes and other elements were extracted from various sources of transmission and transformation equipment data, including both structured and unstructured data, using various techniques and methods. Secondly, these elements were combined using the Neo4j graph database to create a complete knowledge graph for transmission and transformation equipment operation and maintenance, which unifies different types and business data into a coherent and unified knowledge network. Lastly, a question-answering system for transmission and transformation equipment operation and maintenance was built on the Neo4j + Python platform, providing a new approach for operating and maintaining personnel.