Abstract: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.