Electricity Knowledge Graph Construction Method Based On Grid Multi-Source Data

A method for constructing a power knowledge graph repeatedly collects multi-source data from the power grid. To address the issue of low confidence in the constructed knowledge graph, a construction method based on power grid multi-source data is designed. By setting up a multi-source data collection architecture for the physical power grid, the locally linear embedding algorithm is used to filter the repeatedly collected multi-source data. The relationships between power knowledge are transformed into identifiable feature values, and power knowledge is extracted from the multi-source data to divide the graph into hierarchical levels, thereby constructing the structure of the power knowledge graph.