Research on Construction and Application of Regulation of the Multiple Energy Systems Based on Knowledge Graph

Abstract

In this paper, A knowledge graph construction method for regulation of the multiple energy systems combining top-down and bottom-up is proposed. Firstly, define the schema layer of the graph from top to bottom; and then, use different deep learning models to perform knowledge extraction and knowledge fusion on the resource plan, and build the data layer of the graph from the bottom up: the TextCNN model is used to classify the text of the plan, and LR-CNN model is used to named entities recognition for the plan; on the basis of named entity recognition, BERT-BILSTM-CRF model is used to extract the relationship between the named entities. Next, extract the corresponding triples to realize the construction of knowledge graph. Finally, the graph database is used to store and visualize the knowledge graph, and a case of the application process of the knowledge graph is studied. Compared with the traditional text retrieval method, the proposed method improves the decision-making efficiency and decision-making accuracy of multiple energy systems staff and users.