Knowledge graph acquisition method based on deep learning

The invention discloses a knowledge graph acquisition method based on deep learning, and the method comprises the steps: obtaining heterogeneous data, and dividing the heterogeneous data into N piecesof structural data, where N is an integer greater than 1; correspondingly processing the N structural data according to a natural language processing technology to obtain a word vector; inputting theword vector into a graph neural network model to obtain a first knowledge graph; and processing the first knowledge graph according to a clustering method and a bag-of-words model to obtain a secondknowledge graph. Compared with a traditional self-supervision mode, the method is more flexible, different data sources can use different methods, selection can also be performed according to different demand deviations and scene features, the advantages of each method are highlighted to the maximum extent, the cost is better reduced, and the result accuracy is improved. 本发明公开了一种基于深度学习的知识图谱获取方法，包括获取异构数据，将所述异构数据划分为N个结构数据，其中，