Recommendation method based on knowledge graph and deep learning

The invention discloses a recommendation method based on a knowledge graph and deep learning, and belongs to the field of data recommendation, and the recommendation method comprises the following specific steps: (1) collecting movie information for definition recording; (2) constructing a knowledge graph according to each group of data; (3) constructing a related recommendation model based on the knowledge graph; (4) designing a recommendation function and carrying out modular division; by constructing the movie domain knowledge graph, the performance of a recommendation system can be improved, the accuracy of similarity calculation between movies in the recommendation process can be improved, people can be helped to filter out a large amount of useless information, people can quickly obtain movies wanted to be watched from a large amount of information, and the movie recommendation efficiency is improved. And the movie most likely to be favorite by the user is judged through the score to be recommended to t