Recommendation model based on knowledge graph and recurrent neural network

Abstract

The invention discloses a recommendation model based on a knowledge graph and a recurrent neural network. The recommendation model comprises a knowledge graph feature learning module, a diffusion preference set and a recurrent neural network recommendation module. The knowledge graph feature learning module learns each entity and relationship in the knowledge graph to obtain a low-dimensional vector; the diffusion preference set comprises h + 1 layers of diffusion preference sets, wherein h is the number of diffusion layers; each layer of adjacent diffusion preference sets are connected through a knowledge graph, and the recurrent neural network recommendation module learns the diffusion preference set of the user, obtains a deeper user preference representation containing more useful information, and is used for subsequently predicting the probability that the user likes a certain article. The diffusion preference set of the user is acquired by using the knowledge graph and the preference diffusion idea, and the diffusion preference set is used as the input of the recurrent neural network to learn the deeper user preference feature representation for subsequently predicting the probability that the user likes a certain article.

Description

technical field [0001] The invention relates to the field of big data recommendation models, in particular to a recommendation model based on knowledge graphs and cyclic neural networks. Background technique [0002] The recommendation system can learn the user's interests and preferences based on the user's attribute files and historical behavior records, and select the parts that the user may be interested in from the massive content and recommend them to the user, which solves the problem of information overload in the era of big data and improves the user experience. User experience is widely used in news, movies, books and other online content and service platforms. Collaborative filtering recommendation is currently the most widely used recommendation method. It is based on the user's preference for items, discovers the relevance of the item itself, and recommends relevant items for the user; or discovers the user's relevance, and then uses the user's preference items...

AI Technical Summary

Problems solved by technology

The advantage of this type of method is that it fully and intuitively utilizes the network structure of the knowledge graph. The disadvantage is that it is necessary to manually design the meta-path or meta-graph, making it difficult to optimize the model in practice.

Images