Recommendation method based on knowledge graph and long-term and short-term interests of user

Abstract

The invention discloses a recommendation method based on a knowledge graph and long and short term interests of a user, which comprises the following steps: acquiring an item set and mapping the item set to a general knowledge graph, and acquiring user-item interaction information; aggregating neighborhood entities by adopting an entity neighborhood aggregation mode based on the knowledge graph convolutional network to obtain project feature vector representation of the to-be-recommended project; learning user long-term preference vector representation through a preference propagation method; inputting interested items in the historical preference set of the user into a gating loop unit for training according to a time sequence to obtain short-term preference vector representation of the user; and overlapping and fusing the user long-term and short-term preference vector representations according to columns, performing full connection layer processing to obtain a final user preference vector representation, performing inner product calculation on the similarity of corresponding feature dimensions with the item feature vector representation of the to-be-recommended item, inputting the similarity into a multi-layer perceptron, and predicting the probability that the user is interested in the to-be-recommended item. The method improves the recommendation effect, and has the characteristics of high interpretability, strong adaptability and high precision.

Description

technical field [0001] The invention relates to a recommendation method based on knowledge graphs and users' long-term and short-term interests, and belongs to the technical field of recommendation systems. Background technique [0002] With more and more information on the Internet, people find it more and more difficult to find suitable and useful information from the massive Internet information. Under the background of massive information, the problem of "information overload" has appeared, and the huge data information has reduced the efficiency of people's use of information. [0003] In order to cope with the explosive growth of information, the development of business needs of Internet companies, and people's daily network application needs, personalized recommendations of commodities have appeared in the fields of shopping, news, and catering. Commonly used recommendation algorithms mainly include content-based recommendation methods and collaborative filtering-bas...

AI Technical Summary

Problems solved by technology

[0004] The technical problem to be solved by the present invention is to overcome the deficiencies of the prior art, provide a recommendation method based on the knowledge map and the user's long-term and short-term interests, introduce the knowledge map as auxiliary information, and the knowledge map contains a large number of item attribute information and item According to the structured relationship among them, item features can be extracted more deeply according to different attribute relationships, which can effectively alleviate the cold start problem and provide interpretability for the recommendation results. At the same time, two different interest extraction methods are used in different time dimensions to analyze user Long-term preferences and short-term preferences are modeled to extract user interests in a more fine-grained manner, which improves the recommendation effect and solves the problems of single user interest modeling methods and poor interpretability of recommendation results in traditional algorithms

Images