Content recommendation method based on domain knowledge graph

Abstract

The invention provides a content recommendation method based on a domain knowledge graph, and the method comprises the steps: inputting historical click contents of a user into a candidate content generation model based on entity representation, and generating first candidate contents which the user may be interested in; generating a content representation vector based on a content representationlearning model of knowledge graph interest sampling; according to the content representation vector, obtaining click probability distribution of the user to the content, and generating second candidate content which the user may be interested in; and sorting each content in the first candidate content and the second candidate content to obtain a content recommendation list. The knowledge graph-based content recommendation method has the advantages that the relationship between the contents can be established through the knowledge graph, so that the contents recommended to the user have an association relationship with the historical click contents of the user, and the recommendation result is more interpretable. According to the method, the content cold start problem can be solved, and meanwhile, the recommendation performance is improved under the condition of lack of user historical behavior data.

Description

technical field [0001] The invention belongs to the technical field of information processing, and in particular relates to a content recommendation method based on a domain knowledge map. Background technique [0002] In recent years, with the rapid development of the Internet and big data technology, people are faced with the challenge of quickly finding effective information in massive amounts of information. The recommendation system can help people filter information effectively by analyzing people's historical behavior, and recommend their favorite information for users. information of interest. [0003] Existing recommendation methods are generally divided into two types: 1. Use collaborative filtering to establish the similarity relationship between users, or the similarity relationship between content and content, and then recommend content similar to their historical viewing for users . 2. Encode the content and user historical behavior, and then use deep learnin...

AI Technical Summary

Problems solved by technology

[0004] The above two methods have the following problems: On the one hand, a large amount of user historical behavior data is required, and in the absence of user historical behavior data, there is a problem of cold start

On the other hand, the above method only uses user historical behavior data or data label information, lacks content-related multi-source features, has poor ability to mine potential interests of users, and has great limitations in recommending content

In addition, the features used by the above two methods are sparse, resulting in poor recommendation results and high computational resource consumption

Images