Model generation method and device, recommendation method and device

Abstract

Embodiments of the present invention provide a model generation method and device, and a recommendation method and device. On the one hand, in the model generation method of the embodiment of the present invention, by obtaining the document content feature vector of each entity in the knowledge graph, the logical association relationship feature vector between each entity, the user behavior relationship feature vector of each entity, and the feature of each entity At least one of the vectors; thus, machine learning is performed according to at least one of the document content feature vector, the logical association relationship feature vector, the user behavior relationship feature vector, and the feature vector to generate a deep fusion model. Therefore, the technical solution provided by the embodiment of the present invention can generate a deep fusion model by integrating various relationships between entities. The deep fusion model can be used to obtain the degree of surprise between entities, so that entities can be recommended to users based on the degree of surprise, satisfying It meets the user's search and recommendation needs and improves the click-through rate of recommended entities.

Description

【Technical field】 [0001] The present invention relates to the field of search technology, in particular to a model generation method and device, and a recommendation method and device. 【Background technique】 [0002] At present, when the search recommendation is performed, it is based on satisfying the user's main search demand, and stimulating the potential demand of the user by providing the user with other potentially interesting content related to the query word. For example, please refer to figure 1 , which is the first example of search recommendation based on knowledge graphs in the prior art. As shown in the figure, when a user queries "Princeton University", it can be recommended in the non-search result area of ​​the search result page figure 1 Notable alumni of Princeton University shown, this is a recommended entity that is very relevant to the query term "Princeton University". [0003] However, in the prior art, when searching and recommending based on knowle...

AI Technical Summary

Problems solved by technology

[0003] However, in the prior art, when searching and recommending based on knowledge graphs, the recommended entities are often well-known and cannot arouse user interest.

Therefore, this search recommendation method cannot meet the user's search and recommendation needs, resulting in a relatively low click-through rate for recommended entities.

Images