Resource recommendation method and device, readable medium and equipment

Abstract

The invention discloses a resource recommendation method and device, a readable medium and equipment. The method comprises the steps of receiving a resource recommendation request of a target user; and inputting the current attribute information of the target user, the occasion information of the target user and the historical behavior information of the target user for each historical label into a resource recommendation model, and obtaining and outputting the behavior prediction probability of the target user for each historical label. As the resource recommendation model is obtained by training the neural network model according to the attribute information of the multiple users, the information of the occasions where the users are located, the historical behavior information of each user for each historical label and the actual feedback result; when predicting whether the target user clicks the historical label or not, the historical behaviors of the user on the historical labels are considered, and the occasion information and attribute information factors of the user are also considered, so that the behavior prediction probability of the target user on each historical label obtained by the resource recommendation model is more accurate compared with the prior art.

Description

technical field [0001] The present application relates to the technical field of data processing, and in particular to a resource recommendation method, device, readable medium and equipment. Background technique [0002] In the prior art, many softwares that provide users with resources such as news and videos, in order to increase the utilization rate of users, will continuously push the content that the user is interested in to the user through the recommendation system. Specifically, the recommendation system collects the user's behavior information, counts the n tags that the user clicks the most times, considers the counted n tags as the tags that the user is most interested in, and then recommends the n tags to the user. resource. [0003] In existing recommendation systems, resource recommendations are made to users based on the user's interest in tags. But in reality, the user's interest in a tag is not the only factor that affects the user's click behavior on a t...

AI Technical Summary

Problems solved by technology

Therefore, the current recommendation system only relies on the user's interest in tags to make recommendations, and the success rate of recommending resources for users is not high

Images