Information pushing method and device, equipment and storage medium

Abstract

The invention provides an information pushing method and device, equipment and a storage medium, and the method comprises the steps: obtaining a scene model corresponding to a recommendation scene currently displayed by a client, estimating a product preferred by a user in the recommendation scene according to the scene model corresponding to the recommendation scene, and recommending the information of the product preferred by the user in the recommendation scene. In the method, the product preferred by the user in each recommendation scene is estimated by using the scene model obtained by training the joint data of the plurality of recommendation scenes and the scene tasks, so that data sharing of different recommendation scenes can be realized, the relevance between the scene tasks in different recommendation scenes is fully considered, the actual condition of user feedback data is better met, the product preference of the user can be more accurately estimated, and the information recommendation effect is improved.

Description

Technical field [0001] This application relates to the field of machine learning, and in particular, to one information push method, device, device, and storage medium. Background technique [0002] With the development of big data and machine learning technology, it is applied in the field of personalized recommendation technology. Personalized recommendation refers to the analysis of users' preferences by mining the historical behavior of users, so that they can recommend them to users through the client's recommended page. Its preferences and products, etc. [0003] In the prior art, click the CTR, CLICK-THROUGH-RATE predictive model to be widely used in personalized recommendation systems, and the CTR estimate model is used to learn and predict users' feedback, by collecting massive training expectations. Learning training, predict information and product of user preferences. [0004] However, in the multi-recommended scenario, there is interrelationship between different sce...

AI Technical Summary

Problems solved by technology

[0005] This application provides an information push method, device, device and storage medium, which are used to solve the problem that the existing estimation model cannot accurately push user-preferred information and products in a multi-recommendation scenario

Images