Data processing method and device

Abstract

The invention discloses a data processing method and device, and relates to the technical field of computers. A specific embodiment of the method comprises the steps of generating an embedding vector, a behavior embedding vector and an interest evolution embedding vector of a target user and an embedding vector of a target article according to behavior characteristics and basic characteristics of the target user and behavior characteristics and basic characteristics of the target article; splicing the embedding vector of the target user, the behavior embedding vector, the interest evolution embedding vector and the embedding vector of the target article into a combined embedding vector of the target user; and inputting the combined embedding vector of the target user into a pre-trained calculation model so as to output the behavior probability of the target user to the target article. According to the embodiment, the technical problems that the hidden vector table between the user and the article cannot be accurately and efficiently mined, and the long-term, middle-term and recent interest changes of the user cannot be distinguished can be solved.

Description

technical field [0001] The present invention relates to the field of computer technology, in particular to a method and device for processing data. Background technique [0002] Personalized sorting is a technology that uses machine learning and deep learning algorithms to present personalized push results to users in different application scenarios based on the user's personalized characteristics. The most important purpose of this technology is to present to users the items with the highest priority in the hearts of very few users from a large number of candidate sets. [0003] In the course of realizing the present invention, the inventor finds that there are at least the following problems in the prior art: [0004] It is impossible to accurately and efficiently mine the implicit vector table between users and items, and it is impossible to distinguish the long-term, medium-term and short-term interest changes of users, resulting in inaccurate calculation results. Con...

AI Technical Summary

Problems solved by technology

[0005] In view of this, the embodiments of the present invention provide a method and device for processing data to solve the problem of the inability to accurately and efficiently mine the implicit vector representation between users and items, and the inability to distinguish between long-term, medium-term and short-term interest changes of users technical issues

Images