Method, device, server and storage medium for generating training samples

Abstract

The invention relates to a training sample generation method, device and system, a server and a storage medium. The method can comprise the steps that a display event reported through an application program interface is received, the display event is generated and reported when a recommendation list is sent to an account application, and the recommendation list comprises a plurality of recommendation objects sent to an account; in response to the received display event, account feature information of an account and object feature information of an object involved in the recommendation list areacquired from an account information system, and the account feature information and the object feature information are stored in the account information system when the recommendation list is generated; the account feature information and the object feature information are spliced with corresponding label information to generate a training sample; the training sample is output. According to theembodiment of the invention, the training sample can be generated in real time, so as to improve the real-time performance and accuracy of the recommendation model.

Description

technical field [0001] The present disclosure relates to the field of Internet information processing, and in particular to a method, device, server and storage medium for generating training samples. Background technique [0002] With the gradual enrichment of Internet content, major websites will establish recommendation systems to enable accounts to quickly and accurately find their favorite content based on the information recommended by the recommendation system. [0003] The recommendation system can train the recommendation model through machine learning. Among them, it can be based on the specific behavior of the account in the Internet application (such as clicking, liking, following, etc.), and the objects of these behaviors (such as commodities, videos, news, etc.) A training sample for training the recommendation model is generated. [0004] In related technologies, when generating training samples, it is necessary to collect historical behavior information of a...

AI Technical Summary

Problems solved by technology

[0005] The present disclosure provides a method, device, server and storage medium for generating training samples, so as to at least solve the problem in related technologies that the recommendation model can only be trained according to account historical behavior information, thereby affecting the accuracy of the recommendation model

Images