User classification method and device, storage medium and computer equipment

Abstract

The invention relates to a user classification method and apparatus, a storage medium and a computer device. The method comprises the steps of obtaining a user request received by a voice module; analyzing the user request to obtain function information of using the intelligent device by the target user; acquiring scene information of using the intelligent device by the target user according to the position of the voice module; constructing a target user vector according to the scene information and the function information; respectively calculating the target user vector and a plurality of different standard user vectors to obtain a plurality of corresponding cosine similarities; taking the standard user corresponding to the maximum cosine similarity as a target standard user; and takingthe user label corresponding to the target standard user as the classification label of the target user. Through the technical scheme of the invention, the type of the target user can be accurately obtained, and the method is applied to personalized pushing and other services.

Description

technical field [0001] The present application relates to the field of computer technology, and in particular to a user classification method, device, storage medium, and computer equipment. Background technique [0002] With the advent of the era of intelligence, there are more and more user data, and it is imperative to identify user categories based on a large amount of data. Identifying the category of the user is of great significance to the subsequent business. For example, functions such as personalized recommendation and personalized service can be realized according to the category of the user. In the prior art, the user attribute is determined through the user's registration information or browsing information, and the user category cannot be accurately confirmed, so that accurate push cannot be realized. At the same time, for the user, the amount of spam information is too large and the user experience is poor. Contents of the invention [0003] In order to sol...

AI Technical Summary

Problems solved by technology

In the prior art, the user attribute is determined through the user's registration information or browsing information, and the user category cannot be accurately confirmed, so that accurate push cannot be realized. At the same time, for the user, the amount of spam information is too large and the user experience is poor.

Images