User searching method and device

Abstract

The embodiment of the invention provides a user searching method and device, and relates to the technical field of internet application. The method comprises the steps that target representation characteristics generated based on static characteristics and dynamic characteristics of a target user are obtained, wherein the static characteristics are characteristics which are not changed along with the behavior that the user participating in the network behavior; the dynamic characteristics are characteristics changing along with the user participating in the network behavior; calculating the similarity between the target representation characteristics and representation characteristics of existing users stored in a user feature library, wherein the representation characteristics of the existing users are characteristics obtained based on static characteristics, static relations, dynamic characteristics and dynamic relations of the existing users; and searching associated users of the target user in the existing users according to a sequence of the calculated similarities from high to low. When the scheme provided by the embodiment of the invention is applied to search the user, the accuracy of the searched associated user can be improved.

Description

technical field [0001] The invention relates to the technical field of Internet applications, in particular to a user search method and device. Background technique [0002] In different scenarios, service providers can provide services to users belonging to the same category according to the same policy. For example, in the information push scenario, the same information can be pushed for users belonging to the same category; in the black industry user processing scenario, the same information shielding strategy can be used for black industry users to block information. [0003] In view of the above, for a single user, it is possible to search for associated users of the user according to the category to which the user belongs and the categories to which other users belong, and then provide services for the user based on the information of the associated users. [0004] In the prior art, the classification of users is generally determined based on the classification model,...

AI Technical Summary

Problems solved by technology

[0004] In the prior art, the classification of users is generally determined based on the classification model, but due to factors such as the richness of the sample data and the amount of data, the accuracy of user classification using the trained classification model is low, which leads to low accuracy when searching for users. , the accuracy of the searched associated users is low

Images