An information processing method and server

Abstract

The embodiment of the present invention discloses an information processing method and a server. The method includes: obtaining the first historical behavior data obtained by the first user performing operations on the terminal; performing feature construction according to the first historical behavior data to generate the first feature matrix, the first feature matrix is ​​used to represent the correspondence between the first user and the first information; the first feature matrix is ​​compressed according to the first preset rule to generate a second signature matrix, and the second signature matrix is ​​used to represent The minimum hash value corresponding to the second historical behavior data, the second historical behavior data is obtained after the first historical behavior data is compressed; the second signature matrix is ​​processed according to the second preset rule to generate the first model , the first model is used to represent the degree of correlation between the second historical behavior data; the current behavior data of the second user is obtained, and the current behavior data is input into the first model to obtain the associated data associated with the first user.

Description

technical field [0001] The invention relates to the Internet technology in the communication field, in particular to an information processing method and a server. Background technique [0002] With the rapid development of communication technology, the functions and intelligence of the client are becoming more and more abundant. When the user is performing business applications through the client, such as playing a video through a video application installed on the client, send a playback request or request to download the video The server will collect these business requests, and send related information to the client according to the business request, and the client can intelligently recommend related media information (such as a variety show) to the user through the related information. video or TV drama video) or user information, so that users can choose more relevant media information of interest or information about associated users with the same hobbies. For example...

AI Technical Summary

Problems solved by technology

[0004] However, in the prior art method, the server uses prior knowledge to fix or determine the user or item candidate set, when the number of matching users or items in the user or item candidate set is large, the workload of the server to calculate the similarity is Very large, it takes a lot of time, resulting in low time efficiency, and due to the limitations and limitations of the server's prior knowledge, it affects the accuracy of the server in determining similar items or users

Images