Object recommendation method and server

Abstract

The embodiment of the invention discloses an object recommendation method. The method of the embodiment of the invention comprises the following steps: acquiring first historical video information corresponding to an object in a first object set, wherein the object in the first object set is an object with incomplete user feature information; mapping the first historical video information to the user feature information of the corresponding object through a transform function, wherein the transform function is obtained through the user feature information corresponding to the object in a second object set and a mapping relationship of second historical video information corresponding to the object in the second object set, and the object in the second object set is an object with completeuser feature information; determining the similarity the objects corresponding to at least two pieces of user feature information according to the at least two pieces of user feature information; andperforming recommendation between the objects according to the similarity. The embodiment of the invention further provides a server for improving the accuracy of the object recommendation function.

Description

technical field [0001] The present application relates to the field of computer applications, in particular to a method and server for object recommendation. Background technique [0002] In the current Internet era, making friends is no longer exclusive to offline acquaintances. With the Internet as the background, through some applications, people can also establish online friendships between people, eliminating geographical restrictions, and making many like-minded people people become friends. [0003] At present, many social applications have a friend recommendation function. The system recommends friends for users, but the basis for recommending friends is based on a large amount of user characteristic information. User characteristic information can include user interests, hobbies, gender, region, etc., the current technology Among them, the method of obtaining user characteristic information is that the user is required to fill in a personal information form, and th...

AI Technical Summary

Problems solved by technology

[0003] At present, many social applications have a friend recommendation function. The system recommends friends for users, but the basis for recommending friends is based on a large amount of user characteristic information. User characteristic information can include user interests, hobbies, gender, region, etc., the current technology Among them, the method of obtaining user characteristic information is that the user is required to fill in a personal information form, and the user characteristic information is obtained through the personal information form filled in by the user. However, users are often unwilling to fill in these personal information or only fill in a small amount of personal information subjectively, thus Difficulty in obtaining user characteristic information

[0004] It is difficult to obtain user characteristic information, resulting in poor recommendation accuracy of friend recommendation function

Images