User-generated work recommendation method, device, storage medium, program product

By acquiring UGC content and intent characteristics, and combining them with short-term and long-term player profiles, we have achieved accurate recommendation of UGC content in sandbox games. This solves the problems of superficial content understanding and insufficient interest matching in existing technologies, and improves recommendation accuracy and creators' exposure opportunities.

CN121513458BActive Publication Date: 2026-06-19MINI CREATIVE TECH (SHENZHEN) CO LTD
View PDF 3 Cites 0 Cited by

Patent Information

Authority / Receiving Office
CN · China
Patent Type
Patents(China)
Current Assignee / Owner
MINI CREATIVE TECH (SHENZHEN) CO LTD
Filing Date
2026-01-14
Publication Date
2026-06-19

AI Technical Summary

Technical Problem

Existing technologies for recommending user-generated content (UGC) in sandbox games fail to deeply understand the value of content and lack dynamic adaptation to player interests, making accurate recommendations difficult to achieve, resulting in high-quality content being buried and homogeneous content being overexposed.

Method used

By acquiring the content and intent features of user-generated works, combined with long-term and short-term profiles of game players, and employing feature normalization and matching score calculations, target works are accurately recommended.

Benefits of technology

It improved the accuracy of recommendations, solved the cold start problem for high-quality new works, reduced the push of homogeneous content, and enhanced the platform stickiness of game players and the creative enthusiasm of creators.

✦ Generated by Eureka AI based on patent content.

Smart Images

  • Figure CN121513458B_ABST
    Figure CN121513458B_ABST
Patent Text Reader

Abstract

This application discloses a method, device, storage medium, and program product for recommending user-generated works. The method includes: acquiring the characteristics of user-generated works, wherein the characteristics include content characteristics and intent characteristics; determining target works among the user-generated works based on the characteristics of the user-generated works and the player profile of the game player, and pushing them to the game player. The technical solution of this application constructs a recommendation method capable of deeply understanding the value of UGC content and dynamically adapting to the interests and needs of players, thereby achieving accurate recommendation of user-generated works.
Need to check novelty before this filing date? Find Prior Art