Content recommendation method and apparatus, device, and storage medium

US12314832B2 · kind B2 · utility

Assignee

• TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED · CN

Inventors

• Yudan Liu · Lo Wu, CN
• Kaikai Ge · Lo Wu, CN
• Xu Zhang · Beijing, CN
• Leyu Lin · Lo Wu, CN
• Xin Chen · Tangxia, CN
• Xiaobo HAO · Beijing, CN
• Wei Wang · Nanhu, CN
• Kai Zhuang · Lo Wu, CN
• Su Yan · Tangxia, CN
• Zhida Pan · Shanghai, CN
• Linyao Tang · Lo Wu, CN
• Jing Zhang · Shanghai, CN

Key dates

• Filing date: Jun 29, 2021
• Grant date: May 27, 2025
• Expiry date: Feb 28, 2044

Classification

• Technology area (CPC G): Physics
• CPC primary: G06N3/045
• WIPO field: Computer technology
• WIPO sector: Electrical engineering

Abstract

This application discloses a content recommendation method performed at a computer device and belongs to the field of artificial intelligence. The method includes: acquiring a target user vector of a target user; determining n groups of seed user vectors according to the target user vector, each group of seed user vectors corresponding to a respective piece of candidate recommendation content; invoking a look-alike model to calculate a similarity between the target user vector and each group of seed user vectors, the look-alike model being used for calculating a similarity between user vectors based on an attention mechanism; and determining, among the n pieces of candidate recommendation content, target content to be recommended to the target user according to the respective similarities of the corresponding n groups of seed user vectors. This application can resolve a problem of relatively low accuracy of a recommendation method in the related art.