Hierarchical representation learning of user interests

• Main Authors: ZHANG XINGYAO, GONG MING, JIANG DAXIN, SHOU LINJUN
• Format: Patent
• Language: Chinese; English
• Published: 31.03.2023
• Subjects: CALCULATING; COMPUTER SYSTEMS BASED ON SPECIFIC COMPUTATIONAL MODELS; COMPUTING; COUNTING; ELECTRIC DIGITAL DATA PROCESSING; PHYSICS

The present disclosure presents a method, an apparatus, and a computer program product for hierarchical representation learning of user interests. A sequence of historical content items of a user may be obtained. The subject and text of each historical content item in the sequence of historical content items may be identified to obtain a subject sequence and a text sequence corresponding to the sequence of historical content items. A comprehensive topic representation may be generated based on the sequence of topics. A synthetic text representation may be generated based on the text sequence. A user interest representation of the user may be generated based on the synthetic topic representation and the synthetic textual representation. 本公开提出了用于用户兴趣的分层表示学习的方法、装置和计算机程序产品。可以获得用户的历史内容项序列。可以识别所述历史内容项序列中的每个历史内容项的主题和文本，以获得与所述历史内容项序列相对应的主题序列和文本序列。可以基于所述主题序列来生成综合主题表示。可以基于所述文本序列来生成综合文本表示。可以基于所述综合主题表示和所述综合文本表示来生成所述用户的用户兴趣表示。