公开(公告)号：US12132795B2

公开(公告)日：2024-10-29

申请号：US17948082

申请日：2022-09-19

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Xiaobo Hao ,  Kaikai Ge ,  Yudan Liu ,  Linyao Tang ,  Xu Zhang ,  Ruobing Xie ,  Leyu Lin

IPC分类号： G06F16/9535 ,  H04L67/50

CPC分类号： H04L67/535 ,  G06F16/9535

摘要： Embodiments of this application disclose a data recommendation method performed by a computer device. The data recommendation method includes: obtaining a service object set associated with a target user in a plurality of fields in response to a data recommendation request for the target user in a target field, performing cross-field cross-encoding on the plurality of fields and the service object set to obtain a target field interest feature of the target user in the target field; obtaining to-be-recommended service object features of a plurality of to-be-recommended service objects in the target field; and obtaining a target to-be-recommended service object feature matching with the target field interest feature of the target user from the to-be-recommended service object features, and returning a target to-be-recommended service object corresponding to the target to-be-recommended service object feature to the target user.

公开(公告)号：US20210326674A1

公开(公告)日：2021-10-21

申请号：US17362887

申请日：2021-06-29

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Yudan Liu ,  Kaikai Ge ,  Xu Zhang ,  Leyu Lin ,  Xin Chen ,  Xiaobo Hao ,  Wei Wang ,  Kai Zhuang ,  Su Yan ,  Zhida Pan ,  Linyao Tang ,  Jing Zhang

IPC分类号： G06N3/04 ,  G06N3/08

摘要： 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.

公开(公告)号：US20230017667A1

公开(公告)日：2023-01-19

申请号：US17948082

申请日：2022-09-19

申请人： Tencent Technology (Shenzhen) Company Limited

发明人： Xiaobo Hao ,  Kaikai Ge ,  Yudan Liu ,  Linyao Tang ,  Xu Zhang ,  Ruobing Xie ,  Leyu Lin

IPC分类号： H04L67/50 ,  G06F16/9535

摘要： Embodiments of this application disclose a data recommendation method performed by a computer device. The data recommendation method includes: obtaining a service object set associated with a target user in a plurality of fields in response to a data recommendation request for the target user in a target field, performing cross-field cross-encoding on the plurality of fields and the service object set to obtain a target field interest feature of the target user in the target field; obtaining to-be-recommended service object features of a plurality of to-be-recommended service objects in the target field; and obtaining a target to-be-recommended service object feature matching with the target field interest feature of the target user from the to-be-recommended service object features, and returning a target to-be-recommended service object corresponding to the target to-be-recommended service object feature to the target user.