公开(公告)号：US12067607B2

公开(公告)日：2024-08-20

申请号：US18167961

申请日：2023-02-13

申请人： YAHOO ASSETS LLC

发明人： Suleyman Cetintas ,  Xian Wu ,  Jian Yang

IPC分类号： G06Q30/00 ,  G06F16/22 ,  G06F16/901 ,  G06F16/9535 ,  G06N20/00 ,  G06Q10/087 ,  G06Q30/0204 ,  G06Q30/0282 ,  G06Q30/0601 ,  G06Q50/00

CPC分类号： G06Q30/0631 ,  G06F16/2237 ,  G06F16/2264 ,  G06F16/9024 ,  G06F16/9535 ,  G06N20/00 ,  G06Q10/087 ,  G06Q30/0204 ,  G06Q30/0282 ,  G06Q30/0625 ,  G06Q50/01

摘要： Disclosed are systems and methods utilizing neural contextual bandit for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to make item recommendations using latent relations and latent representations, which can improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods use neural network modeling in automatic selection of a number of items for recommendation to a user and using feedback in connection with the recommendation for further training of the model(s).

公开(公告)号：US11587143B2

公开(公告)日：2023-02-21

申请号：US17466879

申请日：2021-09-03

申请人： YAHOO ASSETS LLC

发明人： Suleyman Cetintas ,  Xian Wu ,  Jian Yang

IPC分类号： G06Q30/00 ,  G06Q30/0601 ,  G06F16/9535 ,  G06F16/901 ,  G06F16/22 ,  G06N20/00 ,  G06Q10/087 ,  G06Q30/0204 ,  G06Q50/00 ,  G06Q30/0282

摘要： Disclosed are systems and methods utilizing neural contextual bandit for improving interactions with and between computers in content generating, searching, hosting and/or providing systems supported by or configured with personal computing devices, servers and/or platforms. The systems interact to make item recommendations using latent relations and latent representations, which can improve the quality of data used in processing interactions between or among processors in such systems. The disclosed systems and methods use neural network modeling in automatic selection of a number of items for recommendation to a user and using feedback in connection with the recommendation for further training of the model(s).