公开(公告)号：US12205147B2

公开(公告)日：2025-01-21

申请号：US17491435

申请日：2021-09-30

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Yafei Zhang ,  Junwei Zhong ,  Feng Xia

IPC: G06N20/00 ,  G06F18/214 ,  G06Q30/0251

Abstract: This application provides a feature processing method and apparatus for an artificial intelligence (AI) recommendation model, an electronic device, and a storage medium. The method includes obtaining input data, and converting a data structure of the input data into a uniform sample structure; determining a feature group identifier and a feature extraction function that correspond to the AI recommendation model; extracting a feature group identifier, a feature identifier and a feature value of the input data from the converted input data according to the feature extraction function; and constructing a sample of the AI recommendation model according to the feature group identifier, the feature identifier and the feature value of the input data.

公开(公告)号：US11763145B2

公开(公告)日：2023-09-19

申请号：US16945066

申请日：2020-07-31

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Yi Liu ,  Lantao Hu ,  Bo Zhang ,  Feng Xia ,  Leyu Lin ,  Zhe Feng ,  Lei Chen ,  Jun Rao ,  Shukai Liu ,  Zhijie Qiu ,  Zhenlong Sun ,  Liangdong Wang

IPC: G06N3/08 ,  A61B5/16 ,  G06N5/022 ,  G06V40/20 ,  G06F18/214

CPC classification number: G06N3/08 ,  A61B5/165 ,  G06F18/2155 ,  G06N5/022 ,  G06V40/20

Abstract: This application provides an article recommendation method and apparatus, a computer device, and a storage medium. The method includes: obtaining a historical reading article set of a to-be-analyzed target user, the historical reading article set comprising a plurality of historical articles that have been read by the target user at different reading moments; determining, for each historical article of the plurality of historical articles, first attention degree values between the each historical article and candidate reference historical articles having reading moments before that of the each historical article, the first attention degree values reflecting a possibility that a user is recommended to read the historical article if the user has read the candidate reference historical articles; selecting at least one recommendation reference article from the candidate reference historical articles corresponding to the historical articles according to the first attention degree values between the historical articles and corresponding candidate reference historical articles; and determining, in a recommendable article set at least one candidate recommended article to be recommended to the target user based on the at least one recommendation reference article.

公开(公告)号：US11893071B2

公开(公告)日：2024-02-06

申请号：US17726048

申请日：2022-04-21

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Cheng Ling ,  Yalong Wang ,  Rui Wang ,  Ruobing Xie ,  Feng Xia ,  Leyu Lin

IPC: G06F16/00 ,  G06F16/9536 ,  G06F16/9535 ,  H04L67/50 ,  G06N3/045

CPC classification number: G06F16/9536 ,  G06F16/9535 ,  G06N3/045 ,  H04L67/535

Abstract: This application provides a content recommendation method and apparatus, an electronic device, and a storage medium. The content recommendation method includes obtaining content feedback information of a target object and content feature information of content that is to be recommended in response to a content recommendation request of the target object, the content feedback information comprising explicit feedback information and implicit feedback information and object portrait information of the target object; performing feature interaction according to the explicit feedback information and the implicit feedback information in the content feedback information, and obtaining behavior preference information; performing feature extraction based on the behavior preference information, the content feedback information, and the content feature information, and obtaining a predicted click-through rate (CTR); and determining, according to the predicted CTR, recommended content from the pieces of content that is to be recommended, and transmitting the recommended content to a terminal device.

公开(公告)号：US11537624B2

公开(公告)日：2022-12-27

申请号：US15988908

申请日：2018-05-24

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Lixin Zhang ,  Leyu Lin ,  Feng Xia ,  Mu Yuan ,  Xiangcong Zeng ,  Zhe Feng

IPC: G06F16/2457 ,  G06F16/335

Abstract: Embodiments of the present invention disclose a result ranking method and device. The method includes: acquiring search key-information by using an interaction application, and searching a prestored interaction data set for at least one search result associated with the search key-information; ranking the at least one search result according to a quality assessment score corresponding to each of the at least one search result; and outputting the ranked at least one search result. The quality assessment score corresponding to each search result is a value generated according to a number of historical operations performed on each search result and an interactive influence score of an application identifier performing a historical operation on each search result.

公开(公告)号：US20220284327A1

公开(公告)日：2022-09-08

申请号：US17725429

申请日：2022-04-20

Applicant: Tencent Technology (Shenzhen) Company Limited

Inventor： Shaoliang ZHANG ,  Rui Wang ,  Ruobing Xie ,  Zhihong Yang ,  Feng Xia ,  Leyu Lin

IPC: G06N5/04 ,  G06F16/9535 ,  G06N5/02

Abstract: This application discloses a resource pushing method performed by a computer device. The method includes: obtaining a target recommendation model and a preference feature and a candidate resource set corresponding to a target object, the preference feature including at least a channel preference feature and a content preference feature; obtaining at least one target resource from the candidate resource set based on the target recommendation model and the preference feature; and pushing the at least one target resource to the target object. Such a resource pushing process integrates preferences of the target object in different dimensions, so that the target resource pushed to the target object not only conforms to channel preferences of the target object, but also conforms to content references of the target object, which is beneficial to improving the resource pushing effect, and further increasing the click-through rates (CTRs) of the pushed resources.

公开(公告)号：US11321410B2

公开(公告)日：2022-05-03

申请号：US17235922

申请日：2021-04-20

Applicant: TENCENT TECHNOLOGY (SHENZHEN) COMPANY LIMITED

Inventor： Zhe Feng ,  Zhiping Wang ,  Leyu Lin ,  Ge Wang ,  Yang Cui ,  Jiayi Ding ,  Shuo Wang ,  Qihao Zhu ,  Chenglin Zhong ,  Shanpeng Sun ,  Xiumin Lin ,  Yang Zuo ,  Junhong Yan ,  Ming Zou ,  Xulin Liao ,  Feng Xia ,  Xu Zhang ,  Su Yan ,  Wei Wang ,  Zhiwei Guo ,  Jianxiong Feng

IPC: G06F16/9536 ,  G06F16/9535 ,  G06F3/0483 ,  G06F3/0484 ,  H04L51/52 ,  H04L67/55

Abstract: This application discloses an information recommendation method and apparatus, a device, and a storage medium, and belongs to the field of information recommendation. The method includes starting an application program according to a start operation, a first account being logged in in the application program; obtaining a recommended information flow for the first account, recommended information in the recommended information flow including at least one piece of interactive recommended information, the interactive recommended information being information for which a second account generates an interactive message, the first account and the second account having a social relationship; and displaying an information presentation interface, the information presentation interface comprising the recommended information displayed in an information flow form.