公开(公告)号：US20160156724A1

公开(公告)日：2016-06-02

申请号：US14937143

申请日：2015-11-10

Applicant: Huawei Technologies Co., Ltd.

Inventor： Dong LIU ,  Yunpeng WANG

IPC: H04L29/08 ,  G06F17/30

CPC classification number: H04L67/16 ,  G06F16/9535 ,  G06Q10/10 ,  G06Q10/101 ,  G06Q30/02 ,  G06Q50/01 ,  H04L67/2833 ,  H04L67/306

Abstract: A method for determining a target user for a service policy, which is used to determine the target user to which the service policy is oriented, from users of a first network. The method includes: analyzing aggregated information according to a pre-configured service policy keyword to determine target user information corresponding to the service policy keyword, where the aggregated information includes a first correspondence between user information of the users of the first network and service content, where the service content includes service content of the users of the first network, in the second network; and outputting the target user information, where the target user information is used to indicate the target user to which the service policy is oriented. By using the method according to an embodiment of the present invention, the target user to which the service policy is oriented may be determined accurately.

Abstract translation: 一种用于确定服务策略的目标用户的方法，用于从第一网络的用户确定用于服务策略所针对的目标用户。 该方法包括：根据预先配置的服务策略关键字对聚合信息进行分析，以确定与服务策略关键字相对应的目标用户信息，其中聚合信息包括第一网络的用户的用户信息和服务内容之间的第一对应关系， 其中所述服务内容包括所述第一网络的用户的服务内容，在所述第二网络中; 并输出目标用户信息，其中使用目标用户信息来指示服务策略所针对的目标用户。 通过使用根据本发明的实施例的方法，可以准确地确定服务策略所针对的目标用户。

公开(公告)号：US20230342833A1

公开(公告)日：2023-10-26

申请号：US18215959

申请日：2023-06-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shendi WANG ,  Haoyang LI ,  Yunpeng WANG ,  Chen CAO

IPC: G06Q30/0601 ,  G06Q30/0201

CPC classification number: G06Q30/0631 ,  G06Q30/0201

Abstract: Embodiments of this application disclose a recommendation method. The method in embodiments of this application is applied to a scenario in which an item is recommended to a user, for example, movie recommendation or game recommendation. The method in embodiments of this application includes: obtaining a knowledge graph, where the knowledge graph includes a plurality of first entities indicating items and a plurality of second entities indicating item attributes; and running a neural network based on the knowledge graph and information of the user, to obtain a recommendation result. The neural network is used to perform computing based on at least one first direction and at least one second direction in the knowledge graph to obtain the recommendation result.