公开(公告)号：US11429680B2

公开(公告)日：2022-08-30

申请号：US16234337

申请日：2018-12-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Hao Tian ,  Daren Li ,  Bo Huang ,  Dai Dai ,  Chengxiang Liu ,  Anjun Wei ,  Kexin Ren ,  Haiguang Yuan

IPC: G06F16/00 ,  G06F16/953 ,  G06F16/33 ,  G06F16/31 ,  G06F16/174

Abstract: Embodiments of the present disclosure disclose a method and apparatus for subscribing to a topic. The method includes: matching a persistent topic for a retrieval keyword based on the retrieval keyword of a user combined with at least one of historical behavior or a subscription record of the user; returning the persistent topic to a client for display, so that the user performs subscription; and saving the persistent topic subscribed to by the user, and when a matching resource corresponding to the persistent topic subscribed to by the user is updated, recommending the updated matching resource to the user. Since a recommendation strategy can be timely adjusted according to real-time behavior of a user combined with historical behavior, the probability of hitting a topic of interest to the user is increased.

公开(公告)号：US20190155856A1

公开(公告)日：2019-05-23

申请号：US16234337

申请日：2018-12-27

Applicant: BEIJING BAIDU NETCOM SCIENCE AND TECHNOLOGY CO., LTD.

Inventor： Hao Tian ,  Daren Li ,  Bo Huang ,  Dai Dai ,  Chengxiang Liu ,  Anjun Wei ,  Kexin Ren ,  Haiguang Yuan

IPC: G06F16/953 ,  G06F16/33 ,  G06F16/31 ,  G06F16/174

Abstract: Embodiments of the present disclosure disclose a method and apparatus for subscribing to a topic. The method includes: matching a persistent topic for a retrieval keyword based on the retrieval keyword of a user combined with at least one of historical behavior or a subscription record of the user; returning the persistent topic to a client for display, so that the user performs subscription; and saving the persistent topic subscribed to by the user, and when a matching resource corresponding to the persistent topic subscribed to by the user is updated, recommending the updated matching resource to the user. Since a recommendation strategy can be timely adjusted according to real-time behavior of a user combined with historical behavior, the probability of hitting a topic of interest to the user is increased.