公开(公告)号：US20240095141A1

公开(公告)日：2024-03-21

申请号：US18025148

申请日：2022-03-21

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

Inventor： Yifan ZHANG ,  Yuqi WANG ,  Linfei CHU ,  Jing NING ,  Kunjie SUN ,  Yuhang ZHENG ,  Naifei SONG ,  Shujuan ZHANG ,  Lin LIU ,  Xunzhuo JU ,  Zhengwei CHEN ,  Wei ZHANG ,  Hua ZHANG ,  Congjun ZHOU ,  Tingkang WU ,  Tengfei LV ,  Hanmeng LIU ,  Lei WANG

IPC: G06F11/32 ,  G06F3/0483

CPC classification number: G06F11/323 ,  G06F3/0483

Abstract: A method and an apparatus for displaying an information flow on a terminal device, an electronic device, a computer-readable storage medium, and a computer program product are provided. An implementation is: in response to detecting an activation operation on an application for displaying the information flow, reproducing, on the terminal device, a first page displayed on the terminal device when the application is last switched to running in the background or closed; and in response to determining that a time interval between the activation operation and the application being last switched to running in the background or closed does not exceed a first threshold, displaying a second page as a continuation of a content entry displayed in the first page, where the second page includes at least one first content entry cached in the terminal device before the activation operation but not displayed in the first page.

公开(公告)号：US20240273394A1

公开(公告)日：2024-08-15

申请号：US18020606

申请日：2022-06-21

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

Inventor： Zhaoxu WANG ,  Xiaoyu HU ,  Huijie LIU ,  Yuhang ZHENG ,  Zhiming PENG

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A method of determining a fusion parameter, a method of recommending an information, a method of training a parameter determination model, an electronic device and a storage medium are provided. The method of determining the fusion parameter includes: inputting a recommendation reference information of a target object into a feature extraction network in a parameter determination model to extract a first object feature for the target object; and inputting the first object feature into a multi-task network in the parameter determination model to obtain a first fusion parameter of a plurality of evaluation indexes for the target object. The plurality of evaluation indexes are used to evaluate a preference of the target object for a recommendation information.