公开(公告)号：US20230131871A1

公开(公告)日：2023-04-27

申请号：US18082348

申请日：2022-12-15

Applicant: Beijing Baidu Netcom Science Technology Co., Ltd.

Inventor： Yong SHAO ,  Zhongshan Liu ,  Bing Huang ,  Peilong Wang ,  Yao Wang ,  Yan Wang ,  Fenghui Zhang ,  Qingzhi Zhou

IPC: H04L45/76 ,  H04L45/586 ,  G06N5/025

Abstract: A method, system and apparatus for forwarding data in a virtual network, an electronic device, a storage medium and a computer program product are provided. The method includes: determining, in a process of managing virtual private cloud networks through a central control node, all forwarding rules for nodes in the virtual private cloud networks; synchronizing the forwarding rules in a virtual routing cluster, and determining target forwarding rules corresponding to each virtual private cloud network from the forwarding rules; and through a virtual switch in each virtual private cloud network, learning the target forwarding rules corresponding to the virtual private cloud network to which the virtual switch belongs, and performing data forwarding based on the learned target forwarding rules.

公开(公告)号：US20250117602A1

公开(公告)日：2025-04-10

申请号：US18988044

申请日：2024-12-19

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

Inventor： Zhaoxu Wang ,  Qiang Xie ,  Yuhang Zheng ,  Shouke Qin ,  Zonggang Wu ,  Yuanhua Shao ,  Yan Wang ,  Ruohan Chang ,  Qingqing Wu ,  Lu Wang ,  Songge Guo ,  Chang Li ,  Xi Cao ,  Qian Wu ,  Xiaoyu Hu ,  Huijie Liu ,  Yu Guo ,  Hui Xue ,  Rufeng Cheng

IPC: G06F40/40

Abstract: A large model-based recommendation method includes: determining description information of interested content corresponding to a target user; inputting a content to be recommended, the description information of interested content and current popular search sentences into a large model to generate at least one recommendation card corresponding to the content to be recommended, in which the recommendation card contains a recommendation word associated with the content to be recommended; obtaining a current behavior characteristic of the target user; and in response to the current behavior characteristic satisfying a display condition of the recommendation card, displaying the recommendation card corresponding to at least one content to be recommended.