公开(公告)号：US20220391400A1

公开(公告)日：2022-12-08

申请号：US17764002

申请日：2020-09-10

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhengyuan Peng ,  Chuanfei Xu ,  Chao Yu

IPC: G06F16/2457 ,  G06F16/26

Abstract: A method for identifying questions with same semantics includes creating a user behavior graph based on at least two user logs; determining a first associated question node set based on the user behavior graph and a seed question; calculating, based on the first associated question node set, association scores of questions corresponding to all question nodes in the user behavior graph; using a question corresponding to each associated question node in the first associated question node set as a new seed node, to determine M second associated question node sets; updating, based on the M second associated question node sets, the association scores of the questions corresponding to all the question nodes in the user behavior graph; and determining K questions with top K association scores based on updated association scores of the questions corresponding to all the question nodes in the user behavior graph.

公开(公告)号：US20240031068A1

公开(公告)日：2024-01-25

申请号：US18254371

申请日：2021-11-29

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Zhengyuan Peng

IPC: H04L1/1809

CPC classification number: H04L1/1809 ,  H04L2001/0093

Abstract: This application relates to the field of data transmission technologies, and in particular, to a data transmission method and a related device. The method includes: sending a first data packet to a first multicast group in a multicast manner, where the first multicast group includes a plurality of receiving ends; determining a quantity N of receiving ends that fail to receive the first data packet; and if N is less than a first threshold, sending information about a first receiving end to the receiving end that fails to receive the first data packet, where the first receiving end is a receiving end that successfully receives the first data packet. In solutions in embodiments of this application, requirements on bandwidth and processing performance of a sending end can be reduced during data resending.

公开(公告)号：US20240031739A1

公开(公告)日：2024-01-25

申请号：US18245792

申请日：2021-08-23

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhengyuan Peng

IPC: H04R5/04 ,  H04R5/02 ,  H04S3/00

CPC classification number: H04R5/04 ,  H04R5/02 ,  H04S3/008 ,  H04S2400/01

Abstract: A method and system for determining an audio channel role of a sound box. The method includes: obtaining first distance information between a first sound box and M second sound boxes; obtaining second distance information between one second sound box and at least two other second sound boxes in the M second sound boxes; and determining audio channel role information of the first sound box and the M second sound boxes based on the first distance information, the second distance information, and first indication information. The first indication information is used to indicate relative locations of the first sound box and any of the M second sound boxes, and M is an integer greater than 1.

公开(公告)号：US12008003B2

公开(公告)日：2024-06-11

申请号：US17764002

申请日：2020-09-10

Applicant: Huawei Technologies Co., Ltd.

Inventor： Zhengyuan Peng ,  Chuanfei Xu ,  Chao Yu

IPC: G06F16/00 ,  G06F16/2457 ,  G06F16/26

CPC classification number: G06F16/24578 ,  G06F16/26

Abstract: A method for identifying questions with same semantics includes creating a user behavior graph based on at least two user logs; determining a first associated question node set based on the user behavior graph and a seed question; calculating, based on the first associated question node set, association scores of questions corresponding to all question nodes in the user behavior graph; using a question corresponding to each associated question node in the first associated question node set as a new seed node, to determine M second associated question node sets; updating, based on the M second associated question node sets, the association scores of the questions corresponding to all the question nodes in the user behavior graph; and determining K questions with top K association scores based on updated association scores of the questions corresponding to all the question nodes in the user behavior graph.