-
公开(公告)号:US11983240B2
公开(公告)日:2024-05-14
申请号:US17527295
申请日:2021-11-16
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Zhixiang Chi , Li Gu , Huan Liu , Yuanhao Yu , Yang Wang , Jin Tang
IPC: G06N3/08 , G06F18/21 , G06F18/213 , G06F18/214 , G06F18/243 , G06N3/045 , G06V10/94
CPC classification number: G06F18/213 , G06F18/2148 , G06F18/217 , G06F18/243 , G06N3/045 , G06N3/08 , G06V10/95
Abstract: This disclosure provides for methods and system for meta few-shot class incremental learning. According to an aspect a method is provided. The method includes obtaining at least one weight attention map of a first network and updating weights of a second network using the at least one weight attention map, where the second network is a modulatory network. The method further includes generating at least one feature attention map of the second network based on the at least one weight attention map of the first network and a set of input images of at least one class. The method further includes generating at least one feature map of the first network based on the set of input images of the at least one class, and updating the at least one feature map of the first network based on the feature attention map of the second network.
-
公开(公告)号:US12223618B2
公开(公告)日:2025-02-11
申请号:US17726218
申请日:2022-04-21
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Hengming Wang , Yang Wang , Jie Ji
IPC: G06T3/4053 , H04N5/232 , H04N19/176 , H04N23/951
Abstract: The present application discloses an image processing method and apparatus, and an electronic device, and pertains to the field of image processing. The method includes: obtaining an inter-frame residual between two adjacent image frames to obtain a residual block; determining, based on the residual block, a target pixel region on which super-resolution processing needs to be performed; and performing super-resolution processing on the target pixel region to obtain a target pixel region. For another pixel region, the super-resolution processing result of an image frame that is in the two image frames and on which super-resolution processing is performed is used. This application reduces high computation costs of super-resolution processing.
-
公开(公告)号:US20240427406A1
公开(公告)日:2024-12-26
申请号:US18824694
申请日:2024-09-04
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Tuanbao Fan , Eitan Rosen , Ningbo Sun , Yang Wang , Xiaoshan Shi , Mingfeng Jiang , Yu Liu , Zhangrong Hu
Abstract: A power supply circuit and a frequency adjustment method are provided, to improve running stability of a processing module (200). The power supply circuit obtains an operating voltage of the processing module (200), and generates, based on the operating voltage, a clock signal that indicates an operating frequency of the processing module (200), so that the processing module (200) runs at an operating frequency corresponding to a current operating voltage. Even if the operating voltage fluctuates, running of the processing module (200) is not affected. This improves running stability of the processing module (200) without increasing power consumption.
-
公开(公告)号:US20240320473A1
公开(公告)日:2024-09-26
申请号:US18731020
申请日:2024-05-31
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Yang Wang , Xueqiang Yan , Mingyu Zhao , Shaoyun Wu , Weijun Xing
Abstract: This application discloses a communication method and apparatus, a storage medium, and a program product. The method includes: A server sends training information. The training information includes a global model in a previous round and identifiers of at least two second terminals that participate in a current round of training. A first terminal sends a local model of the first terminal. The local model is obtained based on the global model in the previous round and a shared key. The server receives local models of the at least two second terminals, and aggregates the local models of the at least two second terminals based on a shared key between the at least two second terminals, to obtain an updated global model in the current round. According to the solutions of this application, security in a neural network training process is improved.
-
公开(公告)号:US10715382B2
公开(公告)日:2020-07-14
申请号:US14988420
申请日:2016-01-05
Applicant: Huawei Technologies Co., Ltd.
Inventor: Hongguang Guan , Yang Wang , Feng Li
IPC: G06F15/177 , H04L12/24 , G06F16/9537 , H04L29/08 , H04L29/06 , H04L12/751 , H04L12/26
Abstract: A method for configuring a service node, a service node pool registrar, and a system are provided. The service node pool registrar receives a service node query request sent by a management configuration device, where the service node query request includes a service requirement, where the service requirement is from a user or caused by a network change; the service node pool registrar searches a service node database to obtain service node information that matches the service node query request and sends the matching service node information to the management configuration device, so that the management configuration device performs network and service configuration on the matching service node according to obtained network topology information and the matching service node information.
-
公开(公告)号:US20250139663A1
公开(公告)日:2025-05-01
申请号:US18692648
申请日:2022-08-23
Applicant: Huawei Technologies Co., Ltd.
Inventor: Weicai Zhong , Yang Wang , Xiaoqian Wang , Baoji He
IPC: G06Q30/0251
Abstract: A method includes that a terminal receives first information input by a user in an input box of a first interface. When the user performs an operation on the first interface of the terminal, the terminal requests a server to search for the first information. The server obtains, based on the first information through searching, a product or service that is provided by a target vendor and that is related to the first information, and sends the product or service provided by the target vendor to the terminal. A second interface of the terminal displays the product or service provided by the target vendor.
-
公开(公告)号:US12062387B2
公开(公告)日:2024-08-13
申请号:US18197465
申请日:2023-05-15
Applicant: HUAWEI TECHNOLOGIES CO., LTD.
Inventor: Jingsong Wei , Jun Xu , Yang Wang , Renqi Liu , Hongwei Tang
IPC: G11B7/24038 , G11B7/24062 , G11B7/243 , G11B7/26
CPC classification number: G11B7/268 , G11B7/24062 , G11B7/243 , G11B2007/24314 , G11B2007/24316 , G11B2220/2541
Abstract: An optical storage medium, a method for preparing an optical storage medium, and a system are provided. In this application, the optical storage medium includes a substrate and at least one data layer, the data layer includes a recording layer and a spacer layer, the recording layer is located on the spacer layer, and the data layer is located above the substrate. The recording layer may store data, the recording layer includes an area in which a phase change material is distributed and an area in which no phase change material is distributed, and the two different areas may indicate different data.
-
公开(公告)号:US11630510B2
公开(公告)日:2023-04-18
申请号:US17304615
申请日:2021-06-23
Applicant: Huawei Technologies Co., Ltd.
Inventor: Zhenhao Li , Rasoul Mohammadi Nasiri , Zheng Liu , Hisham Elhalabi , Yuanhao Yu , Roel Vertegaal , Yang Wang , Jin Tang
Abstract: A system and a method for performing 2D on-screen user gaze estimation using an input facial image of a user captured using a camera associated to a processing device having a display. The method and system allow automated user calibration through automatic recording of calibration samples each including a calibration facial image of the user and an interaction point corresponding to a point on the display where an occurrence of a user interaction was detected when the corresponding calibration image was captured. The system and method also optimize user-specific parameters using the calibration samples by iteratively minimizing a total difference between the interaction points of a plurality of the calibration samples and corresponding 2D gaze estimation results and convert an estimated 3D gaze direction into a 2D gaze estimation result corresponding to a point on the display, by applying the users-specific parameters.
-
公开(公告)号:US20230054562A1
公开(公告)日:2023-02-23
申请号:US17975340
申请日:2022-10-27
Applicant: Huawei Technologies Co., Ltd.
Inventor: Hongguang Guan , Yang Wang , Feng Li
IPC: H04L41/0806 , G06F16/9537 , H04L41/12 , H04L41/5051 , H04L41/5054 , H04L41/50 , H04L9/40 , H04L41/0816 , G06F3/06 , H04L43/00 , H04L43/0805 , H04L67/1001 , H04L45/02 , H04L67/1095
Abstract: A method for configuring a service node, a service node pool registrar, and a system are provided. In certain embodiments, the method includes receiving a service node query request sent by a management configuration device. The service node query request includes a service requirement. The service requirement is from a user or caused by a network change. The method further includes searching a service node database, to obtain service node information that matches the service node query request. The method further includes sending the matching service node information to the management configuration device, causing the management configuration device to perform network and service configuration on the matching service node according to network topology information that has been obtained and the matching service node information.
-
公开(公告)号:US11223541B2
公开(公告)日:2022-01-11
申请号:US15133399
申请日:2016-04-20
Applicant: Huawei Technologies Co., Ltd.
Inventor: Liang Xia , Ning Zong , Yang Wang , Qin Wu , Danhua Wang
Abstract: The present invention provides a virtual network function network element management method, apparatus, and system. A VNF resource pool management apparatus receives a VNF network element request message sent by a VNF resource pool user apparatus, where the VNF network element request message includes attribute information and a location policy of a VNF network element that is requested; the VNF resource pool management apparatus determines a first VNF network element that matches the attribute information and the location policy from the VNF resource pool; and the VNF resource pool management apparatus sends a VNF network element response message to the VNF resource pool user apparatus, where the VNF network element response message includes identification information of the first VNF network element. In this way, a risk that a functional group formed by VNF network elements cannot properly work can be avoided.
-
-
-
-
-
-
-
-
-