公开(公告)号：US20230306311A1

公开(公告)日：2023-09-28

申请号：US18325533

申请日：2023-05-30

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanfang Zhang ,  Qinglong Chang ,  Jikun Ding ,  Liang Zhang ,  Xudong Sun

IPC: G06N20/00

CPC classification number: G06N20/00

Abstract: A federated learning method includes: each second device in a plurality of second devices first obtains data distribution information and sends the data distribution information to a first device. The first device receives the data distribution information from the plurality of second devices participating in federated learning. The first device selects a matched federated learning policy based on the data distribution information. The first device sends a parameter reporting policy corresponding to the federated learning to at least one second device in the plurality of second devices. A second device that receives the parameter reporting policy is configured to obtain second gain information based on the parameter reporting policy and a current training sample, and the second gain information is for obtaining a second model of the second device.

公开(公告)号：US20230261993A1

公开(公告)日：2023-08-17

申请号：US18305421

申请日：2023-04-24

Applicant: Huawei Technologies Co., Ltd.

Inventor： Haonan Ye ,  Liang Zhang ,  Jian Cheng ,  Jun Wu

IPC: H04L47/12 ,  H04L41/14 ,  H04L47/11

CPC classification number: H04L47/12 ,  H04L41/14 ,  H04L47/11

Abstract: A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

公开(公告)号：US20230169096A1

公开(公告)日：2023-06-01

申请号：US18150505

申请日：2023-01-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Qinglong Chang ,  Xinyu Hu ,  Yanfang Zhang ,  Xudong Sun ,  Liang Zhang

IPC: G06F16/28 ,  G06F18/23213

CPC classification number: G06F16/285 ,  G06F18/23213

Abstract: A sample data annotation system includes an edge node and a central node. The edge node obtains a key feature of sample data, determines, based on the key feature, whether the sample data is unknown sample data, when the sample data is unknown sample data, performs annotation processing on the sample data to obtain a first annotation result, and sends the first annotation result to the central node. The central node receives the first annotation result, and determines whether the first annotation result indicates successful annotation; and when the first annotation result indicates that the unknown sample data is successfully annotated, performs consistency processing on the first annotation result to obtain a second annotation result, or when the annotation result indicates that the unknown sample data fails to be annotated, performs annotation processing on the unknown sample data to obtain a third annotation result.

公开(公告)号：US20230146912A1

公开(公告)日：2023-05-11

申请号：US18148305

申请日：2022-12-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanfang Zhang ,  Xudong Sun ,  Qinglong Chang ,  Liang Zhang

IPC: G06N20/00 ,  G06F18/22

CPC classification number: G06N20/00 ,  G06F18/22

Abstract: A method, an apparatus, and a computing device for constructing a prediction model, and a storage medium are disclosed, and relate to the field of artificial intelligence technologies. The method includes: obtaining, based on a target dataset of a target prediction scenario and/or scenario information of the target prediction scenario, model search space corresponding to the target prediction scenario; performing model training based on the target dataset and models and hyperparameters that are included in the model search space, to obtain trained prediction models; and obtaining, based on evaluation results of the trained prediction models, a prediction model corresponding to the target prediction scenario. Efficiency of constructing the prediction model can be improved.

公开(公告)号：US20230142028A1

公开(公告)日：2023-05-11

申请号：US18153255

申请日：2023-01-11

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jian Cheng ,  Liang Zhang ,  Li Xue ,  Haonan Ye ,  Weiwang Xu

IPC: H04L43/02

CPC classification number: H04L43/02

Abstract: This application provides a data collection method and a device. A data collection device determines, based on a threshold corresponding to a target indicator, a collection interval for to-be-collected data of the target indicator from a plurality of available collection intervals; and the data collection device collects the data of the target indicator based on the collection interval.

公开(公告)号：US20220414487A1

公开(公告)日：2022-12-29

申请号：US17822581

申请日：2022-08-26

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xiaoyun Si ,  Xinyu Hu ,  Li Xue ,  Jun Wu ,  Liang Zhang

IPC: G06N5/02

Abstract: A method and an apparatus for updating an application identification model, and a storage medium are provided. A client device may determine a plurality of training samples based on identification results of a plurality of pieces of data traffic, and train an application identification model using the training samples. Then, the client device may upload model data of the trained application identification model to a server, and the server performs joint update based on the model data uploaded by a plurality of client devices. Then, the client device may obtain a jointly updated application identification model based on jointly updated model data delivered by the server.

公开(公告)号：US20210344601A1

公开(公告)日：2021-11-04

申请号：US17244256

申请日：2021-04-29

Applicant: Huawei Technologies Co., Ltd.

Inventor： Haonan Ye ,  Liang Zhang ,  Jian Cheng ,  Jun Wu

IPC: H04L12/801 ,  H04L12/24

Abstract: A network device inputs first network status information of the network device in a first time period to an ECN inference model, to obtain an inference result that is output by the ECN inference model based on the first network status information. Then, the network device sends an ECN parameter sample to an analysis device that manages the network device, where the ECN parameter sample includes the first network status information and a target ECN configuration parameter corresponding to the first network status information, and the target ECN configuration parameter is obtained based on the inference result. The network device receives an updated ECN inference model sent by the analysis device.

公开(公告)号：US11138062B2

公开(公告)日：2021-10-05

申请号：US16755280

申请日：2017-10-13

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Liang Zhang ,  Yu Li ,  Chenxiao Zhao ,  Huijin Huang

IPC: G06F11/07 ,  G06F11/14 ,  G06F3/0482

Abstract: This application relates to the field of terminal technologies, and provides a terminal device troubleshooting method and a terminal device, so as to improve accuracy of a result of detecting a fault such as a black screen, or screen freezing that occurs on a terminal device. The troubleshooting method includes: obtaining, a first operation and a first result; determining that the first operation is the same as a predefined second operation and that the first result is a fault result; and when the first operation is the same as the second operation, and the first result is a fault result, determining that an actual fault occurs on a terminal device, where the first operation is an operation currently performed by a user on the terminal device, and the first result is a result of responding by the terminal device to the first operation.

公开(公告)号：US20210271572A1

公开(公告)日：2021-09-02

申请号：US17261239

申请日：2018-11-14

Applicant: Huawei Technologies Co., Ltd.

Inventor： Dechun Qi ,  Leizhen Zang ,  Liang Zhang ,  Xun Zhang ,  Zhijun Lu ,  Jun Xue ,  Haitao Zhu ,  Xiaozhen Meng

IPC: G06F11/14 ,  G06F3/06 ,  G06F21/31 ,  G06F21/60

Abstract: Embodiments of this application relate to the field of storage technologies, and disclose a data backup method and a terminal, to back up user data in a terminal when the terminal cannot be used. A specific solution is as follows: A terminal includes a first data partition, and the first data partition supports to start an operating system when the terminal is powered on. The terminal starts the operating system by using a second data partition after detecting a power-on failure of the terminal or detecting a preset operation of a user. The second data partition is a blank data partition. After the operating system is successfully started, the terminal transmits user data in the first data partition to a first storage medium. The first storage medium is located outside the terminal and is connected to the terminal.

公开(公告)号：US10909221B2

公开(公告)日：2021-02-02

申请号：US15923703

申请日：2018-03-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Liang Zhang ,  Jianrui Yang ,  Xingshui Dong

IPC: H04L29/06 ,  G06F21/10 ,  G06F21/12 ,  G06F8/61 ,  G06F9/455 ,  G06F9/445

Abstract: A container license management method and an apparatus, where the method includes receiving an image download request including information for requesting a license from a container management background, obtaining an image according to the image download request, obtaining the information for requesting a license in the image download request, generating a license image layer corresponding to the information for requesting a license, adding the license image layer to the obtained image, and sending, to the container management background, the image to which the license image layer is added such that the container management background starts a container corresponding to the image, and detects whether the license image layer is valid. Hence, container license management efficiency can be improved.