公开(公告)号：US20230283624A1

公开(公告)日：2023-09-07

申请号：US18316591

申请日：2023-05-12

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Li XUE ,  Weiwang XU ,  Liang ZHANG ,  Jian CHENG

IPC: H04L9/40

CPC classification number: H04L63/1425 ,  H04L63/20 ,  H04L63/0263 ,  H04L63/0236

Abstract: This application provides a method, an apparatus, and a system for determining data flow information. The method includes: obtaining flow parameters of a plurality of data flows within a first time period; obtaining at least one data flow group according to the flow parameters of the plurality of data flows and a flow parameter rule of at least one preset access mode, where a relationship between data flows in each data flow group satisfies a flow parameter rule of one preset access mode; and determining group parameters of each data flow group.

公开(公告)号：US20230017215A1

公开(公告)日：2023-01-19

申请号：US17935120

申请日：2022-09-25

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xudong Sun ,  Yanfang ZHANG ,  Qinglong CHANG ,  Liang ZHANG

IPC: G06F30/20

Abstract: A modeling method and an apparatus are disclosed. The method includes: obtaining a first data set of a first indicator, and determining, based on the first data set, a second indicator similar to the first indicator; and determining a first model based on one or more second models associated with the second indicator. The first model is used to detect a status of the first indicator, and the status of the first indicator includes an abnormal state or a normal state. The second models are used to detect a status of the second indicator, and the status of the second indicator includes an abnormal state or a normal state.

公开(公告)号：US20220366310A1

公开(公告)日：2022-11-17

申请号：US17871084

申请日：2022-07-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiaoyun SI ,  Liang ZHANG ,  Xinyu HU ,  Jun WU

IPC: G06N20/00

Abstract: A method for implementing model update is provided and used in a federated update framework. The method includes: a service device receives difference information uploaded by at least two clients. The service device performs calculation based on the difference information uploaded by the at least two clients, to obtain first difference consistency information, where the first difference consistency information indicates a consistency degree of the difference information uploaded by the at least two clients. The service device performs calculation based on the first difference consistency information, to obtain first training information, where the first training information is used to train a third model, and the third model is obtained by updating the first model by the service device based on the difference information uploaded by the at least two clients. The service device sends the first training information to the at least two clients.

公开(公告)号：US20200167186A1

公开(公告)日：2020-05-28

申请号：US16777516

申请日：2020-01-30

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Guocheng ZHONG ,  Liang ZHANG ,  Jianrui YANG ,  Jinmiao LIU

IPC: G06F9/455 ,  G06F9/54 ,  G06F9/30

Abstract: A container isolation method for a netlink resource includes receiving, by a kernel executed by a processor, a trigger instruction from an application program. The method also includes creating, by the kernel according to the trigger instruction, a container corresponding to the application program, creating a netlink namespace for the container, and sending a notification to the application program indicating that the netlink namespace is created. The method further includes receiving, by the kernel, a netlink message from the container, wherein the netlink message comprises entries generated when the container runs. The method additionally includes storing, by the kernel, the entries based on an identifier of the netlink namespace for the container, to send an entry required by the container to user space of the container.

公开(公告)号：US20170126487A1

公开(公告)日：2017-05-04

申请号：US15403798

申请日：2017-01-11

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yuming XIE ,  Liang ZHANG ,  Jun WU ,  Fan YANG

IPC: H04L12/24 ,  H04L29/12 ,  G06F9/455 ,  H04L12/741

Abstract: A service deployment method and a network functions acceleration platform are provided. The method includes: when an FPGA is powered on, loading, by the FPGA, an FPGA framework file, so that the FPGA includes M partial reconfigurable PR areas, a configuration module, and a data flow forwarding module; when receiving a service configuration instruction, generating, by a physical machine, a VM, and selecting at least one PR area from the M PR areas to establish a correspondence with the VM; performing, by a configuration module, service resource configuration on the selected PR area according to a PR configuration resource, so that the selected PR area has a service processing capability; adding, by the configuration module, a forwarding entry corresponding to the PR area in a forwarding flow table, so that the data flow forwarding module forwards a received network packet to the corresponding PR area.

公开(公告)号：US20230214532A1

公开(公告)日：2023-07-06

申请号：US17924856

申请日：2021-04-22

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Shunhai XU ,  Liang ZHANG ,  Xingmin GUO ,  Faming TANG ,  Hao WANG

IPC: G06F21/62 ,  G06F21/53 ,  G06F21/60

CPC classification number: G06F21/629 ,  G06F21/53 ,  G06F21/602

Abstract: Embodiments of this application provide example permission negotiation methods and apparatuses during communication, and electronic devices. An example first electronic device displays an interface of a currently running communication application, and obtains, in response to the first operation, a permission item restricted for use in a process of communication with a second electronic device. Then, the first electronic device sends a first request to the second electronic device that includes the permission item restricted for use. The first electronic device receives confirmation information of the second electronic device for the permission item restricted for use, and restricts, based on the confirmation information, a locally installed application on applying for the permission item restricted for use. After communication with the second electronic device ends, the first electronic device restores settings of the permission item of the locally installed application to settings preceding the communication with the second electronic device.

公开(公告)号：US20220284352A1

公开(公告)日：2022-09-08

申请号：US17826314

申请日：2022-05-27

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Qinglong CHANG ,  Yanfang ZHANG ,  Xudong SUN ,  Li XUE ,  Liang ZHANG

IPC: G06N20/00

Abstract: A model update system, which may be applied to the network control field, includes a site analysis device and a first analysis device. The site analysis device is configured to: receive a first model sent by the first analysis device; train the first model by using a first training sample to obtain a second model, where the first training sample includes first feature data of a network device in a site network corresponding to the site analysis device; obtain differential data between the first model and the second model; and send the differential data to the first analysis device. The first analysis device is configured to: send the first model to the site analysis device; receive the differential data sent by the site analysis device; and update the first model based on the differential data to obtain a third model.

公开(公告)号：US20220207434A1

公开(公告)日：2022-06-30

申请号：US17696593

申请日：2022-03-16

Applicant: Huawei Technologies Co., Ltd.

Inventor： Li XUE ,  Yanfang ZHANG ,  Hao ZHANG ,  Liang ZHANG ,  Yang LI

IPC: G06N20/20 ,  G06F11/34

Abstract: This application discloses a model training method, apparatus, and system, and belongs to the AI field. The method includes: receiving a machine learning model sent by a first analysis device; and performing incremental training on the machine learning model based on a first training sample set, where feature data in the first training sample set is feature data from a local network corresponding to a local analysis device. In this application, a problem that the machine learning model obtained through offline training cannot be effectively adapted to a requirement of the local analysis device is resolved. Embodiments of this application are used to predict a classification result.

公开(公告)号：US20200244370A1

公开(公告)日：2020-07-30

申请号：US16845489

申请日：2020-04-10

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Nebojsa STOJANOVIC ,  Liang ZHANG ,  Cristian PRODANIUC ,  Jinlong WEI ,  Changsong XIE

IPC: H04B10/54 ,  H04B10/61 ,  H04L1/00

Abstract: An optical communication system that comprises a transmitter adapted to generate a signal by modulating a transmission data as low power consumption symbols of an amplitude modulation format and a monitoring data (MD) as high power consumption symbols of the amplitude modulation format, the MD comprising at least one transmitter parameter and/or at least one receiver parameter of communicating the transmission data. A binary logarithm of a total number of the low power consumption symbols and the high power consumption symbols is a non-integer.

公开(公告)号：US20180191447A1

公开(公告)日：2018-07-05

申请号：US15906514

申请日：2018-02-27

Applicant: Huawei Technologies Co., Ltd.

Inventor： Enbo ZHOU ,  Yuanjun LIANG ,  Tianjian ZUO ,  Liang ZHANG

IPC: H04B10/61

CPC classification number: H04B10/613 ,  H04B10/5053 ,  H04B10/61 ,  H04B10/616 ,  H04B10/6165 ,  H04J14/06

Abstract: An optical signal processing method and a coherent receiver, wherein an in-phase signal XI in a first polarization direction and an in-phase signal YI in a second polarization direction are added up to obtain a signal I; a quadrature signal XQ in the first polarization direction and a quadrature signal YQ in the second polarization direction are added up to obtain a signal Q; and quantization, combination, and digital signal processing are performed on the I and the Q. After summation, two signals need to be quantized. Therefore, a quantity of ADCs is reduced by half. In addition, because power consumption of a summation component is less than that of an ADS, power consumption of optical signal processing can be reduced. In addition, because there is a preset value, the summation may be performed after phase-inversion is performed on one analog signal, thereby avoiding a signal loss caused by the summation.