公开(公告)号：US20230031387A1

公开(公告)日：2023-02-02

申请号：US17957889

申请日：2022-09-30

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Xiaoyun Si ,  Xinyu Hu ,  Li Xue ,  Liang Zhang ,  Fuxing Chen

IPC: G06N3/063 ,  G06N3/08 ,  G11C11/54

Abstract: A method, an apparatus, and a device for obtaining an artificial intelligence model, and a storage medium are provided. A client receives a first artificial intelligence AI model sent by a service end (303). The first AI model includes a plurality of neurons. The client determines, from the plurality of neurons, a target neuron participating in a current round of training, where the current round of training is a non-first round of training, and a quantity of target neurons is less than a total quantity of the plurality of neurons (304). The client trains the target neuron based on local data (305). The client returns parameter data corresponding to the target neuron to the service end (306). The parameter data corresponding to the target neuron is used by the service end to obtain a converged target AI model.

公开(公告)号：US20220368606A1

公开(公告)日：2022-11-17

申请号：US17871498

申请日：2022-07-22

Applicant: Huawei Technologies Co., Ltd.

Inventor： Li Xue ,  Liang Zhang ,  Jian Cheng ,  Haonan Ye ,  Xiaoyun Si

IPC: H04L41/5009 ,  H04L43/08 ,  H04L41/142

Abstract: A forwarding device receives at least one service flow; the forwarding device obtains service information of the at least one service flow, where the service information of the service flow includes identification information of a network object to which the service flow belongs and M key performance indicators KPIs of the service flow, M is an integer greater than 0, and the network object includes one or more devices; and the forwarding device sends training information to a first device, where the training information includes the service information of the at least one service flow or a feature set obtained based on the service information of the at least one service flow, the training information is used to train a fault detection model, and the fault detection model is used to detect whether the network object is in a faulty state.

公开(公告)号：US20220060372A1

公开(公告)日：2022-02-24

申请号：US17497088

申请日：2021-10-08

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin Xiao ,  Li Xue ,  Ruihong Wang ,  Qiang Wang ,  Ping Huang

IPC: H04L12/24

Abstract: A fault localization method includes: obtaining user experience data, network topology data, and resource management data that are of a video service; where the network topology data is used to represent a connection relationship between network devices, and the resource management data is used to represent a connection relationship between user equipment and the network devices; determining a QoE experience indicator of a network device based on the user experience data, the network topology data, and the resource management data; and when QoE represented by the QoE experience indicator of the network device is lower than QoE represented by a device screening threshold, determining the network device as a possible questionable device.

公开(公告)号：US11159363B2

公开(公告)日：2021-10-26

申请号：US16774599

申请日：2020-01-28

Applicant: Huawei Technologies Co., Ltd.

Inventor： Xin Xiao ,  Li Xue ,  Ruihong Wang ,  Qiang Wang ,  Ping Huang

IPC: H04L12/24

Abstract: A fault localization method includes: obtaining user experience data, network topology data, and resource management data that are of a video service; where the network topology data is used to represent a connection relationship between network devices, and the resource management data is used to represent a connection relationship between user equipment and the network devices; determining a QoE experience indicator of a network device based on the user experience data, the network topology data, and the resource management data; and when QoE represented by the QoE experience indicator of the network device is lower than QoE represented by a device screening threshold, determining the network device as a possible questionable device.

公开(公告)号：US20200036605A1

公开(公告)日：2020-01-30

申请号：US16595066

申请日：2019-10-07

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yuming Xie ,  Qian Xiao ,  Zhiman Xiong ,  Li Xue ,  Ming Chen

IPC: H04L12/24 ,  H04L12/26

Abstract: A network element health status detection method and device, where the method includes: determining sampled data of at least one key performance indicator (KPI) of a target network element in a first time window; obtaining a fluctuation score of any KPI in the at least one KPI according to sampled data of the any KPI in the first time window and a steady state value of the any KPI; and determining a health status of the target network element based on a fluctuation score of each KPI. Therefore, a network element health status is determined using single-point performance data of a network element and performance data in a network element time window.

公开(公告)号：US20190238930A1

公开(公告)日：2019-08-01

申请号：US16376425

申请日：2019-04-05

Applicant: Huawei Technologies Co., Ltd.

Inventor： Jie Xiong ,  Li Xue ,  Yihong Huang ,  Youqing Yang

IPC: H04N21/442 ,  H04N21/647 ,  H04N21/6437 ,  H04N21/44

CPC classification number: H04N21/442 ,  H04N17/00 ,  H04N17/004 ,  H04N21/44008 ,  H04N21/6437 ,  H04N21/64792

Abstract: A video quality assessment method and device are provided. The method includes: obtaining a video quality assessment parameter of a to-be-assessed video, where the video quality assessment parameter of the to-be-assessed video includes an average packet loss gap of the to-be-assessed video; determining packet loss dispersion of the to-be-assessed video based on the video quality assessment parameter of the to-be-assessed video; and determining quality of the to-be-assessed video based on a packet loss rate of the to-be-assessed video, an average consecutive packet loss length of the to-be-assessed video, the packet loss dispersion of the to-be-assessed video, and attribute information of the to-be-assessed video. In the technical solution, during video quality assessment, impact of packet loss distribution indicated by the packet loss dispersion on the video quality is considered. Therefore, video quality assessment accuracy can be improved.

公开(公告)号：US10212004B2

公开(公告)日：2019-02-19

申请号：US14992206

申请日：2016-01-11

Applicant: HUAWEI TECHNOLOGIES CO., LTD.

Inventor： Li Xue ,  Jinfeng Zhang ,  Haibo Zhang ,  Jianzheng Zhang

IPC: H04L12/46 ,  H04L12/66 ,  H04L12/741

Abstract: A method for implementing a GRE tunnel is provided. The access device obtains an address of an aggregation gateway group including at least one aggregation gateway. The access device sends a tunnel setup request in which an address of the access device is encapsulated by using the address of the aggregation gateway group as a destination address. The tunnel setup request is used to request for setting up a GRE tunnel. The access device receives a tunnel setup accept response sent back by an aggregation gateway and obtains an address of the aggregation gateway from the response. The aggregation gateway belongs to the aggregation gateway group. The access device configures the address of the aggregation gateway as a network side destination address of the GRE tunnel. A dynamic setup of a GRE tunnel on an access network that uses an aggregation technology is implemented.

公开(公告)号：US09912586B2

公开(公告)日：2018-03-06

申请号：US15185982

申请日：2016-06-17

Applicant: Huawei Technologies Co., Ltd.

Inventor： Chaowa Qiu ,  Li Xue ,  Changbao Liu ,  Wei Cao

IPC: H04L12/721 ,  H04L12/707 ,  H04L12/703 ,  H04L12/723 ,  H04L12/741

CPC classification number: H04L45/68 ,  H04L45/22 ,  H04L45/28 ,  H04L45/50 ,  H04L45/745

Abstract: A method, a system, and a device for establishing a pseudo wire are disclosed. The method includes: receiving, by a switching provider edge at a bifurcation position, a label mapping message, obtaining information of the switching provider edge at the bifurcation position and information of at least two next hops or outgoing interfaces of the switching provider edge through parsing, comparing the information of the switching provider edge at the bifurcation position with information of a local device, and if the information of the switching provider edge at the bifurcation position matches with the information of the local device, establishing at least two pseudo wires from the switching provider edge according to the information of at least two next hops or outgoing interfaces.

公开(公告)号：US20150358858A1

公开(公告)日：2015-12-10

申请号：US14830986

申请日：2015-08-20

Applicant: Huawei Technologies Co., Ltd.

Inventor： Li Xue

IPC: H04W28/08 ,  H04L12/853 ,  H04L29/06 ,  H04L12/707

CPC classification number: H04W28/08 ,  H04L45/24 ,  H04L47/2416 ,  H04L47/38 ,  H04L65/4084 ,  H04L65/602 ,  H04L65/80 ,  H04N21/238 ,  H04N21/2402 ,  H04N21/4622 ,  H04N21/631 ,  H04W28/0226

Abstract: A cooperative communication method includes determining bandwidth of a first wireless network that user equipment (UE) currently accesses, determining bandwidth required by data to be sent to the UE, and when the bandwidth of the first wireless network cannot meet the bandwidth required by the to-be-sent data, sending a first part of data packets to the first wireless network, and sending a second part of the data packets to at least one core network, so that the at least one core network sends the second part of the data packets to the UE using at least one wireless network, where a communications protocol of the first wireless network is different from that of the at least one wireless network. Bandwidth resources can be integrated on wireless networks with different communications protocols, so that fluent transmission of data can be implemented.

Abstract translation: 协作通信方法包括：确定用户设备（UE）当前接入的第一无线网络的带宽，确定要发送给UE的数据所需的带宽，以及当第一无线网络的带宽不能满足所述用户设备 发送数据，将第一部分数据分组发送到第一无线网络，以及将数据分组的第二部分发送到至少一个核心网络，使得至少一个核心网络发送第二部分数据 使用至少一个无线网络向UE发送分组，其中第一无线网络的通信协议与至少一个无线网络的通信协议不同。 带宽资源可以集成在具有不同通信协议的无线网络上，从而可以实现流畅的数据传输。

公开(公告)号：US12237981B2

公开(公告)日：2025-02-25

申请号：US17669638

申请日：2022-02-11

Applicant: Huawei Technologies Co., Ltd.

Inventor： Yanfang Zhang ,  Gang Li ,  Li Xue ,  Wei Lin

IPC: H04L41/14 ,  H04L43/08

Abstract: A traffic anomaly detection method includes obtaining a target time series including N elements; obtaining a target parameter of the target time series, where the target parameter includes at least one of a periodic factor or a jitter density, the periodic factor represents a wave-shaped change that is presented in the target time series and that is about a long-term trend, and the jitter density represents a deviation between an actual value and a target value of the target time series within a target time; determining, from a plurality of types based on the target parameter, a first type to which the target time series belongs, where each of the types corresponds to one parameter set, and the target parameter belongs to a parameter set corresponding to the first type; and detecting an anomaly of the target time series based on a first-type decision model corresponding to the first type.