Performance Measurement Method and Apparatus, and System

    公开(公告)号:US20230269151A1

    公开(公告)日:2023-08-24

    申请号:US18309543

    申请日:2023-04-28

    IPC分类号: H04L43/08 H04L45/741

    摘要: Embodiments of this application provide a performance measurement method and apparatus, and a system. In the method, a bit forwarding ingress router BFIR obtains a first packet, where the first packet includes an identifier of the BFIR, a bit string, and a first parameter that is used for performance measurement, the bit string is used to identify one or more bit forwarding egress routers BFERs, and the first packet is not used to transmit multicast data; and the BFIR sends the first packet to the one or more BFERs based on the bit string included in the first packet.

    Method for Determining Processing Capability, Node, and System

    公开(公告)号:US20230086487A1

    公开(公告)日:2023-03-23

    申请号:US18072981

    申请日:2022-12-01

    IPC分类号: H04L45/74 H04L45/12

    摘要: A method for determining a processing capability includes: a first node sends a message to a second node. The message includes extension header processing capability information, and the extension header processing capability information is used to indicate a processing capability of the first node for an Internet Protocol (IP) version 6 (IPv6) extension header. After receiving the message, the second node obtains, based on the extension header processing capability information, the processing capability of the first node for the IPv6 extension header to determine whether the first node needs to forward or receive a packet.

    Data stream classification method and related device

    公开(公告)号:US11838215B2

    公开(公告)日:2023-12-05

    申请号:US17695491

    申请日:2022-03-15

    摘要: A data stream classification method includes obtaining, based on a packet feature of a current data stream and a behavior classification model, at least one first confidence that is of the current data stream and that corresponds to at least one data stream class, where the behavior classification model is based on a plurality of data stream samples; obtaining, based on feature information of the current data stream and a content classification model, at least one second confidence that is of the current data stream and that corresponds to the at least one data stream class, where the content classification model is based on one or more historical data streams; and determining a data stream class of the current data stream based on the at least one first confidence and the at least one second confidence.

    Packet Processing Method and Apparatus
    5.
    发明公开

    公开(公告)号:US20230318970A1

    公开(公告)日:2023-10-05

    申请号:US18332287

    申请日:2023-06-09

    IPC分类号: H04L45/50 H04L45/00 H04L69/22

    CPC分类号: H04L45/50 H04L45/34 H04L69/22

    摘要: A packet processing method includes carrying an associated channel in an IPv6 packet to provide different types of control channels. The associated channel may be transmitted together with user data. Each type of control channel carries at least one type of control and management message, and one type of control and management message may implement one type of control and management function. For example, if a plurality of control and management functions need to be implemented for the IPv6 network, a plurality of different types of control and management messages may all be carried by using the associated channel, without using a plurality of protocols to carry the plurality of types of control and management messages.

    Action recognition and pose estimation method and apparatus

    公开(公告)号:US11478169B2

    公开(公告)日:2022-10-25

    申请号:US16846890

    申请日:2020-04-13

    摘要: Action recognition methods are disclosed. An embodiment of the methods includes: identifying a video that comprises images of a human body to be processed; identifying at least one image to be processed, wherein the at least one image is at least one of an optical flow image generated based on a plurality of frames of images in the video, or a composite image of one or more frames of images in the video; performing convolution on the at least one image to obtain a plurality of eigenvectors, wherein the plurality of eigenvectors indicate a plurality of features of different locations in the at least one image; determining a weight coefficient set of each of a plurality of human joints of the human body based on the plurality of eigenvectors, wherein the weight coefficient set comprises a weight coefficient of each of the plurality of eigenvectors for the human joint; weighting the plurality of eigenvectors based on the weight coefficient set to obtain an action feature of each of the plurality of human joints; determining an action feature of the human body based on the action feature of each of the human joints; and determining an action type of the human body based on the action feature of the human body.

    METHOD AND APPARATUS FOR IMPLEMENTING MODEL TRAINING, AND COMPUTER STORAGE MEDIUM

    公开(公告)号:US20220121994A1

    公开(公告)日:2022-04-21

    申请号:US17562724

    申请日:2021-12-27

    IPC分类号: G06N20/00 G06K9/62

    摘要: A method and an apparatus for implementing model training, and a computer storage medium are disclosed, and belong to the field of machine learning. When a machine learning model deteriorates, an analysis device first obtains validity information of a first feature set, where the first feature set includes a plurality of features used for training to obtain the machine learning model, the validity information includes a validity score of each feature in the first feature set, and a validity score of a feature is negatively related to correlation of the feature with another feature in the first feature set. Then an invalid feature in the first feature set is determined based on the validity information. A second feature set that does not include the invalid feature is finally generated, where the second feature set is used to retrain the machine learning model.

    Cell Site Gateway (CSG) Determining Method and Apparatus

    公开(公告)号:US20210400553A1

    公开(公告)日:2021-12-23

    申请号:US17466498

    申请日:2021-09-03

    摘要: A cell site gateway (CSG) determining method includes a first device obtains, before a first moment, a location range in which a mobile device is located at the first moment; and the first device obtains an identifier of at least one target CSG based on the location range before the first moment, where the at least one target CSG can provide downlink data transmission for the mobile device at the first moment. The target CSG that can provide the downlink data transmission for the mobile device at the first moment is further determined through estimation of the location range in which the mobile device is located at a subsequent first moment.

    Action Recognition Method and Apparatus

    公开(公告)号:US20210012164A1

    公开(公告)日:2021-01-14

    申请号:US17034654

    申请日:2020-09-28

    IPC分类号: G06K9/62 G06K9/00 G06K9/46

    摘要: An action recognition method and apparatus related to artificial intelligence and include extracting a spatial feature of a to-be-processed picture, determining a virtual optical flow feature of the to-be-processed picture based on the spatial feature and X spatial features and X optical flow features in a preset feature library, where the X spatial features and the X optical flow features include a one-to-one correspondence, determining a first type of confidence of the to-be-processed picture in different action categories based on similarities between the virtual optical flow feature and Y optical flow features, where each of the Y optical flow features in the preset feature library corresponds to one action category, X and Y are both integers greater than 1, and determining an action category of the to-be-processed picture based on the first type of confidence.