中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

5367 records (took 0.058 seconds)

    ADAPTIVE SPATIAL DENSITY BASED CLUSTERING
    447.
    发明公开
    ADAPTIVE SPATIAL DENSITY BASED CLUSTERING 审中-公开

    公开(公告)号：US20230297600A1

    公开(公告)日：2023-09-21

    申请号：US18322067

    申请日：2023-05-23

    Applicant: Snap Inc.

    Inventor： Xabier Jaureguiberry

    IPC: G06F16/28 ,  H04W4/21 ,  G06F16/387 ,  H04W4/029

    CPC classification number: G06F16/285 ,  H04W4/21 ,  G06F16/387 ,  H04W4/029

    Abstract: Methods, systems, and devices for identifying the habitual places of a user, the habitual places of a user being the places where the user spends most of his/her time. In some embodiments, historical location information of a user is accessed, and a plurality of visit points are identified based on the historical location information. The plurality of visit points is clustered into a plurality of clusters. Each one of the clusters is then associated with a habitual place of the user. When the server receives, from a client device associated with the user, current location information of the user, the server identifies a current location of the user based on the current location information, and, if the current location of the user is in a neighborhood of one of the clusters, determine that the user is at the habitual place associated with the cluster.

    Compact neural networks using condensed filters
    448.
    发明授权
    Compact neural networks using condensed filters 有权

    公开(公告)号：US11763130B2

    公开(公告)日：2023-09-19

    申请号：US16949994

    申请日：2020-11-23

    Applicant: Snap Inc.

    Inventor： Yingzhen Yang ,  Jianchao Yang ,  Ning Xu

    IPC: G06K9/00 ,  G06N3/04 ,  G06T7/10 ,  G06T5/20

    CPC classification number: G06N3/04 ,  G06T5/20 ,  G06T7/10

    Abstract: A compact neural network system can generate multiple individual filters from a compound filter. Each convolutional layer of a convolutional neural network can include a compound filters used to generate individual filters for that layer. The individual filters overlap in the compound filter and can be extracted using a sampling operation. The extracted individual filters can share weights with nearby filters thereby reducing the overall size of the convolutional neural network.

    POST-CAPTURE PROCESSING IN A MESSAGING SYSTEM
    449.
    发明公开
    POST-CAPTURE PROCESSING IN A MESSAGING SYSTEM 审中-公开

    公开(公告)号：US20230291702A1

    公开(公告)日：2023-09-14

    申请号：US18318439

    申请日：2023-05-16

    Applicant: Snap Inc.

    Inventor： Jean Luo ,  Oleksandr Grytsiuk ,  Ivan Golub ,  Mykhailo Sokolov

    IPC: H04L51/10 ,  G06T3/60 ,  G06F3/04883 ,  G06T11/60 ,  G06T7/70 ,  H04L51/52

    CPC classification number: H04L51/10 ,  G06T3/60 ,  G06F3/04883 ,  G06T11/60 ,  G06T7/70 ,  H04L51/52

    Abstract: The subject technology retrieves, by a client device from a storage device, first image data captured by the client device at a previous time. The subject technology receiving first metadata corresponding to a selected image processing operation. The subject technology generates second image data based on the first metadata and the image processing operation performed on the first image data. The subject technology generates second metadata comprising information related to the image processing operation, the second metadata including a first identifier associated with the first image data, and second identifier associated with the second image data. The subject technology generates a message comprising the second metadata, the second image data, and the first image data.

Patent Agency Ranking