中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

793 records (took 0.016 seconds)

    DETERMINING ONLINE CLASSIFIER PERFORMANCE VIA NORMALIZING FLOWS
    82.
    发明公开
    DETERMINING ONLINE CLASSIFIER PERFORMANCE VIA NORMALIZING FLOWS 审中-公开

    公开(公告)号：US20240119341A1

    公开(公告)日：2024-04-11

    申请号：US17953255

    申请日：2022-09-26

    Applicant: Lemon Inc.

    Inventor： Xin YANG ,  Hanlin ZHU ,  Tianyi LIU ,  Jiankai SUN ,  Yuanshun YAO ,  Aonan ZHANG ,  Chong WANG

    IPC: G06N20/00

    CPC classification number: G06N20/00

    Abstract: The present disclosure describes techniques for determining performance of a classifier. A first machine learning model and a second machine learning model may be trained by aggregating updates to the first machine learning model and the second machine learning model received from a plurality of client computing devices. A cumulative distribution function (CDF) associated with a distribution of the positive samples in the user data may be estimated using the trained first machine learning model. A probability density function (PDF) associated with a distribution of the negative samples in the user data may be estimated using the trained second machine learning model. An integration-based computation of an area under the receiver operating characteristic curve (AUC) of the classifier may be performed using the PDF and the CDF.

    SAMPLE CLASSIFICATION
    84.
    发明公开
    SAMPLE CLASSIFICATION 审中-公开

    公开(公告)号：US20240104894A1

    公开(公告)日：2024-03-28

    申请号：US17949078

    申请日：2022-09-20

    Applicant: Lemon Inc.

    Inventor： Song Bai ,  Yujun Shi

    IPC: G06V10/764 ,  G06V10/72 ,  G06V10/771

    CPC classification number: G06V10/764 ,  G06V10/72 ,  G06V10/771

    Abstract: A method is proposed for sample processing. A first group of data are received, here data in the first group of data comprises a sample and a classification of the sample, and the classification belonging to a first group of classifications in a plurality of classifications associated with the data. A plurality of data with the classification are selected from the first group of data. A first and a second loss function are determined for training a classification model that represents an association relationship between samples and classifications of the samples based on a plurality of samples comprised in the plurality of data and the classification, the first and second loss functions represent classification accuracy and a feature distribution for the classification model. The classification model is trained based on the first and second loss functions. Therefore, the accuracy of the classification model may be increased.

    INFORMATION DISTRIBUTION METHOD, APPARATUS AND COMPUTER READABLE STORAGE MEDIUM
    85.
    发明公开
    INFORMATION DISTRIBUTION METHOD, APPARATUS AND COMPUTER READABLE STORAGE MEDIUM 审中-公开

    公开(公告)号：US20240086972A1

    公开(公告)日：2024-03-14

    申请号：US18462916

    申请日：2023-09-07

    Applicant: Lemon Inc.

    Inventor： Xudong YANG ,  Haocheng Zhang ,  Hongyu Xiong ,  Jin Jiang ,  Bin Liu

    IPC: G06Q30/0251 ,  G06N3/02

    CPC classification number: G06Q30/0271 ,  G06N3/02 ,  G06Q30/0255

    Abstract: The present disclosure relates to an information distribution method, apparatus, and computer readable storage medium, which relates to the field of information processing. The information distribution method includes: determining a recommended value of a target indicator corresponding to a user based on a historical indicator of information historically distributed by the user and a historical indicator of a category to which the user belongs, wherein an indicator is determined based on resources gained and consumed through distributed information; recommending the recommended value of the target indicator to the user; determining target recipients of target information to be distributed by the user based on a target indicator input by the user, wherein the target indicator input by the user is determined based on the recommended value of the target indicator by the user; and sending the target information to the target recipients.

    Decoder configuration record in coded video
    88.
    发明授权
    Decoder configuration record in coded video 有权

    公开(公告)号：US11902552B2

    公开(公告)日：2024-02-13

    申请号：US17476134

    申请日：2021-09-15

    Applicant: Lemon Inc.

    Inventor： Ye-Kui Wang

    IPC: H04N19/44 ,  H04N19/70 ,  H04N7/01

    CPC classification number: H04N19/44 ,  H04N7/01 ,  H04N19/70

    Abstract: Systems, methods and apparatus for encoding or decoding a file format that stores one or more images are described. One example method includes performing a conversion between a visual media file and a bitstream of a visual media data according to a format rule, wherein the format rule specifies a characteristic of a syntax element in the visual media file, wherein the syntax element has a value that is indicative of a number of bytes used for indicating a constraint information associated with the bitstream.

Patent Agency Ranking