中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

304 records (took 0.027 seconds)

    MACHINE LEARNING MODEL POSITIONING PERFORMANCE MONITORING AND REPORTING
    131.
    发明公开
    MACHINE LEARNING MODEL POSITIONING PERFORMANCE MONITORING AND REPORTING 审中-公开

    公开(公告)号：US20230354247A1

    公开(公告)日：2023-11-02

    申请号：US18188638

    申请日：2023-03-23

    Applicant: QUALCOMM Incorporated

    Inventor： Mohammed Ali Mohammed HIRZALLAH ,  Taesang YOO ,  Srinivas YERRAMALLI ,  Mohammad Tarek FAHIM

    IPC: H04W64/00 ,  H04W4/029

    CPC classification number: H04W64/00 ,  H04W4/029

    Abstract: Disclosed are techniques for wireless communication. In an aspect, a network entity receives a provide location information message from a user equipment (UE), the provide location information message including one or more positioning estimates derived by the UE during one or more positioning inference occasions of a machine learning model, wherein the machine learning model is applied to one or more measurements of a wireless channel between the UE and a network node during each of the one or more positioning inference occasions, and transmits a performance report indicating a performance of the machine learning model at least in deriving the one or more positioning estimates during the one or more positioning inference occasions.

    MACHINE LEARNING FOR BEAM PREDICTIONS WITH CONFIDENCE INDICATIONS
    132.
    发明公开
    MACHINE LEARNING FOR BEAM PREDICTIONS WITH CONFIDENCE INDICATIONS 审中-公开

    公开(公告)号：US20230353264A1

    公开(公告)日：2023-11-02

    申请号：US17661543

    申请日：2022-04-29

    Applicant: QUALCOMM Incorporated

    Inventor： Tianyang BAI ,  Hua WANG ,  Taesang YOO ,  Junyi LI

    IPC: H04B17/373 ,  G06N3/08 ,  H04B17/318 ,  H04W24/08

    CPC classification number: H04B17/373 ,  G06N3/08 ,  H04B17/318 ,  H04W24/08

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a signal. The UE may determine, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises: receiving, by the machine learning model, an input that comprises an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, and based at least in part on a machine learning function and the input, the predicted communication metric and the confidence indication. The UE may perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication. Numerous other aspects are described.

    BEAM SELECTION USING OVERSAMPLED BEAMFORMING CODEBOOKS AND CHANNEL ESTIMATES
    134.
    发明公开
    BEAM SELECTION USING OVERSAMPLED BEAMFORMING CODEBOOKS AND CHANNEL ESTIMATES 审中-公开

    公开(公告)号：US20230318881A1

    公开(公告)日：2023-10-05

    申请号：US17658025

    申请日：2022-04-05

    Applicant: QUALCOMM Incorporated

    Inventor： Hamed PEZESHKI ,  Taesang YOO ,  Tao LUO ,  Mahmoud TAHERZADEH BOROUJENI

    IPC: H04L25/02 ,  H04B7/0456 ,  H04B7/06

    CPC classification number: H04L25/0254 ,  H04L25/0242 ,  H04B7/0456 ,  H04B7/0617

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a first network node may receive, from a second network node, codebook information that indicates a plurality of beams associated with an oversampled transmitter network node beamforming codebook. The first network node may transmit a beam selection report that indicates at least one suggested transmission beam associated with the oversampled transmitter network node beamforming codebook, wherein the beam selection report is based at least in part on a channel estimate that is obtained without obtaining beam measurements associated with beams that are associated with the oversampled transmitter network node beamforming codebook. Numerous other aspects are described.

    GRADIENT ACCUMULATION FOR FEDERATED LEARNING
    137.
    发明公开
    GRADIENT ACCUMULATION FOR FEDERATED LEARNING 审中-公开

    公开(公告)号：US20230232377A1

    公开(公告)日：2023-07-20

    申请号：US17648117

    申请日：2022-01-14

    Applicant: QUALCOMM Incorporated

    Inventor： Eren BALEVI ,  Taesang YOO ,  Tao LUO ,  Hamed PEZESHKI

    IPC: H04W72/04 ,  G06N20/00 ,  H04W24/02

    CPC classification number: H04W72/044 ,  G06N20/00 ,  H04W24/02

    Abstract: A UE may identify, in each round other than an initial round, a first plurality of local model update elements of a present round. The first plurality of local model update elements of the present round may be associated with an updated local machine learning model. The UE may transmit to a base station, in each round other than the initial round, over a multiple access channel via analog signaling, a second plurality of local model update elements of the present round based on a third plurality of local model update elements of the present round. The third plurality of local model update elements of the present round may correspond to a sum of the first plurality of local model update elements of the present round and a local model update error of a previous round immediately before the present round. The analog signaling may be associated with OTA aggregation.

    GAIN SCALING OF INPUT TO NEURAL NETWORK FOR END-TO-END LEARNING IN WIRELESS COMMUNICATION SYSTEM
    139.
    发明申请
    GAIN SCALING OF INPUT TO NEURAL NETWORK FOR END-TO-END LEARNING IN WIRELESS COMMUNICATION SYSTEM 有权

    公开(公告)号：US20230114870A1

    公开(公告)日：2023-04-13

    申请号：US17498651

    申请日：2021-10-11

    Applicant: QUALCOMM Incorporated

    Inventor： June NAMGOONG ,  Taesang YOO ,  Hyojin LEE ,  Naga BHUSHAN ,  Weiliang ZENG

    IPC: G06N3/08 ,  H04W24/10

    Abstract: A method of wireless communication by a user equipment (UE) includes receiving different sets of parameters from different sources as input to a receiver neural network. The method also includes receiving, from a base station, a set of target long-term energy values associated with the receiver neural network. The method further includes calculating a scaling factor for each of the different sets of parameters based on the set of target long-term energy values, and separately scaling each of the different sets of parameters based on the scaling factor calculated for that set in order to generate multiple sets of scaled parameters. The method still further includes transmitting the multiple sets of scaled parameters to the receiver neural network.

Patent Agency Ranking