中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

50 records (took 0.023 seconds)

    CONDITIONAL ARTIFICIAL INTELLIGENCE, MACHINE LEARNING MODEL, AND PARAMETER SET CONFIGURATIONS
    21.
    发明公开
    CONDITIONAL ARTIFICIAL INTELLIGENCE, MACHINE LEARNING MODEL, AND PARAMETER SET CONFIGURATIONS 审中-公开

    公开(公告)号：US20230412470A1

    公开(公告)日：2023-12-21

    申请号：US17841339

    申请日：2022-06-15

    Applicant: QUALCOMM Incorporated

    Inventor： Rajeev Kumar ,  Xipeng Zhu ,  Shankar Krishnan

    IPC: H04L41/16 ,  G06N20/20

    CPC classification number: H04L41/16 ,  G06N20/20 ,  H04W88/02

    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a message from a network entity indicating a set of machine learning models, a set of parameter sets, or both and one or more usage conditions associated with the machine learning models and parameter sets. Based on a usage condition being satisfied, the UE may select a machine learning model, a parameter set, or both for generating a machine learning inference. For example, the UE may select the machine learning model or the parameter set based on a priority, whether sufficient input data is provided, or based on other usage conditions. The UE may generate the machine learning inference using the selected machine learning model or the selected parameter set, and the UE may transmit a report indicating an output of the machine learning inference to the network entity.

    ML model training procedure
    23.
    发明授权
    ML model training procedure 有权

    公开(公告)号：US11818806B2

    公开(公告)日：2023-11-14

    申请号：US17323242

    申请日：2021-05-18

    Applicant: QUALCOMM Incorporated

    Inventor： Rajeev Kumar ,  Eren Balevi ,  Taesang Yoo ,  Xipeng Zhu ,  Gavin Bernard Horn ,  Shankar Krishnan ,  Aziz Gholmieh

    IPC: H04W16/22 ,  H04W88/08 ,  G06N20/00 ,  G06F18/214

    CPC classification number: H04W88/08 ,  G06F18/214 ,  G06N20/00

    Abstract: This disclosure provides systems, devices, apparatus, and methods, including computer programs encoded on storage media, for an ML model training procedure. A network entity may receive a trigger to activate an ML model training procedure based on at least one of an indication from an ML model repository or a protocol of the network entity. The network entity may transmit an ML model training request to activate the ML model training at one or more nodes. The one or more nodes may be associated with a RAN that may transmit, based on receiving the ML model training request, ML model training results indicative of a trained ML model. In aspects, an apparatus, such as a UE, may train the ML model based on an ML model training configuration received from the RAN, and transmit an ML model training report indicative of the trained ML model.

    PARAMETER REPORTING TECHNIQUES FOR REDUCED CAPABILITY USER EQUIPMENT
    27.
    发明申请
    PARAMETER REPORTING TECHNIQUES FOR REDUCED CAPABILITY USER EQUIPMENT 有权

    公开(公告)号：US20230120574A1

    公开(公告)日：2023-04-20

    申请号：US17502765

    申请日：2021-10-15

    Applicant: QUALCOMM Incorporated

    Inventor： Shankar Krishnan ,  Linhai He ,  Xipeng Zhu ,  Gavin Bernard Horn ,  Ozcan Ozturk ,  Miguel Griot ,  Rajeev Kumar

    IPC: H04W24/10

    Abstract: Methods, systems, and devices for wireless communications are described for capability indications by a reduced capability user equipment (UE) and UE-based performance measurement parameter reporting or self-organizing network (SON) parameter reporting based on the capability indications. A reduced capability UE may transmit a set of capabilities to a base station that indicate various types of parameter reporting that are supported at the UE. The base station may identify the UE as a reduced capability device, and set one or more reporting parameters based on the indicated UE capabilities. The base station may provide a reporting configuration to the UE with the one or more reporting parameters, and the UE may provide reporting of measured parameters (e.g., performance measurement parameter reporting or SON parameter reporting) based on the reporting configuration.

    MULTICAST-BROADCAST SERVICES CONFIGURATION EXCHANGE FOR MOBILITY, SINGLE-FREQUENCY NETWORK AND INTERFERENCE COORDINATION
    29.
    发明申请
    MULTICAST-BROADCAST SERVICES CONFIGURATION EXCHANGE FOR MOBILITY, SINGLE-FREQUENCY NETWORK AND INTERFERENCE COORDINATION 有权

    公开(公告)号：US20220360947A1

    公开(公告)日：2022-11-10

    申请号：US17568509

    申请日：2022-01-04

    Applicant: QUALCOMM Incorporated

    Inventor： Xipeng Zhu ,  Prasad Reddy Kadiri ,  Luis Fernando Brisson Lopes ,  Shankar Krishnan

    IPC: H04W4/06 ,  H04W36/00 ,  H04W76/20

    Abstract: Methods, systems, and devices for wireless communications are described. In some systems, a first base station and a second base station may be neighbor base stations and the first base station may receive, from the second base station, information relating to a multicast-broadcast services (MBS) session context of an MBS session supported by the second base station. The first base station may use the received MBS session context information to control communication or connections between the first base station and one or more user equipment (UEs) that are served by the first base station. For example, the first base station may use the received MBS session context information for target cell selection in a handover procedure, an MBS-specific measurement configuration, interference avoidance, or system information block (SIB) construction, among various other use cases.

Patent Agency Ranking