TWO-STAGE FREQUENCY DOMAIN MACHINE LEARNING-BASED CHANNEL STATE FEEDBACK

    公开(公告)号:US20250119224A1

    公开(公告)日:2025-04-10

    申请号:US18484269

    申请日:2023-10-10

    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may communicate signaling with a network entity, the signaling indicating a first bandwidth size and a second bandwidth size associated with a projection parameter (W1) and a compression parameter (W2), respectively. The second bandwidth size may be less than the first bandwidth size. In some cases, the UE may determine W1 and W2 based on a first machine learning (ML) model and a second ML model, respectively. The UE may project a portion of received channel state information (CSI) associated with the first bandwidth size onto a sub-space defined by W1 and may compress a portion of the projection associated with the second bandwidth size based on W2. The UE may transmit channel state feedback including the projection, the compression of the projection, a compression of W1, a compression of W2, or any combination thereof.

    INDICATING CAUSES FOR LIFE CYCLE MANAGEMENT OPERATIONS

    公开(公告)号:US20250048131A1

    公开(公告)日:2025-02-06

    申请号:US18362759

    申请日:2023-07-31

    Abstract: Methods, systems, and devices for wireless communication are described. A network entity may monitor a performance of a machine learning (ML) model or ML model-based functionality associated with a user equipment (UE). The UE may receive one or more control messages that indicate a life cycle management (LCM) operation for the ML model or ML model-based functionality. The one or more control messages may include an indication of whether the LCM operation is based on the performance of the MIL model or ML model-based functionality. In some examples, the indication may include or be an example of a performance report associated with the performance of the ML model or ML model-based functionality. The UE may perform the LCM operation for the ML model or ML model-based functionality. The UE or the network entity may transmit the indication to a server associated with the ML model or ML model-based functionality.

    POSITIONING METHODS FOR UPLINK POWER-LIMITED USER EQUIPMENT

    公开(公告)号:US20250008468A1

    公开(公告)日:2025-01-02

    申请号:US18690220

    申请日:2022-08-01

    Abstract: Disclosed are techniques for wireless positioning. In an aspect, a user equipment (UE) may send, to a first entity, first information indicating a maximum number of positioning signal transmissions or a maximum power for positioning signal transmissions that the UE can support. The UE may receive, from the first entity, configuration information for changing a positioning mode of the UE to a positioning mode selected from a first positioning mode and a second positioning mode. The UE may perform a positioning operation according to the selected positioning mode. In some aspects, the first positioning mode is a normal positioning mode in which the UE sends UL positioning reference signals to a plurality of TRPS, and the second positioning mode is a UL power-limited mode in which the UE sends UL positioning reference signals to only one or a small number of TRPs.

    POSITIONING MODEL PERFORMANCE MONITORING
    138.
    发明公开

    公开(公告)号:US20240114477A1

    公开(公告)日:2024-04-04

    申请号:US18466088

    申请日:2023-09-13

    CPC classification number: H04W64/00 G06N20/00

    Abstract: Various aspects of the present disclosure generally relate to wireless communication. In some aspects, an apparatus may obtain a set of training measurement information associated with a user equipment (UE). The apparatus may obtain a training position value associated with the UE. The apparatus may provide the training position value and the set of training measurement information for training of a model using a machine learning (ML) technique, the model being trained to output location information based at least in part on measurement information. Numerous other aspects are described.

    REPETITION OF XR INFORMATION
    140.
    发明公开

    公开(公告)号:US20240023088A1

    公开(公告)日:2024-01-18

    申请号:US17812988

    申请日:2022-07-15

    CPC classification number: H04W72/1268 H04W72/14 H04L1/08

    Abstract: Apparatus, methods, and computer program products for repetition of XR information are provided. An example method may include receiving XR data associated with an XR application from a network entity. The example method may further include transmitting, for the network entity at a first time, a first transmission including a first instance of XR information and a second instance of XR information. The example method may further include transmitting, for the network entity at a second time, a second transmission including the second instance of XR information and a third instance of XR information, where a time difference between the first time and the second time may be based on a periodicity associated with the XR information.

Patent Agency Ranking