Beam-based machine learning-enabled RFFP positioning

    公开(公告)号:US11843993B2

    公开(公告)日:2023-12-12

    申请号:US17457718

    申请日:2021-12-06

    CPC classification number: H04W4/029 H04B7/0617 H04B17/318

    Abstract: Aspects presented herein may enable an ML module to associate RF fingerprints with beam directions and/or beam features to improve the uniqueness of RF fingerprints. In one aspect, network entity may receive, from one or more wireless devices, a plurality of first RF fingerprints, each of the plurality of first RF fingerprints being associated with at least one directional feature and a location. The network entity may receive a request to determine a position of a UE based on at least one second RF fingerprint associated with the UE or captured by the UE. The network entity may estimate the position of the UE based at least in part on matching the at least one second RF fingerprint to at least one of the plurality of first RF fingerprints.

    Multiple bandwidth part measurements

    公开(公告)号:US11818740B2

    公开(公告)日:2023-11-14

    申请号:US16674988

    申请日:2019-11-05

    Abstract: Methods, systems, and devices for wireless communications are described. A user equipment (UE) may receive a set of synchronization signal block (SSB) configurations for a corresponding set of frequency resource sets configured for communications in a shared frequency spectrum band. The UE may perform a listen-before-talk (LBT) procedure for each frequency resource set. If an LBT procedure is successful, the UE may select and communicate with a base station on the corresponding frequency resource sets. Accordingly, the UE may receive one or more SSBs from the base station on the selected frequency resource sets based on SSB configurations, which may indicate a floating or fixed configuration for SSBs. The UE may perform radio resource management (RRM) and radio link monitoring based on receiving the SSBs in one or more of the selected frequency resource sets according to the corresponding SSB configurations.

    Adaptive sensor activation and configuration for positioning

    公开(公告)号:US11792614B2

    公开(公告)日:2023-10-17

    申请号:US17220894

    申请日:2021-04-01

    CPC classification number: H04W4/38

    Abstract: Aspects of sensor activation or deactivation for positioning a mobile device in a wireless communication network are disclosed. These aspects include, during a positioning session between the mobile device and a location server, determining with the location server that a first trigger condition or a second trigger condition has been met regarding reporting, by the mobile device to the location server, of sensor data from one or more sensors of the mobile device, where: the first trigger condition may comprise a trigger condition for activating the reporting, and the second trigger condition may comprise a trigger condition for deactivating the reporting. Aspects further include sending, from the location server to the mobile device, a message may comprise either: instructions to activate the reporting responsive to determining the first trigger condition has been met, or instructions to deactivate the reporting responsive to determining the second trigger condition has been met.

    LAYER-BY-LAYER TRAINING FOR FEDERATED LEARNING
    488.
    发明公开

    公开(公告)号:US20230316062A1

    公开(公告)日:2023-10-05

    申请号:US17697751

    申请日:2022-03-17

    CPC classification number: G06N3/08 G06N3/04 H04B7/0626

    Abstract: Methods, systems, and devices for wireless communications are described. A network entity may transmit an indication of neural network weights to one or more user equipments (UEs). The neural network weights may be for one or more shared layers of a federated learning neural network. The UEs may train a personalized layer of the neural network using the weights and data at the UEs. The UEs may transmit layer updates to the network entity. The network entity may train the neural network based on the updates. The UEs may send a transmission to the network entity that may be processed according to the neural network at the UEs and the network entity.

    Aligned LBT gaps for single operator FBE NR-SS

    公开(公告)号:US11729828B2

    公开(公告)日:2023-08-15

    申请号:US17649145

    申请日:2022-01-27

    CPC classification number: H04W74/0808 H04W16/14 H04W72/0446 H04W72/23

    Abstract: Aligned listen before talk (LBT) gaps for single operator frame-based equipment (FBE) mode new radio (NR) shared spectrum (NR-SS) is disclosed. Within the FBE mode network, the base station determines a plurality of potential transmission bursts within a fixed frame period. The base station may then reserve a plurality of LBT gaps prior to the starting position of each such transmission burst. The base station communicates the location of each of the LBT gaps to all neighboring network entities and contends for access to the fixed frame period at the beginning of the frame regardless of whether it has data for transmission during the frame. Each neighboring base station that receives the LBT gaps locations will use the same locations in order to align the LBT gaps over the FBE mode network.

Patent Agency Ranking