BACKUP PROCEDURE FOR AMBIENT IOT DEVICE CONNECTIVITY THROUGH A SMARTPHONE

    公开(公告)号:US20240406275A1

    公开(公告)日:2024-12-05

    申请号:US18327974

    申请日:2023-06-02

    Abstract: A user equipment apparatus includes at least one processor and at least one memory. The at least one memory stores instructions which, when executed by the at least one processor, cause the user equipment apparatus at least to: receive, from a network device, an instruction to provide backscattering service to at least one ambient IoT device for a service period of time T, the instruction including a configuration for sidelink communication with one or more backup user equipment apparatuses (backup UEs) capable of providing backscattering service to at least one ambient IoT device; and provide, based on the instruction, the backscattering service by transmitting at least one request for tag identification.

    DRX EXTENSION FOR ENERGY HARVESTING REDCAP UES

    公开(公告)号:US20240397429A1

    公开(公告)日:2024-11-28

    申请号:US18689682

    申请日:2022-12-08

    Abstract: In a system, apparatus, method, and non-transitory computer readable medium for implementing DRX extensions for energy harvesting (EH) REDCAP UEs, a UE device may be caused to, obtain CDRX configuration from a RAN node, the CDRX configuration including at least a desired EH CDRX energy threshold value and a short CDRX timer threshold value, determine whether a current stored energy capacity equals or exceeds the desired EH CDRX energy threshold value at a start of an ON duration of a CDRX cycle, determine EH CDRX settings based on results of the determining and the plurality of adaptive EH CDRX configuration settings, and transmit at least one EH CDRX message to the RAN node based on the determined EH CDRX settings.

    Machine Learning Model Distribution
    14.
    发明公开

    公开(公告)号:US20240097993A1

    公开(公告)日:2024-03-21

    申请号:US18277172

    申请日:2022-02-04

    CPC classification number: H04L41/16 H04L41/0893 H04W24/02

    Abstract: According to an example embodiment, a client device is configured to receive a validation model from a centralised unit device, wherein the validation model includes a machine learning model configured to predict an output from an input based on a plurality of model parameters; collect radio measurements corresponding to the input of the validation model and parameters corresponding to the output of the validation model; obtain predicted parameters as the output of the validation model by feeding the collected radio measurements as the input into the validation model; compare the collected parameters and the predicted parameters; compute a plurality of gradient vectors for the plurality of model parameters of the validation model based on the comparison between the collected parameters and the predicted parameters; and transmit the plurality of gradient vectors for the plurality of model parameters of the validation model to the centralised unit device.

    CLUSTER BASED TRAINING HOST SELECTION IN ASYNCHRONOUS FEDERATED LEARNING MODEL COLLECTION

    公开(公告)号:US20240037450A1

    公开(公告)日:2024-02-01

    申请号:US18266038

    申请日:2021-12-29

    CPC classification number: G06N20/00

    Abstract: Systems, methods, apparatuses, and computer program products for cluster based local ML model training host selection in asynchronous federated learning model collection. A method may include transmitting local model parameters following training of a model of at least one network element to a network node to be used to cluster the at least one network element with one or more other network elements. The method may also include training, by one or more network elements selected from the cluster, an aggregated model using the local model parameters. The method may further include transmitting, by the one or more network elements selected from the cluster, updated local model parameters of the at least one network element as a result of the training to the network node.

    SAMPLING USER EQUIPMENTS FOR FEDERATED LEARNING MODEL COLLECTION

    公开(公告)号:US20230409962A1

    公开(公告)日:2023-12-21

    申请号:US18031383

    申请日:2020-10-29

    CPC classification number: G06N20/00 H04L41/16

    Abstract: First user equipments are detected out of a plurality of user equipments of a cellular communication system (S201). The user equipments respectively correspond to a distributed node of a federated machine-learning concept and respectively generate a partial machine-learning model, wherein partial machine-learning models generated by the plurality of user equipments are to be used to update a global machine-learning model at the network side of the cellular communication system. The first user equipments are user equipments comprising ready partial machine-learning models. Out of the first user equipments, second user equipments are selected at least based on a time information associated with the first user equipments (S203), the ready partial machine-learning models respectively generated by the second user equipments are acquired (S205), the global machine-learning model is updated using the ready partial machine-learning models acquired (S207), and convergence of the global machine-learning model updated by the ready partial machine-learning models acquired is determined (S209). In case convergence of the S207 global machine-learning model is not determined, a process comprising the detecting (S201), selecting (S203), acquiring (S205), updating (S207) and determining (S209) is repeated.

    METHODS AND APPARATUSES FOR MITIGATING REDUCED COMPLEXITY FEATURES IMPACT ON POSITIONING PERFORMANCE

    公开(公告)号:US20230079232A1

    公开(公告)日:2023-03-16

    申请号:US17471860

    申请日:2021-09-10

    Abstract: Systems, methods, apparatuses, and computer program products for positioning support are provided. One method may include receiving, by a UE configured with power saving feature(s), positioning performance requirements for a positioning session. The method may also include estimating an impact of one or more power saving or reduced capability features on positioning measurements associated with the positioning session and, based on the accuracy and latency requirements and the estimated impact, determining the power saving or reduced capability features that the UE can implement while still achieving the accuracy and latency requirements for the positioning session. The method may then include signaling, to a network node, information on the determined power saving or reduced capability features that the UE can implement while still achieving the required accuracy and latency requirements for the positioning session.

    RF-FINGERPRINTING MAP UPDATE
    18.
    发明申请

    公开(公告)号:US20220264514A1

    公开(公告)日:2022-08-18

    申请号:US17672905

    申请日:2022-02-16

    Abstract: Apparatuses and methods in a communication system are disclosed. Data on error between the location of more than one user terminal and the estimated location of the more than one user terminal is obtained, the estimated location obtained utilising radio frequency fingerprinting. It is evaluated whether the error is greater than a given threshold, and if so it is determined whether the error is due to radio frequency fingerprinting or not. Based on the determination decision is made on initialising update of radio frequency fingerprinting map.

    APPARATUS, METHOD, AND COMPUTER PROGRAM

    公开(公告)号:US20250126030A1

    公开(公告)日:2025-04-17

    申请号:US18292267

    申请日:2021-10-07

    Abstract: The disclosure relates to an apparatus comprising at least one processor and at least one memory including computer code for one or more programs, the at least one memory and the computer code configured, with the at least one processor, to cause the apparatus at least to: receive (500), from a model provider function, a user equipment identifier and a model identifier; generate (502) an access key to allow a user equipment identified by the user equipment identifier to access a model identified by the model identifier; store (504) the user equipment identifier and the model identifier along the access key to allow a user equipment identified by the user equipment identifier to access a model identified by the model identifier; and send (506), to the user equipment, the access key.

Patent Agency Ranking