AI-BASED INACTIVITY TIMER DETERMINATION METHOD AND DEVICE IN WIRELESS COMMUNICATION SYSTEM

    公开(公告)号:US20230224728A1

    公开(公告)日:2023-07-13

    申请号:US17998615

    申请日:2021-05-13

    CPC classification number: H04W24/02 H04L69/28 H04W80/10

    Abstract: The present disclosure relates to a communication technique for converging IoT technology with a 5G communication system for supporting a higher data transmission rate beyond a 4G system, and a system therefor. The present disclosure may be applied to an intelligent service (for example, a smart home, a smart building, a smart city, a smart car or connected car, health care, digital education, retail business, a security and safety-related service, etc.) on the basis of 5G communication technology and IoT-related technology. A method carried out by a network data analytics function (NWDAF) device, and a device for carrying out same may be provided according to various embodiments of the present disclosure, the method comprising the steps of: acquiring, for a protocol data unit (PDU) session, traffic pattern-related information, traffic type-related information and current time-related information; determining an inactivity timer value for the PDU session on the basis of the traffic pattern-related information, traffic type-related information and current time-related information; and transmitting the inactivity timer value to a session management function (SMF) device.

    SYSTEM FOR TRAINING MACHINE LEARNING MODELS USING FEDERATED LEARNING

    公开(公告)号:US20240169212A1

    公开(公告)日:2024-05-23

    申请号:US18511455

    申请日:2023-11-16

    CPC classification number: G06N3/098 H04W8/22

    Abstract: A method and system for more efficient federated learning (FL) of a machine learning (ML) model using user equipment (UEs) in cellular networks are disclosed. In particular, a system is provided for reducing the impact of poor channel conditions in a cellular network on the FL process. The cellular network may be a 5G, 6G or next generation cellular network. Advantageously, this disclosure creates redundancies in the transmission of FL trained model parameters to reduce the likelihood of an FL training process being stalled by a failure in transmission of data between UEs and a central parameter server which updates an ML model using data received from UEs.

    METHOD AND APPARATUS FOR SETTING TIMER VALUE IN NETWORK

    公开(公告)号:US20230239960A1

    公开(公告)日:2023-07-27

    申请号:US18186581

    申请日:2023-03-20

    CPC classification number: H04W76/25 H04W24/02

    Abstract: A method for setting a value of an inactivity timer for transitioning between states of a data session in a network comprising a first entity and a second entity providing network analytics is provided. The method includes obtaining, by the second entity, input data comprising communication description information for at least one user equipment (UE), and providing, by the second entity to the first entity, output analytics generated based on the input data, the output analytics comprising UE communications analytics for each data session where the output analytics are used to determining whether to update a value of an inactivity timer for a data session.

Patent Agency Ranking