| CPC H04L 41/16 (2013.01) | 11 Claims |
|
1. An apparatus comprising:
at least one processor; and
at least one non-transitory memory storing instructions, that when executed by the at least one processor, cause the apparatus at least to:
send, by a user equipment of a communication network, towards a network node information comprising a service request for a dedicated bearer for data exchange of at least one of machine learning or artificial intelligence related data,
wherein the data exchange is for training the at least one of a machine learning or an artificial intelligence model for a particular use case; and
based on the information, receive from the network node an indication of a configured dedicated bearer,
wherein the dedicated bearer is configured using predefined settings for a particular quality of service class identifier; and
based on the indication, perform at least one of uplink or downlink data communication on the dedicated bearer for the training,
wherein the at least one of a machine learning or artificial intelligence related data is for the following: full or partial model training, transfer of an offline trained model, model updates, uplink or downlink model transfers for model life-cycle management of the at least one of a machine learning or an artificial intelligence model for the particular use case,
wherein the model life-cycle management manages operations comprising the following: activation, deactivation, switching, and updates for the at least one of a machine learning or an artificial intelligence model,
wherein the particular quality of service class identifier is based on the following: a type of guaranteed bit rate or non-guaranteed bit rate bearer, a maximum bit rate allowed in uplink or downlink, a priority level, a packet delay budget, a default maximum data burst volume, a default averaging window, and a packet loss rate for the dedicated bearer.
|