System, method, device, and program for interface management of AI/ML applications over radio access parameters

An apparatus for adaptive machine-learning related operation signaling in a telecommunication network, the apparatus comprising:

• at least one memory configured to store program code;
• and
• at least one processor configured to read the program code and operate as instructed by the program code, the program code comprising:
• detecting code configured to cause the at least one processor to detect a transition of the user device from a first state associated with a first 5G new radio protocol to a second state associated with the first 5G new radio protocol;
• transmitting code configured to cause the at least one processor to transmit, in response to detecting the transition, first information associated with the transition, wherein the first information comprises a machine-learning collaboration level change request associated with the user device, the machine-learning collaboration level change request being a request to change a machine-learning collaboration level from among a plurality of predetermined machine-learning collaboration levels indicating whether or not a target operation is performed using a machine-learning model at a network node;
• and
• receiving code configured to cause the at least one processor to receive, in response to the transmitted first information, change information associated with the target operation, wherein the change information indicates the machine-learning collaboration level that varies based on the first information transmitted by the user device,
• wherein the target operation is performed based on the indicated machine-learning collaboration level,
• wherein the change information comprises at least one of an acknowledgement of the machine-learning collaboration level change request or a new machine-learning collaboration level based on the machine-learning collaboration level change request, and
• wherein the performing code further comprises:
• based on the new machine-learning collaboration level being changed to a first level in response to the detected transition being to an RRC connected state, performing the target operation based using the machine-learning model at the network node;
• based on the new machine-learning collaboration level being changed to a second level in response to the detected transition being to an RRC disconnected or idle state, performing the target operation using a machine-learning model at the user device and not at the network node;
• and
• based on the new machine-learning collaboration level being changed to a third level, terminating the target operation.

A non-transitory computer-readable medium storing instructions for adaptive machine-learning related operation signaling in a telecommunication network, the instructions comprising:

• one or more instructions that, when executed by one or more processors, cause the one or more processors to:
• detect, by user device, a transition of the user device from a first state associated with a first 5G new radio protocol to a second state associated with the first 5G new radio protocol;
• in response to detecting the transition, transmit, by the user device, first information associated with the transition, wherein the first information comprises a machine-learning collaboration level change request associated with the user device, the machine-learning collaboration level change request being a request to change a machine-learning collaboration level from among a plurality of predetermined machine-learning collaboration levels indicating whether or not a target operation is performed using a machine-learning model at a network node;
• receive, by the user device in response to the transmitted first information, change information associated with a target operation, wherein the change information indicates a machine-learning collaboration level that varies based on the first information transmitted by the user device;
• and
• perform, by the user device, the target operation based on the indicated machine-learning collaboration level,
• wherein the change information comprises at least one of an acknowledgement of the machine-learning collaboration level change request or a new machine-learning collaboration level based on the machine-learning collaboration level change request, and
• wherein performing the target operation based on the indicated machine-learning collaboration level comprises:
• based on the new machine-learning collaboration level being changed to a first level in response to the detected transition being to an RRC connected state, performing the target operation using the machine-learning model at the network node;
• based on the new machine-learning collaboration level being changed to a second level in response to the detected transition being to an RRC disconnected or idle state, performing the target operation using a machine-learning model at the user device and not at the network node;
• and
• based on the new machine-learning collaboration level being changed to a third level, terminating the target operation.