User equipment artificial intelligence-machine-learning capability categorization system, method, device, and program
A method, system, apparatus, and non-transitory computer-readable medium for classifying machine-learning capabilities of a user device in a telecommunication network may be provided. The method may be performed by one or more processors, and may include receiving user device capability information from the user device; based on the user device capability information, determining a classification of machine learning capabilities of the user device; and transmitting, to the user device, data associated with a machine learning model based on the classification of the machine learning capabilities of the user device.
1 . A method for classifying machine-learning capabilities of a user device in a telecommunication network, the method being executed by a processor, and the method comprising:
receiving user device capability information from the user device;
based on the user device capability information, determining a classification of machine-learning capabilities of the user device; and
transmitting, to the user device, data associated with a machine-learning model based on the classification of the machine-learning capabilities of the user device.
2 . The method of claim 1 , wherein the user device capability information includes a plurality of parameters associated with the user device, and wherein each parameter is expressed as a categorical variable.
3 . The method of claim 2 , wherein the plurality of parameters associated with the user device include at least one of a processor type of the user device, a size of available memory, a battery power of the user device, a battery health of the user device, a device type of the user device, or radio frequency hardware capability of the user device.
4 . The method of claim 3 , wherein determining the classification comprises:
evaluating one or more parameters of the user device from the plurality of parameters;
determining a categorical value for each of the one or more parameters; and
based on comparing the categorical value for each of the one or more parameters to a pre-determined set of minimum categorical values, assigning a classification number to the user device based on the categorical value for each of the one or more parameters.
5 . The method of claim 2 , wherein transmitting data associated with a machine-learning model to the user device comprises:
based on the classification of the machine-learning capabilities of the user device, transmitting, to the user device, one of:
training data and model parameters for a full scale training at the user device;
a lightly trained model, a subset of the training data, and the model parameters for a lightweight training at the user device;
a general trained model, a subset of training data, and the model parameters for a specific use case-based update of the general trained model at the user device; and
a trained model for an inference at the user device.
6 . The method of claim 5 , wherein the specific use case-based update for the general trained model is associated with a use case from among a channel-state information (CSI) feedback enhancement, beam management, positioning accuracy, received signal (RS) overhead reduction, load balancing, mobility optimization, or network energy saving.
7 . The method of claim 5 , wherein the lightweight training at the user device includes updating the lightly trained model for a limited number of epochs to achieve an acceptable level of accuracy.
8 . The method of claim 5 , wherein the full scale training at the user device includes generating the machine-learning model using the training data and the model parameters, wherein the generating includes training a model for a large number of epochs to achieve a high level of accuracy.
9 . The method of claim 1 , wherein the classification of the machine-learning capabilities of the user device is indicative of an artificial intelligence model training capacity of the user device.
10 . The method of claim 1 , wherein the classification of the machine-learning capabilities of the user device is indicative of an artificial intelligence model inference capacity of the user device.
11 . The method of claim 1 , wherein the receiving of the user device capability information is in response to receiving a request from the user device.
12 . The method of claim 1 , wherein the receiving of the user device capability information is in response to receiving a request from a network element of the telecommunication network.
13 . An apparatus comprising:
a memory configured to store instructions; and
one or more processors configured to execute the instructions to:
receive user device capability information from the user device;
based on the user device capability information, determine a classification of machine-learning capabilities of the user device; and
transmit, to the user device, data associated with a machine-learning model based on the classification of the machine-learning capabilities of the user device.
14 . The apparatus of claim 13 , wherein the user device capability information includes a plurality of parameters associated with the user device, and wherein each parameter is expressed as a categorical variable.
15 . The apparatus of claim 14 , wherein the determining the classification comprises:
evaluating one or more parameters of the user device from the plurality of parameters;
determining a categorical value for each of the one or more parameters; and
based on comparing the categorical value for each of the one or more parameters to a pre-determined set of minimum categorical values, assigning a classification number to the user device based on the categorical value for each of the one or more parameters.
16 . The apparatus of claim 13 , wherein transmitting data associated with a machine-learning model to the user device comprises:
based on the classification of the machine-learning capabilities of the user device, transmitting, to the user device, one of:
training data and model parameters for a full scale training at the user device;
a lightly trained model, a subset of the training data, and the model parameters for a lightweight training at the user device;
a general trained model, a subset of training data, and the model parameters for a specific use case-based update of the general trained model at the user device; and
a trained model for an inference at the user device.
17 . The apparatus of claim 16 , wherein the lightweight training at the user device includes updating the lightly trained model for a limited number of epochs to achieve an acceptable level of accuracy, and wherein the full scale training at the user device includes generating the machine-learning model using the training data and the model parameters, wherein the generating includes training a model for a large number of epochs to achieve a high level of accuracy.
18 . A non-transitory computer-readable medium storing instructions, the instructions comprising: one or more instructions that, when executed by a network element comprising one or more processors, cause the one or more processors to:
receive user device capability information from the user device;
based on the user device capability information, determine a classification of machine-learning capabilities of the user device; and
transmit, to the user device, data associated with a machine-learning model based on the classification of the machine-learning capabilities of the user device.
19 . The non-transitory computer-readable medium of claim 18 , wherein the user device capability information includes a plurality of parameters associated with the user device; and wherein determining the classification comprises:
evaluating one or more parameters of the user device from the plurality of parameters;
determining a categorical value for each of the one or more parameters; and
based on comparing the categorical value for each of the one or more parameters to a pre-determined set of minimum categorical values, assigning a classification number to the user device based on the categorical value for each of the one or more parameters.
20 . The non-transitory computer-readable medium of claim 18 , wherein transmitting data associated with a machine-learning model user device comprises:
based on the classification of the machine-learning capabilities of the user device, transmitting, to the user device, one of:
training data and model parameters for a full scale training at the user device;
a lightly trained model, a subset of the training data, and the model parameters for a lightweight training at the user device;
a general trained model, a subset of training data, and the model parameters for a specific use case-based update of the general trained model at the user device; and
a trained model for an inference at the user device.