Granted Patent B2

US 12,490,247 · App. 17/982,937 · Granted Dec 2, 2025

Inventors: Yong Jin Kwon (Daejeon, KR); Yun Joo Kim (Daejeon, KR); Hyun Seo Park (Daejeon, KR); An Seok Lee (Daejeon, KR); Yu Ro Lee (Daejeon, KR); Heesoo Lee (Daejeon, KR)

Assignee: ELECTRONICS AND TELECOMMUNICATIONS RESEARCH INSTITUTE

H04W72/0453G06N20/00H04W72/23

Abstract

Claims (78)

1 . A method of a base station, comprising:

determining one of machine learning (ML) models for receiving channel information for a channel to communicate with a terminal based on capability information of the terminal;

providing configuration information of the determined ML model to the terminal;

updating the determined ML model through online training with the terminal; and

receiving channel information using the updated ML model from the terminal when communicating with the terminal,

wherein the online training comprises:

transmitting an online training request for the determined ML model to the terminal; and

updating parameters of the determined ML model to update the determined ML model, and

wherein the online training request instructs the terminal to initiate the online training when receiving an online training response indicating that the online training is possible from the terminal.

2 . The method according to claim 1 , wherein the capability information of the terminal includes at least one of whether the terminal supports use of the ML model, computation capability of the terminal, a memory size of the terminal, a current moving speed of the terminal, or combinations thereof.

3 . The method according to claim 1 , wherein the configuration information of the determined ML model is transmitted as at least one data packet.

4 . The method according to claim 1 , wherein the ML model is a model in which a decoder of the base station and an encoder of the terminal are connected as one pair.

5 . The method according to claim 1 , wherein the ML model is a model in which a decoder of the base station and decoders of one or more terminals including the terminal communicating with the base station are connected as a set.

6 . The method according to claim 1 , wherein the updating of the parameters comprises:

transmitting a reference signal to the terminal;

receiving, from the terminal, channel information measured based on the reference signal;

receiving compressed bits for the channel information;

decoding the compressed bits to obtain channel information;

updating at least one parameter of the determined ML model based on the measured channel information and the obtained channel information; and

transmitting the updated parameters to the terminal.

7 . The method according to claim 1 , wherein the updating of the parameters comprises:

transmitting a reference signal to the terminal;

receiving, from the terminal, channel information measured based on the reference signal;

generating compressed bits based on the channel information through an encoder of the determined ML model;

decoding the generated compressed bits by using a decoder of the determined ML model;

updating at least one parameter of the ML model based on the decoded information and the measured channel information; and

transmitting the updated parameter to the terminal.

8 . The method according to claim 1 , wherein the updating of the parameters comprises:

transmitting a reference signal to the terminal;

receiving, from the terminal, compressed bits corresponding to channel information measured based on the reference signal;

receiving information on updated parameters for the determined ML model from the terminal; and

updating the determined ML model by using the received information of the updated parameters.

9 . A base station comprising:

a transceiver configured to transmit and receive signals with at least one terminal by using an machine learning (ML) model; and

at least one processor,

wherein the at least one processor is executed to:

determine one of ML models for receiving channel information for a channel to communicate with a terminal based on capability information of the terminal;

provide configuration information of the determined ML model to the terminal through the transceiver;

update the determined ML model through online training with the terminal; and

receive channel information using the updated ML model from the terminal when communicating with the terminal,

wherein in the online training, the at least one processor is further executed to:

transmit an online training request for the determined ML model to the terminal through the transceiver and

update parameters of the determined ML model to update the determined ML model, and

wherein the online training request instructs the terminal to initiate the online training when receiving an online training response indicating that the online training is possible from the terminal.

10 . The base station according to claim 9 , wherein the capability information of the terminal includes at least one of whether the terminal supports use of the ML model, computation capability of the terminal, a memory size of the terminal, a current moving speed of the terminal, or combinations thereof.

11 . The base station according to claim 9 , wherein the configuration information of the determined ML model is transmitted as at least one data packet.

12 . The base station according to claim 9 , wherein the ML model is a model in which a decoder of the base station and an encoder of the terminal are connected as one pair.

13 . The base station according to claim 9 , wherein the ML model is a model in which a decoder of the base station and decoders of one or more terminals including the terminal communicating with the base station are connected as a set.

14 . The base station according to claim 9 , wherein in the updating of the parameters, the at least one processor is further executed to:

transmit a reference signal to the terminal through the transceiver;

receive, from the terminal, channel information measured based on the reference signal;

receive compressed bits for the channel information;

decode the compressed bits to obtain channel information;

update at least one parameter of the determined ML model based on the measured channel information and the obtained channel information; and

transmit the updated parameters to the terminal.

15 . The base station according to claim 9 , wherein in the updating of the parameters, the at least one processor is further executed to:

transmit a reference signal to the terminal through the transceiver;

receive, from the terminal, channel information measured based on the reference signal;

generate compressed bits based on the channel information through an encoder of the determined ML model;

decode the generated compressed bits by using a decoder of the determined ML model;

update at least one parameter of the determined ML model based on the decoded information and the measured channel information; and

transmit the updated parameter to the terminal.

16 . The base station according to claim 9 , wherein in the updating of the parameters, the at least one processor is further executed to:

transmit a reference signal to the terminal through the transceiver;

receive, from the terminal, compressed bits corresponding to channel information measured based on the reference signal;

receive information on updated parameters for the determined ML model from the terminal; and

update the determined ML model by using the received information of the updated parameters.

17 . A method of a terminal, comprising:

configuring an machine learning (ML) model to be used for communication with a base station based on configuration information of the ML model received from the base station;

updating the ML model through online training with the base station;

measuring channel information during communication with the base station;

generating compressed bits corresponding to the measured channel information by using the updated ML model; and

transmitting the generated compressed bits to the base station,

wherein the online training comprises:

receiving an online training request for the determined ML model form the base station;

initiating the online training when transmitting an online training response indicating that the online training is possible to the base station, in response to receiving the online training request; and

updating parameters of the determined ML model to update the determined ML model.

18 . The method according to claim 17 , further comprising, when requested by the base station, transmitting capability information of the terminal, the capability information including at least one of whether the terminal supports use of the ML model, computation capability of the terminal, a memory size of the terminal, a current moving speed of the terminal, or combinations thereof.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (29)