Learning-based signal receiving method and device
The present disclosure proposes a method and procedure for performing additional learning using data secured in an actual environment in a basic receiver model optimized for a representative environment and a method of operating a plurality of customized receiver models secured through this and the basic receiver model together.
1 . A method comprising:
receiving a synchronization signal block (SSB) including a master information block (MIB);
receiving a first system information block (SIB) based on the MIB;
transmitting a request of system information to a base station;
receiving a second SIB from the base station based on the request of the system information;
transmitting user equipment (UE) capability information to the base station based on the second SIB;
receiving downlink control information (DCI) from the base station;
receiving learning data based on the DCI;
transmitting, based on a learning data reception condition being satisfied, learning data request information to the base station; and
receiving, from the base station, the learning data based on the base station receiving the learning data request information,
wherein information included in the DCI is related to transmission of the learning data, and the learning data is generated based on a communication environment of a UE,
wherein training on a receiver model is performed based on the learning data and default receiver model, and
wherein the learning data reception condition is satisfied, based on a first condition that the trained receiver model is not present in association with a communication environment entered by the UE, a second condition that there is no learning performed based on previously received learning data, and a third condition that the UE is being charged or a remaining battery level of the UE is greater than or equal to a preset threshold being all satisfied.
2 . The method of claim 1 , wherein the second SIB includes information related to the training on the receiver model, and the UE capability information includes training capability of the UE.
3 . The method of claim 1 , wherein the learning data request information is transmitted based on radio resource control (RRC) signaling or medium access control (MAC) signaling.
4 . The method of claim 1 , wherein the learning data request information indicates a minimum time interval between transmission of the learning data, a statistical distribution of a period in which the base station transmits the learning data, and learning data transmission resource.
5 . The method of claim 4 ,
wherein the learning data is transmitted through the learning data transmission resource,
wherein the learning data transmission resource is allocated based on a uniform distribution in a frequency domain, and
wherein the learning data transmission resource has the minimum time interval and the statistical distribution in a time domain.
6 . The method of claim 1 , wherein the learning data is randomized and transmitted based on at least one of an identifier (ID) of the UE or information on a cell accessed by the UE.
7 . The method of claim 6 , wherein the identifier is an IMSI (International Mobile Subscriber Identity) or an IMEI (International Mobile Equipment Identity), and the information on the cell is an identifier (ID) of the cell.
8 . The method of claim 1 , wherein the training is performed on demodulation of the receiver model.
9 . The method of claim 8 , wherein the training is performed based on a loss function.
10 . The method of claim 9 , wherein the loss function is determined by adding cross entropy to a product of a weight and a bit error rate (BER).
11 . The method of claim 10 ,
wherein the cross entropy is a difference between an estimated value of the learning data and a correct answer (label) value of the learning data, and
wherein the BER is determined based on a result of channel-decoding the learning data.
12 . A user equipment (UE) comprising:
one or more memories configured to store instructions;
one or more transceivers; and
one or more processors configured to connect the one or more memories and the one or more transceivers,
wherein the one or more processors execute instructions to:
receive a synchronization signal block (SSB) including a master information block (MIB);
receive a first system information block (SIB) based on the MIB;
transmit a request of system information to a base station;
receive a second SIB from the base station based on the request of the system information;
transmit UE capability information to the base station based on the second SIB;
receive downlink control information (DCI) from the base station; receive learning data based on the DCI;
transmit, based on a learning data reception condition being satisfied, learning data request information to the base station; and
receive, from the base station, the learning data based on the base station receiving the learning data request information,
wherein information included in the DCI is related to transmission of the learning data, and the learning data is generated based on a communication environment of the UE,
wherein training on a receiver model is performed based on the learning data and default receiver model, and
wherein the learning data reception condition is satisfied, based on a first condition that the trained receiver model is not present in association with a communication environment entered by the UE, a second condition that there is no learning performed based on previously received learning data, and a third condition that the UE is being charged or a remaining battery level of the UE is greater than or equal to a preset threshold being all satisfied.
13 . A method of receiving a signal performed by a base station in a wireless communication system, the method comprising:
transmitting a synchronization signal block (SSB) including a master information block (MIB);
transmitting a first system information block (SIB) based on the MIB;
receiving a request of system information from a user equipment (UE);
transmitting a second SIB to the UE based on the request of the system information;
receiving UE capability information from the UE based on the second SIB;
transmitting downlink control information (DCI) to the UE;
transmitting, to the UE, learning data based on the DCI;
receiving, based on a learning data reception condition being satisfied, learning data request information from the UE; and
transmitting, to the UE, the learning data based on receiving the learning data request information,
wherein information included in the DCI is related to transmission of the learning data, and the learning data is generated based on a communication environment of the UE,
wherein training on a receiver model is performed based on the learning data and default receiver model, and
wherein the learning data reception condition is satisfied, based on a first condition that the trained receiver model is not present in association with a communication environment entered by the UE, a second condition that there is no learning performed based on previously received learning data, and a third condition that the UE is being charged or a remaining battery level of the UE is greater than or equal to a preset threshold being all satisfied.