Method and apparatus for feedback channel status information based on machine learning in wireless communication system

A method of a base station, comprising:

• transmitting, to a terminal, a channel state information (CSI) request message including first indication information indicating one of quantization configuration information of a first artificial intelligence (AI) model configured in the terminal to encode and transmit CSI;
• and
• receiving, from the terminal, a CSI report message including CSI feedback information quantized based on the first indication information of the CSI request message,
• wherein the quantization configuration information of the first AI model includes information on a codebook consisting of latent variables when performing vector quantization and a number of quantized bits for each dimension of the latent variable when performing scalar quantization.

A terminal comprising at least one processor, wherein the at least one processor causes the terminal to perform:

• receiving a channel state information (CSI) request message from a base station, the CSI request message including first indication information indicating one of quantization configuration information of a first artificial intelligence (AI) model configured in the terminal to encode and transmit CSI;
• quantizing generated CSI feedback information based on the first indication information;
• and
• transmitting a CSI report message including the quantized CSI feedback information to the base station-,
• wherein the quantization configuration information of the first AI model includes information on a codebook consisting of latent variables when performing vector quantization and a number of quantized bits for each dimension of the latent variable when performing scalar quantization.