Granted Patent B2

US 12,634,169 · App. 18/087,856 · Granted May 19, 2026

Inventors: Chung Gu Kang (Seoul, KR); Min-Sig Han (Seongnam-si, KR)

Assignee: Korea University Research and Business Foundation

H04L25/0204H04L5/0051H04W72/115

Abstract

Claims (66)

1 . A method performed by a base station in a wireless communication system, comprising:

transmitting a codebook allocated for data transmission to each of multiple user terminals;

receiving a pilot and data from one or more user terminals among the multiple user terminals;

generating active user information based on the data received from the one or more user terminals;

detecting an active user terminal among the multiple user terminals based on the pilot and the active user information;

generating channel estimation information related to the active user terminal; and

detecting the data of the active user terminal based on the channel estimation information,

wherein the method further comprises transmitting information indicating a length of the data to the one or more user terminals, and

wherein transmitting the information indicating the length of the data comprises either transmitting the information indicating the length of the data in response to a data length change request received from the one or more user terminals or transmitting the information indicating the length of the data when a pre-set condition is satisfied.

2 . The method of claim 1 , wherein the data is received through codeword transmitted based on the codebook assigned to each of the one or more user terminals, and

wherein the pilot received from the one or more user terminals is either (i) a pilot randomly selected by the user terminal from among multiple pilot sequences generated in advance by the base station and allocated for the transmission in association with codebooks for multiple user terminals, or (ii) a pilot generated in real time to be associated with a codebook allocated to each of the one or more user terminals through a pilot generation unit of the user terminal.

3 . The method of claim 2 , further comprising transmitting a signal to the one or more user terminals to update the pilot generation unit,

wherein, after transmitting the signal, the pilot is generated in real time via an updated pilot generation unit of the one or more user terminals.

4 . The method of claim 1 , wherein the active user information is generated using a neural network, the neural network being trained with a first learning step and a second learning step

wherein the

wherein the first learning step uses a first loss function defined based on information indicating activation states of the multiple user terminals and the active user information, and

wherein the second learning step uses a second loss function defined based information on the indicating activation states of the multiple user terminals and the information indicating estimated activation states of the multiple user terminals.

5 . A method performed by a user terminal in a wireless communication system, comprising:

receiving a codebook allocated for data transmission from a base station;

generating data based on the codebook;

selecting or generating a pilot; and

transmitting the pilot and the data to the base station,

wherein the user terminal is detected as an active user terminal among multiple user terminals based on the pilot and active user information generated based on the data,

wherein the method further comprises receiving information indicating a length of the data from the base station, and

wherein receiving the information indicating the length of the data comprises either receiving the information indicating the length of the data from the base station in response to a data length change request sent from the user terminal or receiving the information indicating the length of the data when a pre-set condition is satisfied.

6 . The method of claim 5 , wherein the pilot is either (i) a pilot selected by the user terminal from among multiple pilot sequences generated in advance by the base station for allocation to multiple user terminals, or (ii) a pilot generated in real time by a pilot generation unit of the user terminal in association with the codebook allocated to the user terminal.

7 . The method of claim 6 , further comprising receiving a signal from the base station to update the pilot generation unit,

wherein, upon receiving the signal, the pilot is generated in real time through an updated pilot generation unit of the user terminal.

8 . The method of claim 5 , wherein active user information is generated at the base station using a neural network, the neural network being trained with a first learning step and a second learning step,

wherein the first learning step uses a first loss function defined based on information indicating activation states of a plurality of user terminals and the active user information, and

wherein the second learning step uses a second loss function defined based on information indicating activation states of the plurality of user terminals and information indicating estimated activation states of the plurality of user terminals.

9 . A wireless communication system, comprising:

a base station including a transceiver and one or more processors operatively connected to the transceiver; and

a user terminal including a transceiver and one or more processors operatively connected to the transceiver;

wherein the one or more processors of the base station are configured to:

transmit a codebook allocated for data transmission to each of a plurality of user terminals,

receive a pilot and data from one or more user terminals among the plurality of user terminals,

generate active user information based on the data,

detect an active user terminal among the plurality of user terminals based on the pilot and the active user information,

generate channel estimation information related to the active user terminal, and

detect the data of the active user terminal based on the channel estimation information,

wherein the one or more processors of the base station are further configured to transmit information indicating a length of the data to the one or more user terminals, and

wherein transmitting the information indicating the length of the data comprises either transmitting the information indicating the length of the data based on a data length change request received from the one or more user terminals or transmitting the information indicating the length of the data when a pre-set condition is satisfied.

10 . The base station of claim 9 , wherein the data is received through a codeword transmitted based on the codebook assigned to each of the one or more user terminals, and

wherein the pilot received from the one or more user terminals is either (i) a pilot randomly selected by the user terminal from among multiple pilot sequences generated in advance by the base station and allocated for transmissions associated with codebooks for multiple user terminals, or (ii) a pilot generated in real time via a pilot generation unit of the user terminal in association with the codebook allocated to the user terminal.

11 . The base station of claim 10 , wherein the one or more processors are configured to transmit a signal to the one or more user terminals to update the pilot generation unit, and

wherein, when the signal is transmitted, the pilot is generated in real time through an updated pilot generation unit of the user terminal.

12 . The base station of claim 9 ,

wherein the one or more processors are configured to generate the active user information based on a neural network that is trained with the a first learning step and a second learning step,

wherein the first learning step uses a first loss function defined based on information indicating activation states of the plurality of user terminals and the active user information, and

wherein the second learning step uses a second loss function defined based on information indicating activation states of the plurality of user terminals and the information indicating estimated activation states of the plurality of user terminals.

13 . The user terminal of claim 9 , wherein the one or more processors of the user terminal are configured to:

receive a codebook allocated for data transmission from the base station;

generate data based on the codebook:

select or generate a pilot; and

transmit the pilot and the data to the base station, and

wherein the one or more processors of the user terminal are configured to receive information indicating a length of the data from the base station, and

wherein receiving the information indicating the length of the data comprises either receiving the information indicating the length of the data from the base station in response to a data length change request transmitted from the user terminal or receiving the information indicating the length of the data when a pre-set condition is satisfied.

14 . The user terminal of claim 13 ,

wherein the data is transmitted through a codeword based on the codebook allocated to the user terminal, and

wherein the pilot is either (i) a pilot selected by the user terminal from among multiple pilot sequences generated in advance by the base station for allocation to multiple user terminals, or (ii) a pilot generated in real time by a pilot generation unit of the user terminal in association with the codebook allocated to the user terminal.

15 . The user terminal of claim 14 , wherein the one or more processors of the user terminal are configured to receive a signal from the base station to update the pilot generation unit, and

wherein, upon receiving the signal, the pilot is generated in real time through an updated pilot generation unit of the user terminal.

16 . The user terminal of claim 13 , wherein the user terminal is detectable as an active user terminal among the plurality of user terminals based on a neural network that is trained with a first learning step and a second learning step,

wherein the first learning step uses a first loss function defined based on information indicating activation states of the plurality of user terminals and the active user information, and

wherein the second learning step uses a second loss function defined based on information indicating activation states of the plurality of user terminals and information indicating estimated activation states of the plurality of user terminals.

Assignments (1)

Priority Claims (1)

Continuity (1)

References Cited (12)