IP Library › Granted Patent US 12689544

Granted Patent B2

US 12689544 · App. 18/180,431 · Granted Jul 21, 2026

Channel precoder selection for uplink wireless communications

Inventors: Amit Bar-Or Tillinger (Tel-Aviv, IL); Shay Landis (Hod Hasharon, IL); Yehonatan Dallal (Kfar Saba, IL); Idan Michael Horn (Hod Hasharon, IL)

Assignee: QUALCOMM Incorporated

H04L25/0254 H04L25/0242

View Patent ↗

Loading inventors, assignments & file history…

Monitor This Case

Get email alerts when status or documents change.

Order Certified Copies

Most orders are placed with the USPTO same day — all within 24 business hours.

Order via The Patent Place →

Pre-filled with this patent's details

Quick Facts

Patent No.: US 12689544
App. No.: 18/180,431
Granted: Jul 21, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Methods, systems, and devices for wireless communications are described that provide machine-learning models, such as neural network (NN) based precoding functions, that may be used at a user equipment (UE) to determine precoding parameters directly based on channel estimations performed at the UE. A network entity may measure a channel used for communications with the UE and determine coefficients that are to be applied to a machine learning precoding function (e.g., a NN precoding function) at the UE. The network entity may provide the determined coefficients to the UE. The UE may use the indicated coefficients in the NN based precoding function, along with a channel estimation of a channel associated with an uplink transmission, to determine a precoding matrix that is to be applied for the uplink transmission.

Claims (78)

1 . An apparatus for wireless communications at a user equipment (UE), comprising:

one or more processors;

one or more memories coupled with the one or more processors; and

instructions stored in the one or more memories and executable by the one or more processors to cause the apparatus to:

receive, from a network entity, a set of neural-network based precoding coefficients for a neural-network based precoding function for generation of an uplink channel precoding matrix for at least a first uplink communication to be transmitted from the UE;

obtain a channel estimation associated with a wireless channel that carries the first uplink communication;

generate the uplink channel precoding matrix based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation; and

transmit the first uplink communication via the wireless channel using the uplink channel precoding matrix that is based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation.

2 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

transmit, to the network entity, one or more neural-network based precoding capabilities of the UE, one or more restrictions associated with neural-network based precoding at the UE, or any combinations thereof.

3 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

measure one or more downlink reference signals on a downlink channel associated with the wireless channel that carries the first uplink communication; and

determine, responsive to measuring the one or more downlink reference signals, the uplink channel precoding matrix using the neural-network based precoding function and the set of neural-network based precoding coefficients.

4 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

transmit one or more uplink reference signals via the wireless channel for channel estimation and determination of the set of neural-network based precoding coefficients at the network entity.

5 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

receive, subsequent to transmission of the first uplink communication, one or more updated neural-network based precoding coefficients for one or more subsequent uplink communications.

6 . The apparatus of claim 5 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

apply the one or more updated neural-network based precoding coefficients to the neural-network based precoding function; and

transmit an acknowledgment that the one or more updated neural-network based precoding coefficients are received.

7 . The apparatus of claim 5 , wherein the one or more updated neural-network based precoding coefficients are associated with one or more layers of a multi-layered neural-network precoding function.

8 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

transmit, to the network entity, one or more of a neural-network dimensionality capability of the UE, a number of neural-network layers supported at the UE for the neural-network based precoding function, a neural-network connectivity associated with one or more neural-network layers, one or more neural-network structures supported at the UE, or any combinations thereof.

9 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

transmit, to the network entity, an indication of one or more supported neural-network based precoding functions from a set of available neural-network based precoding functions.

10 . The apparatus of claim 9 , wherein the instructions to receive the set of neural-network based precoding coefficients are further executable by the one or more processors to cause the apparatus to:

receive an indication of a selected neural-network based precoding function of the one or more supported neural-network based precoding functions that is to be used for uplink communications from the UE.

11 . The apparatus of claim 1 , wherein the instructions are further executable by the one or more processors to cause the apparatus to:

transmit, to the network entity, one or more of a maximum transmit power available at the UE, an allowed transmission power per antenna for one or more antennas at the UE, one or more power amplifier non-linearity parameters, or any combinations thereof.

12 . A method for wireless communications at a user equipment (UE), comprising:

receiving, from a network entity, a set of neural-network based precoding coefficients for a neural-network based precoding function for generation of an uplink channel precoding matrix for at least a first uplink communication to be transmitted from the UE;

obtaining a channel estimation associated with a wireless channel that carries the first uplink communication;

generating the uplink channel precoding matrix based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation; and

transmitting the first uplink communication via the wireless channel using the uplink channel precoding matrix that is based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation.

13 . The method of claim 12 , further comprising:

transmitting, to the network entity, one or more neural-network based precoding capabilities of the UE, one or more restrictions associated with neural-network based precoding at the UE, or any combinations thereof.

14 . The method of claim 12 , further comprising:

measuring one or more downlink reference signals on a downlink channel associated with the wireless channel that carries the first uplink communication; and

determining, responsive to measuring the one or more downlink reference signals, the uplink channel precoding matrix using the neural-network based precoding function and the set of neural-network based precoding coefficients.

15 . The method of claim 12 , further comprising:

receiving, subsequent to transmission of the first uplink communication, one or more updated neural-network based precoding coefficients for one or more subsequent uplink communications.

16 . The method of claim 15 , wherein the one or more updated neural-network based precoding coefficients are associated with one or more layers of a multi-layered neural network precoding function.

17 . A non-transitory computer-readable medium storing code for wireless communications, the code comprising instructions executable by one or more processors to:

obtain a channel estimation associated with a wireless channel that carries the first uplink communication;

18 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

19 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

measure one or more downlink reference signals on a downlink channel associated with the wireless channel that carries the first uplink communication; and

20 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

transmit one or more uplink reference signals via the wireless channel for channel estimation and determination of the set of neural-network based precoding coefficients at the network entity.

21 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

receive, subsequent to transmission of the first uplink communication one or more updated neural-network based precoding coefficients for one or more subsequent uplink communications.

22 . The non-transitory computer-readable medium of claim 21 , wherein the instructions are further executable by the one or more processors to:

apply the one or more updated neural-network based precoding coefficients to the neural-network based precoding function; and

transmit an acknowledgment that the one or more updated neural-network based precoding coefficients are received.

23 . The non-transitory computer-readable medium of claim 21 , wherein the one or more updated neural-network based precoding coefficients are associated with one or more layers of a multi-layered neural network precoding function.

24 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

25 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

transmit, to the network entity, an indication of one or more supported neural-network based precoding functions from a set of available neural-network based precoding functions.

26 . The non-transitory computer-readable medium of claim 25 , wherein the instructions to receive the set of neural-network based precoding coefficients are further executable by the one or more processors to:

27 . The non-transitory computer-readable medium of claim 17 , wherein the instructions are further executable by the one or more processors to:

28 . A user equipment (UE) for wireless communications, comprising:

means for receiving, from a network entity, a set of neural-network based precoding coefficients for a neural-network based precoding function for generation of an uplink channel precoding matrix for at least a first uplink communication to be transmitted from the UE;

means for obtaining a channel estimation associated with a wireless channel that carries the first uplink communication;

means for generating the uplink channel precoding matrix based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation; and

means for transmitting the first uplink communication via the wireless channel using the uplink channel precoding matrix that is based at least in part on application of the set of neural-network based precoding coefficients to the neural-network based precoding function and the channel estimation.

29 . The UE of claim 28 , further comprising:

means for transmitting, to the network entity, one or more neural-network based precoding capabilities of the UE, one or more restrictions associated with neural-network based precoding at the UE, or any combinations thereof.

30 . The UE of claim 28 , further comprising:

means for measuring one or more downlink reference signals on a downlink channel associated with the wireless channel that carries the first uplink communication; and

means for determining, responsive to measuring the one or more downlink reference signals, the uplink channel precoding matrix using the neural-network based precoding function and the set of neural-network based precoding coefficients.