Neural network-based transmission feedback in a cellular network

Patent metadata

Field	Value
Publication number	US-12556312-B2
Application number	US-202118016502-A
Country	US
Kind code	B2
Filing date	Jul 26, 2021
Priority date	Jul 31, 2020
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Two devices in wireless communication implement a soft transmission feedback scheme. A data-sending device wirelessly communicates a first transmission representing a data block and generated using one or more neural networks to a data-receiving device, which processes the first transmission using one or more neural networks to attempt to recover the data block, as well as to generate transmission feedback indicating a status of the recovery attempt. The feedback is used by one or more neural networks to generate a second transmission that is wirelessly communicated to the data-sending device. One or more neural networks process the second transmission to generate a retransmit control signal. One or more neural networks selectively include at least a portion of the data block for retransmission in a third transmission to the data-receiving device based on the retransmit control signal.

First claim

What is claimed is:

1 . A computer-implemented method, in a data-sending device, comprising:
buffering a first data block in a delay buffer; processing the first data block at a transmitter neural network of the data-sending device to generate a first transmission for wireless communication to a data-receiving device; wirelessly communicating the first transmission to the data-receiving device; processing a second transmission wirelessly received from the data-receiving device at a receiver neural network of the data-sending device to generate a retransmit control signal; generating a third transmission for wireless communication to the data-receiving device by applying a gating function to the first data block in the delay buffer using the retransmit control signal as a control input and providing an output of the gating function to an input of the transmitter neural network; and wirelessly communicating the third transmission to the data-receiving device.

2 . The method of claim 1 , wherein the second transmission represents a hybrid automatic repeat request (HARQ) signal from the data-receiving device.

3 . The method of claim 1 , wherein:
the retransmit control signal comprises a binary signal; and generating the third transmission comprises: generating the third transmission based on at least a portion of the first data block responsive to the binary signal having a first value; and generating the third transmission independent of the first data block responsive to the binary signal having a second value.

4 . The method of claim 1 , wherein:
the retransmit control signal comprises a non-linear activation function; and generating the third transmission to include one or more portions of the first data block based on the non-linear activation function.

5 . The method of claim 1 , wherein each of the transmitter neural network and the receiver neural network has a plurality of neural network architecture configurations, each neural network architecture configuration associated with a different corresponding scheduling grant type of a plurality of scheduling grant types; and
the method further comprises: jointly training the transmitter neural network and the receiver neural network in conjunction with at least one neural network of the data-receiving device using one or more sets of training data, wherein jointly training the transmitter neural network and the receiver neural network includes individually training multiple neural network architecture configurations of the plurality of neural network architecture configurations.

6 . The method of claim 5 , further comprising:
determining a current scheduling grant type implemented for the data-sending device, the current scheduling grant type comprising one of a grant to transmit control information only, a grant to transmit user-plane data only, or a grant to transmit both control information and user-plane data; and configuring the transmitter neural network and the receiver neural network to implement a neural network architecture configuration of the plurality of neural network architecture configurations that is associated with the current scheduling grant type.

7 . The method of claim 1 , wherein:
generating the third transmission includes generating the third transmission at the transmitter neural network further based on a second data block received subsequent to the first data block.

8 . The method of claim 1 , wherein:
processing the second transmission at the receiver neural network of the data-sending device further comprises processing the second transmission at the receiver neural network of the data-sending device to attempt to recover a second data block from the second transmission.

9 . The method of claim 8 , further comprising:
generating a transmission feedback signal at the receiver neural network of the data-sending device, the transmission feedback signal representing a status of recovery of the second data block from the second transmission; and wherein generating the third transmission further includes processing the transmission feedback signal at the transmitter neural network of the data-sending device.

10 . The method of claim 9 , wherein the transmission feedback signal comprises a hybrid automatic repeat request (HARQ) control signal.

11 . A data-sending device comprising:
a radio frequency front end; at least one processor coupled to the radio frequency front end; and a non-transitory computer-readable medium storing one or more sets of instructions, the one or more sets of instructions configured to manipulate the at least one processor to perform the method of claim 1 .

12 . A computer-implemented method, in a data-receiving device, comprising:
receiving, at a receiver neural network of the data-receiving device, a first transmission wirelessly communicated from a data-sending device; processing the first transmission at the receiver neural network of the data-receiving device to attempt to recover a first data block and to generate a first transmission feedback signal representative of the attempt to recover the first data block; generating, at a transmitter neural network of the data-receiving device, a second transmission based on the first transmission feedback signal; and wirelessly communicating the second transmission to the data-sending device.

13 . The method of claim 12 , wherein the second transmission represents a hybrid automatic repeat request (HARQ) signal.

14 . The method of claim 12 , wherein:
the first transmission feedback signal represents a failed attempt to recover the first data block; and the method further includes:
receiving, at the receiver neural network, a third transmission wirelessly communicated from the data-sending device;
processing the third transmission at the receiver neural network of the data-receiving device to attempt to recover at least a portion of the first data block and to generate a second transmission feedback signal representative of the attempt to recover at least a portion of the first data block; and
generating, at the transmitter neural network, a fourth transmission for wireless communication to the data-sending device based on the second transmission feedback signal.

15 . The method of claim 14 , wherein:
each of the transmitter neural network and the receiver neural network has a plurality of neural network architecture configurations, each neural network architecture configuration associated with a different corresponding scheduling grant type of a plurality of scheduling grant types; and the method further includes:
jointly training the transmitter neural network and the receiver neural network in conjunction with at least one neural network of the data-sending device using one or more sets of training data, wherein jointly training the transmitter neural network and the receiver neural network includes individually training multiple neural network architecture configurations of the plurality of neural network architecture configurations.

16 . The method of claim 15 , further comprising:
determining a current scheduling grant type implemented for the data-receiving device, the current scheduling grant type comprising one of a grant to transmit control information only, a grant to transmit user-plane data only, or a grant to transmit both control information and user-plane data; and configuring the transmitter neural network and the receiver neural network to implement a neural network architecture configuration of the plurality of neural network architecture configurat

Assignees

• Google Llc

Inventors

• Wang Jibing
• Stauffer Erik Richard

Classifications

• H04L1/1887 Primary

  Scheduling and prioritising arrangements · CPC title

• H04L1/1874

  Buffer management · CPC title

• G06N3/045

  Combinations of networks · CPC title

• G06N3/048

  Activation functions · CPC title

• H04L1/1812 Primary

  Hybrid protocols; Hybrid automatic repeat request [HARQ] · CPC title