Determining and managing applicability of channel learning model

Patent metadata

Field	Value
Publication number	US-12574131-B2
Application number	US-202318153876-A
Country	US
Kind code	B2
Filing date	Jan 12, 2023
Priority date	Jul 13, 2020
Publication date	Mar 10, 2026
Grant date	Mar 10, 2026

Abstract

This application provides communication methods and communications apparatuses. In an example method, a first communications apparatus determines whether a first channel learning model is applicable, where the first channel learning model is used to determine first channel information based on target channel information, and a data amount of the first channel information is less than a data amount of the target channel information. The first communications apparatus sends a first message in response to determining that the first channel learning model is not applicable, where the first message is used to indicate that the first channel learning model is not applicable. According to the example method, the first communications apparatus can determine applicability of the first channel learning model without assistance of a second communications apparatus.

First claim

What is claimed is:

1 . A method, comprising:
determining, by a first communications apparatus, whether a first channel learning model is applicable, wherein the first channel learning model is used to determine first channel information based on target channel information, and a data amount of the first channel information is less than a data amount of the target channel information; sending, by the first communications apparatus, a first message in response to determining that the first channel learning model is not applicable, wherein the first message is used to indicate that the first channel learning model is not applicable; and receiving, by the first communications apparatus, first indication information, wherein the first indication information is used to indicate one or more of the following: a resource used to transmit the first message, content in the first message, a manner of sending the first message, or a channel learning model training parameter, wherein the channel learning model training parameter comprises at least one of the following: a channel learning model training time or configuration information of a reference signal for channel learning model training.

2 . The method according to claim 1 , wherein the determining, by a first communications apparatus, whether a first channel learning model is applicable comprises:
in response to determining that a variation of a long-term statistical characteristic of a target channel is greater than or equal to a first preset threshold, determining, by the first communications apparatus, that the first channel learning model is not applicable; or in response to determining that a variation of a long-term statistical characteristic of a target channel is less than the first preset threshold, determining, by the first communications apparatus, that the first channel learning model is applicable.

3 . The method according to claim 1 , wherein the target channel information is an input to the first channel learning model, and the first channel information is an output of the first channel learning model.

4 . The method according to claim 1 , wherein the determining, by a first communications apparatus, whether a first channel learning model is applicable comprises at least one of:
determining, by the first communications apparatus based on received first scheduling information, whether the first channel learning model is applicable, or determining, by the first communications apparatus based on data transmission performance, whether the first channel learning model is applicable.

5 . The method according to claim 1 , wherein the determining, by a first communications apparatus, whether a first channel learning model is applicable comprises:
in response to determining that a scenario changes, determining, by the first communications apparatus, that the first channel learning model is not applicable; or in response to determining that a scenario does not change, determining, by the first communications apparatus, that the first channel learning model is applicable, wherein the scenario comprises at least one of the following: an indoor still scenario, an outdoor still scenario, a low-speed moving scenario, a high-speed moving scenario, a suburban scenario, an urban scenario, a macro base station, a micro base station, a vehicle-mounted scenario, a vehicle-to-another device scenario, or a scenario defined in a third generation partnership project protocol.

6 . The method according to claim 1 , wherein the determining, by a first communications apparatus, whether a first channel learning model is applicable comprises:
when a performance indicator of the first channel learning model is less than a second preset threshold, determining, by the first communications apparatus, that the first channel learning model is not applicable, wherein the performance indicator comprises continuity and/or trustworthiness; or in response to determining that a performance indicator of the first channel learning model is greater than or equal to the second preset threshold, determining, by the first communications apparatus, that the first channel learning model is applicable.

7 . The method according to claim 1 , wherein the determining, by a first communications apparatus, whether a first channel learning model is applicable comprises:
determining, by the first communications apparatus based on an error between the target channel information and second channel information, whether the first channel learning model is applicable, wherein the second channel information is determined based on the first channel information and a second channel learning model, and the second channel learning model corresponds to the first channel learning model.

8 . The method according to claim 1 ,
wherein the first indication information is used to indicate the first communications apparatus to perform channel learning model training.

9 . The method according to claim 1 , wherein the method further comprises:
sending, by the first communications apparatus, a first request message, wherein the first request message is used to request one or more of the following: an operation of performing channel learning model training, an operation of sending the first message, or the first indication information.

10 . The method according to claim 1 , wherein the first message is further used to indicate one or more configuration parameters used to update a second channel learning model, and the second channel learning model is used to determine second channel information based on the first channel information.

11 . The method according to claim 1 , wherein the method further comprises:
receiving, by the first communications apparatus, a second message, wherein the second message is used to indicate one or more configuration parameters used to update the first channel learning model.

12 . The method according to claim 10 , wherein the method further comprises:
determining, by the first communications apparatus based on a first parameter, the one or more configuration parameters used to update a second channel learning model, wherein: the first parameter comprises at least one of the following: a cell identifier of a cell in which the first communications apparatus is located, a scenario in which the first communications apparatus is located, a type of the first communications apparatus, or a geographical location in which the first communications apparatus is located.

13 . A communication method, comprising:
receiving, by a second communications apparatus, a first message; determining, by the second communications apparatus based on the first message, that a first channel learning model is not applicable, wherein the first channel learning model is used to determine first channel information based on target channel information, and a dimension of the first channel information is less than a dimension of the target channel information; and sending, by the second communications apparatus, first indication information, wherein the first indication information is further used to indicate one or more of the following: a resource used to transmit the first message, content in the first message, a manner of the first message, or a channel learning model training parameter, wherein the channel learning model training parameter comprises at least one of the following: a channel learning model training time or configuration information of a reference signal for channel learning model training.

14 . The method according to claim 13 , wherein the first indication information is used to indicate

Assignees

• Huawei Tech Co Ltd

Inventors

• Wang Ting
• He Gaoning
• Feng Qi
• Lu Jianmin

Classifications

• H04L25/0202

  Channel estimation · CPC title

• H04B7/0417

  Feedback systems · CPC title

• G06N3/0455

  Auto-encoder networks; Encoder-decoder networks · CPC title

• G06N3/091

  Active learning · CPC title

• G06N3/09

  Supervised learning · CPC title