Machine learning component management

Patent metadata

Field	Value
Publication number	US-12556975-B2
Application number	US-202217821388-A
Country	US
Kind code	B2
Filing date	Aug 22, 2022
Priority date	Aug 22, 2022
Publication date	Feb 17, 2026
Grant date	Feb 17, 2026

Abstract

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may transmit, to a network node, UE capability information associated with at least one machine learning component. The UE may receive, from the network node and based on the UE capability information, configuration information corresponding to the at least one machine learning component. The UE may generate a first machine learning output based on the machine learning component. The UE may perform a communication task based on the first machine learning output. Numerous other aspects are described.

First claim

What is claimed is:

1 . A user equipment (UE) for wireless communication, comprising:
one or more memories; and one or more processors, coupled to the one or more memories, configured to:
transmit, to a network node, UE capability information associated with at least one machine learning component, wherein the UE capability information indicates at least one machine learning operating parameter state associated with the at least one machine learning component based on an indication of at least one machine learning feature name;
receive, from the network node and based on the UE capability information, configuration information corresponding to the at least one machine learning component;
generate a first machine learning output based on the at least one machine learning component; and
perform a communication task based on the first machine learning output.

2 . The UE of claim 1 ,
wherein the one or more processors are further configured to change the at least one machine learning operating parameter state associated with the at least one machine learning component.

3 . The UE of claim 2 ,
wherein the at least one machine learning operating parameter state comprises at least one of a network setting or a machine learning configuration.

4 . The UE of claim 2 ,
wherein the one or more processors are further configured to receive, from the network node, a change indication that indicates a change associated with a plurality of machine learning operating parameters including the at least one machine learning operating parameter.

5 . The UE of claim 1 ,
wherein the at least one machine learning operating parameter state is configured to be changed based on a network indication, and wherein the one or more processors are further configured to:
receive, from the network node, the network indication; and
change the at least one machine learning operating parameter state from a first state to a second state based on the network indication, wherein the at least one machine learning operating parameter state comprises at least one of a network setting associated with the machine learning component or a machine learning configuration associated with the machine learning component.

6 . The UE of claim 1 ,
wherein the UE capability information indicates one or more machine learning parameter states, of the at least one machine learning operating parameter state, associated with the at least one machine learning feature name.

7 . The UE of claim 1 ,
wherein the one or more processors are further configured to transmit UE assistance information that indicates the at least one machine learning operating parameter state that is configured to be changed based on a network indication.

8 . The UE of claim 7 ,
wherein the UE assistance information indicates the at least one machine learning operating parameter state based on including a request for the network indication, wherein the one or more processors are further configured to:
receive, from the network node, the network indication; and
change the at least one machine learning operating parameter state from a first state to a second state based on the network indication.

9 . The UE of claim 1 ,
wherein the at least one machine learning component comprises a first machine learning component instantiated at the UE and a second machine learning component instantiated at the network node, wherein the second machine learning component is correlated with the first machine learning component, wherein a first set of model structures and a first set of parameter sets correspond to the first machine learning component, and wherein a second set of model structures and a second set of parameter sets correspond to the second machine learning component.

10 . The UE of claim 9 ,
wherein a first machine learning configuration corresponds to the first machine learning component, wherein a second machine learning configuration corresponds to the second machine learning configuration, wherein a first set of priorities corresponds to the first machine learning configuration, and wherein a second set of priorities corresponds to the second machine learning configuration.

11 . The UE of claim 10 ,
wherein the one or more processors are further configured to transmit, to the network node, a UE indication of a configuration change associated with the first machine learning configuration, wherein the UE indication indicates at least one of a change in the first machine learning configuration, a change associated with an environment corresponding to the first machine learning configuration, or a change associated with an execution of the first machine learning configuration.

12 . The UE of claim 11 ,
wherein the one or more processors are further configured to:
receive, from the network node, a network indication of a configuration change associated with the second machine learning configuration; and
change the first machine learning configuration based on the network indication.

13 . The UE of claim 12 ,
wherein the UE capability information indicates at least one of cooperation support associated with the second machine learning configuration or that the network indication is to be transmitted based on the configuration change associated with the second machine learning configuration.

14 . The UE of claim 1 ,
wherein the one or more processors are further configured to receive, from the network node, a network indication that indicates an activation operation associated with the at least one machine learning component, a deactivation operation associated with the at least one machine learning component, or a switch operation associated with the at least one machine learning component,
wherein the one or more processors, to generate at least one of the first machine learning output or a second machine learning output, are configured to generate an output based at least in part on the network indication.

15 . The UE of claim 14 ,
wherein the switch operation corresponds to at least one of a switch from a first model structure to a second model structure or a switch from a first parameter set to a second parameter set.

16 . The UE of claim 15 ,
wherein the one or more processors are further configured to:
determine to change at least one machine learning operating parameter state associated with the at least one machine learning component from a first state to a second state; and
transmit, to the network node, a UE indication associated with changing the at least one machine learning operating parameter state from the first state to the second state.

17 . The UE of claim 16 ,
wherein the determination to change the at least one machine learning operating parameter state is based on satisfaction of at least one of a network-configured change condition, a UE change condition, or a UE key performance indicator condition.

18 . The UE of claim 1 ,
wherein the first machine learning output is based on an inference operation.

19 . The UE of claim 1 ,
wherein the first machine learning output is based on a training operation.

20 . A network node for wireless communication, comprising:
one or more memories; and one or more processors, coupled to the one or more memories, configured to:
receive, from a user equipment (UE), UE capability information associated with at least one machine learning component, wherein the UE capability information indicates at least one machine learning operating parameter state associate

Assignees

• Qualcomm Inc

Inventors

• Kumar Rajeev
• Gholmieh Aziz
• Horn Gavin Bernard
• Zhu Xipeng

Classifications

• H04W24/02

  Arrangements for optimising operational condition · CPC title

• H04W8/24

  Transfer of terminal data · CPC title

• H04L41/16

  using machine learning or artificial intelligence · CPC title

• H04W28/18 Primary

  Negotiating wireless communication parameters · CPC title

• G06N20/00 Primary

  Machine learning · CPC title