US 12,231,183 B2Granted

Machine learning for beam predictions with confidence indications

AssigneeQUALCOMM Incorporated

InventorsTianyang Bai, Hua Wang, Taesang Yoo, Junyi Li

Life of this patent

Estimating the term…

Loading patent…

Abstract

Various aspects of the present disclosure generally relate to wireless communication. In some aspects, a user equipment (UE) may receive a signal. The UE may determine, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises: receiving, by the machine learning model, an input that comprises an input metric and an error measurement corresponding to the input metric; and providing, by the machine learning model, and based at least in part on a machine learning function and the input, the predicted communication metric and the confidence indication. The UE may perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication. Numerous other aspects are described.

Claims30

Dependent claims

A method of wireless communication performed by a user equipment (UE), comprising:

receiving a signal comprising a synchronization signal block (SSB);
determining, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, wherein the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises:
receiving, by the machine learning model, an input that comprises an input metric and an error measurement corresponding to the input metric;
obtaining, by the machine learning model and based at least in part on a machine learning function associated with a set of reference signals and the error measurement, a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals, wherein obtaining the set of measurements comprises skipping at least one configured measurement based at least in part on receiving a downlink communication during a measurement occasion corresponding to the at least one configured measurement;
generating, by the machine learning model and based at least in part on the machine learning function, an interpolated measurement corresponding to a first input port, of the machine learning function, for which the measurement was not obtained;
generating, by the machine learning model and based at least in part on the machine learning function, a measurement pattern indication, corresponding to the set of measurements, including:
an indication of at least one of the first input port for which the measurement was not obtained, or a second input port of the machine learning function for which the measurement was obtained, and
an indication of an interpolation error corresponding to the interpolated measurement;
providing, by the machine learning model and based at least in part on the machine learning function and the input, the predicted communication metric and the confidence indication;
and
performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

8 more elements

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:
receive a signal comprising a synchronization signal block (SSB);
determine, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, wherein the machine learning component comprising a machine learning model, and wherein, to determine the predicted communication metric and the confidence indication, the one or more processors are configured to:
receive, by the machine learning model, an input that comprises an input metric and an error measurement corresponding to the input metric;
obtain, by the machine learning model and based at least in part on a machine learning function associated with a set of reference signals and the error measurement, a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals, wherein, to obtain the set of measurements, the one or more processors are configured to skip at least one configured measurement based at least in part on receiving a downlink communication during a measurement occasion corresponding to the at least one configured measurement;
generate, by the machine learning model and based at least in part on the machine learning function, an interpolated measurement corresponding to a first input port, of the machine learning function, for which the measurement was not obtained;
generate, by the machine learning model and based at least in part on the machine learning function, a measurement pattern indication, corresponding to the set of measurements, including:
an indication of at least one of the first input port for which the measurement was not obtained, or a second input port of the machine learning function for which the measurement was obtained, and an indication of an interpolation error corresponding to the interpolated measurement;
and
provide and based at least in part on a machine learning function and the input, the predicted communication metric and the confidence indication;
and
perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

11 more elements

An apparatus for wireless communication at a user equipment (UE), comprising:

one or more memories;
and
one or more processors, coupled to the one or more memories, configured to cause the UE to:
receive a signal comprising a synchronization signal block (SSB);
determine, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, wherein the machine learning component comprising a machine learning model, and wherein, to determine the predicted communication metric and the confidence indication, the one or more processors are configured to:
receive an input that comprises an input metric and an error measurement corresponding to the input metric;
obtain, based at least in part on a machine learning function associated with a set of reference signals and the error measurement, a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals, wherein obtaining the set of measurements comprises skipping at least one configured measurement based at least in part on receiving a downlink communication during a measurement occasion corresponding to the at least one configured measurement;
generate, based at least in part on the machine learning function, an interpolated measurement corresponding to a first input port, of the machine learning function, for which the measurement was not obtained;
generate, based at least in part on the machine learning function, a measurement pattern indication, corresponding to the set of measurements, including:
an indication of at least one of the first input port for which the measurement was not obtained, or a second input port of the machine learning function for which the measurement was obtained, and an indication of an interpolation error corresponding to the interpolated measurement;
provide, based at least in part on the machine learning function and the input, the predicted communication metric and the confidence indication;
and
perform a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

10 more elements

An apparatus for wireless communication, comprising:

means for receiving a signal comprising a synchronization signal block (SSB);
means for determining, based at least in part on a machine learning component, a predicted communication metric and a confidence indication, the machine learning component comprising a machine learning model, and wherein determining the predicted communication metric and the confidence indication comprises:
means for receiving an input that comprises an input metric and an error measurement corresponding to the input metric;
means for obtaining, based at least in part on a machine learning function associated with a set of reference signals and the error measurement, a set of measurements associated with a subset of the set of reference signals, wherein the subset includes fewer reference signals than the set of reference signals, wherein obtaining the set of measurements comprises skipping at least one configured measurement based at least in part on receiving a downlink communication during a measurement occasion corresponding to the at least one configured measurement;
means for generating, based at least in part on the machine learning function, an interpolated measurement corresponding to a first input port, of the machine learning function, for which the measurement was not obtained;
means for generating, based at least in part on the machine learning function, a measurement pattern indication, corresponding to the set of measurements, including:
an indication of at least one of the first input port for which the measurement was not obtained, or a second input port of the machine learning function for which the measurement was obtained, and an indication of an interpolation error corresponding to the interpolated measurement;
means for providing, based at least in part on the machine learning function and the input, the predicted communication metric and the confidence indication;
and
means for performing a wireless communication task based at least in part on the predicted communication metric and the confidence indication.

7 more elements

Dependencies are inferred from the claim text.

Facts

Application: 17/661,543Filed 29 Apr 2022
Published: US 2023/0353264 A12 Nov 2023
Granted: 18 Feb 2025
Term ends: Not estimatedThe source records don’t support an estimate.

Classification9 codes

H04B 7/04
Diversity systems; Multi-antenna system, i.e. transmission or reception using multiple antennas: using two or more spaced independent antennas
H04B 17/373
Of propagation channels: predicting channel quality or other radio frequency [RF] parameters
G06N 3/08
Neural networks: learning methods
H04B 7/0656
Feedback error handling: at the transmitter, e.g. error detection at base station