Metadata generation for artificial intelligence (AI) / machine learning (ML) models
AssigneeMediatek Inc.
InventorsPedram Kheirkhah Sangdeh, Gyu Bum Kyung
Life of this patent
Estimating the term…
Abstract
In an aspect of the disclosure, a method, a computer-readable medium, and an apparatus are provided. The apparatus may be a user equipment (UE). The UE generates metadata for channel state information (CSI) samples. The UE uses the generated metadata to categorize the CSI samples into one or more subsets. The UE uses each subset of the one or more subsets to train a machine learning model or a part of a machine learning model.
Claims16
A method of wireless communication of a user equipment (UE), comprising:
- generating metadata for channel state information (CSI) samples, wherein the generating metadata comprises calculating power spectral entropy (PSE) of the CSI samples;
- using the generated metadata to categorize the CSI samples into one or more subsets;
- using each subset of the one or more subsets to train a machine learning model or a part of a machine learning model;
- obtaining a first CSI sample;
- generating first metadata for the first CSI sample;
- matching the first metadata with metadata corresponding to one or more trained machine learning models;
- and
- when matching metadata is found,
- selecting a first trained machine learning model corresponding to the matching metadata;
- and
- using the selected first machine learning model to process the first CSI sample.
An apparatus for wireless communication, the apparatus being a user equipment (UE), comprising:
- a memory;
- and
- at least one processor coupled to the memory and configured to:
- generate metadata for channel state information (CSI) samples, where to generate metadata, the at least one processor is configured to calculate power spectral entropy (PSE) of the CSI samples;
- use the generated metadata to categorize the CSI samples into one or more subsets;
- use each subset of the one or more subsets to train a machine learning model or a part of a machine learning model;
- obtain a first CSI sample;
- generate first metadata for the first CSI sample;
- match the first metadata with metadata corresponding to one or more trained machine learning models;
- and
- when matching metadata is found:
- select a first trained machine learning model corresponding to the matching metadata;
- and
- use the selected first machine learning model to process the first CSI sample.
A non-transitory computer-readable medium storing computer executable code for wireless communication of a receiver, comprising code to:
- generate metadata for channel state information (CSI) samples, where to generate the metadata, the code is configured to calculate power spectral entropy (PSE) of the CSI samples;
- use the generated metadata to categorize the CSI samples into one or more subsets;
- use each subset of the one or more subsets to train a machine learning model or a part of a machine learning model;
- obtain a first CSI sample;
- generate first metadata for the first CSI sample;
- match the first metadata with metadata corresponding to one or more trained machine learning models;
- and
- when matching metadata is found:
- select a first trained machine learning model corresponding to the matching metadata;
- and
- use the selected first machine learning model to process the first CSI sample.
Dependencies are inferred from the claim text.