# US 2026/0230845 A1 · Methods to support aiml fallback operation

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 2026/0230845 A1
- Document ID: US20260230845A1
- Status: Published application
- Kind: A1
- Application number: 19/044,478
- Filed: 2025-02-03
- Published: 2026-08-06
- Earliest claimed: 2025-02-03
- Assignees: InterDigital Patent Holdings, Inc.
- Applicants: InterDigital Patent Holdings, Inc.
- Inventors: Dylan Watts; Ghyslain Pelletier; Patrick Tooher; Oumer Teyeb; Yugeswar Deenoo Narayanan Thangaraj; Brian Martin; Virgil Comsa; James Miller
- Web page: https://patentgrep.com/patent/US20260230845A1

## CPC

- H04B 17/3913: {Predictive models, e.g. based on neural network models}
- H04W 24/02: Arrangements for optimising operational condition
- G06N 3/044: Recurrent networks, e.g. Hopfield networks
- G06N 3/045: Combinations of networks
- G06N 3/0455: Auto-encoder networks; Encoder-decoder networks
- G06N 3/08: Learning methods
- G06N 3/084: Backpropagation, e.g. using gradient descent
- G06N 3/09: Supervised learning
- G06N 3/098: Distributed learning, e.g. federated learning
- G06N 5/01: Dynamic search techniques; Heuristics; Dynamic trees; Branch-and-bound
- G06N 7/01: Probabilistic graphical models, e.g. probabilistic networks
- G06N 20/00: Machine learning
- G06N 20/10: using kernel methods, e.g. support vector machines [SVM]
- G06N 20/20: Ensemble learning
- H04L 41/16: using machine learning or artificial intelligence
- H04B: TRANSMISSION
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A method may be implemented by a wireless transmit/receive unit (WTRU), including receiving information indicating first applicability conditions and a first configuration for a first artificial intelligence or machine learning (AIML) model category and second applicability conditions and a second configuration for a second AIML model category. It may be determined whether the first AIML model category is applicable to a cell based on the first applicability conditions and first configuration, and whether the second AIML model category is applicable based on the second applicability conditions and second configuration. A report may be sent indicating applicability of the first AIML model category and second AIML category to the cell. It may be determined that the first AIML model category is no longer applicable based on the first configuration. An indication that indicates that the first AIML model category is no longer applicable to the cell may be sent.

## Claims

### Claim 1

A wireless transmit/receive unit (WTRU) comprising:
a processor configured to:
receive information indicating first applicability conditions for a first artificial intelligence or machine learning (AIML) model category and second applicability conditions for a second AIML model category, and a first configuration associated with the first AIML model category and a second configuration associated with the second AIML model category;
determine whether a first AIML model category is applicable to a cell based on the first applicability conditions and the first configuration, and determine whether the second AIML model category is applicable to the cell based on the second applicability conditions and the second configuration;
send a report, wherein the report indicates applicability of the first AIML model category to the cell and indicates the applicability of the second AIML model category to the cell;
determine that the first AIML model category is no longer applicable to the cell based on the first configuration; and
send an indication that indicates that the first AIML model category is no longer applicable to the cell.

### Claim 2 (depends on 1)

The WTRU of claim 1, wherein the processor is further configured to:
perform inference using a model of the first AIML category based on the first configuration in response to determining that the first AIML category is applicable to the cell; and
perform inference using a model of the second AIML category based on the second configuration in response to determining that the first AIML category is no longer applicable to the cell.

### Claim 3 (depends on 1)

The WTRU of claim 1, wherein the first applicability conditions comprise a first indication of one or more of: a number of Transmission-Reception Points (TRPs), a number of antennas, an antenna tilt, a polarization of an antenna, a beam, a geographic area, or a time-period; and
wherein the second applicability conditions comprise a second indication of one or more of: a number of Transmission-Reception Points (TRPs), a number of antennas, an antenna tilt, a polarization of an antenna, a beam, a geographic area, or a time-period.

### Claim 4 (depends on 1)

The WTRU of claim 1, wherein the first AIML model category is associated with a different prediction time horizon, a different prediction confidence level, a different processing requirement, and is configured for a different frequency, a different cell, a different location, or a different time of day as compared to the second AIML model category.

### Claim 5 (depends on 1)

The WTRU of claim 1, wherein the report comprises a list of one or more cells in which at least one AIML model category is applicable based on the first configuration or the second configuration.

### Claim 6 (depends on 1)

The WTRU of claim 1, wherein the report comprises a request to receive multiple configurations for at least one of the first AIML model category and the second AIML model category, wherein the multiple configurations comprise the first configuration and the second configuration.

### Claim 7 (depends on 1)

The WTRU of claim 1, wherein the report comprises an indication of a preference indicating which of the first configuration or the second configuration is to be initially activated and which is to be stored as a fallback configuration.

### Claim 8 (depends on 1)

The WTRU of claim 1, wherein the processor is configured to perform AIML inference according to the first configuration until the first AIML model category is determined to be no longer applicable; and
wherein the indication that the first AIML model category is no longer applicable indicates that the WTRU will use the second configuration associated with the second AIML model category.

### Claim 9 (depends on 1)

The WTRU of claim 1, wherein the processor is configured to determine that the first AIML model category is no longer applicable based on at least one of mobility of the WTRU to a different cell, a change in network-side applicability conditions, or an update in model availability.

### Claim 10 (depends on 1)

The WTRU of claim 1, wherein the first configuration comprises configuration information enabling inference using an AIML model trained on first network conditions; and
wherein the second configuration comprises configuration information enabling inference using an AIML model trained on second network conditions.

### Claim 11

A method implemented by a wireless transmit/receive unit (WTRU), the method comprising:
receiving information indicating first applicability conditions for a first artificial intelligence or machine learning (AIML) model category and second applicability conditions for a second AIML model category, and a first configuration associated with the first AIML model category and a second configuration associated with the second AIML model category;
determining whether the first AIML model category is applicable to a cell based on the first applicability conditions and the first configuration, and determining whether the second AIML model category is applicable to the cell based on the second applicability conditions and the second configuration;
sending a report, wherein the report indicates applicability of the first AIML model category to the cell and indicates applicability of the second AIML model category to the cell;
determining that the first AIML model category is no longer applicable to the cell based on the first configuration; and
sending an indication that indicates that the first AIML model category is no longer applicable to the cell.

### Claim 12 (depends on 11)

The method of claim 11, further comprising:
performing inference using a model of the first AIML category based on the first configuration in response to determining that the first AIML category is applicable to the cell; and
performing inference using a model of the second AIML category based on the second configuration in response to determining that the first AIML category is no longer applicable to the cell.

### Claim 13 (depends on 11)

The method of claim 11, wherein the first applicability conditions comprise a first indication of one or more of: a number of Transmission-Reception Points (TRPs), a number of antennas, an antenna tilt, a polarization of an antenna, a beam, a geographic area, or a time-period; and
wherein the second applicability conditions comprise a second indication of one or more of: a number of Transmission-Reception Points (TRPs), a number of antennas, an antenna tilt, a polarization of an antenna, a beam, a geographic area, or a time-period.

### Claim 14 (depends on 11)

The method of claim 11, wherein the first AIML model category is associated with a different prediction time horizon, a different prediction confidence level, a different processing requirement, and is configured for a different frequency, cell, location, or time of day as compared to the second AIML model category.

### Claim 15 (depends on 11)

The method of claim 11, wherein the report comprises a list of one or more cells in which at least one AIML model category is applicable based on the first configuration or the second configuration.

### Claim 16 (depends on 11)

The method of claim 11, wherein the report comprises a request to receive multiple configurations for at least one of the first AIML model category and the second AIML model category, wherein the multiple configurations comprise the first configuration and the second configuration.

### Claim 17 (depends on 11)

The method of claim 11, wherein the report comprises an indication of a preference indicating which of the first configuration or the second configuration is to be initially activated and which is to be stored as a fallback configuration.

### Claim 18 (depends on 11)

The method of claim 11, further comprising performing AIML inference according to the first configuration until the first AIML model category is determined to be no longer applicable, wherein the indication that the first AIML model category is no longer applicable indicates that the WTRU will use the second configuration associated with the second AIML model category.

### Claim 19 (depends on 11)

The method of claim 11, further comprising determining that the first AIML model is no longer applicable based on at least one of mobility of the WTRU to a different cell, a change in network-side applicability conditions, or an update in model availability.

### Claim 20 (depends on 11)

The method of claim 11, wherein the first configuration comprises configuration information enabling inference using an AIML model trained on first network conditions, and
wherein the second configuration comprises configuration information enabling inference using an AIML model trained on second network conditions.
