# US 2026/0230142 A1 · Monitoring the performance of a model based on machine learning for reporting channel state information

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

- Number: US 2026/0230142 A1
- Document ID: US20260230142A1
- Status: Published application
- Kind: A1
- Application number: 19/154,978
- Filed: 2024-02-13
- Published: 2026-08-06
- Earliest claimed: 2023-02-14
- Assignees: InterDigital Patent Holdings, Inc.
- Applicants: InterDigital Patent Holdings, Inc.
- Inventors: Ahmet Serdar TAN; Patrick TOOHER; Yugeswar Deenoo NARAYANAN THANGARAJ; Mohamed Salah IBRAHIM; Moon IL LEE; Mihaela BELURI
- Web page: https://patentgrep.com/patent/US20260230142A1

## CPC

- H04B 7/0626: {Channel coefficients, e.g. channel state information [CSI]}
- H04L 1/0026: {Transmission of channel quality indication}
- H04B 7/0632: {Channel quality parameters, e.g. channel quality indicator [CQI]}
- H04B 7/0658: {Feedback reduction}
- H04L 1/0029: {Reduction of the amount of signalling, e.g. retention of useful signalling or differential signalling (power control H04W52/04)}
- H04L 1/244: {test sequence generators}
- H04L 5/0057: {Physical resource allocation for CQI}
- H04L 41/16: using machine learning or artificial intelligence
- H04W 72/21: in the uplink direction of a wireless link, i.e. towards the network
- H03M 7/3059: {Digital compression and data reduction techniques where the original information is represented by a subset or similar information, e.g. lossy compression}
- H04L 1/0014: {by adapting the source coding}
- H04B: TRANSMISSION
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- H03M: CODING; DECODING; CODE CONVERSION IN GENERAL (using fluidic means F15C4/00; optical analogue/digital converters G02F7/00; coding, decoding or code conversion, specially adapted for particular applications, see the relevant subclasses, e.g. G01D, G01R, G06F, G06T, G09G, G10L, G11B, G11C, H04B, H04L, H04M, H04N; ciphering or deciphering for cryptography or other purposes involving the need for secrecy G09C)

## Abstract

A wireless transmit receiver unit (WTRU) using two-sided models for channel state information (CSI) feedback is configured to determine input/output CSI mismatch between the CSI reconstructed at the NW-side and the CSI estimated at the WTRU-side. The WTRU receives configuration information including a CSI mismatch measurement method, a CSI mismatch measurement metric and one or more thresholds for CSI mismatch detection. The WTRU receives one or more CSI reference signals (CSI-RSs) and estimates CSI. The WTRU determines a CSI mismatch event when a mismatch measurement exceeds a first CSI mismatch detection threshold. The WTRU selects a CSI mismatch mitigation method as a function of the I/O CSI mismatch measurement and reports CSI feedback for the received CSI-RSs and CSI mismatch information including at least one of: the I/O CSI mismatch measurement, an indication of the determined CSI mismatch event, or the selected CSI mismatch mitigation method.

## Claims

### Claim 1

A method for a wireless transmit receive unit (WTRU), the method comprising:
receiving, from a base station, configuration information for detecting an input/output (I/O) channel state information (CSI) mismatch of two-sided artificial intelligence machine learning (AI/ML) models, the configuration information including a CSI mismatch measurement method, a CSI mismatch measurement metric and one or more thresholds for CSI mismatch detection;
receiving one or more CSI reference signals (CSI-RSs) and estimating CSI based on the received CSI-RSs;
determining an I/O CSI mismatch measurement based on at least one of the CSI mismatch measurement metric, the estimated CSI or the configured CSI mismatch measurement method;
determining a CSI mismatch event when the determined I/O CSI mismatch measurement exceeds a first CSI mismatch detection threshold of the one or more configured thresholds for CSI mismatch detection;
selecting a CSI mismatch mitigation method as a function of the I/O CSI mismatch measurement; and
reporting, to the base station, CSI feedback for the received CSI-RSs and CSI mismatch information, wherein the CSI mismatch information comprises at least one of: the I/O CSI mismatch measurement, an indication of the determined CSI mismatch event, or the selected CSI mismatch mitigation method.

### Claim 2 (depends on 1)

The method of claim 1, wherein the selected CSI mismatch mitigation method comprises:
identifying whether the CSI feedback reporting is to be transmitted using a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH); and
(i) when the CSI feedback reporting uses the PUSCH, decreasing a CSI feedback compression rate when the I/O CSI mismatch measurement exceeds a second CSI mismatch detection threshold of the one or more configured thresholds for CSI mismatch detection; or
(ii) when the CSI feedback reporting uses the PUCCH, requesting to switch the CSI feedback reporting to the PUSCH when the I/O CSI mismatch measurement is less than or equal to the second CSI mismatch detection threshold of the one or more configured threshold for CSI mismatch detection.

### Claim 3 (depends on 1)

The method of claim 1, wherein the selected CSI mismatch mitigation method comprises selecting and reporting an encoder-decoder pair that results in an I/O CSI measurement lower than the first CSI mismatch detection threshold.

### Claim 4 (depends on 1)

The method of claim 1, wherein the CSI mismatch measurement metric comprises a normalized mean squared error (NMSE) or a weighted squared generalized cosine similarity (SGCS) of a channel with the base station.

### Claim 5 (depends on 1)

The method of claim 1, wherein the determined I/O CSI mismatch measurement is based on transmission statistics of previous CSI feedback.

### Claim 6 (depends on 5)

The method of claim 5, wherein the transmission statistics comprise a number of consecutive non-acknowledgements (NACKs).

### Claim 7 (depends on 1)

The method of claim 1, wherein reporting CSI feedback for the received CSI-RSs includes compressed CSI, rank indicator (RI), channel quality index (CQI) and precoding matrix index (PMI).

### Claim 8

A wireless transmit receive unit (WTRU) comprising:
a transceiver and a processor communicatively coupled to the transceiver, the transceiver and processor configured to:
receive, from a base station, configuration information for detecting an input/output (I/O) channel state information (CSI) mismatch of two-sided artificial intelligence machine learning (AI/ML) models, the configuration information including a CSI mismatch measurement method, a CSI mismatch measurement metric and one or more thresholds for CSI mismatch detection;
receive one or more CSI-RSs and estimate CSI based on the received CSI-RSs;
determine an I/O CSI mismatch measurement based on at least one of the CSI mismatch measurement metric, the estimated CSI or the configured CSI mismatch measurement method;
determine a CSI mismatch event when the determined I/O CSI mismatch measurement exceeds a first CSI mismatch detection threshold of the one or more configured thresholds for CSI mismatch detection;
select a CSI mismatch mitigation method as a function of the I/O CSI mismatch measurement; and
report, to the base station, CSI feedback for the received CSI-RSs and CSI mismatch information, wherein the CSI mismatch information comprises at least one of: the I/O CSI mismatch measurement, an indication of the determined CSI mismatch event, or the selected CSI mismatch mitigation method.

### Claim 9 (depends on 8)

The WTRU of claim 8, wherein the selected CSI mismatch mitigation method includes the transceiver and processor further configured to:
identify whether the CSI feedback reporting is to be transmitted using a physical uplink shared channel (PUSCH) or a physical uplink control channel (PUCCH); and
(i) when the CSI feedback reporting uses the PUSCH, decrease a CSI feedback compression rate when the I/O CSI mismatch measurement exceeds a second CSI mismatch detection threshold of the one or more configured thresholds for CSI mismatch detection; or
(ii) when the CSI feedback reporting uses the PUCCH, request to switch the CSI feedback reporting to the PUSCH when the I/O CSI mismatch measurement is less than or equal to the second CSI mismatch detection threshold of the one or more configured threshold for CSI mismatch detection.

### Claim 10 (depends on 8)

The WTRU of claim 8, wherein the selected CSI mismatch mitigation method includes the transceiver and processor further configured to select and report an encoder-decoder pair that results in an I/O CSI measurement lower than the first CSI mismatch detection threshold.

### Claim 11 (depends on 8)

The WTRU of claim 8, wherein the CSI mismatch measurement metric comprises a normalized mean squared error (NMSE) or a weighted squared generalized cosine similarity (SGCS) of a channel with the base station.

### Claim 12 (depends on 8)

The WTRU of claim 8, wherein the determined I/O CSI mismatch measurement is based on transmission statistics of previous CSI feedback.

### Claim 13 (depends on 12)

The WTRU of claim 12, wherein the transmission statistics comprise a number of consecutive non-acknowledgements (NACKs).

### Claim 14 (depends on 8)

The WTRU of claim 8, wherein the report of CSI feedback for the received CSI-RSs includes compressed CSI, rank indicator (RI), channel quality index (CQI) and precoding matrix index (PMI).

### Claim 15

A base station comprising:
a transceiver and a processor communicatively coupled to the transceiver, the transceiver and processor configured to:
send, to a wireless transmit receive unit (WTRU), configuration information for detecting an input/output (I/O) channel state information (CSI) mismatch of two-sided artificial intelligence machine learning (AI/ML) models, the configuration information including a CSI mismatch measurement method, a CSI mismatch measurement metric and one or more thresholds for CSI mismatch detection;
send one or more CSI-RSs for the WTRU to estimate CSI;
receive a rank indicator (RI) and channel quality index (CQI) from the WTRU based on the one or more CSI-RSs; and
receive, from the WTRU, CSI feedback for the sent CSI-RSs and CSI mismatch information, wherein the received CSI mismatch information comprises at least one of: an I/O CSI mismatch measurement, an indication of a determined CSI mismatch event, or a selected CSI mismatch mitigation method.

### Claim 16 (depends on 15)

The base station of claim 15, wherein the selected CSI mismatch mitigation method includes a recommended encoder-decoder pair that results in an I/O CSI measurement lower than the first CSI mismatch detection threshold.

### Claim 17 (depends on 15)

The base station of claim 15, wherein the CSI mismatch measurement metric of the sent configuration information comprises a normalized mean squared error (NMSE) or a weighted squared generalized cosine similarity (SGCS) of a channel.

### Claim 18 (depends on 15)

The base station of claim 15, wherein the received CSI feedback for the sent CSI-RSs includes compressed CSI, rank indicator (RI), channel quality index (CQI) and precoding matrix index (PMI).
