# US 2026/0066970 A1 · Channel state information switching prediction

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

- Number: US 2026/0066970 A1
- Document ID: US20260066970A1
- Status: Published application
- Kind: A1
- Application number: 19/247,920
- Filed: 2025-06-24
- Published: 2026-03-05
- Earliest claimed: 2024-06-26
- Assignees: TeraSpatial, Inc.
- Applicants: TeraSpatial, Inc.
- Inventors: Ahmed Alkhateeb; Ramya Srinivasan; Yu Zhang; Jeyanandh Paramesh; Dhinakarraj Gantala
- Web page: https://patentgrep.com/patent/US20260066970A1

## CPC

- H04B 7/0626: {Channel coefficients, e.g. channel state information [CSI]}
- H04B 7/0639: {Using selective indices, e.g. of a codebook, e.g. pre-distortion matrix index [PMI] or for beam selection}
- H04L 5/0005: {Time-frequency}
- H04L 41/16: using machine learning or artificial intelligence
- H04B: TRANSMISSION
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

Data associated with a coverage area of a base station is obtained. A model is trained based in part on the obtained data associated with the coverage area. The trained model is deployed to make inferences for one or more user equipment (UE) located in the coverage area. A corresponding recommended reference signal outputted by the trained model is utilized to decide on an approach for estimating corresponding channels associated with the one or more UE located in the coverage area

## Claims

### Claim 1

A method, comprising:
obtaining data associated with a coverage area of a base station;
training a model based in part on the obtained data associated with the coverage area;
deploying the trained model to make inferences for one or more user equipment (UE) located in the coverage area; and
utilizing a corresponding recommended reference signal outputted by the trained model to decide on an approach for estimating corresponding channels associated with the one or more UE located in the coverage area.

### Claim 2 (depends on 1)

The method of claim 1, wherein obtaining data associated with the coverage area of the base station includes performing a plurality of channel state information-reference signal (CSI-RS) measurements and a plurality of sounding reference signal (SRS) measurements within the coverage area of the base station.

### Claim 3 (depends on 2)

The method of claim 2, wherein the plurality of CSI-RS measurements and the plurality of SRS measurements are associated with the one or more UEs.

### Claim 4 (depends on 3)

The method of claim 3, where the one or more UEs have a corresponding route.

### Claim 5 (depends on 1)

The method of claim 1, wherein obtaining the data associated with the coverage area of the base station includes collecting information for a selected UE of the one or more UE for a plurality of time windows.

### Claim 6 (depends on 5)

The method of claim 5, wherein the collected information for the selected UE includes one or more of CSI-RS and SRS measurements, CSI-RS and SRS throughput, a number of MU-MIMO UEs, and a number of layers/UE.

### Claim 7 (depends on 5)

The method of claim 5, wherein the selected UE is randomly selected.

### Claim 8 (depends on 5)

The method of claim 5, wherein the selected UE is selected based on quality of service or throughput requirements.

### Claim 9 (depends on 1)

The method of claim 1, wherein the trained model is a supervised machine learning model.

### Claim 10 (depends on 7)

The method of claim 7, wherein each time window of a plurality of time windows is labeled with a corresponding preferred channel acquisition method.

### Claim 11 (depends on 8)

The method of claim 8, wherein the corresponding preferred channel acquisition method is CSI-RS.

### Claim 12 (depends on 8)

The method of claim 8, wherein the corresponding preferred channel acquisition method is SRS.

### Claim 13 (depends on 1)

The method of claim 1, wherein deploying the trained model includes obtaining a sequence of SRS channel estimate or CSI-RS Channel Quality Indicator and Precoding Matrix Indicator reports.

### Claim 14 (depends on 1)

The method of claim 1, wherein the sequence of SRS channel estimate or the CSI-RS Channel Quality Indicator and Precoding Matrix Indicator reports, and the trained model are utilized to decide how to schedule the one or more UEs, including which time slots, frequency blocks, and resources to allocate.

### Claim 15 (depends on 1)

The method of claim 1, wherein the trained model is deployed to perform channel prediction for one or more future time windows.

### Claim 16 (depends on 1)

The method of claim 1, wherein the trained model is located in the base station, on-premises, at a remote server, or on a cloud server.

### Claim 17

A system, comprising:
a processor configured to:
obtaining data associated with a coverage area of a base station;
training a model based in part on the obtained data associated with the coverage area;
deploying the trained model to make inferences for one or more user equipment (UE) located in the coverage area; and
utilize a corresponding recommended reference signal outputted by the trained model to decide on an approach for estimating corresponding channels associated with the one or more UE located in the coverage area; and
a memory coupled to the processor and configured to provide the processor with instructions.

### Claim 18 (depends on 17)

The system of claim 17, wherein to obtain the data associated with the coverage area of the base station, the processor is configured to perform a plurality of channel state information-reference signal (CSI-RS) measurements and a plurality of sounding reference signal (SRS) measurements within the coverage area of the base station.

### Claim 19 (depends on 18)

The system of claim 18, wherein the plurality of CSI-RS measurements and the plurality of SRS measurements are associated with the one or more UEs.

### Claim 20 (depends on 19)

The system of claim 19, where the one or more UEs have a corresponding route.

### Claim 21

A computer program product embodied in a non-transitory computer readable medium and comprising computer instructions for:
obtaining data associated with a coverage area of a base station;
training a model based in part on the obtained data associated with the coverage area;
deploying the trained model to make inferences for one or more user equipment (UE) located in the coverage area; and
utilizing a corresponding recommended reference signal outputted by the trained model to decide on an approach for estimating corresponding channels associated with the one or more UE located in the coverage area.
