# US 2026/0095880 A1 · Methods for Reliable AI/ML Based Positioning

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

- Number: US 2026/0095880 A1
- Document ID: US20260095880A1
- Status: Published application
- Kind: A1
- Application number: 18/902,124
- Filed: 2024-09-30
- Published: 2026-04-02
- Earliest claimed: 2024-09-30
- Assignees: InterDigital Patent Holdings, Inc.
- Applicants: InterDigital Patent Holdings, Inc.
- Inventors: Fumihiro Hasegawa; Yugeswar Deenoo Narayanan Thangaraj; Moon IL Lee; Shahab Hamidi-Rad; Kunjan Shah; Patrick Tooher
- Web page: https://patentgrep.com/patent/US20260095880A1

## CPC

- G01S 5/0236: {Assistance data, e.g. base station almanac}
- H04W 64/00: Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management
- G01S 5/0045: {Transmission from base station to mobile station (G01S5/009 takes precedence)}
- H04L 5/0048: {Allocation of pilot signals, i.e. of signals known to the receiver (allocation of control signalling H04L5/0053; use of control signalling H04L5/0091)}
- G01S 5/01: {Determining conditions which influence positioning, e.g. radio environment, state of motion or energy consumption}
- G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)}
- G01S: RADIO DIRECTION-FINDING; RADIO NAVIGATION; DETERMINING DISTANCE OR VELOCITY BY USE OF RADIO WAVES; LOCATING OR PRESENCE-DETECTING BY USE OF THE REFLECTION OR RERADIATION OF RADIO WAVES; ANALOGOUS ARRANGEMENTS USING OTHER WAVES
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- H04L: TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION (arrangements common to telegraphic and telephonic communication H04M)

## Abstract

A wireless transmit/receive unit (WTRU) may receive, from a server associated with a trained artificial intelligence/machine leaning (AI/ML) model, a first association information. The first association information may comprise a first set of positioning reference signal (PRS) configurations on which the AI/ML model has been trained. The WTRU may receive a request for inferences related to a location of the WTRU via the AI/ML model. The WTRU may send a request for a second association information which may comprise a second set of PRS configurations. The WTRU may determine, by comparing the first and the second association information, the consistency between the first and the second association information based on PRS configurations of the first set of PRS configurations overlapping with PRS configurations of the second set of PRS configurations. The WTRU may implement the trained AI/ML model to generate inferences related to the location of the WTRU.

## Claims

### Claim 1

A wireless transmit/receive unit (WTRU) comprising a processor and memory, the processor and memory configured to:
receive, from a server associated with a trained artificial intelligence/machine leaning (AI/ML) model, a first association information, wherein the first association information comprises a first set of positioning reference signal (PRS) configurations on which the AI/ML model has been trained;
receive, from a network entity, a request for one or more inferences related to a location of the WTRU via the AI/ML model;
send, to the network entity, a request for a second association information;
receive the second association information, wherein the second association information comprises a second set of PRS configurations;
determine, by comparing the first and the second association information, the consistency between the first and the second association information based on a number of PRS configurations of the first set of PRS configurations overlapping with a number of PRS configurations of the second set of PRS configurations;
implement, based on the determined consistency between the first and the second association information, the trained AI/ML model to generate one or more inferences related to the location of the WTRU;
determine a feedback value based on the one or more inferences related to the location of the WTRU; and
send a report, wherein the report comprises the feedback value.

### Claim 2 (depends on 1)

The WTRU of claim 1, wherein the first set of PRS configurations comprises a first set of transmit/reception points (TRPs) and the second set of PRS configurations comprises a second set of TRPs.

### Claim 3 (depends on 2)

The WTRU of claim 2, wherein the processor and memory are further configured to:
receive a timestamp associated with the first or the second association information.

### Claim 4 (depends on 3)

The WTRU of claim 3, wherein the timestamp is updated by the network entity when a TRP is added or removed from the first or second sets of TRPs.

### Claim 5 (depends on 1)

The WTRU of claim 1, wherein the processor and memory are further configured to:
determine that the consistency between the first and second association information is partially consistent based on a portion of the number of PRS configurations of the first set of PRS configurations overlapping with a portion of the number of PRS configurations of the second set of PRS configurations.

### Claim 6 (depends on 1)

The WTRU of claim 1, wherein the processor and memory are further configured to:
determine that the consistency between the first and second association information is fully consistent based on each of the number of PRS configurations of the first set of PRS configurations overlapping with each of the number of PRS configurations of the second set of PRS configurations.

### Claim 7 (depends on 1)

The WTRU of claim 1, wherein the processor and memory are further configured to:
determine that the consistency between the first and second association information are not consistent based on none of the number of PRS configurations of the first set of PRS configurations overlapping with the number of PRS configurations of the second set of PRS configurations.

### Claim 8 (depends on 7)

The WTRU of claim 7, wherein the feedback value comprises a first feedback value, wherein the processor and memory are further configured to generate a second feedback value that is based on a fallback method that does not use the trained AI/ML model due to the first and second association information determined to be not consistent.

### Claim 9 (depends on 1)

The WTRU of claim 1, wherein the processor and memory are further configured to:
receive, from the network, an instruction to perform a consistency check; and
perform the consistency check between the first association information and the second association information based on the instruction.

### Claim 10 (depends on 1)

The WTRU of claim 1, wherein the processor and memory are further configured to:
receive, from the server, the trained AI/ML model.

### Claim 11

A method implemented by a wireless transmit/receive unit (WTRU), the method comprising:
receiving, from a server associated with a trained artificial intelligence/machine leaning (AI/ML) model, a first association information, wherein the first association information comprises a first set of positioning reference signal (PRS) configurations on which the AI/ML model has been trained;
receiving, from a network entity, a request for one or more inferences related to a location of the WTRU via the AI/ML model;
sending, to the network entity, a request for a second association information;
receiving the second association information, wherein the second association information comprises a second set of PRSs;
determining, by comparing the first and the second association information, the consistency between the first and the second association information based on a number of PRS configurations of the first set of PRS configurations overlapping with a number of PRS configurations of the second set of PRS configurations;
receiving, based on the determined consistency between the first and the second association information, from the trained AI/ML model, one or more inferences related to the location of the WTRU;
determining a feedback value based on the one or more inferences related to the location of the WTRU; and
sending a report, wherein the report comprises the feedback value.

### Claim 12 (depends on 11)

The method of claim 11, wherein the first set of PRS configurations comprises a first set of transmit/reception points (TRPs) and the second set of PRS configurations comprises a second set of TRPs.

### Claim 13 (depends on 12)

The method of claim 12, the method further comprising:
receiving a timestamp associated with the first or the second association information.

### Claim 14 (depends on 13)

The method of claim 13, wherein the timestamp is updated by the network entity when a TRP is added or removed from the first or second sets of TRPs.

### Claim 15 (depends on 11)

The method of claim 11, further comprising determining that the consistency between the first and second association information is partially consistent based on a portion of the number of PRS configurations of the first set of PRS configurations overlapping with a portion of the number of PRS configurations of the second set of PRS configurations.

### Claim 16 (depends on 11)

The method of claim 11, the method further comprising:
determining that the consistency between the first and second association information is fully consistent based on all of the number of PRS configurations of the first set of PRS configurations overlapping with all of the number of PRS configurations of the second set of PRS configurations.

### Claim 17 (depends on 11)

The method of claim 11, the method further comprising:
determining that the consistency between the first and second association information are not consistent based on none of the number of PRS configurations of the first set of PRS configurations overlapping with the number of PRS configurations of the second set of PRS configurations.

### Claim 18 (depends on 17)

The method of claim 17, wherein the feedback value comprises a first feedback value, the method further comprising generating a second feedback value that is based on a fallback method that does not use the trained AI/ML model due to the first and second association information determined to be not consistent.

### Claim 19 (depends on 11)

The method of claim 11, the method further comprising:
receiving, from the network, an instruction to perform a consistency check; and
performing the consistency check between the first association information and the second association information based on the instruction.

### Claim 20 (depends on 11)

The method of claim 11, the method further comprising:
receiving, from the server, the trained AI/ML model.
