# US 2025/0168589 A1 · Method and device for determining a location of a mobile device

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

- Number: US 2025/0168589 A1
- Document ID: US20250168589A1
- Status: Published application
- Kind: A1
- Application number: 18/724,896
- Filed: 2022-12-27
- Published: 2025-05-22
- Earliest claimed: 2021-12-29
- Assignees: Grabtaxi Holdings Pte. Ltd.
- Applicants: Grabtaxi Holdings Pte. Ltd.
- Inventors: Vibhuti Dineshkumar VADGAMA; Mei LENG
- Web page: https://patentgrep.com/patent/US20250168589A1

## CPC

- H04W 4/02: Services making use of location information
- H04W 4/33: for indoor environments, e.g. buildings
- G01S 5/02525: {Gathering the radio frequency fingerprints}
- G01S 5/0278: {involving statistical or probabilistic considerations (G01S5/0252, G01S5/0294 take precedence)}
- G06N 3/08: Learning methods
- G06N 3/09: Supervised learning
- H04W 64/00: Locating users or terminals {or network equipment} for network management purposes, e.g. mobility management
- H04W: WIRELESS COMMUNICATION NETWORKS (broadcast communication H04H; communication systems using wireless links for non-selective communication, e.g. wireless extensions H04M1/72)
- 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
- G06N: COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS

## Abstract

Aspects concern a method for determining a location of a mobile device comprising, for each order of a transport or transport-related service, wherein the order is made by means of a respective mobile terminal, generating a training data element from a wireless radio fingerprint observed by the respective mobile terminal at the time of the order and a location of the order, training a machine learning model with the training data elements by using the wireless radio fingerprints as inputs and the respective locations as ground truth and determining the location of a mobile device by acquiring a wireless radio fingerprint observed by the mobile device and feeding the wireless radio fingerprint to the trained machine learning model.

## Claims

### Claim 1

A method for determining a location of a mobile device comprising:
for each order of a service, wherein the order is made by means of a respective mobile terminal, generating a training data element from a wireless radio fingerprint observed by the respective mobile terminal at the time of the order and a location of the order; training a machine learning model with the training data elements by using the wireless radio fingerprints as inputs and the respective locations as ground truth; and determining the location of a mobile device by acquiring a wireless radio fingerprint observed by the mobile device and feeding the wireless radio fingerprint to the trained machine learning model.

### Claim 2 (depends on 1)

The method of claim 1, further comprising getting, for at least some of the training data elements, an estimate of the mobile terminal's location by means of Global Positioning System and evaluating the trained machine learning model by comparing, for the at least some training data elements, the estimate of the mobile terminal's location and a location prediction for by the mobile terminal by the machine learning model.

### Claim 3 (depends on 2)

The method of claim 2, comprising continuing training of the machine learning model depending on the evaluation.

### Claim 4 (depends on 1)

The method of claim 1, wherein the machine learning model is a neural network.

### Claim 5 (depends on 1)

The method of claim 1, wherein each training data element comprises additional machine learning model input data related to the respective mobile terminal, comprising at least one of an indication of a time when the respective mobile terminal has observed the wireless radio fingerprint and information about the mobile terminal and wherein the location of the mobile device is determined by feeding corresponding input data related to the mobile device to the machine learning model.

### Claim 6 (depends on 1)

The method of claim 1, comprising, using the trained neural network, providing localization for a further service.

### Claim 7 (depends on 6)

The method of claim 6, wherein the further service is one of transportation, delivery, shopping, payment and advertising.

### Claim 8 (depends on 1)

The method of claim 1, comprising evaluating a performance difference between the further service when being provided with localization by the neural network and the service when using Global Positioning System-based localization.

### Claim 9 (depends on 8)

The method of claim 8, comprising performing the further service by using localization by the neural network depending on the result of the evaluation of the performance difference.

### Claim 10 (depends on 1)

The method of claim 1, wherein the neural network is trained to provide a latitude and a longitude and/or a geohash from its input.

### Claim 11 (depends on 1)

A localization server configured to perform the method of claim 1.

### Claim 12 (depends on 1)

A computer program element comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform the method of claim 1

### Claim 13 (depends on 1)

A computer-readable medium comprising program instructions, which, when executed by one or more processors, cause the one or more processors to perform the method of claim 1.
