Granted Patent B2

US 12,424,110 · App. 17/721,477 · Granted Sep 23, 2025

Inventors: Alexander Hoekje List (South Burlington, VT); Vincent Moeykens (South Burlington, VT)

Assignee: BETA AIR LLC

G08G5/34G06F16/61G06F16/63G06N20/00G08G5/55G08G5/57G10L15/22G10L15/26G10L2015/223

Abstract

Claims (43)

1. A system for voice recognition in autonomous flight of an electric aircraft, the system comprising:

a computing device communicatively connected to the electric aircraft, the computing device is configured to:

receive a voice datum from a remote device;

determine, using one or more a first machine learning model models and by inputting the voice datum, transcription data describing the voice datum an expression datum corresponding to an actionable query from the remote device;

determine a query by comparing the transcription data against a dataset including commands associated with maneuvers;

generate a communication output as a function of the query by inputting the query into a second machine learning model expression datum;

adjust a flight plan as a function of the communication output;

generate response data associated with one or more commands used to adjust the flight plan; and

transmit the response data to the remote device to control the aircraft via a flight controller.

2. The system of claim 1 , wherein the computing device is further configured to transmit an adjustment notification to an interface device as a function of adjusting the flight plan.

3. The system of claim 2 , wherein:

the system further comprises the interface device; and

the interface device is configured to display the adjustment notification to a user.

4. The system of claim 1 , wherein generating the transcription data further comprises:

selecting a correlated dataset containing a plurality of data entries wherein each dataset comprises a datum of expression data and a first correlated content datum as a function of the voice datum; and

generating, at a clustering unsupervised machine-learning model, the transcription datum as a function of the voice datum and the correlated dataset.

5. The system of claim 1 , wherein the computing device is further configured to extract a query as a function of the transcription data datum.

6. The system of claim 1 , wherein generating the communication output further comprises:

receiving, at the second machine learning a supervised machine-learning model, a first training set as a function of the voice datum and a query; and

generating, at the second machine learning supervised machine-learning model, the communication output as a function of relating the query to a textual output.

7. The system of claim 1 , wherein receiving the voice datum further comprises storing the voice datum, as a dataset, in a data storage system.

8. The system of claim 7 , wherein the computing device is further configured to train a machine learning process as a function of the voice datum in the data storage system.

9. A method for voice recognition in autonomous flight of an electric aircraft, the method comprising:

receiving, at a computing device, at least a voice datum from a remote device; determining, using a first one or more machine learning model models and by inputting the voice datum, transcription data describing the voice datum an expression datum corresponding to an actionable query from the remote device;

determining a query by comparing the transcription data against a dataset including commands associated with maneuvers;

generating, at the computing device, a communication output as a function of the query by inputting the query into a second machine learning model expression datum;

adjusting, at the computing device, a flight plan as a function of the communication output;

generating response data associated with one or more commands used to adjust the flight plan; and

transmitting the response data to the remote device to control the aircraft via a flight controller.

10. The method of claim 9 , wherein the computing device is further configured to transmit an adjustment notification to an interface device as a function of adjusting the flight plan.

11. The method of claim 10 , wherein the interface device is configured to display the adjustment notification to a user.

12. The method of claim 9 , wherein the computing device is further configured to:

generate a transcription datum wherein the generating the transcription datum comprises a machine learning process configured to generate the transcription datum as a function of the voice datum; and

transmit the transcription data to an interface device.

13. The method of claim 12 , wherein determining generating the transcription data further comprises:

selecting a correlated dataset containing a plurality of data entries wherein each dataset comprises a datum of expression data and at least a first correlated content datum as a function of the voice datum; and

generating, using the first machine learning at a clustering unsupervised machine-learning model, the transcription as a function of the voice datum and the correlated dataset, wherein the first machine learning model comprises a clustering unsupervised machine learning model.

14. The method of claim 12 , further comprising extracting a query as a function of the transcription data, wherein the query is extracted at a language processing module.

15. The method of claim 9 , wherein generating the communication output further comprises:

receiving, at the second machine learning a supervised machine-learning model, a first training set as a function of the voice datum and a query; and

generating, at the second machine learning supervised machine-learning model, the communication output as a function of relating the query to a textual output.

16. The method of claim 9 , wherein receiving the voice datum further comprises storing the voice datum, as a dataset, in a data storage system.

17. The method of claim 16 , wherein the method further comprises training a machine learning process as a function of the voice datum.

Assignments (1)

Continuity (2)

References Cited (56)