Method and system for using artificial intelligence to interact with a user of an exercise device during an exercise session

Patent metadata

Field	Value
Publication number	US-12285654-B2
Application number	US-202318497379-A
Country	US
Kind code	B2
Filing date	Oct 30, 2023
Priority date	May 10, 2019
Publication date	Apr 29, 2025
Grant date	Apr 29, 2025

Abstract

A method is disclosed for using an artificial intelligence engine to interact with a user of an exercise device during an exercise session. The method includes generating, by the artificial intelligence engine, a machine learning model trained to receive data as input, and based on the data, providing an output. While a user performs an exercise using the exercise device, the method includes receiving the data from an input peripheral of a computing device associated with the user. Based on the data being received from the input peripheral, the method includes determining, via the machine learning model, the output to control an aspect of the exercise device.

First claim

What is claimed is:

1. A method implemented by a computing device, the method comprising, at the computing device:
generating, by an artificial intelligence engine executing on the computing device, a machine learning model that is trained to receive data as an input; and
while a user performs an exercise using an exercise device that is communicatively coupled to the computing device:
receiving the data and outputting, by the machine learning model:
first instructions that dynamically adjust physical characteristics of the exercise device to correlate with the data, and
second instructions that dynamically transition a virtual coach to at least one different virtual coach in response to determining, based on the data, that at least one performance threshold of the exercise is not being satisfied by the user.

2. The method of claim 1 , wherein the first instructions cause the exercise device to change at least one operating parameter of a plurality of operating parameters of the exercise device.

3. The method of claim 2 , wherein the plurality of operating parameters includes a range of motion of one or more pedals, a speed of a motor, a revolutions per minute of the motor, a speed of a fan, a temperature of a portion of the exercise device, a haptic setting of a portion of the exercise device, or some combination thereof.

4. The method of claim 1 , wherein the data comprises an electronic recording of a voice of the user received via a microphone associated with the computing device or the exercise device.

5. The method of claim 1 , wherein the data is associated with a difficulty of the exercise the user is currently performing, and the method further comprises:
outputting, by the machine learning model, third instructions that modify an exercise plan

associated with the user.

6. The method of claim 1 , wherein:
the virtual coach comprises a virtual character persona, and
the at least one different virtual coach comprises a second virtual persona that is distinct from the virtual persona.

7. The method of claim 1 , wherein, when the data comprises an indication from the user that the exercise is too difficult, the first instructions cause an overall difficulty of the exercise to be reduced for the user.

8. The method of claim 1 , wherein the data comprises at least one instruction to modify at least one operating parameter of the exercise device, and the data is received via a microphone, a touchscreen, a keyboard, a mouse, a proprioceptive sensor, or some combination thereof.

9. A tangible, non-transitory computer-readable medium storing instructions that, when executed by at least one processor included in a computing device, cause the computing device to execute steps that include:
generating, by an artificial intelligence engine executing on the computing device, a machine learning model that is trained to receive data as an input; and
while a user performs an exercise using an exercise device that is communicatively coupled to the computing device:
receiving the data and outputting, by the machine learning model:
first instructions that dynamically adjust physical characteristics of the exercise device to correlate with the data, and
second instructions that dynamically transition a virtual coach to at least one different virtual coach in response to determining, based on the data, that at least one performance threshold of the exercise is not being satisfied by the user.

10. The tangible, non-transitory computer-readable medium of claim 9 , wherein the first instructions cause the exercise device to change at least one operating parameter of a plurality of operating parameters of the exercise device.

11. The tangible, non-transitory computer-readable medium of claim 10 , wherein the plurality of operating parameters includes a range of motion of one or more pedals, a speed of a motor, a revolutions per minute of the motor, a speed of a fan, a temperature of a portion of the exercise device, a haptic setting of a portion of the exercise device, or some combination thereof.

12. The tangible, non-transitory computer-readable medium of claim 9 , wherein the data comprises an electronic recording of a voice of the user received via a microphone associated with the computing device or the exercise device.

13. The tangible, non-transitory computer-readable medium of claim 9 , wherein the data is associated with a difficulty of the exercise the user is currently performing, and the steps further include:
outputting, by the machine learning model, third instructions that modify an exercise plan associated with the user.

14. The tangible, non-transitory computer-readable medium of claim 9 , wherein the virtual coach comprises a virtual character.

15. The tangible, non-transitory computer-readable medium of claim 9 , wherein, when the data comprises an indication from the user that the exercise is too difficult, the first instructions cause an overall difficulty of the exercise to be reduced for the user.

16. The tangible, non-transitory computer-readable medium of claim 9 , wherein the data comprises at least one instruction to modify at least one operating parameter of the exercise device, and the data is received via a microphone, a touchscreen, a keyboard, a mouse, a proprioceptive sensor, or some combination thereof.

17. A computing device, comprising:
at least one processor; and
at least one memory storing instructions that, when executed by the at least one processor, cause the computing device to carry out steps that include:
generating, by an artificial intelligence engine executing on the computing device, a machine learning model that is trained to receive data as an input; and
while a user performs an exercise using an exercise device that is communicatively coupled to the computing device:
receiving the data and outputting, by the machine learning model:
first instructions that dynamically adjust physical characteristics of the exercise device to correlate with the data, and
second instructions that dynamically transition a virtual coach to at least one different virtual coach in response to determining, based on the data, that at least one performance threshold of the exercise is not being satisfied by the user.

18. The computing device of claim 17 , wherein the first instructions cause the exercise device to change at least one operating parameter of a plurality of operating parameters of the exercise device.

19. The computing device of claim 18 , wherein the plurality of operating parameters includes a range of motion of one or more pedals, a speed of a motor, a revolutions per minute of the motor, a speed of a fan, a temperature of a portion of the exercise device, a haptic setting of a portion of the exercise device, or some combination thereof.

20. The computing device of claim 17 , wherein the data comprises an electronic recording of a voice of the user received via a microphone associated with the computing device or the exercise device.

Assignees

• Rehab2Fit Tech Inc
• Rom Tech Inc

Inventors

• Bissonnette Michael
• Berga Luis
• Mason Steven
• Powers Philip
• Steidl James D

Classifications

• A63B2230/50

  temperature · CPC title

• A63B2230/42

  rate · CPC title

• A63B2230/207

  P-O2, i.e. partial O2 value · CPC title

• A63B2230/30

  blood pressure (A63B2230/04 takes precedence) · CPC title

• A63B2225/20

  with means for remote communication, e.g. internet or the like · CPC title