Granted Patent B1

US 12,494,295 · App. 18/957,821 · Granted Dec 9, 2025

Inventors: Blake Browder (Dallas, TX); Joy Figarsky (Little Rock, AR)

Assignee: Behavioral Health Operations, LLC

G16H70/20G06T13/40G09B23/28G16H40/20

Abstract

Claims (73)

1 . An apparatus for an interactive course user interface including a digital avatar, the apparatus comprising:

at least a processor; and

a memory communicatively connected to the at least a processor, wherein the memory contains instructions configuring the at least a processor to:

using a display, configure a user interface to display instructional content to a user;

using the user interface, receive a prompt from the user;

using a large language model (LLM), generate a natural language response based on the prompt and the instructional content;

determine a digital avatar pose demonstration datum including a demonstration of a physical technique for handling a patient as a function of the natural language response and the instructional content, wherein the digital avatar pose demonstration datum comprises a plurality of vertices of the digital avatar and key frame data, wherein the key frame data comprises vertex position data, and wherein determining the digital avatar pose demonstration datum comprises:

appending the instructional content for the digital avatar pose demonstration datum using the LLM; and

generating a pose description of the digital avatar pose demonstration datum using the LLM, wherein the pose description comprises an explanation of the pose's intended purpose; and

using the display, update the user interface, wherein updating the user interface comprises:

generating a digital avatar display element configured to display the digital avatar pose demonstration datum to the user; and

communicating the natural language response to the user.

2 . The apparatus of claim 1 , wherein:

the apparatus further comprises a camera; and

the memory contains instructions configuring the at least a processor to:

using the camera, capture image data of the user;

using a machine vision system, generate a prompt supplement as a function of the image data; and

generate the natural language response, comprising:

generating a combined prompt based on the prompt, the instructional content, and the prompt supplement; and

using the LLM, generating the natural language response based on the combined prompt.

3 . The apparatus of claim 2 , wherein updating the user interface comprises:

determining an overlaid digital avatar pose demonstration datum as a function of the digital avatar pose demonstration datum and the image data; and

displaying the overlaid digital avatar pose demonstration datum on top of the digital avatar pose demonstration datum.

4 . The apparatus of claim 1 , wherein determining the digital avatar pose demonstration datum comprises:

generating pose demonstration training data, wherein the pose demonstration training data comprises exemplary natural language responses correlated to exemplary digital avatar pose demonstration datums;

training a pose demonstration machine-learning model using the pose demonstration training data; and

identifying the digital avatar pose demonstration datum as a function of the natural language response using the trained pose demonstration machine-learning model.

5 . The apparatus of claim 4 , wherein the pose demonstration machine-learning model comprises a large behavior model.

6 . The apparatus of claim 1 , wherein updating the user interface comprises:

receiving a viewing perspective of a user input;

generating the digital avatar pose demonstration datum as a function of the viewing perspective; and

updating the user interface in response to the digital avatar pose demonstration datum.

7 . The apparatus of claim 1 , wherein determining the digital avatar pose demonstration datum comprises:

receiving a pose selection request of a user input; and

generating the digital avatar pose demonstration datum as a function of the pose selection request.

8 . The apparatus of claim 1 , wherein the user interface comprises an instruction display element, wherein the instruction display element is configured to display the natural language response to the user.

9 . The apparatus of claim 8 , wherein generating the digital avatar display element comprises:

receiving a user input for the instruction display element; and

updating the digital avatar display element as a function of the user input.

10 . A method for an interactive course user interface including a digital avatar, the method comprising:

configuring, using at least a processor, a user interface to display instructional content to a user using a display;

receiving, using the at least a processor, a prompt from the user using the user interface;

generating, using the at least a processor, a natural language response based on the prompt and the instructional content using a large language model (LLM);

determining, using the at least a processor, a digital avatar pose demonstration datum including a demonstration of a physical technique for handling a patient as a function of the natural language response and the instructional content, wherein the digital avatar pose demonstration datum comprises a plurality of vertices of the digital avatar and key frame data, wherein the key frame data comprises vertex position data, and wherein determining the digital avatar pose demonstration datum comprises:

appending the instructional content for the digital avatar pose demonstration datum using the LLM; and

generating a pose description of the digital avatar pose demonstration datum using the LLM, wherein the pose description comprises an explanation of the pose's intended purpose; and

updating, using the at least a processor, the user interface using the display, wherein updating the user interface comprises:

generating a digital avatar display element configured to display the digital avatar pose demonstration datum to the user; and

communicating the natural language response to the user.

11 . The method of claim 10 , generating the natural language response comprises:

capturing image data of the user using a camera;

generating a prompt supplement as a function of the image data using a machine vision system;

generating a combined prompt based on the prompt, the instructional content, and the prompt supplement; and

generating the natural language response based on the combined prompt using the LLM.

12 . The method of claim 11 , wherein updating the user interface comprises:

determining an overlaid digital avatar pose demonstration datum as a function of the digital avatar pose demonstration datum and the image data; and

displaying the overlaid digital avatar pose demonstration datum on top of the digital avatar pose demonstration datum.

13 . The method of claim 10 , wherein determining the digital avatar pose demonstration datum comprises:

generating pose demonstration training data, wherein the pose demonstration training data comprises exemplary natural language responses correlated to exemplary digital avatar pose demonstration datums;

training a pose demonstration machine-learning model using the pose demonstration training data; and

identifying the digital avatar pose demonstration datum as a function of the natural language response using the trained pose demonstration machine-learning model.

14 . The method of claim 13 , wherein the pose demonstration machine-learning model comprises a large behavior model.

15 . The method of claim 10 , wherein updating the user interface comprises:

receiving a viewing perspective of a user input;

generating the digital avatar pose demonstration datum as a function of the viewing perspective; and

updating the user interface in response to the digital avatar pose demonstration datum.

16 . The method of claim 10 , wherein determining the digital avatar pose demonstration datum comprises:

receiving a pose selection request of a user input; and

generating the digital avatar pose demonstration datum as a function of the pose selection request.

17 . The method of claim 10 , wherein the user interface comprises an instruction display element, wherein the instruction display element is configured to display the natural language response to the user.

18 . The method of claim 17 , wherein generating the digital avatar display element comprises:

receiving a user input for the instruction display element; and

updating the digital avatar display element as a function of the user input.

Assignments (3)

References Cited (16)