Granted Patent B1

US 12,620,322 · App. 19/044,241 · Granted May 5, 2026

Inventor: Michael Everest (Los Angeles, CA)

Assignee: edYou Technologies Inc.

G09B7/04G06F3/0481G06F40/35G06F40/40G06T7/13G06F2203/04803G06T2200/24G06T2207/20081

Abstract

Claims (77)

1 . An apparatus for generating a learning environment comprising an interactive, multi-window graphical user interface, wherein the apparatus comprises:

at least a computing device, wherein the computing device comprises:

a memory; and

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

generate a graphical user interface, wherein the graphical user interface comprises:

a first window comprising an interactive workspace, wherein the interactive workspace is configured to receive user input comprising one or more of textual data and image data, wherein the first window is configured to provide a drawing input portion, wherein the drawing input portion is configured to receive a drawing input comprising at least user-generated visual elements from a user; and

a second window communicatively connected to the first window, wherein the second window comprises an output element that is configured to interface with a machine learning model;

display the graphical user interface using a downstream device;

receive, through the graphical user interface of the downstream device, a first query associated with user input, wherein the first query comprises multimodal data;

generate, using the machine learning model, return data as a function of processed multimodal data which comprises analyzing user's complexity of text input to determine user's educational level;

modify, using a natural language processor, the return data as a function of an attribute of the processed multimodal data to generate a user specific output; and

display, using the second window of the graphical user interface, the user specific output, wherein displaying the user specific output comprises providing at least a tailored learning support program based on the determined user's educational level and a hint, wherein providing the at least a hint comprises highlighting an error made by the user.

2 . The apparatus of claim 1 , wherein the multimodal data comprises at least an event corresponding to an event handler, wherein the at least an event comprising one or more of:

uploading the image data of the multimodal data; and

submitting the textual data of the multimodal data.

3 . The apparatus of claim 1 , further comprising an application programming interface compatible with the interactive workspace, wherein the application programming interface is configured to:

receive and transmit the multimodal data between the downstream device and the apparatus; and

provide dynamic updates of the user specific output within the interactive workspace.

4 . The apparatus of claim 1 , wherein the machine learning model comprises a large language model, wherein the large language model configured to:

receive a second query;

adjust the user specific output as a function of the second query; and

generate an alternative user specific output.

5 . The apparatus of claim 1 , wherein the first window is configured to provide a text input field, wherein the text input field is configured to receive the textual data from a user.

6 . The apparatus of claim 5 , wherein the second window is arranged adjacent to the first window, wherein the second window is configured to:

display, the user specific output; and

dynamically provide updates to the user specific output based on real-time user interactions.

7 . The apparatus of claim 1 , further comprising a chatbot, wherein the chatbot is configured to:

receive a plurality of user queries;

respond to the plurality of user queries, wherein responding to the plurality of user queries comprises:

retrieving a plurality of user specific data of the user input;

analyzing sentiment data of the plurality of user specific data; and

generating, using the natural language processor, custom responses in the second window as a function of the user specific data and the sentiment data.

8 . The apparatus of claim 1 , wherein the machine learning model is iteratively trained using machine learning model training data, wherein the machine learning model training data comprises historical return data corresponding to historical processed multimodal data.

9 . The apparatus of claim 1 , further configured to generate, using an image processor, the processed multimodal data by identifying, using edge detection techniques, features of the multimodal data.

10 . The apparatus of claim 1 , wherein the processor is further configured to:

receive user feedback; and

refine the machine learning model by:

identifying patterns in between a target output and the user specific output;

calculating a score for the user specific output based on the user feedback and the patterns; and

updating a parameter of the machine learning model as a function of the score.

11 . A method for generating a learning environment comprising an interactive, multi-window graphical user interface, wherein the method comprises:

generating a graphical user interface using at least a processor, wherein the graphical user interface comprises:

a first window comprising an interactive workspace, wherein the interactive workspace is configured to receive user input comprising one or more of textual data and image data, wherein the first window is configured to provide a drawing input portion, wherein the drawing input portion is configured to receive a drawing input comprising at least user-generated visual elements from a user; and

a second window communicatively connected to the first window, wherein the second window comprises an output element that is configured to interface with a machine learning model;

displaying the graphical user interface using a downstream device;

receiving, through the graphical user interface of the downstream device, a first query associated with user input, wherein the first query comprises multimodal data;

generating, using the machine learning model, return data as a function of processed multimodal data which comprises analyzing user's complexity of text input to determine user's educational level;

modifying, using a natural language processor, the return data as a function of an attribute of the processed multimodal data to generate a user specific output; and

displaying, using the second window of the graphical user interface, the user specific output, wherein displaying the user specific output comprises providing at least a tailored learning support program based on the determined user's educational level and a hint, wherein providing the at least a hint comprises highlighting an error made by the user.

12 . The method of claim 11 , wherein the multimodal data comprises at least an event corresponding to an event handler, wherein the at least an event comprising one or more of:

uploading the image data of the multimodal data; and

submitting the textual data of the multimodal data.

13 . The method of claim 11 , further comprising an application programming interface compatible with the interactive workspace, wherein the application programming interface is configured to:

receive and transmit the multimodal data to the downstream device; and

provide dynamic updates of the user specific output within the interactive workspace.

14 . The method of claim 11 , wherein the machine learning model comprises a large language model, wherein the large language model configured to:

receive a second query;

adjust the user specific output as a function of the second query; and

generate an alternative user specific output.

15 . The method of claim 11 , wherein the first window is configured to provide a text input field, wherein the text input field is configured to receive the textual data from a user.

16 . The method of claim 15 , wherein the second window is arranged adjacent to the first window, wherein the second window is configured to:

display, the user specific output; and

dynamically provide updates to the user specific output based on real-time user interactions.

17 . The method of claim 11 , further comprising a chatbot, wherein the chatbot is configured to:

receive a plurality of user queries;

respond to the plurality of user queries, wherein responding to the plurality of queries comprises:

retrieving a plurality of user specific data of the user input;

analyzing sentiment data of the plurality of user specific data; and

generating, using the natural language processor, custom responses in the second window as a function of the user specific data and the sentiment data.

18 . The method of claim 11 , wherein the machine learning model is iteratively trained using machine learning model training data, wherein the machine learning model training data comprises historical return data corresponding to historical processed multimodal data.

19 . The method of claim 11 , further comprising generating, using an image processor, the processed multimodal data by identifying, using edge detection techniques, features of the multimodal data.

20 . The method of claim 11 , further comprising:

receiving, using the at least a processor, user feedback; and

refining, using the at least a processor, the machine learning model by:

identifying patterns in between a target output and the user specific output;

calculating a score for the user specific output based on the user feedback and the patterns; and

updating a parameter of the machine learning model as a function of the score.

Assignments (1)

References Cited (19)