Granted Patent B1

US 12,293,060 · App. 18/897,356 · Granted May 6, 2025

Inventor: Abhijeet Dwivedi (Burlingame, CA)

Assignee: Interactive Aristotle, Inc.

G06F3/0482

Abstract

Claims (80)

1. A system comprising at least one processor configured to perform the operations of:

displaying, via a user interface, a list comprising available control parameters that are selectable for use to control an input to a trained machine learning model;

receiving, via the user interface, a selection of one or more control parameters from the list for control of the input to the trained machine learning model;

distributing configuration information of the selected one or more control parameters to a client device;

receiving an input via the client device, the client device having an instance of the trained machine learning model;

determining whether the one or more control parameters applies to the received input and performing the operations of:

if any of the one or more control parameters applies to the received input then:

displaying, via the client device, a predefined control parameter response; or

 if none of the control parameters apply to the received input then:

providing as an input prompt, the received input, to the trained machine learning model; and

displaying, via the client device, an output generated by the trained machine learning model based in the input prompt.

2. The system of claim 1 , wherein the control parameters include a predetermined listing of questions, wherein the user interface is configured to enable or disable the selection of a particular question listed via the user interface.

3. The system of claim 1 , further comprising the operations of:

training the machine learning model with one or more data sets configured for a predetermined user age range, the machine learning model comprising an LLM; and

distributing the trained machine learning model to a client device.

4. The system of claim 1 , further comprising the operations of:

receiving, via a user interface, an input for an age or an age range of a primary user of the client device; and

selecting, based on the input age or age range, the trained machine learning model from a group of trained machine learning models, where each of the models are associated with an age range.

5. The system of claim 4 , further comprising the operations of:

determining an updated age or updated age range of the primary user; and

selecting, based on the updated age or updated age range, the another trained machine learning model from a group of trained machine learning models, where each of the models are associated with an age range; and

distributing the another trained machine learning model to a client device.

6. The system of claim 1 , further comprising the operations of:

receiving, via a user interface, a textual input describing the predefined control parameter response for each of the selected one or more control parameters.

7. The system of claim 1 , further comprising the operations of:

receiving an input via the user interface to add one or more additional control parameters.

8. The system of claim 1 , wherein the determining whether the one or more control parameter applies comprises:

determining whether one or more words of the received input match one or more words of the one or more control parameters.

9. The system of claim 1 , wherein the determining whether the one or more control parameters applies comprises:

determining a similarity score of the received input to one or more words of the one or more control parameters; and

determining that a control parameter applies if the similarity score is above a predefined confidence level.

10. The system of claim 1 , further comprising the operations of:

receiving, from the client device, one or more word graphs associated with the input received by the client; and

providing for display a user interface depicting the one or more word graphs.

11. The system of claim 10 , further comprising the operations of:

determining whether to update the machine learning model with information associated with the context of the one or more word graphs;

receiving a confirmation to update the machine learning model;

obtaining content or data associated with the context;

updating the machine learning model; and

distributing the machine learning model with the obtained content or data.

12. A computer-implemented method comprising:

displaying, via a user interface, a list comprising available control parameters that are selectable for use to control an input to a trained machine learning model;

receiving, via the user interface, a selection of one or more control parameters from the list for control of the input to the trained machine learning model;

distributing configuration information of the selected one or more control parameters to a client device;

receiving an input via the client device, the client device having an instance of the trained machine learning model;

determining whether the one or more control parameters applies to the received input and performing the operations of:

if any of the one or more control parameters applies to the received input then:

displaying, via the client device, a predefined control parameter response; or

 if none of the control parameters apply to the received input then:

providing as an input prompt, the received input, to the trained machine learning model; and

displaying, via the client device, an output generated by the trained machine learning model based in the input prompt.

13. The method of claim 12 , wherein the control parameters include a predetermined listing of questions, wherein the user interface is configured to enable or disable the selection of a particular question listed via the user interface.

14. The method of claim 12 , further comprising the operations of:

training the machine learning model with one or more data sets configured for a predetermined user age range, the machine learning model comprising an LLM; and

distributing the trained machine learning model to a client device.

15. The method of claim 12 , further comprising the operations of:

receiving, via a user interface, an input for an age or an age range of a primary user of the client device; and

selecting, based on the input age or age range, the trained machine learning model from a group of trained machine learning models, where each of the models are associated with an age range.

16. The method of claim 15 , further comprising the operations of:

determining an updated age or updated age range of the primary user; and

selecting, based on the updated age or updated age range, the another trained machine learning model from a group of trained machine learning models, where each of the models are associated with an age range; and

distributing the another trained machine learning model to a client device.

17. The method of claim 12 , further comprising the operations of:

receiving, via a user interface, a textual input describing the predefined control parameter response for each of the selected one or more control parameters.

18. The method of claim 12 , further comprising the operations of:

receiving an input via the user interface to add one or more additional control parameters.

19. The method of claim 12 , wherein the determining whether the one or more control parameter applies comprises:

determining whether one or more words of the received input match one or more words of the one or more control parameters.

20. The method of claim 12 , wherein the determining whether the one or more control parameters applies comprises:

determining a similarity score of the received input to one or more words of the one or more control parameters; and

determining that a control parameter applies if the similarity score is above a predefined confidence level.

21. The method of claim 12 , further comprising the operations of:

receiving, from the client device, one or more word graphs associated with the input received by the client; and

providing for display a user interface depicting the one or more word graphs.

22. The system of claim 21 , further comprising the operations of:

determining whether to update the machine learning model with information associated with the context of the one or more word graphs;

receiving a confirmation to update the machine learning model;

obtaining content or data associated with the context;

updating the machine learning model; and

distributing the machine learning model with the obtained content or data.

Assignments (1)

Continuity (1)

References Cited (21)

Cited By (1)

US 12,688,280