Granted Patent B2

US 12,609,044 · App. 17/861,051 · Granted Apr 21, 2026

Inventors: Anna T. Wolfe (San Francisco, CA); Alexandra Hernandez (San Diego, CA); Anthony M. Accardo (Los Angeles, CA); Shelly Henling (Pasadena, CA)

Assignee: Disney Enterprises, Inc.

G09B19/00G06N20/00G09B5/06G09B5/065

Abstract

Claims (53)

1 . A system comprising:

a computing platform including processing hardware and a system memory;

a software code and a machine learning (ML) model including a plurality of node weights stored in the system memory, the software code providing a user interface (UI);

the processing hardware configured to execute the software code to:

identify a user of the system;

obtain a user profile of the user;

obtain, from respective application programming interfaces (APIs) of one or more applications utilized by the user, activity data relating to use of the one or more applications by the user;

modify, using the user profile and the activity data, one or more of the plurality of node weights of the ML model to provide a tuned ML model configured to implement at least one of a content-based filtering strategy or a collaborative filtering strategy;

infer, using the tuned ML model, at least one action for advancing a development of the user;

output to the user, using the UI, a recommendation identifying the at least one action;

obtain, from the respective APIs of the one or more applications utilized by the user, additional activity data relating to further use of the one or more applications by the user; and

further modify, using the additional activity data in a closed-loop feedback process in which user behavior drives ongoing modification of model parameters, the tuned ML model to provide a retuned ML model.

2 . The system of claim 1 , wherein the at least one action comprises a plurality of actions for advancing the development of the user, and wherein the recommendation comprises a prioritized list of the plurality of actions.

3 . The system of claim 1 , wherein the processing hardware is further configured to execute the software code to:

receive, using the UI, a user development selection input from or on behalf of the user;

wherein modifying the one or more of the plurality of node weights of the ML model further uses the user development selection input.

4 . The system of claim 1 , wherein the processing hardware is configured to execute the software code to:

identify another user of the system, the another user having another user profile including at least one feature in common with the user profile of the user;

wherein modifying the one or more of the plurality of node weights of the ML further uses the another user profile.

5 . The system of claim 1 , wherein the at least one action for advancing the development of the user comprises initiating a communication with another user of the system.

6 . The system of claim 1 , wherein the at least one action for advancing the development of the user comprises joining an existing group including a plurality of other users of the system.

7 . The system of claim 1 , wherein the at least one action for advancing the development of the user comprises organizing or attending an event including at least one other user of the system.

8 . The system of claim 1 , wherein the at least one action for advancing the development of the user comprises engaging in an educational activity as one of a student or a teacher.

9 . The system of claim 1 , wherein processing hardware is further configured to execute the software code to:

infer, using the retuned ML model, another action for further advancing the development of the user.

10 . The system of claim 9 , wherein processing hardware is further configured to execute the software code to:

determine whether the user has completed the at least one action; and

prompt, using the UI, the user to perform the another action.

11 . A method for use by a system including a computing platform having processing hardware and a system memory storing software code and a machine learning (ML) model including a plurality of node weights, the software code providing a user interface (UI), the method comprising:

identifying, by the software code executed by the processing hardware, a user of the system;

obtaining, by the software code executed by the processing hardware a user profile of the user;

obtaining, by the software code executed by the processing hardware, from respective application programming interfaces (APIs) of one or more applications utilized by the user, activity data relating to use of the one or more applications by the user;

modifying, by the software code executed by the processing hardware and using the user profile and the activity data, one or more of the plurality of node weights of the ML model to provide a tuned ML model configured to implement at least one of a content-based filtering strategy or a collaborative filtering strategy;

inferring, by the software code executed by the processing hardware and using the tuned ML model, at least one action for advancing a development of the user;

outputting to the user, by the software code executed by the processing hardware and using the UI, a recommendation identifying the at least one action;

obtaining, by the software code executed by the processing hardware, from the respective APIs of the one or more applications utilized by the user, additional activity data relating to further use of the one or more applications by the user; and

further modifying, by the software code executed by the processing hardware and using the additional activity data in a closed-loop feedback process in which user behavior drives ongoing modification of model parameters, the tuned ML model to provide a retuned ML model.

12 . The method of claim 11 , wherein the at least one action comprises a plurality of actions for advancing the development of the user, and wherein the recommendation comprises a prioritized list of the plurality of actions.

13 . The method of claim 11 , further comprising:

receiving, by the software code executed by the processing hardware and using the UI, a user development selection input from or on behalf of the user;

wherein modifying the one or more of the plurality of node weights of the ML model further uses the user development selection input.

14 . The method of claim 11 , further comprising:

identifying, by the software code executed by the processing hardware, another user of the system, the another user having another user profile including at least one feature in common with the user profile of the user;

wherein modifying the one or more of the plurality of node weights of the ML model further uses the another user profile.

15 . The method of claim 11 , wherein the at least one action for advancing the development of the user comprises initiating a communication with another user of the system.

16 . The method of claim 11 , wherein the at least one action for advancing the development of the user comprises joining an existing group including a plurality of other users of the system.

17 . The method of claim 11 , wherein the at least one action for advancing the development of the user comprises organizing or attending an event including at least one other user of the system.

18 . The method of claim 11 , wherein the at least one action for advancing the development of the user comprises engaging in an educational activity as one of a student or a teacher.

19 . The method of claim 11 , further comprising:

inferring, by the software code executed by the processing hardware and using the retuned ML model, at least another action for further advancing the development of the user.

20 . The method of claim 19 , further comprising:

determining, by the software code executed by the processing hardware, whether the user has completed the at least one action; and

prompting, by the software code executed by the processing hardware and using the UI, the user to perform the another action.

Assignments (1)

Continuity (1)

References Cited (14)