IP Library Granted Patent US 12,573,313
Granted Patent B2
US 12,573,313 · App. 18/122,340 · Granted Mar 10, 2026

Apparatus and method for generating an educational action datum using machine-learning

Inventor: Michael Everest (Los Angeles, CA)
G09B7/00H04L67/306H04L67/535
View Patent ↗
Loading inventors, assignments & file history…
Monitor This Case
Get email alerts when status or documents change.
Order Certified Copies
Most orders are placed with the USPTO same day — all within 24 business hours.
Order via The Patent Place →
Pre-filled with this patent's details
Quick Facts
Patent No.
US 12,573,313
App. No.
18/122,340
Granted
Mar 10, 2026
Kind
B2
Abstract

An apparatus and method for generating an educational action datum using machine-learning is described. The apparatus includes at least a processor and a memory containing instructions configuring the at least a processor to receive user data pertaining to a user, generate an educational obstacle machine-learning model using an educational machine-learning module, determine an educational obstacle datum as a function of the user data using the educational obstacle machine-learning model, and generate an educational action datum for the user as a function of the educational obstacle datum, wherein the educational action datum comprises at least an educational action datum waypoint.

Claims (58)

1 . An apparatus for generating an educational action datum using machine-learning, 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:

receive user data pertaining to a user, and a Non-Fungible Token (NFT) derived from a web crawler, wherein the web crawler is generated by the at least a processor and scrapes the user data from a plurality of NFTs and is configured to detect at least one data pattern comprising an education strategy correlated to the user data;

generate a virtual avatar using a virtual avatar model as a function of at least a user data item, wherein the virtual avatar comprises at least a personalized characteristic of the user, wherein generating the virtual avatar comprises:

training the virtual avatar model using virtual avatar training data, wherein the virtual avatar training data comprises a plurality of pre-existing virtual avatars from a virtual avatar database;

extracting the at least a user data item from the user data; and

generating the virtual avatar as a function of the entity data;

generate an educational obstacle machine-learning model using an educational machine-learning module;

determine an educational obstacle datum as a function of the user data using the educational obstacle machine-learning model, wherein the educational obstacle machine-learning model is trained using educational obstacle training data, wherein the educational obstacle training data comprises a plurality of user data sets correlated to a plurality of educational obstacle data, wherein training the educational obstacle machine-learning model comprises:

iteratively updating the training data as a function of an adjusted input and a desired output of the educational obstacle machine-learning model;

retraining the educational obstacle machine-learning model using the updated training data; and

determining the educational obstacle datum using the trained educational obstacle machine-learning model;

generate an educational action datum for the user as a function of the educational obstacle datum, wherein the educational action datum comprises at least an educational action datum waypoint; and

instantiate, in a user interface, the virtual avatar, wherein the virtual avatar comprises at least a base image and a plurality of animations of the base image, wherein the virtual avatar is configured to:

receive the educational action datum, wherein the educational action datum is communicated to the virtual avatar using blockchain technology; and

display an animation of the plurality of animations as a function of the educational action datum.

2 . The apparatus of claim 1 , wherein the user data comprises virtual activity data and actual activity data pertaining to the user.

3 . The apparatus of claim 2 , wherein receiving the user data comprises:

receiving the actual activity data from a user profile pertaining to the user.

4 . The apparatus of claim 1 , wherein the educational obstacle datum comprises at least an educational obstacle category associated with the educational obstacle datum.

5 . The apparatus of claim 4 , wherein determining the educational obstacle datum comprises:

generating an educational obstacle classifier using the educational machine-learning module;

classifying the user data into the at least an educational obstacle category using the educational obstacle classifier; and

determining the educational obstacle datum as a function of the at least an educational obstacle category.

6 . The apparatus of claim 1 , wherein generating the educational action datum comprises:

training an educational action machine-learning model with educational action training data using the educational machine-learning module, wherein the educational action training data comprises a plurality of educational obstacle data correlated to a plurality of educational action data; and

generating the education action datum as a function of the trained educational action machine-learning model.

7 . The apparatus of claim 1 , wherein the at least an educational action datum waypoint comprises a user-oriented assignment.

8 . The apparatus of claim 1 , wherein the educational action datum comprises at least a waypoint response associated with the at least an educational action datum waypoint.

9 . A method for generating an educational action datum using machine-learning, the method comprising:

receiving, by at least a processor, user data pertaining to a user and a Non-Fungible Token (NFT) derived from a web crawler, wherein the web crawler is generated by the at least a processor and scrapes the user data from a plurality of NFTs and is configured to detect at least one data pattern comprising an education strategy correlated to the user data;

generating a virtual avatar using a virtual avatar model as a function of at least a user data item, wherein the virtual avatar comprises at least a personalized characteristic of the user, wherein generating the virtual avatar comprises:

training the virtual avatar model using virtual avatar training data, wherein the virtual avatar training data comprises a plurality of pre-existing virtual avatars from a virtual avatar database;

extracting the at least a user data item from the user data; and

generating the virtual avatar as a function of the entity data;

generating, by the at least a processor, an educational obstacle machine-learning model using an educational machine-learning module;

determining, by the at least a processor, an educational obstacle datum as a function of the user data using the educational obstacle machine-learning model, wherein the educational obstacle machine-learning model is trained using educational obstacle training data, wherein the educational obstacle training data comprises a plurality of user data sets correlated to a plurality of educational obstacle data, wherein training the educational obstacle machine-learning model comprises:

iteratively updating the training data as a function of an adjusted input and a desired output of the educational obstacle machine-learning model;

retraining the educational obstacle machine-learning model using the updated training data; and

determining the educational obstacle datum using the trained educational obstacle machine-learning model;

generating, by the at least a processor, an educational action datum for the user as a function of the educational obstacle datum, wherein the educational action datum comprises at least an educational action datum waypoint; and

instantiating, in a user interface, the virtual avatar, wherein the virtual avatar comprises at least a base image and a plurality of animations of the base image, wherein the virtual avatar is configured to:

receive the educational action datum, wherein the educational action datum is communicated to the virtual avatar using blockchain technology; and

display an animation of the plurality of animations as a function of the educational action datum.

10 . The method of claim 9 , wherein the user data comprises virtual activity data and actual activity data pertaining to the user.

11 . The method of claim 10 , wherein receiving the user data comprises:

receiving the actual activity data from a user profile pertaining to the user.

12 . The method of claim 9 , wherein the educational obstacle datum comprises at least an educational obstacle category associated with the educational obstacle datum.

13 . The method of claim 12 , wherein determining the educational obstacle datum comprises:

generating an educational obstacle classifier using the educational machine-learning module;

classifying the user data into the at least an educational obstacle category using the educational obstacle classifier; and

determining the educational obstacle datum as a function of the at least an educational obstacle category.

14 . The method of claim 9 , wherein generating the educational action datum comprises:

training an educational action machine-learning model with educational action training data using the educational machine-learning module, wherein the educational action training data comprises a plurality of educational obstacle data correlated to a plurality of educational action data; and

generating the education action datum as a function of the trained educational action machine-learning model.

15 . The method of claim 9 , wherein the at least an educational action datum waypoint comprises a user-oriented assignment.

16 . The method of claim 9 , wherein the educational action datum comprises at least a waypoint response associated with the at least an educational action datum waypoint.

Continuity (1)
Related Publication 20240312358A1 · Sep 19, 2024
References Cited (23)
US 11189193B2 · Chen · 2021 [cited by applicant]
US 11533272B1 · Sastry · 2022 [cited by examiner]
US 11562329B1 · Stewart · 2023 [cited by examiner]
US 11563591B1 · Jain · 2023 [cited by examiner]
US 20020055089A1 · Scheirer · 2002 [cited by applicant]
US 20130109002A1 · Howard · 2013 [cited by examiner]
US 20140024009A1 · Nealon · 2014 [cited by examiner]
US 20150046190A1 · Strongwater · 2015 [cited by examiner]
US 20150325133A1 · Gaglani · 2015 [cited by examiner]
US 20170084184A1 · Yadav · 2017 [cited by examiner]
US 20170293845A1 · McAllister · 2017 [cited by examiner]
US 20180005116A1 · Pickover · 2018 [cited by examiner]
US 20180350144A1 · Rathod · 2018 [cited by examiner]
US 20190066525A1 · Palau et al. · 2019 [cited by applicant]
US 20190259290A1 · Lynch · 2019 [cited by applicant]
US 20190335006A1 · George · 2019 [cited by examiner]
US 20200020038A1 · Haile · 2020 [cited by examiner]
US 20200302296A1 · Miller · 2020 [cited by examiner]
US 20210365526A1 · Sachson · 2021 [cited by examiner]
US 20220172108A1 · P K · 2022 [cited by examiner]
US 20220384027A1 · Kaleal, III · 2022 [cited by examiner]
US 20230050034A1 · Ben-Elazar · 2023 [cited by examiner]
US 20230419434A1 · Keen · 2023 [cited by examiner]