Granted Patent B2

US 12,468,997 · App. 18/110,469 · Granted Nov 11, 2025

Inventors: Tom Wheelwright (Tempe, AZ); Ryan Husk (Tempe, AZ)

G06Q10/0637G06F18/2431

Abstract

Claims (61)

1 . A system for generating an action strategy, wherein the system comprises:

at least a processor; and

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

receive composition data from a user, wherein the composition data comprises:

at least a plurality of pecuniary goals; and

at least a non-goal group comprising data not related to the at least a plurality of pecuniary goals;

train a group classifier using group training data, and wherein training the group classifier further comprises:

correlating the at least a plurality of pecuniary goals of the composition data one or more composition groups;

updating the group training data with a previous correlation of the at least a plurality of pecuniary goals of the composition data to the one or more composition groups; and

retraining the group classifier as a function of the updated group training data, wherein the group classifier is further configured to classify composition data into the one or more composition groups as a function of the at least a plurality of pecuniary goals;

classify the composition data to one or more composition groups using the group classifier;

receive input on the one or more composition groups from an advisor comprising a professional related to a specific composition group;

provide a composition course as a function of the one or more composition groups, wherein providing the composition course comprises training a course machine-learning model on a course training dataset comprising a correlation between at least one example composition group and at least one example composition course, wherein the course machine-learning model comprises at least an artificial neural network comprising an input layer of nodes, one or more intermediate layers of nodes, and an output layer of nodes adjusting one or more connections and one or more weights between nodes in adjacent layers of the course machine-learning model;

receiving additional course training data from the advisor; and

retraining the course machine-learning model as a function of the course training dataset;

determine an action item as a function of the one or more composition groups wherein determining an action item further comprises generating at least an advisor action related to a review with the advisor; and

generate an action strategy comprising at least a tax strategy as a function of the action item comprising a plurality of steps for the action strategy as a function of a focus level, wherein the focus level comprises a user goal, of the one or more composition groups.

2 . The system of claim 1 , wherein the composition data comprises document data.

3 . The system of claim 1 , wherein the composition course comprises an assessment.

4 . The system of claim 1 , wherein determining the action item comprises receiving an item response from the user.

5 . The system of claim 4 , wherein the item response comprises a course response.

6 . The system of claim 5 , wherein determining the action item comprises determining an item status of the action item as a function of the item response using a status machine-learning model.

7 . The system of claim 6 , wherein the item status comprises a course status, wherein the course status comprises a completion status of the composition course.

8 . The system of claim 7 , wherein determining the action item further comprises:

generating, using an action machine-learning model, a first action item, wherein the action machine-learning model is configured to correlate action training data to the action item;

receiving, using the at least a processor, the course response from the user for the first action item;

determining, using the status machine-learning model, the completion status of the composition course; and

identifying, using the action machine-learning model, a second action item as a function of the completion status of the composition course.

9 . The system of claim 1 , wherein the at least a processor is further configured to generate a report using a graph machine-learning model, wherein the report comprises a graphically represented item of the composition data and generating the report using the graph machine-learning model further comprises:

receiving a graph training data, wherein the graph training data comprises the composition data; and

creating the report as a function of the graph training data, where in the report comprises the graphically represented item of the composition data.

10 . A method for generating an action strategy, wherein the method comprises:

receiving, using at least a processor, composition data from a user, wherein the composition data comprises:

at least a plurality of pecuniary goals; and

at least a non-goal group comprising data not related to the at least a plurality of pecuniary goals;

training, using the at least a processor, a group classifier using a group classifier, wherein the group training data further comprises:

correlating the at least a plurality of pecuniary goals of the composition data to one or more composition groups;

updating the group training data with a previous correlation of the at least a plurality of pecuniary goals of the composition data to the one or more composition groups; and

retraining the group classifier as a function of an updated group training data, wherein the group classifier is further configured to classify composition data into one or more composition groups as a function of the at least a plurality of pecuniary goals;

classifying, using the at least a processor, the composition data to one or more composition groups using the group classifier;

receiving input on the one or more composition groups from an advisor comprising a professional related to a specific composition group;

providing, using the at least a processor, a composition course as a function of the one or more composition groups, wherein providing the composition course comprises training a course machine-learning model on a course training dataset comprising a correlation between at least one example composition group and at least one example composition course, wherein the course machine-learning model comprises at least an artificial neural network comprising an input layer of nodes, one or more intermediate layers of nodes, and an output layer of nodes, adjusting one or more connections and one or more weights between nodes in adjacent layers of the course machine-learning model;

receiving additional course training data from the advisor; and

retraining the course machine-learning model as a function of the course training dataset;

determining, using the at least a processor, an action item as a function of the one or more composition groups wherein determining an action item further comprises generating at least an advisor action related to a review with the advisor; and

generating, using the at least a processor, an action strategy comprising at least a tax strategy as a function of the action item comprising a plurality of steps for the action strategy as a function of a focus level, wherein the focus level comprises a user goal, of the one or more composition groups.

11 . The method of claim 10 , wherein the composition data comprises document data.

12 . The method of claim 10 , wherein the composition course comprises an assessment.

13 . The method of claim 10 , wherein determining the action item comprises receiving an item response from the user.

14 . The method of claim 13 , wherein the item response comprises a course response.

15 . The method of claim 14 , wherein determining the action item comprises determining an item status of the action item as a function of the item response using a status machine-learning model.

16 . The method of claim 15 , wherein the item status comprises a course status, wherein the course status comprises a completion status of the composition course.

17 . The method of claim 16 , wherein determining the action item further comprises:

generating, using an action machine-learning model, a first action item, wherein the action machine-learning model is configured to correlate action training data to the action item;

receiving, using the at least a processor, the course response from the user for the first action item;

determining, using the status machine-learning model, the completion status of the composition course; and

identifying, using the action machine-learning model, a second action item as a function of the completion status of the composition course.

18 . The method of claim 10 , further comprising:

generating, using the at least a processor, a report using a graph machine-learning model, wherein the report comprises a graphically represented item of the composition data and generating the report using the graph machine-learning model further comprises:

receiving a graph training data, wherein the graph training data comprises the composition data; and

creating the report as a function of the graph training data, where in the report comprises the graphically represented item of the composition data.

Continuity (1)

References Cited (27)