Granted Patent B1

US 12,354,038 · App. 18/406,756 · Granted Jul 8, 2025

Inventors: Barbara Sue Smith (Toronto, CA); Daniel J. Sullivan (Toronto, CA)

Assignee: The Strategic Coach Inc.

G06Q10/0631

Abstract

Claims (95)

1. An apparatus for predicting a resource growth pattern, the apparatus comprising:

at least a processor;

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

receive a first datum from a user device, wherein the first datum describes a first activity pattern of the user device;

receive a second datum from a client device, wherein the second datum describes a second activity pattern of the user device;

retrieve a third datum, wherein the third datum describes a prioritization value of the first activity pattern relative to the second activity pattern;

classify the third datum to a label selected from a plurality of labels based on the prioritization value, wherein classifying the third datum further comprises:

generating a representation of the third datum in a first space having a first number of dimensions, wherein generating the representation comprises using a first machine-learning process comprising a representation machine-learning model and further comprising:

receiving representation training data, wherein the representation training data comprises:

 applying an input layer of nodes comprising a plurality of user data, one or more intermediate layers of nodes, and an output layer of nodes comprising a plurality of first space data;

 adjusting one or more connections and one or more weights between nodes in adjacent layers of the representation machine-learning model;

 detecting correlations between the output layer of nodes and the input layer of nodes;

training, iteratively, the representation machine-learning model using the representation training data, wherein training the representation machine-learning model includes retraining the representation machine-learning model using a simulated annealing algorithm, the detected correlations between the output layer of nodes and the input layer of nodes, and user inputs indicating a sub-optimal performance received by the at least processor by performing an auditing process configured to compare outputs of the representation machine-learning model to a convergence test to reconfigure a network of nodes; and

generating the representation of the third datum using the trained representation machine-learning model; and

projecting the representation of the third datum generated by the trained representation machine-learning model to a second space having a second number of dimensions, wherein projecting the representation comprises using a second machine-learning process and results in a projected representation of a second number of dimensions; and

generate an interface query data structure, wherein the interface query data structure configures a remote display device to:

display an input field;

receive at least a user-input datum into the input field, wherein the user-input datum describes updating the prioritization value; and

display a resource growth pattern including displaying the representation based on the user-input datum.

2. The apparatus of claim 1 , wherein generating the interface query data structure further comprises:

retrieving data describing attributes of a user from a database communicatively connected to the at least a processor;

displaying a representation of at least a first label and a second label selected from a plurality of labels in a grid; and

generating the interface query data structure based on the data describing attributes of the user, wherein generating the interface query data structure further comprises:

determining at least a vector from the representation of the at least a first label to the second label; and

configuring the remote display device to display the at least a vector.

3. The apparatus of claim 2 , wherein determining the at least a vector from the at least a first label to the second label further comprises generating the vector including an angle value and a distance value, wherein the angle value and the distance value describe at least a divergence value between the first datum and the second datum.

4. The apparatus of claim 1 , wherein generating the third datum further comprises retrieving data describing current preferences of the user device between a minimum value and a maximum value from a database communicatively connected to the at least a processor, wherein retrieving the data further comprises receiving at least a form element input into the input field.

5. The apparatus of claim 1 , further comprising generating at least an additional input field based on a divergence value that describes divergence between the first datum and the second datum.

6. The apparatus of claim 1 , further comprising:

classifying at least an instance of the first datum to the third datum;

determining a proximity of the at least an instance of the first datum to the third datum based on the first activity pattern; and

adjusting the third datum to reduce the proximity.

7. The apparatus of claim 1 , further comprising:

classifying the second datum to the third datum, wherein classifying the second datum further comprises comparing the second datum to the third datum; and

determining a parity value based on comparison of the second datum to the third datum, wherein the parity value is included within the resource growth pattern.

8. The apparatus of claim 5 , further comprising:

determining a pattern, wherein the pattern describes a user interaction;

classifying at least an element of the pattern to the divergence value; and

adjusting the pattern based on a magnitude of the divergence value.

9. The apparatus of claim 1 , further configured to evaluate the user-input datum comprising:

classifying one or more new instances of the user-input datum to the third datum;

generating at least a divergence value based on the classification; and

displaying the at least a divergence value hierarchically based on magnitude of divergence.

10. The apparatus of claim 1 , wherein classifying the third datum to the label further comprises:

organizing at least some labels based on their respective proximity to a minimal output type and a maximum output type;

aggregating at least an instance of the first datum based on the classification; and

classifying aggregated first data to the label having a closest proximity to the maximum output type.

11. A method for predicting a resource growth pattern, the method comprising:

receiving, by a computing device, a first datum from a user device, wherein the first datum describes a first activity pattern of the user device;

receiving, by the computing device, a second datum from a client device, wherein the second datum describes a second activity pattern of the user device;

receiving, by the computing device, a third datum from a database communicatively connected to the computing device, wherein the third datum describes a prioritization value of the first activity pattern relative to the second activity pattern;

classifying, by the computing device, at least the third datum to a label selected from a plurality of labels based on the prioritization value, wherein classifying the third datum further comprises:

generating a representation of the third datum in a first space having a first number of dimensions, wherein generating the representation comprises using a first machine-learning process comprising a representation machine-learning model and further comprising:

receiving representation training data, wherein the representation training data comprises:

applying an input layer of nodes comprising a plurality of user data, one or more intermediate layers of nodes, and an output layer of nodes comprising a plurality of first space data;

adjusting one or more connections and one or more weights between nodes in adjacent layers of the representation machine-learning model;

detecting correlations between the output layer of nodes and the input layer of nodes;

training, iteratively, the representation machine-learning model using the representation training data, wherein training the representation machine-learning model includes retraining the representation machine-learning model using a simulated annealing algorithm, the detected correlations between the output layer of nodes and the input layer of nodes, and user inputs indicating a sub-optimal performance received by the computing device by performing an auditing process configured to compare outputs of the representation machine-learning model to a convergence test to reconfigure a network of nodes; and

generating the representation of the third datum using the trained representation machine-learning model; and

projecting the representation of the third datum generated by the trained representation machine-learning model to a second space having a second number of dimensions, wherein projecting the representation comprises using a second machine-learning process and results in a projected representation of a second number of dimensions; and

generating, by the computing device, an interface query data structure including an input field, wherein the interface query data structure configures a remote display device to:

display the input field;

receive at least a user-input datum into the input field, wherein the user-input datum describes updating the prioritization value; and

display the resource growth pattern including displaying the representation based on the user-input datum.

12. The method of claim 11 , wherein generating the interface query data structure further comprises:

retrieving data describing attributes of a user from a database communicatively connected to the computing device;

displaying a representation of at least a first label and a second label selected from a plurality of labels in a grid;

generating the interface query data structure based on the data describing attributes of the user, wherein generating the interface query data structure further comprises:

determining at least a vector from the representation of at least the first label to the second label; and

configuring the remote display device to display the vector.

13. The method of claim 12 , wherein determining the at least the vector from at least the first label to the second label further comprises generating the vector including an angle value and a distance value, wherein:

the angle value and the distance value describe at least a divergence value between the first datum and the second datum.

14. The method of claim 11 , wherein generating the third datum further comprises:

retrieving data describing current preferences of the user device between a minimum value and a maximum value from a database communicatively connected to the computing device, wherein retrieving the data further comprises receiving at least a form element input into the input field.

15. The method of claim 11 , further comprising generating at least an additional input field based on a divergence value, which describes divergence between the first datum and the second datum.

16. The method of claim 11 , further comprising:

classifying at least an instance of the first datum to the third datum;

determining a proximity of a respective first datum to the third datum based on the first activity pattern; and

adjusting the third datum to reduce the proximity.

17. The method of claim 11 , further comprising:

classifying the second datum to the third datum, wherein classifying the second datum further comprises:

comparing the second datum to the third datum; and

determining a parity value based on comparison of the second datum to the third datum, wherein the parity value is included within the resource growth pattern.

18. The method of claim 15 , further comprising:

determining a pattern, wherein the pattern describes user interaction with the database;

classifying at least an element of the pattern to the divergence value; and

adjusting the pattern based on a magnitude of the divergence value.

19. The method of claim 11 , further configured to evaluate the user-input datum comprising:

classifying one or more new instances of the user-input datum to at least the third datum;

generating at least a divergence value based on the classification; and

displaying the at least a divergence value hierarchically based on magnitude of divergence.

20. The method of claim 11 , wherein classifying the third datum to the label further comprises:

organizing at least some labels based on their respective proximity to a minimal output type and a maximum output type;

aggregating at least an instance of the first datum based on the classification; and

classifying aggregated first data to the label having a closest proximity to the maximum output type.

Assignments (1)

References Cited (19)