Granted Patent B1

US 12,217,627 · App. 18/398,446 · Granted Feb 4, 2025

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

Assignee: The Strategic Coach Inc.

G09B5/02G06Q10/0633G06Q10/0639G06N20/00

Abstract

Claims (65)

1. An apparatus for determining action guides, wherein the apparatus comprises:

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 a user action, wherein the user action comprises a user usage;

convert the user usage of the user action into a current usage;

obtain action template data, wherein the action template data comprises a template usage configured to determine a relevancy score corresponding to a relevancy strength of data from a web crawler function;

generate training data, wherein the training data comprises a template action expectation as a function of the user action and the action template data;

determine an action feasibility as a function of the current usage and the template action expectation, wherein determining the action feasibility comprises: iteratively training a machine learning model as a function of the training data, wherein iteratively training the machine learning model further comprises:

using the training data applied to an input layer of nodes comprising a plurality of data entries of user action and action template data inputs, one or more intermediate layers of nodes, and an output layer of nodes comprising a plurality of template action expectation, action feasibility, and action guide outputs;

updating the outputs based on an error function iteratively, wherein an error function value is evaluated in training iterations and compared to a threshold;

comparing an output generated by the machine learning model to an input in the training data;

adjusting one or more connections between nodes in adjacent layers of the machine learning model as a function of weighted sums of the inputs;

detecting a scoring function between the output layer of nodes and the input layer of nodes;

determining a correlation between the output layer of nodes and the input layer of nodes;

updating the training data as a function of the scoring function; and

retraining the machine learning model as a function of the scoring function; and

generate an action guide as a function of the action feasibility.

2. The apparatus of claim 1 , wherein:

the user action further comprises a user action expectation; and

the memory contains instructions further configuring the at least a processor to generate the template action expectation as a function of the user action expectation and the action template data.

3. The apparatus of claim 1 , wherein the user usage comprises a time usage.

4. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to:

obtain usage weights of a first current usage and a second current usage; and

calculate the current usage, wherein the current usage comprises a sum of a first current usage and a second current usage that are converted respectively from a first user usage and the second user usage using the usage weights.

5. The apparatus of claim 1 , wherein the template action expectation comprises a positive expectation, wherein the positive expectation comprises a positive expectation weight.

6. The apparatus of claim 1 , wherein the template action expectation comprises a negative expectation, wherein the negative expectation comprises a negative expectation weight.

7. The apparatus of claim 6 , wherein the memory contains instructions further configuring the at least a processor to determine the action feasibility using a feasibility threshold, wherein the feasibility threshold is compared with the negative expectation to determine the action feasibility.

8. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to generate an action abandonment of the action guide when the action feasibility is below a guide threshold.

9. The apparatus of claim 8 , wherein the memory contains instructions further configuring the at least a processor to generate an action redirection of the action guide when the action feasibility is above the guide threshold.

10. The apparatus of claim 1 , wherein the memory contains instructions further configuring the at least a processor to:

receive a rejection of a first action guide from a user; and

generate a second action guide as a function of the rejection.

11. A method for determining action guides, wherein the method comprises:

receiving, using at least a processor, a user action, wherein the user action comprises a user usage;

converting, using the at least a processor, the user usage of the user action into a current usage;

obtaining, using the at least a processor, action template data, wherein the action template data comprises a template usage configured to determine a relevancy score corresponding to a relevancy strength of data from a web crawler function;

generating training data, using the at least a processor, wherein the training data comprises a template action expectation as a function of the user action and the action template data;

determining, using the at least a processor, an action feasibility as a function of the current usage and the template action expectation, wherein determining the action feasibility comprises:

iteratively training a machine learning model as a function of the training data, wherein iteratively training the machine learning model further comprises:

using the training data applied to an input layer of nodes comprising a plurality of data entries of user action and action template data inputs, one or more intermediate layers of nodes, and an output layer of nodes comprising a plurality of template action expectation, action feasibility, and action guide outputs;

updating the outputs based on an error function, wherein an error function value is evaluated in training iterations and compared to a threshold;

comparing an output generated by the machine learning model to an input in the training data;

adjusting one or more connections between nodes in adjacent layers of the machine learning model as a function of weighted sums of the inputs;

detecting a scoring function between the output layer of nodes and the input layer of nodes;

determining a correlation between the output layer of nodes and the input layer of nodes;

updating the training data as a function of the scoring function; and

retraining the machine learning model as a function of the scoring function; and

generating, using the at least a processor, an action guide as a function of the action feasibility.

12. The method of claim 11 , further comprising:

generating, using the at least a processor, the template action expectation as a function of a user action expectation of the user action and the action template data.

13. The method of claim 11 , wherein the user usage comprises a time usage.

14. The method of claim 11 , further comprising:

obtaining, using the at least a processor, usage weights of a first current usage and a second current usage; and

calculating, using the at least a processor, the current usage, wherein the current usage comprises a sum of a first current usage and a second current usage that are converted respectively from a first user usage and the second user usage using the usage weights.

15. The method of claim 11 , wherein the template action expectation comprises a positive expectation, wherein the positive expectation comprises a positive expectation weight.

16. The method of claim 11 , wherein the template action expectation comprises a negative expectation, wherein the negative expectation comprises a negative expectation weight.

17. The method of claim 16 , further comprising:

determining, using the at least a processor, the action feasibility using a feasibility threshold, wherein the feasibility threshold is compared with the negative expectation to determine the action feasibility.

18. The method of claim 11 , further comprising:

generating, using the at least a processor, an action abandonment of the action guide when the action feasibility is below a guide threshold.

19. The method of claim 18 , further comprising:

generating, using the at least a processor, an action redirection of the action guide when the action feasibility is above the guide threshold.

20. The method of claim 11 , further comprising:

receiving, using the at least a processor, a rejection of a first action guide from a user; and

generating, using the at least a processor, a second action guide as a function of the rejection.

Assignments (1)

References Cited (12)