Granted Patent B2

US 12,417,843 · App. 17/164,491 · Granted Sep 16, 2025

Inventor: Kenneth Neumann (Lakewood, CO)

Assignee: KPN INNOVATIONS LLC

G16H50/20G06N20/00G16H70/20

Abstract

Claims (85)

1. A system for confirming an advisory interaction with an artificial intelligence platform the system comprising:

a processor connected to a memory, wherein the processor is further configured to:

receive a first advisory input containing a constitutional inquiry and a user identifier from an advisor client device operated by an informed advisor;

retrieve an expert input from an expert database operating on the processor and located within a best practice module as a function of the first advisory input and the user identifier;

select a machine-learning process as a function of the expert input;

generate a therapeutic corrector utilizing the machine-learning process and the first advisory input wherein the therapeutic corrector further comprises a response to the constitutional inquiry, wherein the therapeutic corrector comprises a recommendation for lab tests a user should analyze as a function of symptom complaints;

analyze lab work of a user to determine a diagnosis for an illness;

display the therapeutic corrector on a graphical user interface located on the processor;

receive a second advisory input from the advisor client device, wherein the second advisory input contains a therapeutic corrector implementation response, and wherein the therapeutic implementation response contains a description of at least one result as a function of implementing the therapeutic corrector;

retrieve from the expert database located in the best practices module a best practices training set wherein the best practices training set correlates therapeutic correctors to therapeutic corrector implementation responses;

update the best practices module to incorporate the therapeutic corrector implementation response as a training set entry in the best practices training set;

obtain an adherence input from the advisor client device;

calculate an inference model as a function of the adherence input; and

update the expert database as a function of the inference model and therapeutic corrector.

2. The system of claim 1 , wherein generating a therapeutic corrector further comprises:

receiving therapeutic training data from an expert database wherein the therapeutic training data includes a plurality of data entries containing constitutional inquiries correlated to therapeutic correctors; and

generating, using a supervised machine-learning algorithm, a therapeutic model that outputs a therapeutic corrector utilizing the therapeutic training data and the first advisory input containing the constitutional inquiry.

3. The system of claim 1 , wherein generating a therapeutic corrector further comprises:

receiving a plurality of unclassified data entries from an expert database; and

generating using an unsupervised machine-learning algorithm the therapeutic corrector utilizing the plurality of unclassified data entries and the advisory input containing the constitutional inquiry.

4. The system of claim 1 , wherein obtaining the adherence input further comprises:

determining a therapeutic effect as a function of the therapeutic corrector; and

obtaining the adherence input as a function of the therapeutic effect.

5. The system of claim 4 , wherein determining the therapeutic effect further comprises:

establishing a therapeutic enumeration;

distinguishing a therapeutic divergence; and

determining the therapeutic effect as a function of the therapeutic enumeration, the therapeutic divergence, and a therapeutic threshold.

6. The system of claim 1 , wherein calculating the inference model further comprises:

retrieving an adherence training set, wherein the adherence training set correlates a monitoring element to a therapeutic adjustment; and

calculating the inference model as a function of the adherence input and the adherence training set using an adherence machine-learning model, wherein the adherence machine-learning model is trained as a function of the adherence training set.

7. The system of claim 1 , wherein calculating the inference model further comprises:

generating a physiological progression parameter; and

calculating the inference model as a function of the physiological progression parameter.

8. The system of claim 7 , wherein generating the physiological progression parameter further comprises:

identifying a status of the therapeutic corrector;

determining functional checkpoints as a function of the therapeutic corrector; and

generating the physiological progression parameter as a function of the functional checkpoints.

9. The system of claim 1 , wherein updating the expert database further comprises:

generating a therapeutic framework; and

updating the expert database as a function of the therapeutic framework.

10. The system of claim 9 , wherein generating the therapeutic framework further comprises:

producing a cryptographic identifier as a function of the user identifier; and

generating the therapeutic framework as a function of the cryptographic identifier.

11. A method for confirming an advisory interaction with an artificial intelligence platform comprising:

receiving, by a processor, a first advisory input containing a constitutional inquiry and a user identifier from an advisor client device operated by an informed advisor;

retrieving, by the processor, an expert input from an expert database operating on the processor and located within a best practices module as a function of the first advisory input and the user identifier;

selecting, by the processor, a machine-learning process as a function of the expert input;

generating, by the processor, a therapeutic corrector utilizing the machine-learning process and the first advisory input wherein the therapeutic corrector further comprises a response to the constitutional inquiry, wherein the therapeutic corrector comprises a recommendation for lab tests a user should analyze as a function of symptom complaints;

analyzing lab work of a user to determine a diagnoses for an illness;

displaying, by the processor, the therapeutic corrector on a graphical user interface located on the processor;

receiving, by the processor, a second advisory input from the advisor client device, wherein the second advisory input contains a therapeutic corrector implementation response, and wherein the therapeutic implementation response contains a description of at least one result as a function of implementing the therapeutic corrector;

retrieve from the expert database located in the best practices module a best practices training set wherein the best practices training set correlates therapeutic correctors to therapeutic corrector implementation responses;

update the best practices module to incorporate the therapeutic corrector implementation response as a training set entry in the best practices training set;

obtaining, by the processor, an adherence input from the advisor client device;

calculating, by the processor, an inference model as a function of the adherence input; and

updating, by the processor, the expert database as a function of the inference model and therapeutic corrector.

12. The method of claim 11 , wherein generating a therapeutic corrector further comprises:

receiving therapeutic training data from an expert database wherein the therapeutic training data includes a plurality of data entries containing constitutional inquiries correlated to therapeutic correctors; and

generating using a supervised machine-learning algorithm a therapeutic model that outputs a therapeutic corrector utilizing the therapeutic training data and the first advisory input containing the constitutional inquiry.

13. The method of claim 11 , wherein generating a therapeutic corrector further comprises:

receiving a plurality of unclassified data entries from an expert database; and

generating using an unsupervised machine-learning the therapeutic corrector utilizing the plurality of unclassified data entries and the advisory input containing the constitutional inquiry.

14. The method of claim 11 , wherein obtaining the adherence input further comprises:

determining a therapeutic effect as a function of the therapeutic corrector; and

obtaining the adherence input as a function of the therapeutic effect.

15. The method of claim 14 , wherein determining the therapeutic effect further comprises:

establishing a therapeutic enumeration;

distinguishing a therapeutic divergence; and

determining the therapeutic effect as a function of the therapeutic enumeration, the therapeutic divergence, and a therapeutic threshold.

16. The method of claim 11 , wherein calculating the inference model further comprises:

retrieving an adherence training set wherein the adherence training set correlates a monitoring element to a therapeutic adjustment; and

calculating the inference model as a function of the adherence input and the adherence training set using an adherence machine-learning model; wherein the adherence machine-learning model is trained as a function of the adherence training set.

17. The method of claim 11 , wherein calculating the inference model further comprises:

generating a physiological progression parameter; and

calculating the inference model as a function of the physiological progression parameter.

18. The method of claim 17 , wherein generating the physiological progression parameter further comprises:

identifying a status of the therapeutic corrector;

determining functional checkpoints as a function of the therapeutic corrector; and

generating the physiological progression parameter as a function of the functional checkpoints.

19. The method of claim 11 , wherein updating the expert database further comprises:

generating a therapeutic framework; and

updating the expert database as a function of the therapeutic framework.

20. The method of claim 19 , wherein generating the therapeutic framework further comprises:

producing a cryptographic identifier as a function of the user identifier; and

generating the therapeutic framework as a function of the cryptographic identifier.

Assignments (2)

Continuity (3)

References Cited (14)