IP Library › Granted Patent US 12670336

Granted Patent B2

US 12670336 · App. 19/196,797 · Granted Jun 30, 2026

Methods, systems, apparatuses, and devices for facilitating customizable communications with users

Inventors: Christopher David McNamara (Nelson, CA); Larry John Skelly (Whitby, CA); Mark Edward Russel Giroux (Winnipeg, CA); Mark Daniel Szynkaruk (Grand Forks, CA)

Assignee: Neoptio Health Incorporated

G06F40/35 G06F3/011 G06F2203/011

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 12670336
App. No.: 19/196,797
Granted: Jun 30, 2026
Kind: B2

External Links

USPTO Patent Center↗ Full Patent PDF↗

Abstract

Disclosed herein is a method for facilitating customizable communications with users. The method may include receiving at least one input associated with at least one user from at least one user device associated with the at least one user, analyzing the at least one input, identifying at least one instruction from a plurality of instructions based on the analyzing of the at least one input, and obtaining at least one output using at least one language model based on the at least one input and the at least one instruction. Further, the method may include transmitting the at least one output to the at least one user device. Further, the method may include storing the at least one input and the at least one output.

Claims (65)

1 . A method for facilitating customizable communications with users, the method comprising:

receiving, using a communication device, at least one input associated with at least one user from at least one user device associated with the at least one user;

analyzing, using a processing device, the at least one input;

identifying, using the processing device, at least one instruction from a plurality of instructions based on the analyzing of the at least one input;

obtaining, using the processing device, at least one output using at least one language model based on the at least one input and the at least one instruction, wherein the at least one language model comprises a generative artificial intelligence model, wherein the at least one input comprises at least one query associated with the at least one user, and at least one characteristic corresponding to at least one of a capability and a limitation of the at least one user device, wherein the obtaining of the at least one output comprises:

determining at least one value to at least one parameter associated with the at least one language model based on the at least one instruction, wherein the at least one parameter governs a behavior of the at least one language model; and

inputting the at least one input to the at least one language model based on the determining, wherein the at least one language model is configured for generating the at least one output based on the at least one value of the at least one parameter and the at least one input, wherein the at least one language model is further configured for tailoring the at least one output based on the at least one characteristic;

analyzing, using the processing device, the at least one output based on at least one criterion;

determining, using the processing device, an appropriacy of the at least one output for the at least one user based on the analyzing of the at least one output, wherein the appropriacy comprises a positive appropriacy and a negative appropriacy;

transmitting, using the communication device, the at least one output to the at least one user device, wherein the transmitting of the at least one output is based on the positive appropriacy of the at least one output; and

storing, using a storage device, the at least one input and the at least one output.

2 . The method of claim 1 , wherein the analyzing of the at least one input comprises analyzing the at least one input using at least one machine learning model, wherein the at least one machine model is configured for classifying at least one of a state and an intent for the at least one user based on the at least one input, wherein the identifying of the at least one instruction is further based on at least one of the state and the intent.

3 . The method of claim 1 , wherein the analyzing of the at least one input comprises analyzing the at least one input using at least one machine learning model, wherein the at least one machine learning model is configured for predicting at least one requirement of the at least one user, wherein the identifying of the at least one instruction is further based on the at least one requirement.

4 . The method of claim 1 further comprising:

obtaining, using the processing device, at least one previous input of the at least one user;

analyzing, using the processing device, the at least one previous input; and

determining, using the processing device, at least one value for at least one variable based on the analyzing of the at least one previous input and the analyzing of the at least one input, wherein the identifying of the at least one instruction is further based on the at least one value of the at least one variable.

5 . The method of claim 1 further comprising:

detecting, using at least one sensor, at least one of a physical state, a physiological state, and an emotional state of the at least one user;

generating, using the processing device, at least one user data associated with the at least one user, wherein the at least one user data comprises at least one sensor data and at least one external data, wherein the at least one sensor data is generated by the at least one sensor based on the detecting of at least one of the physical state, the physiological state, and the emotional state of the at least one user, wherein the at least one external data is generated by at least one external device, wherein the at least one external device comprises a wearable health device; and

analyzing, using the processing device, the at least one user data, wherein the identifying of the at least one instruction is further based on the analyzing of the at least one user data, wherein the at least one sensor data and the at least one external data form an integrated data, wherein the integrated data is used for dynamically adjusting the at least one output of the at least one language model.

6 . The method of claim 1 further comprising:

identifying, using the processing device, at least one first instruction from the plurality of instructions based on the negative appropriacy;

obtaining, using the processing device, at least one modified output using the at least one language model based on the at least one input and the at least one first instruction; and

transmitting, using the communication device, the at least one modified output to the at least one user device.

7 . The method of claim 1 further comprising:

receiving, using the communication device, at least one feedback for at least one previous output corresponding to at least one previous input from the at least one user device;

updating, using the processing device, at least one of a plurality of previous instructions based on the at least one feedback; and

determining, using the processing device, at least one of the plurality of instructions based on the updating, wherein the identifying of the at least one instruction from the plurality of instructions is further based on the determining of at least one of the plurality of instructions.

8 . The method of claim 7 further comprising obtaining, using the processing device, at least one additional information associated with at least one of the plurality of previous instructions, wherein the updating of at least one of the plurality of instructions is further based on the at least one additional information.

9 . The method of claim 1 further comprising:

analyzing, using the processing device, the at least one instruction; and

identifying, using the processing device, at least one portion of at least one data based on the analyzing of the at least one instruction, wherein the at least one language model is further configured for accessing the at least one portion of the at least one data based on the identifying, wherein the generating of the at least one output is further based on the accessing of the at least one portion of the at least one data.

10 . A system for facilitating customizable communications with users, the system comprising:

a communication device configured for:

receiving at least one input associated with at least one user from at least one user device associated with the at least one user; and

transmitting at least one output to the at least one user device, wherein the transmitting of the at least one output is based on a positive appropriacy of the at least one output;

a processing device communicatively coupled with the communication device, wherein the processing device is configured for:

analyzing the at least one input;

identifying at least one instruction from a plurality of instructions based on the analyzing of the at least one input;

obtaining the at least one output using at least one language model based on the at least one input and the at least one instruction, wherein the at least one language model comprises a generative artificial intelligence model, wherein the at least one input comprises at least one query associated with the at least one user, and at least one characteristic corresponding to at least one of a capability and a limitation of the at least one user device, wherein the obtaining of the at least one output comprises:

analyzing the at least one output based on at least one criterion; and

determining an appropriacy of the at least one output for the at least one user based on the analyzing of the at least one output, wherein the appropriacy comprises the positive appropriacy and a negative appropriacy; and

a storage device communicatively coupled with the processing device, wherein the storage device is configured for storing the at least one input and the at least one output.

11 . The system of claim 10 , wherein the analyzing of the at least one input comprises analyzing the at least one input using at least one machine learning model, wherein the at least one machine model is configured for classifying at least one of a state and an intent for the at least one user based on the at least one input, wherein the identifying of the at least one instruction is further based on at least one of the state and the intent.

12 . The system of claim 10 , wherein the analyzing of the at least one input comprises analyzing the at least one input using at least one machine learning model, wherein the at least one machine learning model is configured for predicting at least one requirement of the at least one user, wherein the identifying of the at least one instruction is further based on the at least one requirement.

13 . The system of claim 10 , wherein the processing device is further configured for:

obtaining at least one previous input of the at least one user;

analyzing the at least one previous input; and

determining at least one value for at least one variable based on the analyzing of the at least one previous input and the analyzing of the at least one input, wherein the identifying of the at least one instruction is further based on the at least one value of the at least one variable.

14 . The system of claim 10 further comprising at least one sensor communicatively coupled with the processing device, wherein the at least one sensor is configured for detecting at least one of a physical state, a physiological state, and an emotional state of the at least one user, wherein the processing device is further configured for:

generating at least one user data associated with the at least one user, wherein the at least one user data comprises at least one sensor data and at least one external data, wherein the at least one sensor data is generated by the at least one sensor based on the detecting of at least one of the physical state, the physiological state, and the emotional state of the at least one user, wherein the at least one external data is generated by at least one external device, wherein the at least one external device comprises a wearable health device; and

analyzing the at least one user data, wherein the identifying of the at least one instruction is further based on the analyzing of the at least one user data, wherein the at least one sensor data and the at least one external data form an integrated data, wherein the integrated data is used for dynamically adjusting the at least one output of the at least one language model.

15 . The system of claim 10 , wherein the processing device is further configured for:

identifying at least one first instruction from the plurality of instructions based on the negative appropriacy; and

obtaining at least one modified output using the at least one language model based on the at least one input and the at least one first instruction, wherein the communication device is further configured for transmitting the at least one modified output to the at least one user device.

16 . The system of claim 10 , wherein the communication device is further configured for receiving at least one feedback for at least one previous output corresponding to at least one previous input from the at least one user device, wherein the processing device is further configured for:

updating at least one of a plurality of previous instructions based on the at least one feedback; and

determining at least one of the plurality of instructions based on the updating, wherein the identifying of the at least one instruction from the plurality of instructions is further based on the determining of at least one of the plurality of instructions.

17 . The system of claim 16 , wherein the processing device is further configured for obtaining at least one additional information associated with at least one of the plurality of previous instructions, wherein the updating of at least one of the plurality of instructions is further based on the at least one additional information.

18 . The system of claim 10 , wherein the processing device further configured for:

analyzing the at least one instruction; and

identifying at least one portion of at least one data based on the analyzing of the at least one instruction, wherein the at least one language model is further configured for accessing the at least one portion of the at least one data based on the identifying, wherein the generating of the at least one output is further based on the accessing of the at least one portion of the at least one data.