IP Library Granted Patent US 12,470,655
Granted Patent B1
US 12,470,655 · App. 18/891,704 · Granted Nov 11, 2025

System for processing telephone voice data to drive an application protocol

Inventors: Sharif Vakili (Los Altos, CA); Ashwin K. Nayak (Mountain View, CA)
Assignee: UpDoc Inc.
H04M3/4936
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 12,470,655
App. No.
18/891,704
Granted
Nov 11, 2025
Kind
B1
Abstract

An interactive voice response (IVR) system for processing telephone voice data. Certain aspects of the present disclosure provide for an IVR system that is operably engaged with at least one application engine. The application engine may comprise at least one configurable protocol comprising one or more parameters that may be configured by at least one user. The IVR system may be configured to execute one or more bi-directional voice call with at least one end user to derive voice response data corresponding to variables associated with the one or more parameters. The IVR system may be configured to process the voice response data and provide the voice response data as a formatted data input to the application engine to drive one or more operations for the at least configurable protocol and/or configure, update or modify one or more graphical user interface of an end user application.

Claims (56)

1 . A system for processing telephone voice data, the system comprising:

one or more processors; and

at least one non-transitory computer-readable memory device in communication with the one or more processors and having processor-executable instructions stored thereon that, when executed by the one or more processors, is configured to cause the one or more processors to execute one or more operations, the one or more operations comprising:

providing a first instance of an end user application comprising a user interface to a client device associated with a first end user, wherein the user interface comprises one or more graphical elements configured according to one or more parameters of an application protocol for the end user application, wherein the end user application is a patient medication regimen, and

wherein the application protocol comprises one or more task or interaction sequence for the first end user;

establishing, via a telephony network, a bi-directional voice call between an interactive voice response agent and the client device;

generating, via the interactive voice response agent, at least one conversational prompt comprising a natural language audio output over the bi-directional voice call,

wherein the at least one conversational prompt is configured according to the one or more task or interaction sequence for the first end user;

receiving, via the bi-directional voice call, at least one voice utterance from the first end user in response to the at least one conversational prompt, wherein the at least one voice utterance is received via a receiver of the client device;

processing the at least one voice utterance according to a natural language processing engine to generate at least one dataset comprising the telephone voice data;

processing the telephone voice data to extract one or more variables associated with the one or more parameters of the application protocol;

updating a state of the application protocol according to the one or more variables extracted from the telephone voice data,

wherein updating the state of the application protocol comprises updating the one or more task or interaction sequence for the first end user; and

modifying the one or more graphical elements of the user interface in response to updating the state of the application protocol.

2 . The system of claim 1 wherein the one or more parameters of the application protocol are configured according to one or more user-generated inputs.

3 . The system of claim 1 wherein the one or more graphical elements are modified according to the one or more variables extracted from the telephone voice data.

4 . The system of claim 1 wherein the one or more graphical elements are configured to provide a graphical visualization of one or more steps or operations of the application protocol.

5 . The system of claim 1 wherein the one or more graphical elements are modified to display a stage or degree of progress for the one or more task or interaction sequence.

6 . The system of claim 1 wherein the one or more operations further comprise establishing, via the telephony network, a subsequent bi-directional voice call between the interactive voice response agent and the client device in response to updating the state of the application protocol according to the one or more variables extracted from the telephone voice data.

7 . The system of claim 6 wherein the one or more operations further comprise generating, via the interactive voice response agent, at least one subsequent conversational prompt, wherein the at least one subsequent conversational prompt is configured according to the updated state of the application protocol.

8 . A system for processing telephone voice data, the system comprising:

one or more processors; and

at least one non-transitory computer-readable memory device in communication with the one or more processors and having processor-executable instructions stored thereon that, when executed by the one or more processors, is configured to cause the one or more processors to execute one or more operations, the one or more operations comprising:

receiving a first set of user-generated inputs from a first user, the first set of user-generated inputs comprising one or more parameters for an application protocol of an end user application, wherein the end user application is a patient medication regimen;

configuring the application protocol according to the first set of user-generated inputs,

wherein the application protocol comprises one or more task or interaction sequence for a second user;

configuring at least one conversational prompt for an interactive voice response agent according to the one or more task or interaction sequence for the second user;

establishing, via a telephony network, a bi-directional voice call between the interactive voice response agent and a telephone associated with the second user;

generating, via the interactive voice response agent, a natural language audio output over the bi-directional voice call, the natural language audio output comprising the at least one conversational prompt;

receiving, via the bi-directional voice call, at least one voice utterance from the second user in response to the at least one conversational prompt;

processing the at least one voice utterance according to a natural language processing engine to generate at least one dataset comprising the telephone voice data;

processing the telephone voice data to extract one or more variables associated with the one or more parameters for the application protocol of the end user application; and

updating a state of the application protocol according to the one or more variables extracted from the telephone voice data,

wherein updating the state of the application protocol comprises updating the one or more task or interaction sequence for the second user.

9 . The system of claim 8 wherein the one or more operations further comprise configuring a graphical user interface of the end user application according to the one or more parameters of the application protocol.

10 . The system of claim 9 wherein the one or more operations further comprise presenting an instance of the end user application to the second user via a client device.

11 . The system of claim 10 wherein the one or more operations further comprise modifying one or more graphical elements of the graphical user interface in response to updating the state of the application protocol.

12 . The system of claim 11 wherein the one or more graphical elements are modified according to the one or more variables extracted from the telephone voice data.

13 . The system of claim 12 wherein the one or more graphical elements are configured to provide a graphical visualization of one or more steps or operations of the application protocol.

14 . The system of claim 13 wherein the one or more graphical elements are modified to provide a graphical visualization of a stage or degree of progress for the one or more task or interaction sequence.

15 . A system for processing telephone voice data comprising:

one or more processors; and

at least one non-transitory computer-readable memory device in communication with the one or more processors and having processor-executable instructions stored thereon that, when executed by the one or more processors, is configured to cause the one or more processors to execute one or more operations, the one or more operations comprising:

configuring an application protocol for an end user application, wherein the application protocol comprises one or more task or interaction sequence for an end user of the end user application, wherein the end user application is a patient medication regimen, and wherein the end user application comprises a graphical user interface comprising one or more graphical elements configured to provide a visualization of the one or more task or interaction sequence for the end user;

configuring at least one conversational prompt for an interactive voice response agent according to the one or more task or interaction sequence for the end user;

establishing, via a telephony network, a bi-directional voice call between the interactive voice response agent and a telephone associated with the end user;

providing, via the bi-directional voice call, the at least one conversational prompt to the end user, wherein the at least one conversational prompt comprises a natural language audio output by the interactive voice response agent;

receiving, via the bi-directional voice call, at least one voice utterance from the end user in response to the at least one conversational prompt;

processing the at least one voice utterance according to a natural language processing engine to generate at least one dataset comprising the telephone voice data;

processing the telephone voice data to extract one or more variables associated with one or more parameters of the application protocol; and

configuring or modifying the one or more graphical elements of the graphical user interface according to the one or more variables extracted from the telephone voice data.

16 . The system of claim 15 wherein the one or more operations further comprise updating a state of the application protocol according to the one or more variables extracted from the telephone voice data.

17 . The system of claim 16 wherein updating the state of the application protocol comprises updating the one or more task or interaction sequence for the end user.

18 . The system of claim 15 wherein the one or more operations further comprise providing an instance of the end user application to an end user device associated with the end user.

19 . The system of claim 15 wherein the one or more graphical elements are configured or modified to provide a graphical visualization of a stage or degree of progress for the one or more task or interaction sequence.

20 . The system of claim 15 wherein the one or more operations further comprise receiving a plurality of user-generated input data for configuring the application protocol for the end user application.

Assignments (1)
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Sep 25, 2024
From: VAKILI, SHARIF; NAYAK, ASHWIN K.
To: UPDOC INC.
Reel/Frame 068698/0068 →
References Cited (25)
US 8116445B2 · Odinak et al. · 2012 [cited by applicant]
US 9697057B2 · Allen et al. · 2017 [cited by applicant]
US 11031013B1 · Myers et al. · 2021 [cited by applicant]
US 11176942B2 · Di Fabbrizio et al. · 2021 [cited by applicant]
US 11176945B2 · Paul et al. · 2021 [cited by applicant]
US 11301908B2 · Batcha et al. · 2022 [cited by applicant]
US 11303750B2 · Chavez et al. · 2022 [cited by applicant]
US 11363140B2 · Agarwal et al. · 2022 [cited by applicant]
US 11456887B1 · McCracken et al. · 2022 [cited by applicant]
US 11663250B2 · Raju · 2023 [cited by applicant]
US 11676574B2 · Rakshit et al. · 2023 [cited by applicant]
US 11743378B1 · Johnston et al. · 2023 [cited by applicant]
US 11804211B2 · Aharoni et al. · 2023 [cited by applicant]
US 11956187B2 · Hackman et al. · 2024 [cited by applicant]
US 12008994B2 · De et al. · 2024 [cited by applicant]
US 12020690B1 · Gamzu et al. · 2024 [cited by applicant]
US 20060206310A1 · Ravikumar et al. · 2006 [cited by applicant]
US 20120041775A1 · Cosentino · 2012 [cited by examiner]
US 20130179178A1 · Vemireddy · 2013 [cited by examiner]
US 20170213001A1 · Harrison · 2017 [cited by examiner]
US 20190362319A1 · Yen · 2019 [cited by applicant]
US 20220051661A1 · Park et al. · 2022 [cited by applicant]
US 20220199079A1 · Hanson et al. · 2022 [cited by applicant]
US 20230026945A1 · Friedlander et al. · 2023 [cited by applicant]
US 20240048649A1 · Vaananen · 2024 [cited by applicant]