# US 11,909,901 B2 · System and method for displaying the history of a user's interaction with a voice application

> Agents: this data is available as JSON from the patentgrep API and MCP server — see https://patentgrep.com/llms.txt

- Number: US 11,909,901 B2
- Document ID: US11909901B2
- Status: Granted
- Kind: B2
- Application number: 17/410,683
- Filed: 2021-08-24
- Published: 2021-12-16
- Granted: 2024-02-20
- Earliest claimed: 2005-09-01
- Assignees: Xtone, Inc.
- Applicants: Xtone, Inc.
- Inventors: Vishal Dhawan; Timothy M Price; Minoj Sindhwani
- Web page: https://patentgrep.com/patent/US11909901B2

## CPC

- H04M 1/2478: {Telephone terminals specially adapted for non-voice services, e.g. email, internet access (centralized arrangements where telephones services are combined H04M7/0024; for recording text messages H04M3/5322; for accessing Internet H04M3/4938)}
- H04M 1/2477: {for selecting a function from a menu display (H04M1/2474 takes precedence)}
- H04M 3/42221: {Conversation recording systems (at the subscriber's set H04M1/656)}
- H04M 3/4936: {Speech interaction details (speech recognition per se G10L15/00)}
- H04M 1/2535: {adapted for voice communication over an Internet Protocol [IP] network (Voice over Internet Protocol (VoIP) network equipment and services H04M7/006; implementation or adaptation of Internet protocol [IP], of transmission control protocol [TCP] or of user datagram protocol [UDP] H04L69/16)}
- H04M 1/72445: for supporting Internet browser applications
- H04M 3/493: Interactive information services, e.g. directory enquiries {; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals}
- H04M 2250/74: with voice recognition means
- H04M: TELEPHONIC COMMUNICATION (circuits for controlling other apparatus via a telephone cable and not involving telephone switching apparatus G08)

## Abstract

As a user interacts with a voice application, a history of the prompts played to the user and the users responses are displayed to the user. The displayed prompts and displayed responses could be summaries of the prompts and responses, or they could be full transcriptions of the prompts and responses. A user may be able to select a prompt or response in the history to return to a certain point in the voice application. It may be possible for a user to save a history of the interactions that occurred when a voice application was performed, and to recall the history to continue on from a selected location in the history.

## Claims

### Claim 1

A method of interacting with a user via an interactive voice response (IVR) application, comprising:
playing audio prompts for the user via an interactive voice response application, and recording information about the audio prompts played to the user;
receiving input from the user provided in response to the audio prompts and recording information about the user's responses to the audio prompts;
displaying to the user, on a display screen, a history of all of the audio prompts played to the user and all of the user responses, wherein each time that a new audio prompt is played to the user by the interactive voice response application, a prompt item including information about the new audio prompt is added to the displayed history, and wherein each time that the user provides a response to an audio prompt, a response item with information about the user's response is added to the displayed history;
receiving information indicating that the user has selected a displayed prompt item from the displayed history;
replaying to the user the audio prompt corresponding to the user selected prompt item;
receiving new input from the user provided in response to the replayed audio prompt, wherein the interactive voice response application acts on the received new input as if the user was responding to a first playing of the audio prompt corresponding to the user selected prompt item.

### Claim 2 (depends on 1)

The method of claim 1, wherein at least one of the response items in the displayed history includes information about the content of a user response to an audio prompt.

### Claim 3 (depends on 1)

The method of claim 1, wherein at least one of the response items in the displayed history includes at least a partial transcription of a user's spoken response to an audio prompt.

### Claim 4 (depends on 1)

The method of claim 1, wherein the prompt items and the response items are depicted in a different fashion in the displayed history.

### Claim 5 (depends on 1)

The method of claim 1, wherein receiving information indicating that the user has selected a displayed prompt item comprises receiving data generated by a user input device.

### Claim 6 (depends on 1)

The method of claim 1, wherein receiving information indicating that the user has selected a displayed prompt item comprises receiving data that was generated based on an interpretation of speech input provided by the user.

### Claim 7 (depends on 1)

The method of claim 1, further comprising:
receiving information indicating that the user has selected a displayed response item from the displayed history; and
receiving new input from the user that is to replace the user input that resulted in the user selected response item, wherein the interactive voice response application acts on the received new input as if the user was responding to a first playing of an audio prompt that resulted in the generation of the user selected response item.

### Claim 8 (depends on 7)

The method of claim 7, wherein receiving information indicating that the user has selected a displayed response item comprises receiving data generated by a user input device.

### Claim 9 (depends on 7)

The method of claim 7, wherein receiving information indicating that the user has selected a displayed response item comprises receiving data that was generated based on an interpretation of speech input provided by the user.

### Claim 10 (depends on 1)

The method of claim 1, further comprising displaying to the user on the display screen a plurality of selectable options, wherein the user can select each of the selectable options to cause the interactive voice application to perform various functions.

### Claim 11 (depends on 1)

The method of claim 1, further comprising storing a copy of the displayed history of prompt items and response items after the user finishes interacting with the interactive voice application.

### Claim 12 (depends on 1)

The method of claim 1, wherein receiving input from the user comprises receiving a spoken response from the user, the method further comprising:
interpreting the user's spoken response via speech recognition techniques, wherein the interpreting step includes generating a confidence value that is indicative of a level of confidence that the user's spoken response was correctly interpreted;
displaying to the user, when the confidence value does not rise above a threshold confidence value, a plurality of different potential interpretations of the user's spoken response; and
receiving data that indicates that the user selected one of the displayed potential interpretations of the user's spoken response, wherein the interactive voice response application then acts upon the user selected interpretation of the user's spoken response.

### Claim 13

A non-transitory computer readable medium bearing instructions which, when performed by one or more processors, cause the one or more processors to perform an interactive voice response application for a user, wherein performing the interactive voice response application includes the steps of:
playing audio prompts for the user via an interactive voice response application, and recording information about the audio prompts played to the user;
receiving input from the user provided in response to the audio prompts and recording information about the user's responses to the audio prompts;
displaying to the user, on a display screen, a history of all of the audio prompts played to the user and all of the user responses, wherein each time that a new audio prompt is played to the user by the interactive voice response application, a prompt item including information about the new audio prompt is added to the displayed history, and wherein each time that the user provides a response to an audio prompt, a response item with information about the user's response is added to the displayed history;
receiving information indicating that the user has selected a displayed prompt item from the displayed history;
replaying to the user the audio prompt corresponding to the user selected prompt item;
receiving new input from the user provided in response to the replayed audio prompt, wherein the interactive voice response application acts on the received new input as if the user was responding to a first playing of the audio prompt corresponding to the user selected prompt item.

### Claim 14 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein at least one of the response items in the displayed history includes information about the content of a user response to an audio prompt.

### Claim 15 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein at least one of the response items in the displayed history includes at least a partial transcription of a user's spoken response to an audio prompt.

### Claim 16 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the prompt items and the response items are depicted in a different fashion in the displayed history.

### Claim 17 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein receiving information indicating that the user has selected a displayed prompt item comprises receiving data generated by a user input device.

### Claim 18 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein receiving information indicating that the user has selected a displayed prompt item comprises receiving data that was generated based on an interpretation of speech input provided by the user.

### Claim 19 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the method performed by the one or more processors further comprises:
receiving information indicating that the user has selected a displayed response item from the displayed history; and
receiving new input from the user that is to replace the user input that resulted in the user selected response item, wherein the interactive voice response application acts on the received new input as if the user was responding to a first playing of an audio prompt that resulted in the generation of the user selected response item.

### Claim 20 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein receiving information indicating that the user has selected a displayed response item comprises receiving data generated by a user input device.

### Claim 21 (depends on 19)

The non-transitory computer readable medium of claim 19, wherein receiving information indicating that the user has selected a displayed response item comprises receiving data that was generated based on an interpretation of speech input provided by the user.

### Claim 22 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the method performed by the one or more processors further comprises displaying to the user on the display screen a plurality of selectable options, wherein the user can select each of the selectable options to cause the interactive voice application to perform various functions.

### Claim 23 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein the method performed by the one or more processors further comprises storing a copy of the displayed history of prompt items and response items after the user finishes interacting with the interactive voice application.

### Claim 24 (depends on 13)

The non-transitory computer readable medium of claim 13, wherein receiving input from the user comprises receiving a spoken response from the user, the method further comprising:
interpreting the user's spoken response via speech recognition techniques, wherein the interpreting step includes generating a confidence value that is indicative of a level of confidence that the user's spoken response was correctly interpreted;
displaying to the user, when the confidence value does not rise above a threshold confidence value, a plurality of different potential interpretations of the user's spoken response; and
receiving data that indicates that the user selected one of the displayed potential interpretations of the user's spoken response, wherein the interactive voice response application then acts upon the user selected interpretation of the user's spoken response.
