IP Library › Granted Patent US 9,313,329
Granted Patent B2
US 9,313,329 · App. 12/610,646 · Granted Apr 12, 2016

Voice response systems browsing

Inventors: Peter J. Andrews (Mahopac, NY); Alexander Faisman (Croton-on-Hudson, NY); Genady Grabarnik (Scarsdale, NY); Larisa Shwartz (Scarsdale, NY)
Assignee: International Business Machines Corporation
H04M3/493H04M1/72591H04M3/42391H04M3/533H04M11/066H04M2250/74
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 9,313,329
App. No.
12/610,646
Granted
Apr 12, 2016
Kind
B2
Abstract

A method for voice browsing an integrated voice response server is described. The method includes visually displaying a representation of a choice tree for a service, where the service includes an audio menu of available actions. A selection of an action displayed in the representation is received. The method also includes automatically navigating the audio menu in order to initiate the selected action. Apparatus and computer readable media are also described.

Claims (87)

1. A method performed by a data processor that executes computer program code stored in a non-transitory computer readable media to perform a series of operations, the operations comprising:

visually displaying a graphical representation of a telephone query tree that comprises a multi-stage audio menu of a service,

where the displayed graphical representation comprises a plurality of available actions configured to be selectable by a user who calls the service,

where each stage of the multi-stage audio menu is associated with a list of choices presented audibly,

where each list of choices comprises at least one of:

a choice to perform one of the available actions and a choice to navigate to another stage of the multi-stage audio menu,

where the graphical representation of the telephone query tree comprises a root node, a plurality of interior nodes and at least one leaf node,

where the root node indicates an initial point of the user's communication with the service,

where each interior node is associated with a stage in the multi-stage audio menu, and

where each leaf node is associated with one of:

an available action that ends the user's call to the service or an available action that requires user attention;

receiving, at the data processor, a selection of a leaf node made by the user; and

determining, by the data processor, a series of choices which result in navigating through the multi-stage audio menu in order to initiate the available action associated with the selected leaf node;

navigating, by the data processor on behalf of the user, the audio menu in accordance with the determined series of choices, and

one of, confirming to the user a completion of the navigation of the audio menu on behalf of the user, and connecting, based on the completion of the navigation, the user to a representative of the service,

where determining the series of choices and navigating comprise translating the user's selection to appropriate voice signals and tone signals and transmitting the voice signals and tone signals to the service.

2. The method of claim 1 , where the operations further comprise:

initiating, by the data processor, contact with the service; and

navigating, by the data processor, through the audio menu in order to identify a structure of the audio menu and all actions available via the audio menu.

3. The method of claim 2 , where identifying the structure of the audio menu comprises:

receiving, at the data processor, an audio message comprising an identification of available choices;

performing, by the data processor, voice recognition on the audio message in order to identify the available choices; and

analyzing, by the data processor, the available choices in order to determine the structure of the audio menu and the available actions.

4. The method of claim 2 , where identifying the structure of the audio menu comprises receiving a message signal comprising an identification of the structure of the audio menu and the available actions.

5. The method of claim 1 , where navigating the audio menu comprises:

in response to receiving a prompt for a selection of a choice from the audio menu, generating, by a computer, a response; and

transmitting the response.

6. The method of claim 5 , where the response is an audio message.

7. The method of claim 1 , where navigating the audio menu comprises, in response to the selected action being initiated, alerting a user.

8. The method of claim 1 , where visually displaying the graphical representation of the telephone query tree comprises visually displaying the graphical representation on a screen associated with a telephony device.

9. The method of claim 1 , where the operations further comprise:

receiving, by the data processor, an audio message comprising an identification of available choices for a stage in the multi-stage audio menu;

performing, by the data processor, voice recognition on the audio message in order to identify the available choices for the stage in the audio menu;

for each available choice, selecting, by the data processor, the available choice and converting, by the data processor, a voice message for the available choice into a text message;

analyzing, by the data processor, the available choices in order to determine the structure of the audio menu; and

generating, by the data processor, a representation of the telephone query tree based on the determined structure, where the representation comprises the text message for each of the available choices.

10. An apparatus comprising:

a display configured to visually display a graphical representation of a telephone query tree that comprises a multi-stage audio menu of a service,

where the displayed graphical representation comprises a plurality of available actions configured to be selectable by a user who calls the service,

where each stage of the multi-stage audio menu is associated with a list of choices presented audibly,

where each list of choices comprises at least one of: a choice to perform one of the available actions and a choice to navigate to another stage of the multi-stage audio menu,

where the graphical representation of the telephone query tree comprises a root node, a plurality of interior nodes and at least one leaf node,

where the root node indicates an initial point of the user's communication with the service,

where each interior node is associated with a stage in the multi-stage audio menu, and

where each leaf node is associated with one of:

an available action that ends the user's call to the service or an available action that requires user attention;

an input configured to receive a selection of a leaf node made by the user;

a processor configured to determine a series of choices which result in navigating through the multi-stage audio menu on behalf of the user in order to initiate the available action associated with the selected leaf node and to navigate, on behalf of the user, the audio menu in accordance with the determined series of choices, and

one of, confirming to the user a completion of the navigation of the audio menu on behalf of the user, and connecting, based on the completion of the navigation of the audio menu by the data processor, the user to a representative of the service,

where the processor determining the series of choices which result in navigating through the multi-stage menu comprises the processor translating the user's selection to appropriate voice signals and tone signals and transmitting the voice signals and tone signals to the service.

11. The apparatus of claim 10 , further comprising an interface configured:

to initiate contact with the service; and

to navigate through the audio menu in order to identify a structure of the audio menu and all actions available via the audio menu.

12. The apparatus of claim 10 , further comprising an interface configured:

to receive an audio message comprising an identification of available choices, via the interface;

to perform voice recognition on the audio message in order to identify the available choices; and

to analyze the available choices in order to determine the structure of the audio menu and the available actions.

13. The apparatus of claim 10 , where the processor is configured, in response to determining the selected action being initiated, to alert a user.

14. A non-transitory computer readable medium tangibly encoded with a computer program executable by a processor to perform operations comprising:

visually displaying a graphical representation of a telephone query tree that comprises a multi-stage audio menu of a service,

where the displayed graphical representation comprises a plurality of available actions configured to be selectable by a user who calls the service,

where each stage of the multi-stage audio menu is associated with a list of choices presented audibly,

where each list of choices comprises at least one of:

a choice to perform one of the available actions and a choice to navigate to another stage of the multi-stage audio menu,

where the graphical representation of the telephone query tree comprises a root node, a plurality of interior nodes and at least one leaf node,

where the root node indicates an initial point of the user's communication with the service, where each interior node is associated with a stage in the multi-stage audio menu, and

where each leaf node is associated with one of:

an available action that ends the user's call to the service or an available action that requires user attention;

receiving, at the data processor, a selection of a leaf node made by the user; and

determining, by the data processor, a series of choices which result in navigating through the multi-stage audio menu in order to initiate the available action associated with the selected leaf node;

navigating, by the data processor on behalf of the user, the audio menu in accordance with the determined series of choices, and

one of, confirming to the user a completion of the navigation of the audio menu on behalf of the user, and connecting, based on the completion of the navigation, the user to a representative of the service,

where determining the series of choices and navigating comprise translating the user's selection to appropriate voice signals and tone signals and transmitting the voice signals and tone signals to the service.

15. The computer readable medium of claim 14 , where the operations further comprise:

querying a storage repository to determine if the repository contains the representation of the telephone query tree and, if it does not, then

initiating contact with the service and generating the representation of the telephone query tree based on audio messages received from the service when presenting the multi-stage audio menu.

16. The computer readable medium of claim 15 , where:

initiating contact with the service comprises calling the service to initiate voice contact with the service; and

navigating through the audio menu in order to identify a structure of the audio menu and all actions available via the audio menu.

17. The computer readable medium of claim 16 , where identifying the structure of the audio menu comprises:

receiving an audio message comprising an identification of available choices;

performing voice recognition on the audio message in order to identify the available choices; and

analyzing the available choices in order to determine the structure of the audio menu and the available actions.

18. The computer readable medium of claim 14 , where navigating the audio menu comprises:

in response to receiving a prompt for a selection of a choice from the audio menu, generating, by the data processor, a response; and

transmitting the response.

19. The computer readable medium of claim 14 , where navigating the audio menu comprises, in response to the selected action being initiated, alerting a user.

Assignments (4)
CORRECTION TO CORRECT THE NOTICE OF RECORDATION OF ASSIGNMENT DOCUMENT RECORDED 11/03/2009, AT REEL 023463, FRAME 0843. THE CORRECT SPELLING OF THE 3RD LISTED INVENTOR'S NAME IS GENADY GRABARNIK. Recorded Dec 29, 2009
From: ANDREWS, PETER J.; FAISMAN, ALEXANDER; GRABARNIK, GENADY; SCHWARTZ, LARISA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 023721/0302 →
TO CORRECT THE NOTICE OF RECORDATION OF ASSIGNMENT DOCUMENT RECORDED 11/03/2009, AT REEL 023463, FRAME 0843. THE CORRECT SPELLING OF THE 3RD LISTED INVENTOR'S NAME IS GENADY GRABARNIK. Recorded Dec 29, 2009
From: ANDREWS, PETER J.; FAISMAN, ALEXANDER; GRABARNIK, GENADY; SCHWARTZ, LARISA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 023721/0822 →
TO CORRECT THE NOTICE OF RECORDATION OF ASSIGNMENT DOCUMENT RECORDED 11/03/2009, AT REEL 023463, FRAME 0843. THE CORRECT SPELLING OF THE 3RD LISTED INVENTOR'S NAME IS GENADY GRABARNIK. Recorded Nov 27, 2009
From: ANDREWS, PETER J.; FAISMAN, ALEXANDER; GRABARNIK, GENADY; SHWARTZ, LARISA
To: INTERNATIONAL BUSINESS MACHINES CORPORATI0N
Reel/Frame 023721/0294 →
ASSIGNMENT OF ASSIGNOR'S INTEREST Recorded Nov 3, 2009
From: ANDREWS, PETER J.; FAISMAN, ALEXANDER; GRABARAIK, GENARDY; SHWARTZ, LARISA
To: INTERNATIONAL BUSINESS MACHINES CORPORATION
Reel/Frame 023463/0843 →
Continuity (1)
Related Publication 20110103559A1 · May 5, 2011