Graphical user interface for creating content for a voice-user interface

• US 7,395,505 B1
• Filed: 03/17/2003
• Issued: 07/01/2008
• Est. Priority Date: 03/17/2003
• Status: Expired due to Fees

• Current Assignee: West Interactive Services Corporation (West Corporation)
• Original Assignee: TuVox, Inc. (West Corporation)
• Inventors: Pollock, Steven Samuel, Khosla, Ashok Mitter
• Primary Examiner(s): Vu; Kieu D.
• Assistant Examiner(s): Bonshock; Dennis G.
• Application Number:
  US10/391,145
• Time in Patent Office: 1,933 Days
• Field of Search: 715/705, 715/729, 715/712, 715/713, 715/727
• US Class Current: 715/727
• CPC Class Codes: G06F 3/16 Sound input; Sound output speech processing G10L
• CPC Class Codes: G06F 8/38 for implementing user interfaces
• CPC Class Codes: G10L 15/26 Speech to text systems G10L15/08 takes precedence

Abstract

In one embodiment, the invention provides a method for creating a voice application, the method being implemented by a computer system and comprising generating a graphical user interface comprising a text-to-topic button; receiving first input identifying a location of a text file; receiving second input selecting the text-to-topic button; partitioning content associated with the text file into subjects in response to receiving the second input; and storing information on the partitioning.

Claims

1. A method for creating a voice application, the method being implemented by a computer system, and comprising:

generating a graphical user interface comprising a text-to-topic button;

receiving first input identifying a location of a text file comprising natural language content to be partitioned into subjects;

receiving second input selecting the text-to-topic button;

partitioning the natural language content in the text file into subjects in response to receiving the second input;

wherein a granularity of the partitioning is based on an adjustable displayed parameter to control the granularity of the partitioning into subjects;

storing information on the partitioning; and

wherein the partitioning further comprises structuring the content associated with each subject into a pseudo-conversation with questions and answers.

2. The method of claim 1, wherein partitioning the text comprises associating a subject identifier with each subject.

3. The method of claim 2, further the comprising displaying the subject identifiers and their associated subjects.

4. The method of claim 3, wherein the partitioning comprises grouping the subjects into groups.

5. The method of claim 4, wherein the graphical user interface provides two views, wherein in a first of the two views only the subject groups are visible, the subject identifiers and their associated subjects being hidden, and in the second of the two views the subject identifiers and their associated subjects are additionally displayed;

and a selection mechanism to cause the graphical user interface to change to either of the two views.

6. The method of claim 5, wherein the graphical user interface provides an editor view in which tags associated with content for a subject are displayed;

and a selection mechanism to cause the graphical user interface to change to the editor view.

7. The method of claim 6, further comprising receiving third input selecting a predefined tag;

and displaying the predefined tag on a command area in the editor view;

receiving fourth input including text; and

associating the text with the selected predefined tag.

8. The method of claim 7, wherein the editor view comprises two sub-views, wherein in a first of the two sub-views only tag groupings for the predefined tags are displayed, the content of the tag groupings being hidden from view, and wherein in a second of the two sub-views the tag groupings and the content of the tag groupings are displayed, the graphical user interface then providing a selection mechanism to cause the graphical user interface to change to either of the two sub-views.

9. The method of claim 6, wherein the graphical user interface provides a view comprising a listing of subject topics and subject topic identifiers, said view being normally hidden from view and being accessible from the editor view via a selection mechanism.

10. The method of claim 1, wherein the graphical user interface further comprises a prompt style review button, which when selected causes prompts associated with each topic to be assessed for understandability, and a result of the assessment to be displayed.

11. The method of claim 1, wherein the graphical user interface further comprises a record audio button which when selected causes the system to switch to an audio record mode in which audio associated with a prompt is received by the system and linked to the prompt.

12. The method of claim 11, wherein the graphical user interface provides an indicator to indicate prompts for which no recorded audio exists.

13. The method of claim 12, further comprising automatically providing a warning whenever a prompt for which audio was recorded is changed.

14. The method of claim 1 wherein the graphical user interface further provides a glossary view in which a glossary of anticipated responses for a given prompt is displayed;

and a selection mechanism to select the glossary view.

15. The method of claim 14, wherein the glossary view comprises a shorthand representation for the glossary of anticipated responses.

16. The method of claim 1 further comprising generating a tagged file comprising content to be played by the voice user interface, wherein different components of the content are identified by tags in a markup language.

17. The method of claim 16, wherein the graphical user interface further provides a view to display a content of the tagged file;

and a selection mechanism to select the said view.

18. The method of claim 16, wherein the graphical user interface further comprises a code input mode wherein an editor is provided to allow a user to input code to perform a required function, the system then saving the function and linking it to a location in the tagged file at which the function is called;

and a mechanism to switch to the code input mode.

19. The method of claim 17, wherein the graphical user interface further comprises a glossary review button which when selected causes the system to perform a review of the glossary for errors and conflicts, and to display a result of the review.

20. The method of claim 1, wherein the graphical user interface further comprises a create navigation topic button which when selected causes the system to generate navigation topics associated with the content and to display same.

21. A computer readable medium having stored thereon a sequence of instructions which when executed by a computer, causes the computer to perform a method comprising:

generating a graphical user interface comprising a text to topic button;

receiving first input identifying a location of a text file comprising natural language content to be partitioned into subjects;

receiving second input selecting the text to topic button;

partitioning the natural language text file into subjects in response to receiving the second input;

wherein a granularity of the partitioning is based on an adjustable displayed parameter to control the granularity of the partitioning into subjects;

storing information on the partitioning; and

wherein the partitioning further comprises structuring the content associated with each subject into a pseudo-conversation with questions and answers.

22. The computer readable medium of claim 21, wherein partitioning the text comprises associating a subject topic identifiable with each subject.

23. A system for creating a voice application, the system comprising:

a processor; and

a memory coupled to the processor, the memory storing instructions which when executed by the processor causes the system to perform a method for creating a voice application, the method comprising;

generating a graphical user interface comprising a text-to-topic button;

receiving first input identifying a location of a text file comprising natural language text;

receiving second input selecting the text-to-topic button;

partitioning the natural language in the text file into subjects in response to receiving the second input;

wherein a granularity of the partitioning is based on an adjustable displayed parameter to control the granularity of the partitioning into subjects;

storing information on the partitioning; and

wherein the partitioning further comprises structuring a content associated with each subject into a pseudo-conversation with questions and answers.

24. The system of claim 23, wherein partitioning the text comprises associating a subject topic identifier with each subject.