Dynamic video generation in interactive voice response systems

• US 7,778,397 B2
• Filed: 03/10/2005
• Issued: 08/17/2010
• Est. Priority Date: 03/10/2005
• Status: Active Grant

• Current Assignee: Arlington Technologies, LLC (Dominion Harbor Enterprises, LLC)
• Original Assignee: Avaya Incorporated
• Inventors: Erhart, George William, Skiba, David Joseph, Matula, Valentine C.
• Primary Examiner(s): PATEL, HEMANT SHANTILAL
• Application Number:
  US11/076,597
• Publication Number:
  US 20060203977A1
• Time in Patent Office: 1,986 Days
• Field of Search: 370351-356, 379 8801- 8806, 379/88.13, 379/88.14, 379/88.17, 379/88.18, 379/201.01, 379/265.09, 455/414.1, 455/414.4, 700 86- 89, 704/270, 704/272, 704/277, 709201-203, 715203-204, 715/744
• US Class Current: 379/88.14
• CPC Class Codes: H04M 2201/50 Telephonic communication in combination with video communication
• CPC Class Codes: H04M 2203/253 where a visual mode is used instead of a voice mode
• CPC Class Codes: H04M 3/42314 in private branch exchanges
• CPC Class Codes: H04M 3/493 Interactive information services, e.g. directory enquiries ; Arrangements therefor, e.g. interactive voice response [IVR] systems or voice portals

Abstract

A method and apparatus are disclosed that enable an interactive voice response (IVR) system to generate video content in addition to audio content (e.g., synthesized speech, etc.). The video content is based on the state of the IVR system, the video display capacity of the calling telecommunications terminal, and information supplied by the user via a telecommunications terminal. The illustrative embodiment generates video content based on the text from which the audio content is generated. In particular, the video content comprises an abridged version of this text that is suitable for display at the telecommunications terminal. In the illustrative embodiment, the abridged version of the text is generated via syntactic and semantic processing. In addition, an abridged version of user-supplied information is generated and incorporated into the video content.

Claims

1. A method comprising generating video content during a call that involves an interactive voice response system and a telecommunications terminal, wherein said video content is based on

(i) one or more elements of a Voice eXtensible Markup Language document,

(ii) an estimate of the time remaining in the current state of a Voice eXtensible Markup Language application of said interactive voice response system, and

(iii) the video display capacity of said telecommunications terminal.

2. The method of claim 1 wherein said one or more elements of said Voice eXtensible Markup Language document comprises a text string from which said interactive voice response system generates audio content.

3. The method of claim 2 wherein generating said video content comprises generating an abridged version of said text string.

4. The method of claim 3 wherein generating said abridged version of said text string comprises syntactic processing.

5. The method of claim 4 wherein said syntactic processing is based on a grammar that is specified by a uniform resource identifier in said Voice Extensible Markup Language document.

6. The method of claim 3 wherein generating said abridged version of said text string comprises semantic processing.

7. The method of claim 1 wherein said video content is also based on the time spent in said state of said Voice eXtensible Markup Language application.

8. The method of claim 1 wherein said video content is also based on information input to said interactive voice response system during said call.

9. A method comprising:

(a) receiving a datum that is input via a telecommunications terminal during a call that involves an interactive voice response system and said telecommunications terminal;

(b) when the video display capacity of said telecommunications terminal is below a threshold, generating video content that contains an abridged version of said datum, and

otherwise, generating video content that contains an unabridged version of said datum; and

(c) presenting said video content at said telecommunications terminal.

10. The method of claim 9 wherein said abridged version of said datum is generated via syntactic processing.

11. The method of claim 9 wherein said abridged version of said datum is generated via semantic processing.

12. The method of claim 9 wherein said video content is also based on the state of said interactive voice response system.

13. The method of claim 9 wherein said video content is based on one or more elements of a Voice eXtensible Markup Language document, and wherein said one or more elements of said Voice eXtensible Markup Language document comprises a text string from which said interactive voice response system generates audio content.

14. A method comprising:

(a) receiving at a data-processing system a datum that is input via a telecommunications terminal during a call;

(b) generating a new state for said data-processing system based on the prior state of said data-processing system and on said datum;

(c) generating audio content based on a text string that is associated with said new state; and

(d) when the video display capacity of said telecommunications terminal is below a threshold, generating video content that is based on said new state, said text string, and an abridged version of said datum, and

otherwise, generating video content that is based on said new state, said text string, and an unabridged version of said datum.

15. The method of claim 14 wherein said abridged version of said datum is generated via syntactic processing.

16. The method of claim 15 wherein said text string is part of a Voice Extensible Markup Language document, and wherein said syntactic processing is based on a grammar that is specified by a uniform resource identifier in said Voice Extensible Markup Language document.

17. The method of claim 14 wherein said abridged version of said datum is generated via semantic processing.