Voice-activated customer service assistant

• US 9,275,632 B1
• Filed: 03/19/2014
• Issued: 03/01/2016
• Est. Priority Date: 03/19/2014
• Status: Active Grant

• Current Assignee: West Technology Group LLC (West Corporation)
• Original Assignee: West Corporation
• Inventors: McCobb, Gerald M., Stirk, David
• Primary Examiner(s): Cordero, Marivelisse Santiago
• Assistant Examiner(s): Brinich, Stephen M
• Application Number:
  US14/219,175
• Time in Patent Office: 713 Days
• Field of Search: 704257-258, 704/275, 704/270.1, 704/246, 704/270, 704/261, 704/231, 704/E15.045, 704/E15.039, 379/88.01, 379/88.22, 379/88.02
• US Class Current: 1/1
• CPC Class Codes: G06Q 30/016 After-sales
• CPC Class Codes: G10L 13/00 Speech synthesis; Text to speech systems
• CPC Class Codes: G10L 13/027 Concept to speech synthesisers; Generation of natural phrases from machine-based concepts generation of parameters for speech synthesis out of text G10L13/08
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 17/22 Interactive procedures; Man-machine interfaces
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

A method, apparatus and non-transitory computer readable storage medium, in one embodiment, interpreting at least one input from a user via a wireless device, receiving at least one user account with the at least one input, deriving at least one representation of user intent, identifying at least one task based on the at least one representation of user intent, contacting at least one service to perform the identified at least one task and synthesizing speech to communicate a result of the contact to the wireless device.

Claims

1. A method, comprising:

interpreting at least one input from a user via a wireless device;

receiving at least one user account with said at least one input;

deriving at least one representation of user intent;

identifying at least one task based on said at least one representation of user intent;

contacting at least one service to perform the identified at least one task; and

synthesizing speech to communicate a result of said contact to said wireless device;

comprising testing to communicate said result of said contact to said wireless device;

wherein said identifying is based on voice biometerics.

2. The method of claim 1 further comprising authorizing said received at least one user account.

3. The method of claim 2 further comprising authorizing said at least one customer service account.

4. The method of claim 1, further comprising inputting a response based on the communicated result.

5. The method of claim 1 wherein said interpreting at least one input is based on at least one text input.

6. The method of claim 1 wherein said interpreting at least one input is based on at least one speech input.

7. The method of claim 1 wherein contacting at least one service is to a customer service data center.

8. The method of claim 1 wherein said result of said contact to said wireless device is a set of alternatives.

9. An apparatus, comprising:

a memory, and

a processor configured to

interpret at least one input from a user via a wireless device;

receiving at least one user account with said at least one input;

derive at least one representation of user intent;

identify, based on voice biometrics, at least one task based on said at least one representation of user intent;

contact at least one service to perform the identified at least one task; and

synthesize speech to communicate a result of said contact to said wireless device;

texts to communicate said results of said contact to said wireless device.

10. The apparatus of claim 9 wherein said processor further authorizes said at least one user account.

11. The apparatus of claim 10 wherein said processor further authorizes said at least one customer service account.

12. The apparatus of claim 9 wherein said processor further inputs a response based on the communicated result.

13. A non-transitory computer readable storage medium configured to store instructions that when executed causes a processor to perform:

interpreting at least one input from a user via a wireless device;

receiving at least one user account with said at least one input;

deriving at least one representation of user intent;

identifying at least one task based on said at least one representation of user intent;

contacting at least one service to perform the identified at least one task; and

synthesizing speech to communicate a result of said contact to said wireless device;

comprising texting to communicate said results of said contact to said wireless device;

wherein said identifying based on voice biometrics.

14. The non-transitory computer readable storage medium of claim 13, wherein said interpreting at least one input is based on at least one text input.

15. The non-transitory computer readable storage medium of claim 13, wherein said interpreting at least one input is based on at least one speech input.

16. The non-transitory computer readable storage medium of claim 13, wherein contacting at least one service is to a customer service data center.