Systems and methods for providing a virtual assistant

• US 9,571,645 B2
• Filed: 12/16/2013
• Issued: 02/14/2017
• Est. Priority Date: 12/16/2013
• Status: Active Grant

• Current Assignee: Microsoft Technology Licensing LLC (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Quast, Holger, Smith, Kenneth W. D., Dahan, Jean-Guy E., Mauro, Andrew D.
• Primary Examiner(s): Huynh, Van D
• Application Number:
  US14/107,622
• Publication Number:
  US 20150172463A1
• Time in Patent Office: 1,156 Days
• Field of Search: 379/88.01, 379/93.24, 379/100.14, 379/88.13, 379/142.14, 379/265.01
• US Class Current: 1/1
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 50/40 Business processes related to the transportation industry shipping G06Q10/083
• CPC Class Codes: H04M 3/4936 Speech interaction details speech recognition per se G10L15/00

Abstract

A method for conducting a call between a caller and an interactive voice response (IVR) system, the caller using a device to conduct the call, the device configured to execute a virtual assistant, the method comprising using the virtual assistant to conduct the call at least in part by influencing the style of information provided to the caller during the call and/or the content of information passed between the device and the IVR system during the call.

Claims

1. A method for conducting a call between a caller and an interactive voice response (IVR) system, the method comprising:

receiving, by a virtual assistant executing on an electronic device, voice input from the caller, wherein the virtual assistant is configured to provide audio output to the caller based, at least in part, on the voice input;

accessing, by the virtual assistant, at least some information in a profile of the caller based, at least in part, on the received voice input; and

using the virtual assistant to conduct the call at least in part by influencing based, at least in part, on the accessed at least some information in the profile of the caller, a style of information provided to the caller by the virtual assistant during the call and/or a content of information passed between the electronic device and the IVR system during the call.

2. The method of claim 1,

wherein the profile comprises information specifying a virtual assistant persona;

wherein accessing at least some information in the profile comprises accessing information specifying the virtual assistant persona; and

wherein the virtual assistant conducts the call by influencing the style of information provided to the caller at least in part by adopting the virtual assistant persona when providing information received from the IVR system to the caller.

3. The method of claim 2, wherein the information specifying the virtual assistant persona at least partially specifies a voice font and/or a speaking style so that, when the virtual assistant adopts the virtual assistant persona, the virtual assistant is configured to provide information received from the IVR system to the caller at least in part by generating speech in accordance with the voice font and/or the speaking style.

4. The method of claim 1, further comprising:

receiving, from the IVR system, a request for information from the caller;

determining whether the virtual assistant has access to at least some of the requested information;

when it is determined that the virtual assistant has access to at least some of the requested information, providing the at least some of the requested information to the IVR system without prompting the caller to provide the at least some of the requested information; and

when it is determined that the virtual assistant does not have access to at least some of the requested information, prompting the caller to provide the at least some of the requested information.

5. The method of claim 4, wherein the request for information from the caller comprises a request for information identifying the caller, and wherein the determining whether the virtual assistant has access to at least some of the requested information comprises determining whether information identifying the caller is in a profile of the caller.

6. The method of claim 5, wherein the profile of the caller stores data reflecting the caller'"'"'s behavior in one or more prior calls with the IVR system, and wherein determining whether at least some of the requested information is in the profile of the caller comprises determining whether the data reflecting the caller'"'"'s behavior in or more prior calls with the IVR system includes the at least some of the requested information.

7. A device for use by a caller to conduct a call between the caller and an interactive voice response (IVR) system, the device comprising:

at least one processor configured to;

receive, by a virtual assistant executing on the device, voice input from the caller, wherein the virtual assistant is configured to provide audio output to the caller based, at least in part, on the voice input;

access, by the virtual assistant, at least some information in a profile of the caller based, at least in part, on the received voice input; and

use the virtual assistant to conduct the call at least in part by influencing based, at least in part, on the accessed at least some information in the profile of the caller, a style of information provided to the caller by the virtual assistant during the call and/or a content of information passed between the device and the IVR system during the call.

8. The device of claim 7,

wherein the profile comprises information specifying a virtual assistant persona;

wherein accessing at least some information in the profile comprises accessing information specifying the virtual assistant persona; and

wherein the virtual assistant conducts the call by influencing the style of information provided to the caller at least in part by adopting the virtual assistant persona when providing information received from the IVR system to the caller.

9. The device of claim 8, wherein the information specifying the virtual assistant persona at least partially specifies a voice font and/or a speaking style so that, when the virtual assistant adopts the virtual assistant persona, the virtual assistant is configured to provide information received from the IVR system to the caller at least in part by generating speech in accordance with the voice font and/or the speaking style.

10. The device of claim 7, wherein the at least one processor is further configured to perform acts of:

receiving, from the IVR system, a request for information from the caller;

determining whether the virtual assistant has access to at least some of the requested information;

when it is determined that the virtual assistant has access to at least some of the requested information, providing the at least some of the requested information to the IVR system without prompting the caller to provide the at least some of the requested information; and

when it is determined that the virtual assistant does not have access to at least some of the requested information, prompting the caller to provide the at least some of the requested information.

11. The device of claim 10, wherein the request for information from the caller comprises a request for information identifying the caller, and wherein the determining whether the virtual assistant has access to at least some of the requested information comprises determining whether information identifying the caller is in a profile of the caller.

12. The device of claim 11, wherein the profile of the caller stores data reflecting the caller'"'"'s behavior in one or more prior calls with the IVR system, and wherein determining whether at least some of the requested information is in the profile of the caller comprises determining whether the data reflecting the caller'"'"'s behavior in or more prior calls with the IVR system includes the at least some of the requested information.

13. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one processor, cause the at least one processor to perform a method for conducting a call between a caller and an interactive voice response (IVR) system, the method comprising:

receiving, by a virtual assistant executing on an electronic device, voice input from the caller, wherein the virtual assistant is configured to provide audio output to the caller based, at least in part, on the voice input;

accessing, by the virtual assistant, at least some information in a profile of the caller based, at least in part, on the received voice input; and

using the virtual assistant to conduct the call at least in part by influencing based, at least in part, on the accessed at least some information in the profile of the caller, a style of information provided to the caller by the virtual assistant during the call and/or a content of information passed between the electronic device and the IVR system during the call.

14. The at least one non-transitory computer-readable storage medium of claim 13,

wherein the profile comprises information specifying a virtual assistant persona;

wherein accessing at least some information in the profile comprises accessing information specifying the virtual assistant persona; and

wherein the virtual assistant conducts the call by influencing the style of information provided to the caller at least in part by adopting the virtual assistant persona when providing information received from the IVR system to the caller.

15. The at least one non-transitory computer-readable storage medium of claim 14, wherein the information specifying the virtual assistant persona at least partially specifies a voice font and/or a speaking style so that, when the virtual assistant adopts the virtual assistant persona, the first virtual assistant is configured to provide information received from the IVR system to the caller at least in part by generating speech in accordance with the voice font and/or the speaking style.

16. The at least one non-transitory computer-readable storage medium of claim 13, the method further comprising:

receiving, from the IVR system, a request for information from the caller;

determining whether the virtual assistant has access to at least some of the requested information;

when it is determined that the virtual assistant has access to at least some of the requested information, providing the at least some of the requested information to the IVR system without prompting the caller to provide the at least some of the requested information; and

when it is determined that the virtual assistant does not have access to at least some of the requested information, prompting the caller to provide the at least some of the requested information.

17. The at least one non-transitory computer-readable storage medium of claim 16, wherein the request for information from the caller comprises a request for information identifying the caller, and wherein the determining whether the virtual assistant has access to at least some of the requested information comprises determining whether information identifying the caller is in a profile of the caller.