Systems and methods for providing a virtual assistant

• US 9,804,820 B2
• Filed: 12/16/2013
• Issued: 10/31/2017
• Est. Priority Date: 12/16/2013
• Status: Expired due to Fees

• Current Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Original Assignee: Nuance Communications, Inc. (Microsoft Corporation)
• Inventors: Quast, Holger, Radebaugh, Carey, Brown, Sean P., Harper, Kenneth S., Wyatt, Andrew R.
• Primary Examiner(s): Serrou, Abdelali
• Application Number:
  US14/107,499
• Publication Number:
  US 20150169284A1
• Time in Patent Office: 1,415 Days
• CPC Class Codes: G06F 16/9535 Search customisation based on user profiles and personalisation
• CPC Class Codes: G06F 3/01 Input arrangements or combined input and output arrangements for interaction between user and computer G06F3/16 takes precedence
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06Q 10/10 Office automation; Time management
• CPC Class Codes: G06Q 30/0269 based on user profile or attribute
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue

Abstract

A system comprising at least one processor configured to perform: receiving a first request to access a first user profile of a first user from a first device configured to execute a first virtual assistant to interact with the first user; in response to receiving the first request, providing the first device with access to information in the first user profile so that the first virtual assistant is able to customize, based on the accessed information, its behavior when interacting with the first user; receiving a second request to access the first user profile from a second device configured to execute a second virtual assistant to interact with the first user; and in response to receiving the second request, providing the second device with access to the information so that the second virtual assistant is able to customize, based on the accessed information, its behavior when interacting with the first user.

Claims

1. A system for providing a consistent virtual assistant experience for a user between different devices, the system comprising:

at least one computer-readable storage medium configured to store a plurality of user profiles including a first user profile of a first user, the first user profile comprising information specifying a first virtual assistant persona; and

at least one processor, coupled to the at least one computer-readable storage medium, configured to perform acts of;

receiving a first request to access the first user profile from a first device of the first user, the first device being configured to execute a first virtual assistant to interact with the first user;

in response to receiving the first request, providing the first device with access to at least some information in the first user profile, including the information specifying the first virtual assistant persona, such that the first virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein the information specifying the first virtual assistant persona specifies speech generation settings including a voice font and/or speaking style so that, when the first virtual assistant adopts the first virtual assistant persona, the first virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

after receiving the first request, receiving a second request to access the first user profile from a second device of the first user, the second device being configured to execute a second virtual assistant to interact with the first user, the second device being different from the first device;

in response to receiving the second request, providing the second device with access to the at least some information, including the information specifying the first virtual assistant persona, such that the second virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein when the second virtual assistant adopts the first virtual assistant persona, the second virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information,

wherein the information related to the task being performed by the first device specifies what portion of the task has been performed by the first device.

2. The system of claim 1, wherein the at least one processor is further configured to perform acts of:

updating the first user profile based on information provided by the first user via the first device; and

providing the second device with access to the updated first user profile so that the second virtual assistant customizes, based on at least some updated information in the updated first user profile, the behavior of the second virtual assistant behavior when interacting with the first user.

3. The system of claim 1, wherein at least one processor is configured to perform acts of:

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information.

4. The system of claim 3, wherein the information related to the task being performed by the first device specifies what portion of the task has been performed by the first device.

13. The system of claim 1, wherein the information specifying the first virtual assistant persona specifies a voice font so that the first virtual assistant and the second virtual assistant both use the voice font to generate speech when interacting with the first user upon having adopted the first virtual assistant persona.

5. A method for providing a consistent virtual assistant experience for a user between different devices, the method comprising:

using at least one processor to perform acts of;

receiving a first request to access a first user profile of a first user from a first device of the first user, the first device being configured to execute a first virtual assistant to interact with the first user, the first user profile comprising information specifying a first virtual assistant persona;

in response to receiving the first request, providing the first device with access to at least some information in the first user profile, including the information specifying the first virtual assistant persona, such that the first virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein the information specifying the first virtual assistant persona specifies speech generation settings including a voice font and/or speaking style such that, when the first virtual assistant adopts the first virtual assistant persona, the first virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

after receiving the first request, receiving a second request to access the first user profile from a second device of the first user, the second device being configured to execute a second virtual assistant to interact with the first user, the second device being different from the first device;

in response to receiving the second request, providing the second device with access to the at least some information, including the information specifying the first virtual assistant persona, such that the second virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein when the second virtual assistant adopts the first virtual assistant persona, the second virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information,

wherein the information related to the task being performed by the first device specifies what portion of the task has been performed by the first device.

6. The method of claim 5, wherein the information specifying the first virtual assistant persona specifies a voice font so that the first virtual assistant and the second virtual assistant both use the voice font to generate speech when interacting with the first user upon having adopted the first virtual assistant persona.

7. The method of claim 5, wherein the method further comprises using the at least one processor to perform acts of:

updating the first user profile based on information provided by the first user via the first device; and

providing the second device with access to the updated first user profile so that the second virtual assistant customizes, based on at least some updated information in the updated first user profile, the behavior of the second virtual assistant when interacting with the first user.

8. The method of claim 5, wherein the method further comprises using the at least one processor to perform acts of:

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information.

9. The method of claim 8, wherein the information related to the task being performed by the first device specifies what portion of the task has been performed by the first device.

10. 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 providing a consistent virtual assistant experience for a user between different devices, the method comprising:

receiving a first request to access a first user profile of a first user from a first device of the first user, the first device being configured to execute a first virtual assistant to interact with the first user, the first user profile comprising information specifying a first virtual assistant persona;

in response to receiving the first request, providing the first device with access to at least some information in the first user profile, including the information specifying the first virtual assistant persona, such that the first virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein the information specifying the first virtual assistant persona specifies speech generation settings including a voice font and/or speaking style so that, when the first virtual assistant adopts the first virtual assistant persona, the first virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

after receiving the first request, receiving a second request to access the first user profile from a second device of the first user, the second device being configured to execute a second virtual assistant to interact with the first user, the second device being different from the first device;

in response to receiving the second request, providing the second device with access to the at least some information, including the information specifying the first virtual assistant persona, such that the second virtual assistant is configured to customize, based on the at least some accessed information, its behavior when interacting with the first user at least in part by adopting the first virtual assistant persona when interacting with the first user, wherein when the second virtual assistant adopts the first virtual assistant persona, the second virtual assistant is configured to generate speech using the voice font and/or speaking style of the speech generation settings when interacting with the first user;

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information,

wherein the information related to the task being performed by the first device specifies what portion of the task has been performed by the first device.

11. The at least one non-transitory computer-readable storage medium of claim 10, wherein the method further comprises:

updating the first user profile based on information provided by the first user via the first device; and

providing the second device with access to the updated first user profile so that the second virtual assistant customizes, based on at least some updated information in the updated first user profile, the behavior of the second virtual assistant when interacting with the first user.

12. The at least one non-transitory computer-readable storage medium of claim 10, wherein the method further comprises:

receiving, from the first device, information related to a task being performed at least in part by using the first device;

determining whether performance of the task is to be continued at least in part by using the second device instead of the first device; and

when it is determined that the performance of the task is to be continued at least in part by using the second device, providing the second device with access to the received information.

14. The at least one non-transitory computer-readable storage medium of claim 10, wherein the information specifying the first virtual assistant persona specifies a voice font so that the first virtual assistant and the second virtual assistant both use the voice font to generate speech when interacting with the first user upon having adopted the first virtual assistant persona.