Systems and methods for providing a virtual assistant

• US 10,534,623 B2
• Filed: 12/16/2013
• Issued: 01/14/2020
• 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: Harper, Kenneth S., Jaradeh, Fares, Quast, Holger, Radebaugh, Carey, Brown, Sean P.
• Primary Examiner(s): Chowdhury, Rayeez R
• Application Number:
  US14/107,545
• Publication Number:
  US 20150169336A1
• Time in Patent Office: 2,220 Days
• CPC Class Codes: G06F 3/048 Interaction techniques based on graphical user interfaces [GUI]
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G06F 9/453 Help systems
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/0631 Item recommendations
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: H04L 67/10 in which an application is distributed across nodes in the network software deployment G06F8/60; multiprogramming arrangements G06F9/46

Abstract

A method, performed by at least one computer, the method comprising using the at least one computer to perform acts of accessing information specifying at least one user-specified condition specified by a user and at least one corresponding user-specified action, the user-specified action to be performed when the user-specified condition is met; determining whether the at least one user-specified condition is met; and when it is determined that the at least one user-specified condition is met, causing a virtual assistant executing on a mobile device different from the at least one computer to perform the at least one user-specified action.

Claims

1. A method comprising:

using at least one computer to perform acts of;

accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic;

in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and

after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user;

selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic;

receiving first voice input of the user including a request for additional information about the topic;

processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition.

2. The method of claim 1, further comprising monitoring and/or searching one or more sources of information to obtain the information related to the topic.

3. The method of claim 1, wherein the virtual assistant is configured to perform the at least one corresponding user-specified action at least in part by using another application program configured to execute on the mobile device.

4. The method of claim 1, further comprising:

receiving, from the user, second voice input specifying the at least one user-specified condition and the at least one corresponding user-specified action; and

identifying, at least in part by using automatic speech recognition, the at least one user-specified condition and the at least one corresponding user-specified action specified by the second voice input.

13. The method of claim 1, wherein the topic-dependent language model is tailored to recognition of speech containing words and/or phrases for the topic specified by the at least one user-specified condition.

16. The method of claim 1, wherein accessing the information and causing the virtual assistant executing on the mobile device to perform the at least one corresponding user-specified action are performed proactively by the at least one computer.

17. The method of claim 1, wherein accessing the information and causing the virtual assistant executing on the mobile device to perform the at least one corresponding user-specified action are not performed in response to receiving, from the mobile device, input from the user related to the topic.

18. The method of claim 1, further comprising:

in response to processing the first voice input, causing the virtual assistant to present a response to the request for additional information about the topic to the user at least in part by providing the response to the mobile device.

5. A system comprising:

at least one computer configured to perform acts of;

accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic;

in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and

after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user;

selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic;

receiving first voice input of the user including a request for additional information about the topic;

processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition.

6. The system of claim 5, wherein the at least one computer is further configured to perform monitoring and/or searching of one or more sources of information to obtain the information related to the topic.

7. The system of claim 5, wherein the virtual assistant is configured to perform the at least one action at least in part by using another application program configured to execute on the mobile device.

8. The system of claim 5, wherein the at least one computer is further configured to perform acts of:

receiving, from the user, second voice input specifying the at least one user-specified condition and the at least one corresponding user-specified action; and

identifying, at least in part by using automatic speech recognition, the at least one user-specified condition and the at least one corresponding user-specified action specified by the second voice input.

14. The system of claim 5, wherein the topic-dependent language model is tailored to recognition of speech containing words and/or phrases for the topic specified by the at least one user-specified condition.

19. The system of claim 5, wherein the at least one computer is further configured to:

in response to processing the first voice input, causing the virtual assistant to present a response to the request for additional information about the topic to the user at least in part by providing the response to the mobile device.

9. At least one non-transitory computer-readable storage medium storing processor-executable instructions that, when executed by at least one computer, cause the at least one computer to perform a method comprising acts of:

accessing information specifying at least one user-specified condition and at least one corresponding user-specified action to be performed when the at least one user-specified condition is met, wherein the at least one user-specified condition specifies a topic and the at least one corresponding user-specified action comprises outputting for presentation to a user information related to the topic;

in response to determining that obtained information related to the topic meets the at least one user-specified condition, causing a virtual assistant executing on a mobile device to perform the at least one corresponding user-specified action, wherein performing the at least one corresponding user-specified action comprises outputting, by the virtual assistant, at least some of the obtained information related to the topic for presentation to a user via the mobile device; and

after causing the virtual assistant to output the at least some of the obtained information related to the topic to the user;

selecting a topic-dependent language model, from among a plurality of language models, based on the topic specified by the at least one user-specified condition that was met by the obtained information, wherein the topic-dependent language model is specifically adapted for recognition of input related to the topic;

receiving first voice input of the user including a request for additional information about the topic;

processing the first voice input using automatic speech recognition techniques at least in part by using the topic-dependent language model for the topic specified by the at least one user-specified condition.

10. The at least one non-transitory computer-readable storage medium of claim 9, the method further comprising monitoring and/or searching one or more sources of information to obtain the information related to the topic.

11. The at least one non-transitory computer-readable storage medium of claim 9, wherein the virtual assistant is configured to perform the at least one action at least in part by using another application program configured to execute on the mobile device.

12. The at least one non-transitory computer-readable storage medium of claim 9, the method further comprising:

receiving, from the user, second voice input specifying the at least one user-specified condition and the at least one corresponding user-specified action; and

identifying, at least in part by using automatic speech recognition, the at least one user-specified condition and the at least one corresponding user-specified action specified by the second voice input.

15. The at least one non-transitory computer-readable storage medium of claim 9, wherein the topic-dependent language model is tailored to recognition of speech containing words and/or phrases for the topic specified by the at least one user-specified condition.

20. The at least one non-transitory computer-readable storage medium of claim 9, the method further comprising:

in response to processing the first voice input, causing the virtual assistant to present a response to the request for additional information about the topic to the user at least in part by providing the response to the mobile device.