Intelligent automated assistant

Patent metadata

Field	Value
Publication number	US-10043516-B2
Application number	US-201615385606-A
Country	US
Kind code	B2
Filing date	Dec 20, 2016
Priority date	Sep 23, 2016
Publication date	Aug 7, 2018
Grant date	Aug 7, 2018

Abstract

Systems and processes for operating an automated assistant are disclosed. In one example process, an electronic device provides an audio output via a speaker of the electronic device. While providing the audio output, the electronic device receives, via a microphone of the electronic device, a natural language speech input. The electronic device derives a representation of user intent based on the natural language speech input and the audio output, identifies a task based on the derived user intent; and performs the identified task.

First claim

What is claimed is:

1. An electronic device for operating an automated assistant, the electronic device comprising:
one or more processors;
a memory;
a speaker;
a microphone; and
one or more programs, wherein the one or more programs are stored in the memory and configured to be executed by the one or more processors, the one or more programs including instructions for:
providing, via the speaker of the electronic device, an audio output;
while providing the audio output via the speaker of the electronic device, receiving, via the microphone of the electronic device, a natural language speech input;
in response to receiving the natural language speech input, determining a type of the audio output;
in response to a determination that the audio output is of a first type, adjusting the audio output;
in response to a determination that the audio output is of a second type different from the first type, ceasing to provide the audio output;
deriving a representation of user intent based on the natural language speech input and the audio output;
identifying a task based on the derived user intent; and
performing the identified task.

2. The electronic device of claim 1 , the one or more programs further including instructions for:
identifying one or more parameters associated with the task based on a portion of the audio output;
wherein performing the task includes performing the task based on the identified one or more parameters.

3. The electronic device of claim 2 , the one or more programs further including instructions for: in response to receipt of the natural language speech input, identifying the portion of the audio output.

4. The electronic device of claim 2 ,
wherein providing the audio output comprises providing a speech output indicative of a list of items, and
wherein the portion of the audio output is indicative of an item of the list of items.

5. The electronic device of claim 4 ,
wherein the item is a media item, and
wherein performing the task comprises performing playback, via the speaker, of the media item.

6. The electronic device of claim 4 ,
wherein the item is a location, and
wherein performing the task comprises providing, via the speaker, information associated with the location.

7. The electronic device of claim 1 ,
wherein providing the audio output comprises performing playback of media content, and
wherein performing the task comprises adjusting playback of the media content.

8. The electronic device of claim 7 , wherein adjusting playback of the media content comprises: adjusting a volume of the speaker of the electronic device.

9. The electronic device of claim 7 , wherein adjusting playback of the media content comprises: pausing playback of the media content.

10. The electronic device of claim 1
wherein adjusting the audio output comprises attenuating the audio output.

11. The electronic device of claim 1 , wherein the audio output is a first audio output, the one or more programs further including instructions for:
before providing the first audio output, providing a second audio output.

12. A method for operating an automated assistant, the method comprising:
at an electronic device with a speaker and a microphone,
providing, via the speaker of the electronic device, an audio output;
while providing the audio output via the speaker of the electronic device, receiving, via the microphone of the electronic device, a natural language speech input;
in response to receiving the natural language speech input, determining a type of the audio output;
in response to a determination that the audio output is of a first type, adjusting the audio output;
in response to a determination that the audio output is of a second type different from the first type, ceasing to provide the audio output;
deriving a representation of user intent based on the natural language speech input and the audio output;
identifying a task based on the derived user intent; and
performing the identified task.

13. The method of claim 12 , further comprising:
identifying one or more parameters associated with the task based on a portion of the audio output;
wherein performing the task includes performing the task based on the identified one or more parameters.

14. The method of claim 13 , further comprising: in response to receipt of the natural language speech input, identifying the portion of the audio output.

15. The method of claim 13 ,
wherein providing the audio output comprises providing a speech output indicative of a list of items, and
wherein the portion of the audio output is indicative of an item of the list of items.

16. The method of claim 15 ,
wherein the item is a media item, and
wherein performing the task comprises performing playback, via the speaker, of the media item.

17. The method of claim 15 ,
wherein the item is a location, and
wherein performing the task comprises providing, via the speaker, information associated with the location.

18. The method of claim 12 ,
wherein providing the audio output comprises performing playback of media content, and
wherein performing the task comprises adjusting playback of the media content.

19. The method of claim 18 , wherein adjusting playback of the media content comprises: adjusting a volume of the speaker of the electronic device.

20. The method of claim 18 , wherein adjusting playback of the media content comprises: pausing playback of the media content.

21. The method of claim 12 , wherein adjusting the audio output comprises attenuating the audio output.

22. The method of claim 12 , wherein the audio output is a first audio output, the method further comprising:
before providing the first audio output, providing a second audio output.

23. A non-transitory computer readable storage medium storing one or more programs, the one or more programs comprising instructions, which when executed by one or more processors of an electronic device, cause the device to:
provide, via a speaker of the electronic device, an audio output;
while providing the audio output via the speaker of the electronic device, receive, via a microphone of the electronic device, a natural language speech input;
in response to receiving the natural language speech input, determine a type of the audio output;
in response to a determination that the audio output is of a first type, adjust the audio output;
in response to a determination that the audio output is of a second type different from the first type, cease to provide the audio output;
derive a representation of user intent based on the natural language speech input and the audio output;
identify a task based on the derived user intent; and
perform the identified task.

24. The non-transitory computer readable storage medium of claim 23 , the one or more programs further comprising instructions, which when executed by one or more processors of the electronic device, cause the device to:
identify one or more parameters associated with the task based on a portion of the audio output;
wherein performing the task includes performing the task based on the identified one or more parameters.

25. The non-transitory computer readable storage medium of claim 24 , the one or more programs further comprising instructions, which when executed by one or more processors of the electronic device, cause the device to:
in response to receipt of the natural

Assignees

• Apple Inc

Inventors

• Saddler Harry J
• Piercy Aimee T
• Weinberg Garrett L
• Booker Susan L

Classifications

• G06F3/167

  Audio in a user interface, e.g. using voice commands for navigating, audio feedback · CPC title

• G06F3/04817

  using icons (graphical or visual programming using iconic symbols G06F8/34) · CPC title

• G06F3/011

  Arrangements for interaction with the human body, e.g. for user immersion in virtual reality (blind teaching G09B21/00) · CPC title

• G10L13/02

  Methods for producing synthetic speech; Speech synthesisers · CPC title

• G10L15/22 Primary

  Procedures used during a speech recognition process, e.g. man-machine dialogue · CPC title