Offline personal assistant

Patent metadata

Field	Value
Publication number	US-10755703-B2
Application number	US-201715713503-A
Country	US
Kind code	B2
Filing date	Sep 22, 2017
Priority date	May 11, 2017
Publication date	Aug 25, 2020
Grant date	Aug 25, 2020

Abstract

Systems and processes for performing a task with a digital assistant are provided. In accordance with one example, a method includes, at an electronic device having one or more processors, receiving a natural-language input; determining, based on the natural-language input, a first task and first usefulness score associated with the first task; receiving, from another electronic device, a second task and second usefulness score associated with the second task; determining whether the first usefulness score is higher than the second usefulness score; in accordance with a determination that the first usefulness score is higher than the second usefulness score: performing the first task determined by the electronic device; and providing an output indicating whether the first task has been performed; and in accordance with a determination that the second usefulness score is higher than the first usefulness score: performing the second task received from the another electronic device; and providing an output indicating whether the second task has been performed.

First claim

What is claimed is:

1. 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 electronic device to:
receive a natural-language input;
determine, based on the natural-language input, a first task and a first usefulness score associated with the first task;
provide, to another electronic device, the first task and the first usefulness score associated with the first task;
receive, from the another electronic device, an input indicating whether the first usefulness score is higher than a second usefulness score associated with a second task;
in accordance with the input indicating that the first usefulness score is higher than the second usefulness score:
perform the first task determined by the electronic device; and
provide an output indicating whether the first task has been performed; and

in accordance with the input indicating that the second usefulness score is higher than the first usefulness score:
receive the second task from the another electronic device;
perform the second task received from the another electronic device; and
provide an output indicating whether the second task has been performed.

2. The non-transitory computer-readable storage medium of claim 1 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
providing a text string based on the natural-language input;
determining a user intent based on the text string; and
determining the first task based on the user intent.

3. The non-transitory computer-readable storage medium of claim 1 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
determining the first task based on context of the electronic device.

4. The non-transitory computer-readable storage medium of claim 1 , wherein the instructions further cause the electronic device to:
at the electronic device, provide the natural-language input to the another device, wherein the second task and the second usefulness score associated with the second task are based on the natural-language input.

5. The non-transitory computer-readable storage medium of claim 1 , wherein the first usefulness score is based on a speech-to-text confidence score, a natural-language confidence score, or a combination thereof.

6. The non-transitory computer-readable storage medium of claim 1 , wherein the instructions further cause the electronic device to:
receive a second natural-language input;
determine whether the first task was performed or the second task was performed;
in accordance with a determination that the first task was performed, determine, with the electronic device, a third task based on the second natural-language input; and
in accordance with a determination that the second task was performed, provide the second natural-language input to the another electronic device.

7. The non-transitory computer-readable storage medium of claim 1 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
determining the first task based on a conversational context of the electronic device.

8. The non-transitory computer-readable storage medium of claim 7 , wherein the instructions further cause the electronic device to:
provide the conversational context of the electronic device to the another electronic device.

9. The non-transitory computer-readable storage medium of claim 1 , wherein the natural-language input is a natural-language speech input.

10. A method, comprising:
at an electronic device having one or more processors:
receiving a natural-language input;
determining, based on the natural-language input, a first task and a first usefulness score associated with the first task;
providing, to another electronic device, the first task and the first usefulness score associated with the first task;
receiving, from the another electronic device, an input indicating whether the first usefulness score is higher than a second usefulness score associated with a second task;
in accordance with the input indicating that the first usefulness score is higher than the second usefulness score:
performing the first task determined by the electronic device; and
providing an output indicating whether the first task has been performed; and

in accordance with the input indicating that the second usefulness score is higher than the first usefulness score:
receiving the second task from the another electronic device;
performing the second task received from the another electronic device; and
providing an output indicating whether the second task has been performed.

11. The method of claim 10 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
providing a text string based on the natural-language input;
determining a user intent based on the text string; and
determining the first task based on the user intent.

12. The method of claim 10 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
determining the first task based on context of the electronic device.

13. The method of claim 10 , further comprising:
at the electronic device, providing the natural-language input to the another device, wherein the second task and the second usefulness score associated with the second task are based on the natural-language input.

14. The method of claim 10 , wherein the first usefulness score is based on a speech-to-text confidence score, a natural-language confidence score, or a combination thereof.

15. The method of claim 10 , further comprising:
receiving a second natural-language input;
determining whether the first task was performed or the second task was performed;
in accordance with a determination that the first task was performed, determining, with the electronic device, a third task based on the second natural-language input; and
in accordance with a determination that the second task was performed, providing the second natural-language input to the another electronic device.

16. The method of claim 10 , wherein determining, based on the natural-language input, a first task and a first usefulness score associated with the first task comprises:
determining the first task based on a conversational context of the electronic device.

17. The method of claim 16 , further comprising:
providing the conversational context of the electronic device to the another electronic device.

18. The method of claim 10 , wherein the natural-language input is a natural-language speech input.

19. An electronic device, comprising:
one or more processors;
a memory; 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:
receiving a natural-language input;
determining, based on the natural-language input, a first task and a first usefulness score associated with the first task;
providing, to another electronic device, the first task and the first usefulness score associated with the first task;
receiving, from the another electronic device, an input indicati

Assignees

• Apple Inc

Inventors

• Zeitlin Nicolas
• Paulik Matthias
• Mason Henry G
• Kwong Karric
• Akay Sinan
• Rathinam Saravana Kumar
• Biswas Anumita

Classifications

• G10L15/26 Primary

  Speech to text systems (G10L15/08 takes precedence) · CPC title

• G10L15/1815

  Semantic context, e.g. disambiguation of the recognition hypotheses based on word meaning · CPC title

• G10L15/30

  Distributed recognition, e.g. in client-server systems, for mobile phones or network applications · CPC title

• G10L15/22 Primary

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

• G10L2015/223

  Execution procedure of a spoken command · CPC title