USING CONTEXT INFORMATION TO FACILITATE PROCESSING OF COMMANDS IN A VIRTUAL ASSISTANT

• US 20140297284A1
• Filed: 06/12/2014
• Published: 10/02/2014
• Est. Priority Date: 06/05/2009
• Status: Active Grant

• Current Assignee: Apple Inc.
• Original Assignee: Apple Inc.
• Inventors: GRUBER, Thomas R., NOVICK, Gregory, BRIGHAM, Christopher D., KEEN, Daniel S., PHIPPS, Benjamin S.
• Granted Patent: US 10,475,446 B2
• Time in Patent Office: Days
• US Class Current: 704/257
• CPC Class Codes: G06F 2203/0381 Multimodal input, i.e. interface arrangements enabling the user to issue commands by simultaneous use of input devices of different nature, e.g. voice plus gesture on digitizer
• CPC Class Codes: G10L 15/18 using natural language modelling
• CPC Class Codes: G10L 15/183 using context dependencies, e.g. language models

Abstract

A virtual assistant uses context information to supplement natural language or gestural input from a user. Context helps to clarify the user'"'"'s intent and to reduce the number of candidate interpretations of the user'"'"'s input, and reduces the need for the user to provide excessive clarification input. Context can include any available information that is usable by the assistant to supplement explicit user input to constrain an information-processing problem and/or to personalize results. Context can be used to constrain solutions during various phases of processing, including, for example, speech recognition, natural language processing, task flow processing, and dialog generation.

Claims

1. A computer-implemented method for processing user input to perform a task on an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors, the method comprising:

receiving user input, the user input including a named relationship;

receiving contact information based on an association between the named relationship and a contact associated with the user;

interpreting the received user input to derive a representation of user intent; and

causing to be performed at least one task based at least in part on the derived

representation of user intent and the received contact information.

2. The computer-implemented method of claim 1, wherein the association between a named relationship and a contact is created by the user.

3. The computer-implemented method of claim 1, wherein the association between a named relationship and a contact is stored as a field of the contact.

4. The computer-implemented method of claim 1, wherein the association between a named relationship and a contact is based on prior user input.

5. The computer-implemented method of claim 4, wherein the prior user input comprises user dialog history.

6. The computer-implemented method of claim 4, wherein the prior user input comprises a stated relationship.

7. The computer-implemented method of claim 1, wherein the contact information comprises a phone number and the at least one task includes calling the contact associated with the named relationship.

8. The computer-implemented method of claim 1, wherein the contact information comprises a phone number and the at least one task includes texting the contact associated with the named relationship.

9. The computer-implemented method of claim 1, wherein the contact information comprises an email address and the at least one task includes drafting an email to the contact associated with the named relationship.

10. The computer-implemented method of claim 1, wherein the named relationship comprises a family relationship.

11. The computer-implemented method of claim 1, wherein the named relationship comprises one of mother, father, sister, brother, or boss.

12. The computer-implemented method of claim 1, wherein the received user input is received speech data.

13. The computer-implemented method of claim 1, wherein the received user input is received text data.

14. The computer-implemented method of claim 1, wherein the received user input is received speech data and received text data.

15. A computer-implemented method for processing user input to perform a task on an electronic device with one or more processors and memory storing one or more programs for execution by the one or more processors, the method comprising:

receiving user input,

receiving a named relationship;

receiving contact information based on an association between the named relationship and a contact associated with the user;

interpreting the received user input to derive a user intent; and

causing to be performed at least one action based on the interpretation of user

intent and the contact information associated with the named relationship.

16. The computer-implemented method of claim 15, wherein the association between a named relationship and a contact is stored as a field of the contact.

17. The computer-implemented method of claim 15, wherein the contact information comprises a phone number and the at least one task includes calling the contact associated with the named relationship.

18. The computer-implemented method of claim 15, wherein the contact information comprises a phone number and the at least one task includes texting the contact associated with the named relationship.

19. The computer-implemented method of claim 15, wherein the contact information comprises an email address and the at least one task includes drafting an email to the contact associated with the named relationship.

20. The computer-implemented method of claim 15, wherein the named relationship comprises a family relationship.

21. An electronic device controllable by user inputs, comprising a processor, an input interface, and an output interface, the processor operative to:

receive user input, the user input including a named relationship;

receive contact information based on an association between the named relationship and a contact associated with the user;

interpret the received user input to derive a representation of user intent; and

cause at least one task based at least in part on the derived representation of user intent and the received contact information.

22. The electronic device of claim 21, wherein the association between a named relationship and a contact is stored as a field of the contact.

23. The electronic device of claim 21, wherein the contact information comprises a phone number and the at least one task includes calling the contact associated with the named relationship.

24. The electronic device of claim 21, wherein the contact information comprises a phone number and the at least one task includes texting the contact associated with the named relationship.

25. The electronic device of claim 21, wherein the contact information comprises an email address and the at least one task includes drafting an email to the contact associated with the named relationship.

26. The electronic device of claim 21, wherein the named relationship comprises a family relationship.

27. A non-transitory computer readable medium for processing user input, the computer readable media comprising computer program logic for:

receiving user input, the user input including a named relationship;

receiving contact information based on an association between the named relationship and a contact associated with the user;

interpreting the received user input to derive a representation of user intent; and

causing to be performed at least one task based at least in part on the derived representation of user intent and the received contact information.

28. The non-transitory computer readable medium of claim 27, wherein the association between a named relationship and a contact is stored as a field of the contact.

29. The non-transitory computer readable medium of claim 27, wherein the contact information comprises a phone number and the at least one task includes calling the contact associated with the named relationship.

30. The non-transitory computer readable medium of claim 27, wherein the contact information comprises a phone number and the at least one task includes texting the contact associated with the named relationship.