Suggested query constructor for voice actions

• US 8,849,675 B1
• Filed: 12/18/2013
• Issued: 09/30/2014
• Est. Priority Date: 12/18/2013
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Quasthoff, Matthias, Foerster, Jakob, Tokumine, Simon
• Primary Examiner(s): Armstrong, Angela A
• Application Number:
  US14/132,676
• Time in Patent Office: 286 Days
• Field of Search: 704/251, 704/257, 704/270, 704/275
• US Class Current: 704/275
• CPC Class Codes: G06F 3/167 Audio in a user interface, e.g. using voice commands for navigating, audio feedback
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/225 Feedback of the input speech

Abstract

Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for suggesting a phrase for performing a voice action. The methods, systems, and apparatus include actions of classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter. Additional actions include, in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter, and in response to the prompt, receiving data indicating an entered parameter. Further actions include providing, for output, a suggested complete phrase for performing the voice action using the entered parameter.

Claims

1. A computer-implemented method comprising:

classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter;

in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter;

in response to the prompt, receiving data indicating an entered parameter; and

providing, for output, a suggested complete phrase for performing the voice action using the entered parameter, the suggested complete phrase comprising a phrase that when subsequently received causes the voice action to be performed without prompting for the entry of the parameter after determining that the suggested complete phrase includes one or more terms that correspond to the voice action.

2. The method of claim 1, further comprising receiving the phrase, wherein the phrase includes one or more terms that correspond to the voice action.

3. The method of claim 1, wherein generating a prompt for entry of the parameter comprises at least one of:

generating a user interface for display that includes fields for entry of the parameter; and

synthesizing speech that requests the user speak the parameter.

4. The method of claim 1, further comprising:

receiving data indicating another parameter that is required for the voice action; and

determining that data indicating all parameters that are required for the voice action have been received,

wherein providing, for output, the suggested complete phrase for performing the voice action comprises synthesizing speech of the suggested complete phrase in response to determining that data indicating all the parameters that are required for the voice action have been received.

5. The method of claim 1, further comprising:

before receiving data indicating the entered parameter, receiving data indicating another parameter that is required for the voice action; and

before providing, for output, the suggested complete phrase for performing the voice action using the entered parameter, providing, for display in a user interface, a suggested partially complete phrase for performing the voice action using the other parameter.

6. The method of claim 1, further comprising:

receiving data indicating another parameter that is not required for the voice action, wherein providing, for output, the suggested complete phrase for performing the voice action using the entered parameter comprises providing, for output, a suggested complete phrase for performing the voice action using the received parameter and the received other parameter.

7. The method of claim 1, wherein providing, for output, a suggested complete phrase for performing the voice action using the entered parameter comprises:

selecting a text pattern based at least on the one or more terms that correspond to the voice action; and

generating the suggested complete phrase based at least on applying the selected text pattern to the entered parameter.

8. The method of claim 1, wherein the suggested complete phrase does not include any term that appears in the received phrase.

9. A system comprising:

one or more computers; and

one or more storage devices storing instructions that are operable, when executed by the one or more computers, to cause the one or more computers to perform operations comprising;

classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter;

in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter;

in response to the prompt, receiving data indicating an entered parameter; and

providing, for output, a suggested complete phrase for performing the voice action using the entered parameter, the suggested complete phrase comprising a phrase that when subsequently received causes the voice action to be performed without prompting for the entry of the parameter after determining that the suggested complete phrase includes one or more terms that correspond to the voice action.

10. The system of claim 9, wherein the operations further comprise receiving the phrase, wherein the phrase includes one or more terms that correspond to the voice action.

11. The system of claim 9, wherein generating a prompt for entry of the parameter comprises at least one of:

generating a user interface for display that includes fields for entry of the parameter; and

synthesizing speech that requests the user speak the parameter.

12. The system of claim 9, wherein the operations further comprise:

receiving data indicating another parameter that is required for the voice action; and

determining that data indicating all parameters that are required for the voice action have been received,

wherein providing, for output, the suggested complete phrase for performing the voice action comprises synthesizing speech of the suggested complete phrase in response to determining that data indicating all the parameters that are required for the voice action have been received.

13. The system of claim 9, wherein the operations further comprise:

before receiving data indicating the entered parameter, receiving data indicating another parameter that is required for the voice action; and

before providing, for output, the suggested complete phrase for performing the voice action using the entered parameter, providing, for display in a user interface, a suggested partially complete phrase for performing the voice action using the other parameter.

14. The system of claim 9, wherein the operations further comprise:

receiving data indicating another parameter that is not required for the voice action,

wherein providing, for output, the suggested complete phrase for performing the voice action using the entered parameter comprises providing, for output, a suggested complete phrase for performing the voice action using the received parameter and the received other parameter.

15. A non-transitory computer-readable medium storing instructions executable by one or more computers which, upon such execution, cause the one or more computers to perform operations comprising:

classifying a received phrase as an incomplete phrase for performing a voice action based at least on determining that (i) the voice action requires a parameter, and (ii) that no term of the phrase corresponds to the parameter;

in response to classifying the phrase as an incomplete phrase, generating a prompt for entry of the parameter;

in response to the prompt, receiving data indicating an entered parameter; and

providing, for output, a suggested complete phrase for performing the voice action using the entered parameter, the suggested complete phrase comprising a phrase that when subsequently received causes the voice action to be performed without prompting for the entry of the parameter after determining that the suggested complete phrase includes one or more terms that correspond to the voice action.

16. The computer-readable medium of claim 15, wherein the operations further comprise receiving the phrase, wherein the phrase includes one or more terms that correspond to the voice action.

17. The computer-readable medium of claim 15, wherein generating a prompt for entry of the parameter comprises at least one of:

generating a user interface for display that includes fields for entry of the parameter; and

synthesizing speech that requests the user speak the parameter.

18. The computer-readable medium of claim 15, wherein the operations further comprise:

receiving data indicating another parameter that is required for the voice action; and

determining that data indicating all parameters that are required for the voice action have been received,

wherein providing, for output, the suggested complete phrase for performing the voice action comprises synthesizing speech of the suggested complete phrase in response to determining that data indicating all the parameters that are required for the voice action have been received.

19. The computer-readable medium of claim 15, wherein the operations further comprise:

before receiving data indicating the entered parameter, receiving data indicating another parameter that is required for the voice action; and

before providing, for output, the suggested complete phrase for performing the voice action using the entered parameter, providing, for display in a user interface, a suggested partially complete phrase for performing the voice action using the other parameter.