Voice application finding and user invoking applications related to a single entity

• US 8,515,766 B1
• Filed: 09/28/2012
• Issued: 08/20/2013
• Est. Priority Date: 09/30/2011
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Bringert, Bjorn Erik, Pietryka, Pawel, Hodgson, Peter John, Tickner, Simon, Penha, Henrique, Cohen, Richard Zarek, Zanolin, Luca, Foster, Marcus
• Primary Examiner(s): Smits, Talivaldis Ivars
• Application Number:
  US13/631,282
• Time in Patent Office: 326 Days
• Field of Search: None
• US Class Current: 704/275
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command
• CPC Class Codes: G10L 2015/228 of application context

Abstract

A computing device is configured to initiate actions in response to speech input that includes a name or other indication of an entity, in a first spoken utterance, followed by user choosing an application related to an entity, in a second spoken utterance. The computing device receives the first spoken utterance, identifies an entity based on the first spoke utterance, and indicates a plurality of available applications related to the identified entity. The computing device then receives the second spoken utterance and identifies a selection of at least one of the available applications based on the second spoken utterance. The computing device then invokes the at least one selected application.

Claims

1. A method, comprising:

receiving, by a computing device, a first spoken utterance;

obtaining, by the computing device, first text based upon speech recognition performed upon the first spoken utterance;

identifying, by the computing device, an entity based on the first text;

indicating, by the computing device, a plurality of available actions based on the identified entity, wherein indicating the plurality of available actions comprises indicating a plurality of applications;

after indicating the plurality of available actions, receiving, by the computing device, a second spoken utterance;

obtaining, by the computing device, second text based upon speech recognition performed upon the second spoken utterance;

identifying, by the computing device, a selection of at least one action from among the plurality of available actions based on the second text; and

invoking, by the computing device, one or more of the indicated applications based on the at least one selected action.

2. The method of claim 1, wherein identifying the entity based on the first text comprises:

determining a search query based on the first text;

performing a search based on the search query;

receiving at least one search result for the search; and

identifying the entity in the at least one search result.

3. The method of claim 1, wherein indicating the plurality of applications comprises:

visually displaying textual or graphical indications of the applications.

4. The method of claim 1, wherein indicating the plurality of applications comprises:

providing audible indications of the applications in the form of synthesized speech.

5. The method of claim 1, further comprising:

determining that the first text includes a selection criterion, wherein the plurality of applications satisfy the selection criterion.

6. The method of claim 1, wherein the entity is a person or a place.

7. A computer readable medium having stored therein instructions executable by at least one processor to cause a computing device to perform functions, the functions comprising:

receiving a first spoken utterance;

obtaining first text based upon speech recognition performed upon the first spoken utterance;

identifying an entity based on the first text;

indicating a plurality of available actions based on the identified entity, wherein indicating the plurality of available actions comprises indicating a plurality of applications;

after indicating the plurality of available actions, receiving a second spoken utterance;

obtaining second text based upon speech recognition performed upon the second spoken utterance;

identifying a selection of at least one of the available actions based on the second text; and

invoking one or more of the indicated applications based on the at least one selected action.

8. The computer readable medium of claim 7, wherein identifying the entity based on the first text comprises:

determining a search query based on the first text;

performing a search based on the search query;

receiving at least one search result for the search; and

identifying the entity in the at least one search result.

9. The computer readable medium of claim 7, wherein the entity is a person or a place.

10. The computer readable medium of claim 7, wherein indicating the plurality of applications comprises visually displaying textual or graphical indications of the applications.

11. The computer readable medium of claim 7, wherein indicating the plurality of applications comprises providing audible indications of the applications in the form of synthesized speech.

12. A computing device, comprising:

at least one processor;

data storage;

a plurality of instructions stored in the data storage and executable by the at least one processor to cause the computing device to perform functions, the functions comprising;

receiving a first spoken utterance;

obtaining first text based upon speech recognition performed upon the first spoken utterance;

identifying an entity based on the first text;

indicating a plurality of available actions based on the identified entity, wherein indicating the plurality of available actions comprises indicating a plurality of applications;

after indicating the plurality of available actions, receiving a second spoken utterance;

obtaining second text based upon speech recognition performed upon the second spoken utterance;

identifying a selection of at least one of the available actions based on the second text; and

invoking one or more of the indicated applications based on the at least one selected action.

13. The computing device of claim 12, further comprising a display, wherein indicating the plurality of applications comprises displaying textual or graphical indications of the applications on the display.

14. The computing device of claim 12, further comprising a text-to-speech (TTS) engine, wherein indicating the plurality of applications comprises using the TTS engine to describe the applications in a spoken form.

15. The computing device of claim 12, further comprising a communication interface.

16. The computing device of claim 15, wherein obtaining first text based upon speech recognition performed upon the first spoken utterance comprises communicating with a network server through the communication interface.

17. The computing device of claim 15, wherein obtaining second text based upon speech recognition performed upon the second spoken utterance comprises communicating with a network server through the communication interface.

18. The computing device of claim 15, further comprising a search client.

19. The computing device of claim 18, wherein identifying an entity based on the first text comprises:

determining a search query based on the first text;

using the search client to perform a search based on the search query and receive at least one search result; and

identifying the entity in the at least one search result.

20. The computing device of claim 19, wherein using the search client to perform a search based on the search query and receive at least one search result comprises the search client communicating with a network server through the communication interface.