Customized voice action system

• US 10,147,422 B2
• Filed: 02/26/2016
• Issued: 12/04/2018
• Est. Priority Date: 05/23/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google LLC (Alphabet Inc.)
• Inventors: Mengibar, Pedro J. Moreno
• Primary Examiner(s): He, Jialong
• Application Number:
  US15/054,301
• Publication Number:
  US 20160180848A1
• Time in Patent Office: 1,012 Days
• Field of Search: None
• CPC Class Codes: G06F 40/242 Dictionaries
• CPC Class Codes: G06Q 30/0256 User search
• CPC Class Codes: G06Q 30/0275 Auctions
• CPC Class Codes: G06Q 30/0277 Online advertisement
• CPC Class Codes: G06Q 30/08 Auctions
• CPC Class Codes: G10L 15/08 Speech classification or search
• CPC Class Codes: G10L 15/197 Probabilistic grammars, e.g. word n-grams
• CPC Class Codes: G10L 15/22 Procedures used during a speech recognition process, e.g. man-machine dialogue
• CPC Class Codes: G10L 2015/088 Word spotting
• CPC Class Codes: G10L 2015/223 Execution procedure of a spoken command

Abstract

Systems, methods, and computer-readable media that may be used to modify a voice action system to include voice actions provided by advertisers or users are provided. One method includes receiving electronic voice action bids from advertisers to modify the voice action system to include a specific voice action (e.g., a triggering phrase and an action). One or more bids may be selected. The method includes, for each of the selected bids, modifying data associated with the voice action system to include the voice action associated with the bid, such that the action associated with the respective voice action is performed when voice input from a user is received that the voice action system determines to correspond to the triggering phrase associated with the respective voice action.

Claims

1. A method of commanding a computing device, comprising:

receiving, by one or more servers via a network, a first bid from a first advertiser device, the first bid corresponding to a first voice action grammar in a voice action language model, the first voice action grammar including a first plurality of triggering phrases and a first plurality of electronic actions;

receiving, by the one or more servers via the network, a second bid from a second advertiser device, the second bid corresponding to a second voice action grammar that includes a second plurality of triggering phrases and a second plurality of electronic actions;

selecting, by the one or more servers based on a comparison of the first bid with the second bid, the first bid from a plurality of bids comprising the first bid and the second bid;

weighting, responsive to selection of the first bid based on the comparison, at least one of the first plurality of triggering phrases in the voice action language model to increase a likelihood that a voice input matches the at least one of the first plurality of triggering phrases; and

configuring, by the one or more servers for the computing device, the voice action language model with the weighted first plurality of triggering phrases to enable the first voice action grammar on the computing device to cause the computing device to perform the first plurality of electronic actions of the first voice action grammar responsive to voice input detected by a microphone of the computing device that matches, based on the voice action language model, at least one of the first plurality of triggering phrases of the first voice action grammar,

wherein the first voice action grammar is configured to cause the computing device to perform the first plurality of electronic actions comprising at least two of displaying a website in a browser application, calling a telephone number, displaying a location via a mapping application, downloading a data file, presenting media content, sending an electronic message to a recipient device, performing a search via a search engine, or launching a chat application.

2. The method of claim 1, comprising:

setting, by the one or more servers responsive to the first bid selected from the plurality of bids, a parameter in the voice action language model to increase a likelihood that the voice input matches at least one of the first plurality of triggering phrases.

3. The method of claim 1, comprising:

increasing, by the one or more servers responsive to the first bid selected from the plurality of bids, a likelihood that at least one of a search recognition engine or a semantic parser matches the voice input to at least one of the first plurality of triggering phrases.

4. The method of claim 1, comprising:

determining, by the one or more servers, that a word of a triggering phrase of the first plurality of triggering phrases is not included in the voice action language model maintained by the one or more servers; and

adding, responsive to determining that the word is not included, the word to the voice action language model.

5. The method of claim 1, comprising:

determining, by the one or more servers, that a triggering phrase of the first plurality of triggering phrases is not included in the voice action language model maintained by the one or more servers; and

adding, responsive to determining that the triggering phrase is not included, the triggering phrase to the voice action language model.

6. The method of claim 1, comprising:

enabling, by the one or more servers, the first voice action grammar configured to cause the computing device to perform the first plurality of electronic actions comprising displaying the website in the browser application.

7. The method of claim 1, comprising:

enabling, by the one or more servers, the first voice action grammar configured to cause the computing device to perform the first plurality of electronic actions comprising initiating a call to the telephone number.

8. The method of claim 1, comprising:

enabling, by the one or more servers, the first voice action grammar for a limited time interval.

9. The method of claim 1, comprising:

enabling, by the one or more servers, the first voice action grammar for the computing device responsive to the computing device located in a limited geographical area.

10. A system to command a computing device, comprising:

one or more servers comprising one or more processors and memory;

a voice action system executed by the one or more servers to;

receive, via a network, a first bid from a first advertiser device, the first bid corresponding to a first voice action grammar in a voice action language model, the first voice action grammar including a first plurality of triggering phrases and a first plurality of electronic actions;

receive, via the network, a second bid from a second advertiser device, the second bid corresponding to a second voice action grammar that includes a second plurality of triggering phrases and a second plurality of electronic actions;

select, based on a comparison of the first bid with the second bid on a, the first bid from a plurality of bids comprising the first bid and the second bid;

weight, responsive to selection of the first bid based on the comparison, at least one of the first plurality of triggering phrases in the voice action language model to increase a likelihood that a voice input matches the at least one of the first plurality of triggering phrases; and

configure, for the computing device, the voice action language model with the weighted first plurality of triggering phrases to enable the first voice action grammar on the computing device to cause the computing device to perform the first plurality of electronic actions of the first voice action grammar responsive to voice input detected by a microphone of the computing device that matches, based on the voice action language model, at least one of the first plurality of triggering phrases of the first voice action grammar,

wherein the first voice action grammar is configured to cause the computing device to perform the first plurality of electronic actions comprising at least two of displaying a website in a browser application, calling a telephone number, displaying a location via a mapping application, downloading a data file, presenting media content, sending an electronic message to a recipient device, performing a search via a search engine, or launching a chat application.

11. The system of claim 10, comprising:

the voice action system configured to set, responsive to the first bid selected from the plurality of bids, a parameter in the voice action language model to increase a likelihood that the voice input matches at least one of the first plurality of triggering phrases.

12. The system of claim 10, comprising:

the voice action system configured to increase, responsive to the first bid selected from the plurality of bids, a likelihood that at least one of a search recognition engine or a semantic parser matches the voice input to at least one of the first plurality of triggering phrases.

13. The system of claim 10, comprising:

the voice action system configured to;

determine that a word of a triggering phrase of the first plurality of triggering phrases is not included in the voice action language model maintained by the one or more servers; and

add, responsive to the determination that the word is not included, the word to the voice action language model.

14. The system of claim 10, comprising:

the voice action system configured to;

determine that a triggering phrase of the first plurality of triggering phrases is not included in the voice action language model maintained by the one or more servers; and

add, responsive to the determination that the triggering phrase is not included, the triggering phrase to the voice action language model.

15. The system of claim 10, comprising:

the voice action system configured to enable the first voice action grammar to cause the computing device to perform the first plurality of electronic actions, the first plurality of electronic actions configured to display the website in the browser application.

16. The system of claim 10, comprising:

the voice action system configured to enable the first voice action grammar to cause the computing device to initiate a call to the telephone number.

17. The system of claim 10, comprising:

the voice action system configured to enable the first voice action grammar for a limited time interval.

18. The system of claim 10, comprising:

the voice action system configured to enable the first voice action grammar for the computing device responsive to the computing device located in a limited geographical area.