Customized voice action system

• US 9,275,411 B2
• Filed: 05/23/2012
• Issued: 03/01/2016
• Est. Priority Date: 05/23/2012
• Status: Active Grant

• Current Assignee: Google LLC (Alphabet Inc.)
• Original Assignee: Google Inc. (Alphabet Inc.)
• Inventors: Mengibar, Pedro J. Moreno
• Primary Examiner(s): He, Jialong
• Application Number:
  US13/478,803
• Publication Number:
  US 20130317823A1
• Time in Patent Office: 1,378 Days
• Field of Search: 704/231, 704/251, 704/270, 705/14.7
• US Class Current: 1/1
• 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, comprising:

receiving, at a voice action system comprising at least one server computing system, a plurality of electronic voice action bids from a plurality of advertisers that each represent an offer for modifying the voice action system to include a voice action associated with an electronic voice action bid of the plurality of electronic voice action bids, wherein the voice action comprises a triggering phrase and an action;

selecting, by the voice action system based on a predetermined criteria, one or more electronic voice action bids from among the plurality of electronic voice action bids;

modifying, by the voice action system, data associated with the voice action system to include the voice action for each of the selected one or more electronic voice action bids, wherein the voice action system performs the action associated with the respective voice action responsive to voice input received from a user corresponding to the triggering phrase associated with the respective voice action; and

setting, by the voice action system, a parameter in a voice action language model database to increase a likelihood that the voice action system determines that the voice input received from the user corresponds to the triggering phrase of the selected one or more electronic voice action bids,

wherein at least one voice action bid comprises an offer for modifying the voice action system to include a voice action grammar associated with the voice action bid, wherein the voice action grammar comprises a plurality of voice actions, and wherein modifying the voice action system comprises, for each of the at least one voice action bids having a voice action grammar associated therewith that is selected, modifying the voice action system to include the plurality of voice actions associated with the voice action grammar.

2. The method of claim 1, wherein the voice action system comprises the voice action language model database including words that the voice action system is configured to recognize as being associated with the triggering phrases of the selected one or more electronic voice action bids, and wherein the method further comprises, for each of the words of the triggering phrases for the selected voice action bids:

determining if a word is included in the voice action language model database; and

adding the word to the voice action language model database when the word is not already included in the voice action language model database.

3. The method of claim 1, wherein the voice action system comprises the voice action language model database including phrases that the voice action system is configured to recognize as being a triggering phrase of one or more voice actions, and wherein the method further comprises, for each of the triggering phrases for the selected voice action bids:

determining if the phrase is included in the voice action language model database; and

adding the phrase to the voice action language model database when the phrase is not already included in the voice action language model database.

4. The method of claim 1, wherein the action associated with at least one of the voice actions of the electronic voice action bids comprises displaying a particular website in a browser application.

5. The method of claim 1, further comprising transmitting, from the voice action system, one or more signals to a mobile computing device configured to perform the actions responsive to receiving the one or more signals, wherein each of the actions associated with the electronic voice action bids comprises at least one of:

displaying a specified website in a browser application,

calling a specified telephone number,

displaying or navigating to a specified location using a mapping application,

downloading a specified file,

displaying or playing specified media content,

sending a message to a specified recipient,

performing a specified search on a search service,

opening a text, audio, or video chat application, and

performing a plurality of predetermined actions within an application or on a website.

6. The method of claim 1, wherein one or more of the electronic voice action bids comprise an offer to provide a benefit in exchange for modifying the voice action system to include a voice action associated with the respective electronic voice action bid for a limited amount of time.

7. The method of claim 6, wherein the one or more of the electronic voice action bids comprise an offer to provide a benefit in exchange for modifying the voice action system to include a voice action associated with the respective electronic voice action bid on a particular date or a particular day of the week.

8. The method of claim 1, wherein at least one voice action comprises a plurality of triggering phrases configured to trigger a single action.

9. A voice action system comprising:

at least one computing device operably coupled to at least one memory and configured to;

receive a plurality of electronic voice action bids from a plurality of advertisers that each represent, an offer for modifying the voice action system to include a voice action associated with an electronic voice action bid of the plurality of electronic voice action bids, wherein the voice action comprises a triggering phrase and an action;

select, based on a predetermined criteria, one or more electronic voice action bids from among the plurality of electronic voice action bids;

modify data associated with the voice action system to include the voice action for each of the selected one or more electronic voice action bids, wherein the voice action system performs the action associated with the respective voice action when voice input received from a user corresponds to the triggering phrase associated with the respective voice action; and

set a parameter in a voice action language model database to increase a likelihood that the voice action system determines that the voice input received from the user corresponds to the triggering phrase of the selected one or more electronic voice action bids; and

a memory having the voice action language model database stored therein that includes words that the voice action system is configured to recognize as being associated with a triggering phrase of one or more voice actions,

wherein at least one voice action bid comprises an offer to modify the voice action system to include a voice action grammar associated with the voice action bid, wherein the voice action grammar comprises a plurality of voice actions, and wherein, for each of the at least one voice action bids having a voice action grammar associated therewith that is selected, the at least one computing device is configured to modify the voice action system to include the plurality of voice actions associated with the voice action grammar.

10. The voice action system of claim 9, wherein the at least one computing device is configured to, for each of one or more words of the triggering phrases for the selected voice action bids:

determine if the word is included in the voice action language model database; and

add the word to the voice action language model database when the word is not already included in the voice action language model database.

11. The voice action system of claim 9, wherein the at least one computing device is configured to, for each of the words of the triggering phrases for the selected voice action bids:

determine if the phrase is included in the voice action language model database; and

add the phrase to the voice action language model database when the phrase is not already included in the voice action language model database.

12. The voice action system of claim 9, wherein the action associated with at least one of the voice actions of the electronic voice action bids comprises displaying a particular website in a browser application.

13. The voice action system of claim 9, wherein the at least one computing device is configured to transmit one or more signals to a mobile computing device configured to perform the actions responsive to receiving the one or more signals, wherein each of the actions associated with the electronic voice action bids comprises at least one of:

displaying a specified website in a browser application,

calling a specified telephone number,

displaying or navigating to a specified location using a mapping application,

downloading a specified file,

displaying or playing specified media content,

sending a message to a specified recipient,

performing a specified search on a search service,

opening a text, audio, or video chat application, and

performing a plurality of predetermined actions within an application or on a website.

14. The voice action system of claim 9, wherein one or more of the electronic voice action bids comprise an offer to provide a benefit in exchange for modifying the voice action system to include a voice action associated with the respective electronic voice action bid for a limited amount of time.

15. The voice action system of claim 14, wherein the one or more of the electronic voice action bids comprise an offer to provide a benefit in exchange for modifying the voice action system to include a voice action associated with the respective electronic voice action bid on a particular date or a particular day of the week.

16. A computer-readable storage medium having instructions stored thereon that, when executed by a processor, cause the processor to perform operations comprising:

receiving a plurality of electronic voice action suggestions, wherein each of the electronic voice action suggestions comprises a voice action that a user proposes to include in a voice action system, wherein a voice action comprises a triggering phrase and an action;

selecting one or more electronic voice action suggestions from among the plurality of electronic voice action suggestions; and

modifying data associated with the voice action system to include the voice action for each of the selected one or more electronic voice action suggestions, wherein the voice action system performs the action associated with the respective voice action when voice input received from a user corresponds to the triggering phrase associated with the respective voice action; and

setting a parameter in a voice action language model database to increase a likelihood that the voice action system determines that the voice input received from the user corresponds to the triggering phrase of the selected one or more electronic voice action suggestions,

wherein at least one voice action suggestion comprises a proposal to modify the voice action system to include a voice action grammar associated with the voice action suggestion, wherein the voice action grammar comprises a plurality of voice actions, and wherein modifying the voice action system comprises, for each of the at least one voice action suggestions having a voice action grammar associated therewith that is selected, modifying the voice action system to include the plurality of voice actions associated with the voice action grammar.

17. The computer-readable storage medium of claim 16, wherein the voice action system comprises the voice action language model database including words that the voice action system is configured to recognize as being associated with a triggering phrase of one or more voice actions, and wherein the operations further comprise, for each of the words of the triggering phrases for the selected voice action suggestions:

determining if the word is included in the voice action language model database; and

adding the word to the voice action language model database when the word is not already included in the voice action language model database.

18. The computer-readable storage medium of claim 16, wherein the voice action system comprises the voice action language model database including phrases that the voice action system is configured to recognize as being a triggering phrase of one or more voice actions, and wherein the operations further comprise, for each of the triggering phrases for the selected voice action suggestions:

determining if the phrase is included in the voice action language model database; and

adding the phrase to the voice action language model database when the phrase is not already included in the voice action language model database.