Customized voice action system

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.

1 .- 23 . (canceled) 
     
     
         24 . A system to provide voice interactions, comprising:
 a data processing system comprising one or more processors coupled with memory to:
 receive, from a client device, an audio input acquired via a microphone of the client device; 
 parse the audio input received from the client device to identify a set of strings; 
 determine that the set of strings identified from the audio input does not correspond to any of a plurality of voice commands, the plurality of voice commands maintained on a database and identified as corresponding to a plurality of string sets; and 
 perform, responsive to the determination that the set of strings does not correspond to any of the plurality of voice commands, an action to modify the database to include a voice command corresponding to the set of strings to the plurality of voice commands. 
   
     
     
         25 . The system of  claim 24 , comprising the data processing system to perform the action to provide, to the client device, an audio output indicating that the voice command corresponding to the audio input is not recognized. 
     
     
         26 . The system of  claim 24 , comprising the data processing system to perform the action to provide, to the client device, an audio output prompting for addition of a new voice command to the plurality of voice commands. 
     
     
         27 . The system of  claim 24 , comprising the data processing system to perform the action to configure a language model maintained using the database to add the voice command corresponding to the set of strings to the plurality of voice commands. 
     
     
         28 . The system of  claim 24 , comprising the data processing system to perform, via a search engine, a search using the set of strings determined to not correspond to any of the plurality of voice commands. 
     
     
         29 . The system of  claim 24 , comprising the data processing system to:
 parse the audio input received from the client device to identify the set of strings including a triggering phrase and one or more keywords; and   determine that the triggering phrase identified from the audio input does not correspond to any of the plurality of voice commands, the plurality of voice commands maintained on a database and identified as corresponding to a plurality of triggering phrases.   
     
     
         30 . The system of  claim 24 , comprising the data processing system to perform, responsive to the determination that a triggering phrase included in the set of strings does not correspond to any of the plurality of voice commands, an action to modify the database to include the voice command corresponding to the triggering phrase to a plurality of trigger phrases, the triggering phrase different from all of the plurality of triggering phrases. 
     
     
         31 . The system of  claim 24 , comprising the data processing system to:
 receive, from at least one of a content provider or the client device, an input identifying second set of strings associated with a second voice command to be included in the plurality of voice commands; and   perform, using the input, a second action to modify the database to include the second voice command corresponding to the second set of strings to the plurality of voice commands.   
     
     
         32 . The system of  claim 24 , comprising the data processing system to:
 determine, responsive to receiving a second audio input from the client device, that a second set of strings identified from the second audio input corresponds to a subset of candidate voice commands of the plurality of voice commands; and   select, from the subset of candidate voice commands, a second voice command to be carried out based on a criterion.   
     
     
         33 . The system of  claim 24 , comprising the data processing system to:
 determine, responsive to receiving a second audio input from the client device, that a second set of strings identified from the second audio input corresponds to a second voice command of the plurality of voice commands; and   perform a second action in accordance with the second voice command of the plurality of voice commands determined to correspond to the second set of strings.   
     
     
         34 . A method of providing voice interactions, comprising:
 receiving, by a data processing system, from a client device, an audio input acquired via a microphone of the client device;   parsing, by the data processing system, the audio input received from the client device to identify a set of strings;   determining, by the data processing system, that the set of strings identified from the audio input does not correspond to any of a plurality of voice commands, the plurality of voice commands maintained on a database and identified as corresponding to a plurality of string sets; and   performing, by the data processing system, responsive to the determination that the set of strings does not correspond to any of the plurality of voice commands, an action to modify the database to include a voice command corresponding to the set of strings to the plurality of voice commands.   
     
     
         35 . The method of  claim 34 , comprising performing, by the data processing system, the action to provide, to the client device, an audio output indicating that the voice command corresponding to the audio input is not recognized. 
     
     
         36 . The method of  claim 34 , comprising performing, by the data processing system, the action to provide, to the client device, an audio output prompting for addition of a new voice command to the plurality of voice commands. 
     
     
         37 . The method of  claim 34 , comprising performing, by the data processing system, the action to configure a language model maintained using the database to add the voice command corresponding to the set of strings to the plurality of voice commands. 
     
     
         38 . The method of  claim 34 , comprising performing, by the data processing system, via a search engine, a search using the set of strings determined to not correspond to any of the plurality of voice commands. 
     
     
         39 . The method of  claim 34 , comprising
 parsing, by the data processing system, the audio input received from the client device to identify the set of strings including a triggering phrase and one or more keywords; and   determining, by the data processing system, that the triggering phrase identified from the audio input does not correspond to any of the plurality of voice commands, the plurality of voice commands maintained on a database and identified as corresponding to a plurality of triggering phrases.   
     
     
         40 . The method of  claim 34 , comprising performing, by the data processing system, responsive to the determination that a triggering phrase included in the set of strings does not correspond to any of the plurality of voice commands, an action to modify the database to include the voice command corresponding to the triggering phrase to a plurality of trigger phrases, the triggering phrase different from all of the plurality of triggering phrases. 
     
     
         41 . The method of  claim 34 , comprising
 receiving, by the data processing system, from at least one of a content provider or the client device, an input identifying second set of strings associated with a second voice command to be included in the plurality of voice commands; and   performing, by the data processing system, using the input, a second action to modify the database to include the second voice command corresponding to the second set of strings to the plurality of voice commands.   
     
     
         42 . The method of  claim 34 , comprising
 determining, by the data processing system, responsive to receiving a second audio input from the client device, that a second set of strings identified from the second audio input corresponds to a subset of candidate voice commands of the plurality of voice commands; and   selecting, by the data processing system, from the subset of candidate voice commands, a second voice command to be carried out based on a criterion.   
     
     
         43 . The method of  claim 34 , comprising
 determining, by the data processing system, responsive to receiving a second audio input from the client device, that a second set of strings identified from the second audio input corresponds to a second voice command of the plurality of voice commands; and   performing, by the data processing system, a second action in accordance with the second voice command of the plurality of voice commands determined to correspond to the second set of strings.