Device-specific skill processing

Abstract

Techniques for configuring device-specific skills as top-level skills are described. When a system receives a user input the system performs NLU processing to determine an intent of the user input. In some instances, the system may identify a device-specific skill associated with the device interacted with by the user. At least partially in parallel to performing NLU processing to determine the intent of the user input, the system may also perform NLU processing to determine a likelihood that the user input corresponds to an intent actionable by the device-specific skill. Once the system has finished NLU processing, the system may implement one or more prioritization rules to determine whether the user input should be sent to the device-specific skill or another skill of the system.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method, comprising:
 receiving, from a device, input data representing a first natural language user input;   processing the input data using a first component to determine first data;   processing the input data using a second component to determine second data;   receiving, from the device, third data representing a context of the first natural language user input; and   based at least in part on the third data, causing further processing to be performed using the first data to be performed in response to the first natural language user input.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein the third data includes data corresponding to a wakeword. 
     
     
         23 . The computer-implemented method of  claim 21 , wherein the third data includes a device identifier. 
     
     
         24 . The computer-implemented method of  claim 21 , wherein the third data represents a type of the device. 
     
     
         25 . The computer-implemented method of  claim 21 , wherein the third data represents a profile associated with the device. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein:
 the first component comprises a first speech processing component corresponding to a type of the device; and   the second component comprises a second speech processing component.   
     
     
         27 . The computer-implemented method of  claim 21 , wherein:
 the first data comprises first natural language understanding (NLU) data;   the second data comprises second NLU data; and   the further processing comprises executing an action represented by the first NLU data.   
     
     
         28 . The computer-implemented method of  claim 21 , further comprising:
 processing the third data and the first data to determine first score data;   processing the third data and the second data to determine second score data; and   processing the first score data and the second score data to select the first data for further processing.   
     
     
         29 . The computer-implemented method of  claim 21 , further comprising:
 sending the input data to the first component based at least in part on the device.   
     
     
         30 . The computer-implemented method of  claim 21 , wherein causing further processing comprises sending the first data to a third component associated with the device. 
     
     
         31 . A system comprising:
 at least one processor; and   at least one memory comprising instructions that, when executed by the at least one processor, cause the system to:
 receive, from a device, input data representing a first natural language user input; 
 process the input data using a first component to determine first data; 
 process the input data using a second component to determine second data; 
 receive, from the device, third data representing a context of the first natural language user input; and 
 based at least in part on the third data, cause further processing to be performed using the first data to be performed in response to the first natural language user input. 
   
     
     
         32 . The system of  claim 31 , wherein the third data includes data corresponding to a wakeword. 
     
     
         33 . The system of  claim 31 , wherein the third data includes a device identifier. 
     
     
         34 . The system of  claim 31 , wherein the third data represents a type of the device. 
     
     
         35 . The system of  claim 31 , wherein the third data represents a profile associated with the device. 
     
     
         36 . The system of  claim 31 , wherein:
 the first component comprises a first speech processing component corresponding to a type of the device; and   the second component comprises a second speech processing component.   
     
     
         37 . The system of  claim 31 , wherein:
 the first data comprises first natural language understanding (NLU) data;   the second data comprises second NLU data; and   the further processing comprises executing an action represented by the first NLU data.   
     
     
         38 . The system of  claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 process the third data and the first data to determine first score data;   process the third data and the second data to determine second score data; and   process the first score data and the second score data to select the first data for further processing.   
     
     
         39 . The system of  claim 31 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 send the input data to the first component based at least in part on the device.   
     
     
         40 . The system of  claim 31 , wherein the instructions that cause further processing comprise instructions that, when executed by the at least one processor, cause the system to send the first data to a third component associated with the device.