Response endpoint selection

Abstract

A computing system has multiple endpoint computing devices in local environments to receive verbal requests from various users and a central or remote system to process the requests. The remote system generates responses and uses a variety of techniques to determine where and when to return responses audibly to the users. For each request, the remote system understands who is making the request, determines when to provide the response to the user, ascertains where the user is when it is time to deliver the response, discovers which of the endpoint devices are available to deliver the response, and evaluates which of the available devices is best to deliver the response. The system then delivers the response to the best endpoint device for audible emission or other form of presentation to the user.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method, comprising:
 receiving, from a first device, input audio data corresponding to an input from a first user;   processing the input audio data to determine a request to provide a message to a second user, the second user associated with at least a second device and a third device;   receiving second data corresponding to a location of the second user; and   based at least in part on the second data, causing output data corresponding to the message to be sent to the second device rather than the third device.   
     
     
         22 . The computer-implemented method of  claim 21 , wherein processing the input audio data to determine the request comprises performing automatic speech recognition using the input audio data to determine text data representing the input. 
     
     
         23 . The computer-implemented method of  claim 21 , further comprising:
 determining the second user is associated with user profile data; and   identifying the second device using the user profile data.   
     
     
         24 . The computer-implemented method of  claim 21 , wherein receiving the second data comprises receiving global positioning system (GPS) data. 
     
     
         25 . The computer-implemented method of  claim 21 , wherein receiving the second data comprises receiving Wi-Fi data. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein receiving the second data comprises receiving cell tower data. 
     
     
         27 . The computer-implemented method of  claim 21 , wherein the second device comprises a smartphone. 
     
     
         28 . The computer-implemented method of  claim 21 , further comprising:
 determining user profile data corresponding to the first user; and   determining the second user using the user profile data.   
     
     
         29 . The computer-implemented method of  claim 21 , wherein the second data is received from the second device. 
     
     
         30 . The computer-implemented method of  claim 21 , wherein the output data comprises output audio data and the method further comprises:
 sending the output audio data to the second device; and   sending the second device a command that causes the second device to output audio corresponding to the output audio data.   
     
     
         31 . The computer-implemented method of  claim 21 , further comprising:
 sending the second device a command that causes the second device to display a visual output corresponding to the output data.   
     
     
         32 . 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 first device, input audio data corresponding to an input from a first user; 
 process the input audio data to determine a request to provide a message to a second user, the second user associated with at least a second device and a third device; 
 receive second data corresponding to a location of the second user; 
 based at least in part on the second data, select the second device rather than the third device; and 
 cause output data corresponding to the message to be sent to the second device. 
   
     
     
         33 . The system of  claim 32 , wherein the instructions that cause the system to process the input audio data to determine the request comprise instructions that, when executed by the at least one processor, cause the system to perform automatic speech recognition using the input audio data to determine text data representing the input. 
     
     
         34 . The system of  claim 32 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine the second user is associated with user profile data; and   select the second device based further at least in part on the user profile data.   
     
     
         35 . The system of  claim 32 , wherein the second data comprises global positioning system (GPS) data. 
     
     
         36 . The system of  claim 32 , wherein the second data comprises Wi-Fi data. 
     
     
         37 . The system of  claim 32 , wherein the second data comprises cell tower data. 
     
     
         38 . The system of  claim 32 , wherein the second device comprises a smartphone. 
     
     
         39 . The system of  claim 32 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine user profile data corresponding to the first user; and   determine the second user using the user profile data.   
     
     
         40 . The system of  claim 32 , The system of  claim 32 , wherein the output data comprises output audio data and 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 output audio data to the second device; and   send the second device a command that causes the second device to output audio corresponding to the message.