Virtual assistant acquisitions and training

Abstract

Techniques and architectures for implementing a team of virtual assistants are described herein. The team may include multiple virtual assistants that are configured with different characteristics, such as different functionality, base language models, levels of training, visual appearances, personalities, and so on. The characteristics of the virtual assistants may be configured by trainers, end-users, and/or a virtual assistant service. The virtual assistants may be presented to end-users in conversation user interfaces to perform different tasks for the users in a conversational manner. The different virtual assistants may adapt to different contexts. The virtual assistants may additionally, or alternatively, interact with each other to carry out tasks for the users, which may be illustrated in conversation user interfaces.

1 - 20 . (canceled) 
     
     
         21 . A system, comprising:
 one or more processors; and   a memory communicatively coupled to the one or more processors:   the memory storing executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 process input from a user; 
 formulate a response to the input from the user; 
 identify a customized virtual assistant having attributes related to characteristics of the user and the response to the input; and 
 providing the response to the input to the user wherein the response is presented by the customized virtual assistant. 
   
     
     
         22 . The system of  claim 21 , wherein the memory further stores executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 observe user activity to learn characteristics about a user, wherein the attributes of the customized virtual assistant are based on observed user activity.   
     
     
         23 . The system of  claim 21 , wherein the memory further stores executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 provide a virtual assistant trainer interface.   
     
     
         24 . The system of  claim 21 , wherein the memory further stores executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 identify one or more pieces of contextual information, wherein the attributes of the customized virtual assistant are based on identified pieces of contextual information.   
     
     
         25 . The system of  claim 21 , wherein the memory further stores executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 provide multiple ones of the customized virtual assistants in response to a user input.   
     
     
         26 . The system of  claim 25 , wherein the memory further stores executable instructions that, when executed by the one or more processors, cause the one or more processors to perform acts comprising:
 manage conversations between customized virtual assistants.   
     
     
         27 . The system of  claim 26 , wherein different characteristics of multiple customized virtual assistants comprise at least one of different task mappings, different language models, different types of functionality, different visual appearances, different audible manners of output, different levels of security, different levels of training, or different languages in which the multiple virtual assistants communicate. 
     
     
         28 . The system of  claim 21 , wherein the memory comprises one or more portioned memory stores comprising at least one of a virtual assistant conversation data store, a user characteristic data store, a context data store, and a virtual assistant data store. 
     
     
         29 . A system, comprising:
 a user computing device communicatively coupled to a network and comprising:
 a processor; and 
 an interactive user interface comprising a plurality of customized virtual assistants, the customized virtual assistants communicatively coupled to the processor and the network via the processor, wherein each customized virtual assistant of the plurality of virtual assistants has attributes related to characteristics of a user and a possible contexts of possible user inputs. 
   
     
     
         30 . The system of  claim 29 , wherein the possible contexts comprise at least one of:
 location of the user computing device, concepts identified from a user input, content accessed by the user computing device, and calendar events stored in the user computing device.   
     
     
         31 . The system of  claim 29 , wherein the user computing device comprises one of laptop computer, a desktop computer, a server, a smart phone, an electronic reader device, a mobile handset, a personal digital assistant, a portable navigation device, a portable gaming device, a tablet computer, a wearable computer, a portable media player, a television, a set-top box, a computer system in a car, an appliance, a camera, a robot, a hologram system, a security system, a home-based computer system, home media system, a projector, and an automated teller machine. 
     
     
         32 . A method of presenting a team of virtual assistants to a user via a user computing device, the method comprising:
 processing an input received from a user, the input received as an electrical communication signal from a communications network;   accessing data via one or more processors and a memory and formulating a response to the input ;   identifying a customized virtual assistant having attributes related to characteristics of the user and the response to the input; and   providing the response to the input to the user wherein the response is presented by the customized virtual assistant.   
     
     
         33 . The method of  claim 32 , further comprising:
 observe user activity to learn characteristics about a user, wherein the attributes of the customized virtual assistant are based on observed user activity.   
     
     
         34 . The method of  claim 32 , further comprising:
 proving a virtual assistant trainer interface.   
     
     
         35 . The method of  claim 32 , further comprising:
 identifying one or more pieces of contextual information, wherein the attributes of the customized virtual assistant are based on identified pieces of contextual information.   
     
     
         36 . The method of  claim 32 , further comprising:
 providing one or more of the customized virtual assistants in response to a user input.   
     
     
         37 . The method of  claim 32 , further comprising:
 managing conversations between customized virtual assistants.   
     
     
         38 . The method of  claim 32 , further comprising:
 presenting multiple customized virtual assistants to the user.   
     
     
         39 . The method of  claim 38 , wherein different characteristics of multiple characterized virtual assistants comprise at least one of different task mappings, different language models, different types of functionality, different visual appearances, different audible manners of output, different levels of security, different levels of training, or different languages in which the multiple virtual assistants communicate. 
     
     
         40 . The method of  claim 32 , wherein the memory comprises one or more portioned memory stores comprising at least one of a virtual assistant conversation data store, a user characteristic data store, a context data store, and a virtual assistant data store.