Mapping actions and objects to tasks

Abstract

Techniques for mapping actions and objects to tasks may include identifying a task to be performed by a virtual assistant for an action and/or object. The task may be identified based on a task map of the virtual assistant. In some examples, the task may be identified based on contextual information of a user, such as a conversation history, content output history, user preferences, and so on. The techniques may also include customizing a task map for a particular context, such as a particular user, industry, platform, device type, and so on. The customization may include assigning an action, object, and/or variable value to a particular task.

1 . One or more computer-readable storage media storing computer-readable instructions that, when executed, instruct one or more processors to perform operations, comprising:
 obtaining user input that is received at a smart device during a conversation between a user and a virtual assistant, the user input comprising at least one variable providing information for performing a task;   analyzing the user input to determine the at least one variable and associating the at least one variable with at least one of an action and an object;   identifying a task that is associated with the at least one of the action [[or]] and the object; and   causing the task to be at least partly performed by the virtual assistant.   
     
     
         2 .- 22 . (canceled) 
     
     
         23 . The one or more computer readable storage media of  claim 1 , further comprising deriving a value of the at least one variable of the user input based on the contextual information. 
     
     
         24 . The one or more computer-readable storage media of  claim 1 , wherein the action comprises a verb and the object comprises a noun. 
     
     
         25 . The one or more computer-readable storage media of  claim 1 , wherein the identifying the task comprises:
 identifying one or more tasks in a task map that are associated with the at least one of the action and the object; and   identifying a task, from among the one or more tasks, that is associated with a score that is greater than a threshold and/or that is a single task that is identified in the task map.   
     
     
         26 . The one or more computer-readable storage media of  claim 1 , wherein the identifying the task comprises:
 identifying multiple tasks in a task map that are each associated with at least one of the action or the object;   causing the user to be prompted for additional information regarding the multiple tasks; and   obtaining further user input identifying one of the multiple tasks that is to be performed by the virtual assistant.   
     
     
         27 . The one or more computer-readable storage media of  claim 1 , wherein the identifying the task comprises:
 identifying multiple tasks in a task map that are each associated with at least one of the action or the object;   assigning a score to each of the multiple tasks based at least in part on information related to at least one of the user or the conversation;   ranking the multiple tasks based at least in part on the scores of the multiple tasks; and   selecting a task from the ranked multiple tasks.   
     
     
         28 . The one or more computer-readable storage media of  claim 1 , wherein the task is identified based at least in part on contextual information. 
     
     
         29 . The one or more computer-readable storage media of  claim 1 , wherein the operations further comprise:
 upon identifying the task   obtaining a value for the variable by at least one of causing the user to be prompted for further user input or analyzing contextual information related to at least one of the user or the conversation.   
     
     
         30 . The one or more computer-readable storage media of  claim 1 , wherein the operations further comprise:
 learning information to be associated with the task based at least in part on the conversation between the user and the virtual assistant, the information comprising at least one of the action, the object, or a value of a variable for the task.   
     
     
         31 . A method comprising:
 under control of one or more computing devices configured with executable instructions,   causing a conversation user interface to be output on a smart device to enable a conversation between a user of the smart device and a virtual assistant;   obtaining user input that is received at the smart device during the conversation, the user input comprising at least one variable providing information for performing a task;   analyzing the user input to determine the at least one variable and associating the at least one variable with at least one of an action and an object;   identifying a task that is associated with the at least one of the action and the object; and   causing the task to be at least partly performed by the virtual assistant.   
     
     
         32 . The method of  claim 31 , wherein the analyzing comprises learning information to be associated with the task to be performed by the virtual assistant based at least in part on the conversation of the virtual assistant with the user, the information comprising at least one of the action, the object and a value of the at least one variable. 
     
     
         33 . The method of  claim 32 , wherein the learning comprises:
 identifying input that is received from the user during the conversation;   determining that one or more criteria are not satisfied to classify a particular task that was performed by the virtual assistant for the input as an accurately identified task;   identifying a task that was initiated by the user after the particular task was performed by the virtual assistant; and   identifying at least one of an action or an object of the input to be associated with the task that was initiated by the user.   
     
     
         34 . The method of  claim 32 , wherein:
 the information to be associated with the task to be performed comprises at least one of a current conversation history of the user with the virtual assistant, a previous conversation history of the user with the virtual assistant, input of the user that requests that the at least one task be associated with the particular action-object pair, content output history of the user that identifies content that has been output to the user, user preference information indicating one or more preferences of the user, or device information indicating a type of device that is used by the user.   
     
     
         35 . The method of  claim 31 , wherein the learning comprises:
 identifying a request that is received from the user during the conversation, the request requesting to associate a particular term or phrase with the task.   
     
     
         36 . A method comprising:
 under control of one or more computing devices configured with executable instructions,   causing a conversation user interface to be output on a smart device to enable a conversation between a user of the smart device and a virtual assistant;   analyzing the conversation to determine at least one of an action or an object;   identifying a task that is associated with at least one of the action or the object;   identifying a variable associated with performance of the task; and   obtaining a value for the variable by analyzing contextual information that is related to at least one of the conversation.   
     
     
         37 . The method of  claim 36 , wherein the obtaining the value for the variable comprises analyzing the contextual information that is related to at least one of the conversation or the user, the contextual information comprising at least one of a previous conversation between the user and the virtual assistant, preference information indicating a preference of the user, or content output history that identifies content that has been output to the user. 
     
     
         38 . The method of  claim 37 , wherein the obtaining the value for the variable comprises determining that a term or phrase in contextual information corresponds to the value for the variable based on at least one of a word type or category of the term or phrase. 
     
     
         39 . The method of  claim 36 , wherein at least one of identifying the task or obtaining the value for the variable includes utilizing a goal-based dialog. 
     
     
         40 . The method of  claim 36 , wherein the virtual assistant is configured for at least one of multi-modal input/out, multi-language communication, or multi-channel communication.