Predictive deletion of user input

Abstract

Described are techniques for predicting when data associated with a user input is likely to be selected for deletion. The system may use a trained model to assist with such predictions. The trained model can be configured based on deletions associated with a user profile. An example process can including receiving user input data corresponding to the user profile, and processing the user input data to determine a user command. Based on characteristic data of the user command, the trained model can be used to determine that data corresponding to the user command is likely to be selected for deletion. The trained model can be iteratively updated based on additional user commands, including previously received user commands to delete user input data.

1 .- 20 . (canceled) 
     
     
         21 . A computer-implemented method, comprising:
 receiving first input data corresponding to a first natural language user input;   processing the first input data using a trained model to determine a first user command corresponding to the first input data;   determining first data corresponding to the first input data;   storing the first data in a storage medium;   causing the first user command to be executed;   determining first characteristic data corresponding to the first data; and   processing the first characteristic data to determine that the first data stored in the storage medium is to be selected for deletion from the storage medium.   
     
     
         22 . The computer-implemented method of  claim 21 , further comprising:
 determining system configuration data; and   based at least in part on the system configuration data, causing the first data to be deleted after a period of time following receipt of the first input data.   
     
     
         23 . The computer-implemented method of  claim 21 , further comprising:
 determining user preference data; and   causing the first data to be deleted based at least in part on the user preference data.   
     
     
         24 . The computer-implemented method of  claim 23 , further comprising:
 determining a user profile corresponding to the first natural language user input; and   determining the user preference data is associated with the user profile.   
     
     
         25 . The computer-implemented method of  claim 21 , wherein the first characteristic data corresponds to a context of the first natural language user input. 
     
     
         26 . The computer-implemented method of  claim 21 , wherein the first characteristic data corresponds to time information. 
     
     
         27 . The computer-implemented method of  claim 21 , further comprising:
 causing the first data to be deleted based at least in part on a specified window of time.   
     
     
         28 . The computer-implemented method of  claim 21 , wherein the first data represents words of the first natural language user input. 
     
     
         29 . The computer-implemented method of  claim 21 , further comprising:
 determining, using the trained model, model output data corresponding to the processing of the first input data,   wherein the first data represents the model output data.   
     
     
         30 . The computer-implemented method of  claim 21 , further comprising:
 determining an identifier corresponding to a user of the first natural language user input,   wherein the first data represents the identifier.   
     
     
         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 first input data corresponding to a first natural language user input; 
 process the first input data using a trained model to determine a first user command corresponding to the first input data; 
 determine first data corresponding to the first input data; 
 store the first data in a storage medium; 
 cause the first user command to be executed; 
 determine first characteristic data corresponding to the first data; and 
 process the first characteristic data to determine that the first data stored in the storage medium is to be selected for deletion from the storage medium. 
   
     
     
         32 . 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:
 determine system configuration data; and   based at least in part on the system configuration data, cause the first data to be deleted after a period of time following receipt of the first input data.   
     
     
         33 . 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:
 determine user preference data; and   cause the first data to be deleted based at least in part on the user preference data.   
     
     
         34 . The system of  claim 33 , wherein the at least one memory further comprises instructions that, when executed by the at least one processor, further cause the system to:
 determine a user profile corresponding to the first natural language user input; and   determine the user preference data is associated with the user profile.   
     
     
         35 . The system of  claim 31 , wherein the first characteristic data corresponds to a context of the first natural language user input. 
     
     
         36 . The system of  claim 31 , wherein the first characteristic data corresponds to time information. 
     
     
         37 . 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:
 cause the first data to be deleted based at least in part on a specified window of time.   
     
     
         38 . The system of  claim 31 , wherein the first data represents words of the first natural language user input. 
     
     
         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:
 determine, using the trained model, model output data corresponding to the processing of the first input data,   wherein the first data represents the model output data.   
     
     
         40 . 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:
 determine an identifier corresponding to a user of the first natural language user input,   wherein the first data represents the identifier.