Providing intelligent storage location suggestions

Abstract

One or more embodiments of a content system provide machine-learned storage location recommendations for storing content items. Specifically, an online content management system can train a machine-learning model to identify a storage pattern from previously stored content items in a plurality of storage locations corresponding to a user account of a user. Training the machine-learning model includes training a plurality of classifiers for the plurality of storage locations. The online content management system uses the classifiers to determine whether a content item is similar to the content items in any of the storage locations, and based on the output of the classifiers, provides graphical elements indicating recommended storage locations within a graphical user interface. The user can select a graphical element to move the content item to the corresponding storage location.

What is claimed is: 
     
         1 . A method comprising:
 determining, by at least one processor, characteristics of content items stored in a plurality of storage locations associated with a user account;   determining, by the at least one processor and using a machine-learning model comprising classifiers trained to classify new content items based on the characteristics associated with the content items stored in the plurality of storage locations, rankings for a new content item stored in a first storage location;   determining, by the at least one processor and based on the rankings, a second storage location of the plurality of storage locations; and   providing, for display within a graphical user interface in response to establishing a login session for the user account, a recommendation to store the new content item in the second storage location of the plurality of storage locations.   
     
     
         2 . The method as recited in  claim 1 , further comprising:
 receiving, via the graphical user interface, a user input comprising a selection of the second storage location in response to the recommendation; and   moving the new content item from the first storage location to the second storage location in response to the selection of the second storage location.   
     
     
         3 . The method as recited in  claim 2 , further comprising updating the classifiers of the machine-learning model in response to moving the new content item to the second storage location. 
     
     
         4 . The method as recited in  claim 1 , further comprising receiving the new content item for storage within the first storage location during a previous login session. 
     
     
         5 . The method as recited in  claim 1 , wherein determining the rankings for the new content item comprises:
 determining, utilizing the machine-learning model, storage patterns for a first group of related user accounts comprising the user account based on content items associated with the first group of related user accounts; and   generating the rankings based on the storage patterns determined for the first group of related user accounts.   
     
     
         6 . The method as recited in  claim 5 , further comprising:
 determining, utilizing an additional machine-learning model, storage patterns for a second group of related user accounts based on content items associated with the second group of related user accounts, the first group of related user accounts comprising different user accounts than the second group of related user accounts; and   generating rankings for storing new content items associated with the second group of related user accounts.   
     
     
         7 . The method as recited in  claim 5 , further comprising:
 assigning a first weight to a first related user account of the first group of related user accounts and a second weight to a second related user account of the first group of related user accounts, the first weight being different than the second weight; and   training the classifiers based on the first weight and the second weight to determine the storage patterns weighted toward content items of the first related user account.   
     
     
         8 . The method as recited in  claim 1 , further comprising training the classifiers by assigning a first weight to a most recently stored content item in the plurality of storage locations and a second weight to a content item stored before the most recently stored content item, the first weight being different than the second weight. 
     
     
         9 . The method as recited in  claim 1 , further comprising:
 determining, using the machine-learning model, additional rankings for an additional new content item stored in the first storage location;   determining, based on the rankings, an additional storage location of the plurality of storage locations; and   providing, for display within the graphical user interface in response to establishing the login session for the user account, an additional recommendation to store the additional new content item in the additional storage location of the plurality of storage locations.   
     
     
         10 . The method as recited in  claim 1 , further comprising:
 providing, for display within the graphical user interface, a first portion of a client application comprising content items stored in the first storage location; and   providing, for display within the graphical user interface, a second portion of the client application comprising a graphical element corresponding to the second storage location.   
     
     
         11 . A non-transitory computer readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:
 determine characteristics of content items stored in a plurality of storage locations associated with a user account;   determine, using a machine-learning model comprising classifiers trained to classify new content items based on the characteristics associated with the content items stored in the plurality of storage locations, rankings for a new content item stored in a first storage location;   determine, based on the rankings, a second storage location of the plurality of storage locations;   provide, for display within a graphical user interface in response to establishing a login session for the user account, a recommendation to store the new content item in the second storage location of the plurality of storage locations; and   move, in response to a user input selecting the second storage location, the new content item from the first storage location to the second storage location.   
     
     
         12 . The non-transitory computer readable storage medium as recited in  claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
 update the classifiers of the machine-learning model in response to moving the new content item to the second storage location; and   determine, using the machine-learning model with the updated classifiers, additional rankings for an additional new content item stored in the first storage location.   
     
     
         13 . The non-transitory computer readable storage medium as recited in  claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
 determine the classifiers of the machine-learning model based on characteristics associated with content items of a group of related user accounts comprising the user account; and   generate, using the machine-learning model, rankings for each new content item associated with each user account of the group of related user accounts.   
     
     
         14 . The non-transitory computer readable storage medium as recited in  claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer system to:
 determine a default storage location associated with the user account as the first storage location; and   store the new content item and additional new content items in the default storage location in response to the new content item and the additional new content items being stored for the user account.   
     
     
         15 . The non-transitory computer readable storage medium as recited in  claim 11 , further comprising instructions that, when executed by the at least one processor, cause the computer system to establish the login session for the user account by:
 determining that a previous session associated with the user account was terminated; and   establish a new login session for the user account in response to determining the previous session was terminated.   
     
     
         16 . A system comprising:
 at least one processor; and   a non-transitory computer readable storage medium comprising instructions that, when executed by the at least one processor, cause the system to:
 determine characteristics of content items stored in a plurality of storage locations associated with a user account; 
 determine, using classifiers trained to classify new content items based on the characteristics associated with the content items stored in the plurality of storage locations, rankings for a new content item stored in a first storage location; 
 provide, for display within a graphical user interface in response to establishing a login session for the user account, a recommendation to store the new content item in a second storage location of the plurality of storage locations according to the rankings; and 
 move, in response to a user input selecting the second storage location, the new content item from the first storage location to the second storage location. 
   
     
     
         17 . The system as recited in  claim 16 , further comprising instructions that, when executed by the at least one processor, cause the system to provide the recommendation by providing, for display within the graphical user interface, a split view within a client application, the split view comprising:
 a first portion of the client application including content items stored in the first storage location; and   a second portion of the client application including a graphical element corresponding to the second storage location.   
     
     
         18 . The system as recited in  claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to provide the split view within the client application in response to establishing the login session for the user account. 
     
     
         19 . The system as recited in  claim 17 , further comprising instructions that, when executed by the at least one processor, cause the system to determine the rankings for the new content item based on content items associated with a plurality of related user accounts comprising the user account, wherein the classifiers are trained based on characteristics of the content items associated with the plurality of related user accounts. 
     
     
         20 . The system as recited in  claim 16 , further comprising instructions that, when executed by the at least one processor, cause the system to:
 update the classifiers in response to moving the new content item to the second storage location;   receive a request to store an additional new content item;   determine, using the updated classifiers, additional rankings for the additional new content item;   determine, based on the additional rankings, an additional storage location of the plurality of storage locations; and   provide, for display within the graphical user interface, an additional recommendation to store the additional new content item in the additional storage location of the plurality of storage locations.