Providing intelligent storage location suggestions
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.
1. A method comprising:
determining, by at least one processor, characteristics of a plurality 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 trained to classify new content items based on the characteristics associated with the plurality of content items stored in the plurality of storage locations, storage location scores for a group of content items;
determining, by the at least one processor and based on the storage location scores, a storage location of the plurality of storage locations;
providing a recommendation to store the group of content items in a new storage location within a parent location of the determined storage location; and
moving, in response to a user input selecting the new storage location, the group of content items together as a group to the new storage location within the parent location.
2. The method as recited in claim 1 , wherein the machine-learning model comprises a plurality of classifiers for the plurality of storage locations associated with the user account.
3. The method as recited in claim 2 , wherein determining the storage location scores for the group of content items comprises determining that the group of content items comprise a shared characteristic by determining the shared characteristic using a first classifier of the machine-learning model based on a first characteristic that a first plurality of content items in a first storage location have in common and a second classifier of the machine-learning model based on a second characteristic that a second plurality of content items in a second storage location have in common.
4. The method as recited in claim 3 , wherein:
determining the storage location scores for the group of content items comprises determining, using the machine-learning model, that each content item in the group of content items corresponds to the first classifier associated with the first characteristic; and
determining the storage location of the plurality of storage locations comprises determining the first storage location as a recommended storage location.
5. The method as recited in claim 2 , wherein the plurality of classifiers for the plurality of storage locations associated with the user account are weighted based on priorities associated with the characteristics.
6. The method as recited in claim 2 , further comprising:
determining the storage location scores for the group of content items by scoring, using the plurality of classifiers, the plurality of storage locations for the group of content items; and
providing, for display within a user interface, a graphical element indicating the recommendation to store the group of content items in the new storage location by determining that a storage location score associated with the parent location comprises a highest score from the plurality of storage locations.
7. The method as recited in claim 6 , further comprising providing, for display within the user interface, a subset of storage locations from the plurality of storage locations in an order based on the storage location scores.
8. The method as recited in claim 7 , further comprising determining that each storage location in the subset of storage locations meets a predetermined score threshold.
9. The method as recited in claim 1 , further wherein providing the recommendation to store the group of content items in the new storage location comprises providing a recommendation to create the new storage location at a particular location in a file structure associated with the user account.
10. The method as recited in claim 1 , further comprising:
storing the group of content items in a temporary storage location with a plurality of additional content items in response to the group of content items being stored in a default storage location during a first login session; and
providing the recommendation to store the group of content items in the new storage location in response to establishing a second login session.
11. 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 a plurality of content items stored in a plurality of storage locations associated with a user account;
determine, using a machine-learning model trained to classify new content items based on the characteristics associated with the plurality of content items stored in the plurality of storage locations, storage location scores for a group of content items;
determine, based on the storage location scores, a storage location of the plurality of storage locations;
provide a recommendation to store the group of content items in a new storage location within a parent location of the determined storage location; and
move, in response to a user input selecting the new storage location, the group of content items together as a group to the new storage location within the parent location.
12. The system as recited in claim 11 , wherein the machine-learning model comprises a plurality of classifiers for the plurality of storage locations associated with the user account.
13. The system as recited in claim 12 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine the storage location scores for the group of content items by determining, using the machine-learning model, that each content item in the group of content items corresponds to a classifier associated with a shared characteristic of the group of content items from the plurality of classifiers; and
determine the storage location of the plurality of storage locations by determining that the storage location corresponds to the classifier associated with the shared characteristic.
14. The system as recited in claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to:
determine the storage location scores for the group of content items by scoring, using the machine-learning model, the plurality of storage locations for the group of content items; and
provide, for display within a user interface, a graphical element indicating the recommendation to store the group of content items in the new storage location by determining that a storage location score associated with the determined storage location comprises a highest score from the plurality of storage locations.
15. The system as recited in claim 14 , further comprising instructions that, when executed by the at least one processor, cause the system to provide, for display within the user interface, a subset of storage locations from the plurality of storage locations in an order based on the storage location scores, wherein each storage location in the subset of storage locations meets a predetermined score threshold.
16. The system as recited in claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to create the new storage location at a particular location in a file structure associated with the user account.
17. The system as recited in claim 11 , further comprising instructions that, when executed by the at least one processor, cause the system to:
store the group of content items in a temporary storage location with a plurality of additional content items during a first login session for the user account; and
provide a recommendation to store the group of content items in the new storage location in response to establishing a second login session for the user account.
18. 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 a plurality of content items stored in a plurality of storage locations associated with a user account;
determine, using a machine-learning model trained to classify new content items based on the characteristics of the plurality of content items stored in the plurality of storage locations, storage location scores for a group of content items;
determine, based on the storage location scores, a storage location of the plurality of storage locations;
provide a recommendation to store the group of content items in a new storage location within a parent location of the determined storage location; and
move, in response to a user input selecting the new storage location, the group of content items together as a group to the new storage location within the parent location.
19. The non-transitory computer readable storage medium as recited in claim 18 , further comprising instructions that, when executed by at least one processor, cause the computer system to:
determine the storage location scores for the group of content items by determining, using the machine-learning model, that each content item in the group of content items corresponds to a trained classifier associated with a shared characteristic of the group of content items; and
determine the storage location of the plurality of storage locations by determining that the storage location corresponds to the trained classifier associated with the shared characteristic.
20. The non-transitory computer readable storage medium as recited in claim 18 , further comprising instructions that, when executed by at least one processor, cause the computer system to:
determine the storage location scores for the group of content items by scoring, using the machine-learning model, the plurality of storage locations for the group of content items; and
provide, for display within a user interface, a graphical element indicating the recommendation to store the group of content items in the new storage location by determining that the storage location associated with the parent location comprises a highest score from the plurality of storage locations.