Providing intelligent storage location suggestions

Patent metadata

Field	Value
Publication number	US-9852377-B1
Application number	US-201615348616-A
Country	US
Kind code	B1
Filing date	Nov 10, 2016
Priority date	Nov 10, 2016
Publication date	Dec 26, 2017
Grant date	Dec 26, 2017

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.

First claim

What is claimed is:

1. A method comprising:
determining, by at least one processor, characteristics of a plurality of content items stored in a storage location, the storage location associated with a user account;
training, by the at least one processor, a machine-learning model using a plurality of classifiers for a plurality of storage locations associated with a plurality of user accounts, the plurality of classifiers comprising a classifier based on the characteristics of the plurality of content items in the storage location associated with a user account;
determining, by the at least one processor in response to a request to store an identified content item and using the machine-learning model, that the identified content item is similar to the plurality of content items stored in the storage location associated with the user account; and
providing, for display within a user interface and based on determining that the identified content item is similar to the plurality of content items using the machine-learning model, a graphical element indicating a recommendation to store the identified content item in the storage location associated with the user account.

2. The method as recited in claim 1 , wherein determining the characteristics of the plurality of content items stored in the storage location comprises determining one or more characteristics that the plurality of content items have in common.

3. The method as recited in claim 1 , wherein training the machine-learning model comprises applying, for the classifier for the storage location associated with the user account, a weight to each characteristic from the determined characteristics of the plurality of content items stored in the storage location associated with the user account.

4. The method as recited in claim 1 , wherein training the machine-learning model comprises:
training, for the plurality of storage locations, the plurality of classifiers based on characteristics of a plurality of content items in each of the plurality of storage locations; and
associating, using the plurality of classifiers for the plurality of storage locations, the identified content item with the storage location associated with the user account.

5. The method as recited in claim 4 , further comprising:
scoring, using the plurality of classifiers, the plurality of storage locations for the identified content item; and
providing, for display within the user interface, a graphical element indicating a recommendation to store the identified content item in a storage location with a highest score from the plurality of storage locations.

6. The method as recited in claim 5 , further comprising providing, for display within the user interface, the plurality of storage locations in an order based on rankings associated with the plurality of storage locations.

7. The method as recited in claim 1 , wherein training the machine-learning model comprises determining one or more characteristics of the plurality of content items stored in the storage location associated with the user account that distinguish the storage location associated with the user account from one or more other storage locations in the plurality of storage locations associated with the plurality of user accounts.

8. The method as recited in claim 1 , further comprising:
identifying a parent location of the storage location associated with the user account; and
providing an additional recommendation to store the identified content item in a new storage location within the identified parent location of the storage location associated with the user account.

9. A method comprising:
determining characteristics of a plurality of content items stored in a plurality of storage locations associated with a user account;
training, based on the determined characteristics of the plurality of content items for the plurality of storage locations, a plurality of classifiers for the plurality of storage locations;
receiving one or more new content items for the user account;
storing the one or more new content items in a temporary storage location;
using the plurality of classifiers to identify one or more recommended storage locations for each of the one or more new content items;
providing, within a user interface in response to establishing a user login session for the user account, a subset of recommended storage locations for a content item from the one or more new content items according to a ranking associated with the one or more recommended storage locations for the content item, wherein the subset of recommended storage locations meet a predetermined threshold; and
receiving, by way of the user interface, user input comprising a selection of a recommend storage location for the content item from the one or more new content items.

10. The method as recited in claim 9 , further comprising:
receiving, by way of the user interface, a first user input comprising a selection of a first new content item from the one or more new content items; and
providing, within the user interface in response to the first user input, a first subset of recommended storage locations for the first new content item.

11. The method as recited in claim 10 , further comprising:
receiving, by way of the user interface, a second user input comprising a selection of a second new content item from the one or more new content items; and
providing, within the user interface in response to the second user input, a second subset of recommended storage locations for the second new content item, wherein the second subset of recommended storage locations for the second new content item comprise at least one recommended storage location that is different than the first subset of recommended storage locations for the first new content item.

12. The method as recited in claim 9 , further comprising:
providing, within the user interface, a first view comprising the one or more new content items in the temporary storage location; and
providing, within the user interface, a second view comprising the one or more recommended storage locations.

13. The method as recited in claim 9 , further comprising:
determining that a group of content items in the temporary storage location comprise a shared characteristic;
providing, within the user interface based on the shared characteristic, a recommended storage location for the group of content items;
receiving, by way of the user interface, user input comprising a selection of the recommended storage location for the group of content items; and
moving, in response to the selection of the recommended storage location for the group of content items, the group of content items from the temporary storage location to the recommended storage location for the group of content items.

14. 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 storage location associated with a user account;
traine a machine-learning model using a plurality of classifiers for a plurality of storage locations associated with a plurality of user accounts, the plurality of classifiers comprising a classifier based on the characteristics of the plurality of content items in the storage location associated with a user account;
use the machine-learning model to identify a recommended storage location for a new content item in connection with the user account;
provide, within a user interface, the recommended storage location fo

Assignees

• Dropbox Inc

Inventors

• Kumar Neeraj

Classifications

• G06F16/25

  Integrating or interfacing systems involving database management systems · CPC title

• G06F16/168

  Details of user interfaces specifically adapted to file systems, e.g. browsing and visualisation, 2d or 3d GUIs (query results presentation G06F16/156) · CPC title

• G06F16/90324

  using system suggestions · CPC title

• G06F16/24578

  using ranking · CPC title

• G06F16/285

  Clustering or classification · CPC title