Classifying and organizing digital content items automatically utilizing content item classification models
The present disclosure relates to systems, methods, and non-transitory computer-readable media that utilize machine-learning models to classify content items and automatically organize the content items within a file structure according to their content item classifications. For instance, a content item classification system generates one or more content item classification models to determine classifications for content items and/or folders. In some instances, the classification system detects when new content items are added to a smart folder, determines destination folders to which the content items belong based on classifying the content items, and automatically moves the content items accordingly. In various instances, the classification system generates and utilizes a classification model to organize content items into dynamically-generated folders. In example implementations, the classification system generates and utilizes a classification model to automatically organize existing content items into existing folders.
1 . A system comprising:
at least one processor; and
a non-transitory computer memory comprising instructions that, when executed by the at least one processor, cause the system to:
generate, within a digital file structure comprising a plurality of folders for storing content items, a first automated smart folder that, according to user input defining a first function of the first automated smart folder, triggers classification of content items into subfolder classifications for subfolders nested in the first automated smart folder upon detecting addition of the content items to the first automated smart folder;
generate, within the digital file structure, a second automated smart folder that, according to user input defining a second function of the second automated smart folder, triggers performing the second function upon detecting addition of other content items to the second automated smart folder;
detect an addition of a content item to the first automated smart folder, wherein detecting the addition of the content item to the first automated smart folder triggers classification of the content item into one or more of the subfolder classifications for the subfolders nested in the first automated smart folder; and
in response to detecting the addition of the content item to the first automated smart folder:
classify the content item to a first classification from the subfolder classifications corresponding to the subfolders; and
move the content item to a subfolder corresponding to the first classification from among the subfolders nested in the first automated smart folder.
2 . The system of claim 1 , further comprising instructions that cause the system to classify the content item to the first classification utilizing a classification machine-learning model based on correlating the content item to one or more existing content items within the subfolder.
3 . The system of claim 1 , further comprising instructions that cause the system to generate a classification machine-learning model utilized to classify the content item by re-training a pre-trained classification machine-learning model based on correlating the subfolder classifications with existing content items within the subfolders.
4 . The system of claim 1 , further comprising instructions that cause the system to provide, for display at a client device, a graphical user interface that enables selecting the first automated smart folder as a source folder and the subfolders as destination folders.
5 . The system of claim 1 , further comprising instructions that cause the system to determine, from among a plurality of automated folder types defining respective automations to perform on newly added content items, an automated folder type for the first automated smart folder, wherein the automated folder type designates the first automated smart folder for classifying the content items into the subfolder classifications for the subfolders nested in the first automated smart folder upon addition of the content items to the first automated smart folder.
6 . A computer-implemented method comprising:
generating, within a digital file structure comprising a plurality of folders for storing content items, a first automated smart folder that, according to user input defining a first function of the first automated smart folder, triggers classification of content items into subfolder classifications for subfolders nested in the first automated smart folder upon detecting addition of the content items to the first automated smart folder;
generating, within the digital file structure, a second automated smart folder that, according to user input defining a second function of the second automated smart folder, triggers performing the second function upon detecting addition of other content items to the second automated smart folder;
detecting an addition of a content item to the first automated smart folder, wherein detecting the addition of the content item to the first automated smart folder triggers classification of the content item into one or more of the subfolder classifications for the subfolders nested in the first automated smart folder; and
in response to detecting the addition of the content item to the first automated smart folder:
classifying the content item to a first classification from the subfolder classifications; and
moving the content item from the first automated smart folder to a destination folder associated with the first classification based on classifying the content item to the first classification.
7 . The computer-implemented method of claim 6 , wherein the destination folder is a subfolder of the first automated smart folder.
8 . The computer-implemented method of claim 6 , further comprising:
determining that a folder corresponding to the first classification does not exist based on classifying the content item to the first classification utilizing a classification machine-learning model; and
generating the destination folder to correspond to the first classification based on determining that the folder corresponding to the first classification does not exist.
9 . The computer-implemented method of claim 6 , further comprising generating, for a classification machine-learning model, the subfolder classifications automatically based on analyzing a plurality of content items.
10 . The computer-implemented method of claim 6 , further comprising adding the content item to the first automated smart folder based on receiving the content item via a camera upload.
11 . The computer-implemented method of claim 6 , further comprising generating, for a classification machine-learning model, the subfolder classifications automatically based on search queries of a plurality of content items.
12 . The computer-implemented method of claim 6 , further comprising generating the subfolder classifications for a classification machine-learning model based on the subfolders within the first automated smart folder.
13 . The computer-implemented method of claim 6 , further comprising classifying the content item to the first classification utilizing a classification machine-learning model based on correlating the content item to one or more existing content items within the destination folder.
14 . The computer-implemented method of claim 6 , further comprising classifying the content item to the first classification utilizing a classification machine-learning model based on analyzing text-readable content item data of the content item.
15 . The computer-implemented method of claim 6 , further comprising:
detecting an addition of an additional content item to the first automated smart folder;
classifying the additional content item to a second classification from the subfolder classifications utilizing a classification machine-learning model; and
moving the additional content item from the first automated smart folder to a folder associated with the second classification based on classifying the additional content item to the second classification.
16 . A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computer system to:
generate, within a digital file structure comprising a plurality of folders for storing content items, a first automated smart folder that, according to user input defining a first function of the first automated smart folder, triggers classification of content items into subfolder classifications for subfolders nested in the first automated smart folder upon detecting addition of the content items to the first automated smart folder;
generate, within the digital file structure, a second automated smart folder that, according to user input defining a second function of the second automated smart folder, triggers performing the second function upon detecting addition of other content items to the second automated smart folder;
detect an addition of a content item to the first automated smart folder, wherein detecting the addition of the content item to the first automated smart folder triggers classification of the content item into one or more of the subfolder classifications for the subfolders nested in the first automated smart folder; and
in response to detecting the addition of the content item to the first automated smart folder:
classify the content item to a first classification from the subfolder classifications utilizing a classification model;
generate, based on determining that a folder corresponding to the first classification does not exist, a destination folder to associate with the first classification; and
move the content item from the first automated smart folder to the destination folder based on the content item being classified to the first classification.
17 . The non-transitory computer-readable storage medium of claim 16 , further comprising instructions that cause the computer system to add the content item to the first automated smart folder based on receiving the content item via an electronic message.
18 . The non-transitory computer-readable storage medium of claim 16 , further comprising instructions that cause the computer system to generate the classification model as a classification machine-learning model based on correlating file data from existing content items to the subfolder classifications.
19 . The non-transitory computer-readable storage medium of claim 18 , further comprising instructions that cause the computer system to:
automatically determine the subfolder classifications used to train the classification machine-learning model based on analyzing file data of the existing content items; and
classify the content item to the first classification utilizing the classification machine-learning model.
20 . The non-transitory computer-readable storage medium of claim 18 , further comprising instructions that cause the computer system to:
automatically determine the subfolder classifications used to train the classification machine-learning model based on search queries of a plurality of content items; and
classify the content item to the first classification utilizing the classification machine-learning model.