Generating and utilizing digital media clips based on contextual metadata from digital environments
The present disclosure relates to systems, methods, and non-transitory computer-readable media that dynamically capture, organize, and utilize digital media clips. For example, in one or more implementations, the disclosed systems can capture and generate digital media clips of content items that include both content metadata of the content items as well as contextual metadata of contextual signals surrounding the content item. Additionally, in some implementations, the disclosed systems analyze contextual metadata to search, retrieve, discover, and organize new and existing digital media clips. Further, in various implementations, the disclosed systems facilitate generating digital media clip libraries as well as the creation of digital media collections, where different types of digital media clips can be combined in a cohesive interactive graphical user interface.
1 . A computer-implemented method comprising:
maintaining, for a user account of a content management system, a media clip library comprising digital media clips each comprising a content item, content metadata, and contextual metadata;
identifying a digital media clip from the digital media clips based on receiving an indication of a user selection of the digital media clip;
determining a relatedness level based on receiving an indication of a user selection corresponding to a similarity metric;
generating a search request based on the identified digital media clip and the relatedness level;
tuning a media clip classification machine-learning model based on the relatedness level and the content metadata and the contextual metadata associated with the digital media clips of the user account;
identifying search results comprising one or more content items from one or more sources utilizing the tuned media clip classification machine-learning model and the identified digital media clip of the search request; and
providing the search results comprising the one or more content items in response to the search request.
2 . The computer-implemented method of claim 1 , further comprising:
receiving an indication of a modified similarity metric;
determining a modified relatedness level based on the modified similarity metric; and
generating a modified search request that comprises the modified relatedness level.
3 . The computer-implemented method of claim 1 , wherein the similarity metric comprises a value within a relatedness value range that spans between a highly correlated value and an uncorrelated value.
4 . The computer-implemented method of claim 1 , wherein the similarity metric indicates an uncorrelated value, wherein:
the search request is based on the similarity metric that indicates the uncorrelated value; and
the one or more content items within the search results are uncorrelated with the digital media clip identified to generate the search request.
5 . The computer-implemented method of claim 1 , further comprising generating, for inclusion in the search results, a personalized search result of a content item based on implicit user preferences.
6 . The computer-implemented method of claim 1 , wherein tuning the media clip classification machine-learning model comprises tuning one or more parameters of the media clip classification machine-learning model based on the relatedness level.
7 . The computer-implemented method of claim 1 , further comprising:
identifying a query term based on receiving an indication of a user input; and
providing the query term, the content metadata and the contextual metadata associated with the digital media clip, and the relatedness level to the media clip classification machine-learning model.
8 . A non-transitory computer-readable storage medium comprising instructions that, when executed by at least one processor, cause a computer device to:
access a media clip library of a user account of a content management system, the media clip library comprising digital media clips each comprising a content item, content metadata, and contextual metadata;
receive an indication of a user selection of a digital media clip from the digital media clips;
determine a relatedness level based on receiving an indication of a user selection corresponding to a similarity metric;
generate a search request based on the digital media clip and the relatedness level;
tune a media clip classification machine-learning model based on the relatedness level and the content metadata and the contextual metadata associated with the digital media clips of the user account;
identify search results comprising one or more content items from one or more sources utilizing the tuned media clip classification machine-learning model and the digital media clip of the search request; and
provide the search results comprising the one or more content items in response to the search request.
9 . The non-transitory computer-readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to tune the media clip classification machine-learning model by tuning one or more parameters of the media clip classification machine-learning model based on the relatedness level.
10 . The non-transitory computer-readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to:
receive, via a slider graphical user interface element, an indication of a modified similarity metric;
determine a modified relatedness level based on the modified similarity metric;
generate a modified search request that comprises the modified relatedness level; and
provide modified search results comprising one or more different content items based on the modified relatedness level.
11 . The non-transitory computer-readable storage medium of claim 8 , wherein the similarity metric indicates an uncorrelated value, wherein:
the search request is based on the similarity metric that indicates the uncorrelated value; and
the one or more content items within the search results are uncorrelated with the digital media clip identified to generate the search request.
12 . The non-transitory computer-readable storage medium of claim 8 , further comprising generating, for inclusion in the search results, a personalized search result of a content item based on implicit user preferences.
13 . The non-transitory computer-readable storage medium of claim 8 , wherein the similarity metric comprises a value within a relatedness value range that spans between a very similar value and a very dissimilar value.
14 . The non-transitory computer-readable storage medium of claim 8 , further comprising instructions that, when executed by the at least one processor, cause the computer device to:
identify a query term based on receiving an indication of a user input; and
provide the query term, the content metadata and the contextual metadata associated with the digital media clip, and the relatedness level to the media clip classification machine-learning model.
15 . 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:
receive, from a client device associated with a user account of a content management system, an indication of a digital media clip from a media clip library of the user account, wherein the media clip library comprises digital media clips that each comprise a content item, content metadata, and contextual metadata;
receive, from the client device, an indication of a user selection corresponding to a similarity metric;
determine a relatedness level based on the similarity metric;
generate a search request based on the digital media clip and the relatedness level;
tune a media clip classification machine-learning model based on the relatedness level and the content metadata and the contextual metadata associated with the digital media clips of the user account;
identify search results comprising one or more content items from one or more sources utilizing the tuned media clip classification machine-learning model and the digital media clip of the search request; and
provide the search results comprising the one or more content items in response to the search request.
16 . The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
receive, from the client device, an indication of a modified similarity metric;
determine a modified relatedness level based on the modified similarity metric; and
provide modified search results based on a modified search request comprising the modified relatedness level.
17 . The system of claim 15 , wherein tuning the media clip classification machine-learning model comprises tuning one or more parameters of the media clip classification machine-learning model based on the relatedness level.
18 . The system of claim 15 , wherein:
the similarity metric indicates an uncorrelated value; and
the one or more content items within the search results are uncorrelated with the digital media clip.
19 . The system of claim 15 , further comprising generating, for inclusion in the search results, a personalized search result of a content item based on implicit user preferences.
20 . The system of claim 15 , further comprising instructions that, when executed by the at least one processor, cause the system to:
identify a query term based on receiving an indication of a user input; and
provide the query term, the content metadata and the contextual metadata associated with the digital media clip, and the relatedness level to the media clip classification machine-learning model.