Methods, systems, and apparatuses for generating personalized content
Methods, systems, and apparatuses for identifying key moments of a media asset are described herein. Key moments may be identified, for example, based on analyzing data associated with the media asset and user engagement data associated with the media asset. The data associated with the media asset may be provided to a machine learning model configured to determine one or more first segments of the media asset that satisfy a first threshold. The user engagement data may be analyzed to determine one or more second segments of the media asset that satisfy a second threshold. A compilation of segments of the media asset, representing the key moments thereof, may be generated based on the one or more first segments and the one or more second segments.
1. A method comprising:
receiving, by a computing device, via one or more user devices, engagement data associated with a media asset and the one or more user devices, wherein the engagement data is indicative of a plurality of user interactions, via the one or more user devices, with the media asset;
determining, via a machine learning model and based on the media asset, one or more first segments of the media asset associated with one or more content features satisfying a first threshold, wherein the media asset comprises the one or more content features;
determining, based on the engagement data, one of more second segments of the media asset associated with one or more user interactions, of the plurality of user interactions, satisfying a second threshold;
generating, based on the one or more first segments satisfying the first threshold and the one of more second segments satisfying the second threshold, a compilation of segments of the media asset; and
causing the compilation of segments of the media asset to be output.
2. The method of claim 1 , further comprising:
receiving, via a user interface, a selection of one or more segments of the compilation of segments; and
causing one or more of removing the one or more segments from the compilation of segments or outputting the one or more segments of the compilation of segments.
3. The method of claim 1 , further comprising:
receiving, via a user interface, a selection of one or more third segments of the media asset; and
causing the one or more third segments to be added to the compilation of segments.
4. The method of claim 1 , wherein the plurality of user interactions are associated with a client application, and wherein the media asset is output via the client application at the one or more user devices.
5. The method of claim 1 , wherein the media asset comprises one or more of a virtual event, webinar, a video, a document, or a webpage, and wherein the one or more content features comprise one or more of content topics, content concepts, content subject matter, or content themes.
6. The method of claim 1 , wherein the machine learning model comprises one or more of a text-based learning model, a large language model, a natural language processing application, or a generative pre-trained transformer.
7. The method of claim 1 , further comprising determining data associated with the media asset, wherein the data associated with the media asset comprises one or more of a content type, a content rating, content metadata, a date of creation, a content tag, a content category, a transcript, a content filter, a language, text data associated with the media asset, or the engagement data.
8. The method of claim 1 , wherein determining the one or more first segments of the media asset comprises determining, via the machine learning model, based on data associated with the media asset, the one or more first segments of the media asset associated with the one or more content features satisfying the first threshold.
9. The method of claim 1 , further comprising: generating, by the machine learning model, directed content based on; data indicative of a plurality of attributes associated with one or more users of the one or more user devices, the compilation of segments, and the data associated with the media asset.
10. The method of claim 9 , wherein the plurality of attributes associated with the one or more users comprises one or more of an age, a gender, a location, a profile title, an interest, past content consumption, a professional affiliation, a professional experience, an educational background or experience, a professional certification or license, or a keyword.
11. The method of claim 9 , wherein generating the directed content comprises:
determining, based on the data indicative of the plurality of attributes associated with the one or more users, data indicative of a plurality of similar user profiles; and
generating, via the machine learning model, based on the data indicative of the plurality of similar user profiles and the compilation of segments and data associated with the media asset, the directed content.
12. The method of claim 11 , wherein determining the data indicative of the plurality of similar user profiles comprises:
determining, based on the data indicative of the plurality of attributes associated with the one or more users, a first interest cloud associated with a first user profile; and
determining, based on the first interest cloud associated with the first user profile, the plurality of similar user profiles associated with corresponding interest clouds that are similar to the first interest cloud.
13. The method of claim 11 , wherein determining the data indicative of the plurality of similar user profiles comprises:
determining, based the data indicative of the plurality of attributes associated with one or more second users of one or more second user devices, a first interest cloud associated with a first user profile; and
determining, based on the first interest cloud associated with the first user profile, the plurality of similar user profiles associated with corresponding interest clouds that are similar to the first interest cloud.
14. The method of claim 9 , further comprising:
receiving, based on the directed content, data indicative of one or more user further user interactions associated with each user of the one or more users; and
updating, via the machine learning model, based on the data indicative of one or more further user interactions associated with each user, the directed content.
15. The method of claim 1 , wherein generating the compilation of segments of the media asset comprises:
determining a first weight associated with the one or more first segments that satisfy the first threshold;
determining a second weight associated with the one of more second segments that satisfy the second threshold; and
generating, based on the first weight and the second weight, the compilation of segments of the media asset.
16. The method of claim 1 , wherein causing output of the compilation of segments comprises one or more of: sending the compilation of segments to a second computing device, storing the compilation of segments at the second computing device, or causing an output of the compilation of segments via the second computing device.
17. The method of claim 1 , further comprising:
receiving data indicative of a plurality of attributes associated with one or more users of the one or more user devices;
determining, via the machine learning model, based on data associated with the media asset and the data indicative of the plurality of attributes associated with the one or more users, one or more third segments of the media asset associated with one or more content features satisfying a third threshold;
generating, based on the one or more third segments satisfying the third threshold and the one of more second segments satisfying the second threshold, a second compilation of segments of the media asset; and
causing the second compilation of segments of the media asset to be output.
18. An apparatus comprising:
one or more processors; and
a memory storing processor-executable instructions that, when executed by the one or more processors, cause the apparatus to:
receive, via one or more user devices, engagement data associated with a media asset and the one or more user devices, wherein the engagement data is indicative of a plurality of user interactions, via the one or more user devices, with the media asset;
determine, via a machine learning model and based on the media asset, one or more first segments of the media asset associated with one or more content features satisfying a first threshold, wherein the media asset comprises the one or more content features;
determine, based on the engagement data, one of more second segments of the media asset associated with one or more user interactions, of the plurality of user interactions, satisfying a second threshold;
generate, based on the one or more first segments satisfying the first threshold and the one of more second segments satisfying the second threshold, a compilation of segments of the media asset; and
cause the compilation of segments of the media asset to be output.
19. The apparatus of claim 18 , wherein the processor-executable instructions that cause the apparatus to determine the one or more first segments of the media asset further cause the apparatus to determine, via the machine learning model, based on data associated with the media asset, the one or more first segments of the media asset associated with the one or more content features satisfying the first threshold.
20. The apparatus of claim 18 , wherein the processor-executable instructions that cause the apparatus to generate the compilation of segments of the media asset further cause the apparatus to:
determine a first weight associated with the one or more first segments that satisfy the first threshold;
determine a second weight associated with the one of more second segments that satisfy the second threshold; and
generate, based on the first weight and the second weight, the compilation of segments of the media asset.