Personalized semantic fast-forward videos for next generation streaming platforms
Systems and methods are provided herein for generating a summary for a piece of content using a thumbnail container. This may be accomplished by a system receiving a thumbnail container related to a piece of content. The system may also receive user information, a device characteristic, and/or content information related to the piece of content and use the received data to select a machine learning model. The selected machine learning model can identify one or more thumbnails of the thumbnail container as a thumbnail of interest to a user. The system can then generate a summary of the piece of content based on the thumbnail identified by the machine learning model and display the generated summary for the user.
1. A method comprising:
requesting a first thumbnail container related to a piece of content;
receiving the first thumbnail container comprising a first plurality of thumbnails, wherein a first thumbnail of the first plurality of thumbnails is associated with a time frame;
receiving a machine learning model based on the piece of content;
identifying the first thumbnail from the first plurality of thumbnails using the machine learning model;
requesting a second thumbnail container associated with the time frame;
receiving the second thumbnail container comprising a second plurality of thumbnails, wherein:
a second thumbnail of the second plurality of thumbnails is associated with a first time period,
a third thumbnail of the second plurality of thumbnails is associated with a second time period; and
the first time period and the second time period are within the time frame;
identifying the second thumbnail and the third thumbnail from the second plurality of thumbnails using the machine learning algorithm;
requesting a first video segment at a first resolution and a second video segment at a second resolution, wherein the first video segment is associated with the first time period and the second time period; and
displaying the first video segment at the first resolution and the second video segment at the second resolution,
wherein the machine learning model is requested based on a location, wherein the first thumbnail container is requested by a device in the location.
2. The method of claim 1 , further comprising: requesting the machine learning model based on a genre associated with the piece of content.
3. The method of claim 1 , further comprising: requesting the machine learning model based on a device, wherein the first thumbnail container is requested by the device.
4. A method comprising:
requesting a first thumbnail container related to a piece of content;
receiving the first thumbnail container comprising a first plurality of thumbnails, wherein a first thumbnail of the first plurality of thumbnails is associated with a time frame;
receiving a machine learning model based on the piece of content;
identifying the first thumbnail from the first plurality of thumbnails using the machine learning model;
requesting a second thumbnail container associated with the time frame;
receiving the second thumbnail container comprising a second plurality of thumbnails, wherein:
a second thumbnail of the second plurality of thumbnails is associated with a first time period,
a third thumbnail of the second plurality of thumbnails is associated with a second time period; and
the first time period and the second time period are within the time frame;
identifying the second thumbnail and third thumbnail from the second plurality of thumbnails using the machine learning algorithm;
requesting a first video segment at a first resolution and a second video segment at a second resolution, wherein the first video segment is associated with the first time period and the second time period; and
displaying the first video segment at the first resolution and the second video segment at the second resolution,
wherein the machine learning model is requested based on a characteristic of a device, wherein the first thumbnail container is requested by the device.
5. The method of claim 4 , further comprising:
requesting the machine learning model based on the user profile, wherein the first thumbnail container request is associated with the user profile.
6. The method of claim 4 , wherein displaying the first video segment at the first resolution and the second video segment at the second resolution comprises fast forwarding through the second video segment.
7. The method of claim 4 , wherein displaying the first video segment at the first resolution and the second video segment at the second resolution comprises skipping the second video segment.
8. An apparatus, comprising:
control circuitry; and
at least one memory including computer program code for one or more programs, the at least one memory and the computer program code configured to, with the control circuitry, cause the apparatus to perform at least the following:
receive a first thumbnail container comprising a first plurality of thumbnails associated with a time frame;
receive a machine learning model based on the piece of content;
identify the first thumbnail from the plurality of thumbnails using the machine learning model;
request a second thumbnail container associated with the time frame;
receiving the second thumbnail container comprising a second plurality of thumbnails, wherein:
a second thumbnail of the second plurality of thumbnails is associated with a first time period,
a third thumbnail of the second plurality of thumbnails is associated with a second time period; and
the first time period and the second time period are within the time frame;
identify the second thumbnail and third thumbnail from the second plurality of thumbnails using the machine learning algorithm;
request a first video segment at a first resolution and a second video segment at a second resolution, wherein the first video segment is associated with the first time period and the second time period; and
display the first video segment at the first resolution and the second video segment at the second resolution,
wherein the machine learning model is requested based on a characteristic of a device, wherein the first thumbnail container is requested by the device.
9. The apparatus of claim 8 , wherein the apparatus is further caused to select the machine learning model based on a genre associated with the piece of content.
10. The apparatus of claim 8 , wherein the apparatus is further caused to request the machine learning model based on a characteristic of the apparatus.
11. The apparatus of claim 8 , wherein the apparatus is further caused to request the machine learning model based on a location associated with the apparatus.
12. The apparatus of claim 8 , wherein the apparatus is further caused to request the machine learning model based on the user profile, wherein the first thumbnail container request is associated with the user profile.
13. The apparatus of claim 8 , wherein displaying the first video segment at the first resolution and the second video segment at the second resolution comprises fast forwarding through the second video segment.
14. The apparatus of claim 8 , wherein displaying the first video segment at the first resolution and the second video segment at the second resolution comprises skipping the second video segment.