System and method for generating personalized video trailers
Systems and methods for generating individualized content trailers. Content such as a video is divided into segments each representing a set of common features. With reference to a set of stored user preferences, certain segments are selected as aligning with the user's interests. Each selected segment may then be assigned a label corresponding to the plot portion or element to which it belongs. A coherent trailer may then be assembled from the selected segments, ordered according to their plot elements. This allows a user to see not only segments containing subject matter that aligns with their interests, but also a set of such segments arranged to give the user an idea of the plot, and a sense of drama, increasing the likelihood of engagement with the content.
1. A computer-implemented method, comprising:
identifying a subset of segments of video content having attributes that match attributes of a user profile;
for each respective segment of the identified subset of segments, assigning a plot element label to the respective segment, wherein each plot element label corresponds to a plot element of a plurality of plot elements of the video content, and wherein the assigning comprises:
identifying, for each respective segment, an object type of an object that appears within the respective segment;
determining, for each respective segment, a timepoint associated with the respective segment in relation to a total runtime of the video content; and
determining the plot element label based at least in part on a relationship between the identified object type of the object and the determined timepoint in relation to the total runtime of the video content;
generating a trailer of the video content by arranging the segments of the subset of segments in order based on their respective assigned plot element labels; and
transmitting the trailer of the video content for display to a device associated with the user profile.
2. The method of claim 1 , wherein the assigning further comprises:
training a machine learning model to accept as input the object of each respective segment and output the plot element label for each respective segment.
3. The method of claim 2 ,
wherein the machine learning model is trained using a training set that comprises attributes of a plurality of video content trailers, the attributes of the plurality of video content trailers having respective corresponding plot element labels.
4. The method of claim 2 , wherein the assigning further comprises:
identifying one or more audible phrases of each respective segment;
determining one or more times at which the audible phrases occur within the video content; and
submitting the identified audible phrases and the times as inputs of the machine learning model, to determine the plot element label.
5. The method of claim 2 , wherein the machine learning model comprises one or more of a convolutional neural network or a generative adversarial network.
6. The method of claim 1 , wherein the assigning further comprises:
training a machine learning model to accept as input attributes of each respective segment and output identifications of the type of the object.
7. The method of claim 1 , wherein each plot element label comprises one of (a) an introduction, (b) a transition, (c) a complication, or (d) a conclusion.
8. The method of claim 7 , wherein the arranging further comprises arranging the segments in order of their assigned plot element labels (a)— (d).
9. The method of claim 8 , wherein the arranging further comprises arranging a first set of the segments in the order of their assigned plot element labels (a)-(d), and arranging a second set of the segments in the order, to generate the trailer having the first set of the segments followed by the second set of the segments.
10. The method of claim 1 , wherein:
the trailer of the video content is a first trailer of the video content; and
the arranging further comprises:
retrieving a second trailer from a database, the second trailer being different from the first trailer;
determining a template for an order of segments that matches an order of segments in the second trailer; and
arranging the segments of the first trailer according to the template for the order of segments.
11. A computer-implemented system, comprising:
computer memory;
control circuitry configured to:
identify a subset of segments of video content having attributes that match attributes of a user profile, wherein the attributes of the user profile are stored in the computer memory;
for each respective segment of the identified subset of segments, assign a plot element label to the respective segment, wherein each plot element label corresponds to a plot element of a plurality of plot elements of the video content, and wherein the assigning comprises;
identify, for each respective segment, an object type of an object that appears within the respective segment;
determine, for each respective segment, a timepoint associated with the respective segment in relation to a total runtime of the video content; and
determine the plot element label based at least in part on a relationship between the identified object type of the object and the determined timepoint in relation to the total runtime of the video content;
generate a trailer of the video content by arranging the segments of the subset of segments in order based on their respective assigned plot element labels; and
transmit the trailer of the video content for display to a device associated with the user profile.
12. The system of claim 11 , wherein the control circuitry is further configured to assign the plot element label to the respective segment by:
training a machine learning model to accept as input the object of each respective segment and output the plot element label for each respective segment.
13. The system of claim 12 , wherein the control circuitry is further configured to train the machine learning model using a training set that comprises attributes of a plurality of video content trailers, the attributes of the plurality of video content trailers having respective corresponding plot element labels.
14. The system of claim 12 , wherein the control circuitry is further configured to assign the plot element label to the respective segment by:
identifying one or more audible phrases of each respective segment;
determining one or more times at which the audible phrases occur within the video content; and
submitting the identified audible phrases and the times as inputs of the machine learning model, to determine the plot element label.
15. The system of claim 12 , wherein the machine learning model comprises one or more of a convolutional neural network or a generative adversarial network.
16. The system of claim 11 , wherein the control circuitry is further configured to assign the plot element label to the respective segment by:
training a machine learning model to accept as input attributes of each respective segment and output identifications of the type of the object.
17. The system of claim 11 , wherein each plot element label comprises one of (a) an introduction, (b) a transition, (c) a complication, or (d) a conclusion.
18. The system of claim 17 , wherein the control circuitry is further configured to arrange the segments of the subset of segments by arranging the segments in order of their assigned plot element labels (a)-(d).
19. The system of claim 18 , wherein the control circuitry is further configured to arrange the segments of the subset of segments by arranging a first set of the segments in the order of their assigned plot element labels (a)-(d), and arranging a second set of the segments in the order, to generate the trailer having the first set of the segments followed by the second set of the segments.
20. The system of claim 11 , wherein:
the trailer of the video content is a first trailer of the video content; and
the control circuitry is further configured to:
arrange the segments of the subset of segments by retrieving a second trailer from a database, the second trailer being different from the first trailer;
determine a template for an order of segments that matches an order of segments in the second trailer; and
arrange the segments of the first trailer according to the template for the order of segments.