Systems and methods for generating adapted content depictions
A method for generating a content depiction of particular content that includes a machine learning system programmed to receive profile data representing preferences for content. The machine learning system identifies preferences for content features based upon the profile data, accesses content data representing the particular content and other content, and classifies features of the content data and content structure data within a content structure database system according to content categories. The machine learning system generates a content structure depiction of the particular content by combining content structure data from the content structure database system, wherein the combining is based upon correlating the identified preferences of the profile with the classified content categories. The machine learning system receives feedback data responsive to the content depiction and reprograms a configuration of the machine learning system for generating a content depiction based upon the feedback data.
1. A method comprising:
(a) receiving profile data associated with a user;
(b) receiving metadata of a video item;
(c) retrieving, from a database of movie posters, a plurality of verified movie posters;
(d) accessing a neural network framework, wherein the neural network framework comprises a generator neural network and a discriminator neural network;
(e) generating a proposed movie poster, by inputting into the generator neural network of the neural network framework: (a) the profile data, (b) the metadata of the video item, and (c) the plurality of verified movie posters;
(f) determining whether the proposed movie poster is accepted by inputting into the discriminator neural network of the neural network framework: (a) the proposed movie poster generated by the generator neural network, and (b) the plurality of movie posters;
(g) in response to determining that the proposed movie poster is not accepted:
modifying configurations of the generator neural network of the neural network framework and the discriminator neural network of the neural network framework; and
repeating steps (e)-(f);
(h) in response to determining the proposed movie poster is accepted:
storing the proposed movie poster in a content platform association with the video item; and
generating for display the stored proposed movie poster on the content platform.
2. The method of claim 1 , further comprising:
causing distribution of the proposed movie poster across a computer network to at least one network device associated with the profile data.
3. The method of claim 2 , wherein the profile data comprises at least one of viewing of streaming content, internet browsing history, or social media activity.
4. The method of claim 1 , wherein profile data comprises preferences of genre comprising at least one of action, violence, romance, comedy, mystery, science fiction, or drama.
5. The method of claim 1 , wherein profile data comprises preferences for at least one of actors, actor attributes, emotions, background scenery, geographic location, colors, or animals.
6. The method of claim 1 , wherein the generator neural network has an input layer having nodes representing (a) the profile data, (b) the metadata of the video item, and (c) the plurality of verified movie posters, and a processing layer of nodes and connections between them, the nodes and connections programmed and configured to output the proposed movie poster to an output layer.
7. The method of claim 6 , wherein the discriminator neural network is programmed to compare the proposed movie poster with features of at least one of the plurality of verified movie posters.
8. The method of claim 7 , wherein the discriminator neural network comprises an input layer of nodes representing the proposed movie poster and the plurality of verified movie posters, and a processing layer of nodes and connections between them, the nodes and connections programmed and configured to output a determination of whether the proposed movie poster satisfies criteria of an acceptable movie poster.
9. The method of claim 8 , wherein the generator neural network and discriminator neural network are trained by feedback data, and wherein the generator neural network is trained by the discriminator neural network determination of whether the proposed movie poster satisfies criteria of an acceptable movie poster.
10. The method of claim 9 , wherein feedback data comprises content consumption tracked in response to distribution of the proposed movie poster.
11. A machine learning system comprising one or more processors programmed with instructions to cause the one or more processors to perform:
(a) receive profile data associated with a user;
(b) receive metadata of a video item;
(c) retrieve, from a database of movie posters, a plurality of verified movie posters;
(d) access a neural network framework, wherein the neural network framework comprises a generator neural network and a discriminator neural network;
(e) generate a proposed movie poster, by inputting into the generator neural network of the neural network framework: (a) the profile data, (b) the metadata of the video item, and (c) the plurality of verified movie posters;
(f) determine whether the proposed movie poster is accepted by inputting into the discriminator neural network of the neural network framework: (a) the proposed movie poster generated by the generator neural network, and (b) the plurality of movie posters;
(g) in response to determining that the proposed movie poster is not accepted:
modify configurations of the generator neural network of the neural network framework and the discriminator neural network of the neural network framework; and
repeat steps (e)-(f);
(h) in response to determining the proposed movie poster is accepted:
store the proposed movie poster in a content platform association with the video item;
generate for display the stored proposed movie poster on the content platform.
12. The machine learning system of claim 11 , further programmed with instructions to cause the one or more processors to perform:
cause distribution of the proposed movie poster across a computer network to at least one network device associated with the profile data.
13. The machine learning system of claim 12 , wherein the profile data comprises at least one of viewing of streaming content, internet browsing history, or social media activity.
14. The machine learning system of claim 11 , wherein profile data comprises preferences of genre comprising at least one of action, violence, romance, comedy, mystery, science fiction, or drama.
15. The machine learning system of claim 11 , wherein profile data comprises preferences for at least one of actors, actor attributes, emotions, background scenery, geographic location, colors, or animals.
16. The machine learning system of claim 11 , wherein the generator neural network has an input layer having nodes representing (a) the profile data, (b) the metadata of the video item, and (c) the plurality of verified movie posters, and a processing layer of nodes and connections between them, the nodes and connections programmed and configured to output the proposed movie poster to an output layer.
17. The machine learning system of claim 16 , wherein the discriminator neural network is programmed to compare the proposed movie poster with features of at least one of the plurality of verified movie posters.
18. The machine learning system of claim 17 , wherein the discriminator neural network comprises an input layer of nodes representing the proposed movie poster and the plurality of verified movie posters, and a processing layer of nodes and connections between them, the nodes and connections programmed and configured to output a determination of whether the proposed movie poster satisfies criteria of an acceptable movie poster.
19. The machine learning system of claim 18 , wherein the generator neural network and discriminator neural network are trained by feedback data, and wherein the generator neural network is trained by the discriminator neural network determination of whether the proposed movie poster satisfies criteria of an acceptable movie poster.
20. The machine learning system of claim 19 , wherein feedback data comprises content consumption tracked in response to distribution of the proposed movie poster.