CPC H04N 21/251 (2013.01) [G06N 3/044 (2023.01); G06N 3/08 (2013.01); H04N 21/25883 (2013.01); H04N 21/25891 (2013.01)] | 20 Claims |
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.
|