Automated Generation of Personalized Content Thumbnails

Number: 20230164403
Published: 2023-05-25
Filed: 2021-11-24
Assignee: Disney Enterprises, Inc.
Inventors: Niedt; Alexander et al.
CPC: G06F16/743; G06F3/0482; G06F3/04842; G06Q10/40; G06Q30/0271; G06Q30/0631; H04N21/4312; H04N21/4532; H04N21/4667; H04N21/4755; H04N21/8153; H04N21/84
Verdict: Set aside content thumbnail personalization, business
Source: Google Patents · FreePatentsOnline

Abstract

A system includes a computing platform including processing hardware and a memory storing software code, a trained machine learning (ML) model, and a content thumbnail generator. The processing hardware executes the software code to receive interaction data describing interactions by a user with content thumbnails, identify, using the interaction data, an affinity by the user for at least one content thumbnail feature, and determine, using the interaction data, a predetermined business rule, or both, content for promotion to the user. The software code further provides a prediction, using the trained ML model and based on the affinity by the user, of the desirability of each of multiple candidate thumbnails for the content to the user, generates, using the content thumbnail generator and based on the prediction, a thumbnail having features of one or more of the candidate thumbnails, and displays the thumbnail to promote the content to the user.

Background

BACKGROUND

Digital media content in the form of sports, news, movies, television (TV) programming, video games, and music, for example, are consistently sought out and enjoyed by consumers. Nevertheless, the popularity of a particular item of content, such as a particular movie, movie franchise, TV series, TV episode, or video game, can vary widely. In some instances, that variance in popularity may be due to fundamental differences in personal taste amongst consumers. However, in other instances, the lack of consumer interaction with digital media content may be due less to its inherent undesirability to those consumers than to their reluctance to explore content that is unfamiliar and appears unappealing.

One technique used to promote content to consumers includes displaying a thumbnail depicting characters, locations, or actions central to the storyline or theme of that content. In order for a thumbnail to effectively promote the content it represents, the images appearing in the thumbnail, as well as the composition of those images, should be both appealing and intuitively recognizable. However, what is in fact appealing and intuitively recognizable is in the eye of the beholder, and may be as individualized as any other personal taste or preference. Nevertheless, due to the resources often devoted to developing new content, the efficiency and effectiveness with which such new content can be promoted to consumers has become increasingly important to the prod

Claims

1. A system comprising: a computing platform including a processing hardware and a system memory; the system memory storing a software code, a trained machine learning (ML) model, and a content thumbnail generator; the processing hardware configured to execute the software code to: receive interaction data describing interactions by a user with a plurality of content thumbnails; identify, using the interaction data, an affinity by the user for at least one content thumbnail feature; determine, using at least one of the interaction data or a predetermined business rule, content for promotion to the user; provide a prediction, using the trained ML model and based on the affinity by the user, of a respective desirability of each of a plurality of candidate thumbnails for the content to the user; generate, using the content thumbnail generator and based on the prediction, a thumbnail having features of one or more of the plurality of candidate thumbnails; and display the thumbnail for promoting to the user. || 11. A method for use by a system including a computing platform having a processing hardware and a system memory storing a software code, a trained machine learning (ML) model, and a content thumbnail generator, the method comprising: receiving, by the software code executed by the processing hardware, interaction data describing interactions by a user with a plurality of content thumbnails; identifying, by the software code executed by the processing hardware using the interaction data, an affinity by the user for at least one content thumbnail feature; determining, by the software code executed by the processing hardware using at least one of the interaction data or a predetermined business rule, content for promotion to the user; providing a prediction, by the software code executed by the processing hardware using the trained ML model and based on the affinity by the user, of a respective desirability, of each of a plurality of candidate thumbnails for the content to the user; generating, by the software code executed by the processing hardware using the content thumbnail generator and based on the prediction, a thumbnail having features of one or more of the plurality of candidate thumbnails; and display, by the software code executed by the processing hardware, the thumbnail to promote the content to the user. || 12. The method of clap 11, further comprising providing, by the software code executed by the processing hardware, a graphical user interface (GUI); and displaying, by the software code executed by the processing hardware and via the GUI, the thumbnail among a plurality of other content thumbnails for other content.