User responsive dynamic content transformation

Number: 12096093
Published: 2024-09-17
Filed: 2023-02-09
Assignee: Disney Enterprises, Inc.
Inventors: Comito; Keith et al.
CPC: H04N21/234; H04N21/233; H04N21/44213; H04N21/854; H04N21/8106
Verdict: Set aside content personalization, business
Source: Google Patents · FreePatentsOnline

Abstract

A system includes a hardware processor and a memory storing software code and one or more machine learning (ML) model(s) trained to transform content. The hardware processor executes the software code to ingest content components each corresponding respectively to a different feature of multiple features included in a content file, receive sensor data describing at least one of an action or an environment of a system user, and identify, using the sensor data, at least one of the content components as content to be transformed. The hardware processor further executes the software code to transform, using the ML model(s), that identified content to provide at least one transformed content component, combine a subset of the ingested content components with the at least one transformed content component to produce a dynamically transformed content, and output the dynamically transformed content in real-time with respect to ingesting the content components.

Background

BACKGROUND (1) Digital media content in the form of streaming movies and television (TV) content, for example, is consistently sought out and enjoyed by users. However, in the conventional art, the media content transmitted to users, such as movies, streaming series, and TV program content, is typically pre-rendered and fixed in terms of the number of different visual effects and audio tracks delivered, as well as the characteristics of those pre-rendered features. For example, with respect to audio features of such pre-rendered content, the sound effects, dialogue, background music, specific voices, the use of specific musical instruments, and so forth, of that pre-rendered content are typically completely predetermined. (2) Nevertheless, in an increasingly diverse consumer environment, the tastes and preferences of individual users may vary widely. Consequently, even media content embodying artistic excellence and high production values may be less pleasing to some users than its inherent qualities merit. Due to the resources often devoted to developing new content, the ability to tailor such content to the differing tastes of as many users as possible has become increasingly important to the producers, owners, and distributors of digital media content. Moreover, enabling the tailoring of some features of content in response to individual user tastes and behavior has the potential to make the consumption of such content more desirable and engaging to all users. Consequently

Claims

1. A system comprising: a hardware processor; and a system memory storing a software code and one or more machine learning (ML) model trained to transform content; the hardware processor configured to execute the software code to: ingest a plurality of content components, each of the plurality of content components corresponding respectively to a different feature of a plurality of features included in a content file; receive sensor data describing at least one of an action by a system user or an environment of the system user; identify, using the sensor data, at least one of the ingested plurality of content components as at least one content component to be transformed; transform, using the at least one ML model, the at least one content component to be transformed, to provide at least one transformed content component; combine a subset of the ingested plurality of content components with the at least one transformed content component to produce a dynamically transformed content; and output the dynamically transformed content in real-time with respect to ingesting the plurality of content components. || 13. A method for use by a system including hardware processor and a system memory storing a software code and at least one machine learning (ML) model trained to transform content, the method comprising: ingesting, by the software code executed by the hardware processor, a plurality of content components, each of the plurality of content components corresponding respectively to a different feature of a plurality of features included in a content file; receiving, by the software code executed by the hardware processor, sensor data describing at least one of an action by a system user or an environment of the system user; identifying, by the software code executed by the hardware processor and using the sensor data, at least one of the ingested plurality of content components as an at least one content component to be transformed; transforming, by the software code executed by the hardware processor and using the at least one ML model, the at least one content component to be transformed, to provide at least one transformed content component; combining, by the software code executed by the hardware processor, a subset of the ingested plurality of content components with the at least one transformed content component to produce a dynamically transformed content; and outputting, by the software code executed by the hardware processor, the dynamically transformed content in real-time with respect to ingesting the plurality of content components.