Machine Learning Model-Based Detection of Content Type

Number: 20250356532
Published: 2025-11-20
Filed: 2025-07-30
Assignee: Disney Enterprises, Inc.
Inventors: Jacobs; Mitchel et al.
CPC: H04N21/23439; G06N5/01; G06T7/90; H04N21/816
Verdict: Set aside content-type classification, business
Source: Google Patents · FreePatentsOnline

Abstract

A system includes a hardware processor, and a memory storing a software code and at least one machine learning (ML) model trained to distinguish between a plurality of content types. The hardware processor executes the software code to receive a content file including data identifying a dataset contained by the content file as being a first content type of the plurality of content types; predict, using the at least one ML model and the dataset, based on at least one image parameter, a first probability that a content type of the dataset matches the first content type identified by the data; and determine, based on the first probability, that the content type of the dataset (i) is the first content type identified by the data, (ii) is not the first 10 content type identified by the data, or (iii) is of an indeterminate content type.

Background

BACKGROUND

Motion picture and other video-based content production companies typically accept distribution video masters from multiple sources that may use different workflows and production processes, and may target different consumer distribution video formats. Moreover, the creative processes used by different content sources may differ, so that content received from different sources may each have a different appearance, which makes it challenging for a distribution, mastering or quality-control specialist not involved in the creation of the content to be certain that the content is free of flaws. As a result, mistakes that are made during preparation of the distribution master may go undetected, and may undesirably cause the content to appear defective to consumers, or may result in delays, additional costs, or both, related to correcting the flaw at a later stage closer to the release date of the content to consumers. Consequently, there is a need in the art for an automated image analysis solution capable of distinguishing between different content types in order to detect when a mismatch exists between an expected video format of content received from a source and the actual format of that content.

Claims

21. A system comprising: a hardware processor; a system memory storing a software code; the hardware processor configured to execute the software code to: receive a content file including data identifying a dataset contained by the content file as being a first content type of a plurality of content types; perform an analysis, based on at least one image parameter, to determine whether a content type of the dataset matches the first content type identified by the data; and determine, based on the analysis, that the content type of the dataset (i) is the first content type identified by the data, or (ii) is not the first content type identified by the data. || 31. A method for use by a system including a hardware processor and a system memory storing a software code, the method comprising: receiving, by the software code executed by the hardware processor, a content file including data identifying a dataset contained by the content file as being a first content type of a plurality of content types; performing an analysis, by the software code executed by the hardware processor, based on at least one image parameter, to determine whether a content type of the dataset matches the first content type identified by the data; and determining, by the software code executed by the hardware processor, based on the analysis, that the content type of the dataset (i) is the first content type identified by the data, or (ii) is not the first content type identified by the data.