Interactive Video Content Identification Using Hybrid Fingerprinting

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Video presentation devices lack the ability to identify the video content being rendered without receiving information from a video source, which is problematic for interactive content like video games that vary dynamically based on user interaction, making it difficult to establish reliable reference fingerprint data for identification.

Innovation Solution

A method using a computing system that generates a digital fingerprint of the video content, compares it with reference fingerprints for pre-established segments, and applies a trained neural network to distinguish between pre-established and dynamically-defined segments to identify and continue tracking the video content being rendered.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Loss of information

If video presentation device receives video content from video source, then video content can be rendered, but video presentation device lacks indication of video content identity

Engineering Contradiction:
Improvevideo content identity informationVSAvoidsystem architecture
Core Design Contradiction:
Loss of informationVSDevice complexity

Solution Approach 1:

The video presentation device generates its own digital fingerprint of the received video content and uses this self-generated fingerprint to identify the content, rather than relying on information from the video source. This self-service approach allows the device to independently determine content identity.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

A digital fingerprint acts as an intermediary between the video content and the identification process. The fingerprint generator creates a unique representation of the video content, and this fingerprint serves as the mediator that enables content identification without requiring direct communication of identity information from the video source.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Adaptability or versatility

If video content varies dynamically based on user interaction, then interactivity is improved, but reliable reference fingerprint data cannot be established

Engineering Contradiction:
Improveuser interactivityVSAvoidreference fingerprint data
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The system pre-generates reference fingerprints for multiple possible video content variations and states before the user interaction occurs. These reference fingerprints are stored in advance, allowing the device to compare against them during runtime without needing to predict or pre-know the exact interactive sequence.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The identification system adapts to dynamic video content by continuously generating digital fingerprints of the current video stream and comparing them against reference fingerprints. The system remains flexible and responsive to changes in video content caused by user interactions, maintaining reliability through real-time fingerprint comparison rather than static identification.

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS11936467B2Detecting and responding to rendering of interactive video content
Publication Date: 2024.03.19 ROKU INC
  • US11936467B2 patent drawing
  • US11936467B2 patent drawing
  • US11936467B2 patent drawing

AI summary

A computing system obtains a fingerprint of video content being rendered by a video presentation device, including a first portion representing a pre-established video segment and a second portion representing a dynamically-defined video segment. While obtaining the query fingerprint, the computing system (a) detects a match between the first portion of the query fingerprint and a reference fingerprint that represents the pre-established video segment, (b) based on the detecting of the match, identifies the video content being rendered, (c) after identifying the video content being rendered, applies a trained neural network to at least the second portion of the query fingerprint, and (d) detects, based on the applying of the neural network, that rendering of the identified video content continues. And responsive to at least the detecting that rendering of the identified video content continues, the computing system then takes associated action.