Media Stream Content Placement Using ACR and Multivariate Testing

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing approaches for inserting supplemental content into media streams fail to consider the varying user motivations at different points in the media stream and unique user characteristics, leading to suboptimal consumption of the supplemental content.

Innovation Solution

Perform automated content recognition (ACR) to determine scene changes in a media stream, identify potential supplemental content spots based on these changes, and conduct multivariate testing (e.g., A/B testing) across multiple media devices to determine the optimal spot for inserting supplemental content.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If supplemental content is inserted at fixed predetermined spots in the media stream, then the insertion process is simple and consistent, but user consumption of the supplemental content is suboptimal because it does not account for varying user motivation at different points in the stream

Engineering Contradiction:

Improvesupplemental content consumptionVSAvoidcontent insertion system complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system dynamically determines optimal supplemental content spots based on real-time analysis of media stream characteristics and user behavior patterns. Instead of using fixed predetermined spots, the system adapts the insertion timing based on scene changes, user engagement metrics, and contextual factors to maximize content consumption while maintaining simplicity in the overall process

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system automatically analyzes the media stream and identifies optimal insertion spots without requiring manual intervention or complex external analysis tools. The automated content recognition and analysis capabilities enable the system to self-determine the best timing for supplemental content based on the stream's inherent characteristics

Inventive Principle:

Principle #25Self-service

2Productivity

If manual insertion of supplemental content is performed to ensure optimal timing, then content consumption can be maximized, but the process becomes time intensive and error prone

Engineering Contradiction:

Improvesupplemental content consumptionVSAvoidtime required for content insertion

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs automated content recognition and analysis to independently determine optimal insertion spots without requiring manual review or intervention. The automated detection of scene changes, user engagement patterns, and contextual factors eliminates time-consuming manual processes while maintaining high accuracy in spot selection

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The system replaces manual mechanical processes of content insertion with automated digital analysis and decision-making algorithms. The automated content recognition system uses computational methods to analyze media streams and determine optimal spots, eliminating human error and time consumption associated with manual selection

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If the same supplemental content spot is used for all users, then the system is simple to operate, but it fails to account for unique user characteristics such as time of day preferences

Engineering Contradiction:

Improveuser-specific content placementVSAvoidcontent insertion system complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system tailors supplemental content placement to local user characteristics such as time of day, device type, and viewing patterns. Instead of using a uniform approach for all users, the system adapts the insertion timing and positioning based on specific user contexts to maximize engagement while maintaining manageable system complexity through targeted personalization

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS20250294195A1Automatically determining an optimal supplemental content spot in a media stream

Publication Date: 2025.09.18 ROKU INC

AI summary

Disclosed herein are system, apparatus, article of manufacture, method and/or computer program product embodiments, and/or combinations and sub-combinations thereof, for determining an optimal spot to insert supplemental content into a media stream to maximize the consumption of the supplemental content by users. An example embodiment operates by performing automated content recognition (ACR) on the media stream, thereby determining scene changes in the media stream. The embodiment identifies a plurality of potential supplemental content spots in the media stream based on the determined scene changes. The embodiment then performs a multivariate test involving test supplemental content over a portion of the potential supplemental content spots to a plurality of media devices, thereby determining the optimal supplemental content spot among the plurality of potential supplemental content spots in the media stream.