Dynamic Secondary Content Insertion in Online Video

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current methods for inserting secondary content into primary video content in online systems fail to effectively balance potential gains and losses in user engagement, as they do not account for user behavior and interaction probabilities, leading to interruptions that may deter users from watching videos.

Innovation Solution

An online system determines whether to insert secondary content into primary content items like videos based on gain and loss scores, using machine learning techniques to predict user behavior and identify optimal insertion positions that minimize disruption while maximizing engagement and compensation.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If secondary content is inserted into primary video content, then system revenue and user engagement can be increased, but user experience deteriorates due to interruptions in video playback

Engineering Contradiction:

Improvesystem revenueVSAvoiduser experience degradation

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system dynamically changes the insertion parameters of secondary content based on real-time analysis of video content characteristics and user behavior patterns. By adjusting insertion timing, duration, and position parameters, the system optimizes revenue generation while minimizing disruption to user experience.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system performs preliminary analysis of video content to identify optimal insertion points before actual insertion occurs. Machine learning models pre-process video metadata, scene descriptions, and user engagement patterns to determine the most favorable positions for secondary content insertion, thereby avoiding harmful interruptions.

Inventive Principle:

Principle #10Preliminary action

2Quantity of substance

If secondary content is inserted at more positions in the video, then compensation and engagement increase, but video continuity is impaired

Engineering Contradiction:

Improveamount of secondary contentVSAvoidvideo continuity

Core Design Contradiction:

Quantity of substanceVSStability of the object's composition

Solution Approach 1:

The system applies different insertion strategies to different local regions of the video based on content type and user engagement patterns. High-engagement segments receive fewer or no insertions, while low-engagement segments can accommodate more secondary content, thereby maintaining overall video continuity while maximizing compensation opportunities.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system selectively inserts secondary content only in specific portions of the video where it is least likely to disrupt user experience. By applying partial action rather than uniform insertion across the entire video, the system achieves compensation goals without significantly impairing video continuity.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If machine learning techniques are used to predict user behavior, then insertion accuracy improves, but system complexity increases

Engineering Contradiction:

Improveuser behavior prediction accuracyVSAvoidsystem complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The system introduces machine learning models as intermediary components that process video metadata and user behavior data to generate insertion recommendations. These models act as mediators between raw data and insertion decisions, improving prediction accuracy while isolating the core video playback system from complex analytical operations.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The system divides the complex task of secondary content insertion into separate modular components: video analysis module, user behavior prediction module, insertion decision module, and execution module. This segmentation allows each component to specialize in specific functions, improving overall prediction accuracy while managing system complexity through modular architecture.

Inventive Principle:

Principle #1Segmentation

Data Source

PatentUS11363317B2Inserting secondary content into primary content presented by an online system

Publication Date: 2022.06.14 META PLATFORMS INC

AI summary

An online system receives a request for a video to be presented by the online system to a target user. The online system determines whether to insert secondary content into the video. For such a determination, the online system identifies a position in the video for inserting secondary content. Further, the online system determines a loss score and a gain score. The loss score measures a loss of interaction by the target user if the secondary content were inserted. The gain score includes a monetary compensation to be received by the online system for inserting the secondary content at the identified position. The online system compares the loss score and the gain score. Based on the gain score offsetting the loss score, the online systems modifies the video by inserting the secondary content at the identified position and provides the modified video for display to the target user.