Just-in-Time Ad Placement Scaling via Dynamic Request Scheduling

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional ad placement systems are overwhelmed by bursts of ad decisions in scenarios with tens of thousands of unique digital streams, leading to processing and I/O resource overruns, necessitating a solution to scale just-in-time ad placement effectively.

Innovation Solution

The system dynamically adjusts ad selection request times based on the cumulative effect of other requests, distributing them to avoid overload by predicting ad placement timelines and selecting request times that do not exceed the performance limits of ad selection servers, allowing for efficient handling of multiple streams and interactive user behavior.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Quantity of substance

If conventional ad placement systems are used to handle increased numbers of unique streams, then the system can support more streams, but processing and I/O resources become overloaded during bursts of ad decisions

Engineering Contradiction:

Improvenumber of unique streamsVSAvoidprocessing resource overload

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system performs preliminary actions by predicting ad placement times and proactively scheduling ad selection requests before actual ad decisions are needed. This allows the system to smooth out request timing and avoid bursts that would overload processing resources during high-stream scenarios

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system dynamically adjusts the timing of ad selection requests based on predicted ad placement timelines and cumulative request effects. This dynamic scheduling allows the system to adapt request timing to current system conditions and stream volume, preventing resource overload while supporting increased numbers of unique streams

Inventive Principle:

Principle #15Dynamics

2Reliability

If ad selection requests are made close to ad placement time for just-in-time placement, then ad effectiveness increases, but processing bursts occur that overrun server capacity

Engineering Contradiction:

Improvead placement effectivenessVSAvoidserver processing capacity

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The system performs preliminary scheduling of ad selection requests based on predicted ad placement times. By calculating and scheduling requests in advance while maintaining proximity to actual placement times, the system preserves just-in-time effectiveness while preventing processing bursts that would exceed server capacity

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The system implements periodic scheduling of ad selection requests based on predicted ad placement timelines. This distributes requests periodically over time rather than allowing bursts, maintaining the timing proximity needed for effective just-in-time placement while keeping processing loads within server capacity

Inventive Principle:

Principle #19Periodic action

3Productivity

If ad selection requests are distributed earlier to avoid overload, then server capacity is preserved, but ad placement timing precision decreases

Engineering Contradiction:

Improveserver processing capacityVSAvoidad placement timing precision

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs preliminary scheduling calculations that determine the optimal balance between request timing and placement precision. By scheduling requests in advance with calculated timing offsets, the system preserves server capacity while minimizing the time loss from early scheduling through intelligent offset calculation

Inventive Principle:

Principle #10Preliminary action

Data Source

PatentUS8069464B2Architecture for scaling just-in-time placement of advertising content

Publication Date: 2011.11.29 TRITON US VP ACQUISITION CO

AI summary

In one embodiment, a method comprises determining ad placement times for each of a plurality of associated streams. The method also comprises determining an ad selection request time for each of a plurality of ad selection requests based on a cumulative effect of any other ad selection requests occurring at substantially the same time as the determined ad selection time. Each of the plurality of ad selection requests corresponds to one of the plurality of ad placement times.