Ad Serving Arbitration for Optimal Configuration Utility

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Current ad serving systems face challenges in determining the optimal configuration of ads to maximize utility and user satisfaction, often resulting in wasted ad budget due to inefficient ad placement and relevance.

Innovation Solution

The method involves generating sets of ads with different characteristics and using an arbitration function to select the winning set, considering factors like ad features, serving parameters, and user interactions to determine the best ad configuration for each document, thereby optimizing ad placement and user engagement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If all available ad spots are filled to maximize advertiser revenue, then ad system utility is improved, but user satisfaction and document publisher quality deteriorate due to excessive ads

Engineering Contradiction:

Improvead system utilityVSAvoiduser satisfaction

Core Design Contradiction:

ProductivityVSObject-affected harmful factors

Solution Approach 1:

The system dynamically changes the parameter of ad configuration by generating multiple candidate configurations with different numbers and arrangements of ads, then selects the optimal configuration that balances revenue and user satisfaction

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The ad serving system transitions from static filling of all ad spots to dynamic selection of optimal ad configurations based on arbitration of multiple factors including user satisfaction and publisher quality

Inventive Principle:

Principle #15Dynamics

2Speed

If traditional auction models are used to fill ad spots based on bid price only, then ad placement speed is improved, but ad relevance and system utility deteriorate

Engineering Contradiction:

Improvead placement speedVSAvoidad relevance

Core Design Contradiction:

SpeedVSReliability

Solution Approach 1:

The arbitration function considers multiple parameters beyond bid price including ad performance metrics (selection rate, conversion rate), ad relevancy, and user satisfaction to select winning ads, improving overall system utility

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The ad serving system integrates multiple functions into a single arbitration process: evaluating bid price, ad performance, ad relevancy, and user satisfaction simultaneously to make comprehensive ad placement decisions

Inventive Principle:

Principle #6Universality (Multi-functionality)

3Quantity of substance

If multiple ads are served in available spots to increase advertiser participation, then ad system revenue is improved, but overall system utility deteriorates due to inclusion of low-value 'bottom feeder' advertisers

Engineering Contradiction:

Improvenumber of ads servedVSAvoidoverall system utility

Core Design Contradiction:

Quantity of substanceVSReliability

Solution Approach 1:

The system uses a utility function that incorporates multiple parameters including ad performance metrics and user satisfaction to evaluate and compare different ad configurations, enabling discrimination against low-value ads

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system uses feedback from ad performance metrics (selection rate, conversion rate) and user satisfaction measurements to continuously improve ad configuration selection and eliminate bottom feeder advertisers

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS10762536B2Using the utility of configurations in ad serving decisions

Publication Date: 2020.09.01 GOOGLE LLC

AI summary

Instead of accepting competing ads and using an arbitration function (e.g., an auction) to choose winning ads to be served with a document, sets of ads (perhaps having different characteristics) can be generated, and an arbitration function can be used to select the winning set of ads. Such arbitrations on sets of ads can consider how ads, search results, colors, positions, fonts, etc., all interact with each other and affect the usefulness of the sets of ads to advertisers, end users, document publishers, and/or an ad serving entity.