Creative Extension Selection for Content Performance Optimization

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Content providers face challenges in creating effective and attractive content items for computerized content delivery networks, as existing methods lack efficiency in optimizing content performance based on user interactions and serving contexts.

Innovation Solution

A method and system that utilize click types and creative extensions to optimize content performance by calculating predicted performance metrics using models, selecting optimal click types and creative extensions, and generating content items tailored to specific serving contexts, incorporating user interaction criteria and data assets.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If automated content generation is implemented, then content performance and click-through rates improve, but system complexity and computational requirements increase

Engineering Contradiction:

Improvecontent performanceVSAvoidsystem complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system segments content generation into distinct modules: creative extension selection, click type selection, and content item generation. Each module handles a specific aspect of content creation, allowing independent optimization and reducing overall system complexity while maintaining high productivity through specialized processing for each function.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system performs preliminary actions by pre-calculating predicted performance metrics for different creative extensions and click types before actual content delivery. This advance computation allows the system to select optimal content configurations in real-time without increasing processing complexity during content serving, thus improving content performance without proportionally increasing system complexity.

Inventive Principle:

Principle #10Preliminary action

2Measurement precision

If multiple click types and creative extensions are evaluated, then content optimization improves, but computational time and processing resources increase

Engineering Contradiction:

Improvecontent optimizationVSAvoidcomputational time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system applies partial action by evaluating only the most relevant creative extensions and click types for each specific content request based on serving context, rather than exhaustively analyzing all possible combinations. This selective evaluation maintains high optimization precision while reducing computational time and processing resources required.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system replaces traditional mechanical content selection methods with machine learning models that predict performance metrics. These models quickly evaluate multiple click types and creative extensions by learning from historical data, providing precise optimization recommendations without requiring extensive real-time computational analysis of each content variant.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Adaptability or versatility

If personalized content generation is implemented, then user engagement and click-through rates improve, but data processing requirements and model complexity increase

Engineering Contradiction:

Improvepersonalization capabilityVSAvoidmodel complexity

Core Design Contradiction:

Adaptability or versatilityVSDevice complexity

Solution Approach 1:

The system applies local quality by tailoring content characteristics specifically to each serving context and user interaction scenario. Different creative extensions and click types are selected based on local conditions such as device type, platform, and user behavior patterns, enabling effective personalization without requiring a single complex model to handle all scenarios universally.

Inventive Principle:

Principle #3Local quality

Solution Approach 2:

The system achieves versatility through a unified content generation framework that handles multiple content types, platforms, and user scenarios using the same underlying architecture. The performance prediction models and selection mechanisms work across diverse contexts, providing personalized content adaptation without proportionally increasing model complexity through multiple specialized systems.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS11182823B2Automated creative extension selection for content performance optimization

Publication Date: 2021.11.23 GOOGLE LLC

AI summary

Systems and methods for optimizing content performance using creative extensions are provided. A content generation system receives request for a content item for presentation on a client device. The request includes an indication of a serving context for the content item. The content generation system uses a creative extension performance model and the serving context for the content item to calculate a predicted performance metric for the content item for multiple different potential creative extensions. Each of the potential creative extensions defines a different action that occurs in response to a user interaction with the content item. The content generation system selects one of the potential creative extensions based on the predicted performance metrics and generates a content item having the selected creative extension using data assets extracted from various data sources. The creative extension performance model is updated using event data from the client device.