Cluster-Based Content Placement Criteria Expansion

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing content placement systems on the internet struggle to effectively identify and utilize supplemental placement criteria that enhance the display of online content, such as ads, by clustering similar content items based on semantic and user similarities, leading to suboptimal ad placement and user engagement.

Innovation Solution

A computer-implemented method and system that identifies clusters of online content items sharing semantic or user similarities, determines cluster placement criteria based on quality metrics, and associates new content with these clusters to expand and improve placement criteria for more effective ad display.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If content placement systems use basic placement criteria without clustering, then the system complexity is low, but the content placement relevance and effectiveness deteriorate

Engineering Contradiction:

Improvecontent placement relevanceVSAvoidsystem complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent segments the content placement system into multiple clusters based on semantic similarity and user similarity. Each cluster contains content items with related characteristics, allowing the system to evaluate and select placement criteria for each cluster separately. This segmentation improves placement relevance by matching content with appropriate clusters while managing complexity through modular cluster-based processing.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The patent performs preliminary clustering of content items based on semantic and user similarities before the actual content placement decision. By pre-organizing content into clusters and determining cluster placement criteria in advance, the system reduces the complexity of real-time placement decisions while improving relevance through pre-computed similarity relationships.

Inventive Principle:

Principle #10Preliminary action

2Productivity

If the system clusters content items based on semantic and user similarities, then the content placement effectiveness improves, but the computational time and processing complexity increase

Engineering Contradiction:

Improvecontent placement effectivenessVSAvoidcomputational time

Core Design Contradiction:

ProductivityVSLoss of time

Solution Approach 1:

The system performs clustering computations and determines cluster placement criteria in advance, before actual content placement is needed. By pre-computing semantic similarities, user similarities, and cluster characteristics, the system reduces the computational burden during real-time content placement while maintaining high effectiveness through pre-established cluster relationships.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent applies partial clustering by focusing computational resources on identifying the most relevant clusters for each content item rather than computing all possible similarities. The system determines cluster placement criteria for the most significant clusters, achieving effective content placement without the excessive computational cost of complete clustering analysis.

Inventive Principle:

Principle #16Partial or excessive action

3Measurement precision

If the system uses multiple cluster placement criteria, then the content selection quality improves, but the criterion selection complexity increases

Engineering Contradiction:

Improvecontent selection qualityVSAvoidcriterion selection complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent employs multiple cluster placement criteria with different parameters including semantic similarity metrics, user similarity metrics, and quality metrics. By changing and comparing multiple parameters for each cluster, the system achieves precise content selection while managing complexity through systematic parameter evaluation and selection of the most relevant criteria for each content item.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The system applies different placement criteria to different clusters based on their specific characteristics. Each cluster receives customized placement criteria selection based on its semantic and user similarity properties, achieving high selection quality for each local cluster while managing overall complexity through localized rather than uniform criterion application.

Inventive Principle:

Principle #3Local quality

Data Source

PatentUS11036813B2Content placement criteria expansion

Publication Date: 2021.06.15 GOOGLE LLC

AI summary

Systems and methods of providing information via a computer network are provided. A data processing system can identify a cluster that includes a plurality of online content items having a semantic or user similarity. The data processing system determines a plurality of cluster placement criteria of the cluster, and receives content configured for display with a web page. The content can be associated with the cluster based on the semantic or user similarity. A cluster placement criterion of the plurality of cluster placement criteria can be selected based on a quality metric of the selected cluster placement criterion, and the selected cluster placement criterion can be provided as a supplemental criterion used to select the content for display with the web page.