Smart Pixel Audience Segmentation via Semantic Topic Detection

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Publishers face challenges in categorizing and classifying their resources by topics, which is time-consuming and often outdated, making it difficult to target specific audience segments for content delivery and advertising.

Innovation Solution

A system that uses smart pixels to collect data on user interactions with publisher resources, determining associated topics and storing user identifiers in an audience data structure, allowing for dynamic classification and segment generation based on semantic analysis, enabling targeted content delivery and auction adjustments.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If manual classification of publisher resources by topics is performed, then categorization accuracy can be maintained, but time consumption and labor costs increase significantly

Engineering Contradiction:

Improvecategorization accuracyVSAvoidtime consumption

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The patent replaces manual mechanical classification with automated topic detection systems that use semantic analysis and machine learning algorithms to categorize publisher resources by topic, eliminating the need for human reviewers while maintaining or improving categorization accuracy

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Solution Approach 2:

The system enables publisher resources to self-categorize by automatically detecting topics through semantic analysis of resource content, allowing resources to classify themselves without external human intervention or manual input from publishers

Inventive Principle:

Principle #25Self-service

2Ease of operation

If publisher resources are classified by topics in advance, then targeted content delivery can be achieved, but the classification becomes outdated as new resources are added

Engineering Contradiction:

Improvetargeted content deliveryVSAvoidclassification currency

Core Design Contradiction:

Ease of operationVSDuration of action of stationary object

Solution Approach 1:

The patent implements dynamic topic detection that continuously updates resource classifications as new resources are added or existing resources are modified, ensuring the classification system remains current without requiring periodic manual reclassification campaigns

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system maintains continuous topic detection and classification operations, automatically processing new publisher resources as they are added to ensure the audience data structure remains up-to-date without interruption or manual intervention

Inventive Principle:

Principle #20Continuity of useful action

3Measurement precision

If comprehensive audience data is collected through pixel firing, then audience segmentation precision improves, but data processing complexity increases

Engineering Contradiction:

Improveaudience segmentation precisionVSAvoiddata processing complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent segments the comprehensive audience data into structured audiences based on topic associations, dividing the large dataset into manageable topic-based groups that are easier to process and query while maintaining segmentation precision

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The system introduces an intermediary audience data structure that sits between raw pixel firing data and final audience segments, pre-processing and organizing data by topic associations to reduce the complexity of subsequent querying and segment generation operations

Inventive Principle:

Principle #24Intermediary (Mediator)

4Adaptability or versatility

If publishers manually create user lists for targeted campaigns, then control over user data is maintained, but the effort and time required increases

Engineering Contradiction:

Improvepublisher controlVSAvoidcampaign setup efficiency

Core Design Contradiction:

Adaptability or versatilityVSProductivity

Solution Approach 1:

The system enables publishers to self-serve by automatically generating topic-based audiences and user lists based on their published resources, allowing publishers to maintain full control over their data while eliminating manual list creation efforts

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The audience data structure serves multiple functions simultaneously: it enables targeted content delivery, supports auction adjustments, provides audience analytics, and generates user lists for campaigns, allowing publishers to derive multiple benefits from a single automated classification system

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS10817884B2Building topic-oriented audiences

Publication Date: 2020.10.27 GOOGLE LLC

AI summary

Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium for creating and querying for audience data. A method includes: receiving data associated with each firing of a pixel as a result of a display of a publisher resource, wherein the data includes an identifier for the publisher, a URL associated with the resource, and a user identifier associated with a user device on which the resource was displayed; determining for each pixel firing one or more topics associated with a given resource; storing the user identifier in association with the determined one or more topics in an audience data structure; receiving a query to identify a segment of the audience; identifying one or more topics in the audience data structure based at least in part on terms of the query; and identifying user identifiers that are in an audience segment defined by the query.