Automated Ad Variant Detection Using Segment Hit Vectors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current automated techniques inadequately address the detection of variants of advertisements in ad databases, leading to inefficiencies and errors in classification and tagging processes, which are time-consuming and prone to human curator discrepancies.
Innovation Solution
An automated method using vector of segment hits is employed to identify when a first advertisement is a likely variant of a second by comparing vectors created from sequential segments of both ads, determining matching segments to identify variants and associate them with existing metadata.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If automated techniques are used to classify and tag ads, then productivity is improved, but the ability to detect variants of ads deteriorates
Solution Approach 1:
The ad is divided into multiple sequential segments of predefined time length. A vector of segment hits is created by comparing each segment of the sample ad with segments of the reference ad. This segmentation allows the system to detect variants by analyzing segment-level matches while maintaining overall ad identification efficiency.
Solution Approach 2:
A vector of segment hits serves as an intermediary representation between the raw ad content and the variant detection decision. The vector captures matching patterns across segments, enabling automated techniques to detect variants with high precision while maintaining productivity.
2Measurement precision
If human curators are used to classify and tag ads, then measurement precision is improved, but productivity deteriorates
Solution Approach 1:
The system performs self-service by automatically detecting ad variants through vector comparison without requiring human curator intervention. The automated process identifies variants by comparing segment hit vectors, achieving both high precision and high productivity simultaneously.
Solution Approach 2:
The patent replaces the mechanical human judgment process with an automated computational system. The vector of segment hits comparison mechanism substitutes human curator analysis, eliminating human judgment discrepancies while maintaining high classification accuracy and increasing processing speed.
3Quantity of substance
If all new ads are stored in the database, then completeness of ad inventory is improved, but device complexity deteriorates
Solution Approach 1:
Variant ads are merged with their reference ad in the database. Instead of storing duplicate variant ads separately, the system groups them together using the vector of segment hits comparison. This reduces database size and management complexity while maintaining complete ad inventory through variant associations.
Solution Approach 2:
The reference ad serves as a universal representation for itself and all its variants. By storing one reference ad and identifying variants through vector comparison, the system achieves multi-functionality where a single database entry represents multiple related ads, reducing overall database complexity.
Data Source
AI summary
Automated methods are provided for identifying when a first advertisement (ad) is a likely match of either a second ad, or one or more variants of the second ad. The first ad, the second ad, and the one or more variants of the second ad each include a plurality of sequential segments of a predefined time length, wherein the second ad and the one or more variants of the second ad are each reference ads, and the first ad is a sample ad. Vectors of segment hits are created for the various ads and are compared to each other to identify matches that represent such variants.