Navigation Path Analysis for Ad Targeting Accuracy

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Publishers manipulate websites to artificially rank high in search results and generate revenue by displaying low informational content with high click-through rates, leading to users selecting ads without genuine interest, which affects the effectiveness of advertisement targeting and user experience.

Innovation Solution

A system and method that determine selection data, such as click-through rates, to identify manipulated articles and geographical locations, allowing for targeted advertisement selection and differentiation between informative and non-informative content, thereby improving ad relevance and user engagement.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Productivity

If publishers create web sites with little informational content and host multiple advertisements, then the number of ad clicks increases and revenue is generated, but the quality of advertisement targeting deteriorates and user experience worsens

Engineering Contradiction:
Improvead click-through rateVSAvoidad targeting effectiveness
Core Design Contradiction:
ProductivityVSReliability

Solution Approach 1:

The system performs preliminary analysis of user navigation paths and article information quality before advertisement selection. By pre-calculating path metrics and content quality scores, the system can identify manipulated articles in advance and exclude them from ad placement, ensuring that ads are only shown on genuine content pages where targeting remains effective.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system introduces an intermediary evaluation layer between the article and advertisement matching process. This intermediary assesses the quality of the article based on navigation path data and information content, acting as a gatekeeper that prevents ads from being placed on manipulated low-quality pages, thus preserving ad targeting effectiveness while still allowing high click-through rates on genuine content.

Inventive Principle:
Principle #24Intermediary (Mediator)

2Productivity

If publishers manipulate websites to appear high in search results, then visibility and ad revenue increase, but the accuracy of keyword matching and ad relevance decreases

Engineering Contradiction:
Improvesearch result visibilityVSAvoidkeyword matching accuracy
Core Design Contradiction:
ProductivityVSMeasurement precision

Solution Approach 1:

The system implements feedback mechanisms that monitor user navigation patterns and article performance metrics. By analyzing whether users actually engage with the content or immediately click ads, the system provides feedback on article quality. This feedback loop allows the system to adjust keyword matching accuracy by identifying and downweighting manipulated articles that show signs of deception, thereby maintaining precise ad relevance despite high visibility.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The system dynamically changes parameters such as keyword weightage and matching thresholds based on detected article quality. For articles identified as manipulated through navigation path analysis, the system adjusts the parameter weights to reduce their influence on ad selection, effectively changing the matching criteria to maintain accuracy while allowing manipulated articles to maintain their search visibility.

Inventive Principle:
Principle #35Parameter changes

3Speed

If users click on advertisements to view more informative web pages, then navigation efficiency improves, but the distinction between genuine interest and manipulation becomes blurred

Engineering Contradiction:
Improvenavigation efficiencyVSAvoidmanipulation detection
Core Design Contradiction:
SpeedVSDifficulty of detecting and measuring

Solution Approach 1:

The system adds another dimension to the analysis by examining the entire navigation path rather than just individual clicks. Instead of looking at a single ad click in isolation, the system analyzes the sequence of pages visited, the time spent on each page, and the pattern of navigation. This multi-dimensional approach allows the system to distinguish between genuine user research behavior (visiting multiple informative pages) and manipulation patterns (rapid sequential clicks on ads from low-quality pages), thereby maintaining manipulation detection accuracy while preserving navigation efficiency.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

Data Source

PatentUS8005716B1Methods and systems for establishing a keyword utilizing path navigation information
Publication Date: 2011.08.23 GOOGLE LLC
  • US8005716B1 patent drawing
  • US8005716B1 patent drawing
  • US8005716B1 patent drawing

AI summary

Systems and methods for determining and utilizing path navigation information. In one aspect, a method includes determining an article containing at least one item, determining a path associated with the article, and identifying at least one term associated with the at least one item based at least in part on the path.