Negative Keyword Segmentation for Ad Targeting Optimization

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems for displaying website invitations on search engines, such as Google Adwords, lack effectiveness in identifying and utilizing negative keywords and optimizing invitation cues based on user interactions, leading to inefficient ad targeting and reduced conversion rates.

Innovation Solution

A system and method for identifying negative keywords and generating invitation cueing sets by analyzing user interactions from website logs, defining keywords that did not result in transactions as negative keywords, and using these to improve ad targeting by excluding non-converting keywords and optimizing invitation templates.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Area of stationary object

If website invitations are displayed based on broad keyword matching, then ad coverage and visibility are improved, but ad relevance and conversion rates deteriorate

Engineering Contradiction:
Improvead coverageVSAvoidconversion rate
Core Design Contradiction:
Area of stationary objectVSReliability

Solution Approach 1:

The patent segments keywords into positive and negative categories based on user interaction data. Positive keywords trigger ad display while negative keywords suppress them, creating a segmented approach to keyword matching that improves both coverage and relevance simultaneously

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system implements feedback loops by collecting user interaction data (clicks, conversions, bounce rates) and using this information to dynamically adjust keyword classification. This feedback mechanism continuously improves ad relevance while maintaining broad coverage

Inventive Principle:
Principle #23Feedback

2Area of stationary object

If all keywords are used for ad targeting, then ad visibility is improved, but ad budget efficiency deteriorates

Engineering Contradiction:
Improvead visibilityVSAvoidad budget efficiency
Core Design Contradiction:
Area of stationary objectVSLoss of energy

Solution Approach 1:

The patent extracts and isolates negative keywords from the overall keyword set based on poor performance metrics. These extracted negative keywords are then excluded from ad targeting, preventing wasted budget spend while maintaining visibility through positive keywords

Inventive Principle:
Principle #2Taking out (Extraction)

Solution Approach 2:

The system changes the parameter of keyword effectiveness by using conversion data to reclassify keywords from positive to negative status. This dynamic parameter adjustment optimizes budget allocation toward high-converting keywords while eliminating spend on low-performing ones

Inventive Principle:
Principle #35Parameter changes

3Area of stationary object

If negative keywords are not identified and excluded, then ad coverage is maintained, but ad relevance and user experience deteriorate

Engineering Contradiction:
Improvead coverageVSAvoidad relevance
Core Design Contradiction:
Area of stationary objectVSLoss of information

Solution Approach 1:

The patent implements a dynamic keyword classification system where keywords can transition between positive and negative status based on real-time performance data. This dynamic adjustment maintains ad coverage through positive keywords while automatically filtering out irrelevant negative keywords to preserve ad relevance

Inventive Principle:
Principle #15Dynamics

Data Source

PatentUS9400844B2System for finding website invitation cueing keywords and for attribute-based generation of invitation-cueing instructions
Publication Date: 2016.07.26 KENSHOO
  • US9400844B2 patent drawing
  • US9400844B2 patent drawing
  • US9400844B2 patent drawing

AI summary

A system for identifying keywords which may include a non-acquiescence information collector operative to collect information indicating, for each individual website from among a multiplicity of websites, at least one keyword which brought at least one user into contact with said individual website but did not result in a defined criterion for acquiescence of a user to at least one suggestion presented by said website; and a negative keyword definer operative to define at least one specific keyword which brought at least one user into contact with a specific website but did not result in a transaction between said user and said website, as a negative keyword for said specific website. Positive keyword extraction based on aggregation of visitor acquiescence information may be provided. Paradigm structuring may include template generation of invitations and/or attribute based generation of invitation cueing sets.