Non-invasive User Fingerprint Reconciliation for Ad Analytics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

The online advertising industry faces challenges in reconciling user identifiers from impression log data and behavioral targeting data, limiting the ability to assess performance and optimize advertising campaigns effectively, as these data sets are typically collected and managed disjointly without a common identifier, leading to poor planning and modeling.

Innovation Solution

The use of non-invasive user fingerprints, combined with a sampling method that optimally matches these fingerprints, allows for the reconciliation and analysis of impression and user profile data, enabling the creation of a merged dataset that can be used for advanced analytics in targeted advertising campaigns.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Ease of operation

If user identifiers from impression log data and behavioral targeting data are kept separate, then data collection and management remain simple and disjointed, but the ability to assess campaign performance and optimize advertising is limited

Engineering Contradiction:

Improvedata collection and management simplicityVSAvoidcampaign performance assessment capability

Core Design Contradiction:

Ease of operationVSLoss of information

Solution Approach 1:

The patent introduces a probabilistic matching process as an intermediary mechanism that connects impression log data and behavioral targeting data through fingerprint comparison. This mediator enables the reconciliation of otherwise disjointed data sets without requiring direct identifier linkage, thus preserving data management simplicity while enabling performance assessment.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent creates fingerprint copies of user identifiers from both data sources and compares these copies probabilistically. By working with fingerprint representations rather than direct user identifiers, the system enables data reconciliation while maintaining the original data structures and management approaches intact.

Inventive Principle:

Principle #26Copying

2Reliability

If non-invasive user fingerprints are used to reconcile data, then user privacy is protected and data can be linked across sources, but the complexity of the matching and sampling process increases

Engineering Contradiction:

Improveuser privacy protectionVSAvoidfingerprint matching and sampling process

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The patent applies sampling methodology to select a representative subset of fingerprints for matching rather than processing all possible combinations. This partial action approach reduces the computational complexity of the fingerprint matching process while maintaining the reliability of privacy protection and data reconciliation outcomes.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The patent transforms the complex fingerprint matching problem into a probabilistic sampling problem by changing the approach from exhaustive comparison to statistical representation. This parameter change in methodology simplifies the overall process complexity while preserving privacy protection capabilities.

Inventive Principle:

Principle #35Parameter changes

3Productivity

If behavioral targeting data is used for advanced analytics, then campaign optimization improves, but the data must be reconciled across multiple sources which is currently difficult

Engineering Contradiction:

Improvecampaign optimization effectivenessVSAvoiddata reconciliation process

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The probabilistic fingerprint matching serves as an intermediary layer that enables behavioral targeting data from multiple sources to be reconciled and integrated. This mediator allows advanced analytics and campaign optimization to proceed by connecting otherwise disparate data sources without requiring complex direct integration protocols.

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS10453070B2Non-invasive sampling and fingerprinting of online users and their behavior

Publication Date: 2019.10.22 BLUE KAI INC

AI summary

A system, method, apparatus, and processor readable non-transitive storage media are described for matching items in large datasets based on non-invasive fingerprints of users so that collected metric data for advertisements (media) and behavioral data may be reconciled and analyzed. Since user fingerprints may not generate a unique one to one correspondence or mapping under certain constraints, the various embodiments employ a sampling method that optimally matches the output of a random sampling of non-invasive fingerprints. The use of non-invasive fingerprints and specialized sampling enables the various embodiments to provide advanced analytics for advertising content and metric data in targeted behavior advertising campaigns. To compare impressions with user profile data, the various embodiments employ in part the time stamp dimension of user profiles to generate temporally unique persistent non-invasive fingerprints.