Device Identifier Quality Scoring for Uniqueness Detection
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to determine the uniqueness of device identifiers accurately, leading to ineffective targeted content delivery and inadequate fraud detection due to shared device identifiers, which can result in undesired actions or missed opportunities.
Innovation Solution
A device identification system that uses evaluation rules derived from historical data and machine learning to calculate a device quality score, allowing for the determination of a device identifier's uniqueness and enabling tailored actions based on its quality score.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If device identifiers are used for identification, then device distinction is enabled, but accuracy of uniqueness determination deteriorates due to shared identifiers
Solution Approach 1:
The patent introduces device quality scores as an intermediary mechanism to evaluate the reliability of device identifiers. Instead of directly trusting or discarding identifiers, the system calculates quality scores based on multiple parameters (device characteristics, behavior patterns, historical data) to mediate the identification process. This intermediary scoring system resolves the contradiction by providing a nuanced assessment of identifier reliability rather than binary trust/distrust decisions.
Solution Approach 2:
The system transforms the static device identifier into a dynamic evaluation process by introducing multiple parameters (device type, OS version, browser information, behavioral patterns) that change and evolve over time. The device quality score is continuously updated based on these parameter changes, allowing the system to adapt to new information and improve accuracy of uniqueness determination while maintaining reliability assessment.
2Reliability
If device identifiers are shared across devices, then fraud detection capability is improved, but content delivery effectiveness deteriorates
Solution Approach 1:
The patent applies local quality by treating different device identifiers with different levels of trust based on their specific quality scores. Instead of uniform treatment of all identifiers, the system evaluates each identifier individually using device-specific parameters and historical data. This allows the system to maintain high content delivery effectiveness for unique, high-quality identifiers while still achieving fraud detection through identification of low-quality, shared identifiers.
Solution Approach 2:
The system introduces dynamics by continuously updating device quality scores based on changing parameters and behavioral patterns. The identification and content delivery process is not static but adapts in real-time based on the current quality assessment. This dynamic approach enables the system to optimize content delivery effectiveness while maintaining fraud detection capability as new information becomes available.
3Device complexity
If traditional device identification methods are used, then system complexity is reduced, but measurement precision of device uniqueness deteriorates
Solution Approach 1:
The patent segments the device identification process into distinct components: parameter collection, quality score calculation, and identification decision-making. By dividing the complex evaluation into modular segments (device characteristics, behavioral patterns, historical data analysis), the system achieves high measurement precision while managing complexity through structured organization. Each segment can be independently optimized and maintained.
Data Source
AI summary
Systems and methods for determining uniqueness of device identifiers are provided. The uniqueness of a device identifier may be indicated by a device quality score or grade that is calculated based on a plurality of parameters associated with a device identifier as well as evaluation rules derived based on historical data. The plurality of parameters may be associated with a network event or transaction associated with the device identifier. The evaluation rules may be derived using machine learning techniques. Based on uniqueness of a device identifier, a suitable action or measure may be taken.