Virtual Entity Pool for Cross-Device User Identification
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing technologies face challenges in accurately determining unique users across multiple devices, as cookies cannot differentiate between users on different devices and are affected by cookie deletion, leading to inaccuracies in measuring audience exposure to content.
Innovation Solution
A method involving the creation of a virtual pool of entities, division into sub-pools, recording cookies, and using machine learning and statistical analysis to determine unique entities by assigning virtual entities to cookies, accounting for geographic location and demographics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If cookies are used to track users across devices, then user exposure can be monitored, but accuracy deteriorates because cookies cannot differentiate between users on different devices
Solution Approach 1:
The patent introduces probability distribution functions as an intermediary layer between cookie data and user identification. Instead of directly mapping cookies to users, the system uses statistical models that incorporate multiple data sources (device characteristics, browsing behavior, geographic location) to probabilistically determine unique user identity across devices, thereby resolving the information loss problem
Solution Approach 2:
The system transforms the measurement parameters from simple cookie identifiers to multi-dimensional statistical parameters including device fingerprints, browsing patterns, and demographic probabilities. This parameter transformation enables more precise user differentiation across devices by capturing nuanced behavioral characteristics rather than relying on single-point cookie data
2Ease of manufacture
If traditional cookie-based tracking is used, then implementation is simple, but measurement accuracy deteriorates due to cookie deletion and device variability
Solution Approach 1:
The patent segments the user tracking problem into multiple independent components: device fingerprinting, behavioral pattern recognition, geographic location tracking, and probability calculation. Each component processes specific data types independently, then combines results through statistical models. This segmentation maintains implementation feasibility while dramatically improving measurement accuracy by not relying on a single vulnerable cookie mechanism
Solution Approach 2:
Statistical models and probability distribution functions serve as intermediaries that process and reconcile data from multiple tracking sources. These intermediaries transform raw, potentially conflicting data into reliable user identification metrics, maintaining system simplicity while enhancing accuracy through layered processing
3Adaptability or versatility
If multiple devices are used by same user, then user flexibility increases, but user identification becomes difficult leading to duplicate content exposure
Solution Approach 1:
The system changes from static identification parameters (single cookie ID) to dynamic multi-parameter profiles that adapt to different devices. By continuously analyzing browsing behavior patterns, device characteristics, and contextual data across sessions, the system maintains accurate user identification even when users switch between multiple devices, preventing duplicate content exposure while preserving user flexibility
Data Source
AI summary
Methods, systems, and apparatus include computer programs encoded on a computer-readable storage medium, including a method for discovering unique entities over multiple devices. A virtual pool of entities is created and divided into subpools, each including fewer than all entities. Subpools are subdivided into delta pools. Cookies are recorded for each delta pool when the particular portion of content is presented to or accessed by entities in the delta pool. Recorded cookies are divided into cookie types based on cookie characteristics. Machine learning and statistical analysis algorithms are used to automatically determine sizes of delta pools and probabilities of each cookie type being classified as belonging to particular delta pools. Virtual entities are assigned from the virtual pool to each of the recorded cookies that were recorded when the particular portion of content was presented. A number of unique entities that accessed the particular portion of content is determined.