User Profile Generation via Periodic Location Fixes
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current demographic and marketing profiling methods are limited by their coarse resolution, failing to accurately target small or concentrated communities and individuals due to their inability to capture high-resolution consumer behavior and mobility patterns, leading to ineffective personalized marketing and media delivery.
Innovation Solution
The method involves generating user profiles based on periodic location fixes from mobile devices, which are analyzed to determine visited locations, dwell times, and demographic details, allowing for high-resolution geographic and demographic profiling, enabling personalized marketing and media delivery at an individual level.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If demographic profiling is conducted at coarse geographic levels (county or metropolitan populations), then manual data collection methods (surveys, census reports) can be used, but the resolution is insufficient to capture small or concentrated communities and individual behavior patterns
Solution Approach 1:
The patent replaces manual data collection methods (surveys, census reports) with automated electronic data collection from mobile devices. Location data is automatically captured via GPS and mobile phone sensors, eliminating the need for manual surveying and census-taking while achieving much higher geographic resolution at the individual level.
Solution Approach 2:
The patent introduces mobile devices as intermediaries between individuals and the profiling system. These devices automatically collect location data and transmit it to servers, serving as a bridge that enables high-resolution tracking without requiring direct manual intervention from researchers or census workers.
2Measurement precision
If household-level segmentation is used, then demographic information can be obtained, but the profile is assumed for every person in the household irrespective of their age group or financial responsibilities
Solution Approach 1:
The patent segments the population from household-level to individual-level by tracking each person's mobile device separately. This divides the aggregate household data into distinct individual profiles, allowing each person to be profiled according to their own location patterns rather than inheriting household-level assumptions.
Solution Approach 2:
The patent collects more location data than traditionally necessary by continuously tracking individual mobile devices rather than relying on periodic household surveys. This excessive data collection ensures that individual behavior patterns are captured in sufficient detail to create accurate individual profiles.
3Adaptability or versatility
If web usage patterns are tracked, then predicted profiles of sites or content of interest can be generated, but behavior outside that environment including mobility and consumption patterns around home location cannot be predicted
Solution Approach 1:
The patent adds a new dimension to behavior tracking by moving from virtual web usage patterns to physical world location data. GPS coordinates and mobile device positioning provide spatial information about real-world mobility that complements online behavior data, enabling prediction of both digital and physical consumption patterns.
Solution Approach 2:
The patent creates a universal profiling system that works across multiple environments by combining web usage tracking with location-based tracking. The same mobile device and server infrastructure that tracks online behavior also tracks offline mobility, providing a unified approach to predicting both virtual and physical consumer behavior.
Data Source
AI summary
Implementations relate to systems and methods for generating a user profile based on periodic location fixes. A cellular telephone or other mobile device captures location information via GPS or other capability. A location history can be generated from accumulated location fixes. The location history is then analyzed to detect the user's travel and dwell patterns. That information can be combined with business classification (e.g., SIC, etc.) or Point of Interest (POI) databases to identify a user's likely home, work, or other locations based on dwell-times, time of day, and other parameters. The user's age and gender can potentially be inferred based on types of locations visited, such as school locations. The user profile can be correlated with market segmentation databases to generate a marketing rating, such as a Nielsen or Claritas rating. Advertising, media, or other content can then be tailored to the user's individual location and demographic profiles.