Device Quality Score for Location Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Mobile devices struggle to accurately determine high-value geographic locations such as home and work places without direct user input, as existing location tracking methods like cookies are not applicable, and proximity activation systems alone may not provide sufficient location accuracy.
Innovation Solution
The Reveal™ system uses a point rank algorithm and machine learning to analyze startup events and proximity data from beacons, filtering and clustering latitude and longitude information to determine home and work locations by establishing a point rank index and utilizing DBSCAN algorithm for accurate location assignment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If proximity activation systems and startup events are used to determine location, then location tracking capability is improved, but location accuracy and reliability deteriorate
Solution Approach 1:
The system performs preliminary actions by collecting and storing multiple startup events and proximity activations over time before determining the final location. The point rank algorithm accumulates location data points from various sources (startup events, beacon proximities) and processes them in batches to establish high-value geographic locations, rather than relying on single-point measurements that lack accuracy.
Solution Approach 2:
The system implements feedback mechanisms by continuously monitoring and re-evaluating location confidence scores. The point rank algorithm assigns ranks to different location hypotheses based on accumulated evidence, and the system can refine location determinations over time as more startup events and proximity data are collected, improving accuracy through iterative feedback.
2Reliability
If multiple data sources are aggregated for location determination, then location reliability is improved, but system complexity increases
Solution Approach 1:
The system segments the location determination process into distinct functional modules: startup event collection, proximity activation tracking, point rank algorithm processing, and high-value location assignment. Each module handles specific aspects of data processing independently, making the overall complex system manageable through modular organization and clear separation of concerns.
Solution Approach 2:
The point rank algorithm serves as an intermediary that mediates between multiple data sources (startup events, beacon proximities) and the final location determination. It transforms raw, heterogeneous data from various sources into a standardized ranking system that can be processed to identify high-value geographic locations, simplifying the integration of multiple data streams.
3Measurement precision
If direct user input is required for location data, then location accuracy is improved, but ease of operation deteriorates
Solution Approach 1:
The system implements self-service by automatically collecting location data from startup events and proximity activations without requiring direct user input. The mobile application autonomously tracks when it starts up and when the device approaches beacon locations, automatically processing this data through the point rank algorithm to determine high-value geographic locations like home and work addresses.
Solution Approach 2:
The system uses startup events and beacon proximities as intermediaries to indirectly capture location information without requiring users to manually input data. These intermediate data sources naturally occur during normal device usage, allowing the system to infer high-value locations from patterns in the intermediary data rather than direct user declarations.
Data Source
AI summary
The present invention is a method and system for scoring the reliability of a predictive determination regarding the assigning of a geographic location, such as a work or home location, to the owner or user of a mobile device. Mobile devices such as smart phones, tablets, internet computers, and other hand-held mobile devices may be preferentially targeted for ads based upon the geographic location of the owner or user of the mobile device. The home or work location is determined based upon startup events associated with the mobile device as tracked by startup activations of the mobile device, beacon activations, tile activations, or any other Bluetooth or near field communication device activation, during either day time or night time hours. Reliability scoring of the determination is affected through extraction and normalization of discrete features of a device.