Indoor Location Obfuscation Using Modulated Light and Zone-Based Privacy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current technologies for determining customer positions in indoor spaces, such as warehouses or stores, face challenges in balancing data collection for service development with privacy concerns, as existing methods may compromise customer privacy and are inefficient in managing location determination.
Innovation Solution
A system utilizing modulated illumination from light sources and portable mobile devices to capture images, which processes and obfuscates location data using a machine learning model trained on accuracy offsets, ensuring privacy compliance by shifting or blurring images based on predetermined privacy levels in different zones.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of information
If location data is collected for service development, then data availability improves, but customer privacy is compromised
Solution Approach 1:
The patent applies local quality by implementing different privacy protection levels for different zones within the indoor space. Each zone is assigned a specific privacy level, and images are processed differently based on their location. High-privacy zones receive greater obfuscation while low-privacy zones maintain better location accuracy, thus collecting useful data while protecting customer privacy where needed.
Solution Approach 2:
The patent changes the parameter of image processing intensity based on zone-specific privacy levels. By adjusting the degree of obfuscation (parameter change) according to the predetermined privacy level of each zone, the system enables granular data collection in some areas while maintaining strong privacy protection in others, resolving the contradiction between data availability and privacy protection.
2Object-affected harmful factors
If image obfuscation is applied to protect privacy, then privacy protection improves, but location determination accuracy deteriorates
Solution Approach 1:
The patent resolves this contradiction by applying local quality through zone-based differential privacy protection. Different regions of the indoor space are assigned different privacy levels, and image obfuscation is applied selectively. In low-privacy zones, minimal obfuscation maintains high location accuracy, while in high-privacy zones, stronger obfuscation protects customer privacy. This localized approach ensures that privacy protection does not uniformly degrade location determination accuracy across all areas.
3Object-affected harmful factors
If uniform privacy protection is applied across all zones, then privacy protection improves, but data utility for service development deteriorates
Solution Approach 1:
The patent implements local quality by dividing the indoor space into multiple zones with different predetermined privacy levels. This allows the system to apply uniform privacy protection principles within each zone while varying the protection intensity across different zones. Low-privacy zones provide useful position data for service development, while high-privacy zones ensure customer privacy protection, thus maintaining overall data utility without compromising privacy.
Solution Approach 2:
The patent applies parameter changes by adjusting the privacy level parameter for each zone independently. This enables granular control over the degree of image obfuscation applied in different areas. By changing the privacy level parameter based on zone characteristics and service requirements, the system optimizes the balance between privacy protection and data utility, allowing valuable position data to be collected in appropriate zones while maintaining privacy where needed.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach efficiently manages location obfuscation, ensuring privacy protection while enabling granular data collection for service development without compromising navigation accuracy, by using a machine learning model to determine the extent of image processing required based on privacy levels in various zones.
Implementation Method 1
a plurality of light sources, wherein each light source of the plurality of light sources is configured to emit modulated illumination
Data Source
AI summary
A system (100) for obfuscation of a position of at least one subject (110) in an indoor space (120), comprising a plurality of light sources (130) configured to emit modulated illumination, a mobile device (150) arranged to be portable by the at least one subject, configured to capture image(s) (156) comprising the modulated illumination, a server (160) configured to receive first image(s) (152) and determine a location of the mobile device(s), receive information related to zone(s) of the indoor space, predetermined privacy level(s) and privacy threshold level(s), and to perform a processing of the image(s) and a determination of an accuracy of the location of the mobile device(s), train a machine learning, ML, model by inputting the determined accuracy, wherein the mobile device is further configured to perform a processing of a captured second image(s) (154) by the trained ML model.