Device Signature Correlation for Accurate Indoor Proximity Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing device tracking methods, such as label-based and GNSS-based systems, are prone to errors and inaccuracies, especially in indoor environments, and radio-based tracking lacks precision due to signal fading, making it difficult to determine the relative position of devices within containers or vehicles.
Innovation Solution
A method and apparatus that utilize device signatures from sensors like cameras and microphones to generate parameters based on measurements, which are then correlated using neural networks to determine the proximity of mobile devices, allowing for relative positioning within a confined environment.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Extent of automation
If label-based tracking methods are used, then devices can be assigned to positions, but the method is tedious and prone to error with low automation
Solution Approach 1:
The patent replaces manual label-based tracking with acoustic signal-based automatic tracking. Devices emit or respond to acoustic signals that are captured by microphones, and neural networks automatically process these signals to determine relative positions, eliminating manual label assignment and improving both automation and reliability
Solution Approach 2:
The patent introduces acoustic signals as an intermediary medium for device tracking. Instead of directly reading labels or using satellite signals, the system uses sound waves that propagate through the environment and carry information about device positions, enabling automatic and reliable tracking
2Reliability
If GNSS-based tracking is used, then absolute position can be determined outdoors, but signals cannot penetrate walls making indoor tracking unreliable
Solution Approach 1:
The patent changes the physical parameter used for tracking from electromagnetic satellite signals (GNSS) to acoustic signals. Sound waves can penetrate walls and propagate through indoor environments effectively, making the system adaptable to indoor settings while maintaining reliable position determination
Solution Approach 2:
The system uses bidirectional acoustic communication where devices both emit and receive signals. This feedback mechanism allows devices to determine relative positions by analyzing the acoustic signals they receive from other devices, enabling reliable indoor tracking
3Measurement precision
If radio-based tracking with triangulation is used, then position can be determined in space, but precision degrades significantly due to signal fading in object-filled spaces
Solution Approach 1:
The patent converts the harmful effect of signal fading into a useful measurement. Instead of trying to avoid multipath propagation and signal degradation, the system uses neural networks to analyze the characteristic patterns of acoustic signals including their reflections and fading, transforming these environmental effects into additional information about the tracking environment that improves rather than degrades precision
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed is a technique of determining a measure of proximity between two devices (4, 6). A method implementation of the technique comprises obtaining a first device signature comprising an indication of a first point in time and a first parameter characteristic of a first measurement performed by a first sensor (10) comprised in the first device (4); obtaining a second device signature comprising an indication of a second point in time and a second parameter characteristic of a second measurement performed by a second sensor (12) comprised in the second device (6); and determining, based on the first device signature and the second device signature, the measure of proximity between the first device (4) and the second device (6).