Wireless Access Point Zone Classification via Signal Strength and AoA
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing location tracking technologies for mobile devices in multi-zone environments, such as shopping malls or train stations, face challenges in accurately predicting the zone location of mobile devices without invading user privacy, with conventional methods like video monitoring raising privacy concerns and having limited accuracy.
Innovation Solution
A system that uses signal strength information and angle-of-arrival data from multiple access points to generate a software model through machine learning, classifying mobile devices into specific zones and enabling actions based on these predictions, while maintaining user privacy by not relying on video monitoring.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If video monitoring is used to track mobile device locations, then location accuracy is improved, but user privacy is compromised
Solution Approach 1:
The patent replaces video monitoring (optical/mechanical system) with wireless signal-based detection (electromagnetic system). Access points detect mobile devices using signal strength and angle-of-arrival measurements, eliminating the need for cameras while maintaining location tracking capability. This substitution resolves the contradiction by achieving accurate location measurement without visual surveillance that invades privacy.
Solution Approach 2:
The patent introduces wireless access points and signal processing algorithms as intermediaries between the mobile devices and the location tracking system. Instead of directly observing users via video, the system uses wireless signals as an intermediary medium to infer location indirectly. This intermediary approach maintains measurement precision while avoiding direct visual intrusion into user privacy.
2Device complexity
If conventional location tracking methods are used, then implementation simplicity is improved, but prediction accuracy in multi-zone environments deteriorates
Solution Approach 1:
The patent segments the service area into multiple distinct zones, each with its own access points and classification model. The system divides the complex multi-zone environment into manageable segments, training separate software models for each zone pair combination. This segmentation enables accurate zone prediction in complex environments while maintaining reasonable system simplicity through modular model architecture.
Solution Approach 2:
The patent adds angular dimension to location tracking by incorporating angle-of-arrival (AoA) measurements alongside signal strength. This dimensional enhancement transforms 2D signal strength data into 3D spatial information, enabling accurate zone classification in multi-zone environments. The additional angular dimension provides the discrimination power needed to distinguish between adjacent zones without significantly increasing system complexity.
3Measurement precision
If machine learning software models are trained for each zone pair, then prediction accuracy is improved, but computational complexity increases
Solution Approach 1:
The patent performs preliminary offline training of software models using historical data collected during non-peak periods. The system pre-trains classification models for all zone pairs beforehand, storing the trained models for rapid online inference. This preliminary action separates the computationally intensive training phase from the real-time prediction phase, achieving high classification accuracy without burdening the real-time system with complex computations.
Solution Approach 2:
The patent transforms raw signal strength and AoA measurements into standardized feature vectors with consistent scaling and normalization. By changing the parameter representation format and applying dimensionality reduction techniques, the system reduces the complexity of input data fed into software models. This parameter transformation enables accurate zone classification while keeping computational requirements manageable through efficient feature engineering.
Data Source
AI summary
Techniques for generating a prediction for a location of a mobile device includes a network controller obtaining signal strength information and angle-of-arrival information for mobile devices from a plurality of access points disposed at a location that includes two or more zones. The network controller extracts features from the obtained information. The features indicate whether the mobile devices are more likely in a first zone than in one or more of second zones of the two or more zones. The network controller generates a software model for classifying a mobile device into one of the two or more zones by applying a computer learning process to the extracted features. The network controller uses the software model to generate a prediction indicating that a first mobile device is in one of the two or more zones, and performs an action at the location based on the prediction.