ML Model Detecting Venue Device Presence via Wireless Pings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems for tracking foot traffic within venues face inaccuracies due to reliance on GPS data, which struggles to differentiate between devices inside and outside a venue, and foot traffic models are not universally applicable across different types and sizes of stores.
Innovation Solution
A machine-learning model trained on wireless pings from mobile devices, using parameters like signal strength, dwell time, and MAC address, to determine device location within a specific venue, incorporating additional data from systems like POS and loyalty programs to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS technology is used to track foot traffic, then user location can be determined, but the system requires user interaction (enabling GPS tracking) and cannot accurately differentiate between devices inside and outside the venue
Solution Approach 1:
The patent uses wireless network infrastructure (access points, routers) as intermediaries to detect device presence. Instead of relying on GPS which requires active user permission, the system passively monitors wireless signals from devices to determine their location and presence in the venue, eliminating the need for users to enable location tracking services.
Solution Approach 2:
The patent replaces the mechanical/GPS-based location system with a wireless network-based detection system. By substituting GPS technology with wireless network signal analysis, the system achieves location detection without requiring the mechanical interaction of enabling GPS services on user devices.
2Adaptability or versatility
If a universal foot traffic model is applied across different venues, then model deployment is simplified, but the model becomes inaccurate for different types and sizes of stores
Solution Approach 1:
The patent segments the foot traffic detection task into venue-specific models. Instead of using a single universal model, the system creates and trains separate machine learning models for each venue, allowing each model to be optimized for that specific venue's characteristics, layout, and traffic patterns while maintaining the ability to deploy across multiple venues.
Solution Approach 2:
The patent applies local quality by training venue-specific models that are tailored to the unique characteristics of each location. Each model incorporates local data about the venue's layout, typical foot traffic patterns, and spatial characteristics, enabling high-accuracy detection for each specific venue while the overall system maintains versatility through automated model training and deployment.
Data Source
AI summary
A model is configured to determine whether a device is located within a venue. During a baseline time period, the system detects wireless pings from mobile devices. The system obtains device parameters from the wireless pings. The system evaluates the device parameters to determine whether a mobile device entered the venue or remained outside of the venue. The system trains a model on training data corresponding to the baseline time period, the model configured to differentiate between devices that enter the venue and devices that remain outside the venue based on device parameters associated with the device. The system applies the model to future detected devices to determine whether or not the devices enter the venue.