Wireless User Geolocation Without GPS Using Cell-Specific Models
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Wireless service providers lack accurate methods to geolocate a significant portion of their users due to GPS data unavailability, necessitating alternative techniques for real-time location prediction in cellular networks.
Innovation Solution
Utilizing machine learning models trained on key performance indicators like signal strength and timing events to predict user locations, with adjustable accuracy and latency based on computational constraints.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If GPS data is used for geolocation, then location accuracy is improved, but GPS data is unavailable for a significant portion of users
Solution Approach 1:
The patent uses machine learning models as intermediaries to predict user locations based on network event data when GPS data is unavailable. The models act as a mediator between network measurements and location estimation, providing geolocation capability for users without GPS access.
Solution Approach 2:
The patent replaces the GPS-based mechanical positioning system with a computational approach using machine learning models that analyze network event data. This substitution enables geolocation through software-based prediction rather than hardware-based satellite positioning.
2Reliability
If machine learning models are used to predict user locations, then geolocation capability is improved for users without GPS, but computational resources and processing time are consumed
Solution Approach 1:
The patent segments the geolocation task by implementing separate machine learning models for different cells in the wireless network. Each model is trained on local event data and operates independently, distributing the computational load across multiple specialized models rather than using a single complex centralized system.
Solution Approach 2:
The patent performs preliminary training of machine learning models using historical event data before actual geolocation operations. This pre-computation phase prepares the models in advance, reducing the computational burden during real-time location prediction and enabling faster inference.
3Adaptability or versatility
If real-time location prediction is implemented for millions of users, then network utility is improved, but processing speed and latency become critical constraints
Solution Approach 1:
The patent divides the large-scale geolocation problem into smaller cell-specific tasks, with each machine learning model handling predictions for its local cell. This segmentation enables parallel processing across multiple cells, improving overall processing speed and reducing latency for millions of users.
Solution Approach 2:
The patent processes event data in batches and uses approximate prediction methods that provide sufficient accuracy for most applications without requiring exhaustive computation. This partial action approach achieves acceptable results within real-time constraints while maintaining high productivity.
Data Source
AI summary
A method includes selecting a first machine learning model from a plurality of machine learning models that are trained for use in performing geolocation, wherein the first machine learning model is selected to perform geolocation within a first cell of a plurality of cells of a wireless network, acquiring event data from a plurality of wireless devices within the first cell, grouping the event data into a plurality of records, wherein each record of the plurality of records contains event data that indicates a common wireless device of the plurality of wireless devices, a common cell of the plurality of cells, and a common timestamp, and generating a predicted location of a first wireless device of the plurality of wireless devices, using the first machine learning model, wherein the first machine learning model outputs the predicted location in response to an input of a record of the plurality of records.