Location-Spoofing Detection via Inference Engine and ML
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Location-spoofing by transport providers in on-demand transport services, which involves falsifying location data to deceive GPS systems and manipulate routes, leading to fraudulent activities such as fare manipulation and queue jumping, is a significant challenge that existing technologies have not adequately addressed.
Innovation Solution
A computing system that detects location-spoofing by analyzing location data from transport providers, using a combination of sensor data, driving profiles, and machine learning algorithms to determine if a transport provider is operating a location-spoofing application, and excludes such providers from service requests, thereby preventing fraudulent activities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If location-spoofing detection analysis is performed on transport providers, then reliability of transport service is improved, but device complexity increases
Solution Approach 1:
The patent introduces an inference engine as an intermediary component that receives location data from transport providers and performs detection analysis. This intermediary layer handles the complex analysis work, separating the detection function from both the transport providers' devices and the core matching engine, thereby improving reliability while managing system complexity through modular architecture.
Solution Approach 2:
The patent replaces manual or simple verification methods with automated machine learning-based inference engines that analyze location data patterns. This substitution of mechanical/simpler verification systems with intelligent automated systems enables sophisticated spoofing detection without requiring complex manual intervention, resolving the contradiction between reliability improvement and complexity management.
2Measurement precision
If location data analysis is performed to detect spoofing, then measurement precision of location authenticity is improved, but loss of time increases
Solution Approach 1:
The inference engine performs location authenticity analysis in advance during the provider selection process, before final matching occurs. By conducting detection analysis preliminarily and continuously monitoring location data patterns, the system identifies suspicious providers early, preventing fraudulent matching while maintaining efficient service delivery and minimizing time loss.
Solution Approach 2:
The system implements continuous feedback loops where location data from transport providers is constantly analyzed by the inference engine. This real-time feedback mechanism allows the system to detect spoofing patterns as they occur, adjusting provider eligibility dynamically without requiring complete re-verification, thus maintaining measurement precision while reducing overall time loss through iterative rather than exhaustive checking.
Data Source
AI summary
A computing system can receive location data from a computing device of a driver. Based at least in part on the location data, execute a location-based feasibility model to determine that one or more anomalous locational attributes are present, where the location-based feasibility model outputs a probability that the computing device of the respective driver is performing location-spoofing. Based on the probability indicating that the computing device of the driver is performing location-spoofing, the system associates a data set with a driver profile of the respective driver.