Suspect Data Source Detection in Location Services
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The accuracy and quality of geo-location data in location-based services networks are often compromised due to anomalies, errors, or fraudulent activities, leading to inefficient and irrelevant advertisements being delivered to users, which is time-consuming and costly to evaluate manually.
Innovation Solution
A method and system that calculates notional speed between consecutive geo-coordinates, flags suspicious data sources with excessive speed, and analyzes the frequency and error rates of these sources to identify suspect data sources, using a weighted graph approach to determine the source of erroneous data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual evaluation of geo-location data quality is performed, then accuracy and quality can be assessed, but time consumption and cost increase significantly
Solution Approach 1:
The system enables self-service by having data sources automatically flag themselves as suspect when their geo-location data shows impossible speeds. The analysis system automatically identifies patterns without requiring manual human evaluation, allowing the system to self-regulate and self-optimize data quality through automated detection and flagging of anomalous entries.
Solution Approach 2:
The patent replaces the mechanical manual evaluation process with an automated computational system. The analysis system uses algorithms to calculate speeds between consecutive geo-location points, automatically identifies impossible speeds, and flags suspect data sources without human intervention, thereby eliminating time-consuming manual assessment while maintaining accuracy.
2Adaptability or versatility
If geo-location data from multiple data sources is collected, then comprehensive coverage is achieved, but data quality and accuracy deteriorate due to anomalies and errors
Solution Approach 1:
The system implements feedback mechanisms where the analysis system continuously monitors geo-location data from multiple sources, identifies anomalies in real-time, and provides feedback by flagging suspect data sources. This feedback loop enables the system to maintain data quality while collecting comprehensive data from multiple sources, as the feedback mechanism automatically filters out erroneous entries.
Solution Approach 2:
The patent applies local quality by treating different data sources differently based on their individual reliability patterns. Instead of uniformly accepting all data sources, the system analyzes each source's historical performance and flags specific entries from specific sources when anomalies are detected. This allows the system to maintain high data quality from reliable sources while still benefiting from comprehensive coverage through multiple sources.
3Ease of manufacture
If conventional methods to detect anomalies are used, then simple filtering is applied, but measurement precision and reliability of geo-location data deteriorate
Solution Approach 1:
The system employs dynamic analysis by calculating speeds between consecutive geo-location points and adapting the detection criteria based on real-time data patterns. Rather than using static filtering rules, the system dynamically computes impossible speeds based on the actual movement patterns of devices, allowing it to accurately identify anomalies while maintaining ease of implementation through automated calculation.
Data Source
AI summary
A method and system for determining a suspected data source among one or more data sources reporting geo coordinate data in a location based services network is disclosed. In some embodiments, the method includes, receiving geo coordinates of a user device reported by the one or more data sources over a period of time, calculating a notional speed between geo coordinates reported at two consecutive times, flagging simultaneously, one or more data sources that reported the geo coordinates at the two consecutive times resulting in a notional speed that exceeds a predefined notional speed, and analysing a data on at least one of, the number of instances of geo coordinates reported by a data source, the number of instances a data source was flagged, the data sources that were also flagged simultaneously with each flagging, for determining the suspect source of data.