Geographic Area Profiling Using Active and Passive Mobile Network Events
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for profiling geographic areas based on mobile network data are limited in accuracy and scope, particularly in determining socio-demographic profiles and user behavior, and do not effectively utilize passive network events.
Innovation Solution
A method and system that utilizes active and passive network events from mobile devices to calculate user parameters, identify points of interest, and determine socio-demographic profiles by assigning statistical weights to resident users, combining these with external datasets to extrapolate information to the general population, and aggregate by micro-segments.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If existing methods use mobile network data for geographic area profiling, then data collection is simplified, but measurement precision of socio-demographic profiles is insufficient
Solution Approach 1:
The patent combines multiple data sources including active network events (calls, SMS, data traffic) and passive network events (device presence, cell tower locations, handovers) to create a comprehensive user profile. This merging of data types enables precise socio-demographic profiling while maintaining ease of data collection through existing network infrastructure.
Solution Approach 2:
The system uses a unified data collection framework that handles multiple types of network events (active and passive) through a single processing architecture. This multi-functional approach allows precise geographic area profiling without requiring separate specialized systems for each data type, thus improving measurement precision while maintaining operational simplicity.
2Measurement precision
If the system processes active and passive network events to improve profiling accuracy, then measurement precision improves, but device complexity increases
Solution Approach 1:
The patent segments the data processing system into distinct modules: one for collecting active network events, another for passive network events, a third for user profile generation, and a fourth for geographic area characterization. This segmentation allows the complex task of processing multiple event types to be broken down into manageable components, improving accuracy while controlling system complexity through modular architecture.
Solution Approach 2:
The system introduces an intermediary processing layer that standardizes and normalizes both active and passive network events before feeding them into the user profile generation algorithm. This intermediary layer abstracts the complexity of handling different event types from the final profiling function, enabling high measurement precision while keeping the core processing logic relatively simple and maintainable.
3Measurement precision
If statistical weights are assigned to resident users for extrapolation, then measurement precision of population characteristics improves, but loss of information increases
Solution Approach 1:
The patent applies different statistical weighting strategies to different user groups based on their local characteristics and representation in the network data. Users in specific geographic areas or demographic groups receive adjusted weights based on their actual network presence and the corresponding population demographics. This local quality approach enables precise population characteristic estimation while minimizing information loss by treating different user populations differently rather than applying a uniform weighting scheme.
Solution Approach 2:
The system dynamically adjusts statistical weight parameters based on network data quality, geographic location, and demographic characteristics. By changing the weight parameters adaptively rather than using fixed values, the system achieves high measurement precision for population characteristics while reducing information loss. The parameter changes allow the system to compensate for sampling biases and data gaps without requiring complete user data, thus maintaining privacy while improving accuracy.
Data Source
AI summary
The present invention discloses a method, system and computer program for characterising geographic areas. The method comprises accessing user data from a mobile network operator, said data being associated with active and/or passive network events from the connections established between user mobile devices and mobile network operator towers; calculating a set of user parameters using said accessed data, the calculation of the parameters comprising: calculating a visit parameter, calculating points of interest of each user, and obtaining web browsing data from mobile devices based on obtaining network traffic from each device in the network; and determining a characterisation profile of a geographic area by calculating a socio-demographic profile of the temporary and permanent resident users in said geographic area.