Crowd Counting via Aggregated Mobile Network Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing crowd counting methods using mobile communication networks face challenges in accurately determining the number of people at public events due to limitations in defining the optimal Area of Interest (AoI) and privacy concerns related to individual user data collection.
Innovation Solution
A method and system that determine the optimal AoI by analyzing aggregated mobile network data, including user equipment (UE) traffic patterns over time, to estimate the number of people at an event while ensuring user privacy by not collecting identifiable information, using a computation engine to process data and normalize statistical quantities to calculate the precise number of attendees.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Object-affected harmful factors
If aggregated mobile network data is used to count crowd, then user privacy is protected, but measurement precision deteriorates due to lack of individual user data
Solution Approach 1:
The patent segments the AoI into multiple cells, each served by a base station. Instead of analyzing individual user data across the entire AoI, the system aggregates anonymous connection data at the cell level first, then combines results from multiple cells. This segmentation allows privacy protection at the individual level while achieving accurate crowd counting through aggregated statistical analysis of connection durations and frequencies across segmented areas.
Solution Approach 2:
The patent introduces base stations as intermediaries between users and the crowd counting system. Base stations collect and anonymize user connection data locally before transmitting aggregated statistics to the crowd counting server. This intermediary layer ensures that individual user identities and detailed behavior patterns remain protected, while still enabling accurate crowd estimation through aggregated metrics like total connection duration and number of unique users per cell.
2Ease of operation
If a fixed Area of Interest radius is used, then the system is simple to operate, but measurement precision deteriorates because the optimal radius varies with different events and locations
Solution Approach 1:
The patent implements dynamic AoI radius adjustment based on historical crowd data, event type, and location characteristics. Instead of using a fixed radius, the system adapts the AoI boundaries to match the actual crowd dispersion patterns for different events (e.g., concerts vs. sports matches) and locations (e.g., stadium vs. open square). This dynamic adaptation maintains operational simplicity through automated adjustment while significantly improving measurement precision by aligning the AoI with actual crowd boundaries.
Solution Approach 2:
The patent changes the AoI radius parameter dynamically based on multiple factors including historical crowd density data, event type classification, and geographic location features. The system automatically adjusts the radius to optimize the inclusion of actual attendees while excluding non-attendees, transforming the static AoI definition into a flexible, context-aware parameter that adapts to different counting scenarios without requiring manual reconfiguration.
3Measurement precision
If individual user connection data is collected to improve counting accuracy, then measurement precision improves, but loss of information increases due to privacy concerns and data protection requirements
Solution Approach 1:
The patent extracts only the essential anonymized metrics needed for crowd counting from individual user connection data. Instead of collecting and storing detailed user information, the system extracts aggregate statistics such as total connection duration, number of unique users, and connection frequency at the cell level. This extraction approach maintains measurement precision by capturing sufficient statistical information while eliminating privacy-sensitive data, thus preventing information loss related to user identities and personal behaviors.
Data Source
Figure 1
Figure 2A~2E
Figure 3A~3B
AI summary
A method of estimating a number of persons gathering at an Area of Interest (107) during a time interval on a day, wherein said Area of Interest (107) is defined by an Area of Interest center and an Area of Interest radius and is covered by a mobile telecommunication network (105) having a plurality of communication stations (105a) each of which adapted to manage communications of user equipment in one or more served areas (105b) in a covered geographic region (300; 300') over which the mobile telecommunication network (105) extends, the method comprising the steps of: a) subdividing the covered geographic region (300; 300') in a plurality of surface elements (205); b) defining (604) a plurality of calculated radius values of the Area of interest radius, and, for each calculated radius value: c) identifying (606) a number of relevant surface elements (505a-d) of the covered geographic region (300; 300') comprised within the Area of interest; d) computing (610; 612) a first number of User Equipment served by the mobile communication network (105)during the time interval on the day within the Area of Interest (107) based on aggregated data regarding a usage of the mobile communication network (105); e) computing (614; 616) a second number of User Equipment served by the mobile communication network (105) during the time interval for each day of a predetermined number of previous days preceding the day within the Area of Interest (107) based on the aggregated data regarding the usage of the mobile communication network (105); f) combining (618, 620) the first number of User Equipment and the second numbers of User Equipment for obtaining a statistical quantity; g) computing a normalized statistical quantity by normalizing (622) the statistical quantity with respect to the radii of the relevant served areas (505a-d); h) computing (630) an optimum radius value of the Area of Interest radius as the average of the calculated radius values weighted by the normalized statistical quantity; i) estimating (632-646) a number of persons gathering within the Area of Interest (107) having the Area of Interest radius equal to the optimum radius value. In one embodiment of the invention, the aggregated data regarding a usage of the mobile communication network (105) comprise a number of served User Equipment traffic load, number of voice calls, number of SMS transmitted and/or volume of binary data exchanged within preferably each one of the communication stations (105a) of the mobile communication network (105).