Scam Call Detection Using Signalling Data and Risk Profiles
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing phone fraud schemes, such as 'ping calls' and premium rate Value-Added Service (VAS) number scams, result in significant costs for both telephone operators and subscribers, and existing fraud detection methods are inefficient, complex, and disruptive to legitimate users.
Innovation Solution
A method and system for detecting fraudulent phone calls by collecting network signalling data, using detection algorithms to identify suspicious calls, comparing them against a certification database, and defining risk profiles for targeted fraud prevention.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If complex fraud detection methods are implemented, then fraud detection capability is improved, but system complexity and disruption to legitimate users increases
Solution Approach 1:
The fraud detection system is segmented into multiple independent components: a signalling data collection module that gathers call data, a detection algorithm module that analyzes patterns, and a certification database module that stores verified fraudulent numbers. This segmentation allows each component to be optimized independently while reducing overall system complexity and making the system easier to deploy and maintain.
Solution Approach 2:
The patent introduces an intermediary certification database that acts as a mediator between the detection algorithms and the fraud prevention actions. This database stores pre-certified fraudulent target numbers and serves as a reference point, allowing the system to make accurate fraud determinations without requiring complex real-time analysis of every call pattern, thereby reducing system complexity while maintaining high detection reliability.
2Object-generated harmful factors
If aggressive fraud prevention measures are taken, then fraud loss is reduced, but impact on legitimate users increases
Solution Approach 1:
The system applies local quality by implementing targeted fraud prevention measures specifically for calls involving certified fraudulent target numbers, rather than applying blanket restrictions to all outgoing calls. The detection algorithm and certification database work together to identify only those calls that pose actual fraud risk, allowing legitimate calls to proceed uninterrupted while blocking only the fraudulent ones, thus reducing fraud loss without impacting legitimate users.
3Measurement precision
If comprehensive fraud detection is implemented, then detection accuracy is improved, but deployment difficulty increases
Solution Approach 1:
The system employs preliminary action by pre-certifying fraudulent target numbers and storing them in the certification database before they are needed for detection. The detection algorithm is pre-configured with certification criteria and can immediately compare incoming call data against the pre-populated database. This preliminary preparation ensures high detection accuracy while simplifying deployment, as the system does not require complex real-time certification logic to be implemented during deployment.
Data Source
AI summary
The invention relates to a method for controlling scams in which a phone call requests a return call to a target number, comprising the following steps:collecting signalling data of phone calls made via a telephone network (2);detecting suspicious calls from signalling data collected and using a detection algorithm, and for each suspicious call detected, identifying a suspicious number;comparing the suspicious number with a number and/or at least one range of certified target numbers contained in a certification database, and defining a risk profile for the suspicious number accordingly.Methods and systems for controlling phone scams.