Subscriber Data Protection via Multi-Stage Call Analysis

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current systems fail to effectively detect and protect subscriber data from unwanted calls, leading to high false positive and false negative errors, and inadequate protection against sophisticated fraudulent schemes.

Innovation Solution

A method involving a detection module that intercepts network traffic, analyzes call parameters and stream data using techniques like speech recognition, image recognition, and machine learning to identify unwanted calls, and tags subscribers to protect sensitive information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional fraud detection methods are used, then the system is simple to operate, but the detection precision is low leading to high false positive and false negative errors

Engineering Contradiction:
Improvedetection precisionVSAvoidsystem complexity
Core Design Contradiction:
Measurement precisionVSDevice complexity

Solution Approach 1:

The fraud detection system is segmented into multiple independent modules: a detection module that intercepts network traffic and analyzes call parameters, a stream data analysis module that processes call stream data using speech and image recognition, and a data protection module that tags subscriber data. Each module performs a specific function, allowing the system to achieve high detection precision through specialized analysis while maintaining manageable complexity through modular architecture.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The system transitions from analyzing only traditional call parameters to a multi-dimensional approach that includes both call parameters and call stream data (audio, video, images). This dimensional expansion allows the detection system to examine fraudulent calls from multiple angles simultaneously, significantly improving detection precision by capturing subtle indicators that single-dimensional analysis would miss.

Inventive Principle:
Principle #17Another dimension (Dimensionality change)

2Measurement precision

If comprehensive analysis of call parameters and stream data is performed, then the detection accuracy improves, but the processing time increases

Engineering Contradiction:
Improvedetection accuracyVSAvoidprocessing time
Core Design Contradiction:
Measurement precisionVSLoss of time

Solution Approach 1:

The detection module performs preliminary analysis of call parameters immediately upon intercepting network traffic, before the call stream data is fully transmitted. This preliminary assessment allows the system to identify obvious fraudulent patterns early and apply more intensive stream data analysis only when necessary, thereby improving detection accuracy while minimizing overall processing time for clearly fraudulent or clearly legitimate calls.

Inventive Principle:
Principle #10Preliminary action

Solution Approach 2:

The system implements feedback mechanisms where the results from call parameter analysis inform the subsequent stream data analysis. If the initial parameter analysis indicates low suspicion, the system can reduce the intensity of stream data processing. Conversely, if parameters suggest potential fraud, the system intensifies stream data analysis. This feedback-driven adaptive processing improves detection accuracy while optimizing processing time based on actual risk levels.

Inventive Principle:
Principle #23Feedback

3Reliability

If subscriber data is protected through tagging and identification, then the security level improves, but the system complexity increases

Engineering Contradiction:
Improvesecurity levelVSAvoidsystem complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The system introduces tags as intermediary markers that link detection results to subscriber data without requiring direct integration between the detection module and data storage systems. These tags serve as a simple yet effective mechanism to identify and protect subscriber data associated with fraudulent calls, improving security while avoiding the complexity of deep system integration. The tags act as a lightweight bridge between detection and protection functions.

Inventive Principle:
Principle #24Intermediary (Mediator)

Data Source

PatentEP4145764A1System and method for protecting subscriber data in the event of unwanted calls
Publication Date: 2023.03.08 AO KASPERSKY LAB
  • EP4145764A1 patent drawingFigure 1
  • EP4145764A1 patent drawingFigure 2
  • EP4145764A1 patent drawingFigure 3

AI summary

A method for protecting subscriber data includes intercepting network traffic associated with a call. The network traffic includes call parameters and call stream data. A first set of the call parameters is analyzed. A first probability value of the call being declared as unwanted is determined. The call stream data is analyzed to define a second set of call parameters. The first set of call parameters is reanalyzed based on the second set. A second probability value of the call being declared as unwanted is determined. A determination is made if the second probability value exceeds a second threshold value. The call is declared as unwanted, in response to determining that the second probability value exceeds the second threshold. The first and second sets of call parameters are transmitted to an application configured to protect data of a protected subscriber.