Voice Characteristic Analysis for Fraud Detection Without Caller ID
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current fraud detection methods in call-based advertising rely heavily on caller ID, which can be easily circumvented by fraudsters using temporary phone numbers or fake IDs, necessitating a more robust solution that does not depend on caller ID.
Innovation Solution
A system and method that analyzes voice characteristics, such as mel-frequency cepstrum coefficients, using statistical processing techniques like Bayesian models or machine learning to identify distributions indicative of fraudulent activity, allowing for the detection of fraudulent calls without relying on caller ID, transcription, or recordings.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If caller ID is used for fraud detection, then detection accuracy is improved, but the system becomes vulnerable to temporary phone numbers and fake IDs
Solution Approach 1:
The patent extracts the fraud detection dependency from caller ID and relocates it to voice characteristics. By analyzing acoustic features such as pitch, tone, and speech patterns, the system identifies fraudulent calls based on the actual voice content rather than the displayed phone number, thereby eliminating the harmful factor of caller ID circumvention while maintaining detection reliability
Solution Approach 2:
The patent introduces voice characteristics as an intermediary between the caller and the detection system. Instead of directly relying on the caller ID display, the system uses voice analysis as a mediator to verify the caller's identity and detect fraud, creating a more secure detection mechanism that is not easily circumvented
2Reliability
If voice characteristic analysis is implemented, then fraud detection robustness is improved, but system complexity increases
Solution Approach 1:
The patent replaces complex mechanical verification systems with acoustic analysis. Instead of relying on multiple layers of manual verification or complex identity validation mechanisms, the system uses voice recognition technology to directly identify fraudulent calls, simplifying the overall system architecture while enhancing robustness
Solution Approach 2:
The patent transforms the detection approach by changing the analysis parameters from caller ID metadata to acoustic characteristics. By measuring voice-related parameters such as frequency, amplitude, and speech patterns, the system achieves more robust fraud detection with manageable complexity, as these acoustic parameters provide direct insight into the caller's identity
Data Source
AI summary
A system and method for monitoring telephone calls to detect fraudulent activity and take corrective action is described. The system receives a first group of telephone calls having associated voice characteristics and analyzes the first group of telephone calls to identify and store a first set of distributions of voice characteristics that are indicative of normal activity, fraudulent activity, or indeterminate activity. The system receives a second group of telephone calls to be analyzed. The system analyzes the second group of telephone calls to identify a second set of distributions of voice characteristics associated with the second group of telephone calls. The system then compares the second set of distributions of voice characteristics to the stored first set of distributions of voice characteristics to assess a probability that one or more telephone calls in the second group of telephone calls represents normal, fraudulent, or indeterminate activity. If the assessed probability of fraudulent activity exceeds a threshold, the system takes appropriate corrective action, such a flagging the fraudulent call or withholding a financial incentive associated with the fraudulent call.