Voice Analysis Call Filtering System
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current telephone call filtering systems are inadequate in preventing unwanted calls, as they rely primarily on calling party identification and do not provide sufficient security against anonymous or spoofed numbers, leading to issues with false positives and intrusiveness.
Innovation Solution
A process that filters unwanted calls by combining analysis of the calling party number with voice analysis, allowing for immediate blocking of suspicious calls without ringing the recipient's phone, and uses semantic analysis to determine the call's legitimacy, with optional biometric authentication.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If voice analysis is added to calling party number analysis, then call filtering reliability is improved, but device complexity increases
Solution Approach 1:
The filtering system is divided into multiple independent modules: a calling party number analysis module that evaluates the number itself, and a voice analysis module that processes the caller's voice. These modules operate separately but their results are combined to make the final filtering decision, allowing each module to be optimized independently while maintaining overall system reliability.
Solution Approach 2:
The patent introduces an intermediary filtering system that acts as a mediator between the incoming call and the recipient's device. This intermediary analyzes both the calling party number and voice characteristics, then decides whether to allow, block, or request additional verification before connecting the call, thereby improving reliability without requiring changes to the recipient's device.
2Reliability
If strict filtering rules are applied, then unwanted call blocking is improved, but false positives increase
Solution Approach 1:
The system dynamically adjusts filtering parameters based on multiple characteristics including calling party number patterns, voice biometric features, time of day, and call frequency. By changing and weighing multiple parameters rather than relying on a single strict rule, the system achieves better unwanted call blocking while reducing false positives through more nuanced decision-making.
Solution Approach 2:
Instead of applying a single binary filter decision, the system performs partial analysis by first evaluating the calling party number, then selectively applying voice analysis based on the initial assessment. This staged approach allows the system to apply stricter filtering only when necessary, reducing unnecessary false positives while maintaining effective blocking of unwanted calls.
3Reliability
If authentication requirements are increased, then call security is improved, but ease of operation deteriorates
Solution Approach 1:
The voice biometric authentication system operates automatically without requiring user intervention. The system extracts voice characteristics during the call setup phase and performs authentication autonomously, eliminating the need for users to manually verify caller identity or input authentication codes, thereby maintaining ease of operation while improving security.
Solution Approach 2:
The system performs voice biometric authentication in advance during the call setup phase, before the call is connected to the recipient. By conducting security verification preliminarily and automatically, the system ensures call security without requiring the recipient to take any action during the actual call, thus maintaining ease of operation.
Data Source
AI summary
Method of filtering undesirable incoming telephone calls, in which a decision to block a call or to transmit it is based both on the caller's number and on analysis of the caller's voice.