Real-Time Scam Call Filtering via Dynamic Weight Adjustment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current call validation methods for identifying scam calls are cumbersome and not fast enough to support real-time scam call management, often requiring multiple operations and failing to maintain timely validation.
Innovation Solution
A method that involves identifying call parameters, assigning scores to calls based on these parameters, categorizing calls as potential scams, and adjusting call parameter weights based on deviations in call percentages to optimize scam call filtering.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If current call validation methods are used to identify scam calls, then call filtering is performed, but the process is cumbersome and not fast enough for real-time management
Solution Approach 1:
The system performs preliminary actions by pre-establishing call parameter weights and scoring thresholds before actual call validation occurs. Call parameters are pre-configured with weights based on their scam-indicative value, and scoring thresholds are predetermined to enable rapid real-time classification without complex calculations during the validation moment
Solution Approach 2:
The validation process is segmented into distinct operational phases: call parameter identification, scoring based on weighted parameters, threshold comparison, and classification. This segmentation allows each phase to be optimized independently and executed efficiently in sequence, reducing overall process complexity and improving speed
2Measurement precision
If multiple operations are performed to validate calls, then call categorization is achieved, but the process becomes burdensome and slow
Solution Approach 1:
The system incorporates feedback mechanisms where call classification results and outcomes are fed back into the parameter weight adjustment process. This allows the system to learn from actual call patterns and refine parameter weights dynamically, improving categorization accuracy over time without adding operational steps to individual call validations
Solution Approach 2:
The system dynamically adjusts call parameter weights based on observed call patterns and scam trends. By changing the parameters (weights) rather than the validation process itself, the system maintains fast validation speed while continuously improving categorization accuracy through adaptive parameter optimization
3Reliability
If call parameter weights are dynamically adjusted, then filtering accuracy is improved, but system complexity increases
Solution Approach 1:
The system performs self-service by automatically adjusting call parameter weights based on observed call patterns and classification outcomes. The weight adjustment mechanism operates autonomously without requiring manual intervention or complex external control systems, thereby improving reliability while maintaining relatively simple system architecture
Data Source
AI summary
One example method of operation may include determining a call received from a calling party and intended for a subscriber device has an elevated likelihood of being a scam call, determining a percentage of calls over a current period of time being filtered as scam calls by a carrier server, when the percentage of calls being filtered as scam calls during the current period of time is above a call threshold percentage, retrieving call history information associated with a subscriber profile of the subscriber device, identifying one or more call patterns from the call history information of the subscriber profile corresponding to the received call, and determining whether to permit the received call based on the identified one or more call patterns.