Real-Time Scam Call Screening With Adaptive Call Metrics

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Existing call management systems on mobile devices lack effective tools to identify scam or spam calls in real-time, relying heavily on caller numbers which can be spoofed or unreliable, leading to increased annoyance and potential financial loss.

Innovation Solution

A call management system that utilizes machine learning and real-time analysis of call data, including call routing and session parameters, to assign scam scores and block or manage calls based on composite scores derived from multiple models, dynamically adapting to evolving scammer tactics.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If traditional call management systems rely on caller numbers for identification, then the system simplicity is maintained, but the reliability of scam call detection deteriorates due to number spoofing

Engineering Contradiction:

Improvescam call detection reliabilityVSAvoidcall management system complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

The system transitions from relying solely on caller number parameters to analyzing multiple call parameters including call routing information, session parameters, and behavioral patterns. This parameter expansion enables more reliable scam detection by evaluating the complexity of call characteristics rather than depending on a single spoofable identifier.

Inventive Principle:

Principle #35Parameter changes

Solution Approach 2:

The patent introduces an intermediary call management server that acts as a mediator between the calling and called parties. This server performs complex analysis of call parameters and routing information, then provides scam likelihood assessments to mobile devices. The intermediary handles the computational complexity centrally while keeping individual user devices relatively simple.

Inventive Principle:

Principle #24Intermediary (Mediator)

2Measurement precision

If real-time analysis of multiple call parameters is performed, then the precision of scam identification is improved, but the processing time and system complexity increase

Engineering Contradiction:

Improvescam call identification precisionVSAvoidcall processing time

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary analysis of call parameters as soon as call data becomes available, before the call is fully established. By initiating scam likelihood assessment early in the call setup process using available routing and session parameters, the system reduces the time penalty of comprehensive analysis while maintaining high identification precision.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The call analysis process is segmented into multiple stages: initial parameter extraction, intermediate scam likelihood assessment, and final determination. This segmentation allows the system to provide preliminary scam assessments based on available parameters while continuing to gather additional data, thereby reducing perceived processing time without sacrificing final identification precision.

Inventive Principle:

Principle #1Segmentation

3Object-affected harmful factors

If aggressive call blocking based on scam scores is implemented, then the protection against scam calls is improved, but the risk of blocking legitimate calls increases

Engineering Contradiction:

Improvescam call harm reductionVSAvoidlegitimate call delivery reliability

Core Design Contradiction:

Object-affected harmful factorsVSReliability

Solution Approach 1:

Instead of implementing aggressive blocking based on single threshold scores, the system applies partial action by providing scam likelihood assessments that enable user discretion. The call management server calculates scam scores but allows users to make informed decisions about whether to block or answer calls, thereby reducing false positives while still protecting against obvious scams through user awareness.

Inventive Principle:

Principle #16Partial or excessive action

Solution Approach 2:

The system incorporates feedback mechanisms where user responses to scam assessments are collected and used to refine future scam likelihood calculations. This feedback loop allows the system to learn from actual user decisions, adjusting its scoring algorithms to better distinguish between scam and legitimate calls, thereby reducing the risk of blocking valid calls while maintaining protection against scams.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS12457293B1Call screening service for communication devices

Publication Date: 2025.10.28 FIRST ORION CORP

AI summary

One example method of operation may include collecting call metric data over a predefined period of time for identified calls, querying the call metric data to identify whether one or more call filtering criteria parameters require changes, determining one or more call filtering criteria parameters require changes based on a deviation from one or more expected call metric data values included in the call metric data, modifying one or more of the call filtering criteria parameters, and updating an active call scam model stored on a call processing server based on the one or more call filtering parameters.