Robocall Detection via Burst Thresholds on New Numbers
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current strategies for identifying and mitigating unauthorized robocalls are ineffective, as they can be easily circumvented by robocallers, often require user intervention, and may compromise personal data privacy.
Innovation Solution
A method involving a provider-maintained list of newly assigned phone numbers, where numbers exceeding call thresholds are flagged and suspended, without requiring user action or analysis of call content, using automated detection models and pruning rules to manage the list and differentiate robocallers from legitimate users.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If automated detection models and pruning rules are used to manage the list of newly assigned phone numbers, then the accuracy of identifying robocallers is improved, but the device complexity increases
Solution Approach 1:
The system segments the phone number monitoring process into distinct phases: maintaining a list of newly assigned numbers, applying pruning rules to reduce the list, and using detection models to identify robocallers. This segmentation allows each component to be optimized independently, improving accuracy without proportionally increasing overall complexity.
Solution Approach 2:
The system performs preliminary actions by maintaining and pruning a list of newly assigned phone numbers before actual robocall detection begins. This preliminary filtering reduces the volume of numbers requiring detailed analysis, thereby improving detection accuracy while limiting the complexity growth of the overall system.
2Productivity
If provider-level data is leveraged for automated detection, then the productivity of robocaller identification is improved, but the loss of information privacy increases
Solution Approach 1:
The system extracts only the essential information needed for detection (call volume, call patterns, number assignment data) from provider-level data, while deliberately excluding sensitive personal information. This extraction approach enables high-productivity automated detection while minimizing privacy loss by taking out only what is necessary for the detection function.
Solution Approach 2:
The provider acts as an intermediary that enables detection without direct user involvement. Users provide data to their provider, and the provider's automated system performs detection using aggregated provider-level data. This intermediary structure improves productivity through automated processing while protecting user privacy by eliminating the need for users to directly share sensitive information with detection systems.
3Reliability
If call thresholds are monitored and exceeded numbers are flagged, then the reliability of robocaller detection is improved, but the loss of time for processing increases
Solution Approach 1:
The system applies partial monitoring by focusing only on newly assigned phone numbers and applying detection only when call thresholds are exceeded. This partial action approach improves reliability by concentrating resources on high-risk cases while reducing overall processing time by not continuously analyzing all phone numbers at full detail.
Solution Approach 2:
The system uses periodic threshold-based monitoring instead of continuous analysis. Call data is processed in intervals, with detection triggered only when predefined thresholds are exceeded. This periodic action maintains reliable detection for suspicious patterns while significantly reducing the time lost to processing normal, low-risk call volumes.
Data Source
AI summary
Described are techniques including a computer-implemented method of maintaining a list of newly assigned phone numbers. The method further comprises intermittently removing phone numbers from the list of newly assigned phone numbers. The method further comprises determining that a newly assigned phone number initiates a number of calls per unit time that exceeds a threshold number of calls per unit time. The method further comprises automatically flagging the newly assigned phone number as a possible robocaller.