Robocall Detection via Multi-Stage Verification and Cloud Databases
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current call blocking applications are ineffective in distinguishing between legitimate and illegitimate calls, often blocking desired calls due to reliance on prediction methods, geographic location, and manual blacklisting, while failing to address call spoofing and neighbor spoofing effectively.
Innovation Solution
A method and system that checks caller identification information through multiple tests, including a selection input requirement, and utilizes cloud-based databases to identify and block recorded robocalls, preventing call spoofing and neighbor spoofing by automatically designating suspicious calls to voicemail.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If call blocking applications use prediction methods derived from call data collected from consumers, then they can identify potential robocalls, but they block legitimate calls the consumer desires to actually receive
Solution Approach 1:
The system segments the call filtering process into multiple distinct stages: initial prediction filtering, human response verification, and final routing decision. This multi-stage segmentation allows the system to catch robocalls early while providing opportunities to rescue legitimate calls that were incorrectly flagged, thereby resolving the contradiction between detection accuracy and reliable delivery of legitimate calls
Solution Approach 2:
The system introduces an intermediary human response mechanism between the prediction algorithm and the final call blocking action. By requiring human verification through response codes before definitively blocking a call, the system creates a buffer that prevents premature blocking of legitimate calls while maintaining the ability to filter robocalls effectively
2Measurement precision
If call blocking applications block calls based on geographic location or area code, then they can filter potential robocalls, but they block legitimate calls the consumer desires to actually receive
Solution Approach 1:
The system dynamically adjusts call routing decisions based on real-time human verification responses rather than relying on static geographic or area code-based rules. This dynamic approach allows the system to adapt to each specific call situation, maintaining high filtering accuracy while preserving the ability to accept legitimate calls from any geographic location based on human verification
3Reliability
If call blocking applications require consumer to manually create blacklists of robocall numbers, then they can block known robocalls, but they place a big burden on the consumer and create confusion
Solution Approach 1:
The system implements self-service by automatically learning and adapting to consumer preferences through the verification response codes provided during calls. Rather than requiring consumers to manually maintain blacklists, the system autonomously builds and updates its filtering rules based on consumer feedback, thereby maintaining reliable robocall blocking while eliminating the burden of manual blacklist management
Solution Approach 2:
The system incorporates continuous feedback loops where consumer responses to verification messages are automatically processed to refine filtering algorithms. This feedback mechanism allows the system to improve its robocall detection accuracy over time without requiring active consumer participation in blacklist maintenance, resolving the contradiction between reliable blocking and ease of operation
4Measurement precision
If call blocking applications use multiple cloud-based databases and tests, then they can improve robocall detection accuracy, but they increase system complexity
Solution Approach 1:
The system employs a universal verification message framework that can be applied across multiple cloud-based databases and testing stages. This multi-functional approach allows the same basic verification mechanism to serve multiple purposes: identifying robocalls, verifying legitimate calls, and building consumer preference profiles, thereby improving detection accuracy while managing system complexity through standardized reusable components
Data Source
AI summary
A method and system for automatically blocking recorded robocalls. Caller identification information from an incoming is checked with plural different tests and with one test that requires a caller input a selection input. Requiring a response from such a selection input provides an additional level of detection for recorded robocalls. In addition, plural different cloud based databases of known robocall numbers are checked with plural different tests with cloud based Software as a Service (SaaS) applications to provide other levels of detection for recorded robocalls. The method and system automatically identify and process recorded robocalls and help prevent call spoofing and neighbor spoofing by recorded robocalls.