Undesirable Call Recognition Using Probabilistic Hash Analysis
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for recognizing undesirable calls on remote devices lack accuracy and compromise user data security, particularly when analyzing personal data for spam detection and software provision.
Innovation Solution
A system and method that generates probabilistic hashes from unique call identifiers on a secure device, applies frequency analysis to identify suspicious calls, and requests additional data only when necessary to enhance recognition accuracy while ensuring data security.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If personal data is transmitted to remote devices for analysis, then recognition accuracy improves, but data security deteriorates
Solution Approach 1:
The patent introduces hash values as an intermediary representation of personal data. Instead of transmitting raw personal data (phone numbers, emails) to remote devices, the system transmits hash values which are cryptographic transformations that preserve the ability to identify and analyze call patterns while preventing direct access to the original personal information. This intermediary mechanism resolves the contradiction by enabling accurate recognition analysis without compromising data security.
Solution Approach 2:
The patent creates a copy of the personal data in the form of hash values that can be transmitted and analyzed remotely. The hash values serve as a surrogate representation that maintains the functional properties needed for recognition accuracy (identifying repeated calls from the same source) while being inherently more secure for transmission. This copying approach allows the original personal data to remain secure on the user device while enabling remote analysis.
2Measurement precision
If all call data is transmitted for analysis, then recognition accuracy improves, but data transmission volume increases
Solution Approach 1:
The patent extracts only the essential identifying features of calls (hash values of phone numbers, emails, or other identifiers) and transmits them for analysis, rather than transmitting complete call data including personal information, call recordings, and metadata. This extraction approach maintains recognition accuracy by preserving the key identifying characteristics while dramatically reducing the volume of data that needs to be transmitted over the network.
3Reliability
If complete personal data is analyzed locally, then data security improves, but recognition accuracy deteriorates
Solution Approach 1:
The patent uses hash values as an intermediary that enables secure local processing while still allowing for enhanced remote analysis when needed. The system can perform initial analysis locally using hash values to maintain security, and selectively transmit additional information to remote devices for improved accuracy when the local analysis is insufficient, thus resolving the contradiction between local security and remote accuracy.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed herein are systems and methods for recognizing undesirable calls on a remote device. In one example, an exemplary method comprises, generating, for each call, a call identifier from a probabilistic hash received from a secure device, the probabilistic hash having been computed by the secure device based on a unique call identifier associated with call data collected for the call; analyzing the generated call identifiers to identify at least one of the generated call identifiers as a suspicious call identifier; requesting data, from the secure device associated with the suspicious call identifiers, where the requested data includes at least information about the call associated with the suspicious call identifier; and analyzing data received in response to the request and recognizing suspicious call identifier and the call associated with the suspicious call identifier as undesirable based on the analysis of the data received in response to the request.