Analytics Server for Call Fraud Analysis and ANI Privacy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional approaches to evaluating and authenticating calls in telecommunications systems that require privacy preservation of caller ANI (Automatic Number Identification) face challenges in accurately assessing call risks without exposing the ANI to destination systems, as they rely on caller ANI for authentication and risk evaluation.
Innovation Solution
An analytics server is positioned between the caller and the destination provider system within telecommunications networks, receiving call data from terminating carriers, extracting caller ANI, and applying machine-learning architectures to generate risk scores while redacting the ANI from the destination system, using portability data from third-party databases to assess call risks without revealing the ANI.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If conventional approaches use caller ANI for authentication and risk evaluation, then authentication accuracy is improved, but caller privacy is compromised
Solution Approach 1:
The patent introduces an analytics server as an intermediary component positioned between the telephony network and the destination system. This server receives call data containing the caller ANI, performs risk assessment using machine learning models, and returns risk scores without exposing the actual ANI to the destination system. The intermediary preserves caller privacy while enabling accurate risk evaluation through its mediating position in the architecture.
Solution Approach 2:
The patent extracts the sensitive caller ANI information from the data stream before it reaches the destination system. The analytics server retrieves the ANI from call data, uses it for risk assessment processing, and then removes it from the data that is forwarded to the destination. This extraction approach allows the system to utilize the ANI for authentication purposes while preventing its exposure to systems that do not require it.
2Loss of information
If caller ANI is redacted to preserve privacy, then caller privacy is improved, but risk assessment capability deteriorates
Solution Approach 1:
The patent performs risk assessment actions before the call is routed to the destination system. The analytics server receives call data, extracts the caller ANI, and executes machine learning-based risk assessment in advance. The risk scores are generated and returned to the destination system without the actual ANI being exposed. This preliminary action ensures that risk assessment capability is maintained while privacy is protected from the outset.
Solution Approach 2:
The analytics server acts as a mediator that enables risk assessment without direct ANI exposure to the destination system. It receives the ANI from the telephony network, processes it through machine learning models to generate risk scores, and returns only the scores without the ANI. This intermediary approach resolves the contradiction by allowing risk assessment to occur while preventing ANI leakage to systems that don't need it.
3Loss of information
If analytics server is positioned between caller and destination system, then caller privacy is improved, but system complexity increases
Solution Approach 1:
The analytics server is designed to perform multiple functions within a single component: it receives call data from the telephony network, extracts caller ANI, executes machine learning risk assessment models, generates risk scores, and returns results to the destination system. By consolidating these diverse functions into one multi-functional server, the patent reduces the need for multiple separate systems, thereby managing complexity while achieving privacy protection.
Solution Approach 2:
The analytics server serves as a single intermediary point that handles all privacy-related operations. Rather than distributing privacy protection logic across multiple systems or components, the patent centralizes it in one server that mediates between the telephony network and destination systems. This centralized intermediary approach simplifies the overall architecture compared to distributed privacy protection mechanisms.
Data Source
AI summary
Disclosed are systems and methods including processes executed by a server that executes software routines for machine-learning architectures that receive call-invite messages containing data from a terminating carrier. The server a caller ANI and types of call data. The server further requests data from a telephony database. The server applies and executes the software programming of the machine-learning architecture on the call data (from the terminating carrier) and the portability data (from the telephony database) to generate risk scores. The server stores the data and the risk scores into a request database, until a provider server requests the risk scores in a threat assessment request. The server returns a threat assessment message to the provider server in response to the threat assessment request. The threat assessment message includes information about the caller or caller device, and the risk scores, but not the caller ANI.