Cloud-Based Scam Detection for Voice Calls
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current telecommunication networks face challenges in accurately identifying and alerting users to potential harmful or dislike numbers, as existing scam detection logic can be evaded by robocallers who manipulate call originator information, making it difficult for end users to determine whether incoming calls are from harmful or undesirable sources.
Innovation Solution
A machine learning model trained on voice call data is implemented to classify incoming calls as potential harmful or dislike numbers by analyzing metrics such as call duration, rejection rates, and caller ID patterns, and presenting specific strings on user interfaces to assist users in decision-making, while also considering personal data and user feedback to enhance accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional authentication logic based on IMS attributes is used, then the system is simple to implement, but it can be easily evaded by robocallers manipulating call originator information
Solution Approach 1:
The patent introduces cloud-based services as an intermediary between the telephony network and end users. The cloud service receives call session information from TAS, performs sophisticated analysis using multiple data sources including call detail records, device information, and user feedback, then returns scam probability assessments to the end user device without requiring complex local implementation
Solution Approach 2:
The patent moves the detection logic from the traditional telephony network dimension to a cloud-based dimension. By leveraging cloud computing resources and multiple data dimensions (call patterns, device characteristics, user feedback), the system achieves higher detection accuracy while keeping the endpoint implementation simple
2Measurement precision
If cloud-based machine learning analysis is implemented, then detection accuracy is improved, but data processing time and computational resources increase
Solution Approach 1:
The system performs preliminary analysis by pre-computing scam probability assessments for phone numbers before actual calls occur. Call detail records and device information are analyzed in advance, and results are cached in the cloud. When a call is made, the pre-computed results are quickly retrieved and presented to the user, significantly reducing real-time processing delays
Solution Approach 2:
The system leverages existing data sources that are already available in the telecommunication network, such as call detail records and device information from the IMS. By reusing this existing data infrastructure, the system avoids the need for separate data collection processes and reduces overall processing time
Data Source
AI summary
Methods and systems for improving the detection and alert logic by cloud data for a potential harmful or dislike number are described herein. According to an implementation, a computer server, e.g., a telephony application server (TAS), may receive a voice call associated with a phone number to a user. The TAS may determine that the phone number is associated with a category of a potential harmful number or a potential dislike number. The TAS may generate a string indicative of the category and present the string on a user interface of the user device. The TAS may apply a machine learning model to classify an incoming call. The machine learning model may be trained based on one or more voice data metrics such as call duration, call rejection rate, etc. The training may be further supplemented by personal data on the user device to provide accurate classification.