Remote Mobile Device Type Determination Using Multi-Input Data
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current methods for remote mobile device identification often rely on a single type of data set, which can be inaccurate due to spoofing and varying traffic patterns, and struggle with new device types and obsolescence, leading to inconsistencies and security risks.
Innovation Solution
A method and system that utilize multiple types of data sets from a radio access network and packet core, processed through a machine learning model to determine device type, including control, traffic, and application data, enhancing accuracy and consistency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Device complexity
If a single type of data set is used for device identification, then the system complexity is reduced, but the identification accuracy deteriorates due to spoofing and varying traffic patterns
Solution Approach 1:
The patent combines multiple data sets including device identifiers, traffic information, control information, and application data into a unified analysis framework. This merging of diverse data sources enables more accurate device type determination by cross-validating information across different data types, thereby resolving the contradiction between system simplicity and identification accuracy.
2Measurement precision
If multiple types of data sets are processed, then the identification accuracy is improved, but the data processing complexity increases
Solution Approach 1:
The patent segments the processing of multiple data sets by assigning specific processing logic to each data type (device identifiers, traffic information, control information, application data). This segmentation allows the system to handle complex multi-data processing through modular, organized routines, reducing the perceived complexity while maintaining high identification accuracy.
Solution Approach 2:
The patent introduces an intermediary processing layer that collects, normalizes, and integrates data from multiple sources before final analysis. This intermediary structure manages the complexity of processing multiple data types by providing a standardized interface between diverse data sources and the decision-making logic.
3Ease of manufacture
If traditional identification methods are used, then the implementation is simpler, but the reliability deteriorates due to spoofing and device obsolescence
Solution Approach 1:
The patent creates a composite identification approach that combines multiple data types (device identifiers, traffic patterns, control information, application data) into a unified device type determination system. This composite methodology enhances reliability by not depending on a single data source that can be spoofed or become obsolete, while maintaining implementation feasibility through structured processing routines.
4Device complexity
If device identifiers are used alone, then the processing is simpler, but the security deteriorates due to spoofing risks
Solution Approach 1:
The patent implements preliminary anti-action by cross-validating device identifiers with multiple other data types (traffic information, control information, application data) before making identification decisions. This preliminary verification process prevents spoofing attacks by detecting inconsistencies across different data sources, thereby enhancing security without significantly increasing processing complexity.
Data Source
AI summary
Methods and systems for determining the type of a remote mobile device by combining multiple types of data sets. The system collects various types of data sets, such as data sets associated with identity information, traffic patterns, control signaling, and application data associated with a remote mobile device from a radio access network and a packet core. This data is processed using a machine learning model, or using other processing techniques, to generate an output data set, which is used to determine the device type. The determination is more accurate and consistent than using only one type of data set. The system can be implemented in various environments, including local servers, cloud-based servers, hybrid servers, and distributed servers. The service can be provided to clients as a cloud service, where clients provide a mobile number, and the service provider handles the data collection, processing, and device type determination.