Network Signal Algorithm Selection for Mobile App Usage Profiling
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing techniques for application usage profiling, particularly in 5G networks, face challenges such as insufficient coverage, sample bias, and computational costs, making it difficult to accurately detect and predict application usage across diverse devices and applications.
Innovation Solution
A system that selects the best predictive algorithm from a variety of algorithms based on network signals, specifically Server Name Indication (SNI) signals, to accurately predict application usage, using machine learning models trained on network signals, and dynamically updates these algorithms to adapt to changes in application behavior.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If deep packet inspection is used to detect application packets, then measurement precision is improved, but use of energy increases due to computational cost
Solution Approach 1:
The patent extracts only the essential identifying features from network packets (source/destination IPs, ports, protocols) rather than performing full deep packet inspection. This selective extraction maintains application identification accuracy while dramatically reducing computational energy consumption by avoiding analysis of encrypted payload data.
Solution Approach 2:
Instead of analyzing packet contents to identify applications (traditional DPI approach), the patent inverts the approach by using network flow characteristics and metadata patterns to infer application usage. This reversal enables accurate application detection without the high computational cost of traditional deep packet inspection.
2Reliability
If traditional application profiling techniques are used, then device complexity is reduced, but reliability decreases due to insufficient coverage and sample bias
Solution Approach 1:
The patent creates a universal profiling system that handles multiple application types and network scenarios through a single unified machine learning framework. The system processes diverse network signals (HTTP, HTTPS, DNS, mobile data) using the same architecture, improving reliability across different applications without proportionally increasing device complexity.
Solution Approach 2:
The patent introduces machine learning models as intermediary components between raw network signals and application usage conclusions. These ML intermediaries process and interpret network data, enabling accurate application profiling while abstracting the complexity from the core system architecture and reducing direct complexity requirements.
3Adaptability or versatility
If 5G network capabilities are utilized to support diverse applications, then adaptability is improved, but difficulty of detecting and measuring increases due to ultrahigh-speed service delivery
Solution Approach 1:
The patent performs preliminary classification and filtering of network signals before detailed analysis. By pre-processing network data to identify relevant patterns and characteristics early in the detection process, the system reduces the complexity of subsequent measurement tasks while maintaining the ability to detect diverse 5G applications.
Solution Approach 2:
The patent adapts detection parameters and thresholds based on the specific 5G network conditions and application types being monitored. By dynamically adjusting measurement parameters according to network speed, traffic patterns, and application characteristics, the system maintains detection accuracy across diverse 5G services without requiring increasingly complex measurement infrastructure.
Data Source
AI summary
The disclosed technique incudes a method for dynamically selecting an algorithm that predicts usage of a mobile application based on network signals. In one example, an application profile includes known network signals and designates a best predictive algorithm. When network signals of user devices are subsequently captured, the best algorithms of sufficiently matching profiles are used to estimate application usage. As such, for example, the popularity of a particular application or relationships among applications can be determined for managing the network or for commercial purposes.