Unified QoE Framework for Encrypted Mobile Traffic
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional network analytics systems lack the ability to provide detailed, user-perceived service quality metrics for mobile networks, especially for encrypted traffic, and require extensive training data and tailored models for each service provider, making them costly and difficult to maintain.
Innovation Solution
A unified Quality of Experience (QoE) framework that calculates QoE metrics using a generic loss model based on Key Performance Indicators (KPIs), accounting for accessibility, integrity, and retainability, and utilizing machine learning for parameter optimization, independent of specific service providers.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If service-specific QoE models are developed for each service provider, then measurement precision of QoE metrics is improved, but device complexity and maintenance difficulty increase significantly
Solution Approach 1:
The patent implements a universal QoE calculation framework that works across multiple service providers and service types without requiring provider-specific models. The system uses a common set of KPIs and a unified QoE calculation formula that can be applied generically to different services (voice, video, data, messaging) and different providers, eliminating the need for extensive customization while maintaining measurement precision through service-type-specific weighting parameters.
Solution Approach 2:
The system changes parameters (weighting factors for accessibility, integrity, and retainability) based on service type rather than requiring complete model redesign for each provider. By adjusting these parameters according to service characteristics (e.g., different weights for voice vs. video services), the system achieves accurate QoE measurement across diverse services while maintaining a single unified model structure.
2Measurement precision
If extensive training data is collected for each service provider, then QoE measurement precision is improved, but loss of time and productivity decrease due to extensive data collection requirements
Solution Approach 1:
The patent extracts only the essential KPIs needed for QoE calculation from the network data, rather than collecting and processing extensive training data for each provider. The system identifies and collects a minimal set of critical performance indicators (accessibility, integrity, retainability metrics) that are sufficient for accurate QoE measurement, significantly reducing data collection time and processing overhead.
Solution Approach 2:
The system establishes a pre-configured QoE calculation framework with predefined KPIs and calculation methodologies that can be immediately applied to new service providers without requiring extensive prior data collection and model training. This preliminary setup enables rapid deployment of QoE monitoring across multiple providers while maintaining measurement accuracy.
3Adaptability or versatility
If tailored QoE models are created for each service provider, then adaptability to specific service characteristics is improved, but ease of operation and maintenance deteriorate
Solution Approach 1:
The system achieves adaptability to different service providers through a universal framework that automatically applies the same QoE calculation methodology across all providers. The unified model structure with service-type-specific parameters provides sufficient adaptability for different service characteristics (voice, video, data, messaging) while eliminating the operational complexity of maintaining separate tailored models for each provider.
4Measurement precision
If detailed service quality monitoring is implemented, then measurement precision of service quality issues is improved, but device complexity and processing requirements increase
Solution Approach 1:
The patent extracts and monitors only the three essential QoE dimensions (accessibility, integrity, retainability) and their associated KPIs, rather than implementing comprehensive detailed monitoring of all possible service quality parameters. This focused approach achieves sufficient measurement precision for identifying service quality issues while keeping the analytics system complexity manageable through selective KPI collection and a unified calculation framework.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Provided herein is a unified Quality of Experience (QoE) framework for determining QoE metrics for a plurality of mobile services based, in part, on the Key Performance Indicators (KPIs) that are collected for the services. The QoE metrics are scalar values, fall on a unified scale, and eliminate any dependencies that may exist between the KPIs used in determining the QoE metrics. The unified QoE framework includes a generic QoE calculation module having a loss model component, a KPI coupling calculation component, and a machine learning (ML) parameter optimization component. The QoE calculation module correlates network event information and calculates various resource and/or network KPIs. Additionally, the QoE calculation module calculates service KPIs for a predetermined number of traffic types, and estimates factors due to losses, drops, and soft drops. Additionally, the internal functional parameters of the underlying KPI are determined and/or optimized without requiring external intervention or the initial setting of parameters.