End-User Application QoE Recommendation Service With Predictive Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing systems struggle to distinguish between objective and subjective application malfunctions, leading to unsatisfactory user experiences and a lack of effective recourse for end users when applications subjectively malfunction.
Innovation Solution
A predictive application aware routing engine uses machine learning to analyze network and application telemetry, predicting potential Quality of Experience (QoE) issues and suggesting remedial actions to end users, with feedback loops to refine the recommendation service.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional support resources (documentation, FAQs) are provided, then objective application malfunctions can be addressed, but subjective application malfunctions remain unresolved
Solution Approach 1:
The patent replaces traditional manual QoE assessment methods with an automated machine learning-based prediction system. The system uses telemetry data from multiple sources (client devices, network infrastructure, application servers) to automatically predict QoE metrics, substituting human judgment and manual measurement with computational algorithms that can objectively quantify subjective user experience.
Solution Approach 2:
The patent introduces a recommendation service as an intermediary between the application and the user. This service acts as a mediator that receives telemetry data, processes it through machine learning models, generates personalized recommendations, and delivers them to users through the application interface, bridging the gap between technical system data and user experience improvement.
2Ease of operation
If a recommendation service is implemented, then user experience can be improved, but system complexity increases
Solution Approach 1:
The patent divides the complex QoE prediction and recommendation system into distinct modular components: telemetry collection modules (client-side, network-side, server-side), machine learning prediction engines, recommendation generation services, and feedback processing systems. Each component handles a specific aspect of the overall system, making the complexity manageable and the system easier to implement and maintain.
3Measurement precision
If feedback loops are added to refine recommendations, then recommendation accuracy improves, but processing time increases
Solution Approach 1:
The patent implements preliminary action by continuously collecting and pre-processing telemetry data in the background before users actually experience QoE issues. The system proactively builds prediction models and prepares recommendations in advance, so when a QoE degradation is detected, the system can quickly retrieve and present pre-computed recommendations rather than performing time-consuming analysis at the moment of user need.
Data Source
AI summary
In one embodiment, a recommendation service of a device provides a recommended action to a client of an online application predicted to improve a quality of experience metric for the online application. The device receives feedback from the client indicative of the recommended action not being implemented by a user of the client. The device determines, based on the feedback, a reason for the recommended action not being implemented. The device updates the recommendation service based on the reason for the recommended action not being implemented.