Virtual Meeting Stream Quality Prediction via Time Map Correlation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Large-scale communication systems face challenges in efficiently managing resources for virtual meetings, leading to quality issues due to under-investment or high costs from over-investment, and administrators struggle to maintain infrastructure quality due to server load and user-device issues, rather than equipment failures.
Innovation Solution
A method that involves receiving future virtual-meeting time intervals and attributes, correlating them to recurring time intervals, retrieving a time-based performance pattern, and determining stream quality to publish information about the determined stream quality to requestors, utilizing an information handling system that collects, classifies, and queries data from multiple sources to optimize resource allocation and infrastructure management.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Loss of energy
If resources are under-invested to reduce costs, then cost is reduced, but communication quality degrades during high-demand intervals
Solution Approach 1:
The system performs preliminary analysis of historical performance data to identify recurring time intervals with quality degradation patterns. By predicting future quality issues before they occur, the system enables proactive resource allocation adjustments, allowing resources to be scaled up only when and where needed rather than maintaining constant over-provisioning.
Solution Approach 2:
The system dynamically adjusts resource allocation based on predicted quality degradation patterns. By continuously monitoring performance data and updating predictions, the system adapts resource provisioning to match actual demand patterns, transitioning from static to dynamic resource management that optimizes both cost and quality.
2Reliability
If resources are over-invested to ensure quality, then communication quality is maintained, but cost increases due to unused resources
Solution Approach 1:
Instead of fully over-provisioning resources to guarantee quality, the system applies partial action by allocating resources only to the extent needed based on predicted demand patterns. The system identifies specific time intervals and locations where quality degradation is likely, and provisions resources partially and selectively rather than universally and continuously.
Solution Approach 2:
The system changes the parameter of resource allocation from fixed to variable based on predicted quality patterns. By adjusting resource levels dynamically according to predicted demand, the system optimizes the balance between maintaining quality and reducing unnecessary resource costs.
3Measurement precision
If administrators manually monitor and manage infrastructure, then quality issues can be detected, but time and operational complexity increase
Solution Approach 1:
The system enables self-service by automatically monitoring infrastructure performance and predicting quality degradation without requiring continuous administrator intervention. The automated prediction system performs the monitoring and analysis functions that would otherwise require manual administrator effort, freeing up administrative time while maintaining or improving detection precision.
Solution Approach 2:
The system implements continuous feedback loops by automatically collecting performance data, analyzing patterns, and generating predictions. This automated feedback mechanism replaces manual monitoring, providing continuous quality detection without the time cost of human administrators reviewing data continuously.
4Measurement precision
If detailed performance data is collected from multiple sources, then prediction accuracy improves, but system complexity increases
Solution Approach 1:
The system achieves universality by creating a unified prediction framework that handles multiple data sources and stream types through a single analytical engine. Rather than implementing separate analysis systems for each data source, the platform provides a universal solution that processes diverse performance data through common patterns, reducing overall system complexity while maintaining high prediction accuracy.
Data Source
AI summary
In one embodiment, a method includes receiving a future virtual-meeting time interval and a set of virtual-meeting attributes in relation to a future virtual meeting. The method also includes correlating the future virtual-meeting time interval to at least one recurring time interval of a time map. In addition, the method includes retrieving a time-based performance pattern. The method further includes determining, from the time-based performance pattern, a stream quality for the virtual-meeting attributes at the at least one recurring time interval. In addition, the method includes publishing information related to the determined stream quality to a requestor.