Real-Time Call Quality Prediction and Adaptation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems, such as VoIP, lack real-time adaptation mechanisms to improve user experience based on dynamic feedback, relying on offline analysis and pre-configured models that do not account for changing network conditions and user preferences.
Innovation Solution
A communication client application that models user feedback scores in relation to technical parameters, dynamically adapting call settings such as echo, noise, and bandwidth to enhance the quality of experience by predicting and adjusting call quality scores in real-time, using a server-hosted or peer-to-peer model that incorporates user feedback and technical data for ongoing system optimization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If offline analysis and pre-configured models are used for call quality assessment, then model complexity is reduced and ease of operation is improved, but real-time adaptation capability deteriorates
Solution Approach 1:
The patent implements dynamic adaptation by continuously updating call quality predictions during active calls based on real-time technical parameters. The system transitions from static pre-configured models to dynamic models that adapt to changing network conditions, user behavior, and call characteristics, enabling real-time optimization of call quality.
Solution Approach 2:
The system incorporates feedback loops where actual call quality data and user interactions are continuously collected and used to refine predictions. The model learns from real-world performance data and adjusts its parameters dynamically, creating a closed-loop system that improves call quality through continuous feedback from the operational environment.
2Adaptability or versatility
If dynamic real-time adaptation is implemented, then adaptability and call quality improvement are enhanced, but computational complexity and processing time increase
Solution Approach 1:
The system performs preliminary actions by pre-calculating and storing call quality predictions for various technical parameter combinations during the training phase. This pre-computation allows the system to quickly retrieve and apply pre-determined optimization strategies during real-time operations, reducing the computational burden during actual calls while maintaining adaptability.
Solution Approach 2:
The patent utilizes parameter changes by dynamically adjusting a limited set of critical call parameters (such as bitrate, resolution, frame rate) based on predicted quality improvements. Rather than optimizing all possible system parameters, the focus is placed on changing key parameters that have the most significant impact on call quality, thereby reducing computational complexity while maintaining effective adaptation.
3Measurement precision
If more technical parameters are monitored and analyzed, then measurement precision of call quality is improved, but data processing requirements and system complexity increase
Solution Approach 1:
The system applies the extraction principle by selectively monitoring and analyzing only the most relevant technical parameters that have the greatest impact on call quality. Rather than processing all available system data, the model extracts and focuses on critical parameters such as network bandwidth, latency, packet loss, and device performance metrics, reducing data processing requirements while maintaining high measurement precision for call quality assessment.
Data Source
Figure 1~2
Figure 3
Figure 4
AI summary
The disclosure relates to a communication client application for running on a user terminal to conduct calls over a network. The client is configured to access a model which models quality of user experience for calls based on a set of technical parameters of each call. The model itself is based on user feedback indicating subjective quality of multiple past calls as experienced by multiple users, modeled with respect to the technical parameters collected from each of the past calls. The model generates a predicted call quality score predicting the quality of user experience for the call given its technical parameters. Based on this process, one or more of the technical parameters of the call can be adapted to try to increase the quality experienced by the user.