Communication Quality Score Machine Learning Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing communication systems face challenges in consistently measuring call quality across different endpoint and service providers, as mean opinion score (MOS) implementations vary and are not uniformly applied, leading to inconsistent user experience.
Innovation Solution
A communication system that uses a quality score machine learning model to generate an estimated quality score by collecting data from various communication nodes and devices, providing a consistent and user-centric measure of call quality, and leveraging this data to improve session quality by modifying properties such as codec or service provider.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If mean opinion score (MOS) is used to measure call quality, then user experience can be evaluated, but the measurement becomes inconsistent across different endpoint and service providers
Solution Approach 1:
The patent transforms the subjective MOS parameter into an objective quality score through machine learning. The system collects multiple objective parameters (packet loss, jitter, latency, codec information) and uses a trained model to generate a consistent quality score that replaces the variable MOS implementation, thereby achieving measurement consistency while adapting to different network conditions and device types.
Solution Approach 2:
The machine learning model acts as an intermediary between raw network parameters and quality assessment. Instead of directly comparing MOS values from different providers, the system uses the trained model as a mediator that processes inputs from various sources and produces a unified, consistent quality score that eliminates implementation variations.
2Measurement precision
If quality data is collected from multiple communication nodes, then measurement accuracy improves, but system complexity increases
Solution Approach 1:
The quality score machine learning model serves multiple functions: it processes data from various communication nodes, handles different parameter types (packet loss, jitter, latency), and generates consistent quality assessments. This multi-functionality reduces the need for separate systems for each measurement task, thereby managing complexity while maintaining high measurement precision through comprehensive data collection.
3Measurement precision
If machine learning model is trained on communication session data, then quality estimation accuracy improves, but processing time and computational resources increase
Solution Approach 1:
The system performs the computationally intensive machine learning model training in advance, before actual quality assessment is needed. The pre-trained model can then quickly process real-time network parameters and generate quality scores without requiring extensive processing time during live communication sessions, thus reducing loss of time while maintaining high estimation accuracy.
Data Source
AI summary
Methods, systems, and apparatus, including computer programs encoded on a computer storage medium, for evaluating the quality of a communication session. One of the methods includes identifying, by a communication system, a communication session between one or more users of the communication system, wherein, during the communication session, session data is routed between a first communications device of a first user of the communication system and one or more other communications devices along a communication path; obtaining, from each of a plurality of communication nodes along the communication path, quality data relating to a quality of the communication session at the communication node; generating, using the quality data, a model input to a quality score machine learning model; and providing the model input as input to the quality score machine learning model to generate the estimated quality score for at least the portion of the communication session.