Network Service Evaluation Using Adaptive KQI Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing network service evaluation methods using fixed empirical thresholds fail to adapt to fluctuating quality indicators, leading to evaluation errors when network quality fluctuates normally.
Innovation Solution
Perform statistical analysis on key quality indicators (KQIs) using call detail record (CDR) data to dynamically adjust thresholds, allowing for more flexible and accurate evaluation by obtaining perception scores based on adaptive thresholds.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Adaptability or versatility
If a fixed empirical threshold is used for quality indicator evaluation, then the evaluation standard is simple and easy to implement, but it cannot adapt to normal fluctuations in network quality indicators, leading to evaluation errors
Solution Approach 1:
The patent implements dynamic thresholds that automatically adjust according to historical quality indicator data and fluctuation patterns. Instead of using fixed empirical thresholds, the system continuously learns from past performance data and adapts threshold values to accommodate normal network variations, thereby resolving the contradiction between adaptability and system complexity
Solution Approach 2:
The system incorporates feedback mechanisms that monitor quality indicator fluctuations over time and use this information to refine evaluation thresholds. By analyzing historical data and feedback from the network performance, the system dynamically adjusts thresholds to distinguish between normal fluctuations and actual quality degradation, achieving adaptability without excessive complexity
2Measurement precision
If statistical analysis is performed on CDR data to obtain dynamic thresholds, then the evaluation accuracy is improved, but the computational complexity and data processing requirements increase
Solution Approach 1:
The patent performs preliminary statistical analysis on CDR data during idle periods or in advance of evaluation cycles. By pre-processing and storing statistical characteristics of quality indicators, the system reduces the computational burden during actual evaluation while maintaining high precision, thus balancing measurement accuracy with system complexity
Solution Approach 2:
The system creates simplified models or copies of the complex CDR data relationships through statistical analysis. Instead of processing raw CDR data in real-time, the patent generates aggregated statistical representations that capture essential patterns, reducing computational complexity while preserving evaluation precision
Data Source
AI summary
Embodiments of the present application relate to the field of communications, and provide a method for evaluating a network service, an electronic device and a storage medium. The method for evaluating a network service comprises: performing statistical analysis on each key quality indicator (KQI) according to call detail record (CDR) data in a first cycle, to obtain a first threshold of each KQI; obtaining a second threshold of each KQI according to the first threshold of each KQI in a second cycle, wherein, the second cycle comprises at least one first cycle; and obtaining a perception score of the network service according to the second threshold of each KQI and CDR data in a third cycle. The method is applied to the process of evaluating the network service.