User-Correlated Cell Scoring for Telecom KPI Prioritization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for calculating Key Performance Indications (KPIs) in telecom networks fail to measure customer experience and compute a realistic user score for arbitrary geographical areas served by multiple telecom cells, as they lack counters that account for spatial density variations and user experience across different regions.
Innovation Solution
A system and method for computing a User Correlated Network Score (CNS) that aggregates call records from mobile users, using KPIs like throughput, PRB utilization, interference ratio, call drop rate, and call setup success rate, to derive a user correlation factor and scale the network score, providing a realistic user profile and predictive insights.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If network KPIs are calculated from counters measured by network elements, then network performance metrics can be obtained, but customer experience measurement is not provided
Solution Approach 1:
The patent segments the network performance evaluation into two distinct components: network-side KPIs (from network elements) and user-side experience metrics (from customer devices). This segmentation allows both network performance and customer experience to be measured independently and then correlated, resolving the contradiction by capturing both dimensions without conflating them.
Solution Approach 2:
The patent introduces call records as an intermediary data source that bridges the network side and user side. Call records contain both network performance indicators and user experience indicators, serving as a mediator that enables correlation between network KPIs and customer experience without requiring direct integration of separate measurement systems.
2Reliability
If existing KPI computation methods are used, then network element performance can be assessed, but realistic user score for geographical areas cannot be computed
Solution Approach 1:
The patent merges network element performance data with user experience data from call records to create a comprehensive evaluation framework. By combining these previously separate data sources, the system can compute realistic user scores for geographical areas while maintaining reliable network element performance assessment, thus resolving the contradiction between the two measurement needs.
Solution Approach 2:
The patent adds a geographical dimension to the performance evaluation by computing user scores for specific geographical areas. This dimensional extension transforms the evaluation from purely network-element-centric to include spatial-user-centric metrics, enabling realistic user score computation without compromising network element performance assessment.
3Productivity
If network cells are optimized based on overall network KPIs, then network-wide performance improves, but cells impacting users most are not identified
Solution Approach 1:
The patent applies local quality by computing user correlated network scores for individual cells based on call records specific to each cell. This allows identification of which specific cells have the most impact on user experience in different geographical areas, enabling targeted optimization rather than uniform network-wide improvements. The local user experience metrics are then correlated with network KPIs to identify priority cells for optimization.
Data Source
AI summary
Low-performing cells, serving a telecom deployment in a given geographical area, are commonly identified by the telecom operators based on one or more Network KPIs computed for each of the cells being part of the deployment. However, most of these KPIs describe the overall state of affairs of the cell without any insight into the user usage profile of the cell. The present disclosure proposes a novel method to adjust the network KPIs based on scores of the macro cell or the small cell (101) with the user usage profile of the cell to obtain the user correlated network scores of the cells and prioritize the low-performing cells in the network in order of degree of impact on users and their usage. Another aspect of this disclosure is that it shall predict and compute a realistic user score to get predictive insights into user profiles for solutions and preventive measures.