ML Prediction of Wireless Network User Problem Reporting

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Users of wireless telecommunication networks often experience issues such as dropped calls and low reception but rarely report these problems, leading to significant customer care costs due to the time-consuming nature of reporting and the large user base.

Innovation Solution

A method using key performance indicators (KPIs) processed by a processor to create images for machine learning models, specifically convolutional neural networks, to predict whether a user will report network issues, allowing for proactive identification of problematic areas and targeted remedial actions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If users experience network problems and call customer care centers to report them, then problem reporting is achieved, but customer care costs and time consumption increase significantly

Engineering Contradiction:

Improveproblem reportingVSAvoidcustomer care costs

Core Design Contradiction:

ReliabilityVSLoss of energy

Solution Approach 1:

The system performs preliminary actions by proactively identifying users who are likely to experience network problems before they actually do, using machine learning models that analyze historical data and patterns. This allows the network operator to take preventive measures, such as sending notifications or dispatching technicians, before the user needs to call customer care, thereby reducing reporting costs while maintaining reliable problem detection

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the mechanical system of manual customer care calls with an automated electronic notification system. Instead of users calling customer centers, the system automatically sends notifications to users about predicted network issues, substituting human-operated telephone support with automated digital communication, thereby reducing energy consumption and costs

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Reliability

If users experience network problems and call customer care centers to report them, then problem reporting is achieved, but time consumption increases significantly

Engineering Contradiction:

Improveproblem reportingVSAvoidtime consumption

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system performs preliminary actions by proactively notifying users of predicted network issues before they occur, eliminating the need for users to spend time calling customer care centers. The automated notification system delivers information to users instantly, saving significant time compared to manual reporting processes

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the time-consuming mechanical process of manual customer care calls with automated electronic notifications. Users receive instant digital alerts about network issues without needing to make calls, thereby eliminating time consumption associated with customer care interactions

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Loss of energy

If the network operator proactively identifies and addresses network issues using machine learning models, then customer care costs are reduced, but system complexity increases

Engineering Contradiction:

Improvecustomer care costsVSAvoidsystem complexity

Core Design Contradiction:

Loss of energyVSDevice complexity

Solution Approach 1:

The patent applies universality by creating a multi-functional system where the machine learning model serves multiple purposes: it predicts network issues, identifies at-risk users, generates notifications, and provides analytics for network optimization. This consolidates what would otherwise require separate systems into a single unified platform, managing complexity while achieving cost reduction

Inventive Principle:

Principle #6Universality (Multi-functionality)

Solution Approach 2:

The system introduces an intermediary machine learning model that acts as a mediator between raw network data and customer care actions. This intermediary layer processes and interprets data, transforming complex network states into simple prediction outcomes that trigger automated responses, thereby managing system complexity through modular architecture

Inventive Principle:

Principle #24Intermediary (Mediator)

Data Source

PatentUS11751087B2Predicting whether a user of a wireless telecommunication network will report a problem

Publication Date: 2023.09.05 T MOBILE US INC

AI summary

Presented here is a method to predict whether a user of a wireless telecommunication network will report a problem or issue associated with the wireless telecommunication network. A processor can obtain multiple key performance indicators (KPIs) describing a user experience with the wireless telecommunication network. The processor can calculate at least a daily value of each KPI according to a rule specific to the KPI. The processor can create an image representing a value of each KPI, where a first axis of the image identifies the KPI, and where a second axis of the image represents the daily value of the KPI. The processor can predict whether the user of the wireless telecommunication network will report the problem by providing the image to a machine learning model and receiving a prediction from the machine learning model whether the user of the wireless telecommunication network will report the problem.