ML Prediction Engine for IT Support User Experience Evaluation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Traditional methods for evaluating user experience in IT support services rely on technical metrics and customer satisfaction surveys, which may not accurately or timely reflect end-user experience, especially in moving from Service Level Agreements (SLA) to Experience Level Agreements (XLA).
Innovation Solution
A method and system using a machine learning-based multi-score prediction engine that analyzes historical IT support service tickets to predict metric scores for user experience, incorporating system-defined and user-defined weights to calculate a support service score, thereby evaluating user experience proactively and accurately.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional technical metrics and customer satisfaction surveys are used to evaluate user experience, then the evaluation process is simple and straightforward, but the accuracy and timeliness of reflecting end-user experience deteriorates
Solution Approach 1:
The patent replaces traditional mechanical survey methods with a machine learning-based automated prediction system. The ML model processes historical ticket data to predict user experience metrics, eliminating the need for manual surveys while improving accuracy and timeliness of measurement.
Solution Approach 2:
The system uses historical support ticket data to automatically predict user experience outcomes without requiring active user participation. The ML model self-trains on past data and continuously improves its predictions, providing timely feedback without user input.
2Measurement precision
If customer satisfaction surveys are sent immediately after support service, then the timing is timely, but the accuracy of reflecting real user experience deteriorates
Solution Approach 1:
The system performs preliminary analysis of historical ticket data to train the ML prediction model before actual user experience evaluation is needed. This pre-training enables the system to provide accurate, timely predictions without waiting for post-service surveys.
Solution Approach 2:
The patent substitutes post-service surveys with a predictive analytics system that proactively evaluates user experience based on ticket patterns and outcomes, eliminating the time delay inherent in survey-based approaches.
3Productivity
If SLA metrics are used to measure IT support service performance, then the focus is on process completion and output, but the connection to end-user experience and productivity deteriorates
Solution Approach 1:
The system establishes a feedback loop where ML predictions of user experience metrics are continuously compared with actual outcomes. This feedback enables the system to refine its predictions and align SLA metrics with actual user experience, improving the connection to productivity.
Solution Approach 2:
The patent transforms traditional SLA parameters into experience-based metrics by using ML models to predict and evaluate user experience outcomes. This parameter transformation bridges the gap between process completion metrics and actual user productivity impacts.
Data Source
AI summary
Embodiments of this disclosure include a method and system for machine learning based evaluation of user experience on information technology (IT) support service. The method may include obtaining a field data of an IT support service ticket and obtaining a multi-score prediction engine. The method may further include predicting metric scores of a plurality of IT support service metrics for the support service ticket based on the field data by executing the multi-score prediction engine. The method may further include obtaining system-defined weights and user-defined weights for the plurality of service metrics and calculating a support service score for the support service ticket based on the metric scores, the system-defined weights, and the user-defined weights. The method may further include evaluating user experience based on the support service score.