ML-Based User Experience Quantification in Information Handling Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current information handling systems lack effective methods to quantify and improve end-user experiences, as they rely on manual assessments and do not utilize data-driven approaches to optimize performance and user satisfaction.
Innovation Solution
An information handling system that incorporates a machine learning model trained with telemetry and user survey data to calculate composite scores, enabling data-driven optimization of user experiences by identifying areas for improvement.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If manual assessments are used to evaluate user experiences, then implementation complexity is low, but measurement precision and objectivity are insufficient
Solution Approach 1:
The patent replaces manual assessment mechanisms with an automated machine learning model that processes telemetry data and survey responses. This substitution eliminates human subjectivity and scales the evaluation process, achieving precise quantification of user experiences through computational algorithms rather than manual judgment.
Solution Approach 2:
The patent introduces a machine learning model as an intermediary between raw data (telemetry and surveys) and user experience assessment. This intermediary layer processes multiple data sources, synthesizes them into meaningful patterns, and generates objective experience scores, bridging the gap between complex data and actionable insights.
2Loss of information
If data-driven approaches are implemented to optimize performance, then user experience quantification improves, but data processing requirements and computational resources increase
Solution Approach 1:
The patent extracts only the most relevant features from large volumes of telemetry data and survey responses that are necessary for training and executing the machine learning model. By selecting and processing only critical data elements rather than analyzing entire datasets, the system maintains high insight quality while reducing computational overhead and energy consumption.
3Measurement precision
If composite scores are calculated using machine learning models, then user experience measurement accuracy improves, but model training and execution time increase
Solution Approach 1:
The patent performs model training in advance using historical telemetry data and survey responses, creating a pre-trained machine learning model. This preliminary action allows the system to make rapid predictions on new data without requiring real-time training, thus achieving accurate experience measurements while minimizing execution time during actual operations.
Data Source
AI summary
An information handling system includes a storage and a processor. The storage stores a machine learning (ML) model. The processor receives first telemetry data associated with a second information handling system, and user survey data associated with the second information handling system. Based on the first telemetry data and the user survey data, the processor trains the ML model. The processor receives second telemetry data for the second information handling system. The processor executes the ML model to determine a composite score for the second information handling system.