Multi-Layer Machine Learning for Unified UX Score
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current frameworks, such as HEART and USER, are unable to measure overall user experience within cloud computing environments and track a user's journey from initial engagement to becoming a customer of a cloud service provider.
Innovation Solution
The use of sentiment analysis and theme classification techniques, trained through multiple layers of a machine learning environment, to generate a unified user experience (UX) score. This involves accessing training data, training layers of the machine learning model, and determining a layer order based on noise from the training data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional frameworks (HEART, USER) are used to measure user experience, then measurement simplicity is maintained, but measurement precision and comprehensiveness of user journey tracking deteriorate
Solution Approach 1:
The patent segments the user experience measurement into multiple layers: sentiment analysis layer (processing individual feedback), theme classification layer (categorizing feedback topics), and unified scoring layer (aggregating into journey-stage scores). This segmentation enables precise measurement at each layer while managing overall system complexity through modular architecture.
Solution Approach 2:
The patent adds temporal and contextual dimensions to traditional UX measurement by tracking user journey stages (awareness, consideration, decision, retention, advocacy) and analyzing sentiment/theme across these dimensions. This transforms single-point measurements into multi-dimensional user journey analytics.
2Loss of information
If multiple layers of machine learning model are trained to perform sentiment analysis and theme classification, then user experience insights are improved, but training time and computational resources increase
Solution Approach 1:
The patent performs preliminary actions by pre-training sentiment analysis and theme classification layers separately on curated datasets before deployment. This preliminary training reduces online adaptation time and enables the system to quickly process user feedback without extensive real-time training.
Solution Approach 2:
The patent implements a multi-layer approach where sentiment analysis and theme classification are performed as separate partial actions rather than a single comprehensive model. This allows selective training and optimization of each layer, reducing overall training time while maintaining comprehensive user experience analysis.
Data Source
AI summary
Techniques for generating a unified user experience (UX) score using sentiment analysis and theme classification, training multiple layers of a machine learning environment to perform sentiment analysis and theme classification, and arranging layers of a machine learning environment based on noise from training data are provided. A unified UX score is generated from categories that are indicative of a user's journey in association with the cloud service provider. Machine learning environments are trained and used to perform sentiment analysis and theme classification on user feedback data. The layers of a machine learning environment can also be arranged based on noise generated from training data used to train the models of the machine learning environments.