Unified UX Score via Sentiment Analysis and Theme Classification

Resolve Bottlenecks,
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, combined with machine learning environments, to generate a unified user experience (UX) score. This score is computed by combining scores from categories like happiness, adoption, mindshare, success of tasks, engagement, and retention, each contributing a predetermined percentage.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If existing frameworks (HEART, USER) are used to measure user experience, then individual product/service metrics can be obtained, but overall user experience and user journey tracking within cloud computing environment cannot be measured

Engineering Contradiction:

Improveuser experience measurement capabilityVSAvoidframework applicability to cloud environment

Core Design Contradiction:

Measurement precisionVSAdaptability or versatility

Solution Approach 1:

The patent combines multiple existing frameworks (HEART, USER) and integrates them with sentiment analysis and theme classification to create a unified user experience measurement system. This merging allows the system to capture both individual product metrics and overall user journey metrics within cloud computing environments, resolving the limitation of existing frameworks.

Inventive Principle:

Principle #5Merging (Combining)

Solution Approach 2:

The patent creates a universal user experience measurement framework that can be applied across multiple cloud services and products. The system processes feedback from various sources (surveys, social media, support tickets) and generates unified scores that reflect overall user experience, making it adaptable to different cloud computing contexts while maintaining comprehensive measurement capability.

Inventive Principle:

Principle #6Universality (Multi-functionality)

2Measurement precision

If multiple feedback sources are integrated to improve measurement comprehensiveness, then overall user experience can be measured, but system complexity increases

Engineering Contradiction:

Improveuser experience measurement comprehensivenessVSAvoidsystem architecture complexity

Core Design Contradiction:

Measurement precisionVSDevice complexity

Solution Approach 1:

The patent introduces machine learning models as intermediary components that automatically process and synthesize feedback from multiple sources. These models act as mediators between raw feedback data and final user experience scores, reducing the complexity of manually integrating diverse feedback sources while maintaining comprehensive measurement capability.

Inventive Principle:

Principle #24Intermediary (Mediator)

Solution Approach 2:

The patent replaces manual feedback analysis and integration processes with automated machine learning-based sentiment analysis and theme classification systems. This substitution eliminates the need for complex manual processing workflows while achieving comprehensive user experience measurement across multiple feedback sources.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

Data Source

PatentUS20250124475A1Generating a unified user experience score using sentiment analysis and theme classification

Publication Date: 2025.04.17 ORACLE INT CORP

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.