Model generation system, evaluation system, model generation method, and model generation program
The model generation system efficiently evaluates user interfaces by generating sample screens and using biometric information to create an inference model, addressing inefficiencies and subjectivity in existing methods, achieving accurate and objective usability assessment.
WO2026127095A1PCT designated stage Publication Date: 2026-06-18RESONAC CORP
Patent Information
- Authority / Receiving Office
- WO · WO
- Patent Type
- Applications
- Current Assignee / Owner
- RESONAC CORP
- Filing Date
- 2025-12-11
- Publication Date
- 2026-06-18
AI Technical Summary
⚠Technical Problem
Existing methods for evaluating user interfaces using user biometric information are inefficient and subjective, lacking accurate quantitative criteria.
⚗Method used
A model generation system that generates sample operation screens using an image generation model, obtains biometric information during operation, and performs machine learning to create an inference model for evaluating usability, allowing for efficient and objective assessment.
🎯Benefits of technology
Enables quick and efficient evaluation of user interfaces using biometric information, providing a more accurate and objective assessment of usability.
✦ Generated by Eureka AI based on patent content.
Smart Images
Figure JP2025043312_18062026_PF_FP_ABST
Abstract
This model generation system comprises at least one processor. The at least one processor acquires a designation prompt for generating a sample image, inputs each of one or more designation prompts to an image generation model to generate one or more sample images that correspond to one or more sample operation screens, sets an evaluation value related to an operation performed on a screen for each of the one or more sample operation screens, acquires biological information of a subject during an operation performed on the sample operation screen for each of the one or more sample operation screens that are generated on the basis of the one or more sample images, executes machine learning using teaching data that includes a combination of the biological information and the evaluation value for each of the one or more sample operation screens, and generates an inference model for inferring the evaluation value of a target operation screen from the biological information of a user during an operation performed on the target operation screen.
Need to check novelty before this filing date? Find Prior Art