Vision Testing Prediction Model Confidence Score Selection

Solution Overview

Problem

Current vision defect determination methods are inefficient due to the need to test numerous locations of a user's field of view, making the process slow and cumbersome, often requiring testing of thousands of combinations of characteristics.

Innovation Solution

A system that uses confidence-based selection of testing locations by providing initial feedback to a prediction model, which predicts characteristics and assigns confidence scores to locations, allowing for the efficient selection and testing of key locations during a visual test presentation, and generates visual defect information based on feedback.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Measurement precision

If traditional vision testing methods test many locations with multiple characteristics, then measurement precision is improved, but productivity deteriorates due to the slow and inefficient testing process

Engineering Contradiction:

Improvevision defect determination accuracyVSAvoidtesting speed

Core Design Contradiction:

Measurement precisionVSProductivity

Solution Approach 1:

The system performs preliminary testing at a first set of locations to obtain initial feedback before the main vision test. This preliminary action provides advance information that is used by the prediction model to identify promising locations, allowing the system to focus subsequent testing efforts more efficiently while maintaining comprehensive coverage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the traditional mechanical/sequential testing approach with a machine learning-based prediction system. The prediction model uses initial feedback to predict characteristics at additional locations and identify promising test locations, substituting computational intelligence for exhaustive systematic testing and dramatically improving testing efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

2Measurement precision

If traditional vision testing tests numerous combinations of characteristics, then measurement precision is improved, but loss of time increases due to the cumbersome testing process

Engineering Contradiction:

Improvevision defect determination accuracyVSAvoidtesting duration

Core Design Contradiction:

Measurement precisionVSLoss of time

Solution Approach 1:

The system performs preliminary testing at a first set of locations to obtain initial feedback before the main vision test. This preliminary action provides advance information that is used by the prediction model to identify promising locations, allowing the system to focus subsequent testing efforts more efficiently while maintaining comprehensive coverage.

Inventive Principle:

Principle #10Preliminary action

Solution Approach 2:

The patent replaces the traditional mechanical/sequential testing approach with a machine learning-based prediction system. The prediction model uses initial feedback to predict characteristics at additional locations and identify promising test locations, substituting computational intelligence for exhaustive systematic testing and dramatically improving testing efficiency.

Inventive Principle:

Principle #28Mechanics substitution (Replace mechanical system)

3Productivity

If prediction model is used to select testing locations, then productivity is improved by reducing testing complexity, but device complexity increases due to the prediction model and confidence score system

Engineering Contradiction:

Improvetesting efficiencyVSAvoidprediction model complexity

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The system implements a feedback loop where initial test results are fed into the prediction model, which then identifies promising locations for further testing. The confidence scores generated by the model provide a quantitative feedback mechanism that guides the selection of subsequent test locations, creating an adaptive testing process that improves efficiency while managing complexity through systematic decision-making.

Inventive Principle:

Principle #23Feedback

Data Source

PatentUS11659988B2Vision testing via prediction-based setting of an initial stimuli characteristic for user interface locations

Publication Date: 2023.05.30 UNIV OF MIAMI

AI summary

In some embodiments, initial feedback indicating threshold characteristics (under which a user sees initial stimuli presented on a user interface) may be provided to a prediction model, and a set of predicted characteristics (for a set of locations of the user interface) and a set of confidence scores associated with the set of locations may be obtained via the prediction model. Based on the set of confidence scores, one or more locations may be selected to be tested during a visual test presentation. As an example, the locations may be selected over one or more other locations of the set of locations based on the set of confidence scores. Based on predicted characteristics associated with the selected locations, stimuli may be presented at the selected locations during the visual test presentation. Visual defect information for the user may be generated based on feedback from the visual test presentation.