Adaptive Vision Testing Using Behavioral Confidence Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Typical vision tests performed without professional guidance are complex and do not adapt to individual needs, leading to unreliable results and a lack of trust in the testing process, as they do not consider the person's behavior during the test.
Innovation Solution
A computer-implemented method and training apparatus for training a machine learning model to determine a confidence value during a vision testing procedure, using recorded behavior and known confidence values to adjust the model, ensuring reliable and reproducible results by minimizing deviations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If a typical vision test is performed without professional guidance, then the testing procedure is simple and accessible, but the results are unreliable and the person does not trust the process
Solution Approach 1:
The system implements feedback by monitoring the person's behavior during the test (e.g., head movements, eye tracking) and using this information to adjust the testing procedure in real-time. The machine learning model processes behavioral data to provide feedback that improves result reliability while maintaining accessibility.
Solution Approach 2:
The vision testing system enables self-service by allowing persons to perform comprehensive vision tests without professional guidance. The automated machine learning model compensates for the lack of professional oversight by independently analyzing behavioral data and determining vision parameters, making reliable testing accessible to anyone.
2Device complexity
If a typical vision test does not consider the person's behavior, then the testing procedure is simple, but it does not adapt to individual needs
Solution Approach 1:
The testing procedure transitions from static to dynamic by continuously monitoring the person's behavior during the test and adapting parameters in real-time. The system adjusts test difficulty, presentation timing, and evaluation criteria based on observed behavioral patterns, enabling individualized testing while maintaining procedural simplicity through automation.
Solution Approach 2:
The system changes testing parameters (such as stimulus presentation rate, symbol size, test duration) based on detected behavioral parameters like eye movement patterns, head stability, and response time. These parameter adjustments are automatically made by the machine learning model to suit each person's individual testing characteristics.
3Reliability
If behavior information is recorded and processed using machine learning, then the results become reliable and adaptive, but the device complexity increases
Solution Approach 1:
The system replaces complex mechanical or manual processing methods with machine learning algorithms that run on standard computing devices. Instead of requiring sophisticated hardware or professional operator intervention, the machine learning model processes behavioral data using software-based pattern recognition, reducing physical device complexity while maintaining high reliability.
Data Source
AI summary
A computer-implemented method for training of a machine learning model for determining a confidence value during at least one test cycle of a vision testing procedure is disclosed. The confidence value is designated to determine at least one action in at least one subsequent test cycle of the vision testing procedure. Further, a trained machine learning model, a computer program having instructions for training of the machine learning model and a training apparatus are disclosed. Additionally, a computer-implemented method for performing the vision testing procedure on a person, a computer program having instructions for performing the vision testing procedure, a vision test apparatus, and a method for producing a geometrical model of at least one spectacle lens for manufacturing of at least one spectacle lens are disclosed.