Eyeglass Lens Selection Support System Using Learning Model
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for selecting eyeglass lenses, such as progressive multifocal lenses, face challenges in accurately determining optimal lenses for users due to the complexity of considering multiple parameters, leading to potential discomfort and dissatisfaction, especially for users without specialized knowledge.
Innovation Solution
A learning model generation method that associates user attribute information, eye measurement information, and use application information to infer the specifications of suitable eyeglass lenses, using a computer program and system that inputs this data to generate and display recommended lens specifications.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Ease of operation
If rule-based selection methods are used to narrow down lens candidates based on store staff experience, then the selection process becomes more structured, but it is difficult to define optimal rules in advance when multiple parameters are involved
Solution Approach 1:
The patent replaces the mechanical rule-based selection system with an information processing system (computer algorithm) that automatically processes multiple parameters and generates lens recommendations, eliminating the need for complex manual rule definition while maintaining structured decision-making
Solution Approach 2:
The patent transforms the selection approach from qualitative rules to quantitative parameter processing, where multiple lens parameters (addition power, progressive addition, design type) are processed as data inputs to generate optimized recommendations based on user characteristics
2Measurement precision
If assessment data for multiple lens parameters is collected and processed, then more comprehensive lens recommendations can be provided, but the complexity of defining and processing multiple parameters increases
Solution Approach 1:
The patent replaces complex manual parameter assessment with automated computer processing that handles multiple lens parameters simultaneously, achieving comprehensive evaluation without proportional increase in operational complexity
Solution Approach 2:
The patent creates a universal processing system that handles multiple different parameters (user age, refractive error, lens type, addition power) through a single integrated algorithm, allowing the same system to process diverse parameters without requiring separate processing mechanisms for each
3Adaptability or versatility
If store staff present lens candidates based on their knowledge and experience, then personalized recommendations can be provided, but individual skills vary and make formalization difficult
Solution Approach 1:
The patent creates a standardized digital model that captures and replicates expert lens selection knowledge in a formalized algorithm, allowing consistent application of personalized recommendations without relying on individual staff skills or difficult-to-formalize experience
Solution Approach 2:
The patent enables the system to automatically generate personalized lens recommendations based on user input data, reducing dependence on staff interpretation and making the personalization process systematic rather than skill-dependent
Data Source
AI summary
A learning model generation method, a computer program, an eyeglass lens selection support method and an eyeglass lens selection support system that can be expected to support selection of an eyeglass lens by inferring specifications of an eyeglass lens suitable for a user. The eyeglass lens selection support system according to an embodiment includes a storage unit that stores a learning model that outputs specification information of an eyeglass lens if attribute information of a user, measurement information related to eyes of the user and use application information of eyeglasses by the user are input, a user information acquisition unit that acquires the attribute information, measurement information and use application information, and a specification information acquisition unit that inputs the attribute information, measurement information and use application information acquired by the user information acquisition unit to the learning model, and acquires the specification information output by the learning model.