Intelligent eye protection method for children

Abstract

This invention provides a smart eye protection method for children, relating to the field of myopia prevention and control technology. The method utilizes multi-type sensing components integrated into smart glasses to simultaneously collect ambient light data, eye movement data, eye posture data, and eye usage duration data of the target child. After cleaning, preprocessing, and feature extraction of the collected data, it is input into an intelligent analysis model pre-trained with children's eye behavior sample data. This model identifies ambient light risks, abnormal eye behavior states, and visual fatigue states, matching corresponding intervention levels and methods. Intervention prompts are output through the interactive components of the smart glasses. Simultaneously, dynamic data is continuously collected to supplement the training dataset, iteratively optimizing the recognition accuracy and intervention strategies of the intelligent analysis model. This invention enables intelligent monitoring and personalized intervention of children's eye behavior across all scenarios, effectively improving the sustainability and effectiveness of myopia prevention and control in children.

Description

Technical Field

[0001] This invention relates to the field of myopia prevention and control technology for children, specifically to a smart eye protection method for children. Background Technology

[0002] Traditional methods of children's eye care rely heavily on manual reminders from parents and teachers. These methods only correct poor eye posture through visual observation and cannot provide real-time, continuous monitoring of children's eye-use behavior or accurately identify potential risks in ambient light. This makes it difficult to intervene effectively as soon as poor eye-use behavior occurs. Furthermore, traditional eye care products are limited in function, offering only simple reminders from a single perspective. They cannot comprehensively assess children's eye movements, screen time, and ambient light quality, nor can they adapt to the different age-specific eye characteristics and developmental patterns of children. This makes personalized eye care intervention difficult and fails to fundamentally help children develop healthy eye habits, resulting in very limited long-term myopia prevention effects.

[0003] While some existing smart eye protection products for children incorporate basic sensor monitoring functions, they generally suffer from incomplete monitoring dimensions and insufficient intelligence, failing to achieve comprehensive coverage of ambient light quality monitoring, eye behavior tracking, and visual fatigue assessment. The monitoring algorithms of existing products are mostly developed based on general adult data, without using children's specific eye behavior sample data for model training. This results in insufficient accuracy in identifying abnormal eye behavior in children, easily leading to misjudgments and missed detections, and also fails to adapt to the stage-specific characteristics of children's eye development and behavioral cognitive patterns. Furthermore, the intervention methods of existing products are relatively simple, often relying on simple vibrations or voice reminders, without designing tiered intervention strategies and appropriate guidance content tailored to children's cognitive characteristics. Children have low acceptance rates, and long-term use can easily lead to resistance, hindering continuous and effective intervention and guidance. In addition, existing products lack a complete family management system, failing to synchronize and aggregate children's eye data for analysis, and unable to iteratively optimize model performance through continuously collected dynamic data. This makes it difficult to form a closed-loop system for myopia prevention and control throughout the entire cycle, and the overall practicality and long-term prevention and control effects cannot meet the actual needs of children's myopia prevention and control. Summary of the Invention

[0004] In view of the above-mentioned technical shortcomings, the purpose of this invention is to provide a smart eye protection method for children, which realizes intelligent monitoring and personalized intervention of children's eye use behavior in all scenarios, and improves the sustainability and effectiveness of myopia prevention and control in children.

[0005] To achieve the above objectives, the present invention adopts the following technical solution:

[0006] A smart eye protection method for children includes the following steps:

[0007] Step 1: Using the multi-type sensing components on the smart glasses, ambient light data, eye movement data, eye posture data, and eye usage duration data of the target child's environment are collected simultaneously. Outlier removal, missing value completion, and data standardization are performed on all collected data to complete data cleaning and preprocessing. Pixel-level feature extraction is performed on the preprocessed image data, and trend feature extraction is performed on the preprocessed numerical data. All extracted features are integrated to form a multi-dimensional feature dataset.

[0008] Step 2: Input the multi-dimensional feature dataset into the intelligent analysis model that has been pre-trained with children's eye use behavior sample data. The intelligent analysis model will then identify ambient light risks, abnormal eye use behavior, and visual fatigue.

[0009] Step 3: Based on the identification results of the intelligent analysis model, match the corresponding intervention level and intervention method;

[0010] Step four: Output corresponding intervention prompts through the interactive components of the smart glasses;

[0011] Step 5: Continuously collect dynamic eye use data and environmental data of the target children, add new data to the training dataset, and iteratively optimize the recognition accuracy and intervention strategy of the intelligent analysis model.

[0012] Preferably, in step one, ambient light data is collected by the visible spectrum sensor, flicker sensor, glare sensor, ambient light and color temperature sensor mounted on the smart glasses. The ambient light data includes light brightness, color temperature, blue light content, flicker frequency, and glare intensity. Eye dynamic data and eye posture data are collected by the infrared camera and distance and posture sensor mounted on the smart glasses. The eye dynamic data includes eye movement trajectory and blink frequency. The eye posture data includes eye distance, head tilt angle, and viewing angle. The eye usage duration data includes continuous eye usage duration and cumulative daily eye usage duration.

[0013] Preferably, in step two, the intelligent analysis model compares ambient light data with preset safety thresholds for children's eye use environment to identify the type of ambient light risk and determine the corresponding risk level; the intelligent analysis model comprehensively analyzes eye dynamic data, eye posture data, and eye use duration data based on preset standards for children's healthy eye use to identify abnormal eye use behavior; and the intelligent analysis model combines eye dynamic characteristics to determine the visual fatigue state of the target child.

[0014] Preferably, in step three, the corresponding intervention levels are divided according to the ambient light risk level, the degree of abnormal eye use behavior, and the state of visual fatigue, and appropriate intervention methods and gamified eye muscle relaxation training content are matched.

[0015] Preferably, when the intelligent analysis model identifies an ambient light risk, it sends a control command to the electronically controlled lens of the smart glasses to adjust the light transmittance of the electronically controlled lens.

[0016] Preferably, vision test content is displayed through the display components of smart glasses, the vision test results of the target children are collected, the vision change trend of the target children is tracked, and recommended content on eye use habits is generated.

[0017] Preferably, the collected eye use data, intelligent analysis results, and intervention records are synchronized to the parent's application to generate an eye use behavior statistical report.

[0018] Compared with the prior art, the beneficial effects of the present invention are as follows:

[0019] This invention utilizes smart glasses equipped with multiple types of sensors to simultaneously collect multi-dimensional eye-related data, achieving comprehensive, real-time, and continuous monitoring of children's eye use status. This solves the problems of traditional methods, which only monitor a single dimension and cannot track in real time. The invention employs an intelligent analysis model pre-trained with children's eye behavior sample data for data processing and status recognition. This model is adapted to children's eye behavior characteristics and eye development patterns, effectively improving the accuracy of identifying environmental light risks, abnormal eye behavior, and visual fatigue, and reducing misjudgments and omissions.

[0020] This invention matches the identification results with corresponding intervention levels and methods, and designs suitable guidance content based on children's cognitive characteristics, which can improve children's acceptance and avoid resistance from long-term use. By actively adjusting the light transmittance of the smart glasses' electronically controlled lenses, proactive protection against harmful light sources is achieved, further enhancing eye protection. Eye usage data, analysis results, and intervention records are synchronized to the parent's application, allowing parents to promptly monitor and remotely manage their children's eye use. Continuously collecting dynamic data to supplement the training dataset and iteratively optimizing the model can continuously improve system performance. Simultaneously, adjusting relevant parameters according to the child's individual situation enables personalized eye protection intervention, forming a complete myopia prevention and control closed loop. Attached Figure Description

[0021] Figure 1 This is a flowchart of the method of the present invention. Detailed Implementation

[0022] The invention will now be further described with reference to the accompanying drawings.

[0023] like Figure 1 As shown, a smart eye protection method for children includes the following steps:

[0024] Step 1: Using the multi-type sensing components on the smart glasses, ambient light data, eye movement data, eye posture data, and eye usage duration data of the target child's environment are collected simultaneously. Outlier removal, missing value completion, and data standardization are performed on all collected data to complete data cleaning and preprocessing. Pixel-level feature extraction is performed on the preprocessed image data, and trend feature extraction is performed on the preprocessed numerical data. All extracted features are integrated to form a multi-dimensional feature dataset.

[0025] Ambient light data is collected through visible spectrum sensors, flicker sensors, glare sensors, ambient light and color temperature sensors equipped on the smart glasses. Ambient light data includes light brightness, color temperature, blue light content, flicker frequency, and glare intensity. Eye dynamic data and eye posture data are collected through infrared cameras, distance and posture sensors equipped on the smart glasses. Eye dynamic data includes eye movement trajectory and blink frequency. Eye posture data includes viewing distance, head tilt angle, and field of view. Eye usage duration data includes continuous eye usage duration and cumulative daily eye usage duration.

[0026] Step 2: Input the multi-dimensional feature dataset into the intelligent analysis model that has been pre-trained with children's eye use behavior sample data. The intelligent analysis model will then identify ambient light risks, abnormal eye use behavior, and visual fatigue.

[0027] The intelligent analysis model compares ambient light data with preset safety thresholds for children's eye use environment to identify types of ambient light risks and determine the corresponding risk levels. Based on preset standards for children's healthy eye use, the intelligent analysis model comprehensively analyzes dynamic eye data, eye posture data, and eye use duration data to identify abnormal eye use behaviors. The intelligent analysis model combines dynamic eye characteristics to determine the visual fatigue state of the target child.

[0028] Step 3: Based on the identification results of the intelligent analysis model, match the corresponding intervention level and intervention method; divide the corresponding intervention level according to the ambient light risk level, the degree of abnormal eye behavior, and the visual fatigue state, and match the appropriate intervention method and gamified eye muscle relaxation training content; when the intelligent analysis model identifies the ambient light risk, it sends a control command to the electronic control lens of the smart glasses to adjust the light transmittance of the electronic control lens.

[0029] Step four: Output corresponding intervention prompts through the interactive components of the smart glasses; display vision test content through the display components of the smart glasses, collect vision test results of the target children, track the vision change trends of the target children, and generate recommended content for eye use habits.

[0030] Step 5: Continuously collect dynamic eye use data and environmental data of the target children, add new data to the training dataset, and iteratively optimize the recognition accuracy and intervention strategy of the intelligent analysis model; synchronize the collected eye use data, intelligent analysis results, and intervention records to the parent application to generate an eye use behavior statistical report.

[0031] Example 1

[0032] This embodiment provides a smart eye protection method for children, and the specific implementation process is as follows:

[0033] Step one involves simultaneously collecting ambient light data, eye movement data, eye posture data, and eye usage duration data of the target child's environment using multiple types of sensors integrated into the smart glasses. All collected data undergoes outlier removal, missing value imputation, and data standardization to complete data cleaning and preprocessing. Pixel-level feature extraction is performed on the preprocessed image data, and trend feature extraction is performed on the preprocessed numerical data. All extracted features are then integrated to form a multi-dimensional feature dataset.

[0034] Step two involves inputting the multi-dimensional feature dataset into the intelligent analysis model pre-trained using children's eye-use behavior sample data. The intelligent analysis model compares ambient light data with preset safety thresholds for children's eye-use environment to identify ambient light risk types and determine corresponding risk levels. Based on preset healthy eye-use standards for children, the intelligent analysis model comprehensively analyzes eye movement data, eye posture data, and eye-use duration data to identify abnormal eye-use behaviors. Finally, the intelligent analysis model combines eye movement characteristics to determine the visual fatigue state of the target child.

[0035] Step 3: Based on the level of ambient light risk, the degree of abnormal eye behavior, and the state of visual fatigue, corresponding intervention levels are defined, and appropriate intervention methods and gamified eye muscle relaxation training content are matched.

[0036] Step four involves outputting corresponding intervention prompts through the interactive components of the smart glasses. When the intelligent analysis model identifies an ambient light risk, it sends a control command to the electronically controlled lens of the smart glasses to adjust the light transmittance of the lens. Matching gamified eye muscle relaxation training content is then displayed through the smart glasses' display components.

[0037] Step 5: Display vision test content through the smart glasses' display components, collect vision test results from the target children, track the children's vision change trends, and generate recommended content for eye use habits. Synchronize the collected eye use data, intelligent analysis results, and intervention records to the parent's application to generate a statistical report on eye use behavior.

[0038] Step Six: Continuously collect dynamic eye use data and environmental data of the target children, add new data to the training dataset, and iteratively optimize the recognition accuracy and intervention strategies of the intelligent analysis model. Based on the target children's age and basic vision data, adjust the safety threshold and intervention trigger conditions of the intelligent analysis model.

[0039] Example 2

[0040] This embodiment provides a children's intelligent eye protection system to implement the above-mentioned children's intelligent eye protection method, including smart glasses, an intelligent analysis module, an intervention matching module, an interactive execution module, a vision detection module, a data synchronization module, and an iterative optimization module.

[0041] The smart glasses are equipped with multiple types of sensors, including visible spectrum sensors, flicker sensors, glare sensors, ambient light and color temperature sensors, infrared cameras, and distance and posture sensors. The visible spectrum sensors, flicker sensors, glare sensors, and ambient light and color temperature sensors collect ambient light data, including light intensity, color temperature, blue light content, flicker frequency, and glare intensity. The infrared camera collects dynamic eye data, including eye movement trajectory and blink frequency. The distance and posture sensors collect eye posture data, including viewing distance, head tilt angle, and field of view. The smart glasses also record eye usage time data, including continuous eye usage time and cumulative daily eye usage time.

[0042] The intelligent analysis module communicates with multiple types of sensing components to receive all data collected by these components. It performs outlier removal, missing value completion, and data standardization on all collected data, completing data cleaning and preprocessing. The intelligent analysis module extracts pixel-level features from the preprocessed image data and trend features from the preprocessed numerical data, integrating all extracted features to form a multi-dimensional feature dataset. The intelligent analysis module includes an analysis unit pre-trained with children's eye-use behavior sample data. This unit compares ambient light data with preset safety thresholds for children's eye-use environments to identify ambient light risk types and determine corresponding risk levels. Based on preset standards for children's healthy eye use, the analysis unit comprehensively analyzes eye movement data, eye posture data, and eye-use duration data to identify abnormal eye-use behaviors. Finally, the analysis unit combines eye movement characteristics to determine the visual fatigue state of the target child.

[0043] The intervention matching module communicates with the intelligent analysis module to classify corresponding intervention levels based on the level of ambient light risk, the degree of abnormal eye use behavior, and the state of visual fatigue, and to match appropriate intervention methods and gamified eye muscle relaxation training content.

[0044] The interactive execution module communicates with the intervention matching module and is mounted on the smart glasses. The interactive execution module includes an electronically controlled lens, a display component, and a voice prompt component. The electronically controlled lens receives control commands and adjusts its light transmittance. The display component projects gamified eye muscle relaxation training content and vision test content. The voice prompt component outputs intervention prompts in voice format.

[0045] The vision testing module communicates with the display component to collect vision test results of the target children, track the vision change trends of the target children, and generate recommended content on eye habits.

[0046] The data synchronization module communicates with the intelligent analysis module, intervention matching module, and vision testing module to synchronize the collected eye use data, intelligent analysis results, intervention records, and vision test results to the parent's application and generate an eye use behavior statistical report.

[0047] The iterative optimization module communicates with multiple types of sensing components and the intelligent analysis module to continuously collect dynamic eye use data and environmental data of the target children. New data is added to the training dataset, and the recognition accuracy and intervention strategies of the intelligent analysis module are iteratively optimized. The iterative optimization module also adjusts the safety thresholds and intervention triggering conditions of the intelligent analysis module based on the target children's age and basic vision data.

Claims

1. A smart eye protection method for children, characterized in that, Includes the following steps: Step 1: Using the multi-type sensing components on the smart glasses, ambient light data, eye movement data, eye posture data, and eye usage duration data of the target child's environment are collected simultaneously. Outlier removal, missing value completion, and data standardization are performed on all collected data to complete data cleaning and preprocessing. Pixel-level feature extraction is performed on the preprocessed image data, and trend feature extraction is performed on the preprocessed numerical data. All extracted features are integrated to form a multi-dimensional feature dataset. Step 2: Input the multi-dimensional feature dataset into the intelligent analysis model that has been pre-trained with children's eye use behavior sample data. The intelligent analysis model will then identify ambient light risks, abnormal eye use behavior, and visual fatigue. Step 3: Based on the identification results of the intelligent analysis model, match the corresponding intervention level and intervention method; Step four: Output corresponding intervention prompts through the interactive components of the smart glasses; Step 5: Continuously collect dynamic eye use data and environmental data of the target children, add new data to the training dataset, and iteratively optimize the recognition accuracy and intervention strategy of the intelligent analysis model.

2. The intelligent eye protection method for children as described in claim 1, characterized in that, In step one, ambient light data is collected using the visible spectrum sensor, flicker sensor, glare sensor, ambient light and color temperature sensor mounted on the smart glasses. The ambient light data includes light brightness, color temperature, blue light content, flicker frequency, and glare intensity. Eye dynamic data and eye posture data are collected using the infrared camera, distance and posture sensor mounted on the smart glasses. Eye dynamic data includes eye movement trajectory and blink frequency. Eye posture data includes eye distance, head tilt angle, and field of view. Eye usage duration data includes continuous eye usage duration and cumulative daily eye usage duration.

3. The intelligent eye protection method for children as described in claim 1, characterized in that, In step two, the intelligent analysis model compares ambient light data with preset safety thresholds for children's eye use environment to identify the types of ambient light risks and determine the corresponding risk levels; based on preset standards for children's healthy eye use, the intelligent analysis model comprehensively analyzes dynamic eye data, eye posture data, and eye use duration data to identify abnormal eye use behavior; the intelligent analysis model combines dynamic eye characteristics to determine the visual fatigue state of the target child.

4. The intelligent eye protection method for children as described in claim 1, characterized in that, In step three, intervention levels are determined based on the level of ambient light risk, the degree of abnormal eye behavior, and the state of visual fatigue, and appropriate intervention methods and gamified eye muscle relaxation training content are matched accordingly.

5. A method for intelligent eye protection for children as described in claim 1, characterized in that, When the intelligent analysis model identifies a risk from ambient light, it sends a control command to the electronically controlled lens of the smart glasses to adjust the light transmittance of the lens.

6. The intelligent eye protection method for children as described in claim 1, characterized in that, Vision test content is displayed through the smart glasses' display components, the vision test results of the target children are collected, the vision change trends of the target children are tracked, and recommended content on eye habits is generated.

7. A child intelligent eye protection method as described in claim 1, characterized in that, The collected eye use data, intelligent analysis results, and intervention records are synchronized to the parent's application to generate an eye use behavior statistical report.

Images