Intelligent eye health monitoring system based on Arduino + openCV technology

Abstract

The invention discloses an intelligent eye health monitoring system based on an Arduino + openCV technology, and the system comprises a sensor detection module which is used for collecting eye health data and surrounding environment data of a user in real time; the data processing module is used for analyzing sensor data; the adaptive ambient light adjusting module is used for automatically adjusting the lighting condition according to the ambient light intensity; the personalized eye protection suggestion generation module is used for generating personalized eye protection suggestions and early warning; the intelligent reminding and interaction module is used for providing multi-mode reminding; the health data analysis and report generation module is used for generating health reports and suggestions; the multi-factor health risk assessment module is used for analyzing health data and environmental factors; the intelligent glasses integration module is used for integrating monitoring and reminding functions; and the system self-optimization and learning module is used for dynamically optimizing the system performance. Through multi-sensor fusion and an intelligent algorithm, real-time monitoring, personalized suggestion generation and dynamic optimization management of eye health are realized.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent wearable devices, and in particular to an intelligent eye health monitoring system based on Arduino+openCV technology. Background Art

[0002] With the increasing degree of digitalization in modern society, people are increasingly dependent on electronic devices in work, study and entertainment, and eye health problems caused by long-term use of electronic devices have become a global hot topic. In particular, problems such as visual fatigue, dry eyes, and aggravated myopia caused by staring at the screen for a long time have significantly affected the quality of life of people of different ages. Eye health problems are not only short-term discomfort, but are also likely to cause long-term damage to vision. Studies have shown that long-term exposure to poor lighting conditions or improper eye posture will significantly increase the risk of eye fatigue. In addition, unreasonable eye behavior and neglect of eye health monitoring make it difficult to detect early visual fatigue or eye lesions, thereby missing the best time for intervention and prevention.

[0003] In the prior art, eye health monitoring devices mainly focus on the realization of a single function, such as monitoring the intensity of ambient light, reminding users that the blinking frequency is too low, or recording the time of eye use. However, these devices have many shortcomings in technical implementation and user experience. First of all, most devices rely on a single sensor and can only collect limited health data. For example, some devices can only monitor the intensity of ambient light and cannot comprehensively evaluate eye health in combination with multi-dimensional parameters such as humidity and temperature. This monitoring method cannot meet the user's needs for comprehensive health analysis, especially in complex eye use scenarios, such as office environments where lighting conditions change rapidly, or indoor and outdoor scenes with low humidity and large temperature differences.

[0004] Secondly, in the existing technology, most eye health monitoring devices lack intelligent data processing capabilities. Traditional devices only simply record or count the collected data, and are unable to mine users' eye behavior patterns or predict health trends through data analysis. For example, although some devices can prompt users to rest, they cannot generate personalized eye care recommendations based on the user's specific health status, ignoring the differences in individual needs. In addition, these devices usually lack adaptive learning functions and cannot dynamically optimize monitoring parameters or reminder strategies based on long-term data, which limits the long-term use value of the equipment.

[0005] In addition, existing eye health monitoring devices mostly interact with users in a single way, such as only reminding through simple visual or sound signals. This single interaction method is easily ignored by users, and the effectiveness of reminders and intervention effects are poor. At the same time, due to the lack of two-way interaction capabilities with users, the device cannot obtain user feedback information in a timely manner, nor can it be dynamically adjusted according to user habits, resulting in a poor user experience. These problems make it difficult for existing devices to be widely popularized among different populations.

[0006] There is still an obvious technical shortcoming in the monitoring and intervention of eye health problems, that is, the lack of comprehensive analysis capabilities of environmental and physiological parameters. Existing technologies are mostly limited to unilateral monitoring of the eyes or the environment, while ignoring the impact of external conditions such as ambient light, humidity, and temperature on eye behavior and health. Long-term exposure to uneven light or inappropriate humidity will aggravate eye discomfort and fatigue, but most devices cannot be adjusted according to environmental parameters, failing to achieve all-round monitoring and management from environment to behavior.

[0007] Based on this, the main defects of the existing technology can be summarized as follows: First, the data collection is single and cannot fully cover the key indicators of the user's eye health; second, the data processing capability is limited, lacking in-depth analysis and intelligent suggestion generation functions; third, the user interaction experience is poor, lacking diversified reminder methods and personalized feedback mechanisms; fourth, lacking adaptive optimization capabilities, unable to dynamically adjust system parameters based on the user's long-term data; fifth, ignoring the comprehensive impact of the environment and health, it is difficult to provide users with an integrated health management solution.

[0008] Therefore, how to provide an intelligent eye health monitoring system based on Arduino+openCV technology is a problem that technical personnel in this field need to solve urgently. Summary of the invention

[0009] One purpose of the present invention is to propose an intelligent eye health monitoring system based on Arduino+openCV technology. The present invention makes full use of multi-sensor fusion technology, deep learning algorithm and adaptive learning technology, and describes in detail the specific implementation method of intelligently collecting user eye health data, analyzing user health behavior patterns, generating personalized eye protection suggestions and real-time reminders. This method has the advantages of comprehensive monitoring range, intelligent data processing, diversified interaction methods and strong system adaptive optimization capabilities. It can provide users with accurate and dynamic eye health management services, and effectively alleviate health problems caused by long-term eye use.

[0010] According to an embodiment of the present invention, an intelligent eye health monitoring system based on Arduino+openCV technology includes:

[0011] The sensor detection module is used to collect the user's eye health data and surrounding environment data in real time;

[0012] A data processing module, used to receive and analyze the data collected by the sensor detection module;

[0013] Adaptive ambient light adjustment module, used to adjust lighting conditions according to the ambient light intensity monitored in real time;

[0014] Personalized eye protection suggestion generation module, used to generate eye protection suggestions and warnings based on user health data and eye habits;

[0015] Intelligent reminder and interaction module, used to provide multi-modal reminders based on the user's eye status and personalized settings;

[0016] Health data analysis and report generation module, used to regularly analyze user health data, generate health reports and long-term management suggestions;

[0017] Multi-factor health risk assessment module, used to comprehensively analyze the user's health data and environmental factors;

[0018] Smart glasses integration module, used to embed monitoring and reminder functions into smart glasses;

[0019] System self-optimization and learning module, used to continuously optimize system performance based on long-term user data.

[0020] Optionally, modules can be connected via the following methods:

[0021] S1, collecting the user's eye health data and surrounding environment data through the sensor detection module;

[0022] S2, integrating the data collected by each sensor and standardizing the data through the data acquisition and fusion module;

[0023] S3. Using the deep learning model in the data processing module, extract features from the standardized data, generate feature vectors containing eye health parameters, and build the user's health behavior pattern in combination with historical data;

[0024] S4, inputting the characteristic vector of the user's health behavior pattern and eye health parameters into the time series analysis module to predict the user's eye health trend and identify potential eye health risks;

[0025] S5. Based on the user's current health status and eye-use environment, the personalized eye-protection suggestion generation module is used to generate eye-protection suggestions, including rest time reminders, screen brightness adjustment suggestions, and eye-use behavior improvement measures;

[0026] S6. When the user's health risk exceeds the warning threshold, a multimodal reminder mechanism is triggered to remind the user to take intervention measures through sound, vibration or visual signals;

[0027] S7. Provide users with eye protection advice, real-time health data display and interactive feedback functions through the user interaction interface, and optimize the health advice generation strategy based on user feedback;

[0028] S8. Utilize the system’s adaptive learning module to dynamically adjust monitoring parameters, suggestion generation strategies, and reminder mechanisms based on users’ long-term usage data and behavior changes.

[0029] Optionally, S1 includes the following specific steps:

[0030] S11, using an infrared sensor to collect user's eye temperature data and record eye surface temperature data;

[0031] S12, obtaining user eye humidity data through a non-contact humidity sensor to generate eye humidity information;

[0032] S13, collecting ambient light data through an ambient light sensor to generate ambient light intensity information;

[0033] S14, collecting blink activity data through a blink monitoring sensor, and recording the user's blink frequency parameters, including the temperature change and the ambient temperature during the monitoring process;

[0034] S15, measuring the distance between the user and the device through an infrared proximity sensor, recording the sensor output voltage value and generating distance data;

[0035] S16. Store the collected eye health data and environmental data into sensor data sets respectively.

[0036] Optionally, S3 includes the following specific steps:

[0037] S31, inputting the sensor data after time synchronization processing into a feature extraction unit, including eye temperature data, eye humidity data, ambient light intensity data and blink frequency data;

[0038] S32. Use the deep learning model to extract features from the input data and generate a feature vector containing multi-dimensional health parameters:

[0039] Z=f(H,T,I,f b );

[0040] Among them, f is the feature extraction function, H is the eye humidity, T is the eye temperature, I is the ambient light intensity, and f b is the blink frequency;

[0041] S33, compare and analyze the generated feature vector with the user's historical health data to extract historical trends and behavior characteristics:

[0042] ΔZ=ZZ prev ;

[0043] Among them, ΔZ represents the feature change vector, Z prev is the feature vector at the previous time point, and Z is the current feature vector;

[0044] S34, constructing a health behavior model of the user, dynamically updating the health model based on the parameters of the feature vector, and describing the association between the user's eye behavior and health status;

[0045] S35. Store the user's health behavior pattern in the data analysis engine.

[0046] Optionally, S4 includes the following specific steps:

[0047] S41, inputting the generated user feature vector and health behavior pattern into a time series analysis module to establish a time series data set;

[0048] S42. Based on the time series data set, the user's health status is modeled using an autoregressive model:

[0049] U t =α·U t-1 +β+∈ t ;

[0050] Among them, α is the autoregressive coefficient, β is the trend term, ∈ t is the random error term, U t-1 Indicates the health status at the previous time point;

[0051] S43, predicting the user's health status change trend in the future time period based on the modeling results;

[0052] S44. Using the health status change trend and current health behavior pattern, combined with the user's specific threshold, determine whether there is a health risk:

[0053]

[0054] Among them, R is the health risk assessment result, ΔU is the trend of health status change, T threshold A specific threshold for the user;

[0055] S45. Output the health risk determination results and health trend data to the personalized eye care suggestion generation module.

[0056] Optionally, S5 includes the following specific steps:

[0057] S51, inputting the generated health risk determination results, health trend data, feature vectors and health behavior patterns into a personalized eye protection suggestion generation module;

[0058] S52, generating a preliminary eye protection suggestion set according to the user's current health status, including a rest time reminder, screen brightness adjustment suggestions, and eye behavior improvement measures for the user;

[0059] S=f s (Z,M behavior ,U t );

[0060] Among them, S represents the set of eye protection suggestions, f s is the suggestion generation function, Z is the current health feature vector, M behavior For healthy behavior patterns, U t for health status;

[0061] S53, screening the preliminary eye protection suggestion set based on the health risk determination result, and extracting suggestion items that meet the current health risk status;

[0062] S54, optimizing the screened eye protection suggestion set according to the user's current eye environment and personalized needs, and generating a final personalized eye protection suggestion:

[0063] S personalized =h(S R ,E);

[0064] Among them, h is the recommended optimization function, E is the user's current environment parameter, S R For eye protection, S personalized Provide personalized eye care suggestions;

[0065] S55. Output the personalized eye protection suggestions to the intelligent reminder module, and the suggestions include rest time reminders, behavior adjustment measures and environment optimization suggestions.

[0066] Optionally, S6 includes the following specific steps:

[0067] S61, inputting the generated personalized eye protection suggestions and health risk determination results into the intelligent reminder module to identify the reminder content that needs to be triggered;

[0068] S62. Determine the priority of reminders based on the health risk level and the content of the recommendations. The priority is divided into three levels: high, medium and low according to the severity of the health risk and the importance of the recommendations:

[0069] P priority =γ·R+δ·|S personalized |;

[0070] Among them, γ is the risk weight, δ is the recommended content weight, |S personalized | is the number of recommendations in the recommendation set, R is the health risk level, P priority The priority of the reminder;

[0071] S63, selecting an appropriate multi-modal reminder method according to the reminder content, including sound reminder, vibration reminder and visual signal reminder, and the selection of the reminder method is matched according to the user preference and the usage scenario;

[0072] S64: Generate reminder trigger time and frequency, and calculate appropriate reminder interval time according to health status and reminder priority:

[0073]

[0074] Among them, T current is the current time, P priority To remind the priority, T trigger Trigger time for reminder;

[0075] S65, executing the reminder content through the intelligent reminder module, specifically including issuing a sound signal, triggering vibration and lighting up a visual signal, to remind the user to take corresponding eye protection measures;

[0076] S66. Record the user's reminder response, including whether the eye protection suggestion is executed and the execution time information.

[0077] Optionally, S7 includes the following specific steps:

[0078] S71, inputting the reminder execution result of the intelligent reminder module and the user's response information to the eye protection suggestion into the user interaction interface, and displaying the eye protection suggestion and health data in real time;

[0079] S72. Display the user's current health status through an interactive interface, including eye temperature, humidity, light intensity, and blinking frequency. All data are updated in real time according to time series.

[0080] S73, recording the user's feedback on the health advice, including whether the user accepts the advice, the implementation status after acceptance, and the user's manual adjustment behavior record;

[0081] S74, classifying and arranging the user feedback information to generate a feedback set, wherein the feedback set includes positive feedback and adjustment feedback;

[0082] S75, comparing the user feedback information with the health behavior pattern and historical data, analyzing the correlation between the feedback and the health trend, and calculating the recommended optimization parameters;

[0083] S76. Storing the optimized eye protection suggestions in a personalized eye protection suggestion generation module.

[0084] Optionally, S8 includes the following specific steps:

[0085] S81, inputting the health data set and feedback information set generated by the user during long-term use into the system adaptive learning module for analyzing the user behavior pattern and feedback preference;

[0086] S82. Combine the health trend data, feature vectors and feedback association parameters, use the learning function to dynamically adjust the health analysis model and reminder strategy of the system, and calculate the optimized model parameters:

[0087] P model =L(D history ,F,U t ,Z,R);

[0088] Among them, P model represents the optimized model parameters, L is the online learning algorithm, and D history is the user's long-term health data set, F is the user feedback information set, U t is the health trend data of the user at time t, Z is the user's current health feature vector, and R is the feedback association parameter;

[0089] S83. updating the health analysis model according to the optimized model parameters, including the health trend prediction model and the health behavior pattern model;

[0090] S84, dynamically adjusting the monitoring parameters of the sensor, and setting the optimal sensor sampling frequency and data collection range according to the user's historical data and real-time health status;

[0091] S85, optimizing the personalized eye protection suggestion generation logic, adjusting the weight parameters of the suggestion generation function according to the user feedback preference, and generating an updated suggestion logic;

[0092] S86. Store the optimized health analysis model and suggestion generation logic in the system memory, and dynamically adjust the reminder content and frequency according to the optimization results.

[0093] The beneficial effects of the present invention are:

[0094] Through the implementation of the present invention, the problems of single monitoring, insufficient intelligence and poor interactive experience existing in the prior art can be significantly solved, and the accuracy and practicality of eye health monitoring can be comprehensively improved. The present invention adopts multi-sensor fusion technology to achieve multi-dimensional, real-time monitoring of the user's eye health and surrounding environment, including the collection of key indicators such as eye temperature, humidity, light intensity and blinking frequency, covering the core parameters that affect eye health. Combined with deep learning algorithms, the present invention can perform feature extraction and behavior pattern analysis on the collected data, thereby generating user health trend predictions and eye risk assessments, making up for the defect that traditional equipment cannot perform intelligent analysis.

[0095] In addition, the present invention uses a personalized eye protection suggestion generation module to dynamically generate rest reminders, screen brightness adjustment and other suggestions based on the user's current health status and eye environment, and supports multimodal reminder functions, including multiple methods of sound, vibration and visual signals, making reminders more flexible and efficient. Through the user interaction interface, the system can display real-time health data, receive user feedback, and optimize reminder strategies and health analysis models based on long-term feedback data and behavioral changes, thereby improving the personalization of suggestions and the system's adaptability.

[0096] The present invention also solves the technical shortcoming of the lack of comprehensive analysis of environmental parameters in existing equipment. It can comprehensively evaluate the user's health status by combining external factors such as ambient light intensity, humidity and temperature, and adjust monitoring parameters and reminder content in real time to ensure the accuracy of monitoring and the scientific nature of reminders. At the same time, through the adaptive learning module, the system can dynamically adjust various monitoring and analysis functions according to the user's long-term usage data, so that the system can better meet user needs in long-term use.

[0097] To sum up, the present invention has the significant advantages of comprehensive monitoring, intelligent data analysis, diversified reminder interactions, and strong system adaptive optimization capabilities. It provides users with a real-time, accurate, and personalized eye health management solution, effectively improves users' eye habits, reduces health risks caused by long-term eye use, and greatly enhances users' health management experience and the long-term use value of the system. BRIEF DESCRIPTION OF THE DRAWINGS

[0098] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0099] Figure 1 This is a flow chart of the intelligent eye health monitoring system based on Arduino+openCV technology proposed by the present invention;

[0100] Figure 2This is a schematic diagram of the composition of the multi-sensor detection module of the intelligent eye health monitoring system based on Arduino+openCV technology proposed in the present invention. DETAILED DESCRIPTION

[0101] The present invention will now be described in further detail with reference to the accompanying drawings. These drawings are simplified schematic diagrams, which only illustrate the basic structure of the present invention in a schematic manner, and therefore only show the components related to the present invention.

[0102] refer to Figure 1-2 , an intelligent eye health monitoring system based on Arduino+openCV technology, including:

[0103] The sensor detection module is used to collect the user's eye health data and surrounding environment data in real time;

[0104] A data processing module, used to receive and analyze the data collected by the sensor detection module;

[0105] Adaptive ambient light adjustment module, used to adjust lighting conditions according to the ambient light intensity monitored in real time;

[0106] Personalized eye protection suggestion generation module, used to generate eye protection suggestions and warnings based on user health data and eye habits;

[0107] Intelligent reminder and interaction module, used to provide multi-modal reminders based on the user's eye status and personalized settings;

[0108] Health data analysis and report generation module, used to regularly analyze user health data, generate health reports and long-term management suggestions;

[0109] Multi-factor health risk assessment module, used to comprehensively analyze the user's health data and environmental factors;

[0110] Smart glasses integration module, used to embed monitoring and reminder functions into smart glasses;

[0111] System self-optimization and learning module, used to continuously optimize system performance based on long-term user data.

[0112] In this implementation, the modules are implemented by the following method:

[0113] S1, collecting the user's eye health data and surrounding environment data through the sensor detection module;

[0114] S2, integrating the data collected by each sensor and standardizing the data through the data acquisition and fusion module;

[0115] S3. Using the deep learning model in the data processing module, extract features from the standardized data, generate feature vectors containing eye health parameters, and build the user's health behavior pattern in combination with historical data;

[0116] S4, inputting the characteristic vector of the user's health behavior pattern and eye health parameters into the time series analysis module to predict the user's eye health trend and identify potential eye health risks;

[0117] S5. Based on the user's current health status and eye-use environment, the personalized eye-protection suggestion generation module is used to generate eye-protection suggestions, including rest time reminders, screen brightness adjustment suggestions, and eye-use behavior improvement measures;

[0118] S6. When the user's health risk exceeds the warning threshold, a multimodal reminder mechanism is triggered to remind the user to take intervention measures through sound, vibration or visual signals;

[0119] S7. Provide users with eye protection advice, real-time health data display and interactive feedback functions through the user interaction interface, and optimize the health advice generation strategy based on user feedback;

[0120] S8. Utilize the system’s adaptive learning module to dynamically adjust monitoring parameters, suggestion generation strategies, and reminder mechanisms based on users’ long-term usage data and behavior changes.

[0121] In this implementation, S1 includes the following specific steps:

[0122] S11, using an infrared sensor to collect user's eye temperature data and record eye surface temperature data;

[0123] S12, obtaining user eye humidity data through a non-contact humidity sensor to generate eye humidity information;

[0124] S13, collecting ambient light data through an ambient light sensor to generate ambient light intensity information;

[0125] S14, collecting blink activity data through a blink monitoring sensor, and recording the user's blink frequency parameters, including the temperature change and the ambient temperature during the monitoring process;

[0126] S15, measuring the distance between the user and the device through an infrared proximity sensor, recording the sensor output voltage value and generating distance data;

[0127] S16. Store the collected eye health data and environmental data into sensor data sets respectively.

[0128] In this implementation, S3 includes the following specific steps:

[0129] S31, inputting the sensor data after time synchronization processing into a feature extraction unit, including eye temperature data, eye humidity data, ambient light intensity data and blink frequency data;

[0130] S32. Use the deep learning model to extract features from the input data and generate a feature vector containing multi-dimensional health parameters:

[0131] Z=f(H,T,I,f b );

[0132] Among them, f is the feature extraction function, H is the eye humidity, T is the eye temperature, I is the ambient light intensity, and f b is the blink frequency;

[0133] S33, compare and analyze the generated feature vector with the user's historical health data to extract historical trends and behavior characteristics:

[0134] ΔZ=ZZ prev ;

[0135] Among them, ΔZ represents the feature change vector, Z prev is the feature vector at the previous time point, and Z is the current feature vector;

[0136] S34, constructing a health behavior model of the user, dynamically updating the health model based on the parameters of the feature vector, and describing the association between the user's eye behavior and health status;

[0137] S35. Store the user's health behavior pattern in the data analysis engine.

[0138] In this implementation, S4 includes the following specific steps:

[0139] S41, inputting the generated user feature vector and health behavior pattern into a time series analysis module to establish a time series data set;

[0140] S42. Based on the time series data set, the user's health status is modeled using an autoregressive model:

[0141] U t =α·U t-1 +β+∈ t ;

[0142] Among them, α is the autoregressive coefficient, β is the trend term, ∈ t is the random error term, U t-1 Indicates the health status at the previous time point;

[0143] S43, predicting the user's health status change trend in the future time period based on the modeling results;

[0144] S44. Using the health status change trend and current health behavior pattern, combined with the user's specific threshold, determine whether there is a health risk:

[0145]

[0146] Among them, R is the health risk assessment result, ΔU is the trend of health status change, T threshold A specific threshold for the user;

[0147] S45. Output the health risk determination results and health trend data to the personalized eye care suggestion generation module.

[0148] In this implementation, S5 includes the following specific steps:

[0149] S51, inputting the generated health risk determination results, health trend data, feature vectors and health behavior patterns into a personalized eye protection suggestion generation module;

[0150] S52, generating a preliminary eye protection suggestion set according to the user's current health status, including a rest time reminder, screen brightness adjustment suggestions, and eye behavior improvement measures for the user;

[0151] S=f s (Z,M behavior ,U t );

[0152] Among them, S represents the set of eye protection suggestions, f s is the suggestion generation function, Z is the current health feature vector, M behavior For healthy behavior patterns, U t for health status;

[0153] S53, screening the preliminary eye protection suggestion set based on the health risk determination result, and extracting suggestion items that meet the current health risk status;

[0154] S54, optimizing the screened eye protection suggestion set according to the user's current eye environment and personalized needs, and generating a final personalized eye protection suggestion:

[0155] S personalized =h(S R ,E);

[0156] Among them, h is the recommended optimization function, E is the user's current environment parameter, S R For eye protection, S personalized Provide personalized eye care suggestions;

[0157] S55. Output the personalized eye protection suggestions to the intelligent reminder module, and the suggestions include rest time reminders, behavior adjustment measures and environment optimization suggestions.

[0158] In this implementation, S6 includes the following specific steps:

[0159] S61, inputting the generated personalized eye protection suggestions and health risk determination results into the intelligent reminder module to identify the reminder content that needs to be triggered;

[0160] S62. Determine the priority of reminders based on the health risk level and the content of the recommendations. The priority is divided into three levels: high, medium and low according to the severity of the health risk and the importance of the recommendations:

[0161] P priority =γ·R+δ·|S personalized |;

[0162] Among them, γ is the risk weight, δ is the recommended content weight, |S personalized | is the number of recommendations in the recommendation set, R is the health risk level, P priority The priority of the reminder;

[0163] S63, selecting an appropriate multi-modal reminder method according to the reminder content, including sound reminder, vibration reminder and visual signal reminder, and the selection of the reminder method is matched according to the user preference and the usage scenario;

[0164] S64: Generate reminder trigger time and frequency, and calculate appropriate reminder interval time according to health status and reminder priority:

[0165]

[0166] Among them, T current is the current time, P priority To remind the priority, T trigger Trigger time for reminder;

[0167] S65, executing the reminder content through the intelligent reminder module, specifically including issuing a sound signal, triggering vibration and lighting up a visual signal, to remind the user to take corresponding eye protection measures;

[0168] S66. Record the user's reminder response, including whether the eye protection suggestion is executed and the execution time information.

[0169] In this implementation, S7 includes the following specific steps:

[0170] S71, inputting the reminder execution result of the intelligent reminder module and the user's response information to the eye protection suggestion into the user interaction interface, and displaying the eye protection suggestion and health data in real time;

[0171] S72. Display the user's current health status through an interactive interface, including eye temperature, humidity, light intensity, and blinking frequency. All data are updated in real time according to time series.

[0172] S73, recording the user's feedback on the health advice, including whether the user accepts the advice, the implementation status after acceptance, and the user's manual adjustment behavior record;

[0173] S74, classifying and arranging the user feedback information to generate a feedback set, wherein the feedback set includes positive feedback and adjustment feedback;

[0174] S75, comparing the user feedback information with the health behavior pattern and historical data, analyzing the correlation between the feedback and the health trend, and calculating the recommended optimization parameters;

[0175] S76. Storing the optimized eye protection suggestions in a personalized eye protection suggestion generation module.

[0176] In this implementation, S8 includes the following specific steps:

[0177] S81, inputting the health data set and feedback information set generated by the user during long-term use into the system adaptive learning module for analyzing the user behavior pattern and feedback preference;

[0178] S82. Combine the health trend data, feature vectors and feedback association parameters, use the learning function to dynamically adjust the health analysis model and reminder strategy of the system, and calculate the optimized model parameters:

[0179] P model =L(D history ,F,U t ,Z,R);

[0180] Among them, P model represents the optimized model parameters, L is the online learning algorithm, and D history is the user's long-term health data set, F is the user feedback information set, U t is the health trend data of the user at time t, Z is the user's current health feature vector, and R is the feedback association parameter;

[0181] S83. updating the health analysis model according to the optimized model parameters, including the health trend prediction model and the health behavior pattern model;

[0182] S84, dynamically adjusting the monitoring parameters of the sensor, and setting the optimal sensor sampling frequency and data collection range according to the user's historical data and real-time health status;

[0183] S85, optimizing the personalized eye protection suggestion generation logic, adjusting the weight parameters of the suggestion generation function according to the user feedback preference, and generating an updated suggestion logic;

[0184] S86. Store the optimized health analysis model and suggestion generation logic in the system memory, and dynamically adjust the reminder content and frequency according to the optimization results.

[0185] Embodiment 1:

[0186] In order to verify the feasibility of the present invention in implementation, the present invention was applied to a software development company. The team members were engaged in programming and testing for a long time, and the average daily eye use time exceeded 10 hours, which led to frequent visual fatigue and eye discomfort. In order to solve this problem, the team introduced the intelligent eye health monitoring system based on Arduino and OpenCV technology of the present invention, and conducted a one-month test on it to verify the actual effect of the present invention.

[0187] During the test, team members wore smart glasses integrated with this system, which monitored the user's eye temperature, humidity, light intensity, and blink frequency in real time through built-in sensors (infrared sensor, humidity sensor, ambient light sensor, and blink monitoring module). These data are analyzed by the system's processing module to generate the user's health status parameters, and combined with the time series model to predict health trends. The system dynamically generates eye protection recommendations based on the user's current health status and environmental parameters, and reminds the user to take timely intervention measures through vibration, sound or visual signals.

[0188] One day, after a developer had worked for two hours in a row, the system detected that the user's blinking frequency dropped to 8 times per minute, which was below the lower limit of the healthy range. At the same time, the ambient light intensity was insufficient, only 320 lux. The system first reminded the user to take a short break through vibration, and at the same time suggested that he do eye exercises and adjust the brightness of the desk lamp to an appropriate level of 500 lux. After the user accepted the suggestion, the blinking frequency returned to 12 times per minute within 15 minutes, and the eye humidity also increased from 46% to 58%.

[0189] During the test, the system recorded the feedback and usage data of each member through the user interface. For example, one user was not sensitive to sound reminders, but responded quickly to vibration reminders. Through the adaptive learning function, the system adjusted the user's main reminder method to vibration, which significantly improved the effectiveness of the reminder. In addition, in the monitoring of the lighting environment of team members, the system found that 70% of the members had insufficient light intensity in their working environment. Through the dynamic light adjustment function, the light intensity was effectively improved.

[0190] After the test, the comparative analysis results showed that the blinking frequency of team members generally increased from 9 times per minute to 12-15 times, the visual fatigue rate dropped from the original 78% to 32%, and the average work efficiency increased by 20%. Through long-term monitoring of health data, the system also generates a personalized health report for each member, including health status trends and eye behavior recommendations, to further help users improve long-term eye habits.

[0191] Table 1 Comparison of eye health data before and after the R&D team test

[0192]

[0193] Table 2 Single user working status adjustment process data

[0194]

[0195] It can be observed from Table 1 that the average blinking frequency, eye humidity, ambient light intensity and visual fatigue rate of the R&D team before and after the test all changed significantly. Before the introduction of this system, the average blinking frequency of the members was generally lower than the health standard, with the lowest being only 8 times per minute, while after the test it increased to 12-15 times per minute, returning to the normal range. Eye humidity also increased from 45%-50% before the test to 55%-62% after the test, indicating that the eye environment of the members has been significantly improved through the reminders and interventions of the system. In addition, the ambient light intensity increased from less than 300 lux to a suitable range of 400-600 lux after the test, effectively alleviating visual fatigue caused by insufficient light. The visual fatigue rate was significantly reduced from the original 75%-80% to 25%-35%, which directly reflects the reduction of the user's eye burden. The improvement in work efficiency also shows that the improvement in health status has a positive effect on work concentration, and the work efficiency of team members has increased by an average of 18%-22%.

[0196] Table 2 further reveals the specific performance of the system in user personalized health management. For example, during the use of a typical user, the system detected that his blinking frequency gradually decreased from 10 times per minute in the morning to 8 times per minute in the afternoon, accompanied by a continuous decrease in eye moisture. Through the system's multimodal reminder function, the user received vibration reminders at 10:30 and 13:00 respectively, and adjusted his eye habits. After that, the user's blinking frequency recovered to 12 times per minute at 15:30, eye moisture increased from 43% to 55%, and the light intensity was dynamically adjusted to maintain within a comfortable range of 500 lux. The user's feedback on the vibration reminder was positive, proving the effectiveness of the system's reminder strategy in actual scenarios.

[0197] Comprehensive analysis of the data in Table 1 and Table 2 shows that the present invention not only effectively improves the user's eye habits, but also significantly reduces the incidence of visual fatigue through multi-dimensional monitoring and intelligent intervention methods. In particular, through the adaptive learning function, the system can dynamically adjust the reminder strategy and suggestion content according to the user's long-term usage data, thereby achieving highly personalized health management. This combination of scientificity and flexibility enables the system to continue to play a role in long-term use, providing users with accurate and efficient health monitoring and behavior guidance services, and has a wide range of application value.

[0198] The above description is only a preferred specific implementation manner of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can make equivalent replacements or changes according to the technical scheme and inventive concept of the present invention within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

Claims

1. Intelligent eye health monitoring system based on Arduino+openCV technology, characterized by: include: The sensor detection module is used to collect the user's eye health data and surrounding environment data in real time; A data processing module, used to receive and analyze the data collected by the sensor detection module; Adaptive ambient light adjustment module, used to adjust lighting conditions according to the ambient light intensity monitored in real time; Personalized eye protection suggestion generation module, used to generate eye protection suggestions and warnings based on user health data and eye habits; Intelligent reminder and interaction module, used to provide multi-modal reminders based on the user's eye status and personalized settings; Health data analysis and report generation module, used to regularly analyze user health data, generate health reports and long-term management suggestions; Multi-factor health risk assessment module, used to comprehensively analyze the user's health data and environmental factors; Smart glasses integration module, used to embed monitoring and reminder functions into smart glasses; System self-optimization and learning module, used to continuously optimize system performance based on long-term user data.

2. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 1, characterized in that: The modules are implemented in the following ways: S1, collecting the user's eye health data and surrounding environment data through the sensor detection module; S2, integrating the data collected by each sensor and standardizing the data through the data acquisition and fusion module; S3. Using the deep learning model in the data processing module, extract features from the standardized data, generate feature vectors containing eye health parameters, and build the user's health behavior pattern in combination with historical data; S4, inputting the characteristic vector of the user's health behavior pattern and eye health parameters into the time series analysis module to predict the user's eye health trend and identify potential eye health risks; S5. Based on the user's current health status and eye-use environment, the personalized eye-protection suggestion generation module is used to generate eye-protection suggestions, including rest time reminders, screen brightness adjustment suggestions, and eye-use behavior improvement measures; S6. When the user's health risk exceeds the warning threshold, a multimodal reminder mechanism is triggered to remind the user to take intervention measures through sound, vibration or visual signals; S7. Provide users with eye protection advice, real-time health data display and interactive feedback functions through the user interaction interface, and optimize the health advice generation strategy based on user feedback; S8. Utilize the system’s adaptive learning module to dynamically adjust monitoring parameters, suggestion generation strategies, and reminder mechanisms based on users’ long-term usage data and behavior changes.

3. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S1 comprises the following specific steps: S11, using an infrared sensor to collect user's eye temperature data and record eye surface temperature data; S12, obtaining user eye humidity data through a non-contact humidity sensor to generate eye humidity information; S13, collecting ambient light data through an ambient light sensor to generate ambient light intensity information; S14, collecting blink activity data through a blink monitoring sensor, and recording the user's blink frequency parameters, including the temperature change and the ambient temperature during the monitoring process; S15, measuring the distance between the user and the device through an infrared proximity sensor, recording the sensor output voltage value and generating distance data; S16. Store the collected eye health data and environmental data into sensor data sets respectively.

4. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S3 includes the following specific steps: S31, inputting the sensor data after time synchronization processing into a feature extraction unit, including eye temperature data, eye humidity data, ambient light intensity data and blink frequency data; S32. Use the deep learning model to extract features from the input data and generate a feature vector containing multi-dimensional health parameters: Z=f(H,T,I,f b ); Among them, f is the feature extraction function, H is the eye humidity, T is the eye temperature, I is the ambient light intensity, and f b is the blink frequency; S33, compare and analyze the generated feature vector with the user's historical health data to extract historical trends and behavior characteristics: ΔZ=ZZ prev ; Among them, ΔZ represents the feature change vector, Z prev is the feature vector at the previous time point, and Z is the current feature vector; S34, constructing a health behavior model of the user, dynamically updating the health model based on the parameters of the feature vector, and describing the association between the user's eye behavior and health status; S35. Store the user's health behavior pattern in the data analysis engine.

5. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S4 comprises the following specific steps: S41, inputting the generated user feature vector and health behavior pattern into a time series analysis module to establish a time series data set; S42. Based on the time series data set, the user's health status is modeled using an autoregressive model: U t =α·U t-1 +β+∈ t ; Among them, α is the autoregressive coefficient, β is the trend term, ∈ t is the random error term, U t-1 Indicates the health status at the previous time point; S43, predicting the user's health status change trend in the future time period based on the modeling results; S44. Using the health status change trend and current health behavior pattern, combined with the user's specific threshold, determine whether there is a health risk: Among them, R is the health risk assessment result, ΔU is the trend of health status change, T threshold A specific threshold for the user; S45. Output the health risk determination results and health trend data to the personalized eye care suggestion generation module.

6. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S5 comprises the following specific steps: S51, inputting the generated health risk determination results, health trend data, feature vectors and health behavior patterns into a personalized eye protection suggestion generation module; S52, generating a preliminary eye protection suggestion set according to the user's current health status, including a rest time reminder, screen brightness adjustment suggestions, and eye behavior improvement measures for the user; S=f s (Z,M behavior ,U t ); Among them, S represents the set of eye protection suggestions, f s is the suggestion generation function, Z is the current health feature vector, M behavior For healthy behavior patterns, U t for health status; S53, based on the health risk determination result, screening the preliminary eye protection suggestion set to extract suggestions that meet the current health risk status; S54, optimizing the screened eye protection suggestion set according to the user's current eye environment and personalized needs, and generating a final personalized eye protection suggestion: S personalized =h(S R ,E); Among them, h is the recommended optimization function, E is the user's current environment parameter, S R For eye protection, S personalized Provide personalized eye care suggestions; S55. Output the personalized eye protection suggestions to the intelligent reminder module, and the suggestions include rest time reminders, behavior adjustment measures and environment optimization suggestions.

7. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S6 comprises the following specific steps: S61, inputting the generated personalized eye protection suggestions and health risk determination results into the intelligent reminder module to identify the reminder content that needs to be triggered; S62. Determine the priority of reminders based on the health risk level and the content of the recommendations. The priority is divided into three levels: high, medium and low according to the severity of the health risk and the importance of the recommendations: P priority =γ·R+δ·|S personalized |; Among them, γ is the risk weight, δ is the recommended content weight, |S personalized | is the number of recommendations in the recommendation set, R is the health risk level, P priority The priority of the reminder; S63, selecting an appropriate multi-modal reminder method according to the reminder content, including sound reminder, vibration reminder and visual signal reminder, and the selection of the reminder method is matched according to the user preference and the usage scenario; S64: Generate reminder trigger time and frequency, and calculate appropriate reminder interval time according to health status and reminder priority: Among them, T current is the current time, P priority To remind the priority, T trigger Trigger time for reminder; S65, executing the reminder content through the intelligent reminder module, specifically including issuing a sound signal, triggering vibration and lighting up a visual signal, to remind the user to take corresponding eye protection measures; S66. Record the user's reminder response, including whether the eye protection suggestion is executed and the execution time information.

8. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S7 comprises the following specific steps: S71, inputting the reminder execution result of the intelligent reminder module and the user's response information to the eye protection suggestion into the user interaction interface, and displaying the eye protection suggestion and health data in real time; S72. Display the user's current health status through an interactive interface, including eye temperature, humidity, light intensity, and blinking frequency. All data are updated in real time according to time series. S73, recording the user's feedback on the health advice, including whether the user accepts the advice, the implementation status after acceptance, and the user's manual adjustment behavior record; S74, classifying and arranging the user feedback information to generate a feedback set, wherein the feedback set includes positive feedback and adjustment feedback; S75, comparing the user feedback information with the health behavior pattern and historical data, analyzing the correlation between the feedback and the health trend, and calculating the recommended optimization parameters; S76. Storing the optimized eye protection suggestions in a personalized eye protection suggestion generation module.

9. The intelligent eye health monitoring system based on Arduino+openCV technology according to claim 2, characterized in that: The S8 comprises the following specific steps: S81, inputting the health data set and feedback information set generated by the user during long-term use into the system adaptive learning module for analyzing the user behavior pattern and feedback preference; S82. Combine the health trend data, feature vectors and feedback association parameters, use the learning function to dynamically adjust the health analysis model and reminder strategy of the system, and calculate the optimized model parameters: P model =L(D history ,F,U t ,Z,R); Among them, P model represents the optimized model parameters, L is the online learning algorithm, and D history is the user's long-term health data set, F is the user feedback information set, U t is the health trend data of the user at time t, Z is the user's current health feature vector, and R is the feedback association parameter; S83. updating the health analysis model according to the optimized model parameters, including the health trend prediction model and the health behavior pattern model; S84, dynamically adjusting the monitoring parameters of the sensor, and setting the optimal sensor sampling frequency and data collection range according to the user's historical data and real-time health status; S85, optimizing the personalized eye protection suggestion generation logic, adjusting the weight parameters of the suggestion generation function according to the user feedback preference, and generating an updated suggestion logic; S86. Store the optimized health analysis model and suggestion generation logic in the system memory, and dynamically adjust the reminder content and frequency according to the optimization results.

Images