Naked eye 3D visual health management method and system based on big data, electronic equipment and storage medium

Abstract

The invention belongs to the technical field of eye health management, and discloses a naked eye 3D visual health management method and system based on big data, electronic equipment and a storage medium, and the method comprises the steps: collecting a high-quality eye data set according to the eye physiological structure and behavior habit difference of a user; constructing a health assessment model based on the high-quality eye data set; evaluating the vision state of the user by using the health evaluation model; and generating a health management scheme based on the user vision state. According to the invention, not only can real-time vision state monitoring be provided, but also targeted vision protection suggestions can be provided according to the specific conditions of the user, so that vision health problems can be effectively prevented and managed. In combination with modern science and technology, the method is expected to bring revolutionary progress to the field of vision health management, the life quality of people is improved, and social and economic burdens caused by vision problems are reduced.

Description

Technical Field

[0001] The present invention relates to the technical field of eye health management, and particularly to a naked-eye 3D vision health management method, system, electronic device and storage medium based on big data. Background Art

[0002] Today, with the rapid development of information technology, people's lifestyles have undergone earth-shaking changes, especially the increasing dependence on electronic devices. It has become normal to use electronic screen devices such as computers and smartphones for a long time, which has directly led to the prevalence and younger age of vision health problems such as myopia, dry eye syndrome and visual fatigue. According to statistics, the number of myopia patients globally is increasing at an alarming rate, especially among teenagers and young adults. In addition, due to the lack of effective vision health management and monitoring means, many people are not aware of the severity of their vision problems before they become serious, resulting in the missed best prevention and treatment opportunities.

[0003] Traditional vision detection and health management methods have many limitations. First of all, these methods often rely on regular eye examinations, lacking continuity and real-time nature, and unable to provide immediate feedback and suggestions for users. Secondly, due to the lack of personalized data collection and analysis, these methods cannot fully consider individual differences, such as different eye physiological structures and behavioral habits, resulting in limited universality and effectiveness of vision management programs. In addition, with the development of big data and artificial intelligence technologies, people's demand for intelligent and personalized health management is increasing day by day, expecting to achieve more efficient and accurate vision health monitoring and management through technological means. Summary of the Invention

[0004] In order to solve the above technical problems, the present invention proposes a naked-eye 3D vision health management method and system based on big data, aiming to construct a personalized health assessment model and generate a customized health management plan by collecting and analyzing the differences in users' eye physiological structures and behavioral habits.

[0005] To achieve the above object, the present invention provides a naked-eye 3D vision health management method based on big data, the method comprising:

[0006] Collecting a high-quality eye dataset according to the differences in users' eye physiological structures and behavioral habits;

[0007] Constructing a health assessment model based on the high-quality eye dataset;

[0008] Evaluating the user's vision status by using the health assessment model;

[0009] Generating a health management plan based on the user's vision status.

[0010] Preferably, the method for collecting the high-quality eye dataset includes: according to the differences in the physiological structure and behavioral habits of the user's eyes, using an adaptive threshold method to screen the quality of the collected eye data, judging whether the data is abnormal by comparing it with a preset threshold, and if it is abnormal, starting a correction mechanism to obtain the high-quality eye dataset.

[0011] Preferably, a linear interpolation method is used to correct the collected data:

[0012]

[0013] Among them, P bilink represents the pupil diameter at the moment of blinking; P before represents the pupil diameter at the moment immediately before blinking; P after represents the pupil diameter at the moment immediately after blinking; t before and t after respectively represent the time points of two moments before and after the eye, and t represents the time point at the moment of blinking.

[0014] Preferably, support vector machines, random forests and neural network algorithms are used, combined with expert knowledge rules, to train multiple base classifiers, and an ensemble learning method is used to construct the health assessment model;

[0015] Among them, the support vector machine is used as the first base classifier, adopting a radial basis function kernel, and is used to process the high-dimensional feature space;

[0016] The random forest is used as the second base classifier, and is used to process non-linear relationships and provide a ranking of feature importance;

[0017] The neural network is used as the third base classifier, and is used to capture complex non-linear patterns.

[0018] The present invention also provides a naked-eye 3D visual health management system based on big data. The system is used to implement the above method and includes: a collection module, a construction module, an evaluation module and a generation module;

[0019] The construction module is used to collect a high-quality eye dataset according to the differences in the physiological structure and behavioral habits of the user's eyes;

[0020] The construction module is used to construct a health assessment model based on the high-quality eye dataset;

[0021] The evaluation module is used to evaluate the user's vision status by using the health assessment model;

[0022] The generation module generates a health management plan based on the user's vision status.

[0023] Preferably, the working process of the acquisition module includes: according to the differences in the physiological structure and behavioral habits of the user's eyes, using an adaptive threshold method to screen the quality of the acquired eye data, comparing it with a preset threshold to determine whether the data is abnormal, and if it is abnormal, starting a correction mechanism to obtain the high-quality eye data set.

[0024] Preferably, the method of linear interpolation is used to correct the acquired data:

[0025]

[0026] Among them, P bilink represents the pupil diameter at the moment of blinking; P before represents the pupil diameter at the moment immediately before blinking; P after represents the pupil diameter at the moment immediately after blinking; t before and t after respectively represent the time points of two moments before and after the eye, and t represents the time point of the moment of blinking.

[0027] Preferably, the working process of the construction module includes: using support vector machine, random forest and neural network algorithms, combined with expert knowledge rules, training multiple base classifiers, and using an ensemble learning method to construct the health assessment model;

[0028] Among them, the support vector machine is used as the first base classifier, using a radial basis function kernel to process the high-dimensional feature space;

[0029] The random forest is used as the second base classifier to process non-linear relationships and provide a ranking of feature importance;

[0030] The neural network is used as the third base classifier to capture complex non-linear patterns.

[0031] The present invention also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, the above method is implemented.

[0032] The present invention also provides a computer-readable storage medium, characterized in that the computer-readable storage medium stores a computer program, and when the computer program is executed, the above method is implemented.

[0033] Compared with the prior art, the beneficial effects of the present invention are:

[0034] The present invention can not only provide real-time vision status monitoring, but also offer targeted vision protection suggestions according to the specific conditions of users, thereby effectively preventing and managing vision health problems. By combining modern technologies, the present invention is expected to bring revolutionary progress to the field of vision health management, improve people's quality of life, and reduce the social and economic burdens caused by vision problems. BRIEF DESCRIPTION OF THE DRAWINGS

[0035] To more clearly illustrate the technical solutions of the present invention, the drawings required for use in the embodiments will be briefly introduced below. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can be obtained based on these drawings.

[0036] Figure 1 It is a schematic flowchart of the method according to an embodiment of the present invention;

[0037] Figure 2 It is a schematic structural diagram of an electronic device according to an embodiment of the present invention.

[0039] 1010, processor; 1020, memory; 1030, input / output interface; 1040, communication interface; 1050, bus. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0040] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts shall fall within the protection scope of the present invention.

[0041] It should be noted that unless otherwise defined, the technical terms or scientific terms used in the embodiments of the present disclosure should have the ordinary meaning understood by those of ordinary skill in the art to which the present disclosure belongs. The "first", "second" and similar terms used in the embodiments of the present disclosure do not indicate any order, quantity or importance, but are only used to distinguish different components. The terms such as "including" or "comprising" mean that the elements or items appearing before the term cover the elements or items listed after the term and their equivalents, without excluding other elements or items. The terms such as "connected" or "coupled" are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. The terms such as "upper", "lower", "left", "right" are only used to represent relative positional relationships, and when the absolute position of the object being described changes, the relative positional relationship may also change accordingly.

[0042] To make the above objects, features, and advantages of the present invention more obvious and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0043] Embodiment 1

[0044] As can be seen from the background art, traditional vision detection and health management methods have many limitations. First of all, these methods often rely on regular eye examinations, lacking continuity and real-time nature, and unable to provide immediate feedback and suggestions for users. Secondly, due to the lack of personalized data collection and analysis, these methods cannot fully consider individual differences, such as differences in eye physiological structures and behavioral habits, resulting in limited universality and effectiveness of vision management programs.

[0045] The embodiment of the present invention provides a big data-based naked-eye 3D visual health management method, as Figure 1 shown, the steps include:

[0046] S1. Collect a high-quality eye dataset according to the differences in the user's eye physiological structure and behavioral habits.

[0047] According to the differences in the user's eye physiological structure and behavioral habits, an adaptive threshold method is used to screen the quality of the collected eye data. By comparing with a preset threshold, it is judged whether the data is abnormal. If it is abnormal, a correction mechanism is started to obtain a high-quality eye dataset. If the judgment result shows that the eye data is abnormal, a correction mechanism is started, and a data enhancement algorithm is used to correct the abnormal eye data. After being processed by the correction mechanism, the corrected eye data is obtained and added to the high-quality eye dataset. A clustering algorithm is used to perform clustering analysis on the high-quality eye dataset to obtain the clustering results of different users' eye features. According to the clustering results, the preset threshold in the adaptive threshold method is dynamically adjusted for different categories of users' eye features to improve the accuracy of eye data quality screening.

[0048] Specifically, when obtaining the user's eye data, individual differences need to be considered. For example, the palpebral fissure height, pupil size, and fixation habit, etc. will all affect the data quality. In this embodiment, an infrared camera is used to capture eye images during data collection, and at the same time, information such as the blink frequency, pupil diameter change, and fixation point position is recorded. The blink frequencies of different users vary greatly. For example, some people blink 10 times per minute, while some people may blink more than 20 times, which will affect the continuity of data collection. For the obtained eye data, an adaptive threshold method is used to establish a quality evaluation model. The core of this method lies in dynamically adjusting the threshold according to the real-time statistical characteristics of the data, rather than being fixed.

[0049] For the above-mentioned adaptive threshold algorithm, taking the pupil diameter data as an example, first calculate the average value μ and standard deviation σ of the pupil diameter within a period of time, and then use the average value plus or minus several times the standard deviation as the threshold range. For example, when the average pupil diameter is 4 mm and the standard deviation is 0.5 mm, the set threshold is μ - kσ to μ + kσ, that is, 3 mm to 5 mm. Input the eye data into the model for evaluation and compare it with the preset threshold. If the pupil diameter data of a certain user is lower than 3 mm for a long time, the model will determine that the data is abnormal.

[0050] For example, the system detects that a certain user's pupil diameter remains around 2.5 mm within 10 seconds, which is lower than the set lower limit of 3 mm, and it is marked as abnormal. For abnormal data, start the correction mechanism. The data enhancement algorithm can correct the abnormal data. For example, for the temporary data loss caused by blinking, the interpolation method can be used to estimate the missing value by using the data at the moments before and after the missing data point. If a user blinks at a certain moment, resulting in the missing of pupil diameter data, the pupil diameter data at the two moments before and after the blink can be used to estimate the pupil diameter at the blinking moment through the linear interpolation method. The corrected data is added to the high-quality data set. The formula of the linear interpolation method is as follows:

[0051]

[0052] Among them, P bilink represents the pupil diameter at the blinking moment; P before represents the pupil diameter at the moment before the blink; P after represents the pupil diameter at the moment after the blink; t before and t after represent the time points of the two moments before and after the eye respectively, and t represents the time point of the blinking moment.

[0053] Use the clustering algorithm (K-means is used in this embodiment) to analyze the high-quality data set. According to the two characteristics of the average pupil diameter and blinking frequency of the user, the users are divided into different groups. For example, one group of users has a relatively large average pupil diameter and a relatively low blinking frequency, and another group of users has a relatively small average pupil diameter and a relatively high blinking frequency. In this way, users with similar eye characteristics can be grouped together. Dynamically adjust the threshold according to the clustering results. For example, for the group of users with a relatively large average pupil diameter, the lower limit threshold of the pupil diameter can be appropriately increased, for example, from 3 mm to 3.5 mm. For the group of users with a relatively high blinking frequency, the requirement for data continuity can be appropriately relaxed. The purpose of doing this is to make the threshold more suitable for the characteristics of different user groups and improve the accuracy of data quality evaluation. Moreover, doing so can more finely distinguish the eye characteristics of different user groups, thereby improving the accuracy of data analysis.

[0054] S2. Build a health assessment model based on a high-quality eye dataset.

[0055] Based on the high-quality eye dataset, obtain vision-related indicators such as pupil diameter and fixation point coordinates. Use support vector machine, random forest, and neural network algorithms, combined with expert knowledge rules, to train multiple base classifiers. Adopt an ensemble learning method to build an accurate and reliable health assessment model. Use the support vector machine algorithm to train the first base classifier with feature vectors to obtain the first vision health assessment sub-model. Use the random forest algorithm to train the second base classifier with feature vectors to obtain the second vision health assessment sub-model. Use the neural network algorithm to train the third base classifier with feature vectors to obtain the third vision health assessment sub-model. Use the ensemble learning method to perform weighted fusion on the three vision health assessment sub-models to build the final vision health assessment model. Use test data to evaluate the built vision health assessment model. If the model performance meets the preset threshold, it is determined as the final model; if the model performance does not reach the preset threshold, adjust the model parameters and retrain the model until the performance requirements are met.

[0056] Specifically, the support vector machine (SVM) is used as the first base classifier, which is suitable for processing high-dimensional feature spaces. In this embodiment, the radial basis function (RBF) kernel is selected, and the kernel parameters and penalty coefficients are optimized through cross-validation.

[0057] Since this embodiment considers it a non-linear problem, the expression of the above SVM is as follows:

[0058]

[0059] In the formula, w is the normal vector of the hyperplane; b represents the bias term, ξ i represents the slack variable; C represents the regularization parameter; n represents the number of samples.

[0060] The expression of the RBF kernel is as follows:

[0061] K(x i , x j ) = exp(-γ||x i - x j || 2 )

[0062] Among them, K(x i , x j ) represents the value of the kernel function; i and j represent the indices of the samples; γ represents the parameter of the kernel function.

[0063] As the second base classifier, the random forest can handle non - linear relationships and provide a ranking of feature importance. The number of trees can be set from 100 to 500, and the optimal parameters can be selected through out - of - bag error. Each decision tree in the random forest is trained on a random subset of the data, which can increase the diversity of the model and reduce the risk of overfitting. The prediction result of the random forest is obtained by voting or averaging the prediction results of all decision trees. Its expression is as follows:

[0064]

[0065] Among them, represents the final prediction result of the random forest; y1, y2,..., y T represent the prediction results of each decision tree; T represents the total number of decision trees (set to 100 - 500 in this embodiment); the mode function represents the mode, that is, the category with the most occurrences.

[0066] As the third base classifier, the neural network can capture complex non - linear patterns. It adopts a multi - layer perceptron structure, which includes an input layer, two hidden layers and an output layer, and uses the ReLU activation function and dropout regularization.

[0067] These three algorithms each have their own advantages and can evaluate visual health from different perspectives. The ensemble learning method combines multiple models to improve the overall performance and robustness. In this implementation, the weighted average method is used to allocate weights according to the performance of each model on the validation set. According to the experiment, the accuracies of SVM, random forest and neural network in this embodiment on the validation set are 0.85, 0.82 and 0.88 respectively, and the weights are allocated according to the ratio of 3:2:4.

[0068] Model evaluation is a key step to ensure the reliability of the model. 10 - fold cross - validation is used, and indicators such as accuracy, precision, recall and F1 - score are comprehensively considered. When setting the performance threshold, the sensitivity and specificity of the model are weighed. For example, for visual health screening, recall may be more emphasized to avoid missed diagnoses. If the model performance does not meet the standard, the model can be optimized by adjusting parameters, increasing training data or trying new feature engineering methods. This method of multi - model fusion can make full use of the advantages of different algorithms and improve the accuracy and reliability of visual health assessment. Through continuous iterative optimization, the finally constructed model will be able to provide a powerful auxiliary tool for ophthalmic diagnosis.

[0069] S3. Use the health assessment model to evaluate the user's visual status.

[0070] Input the collected user eye data into the health assessment model to evaluate the user's vision status. In this embodiment, a user is selected with a naked eye vision of 4.7 for the left eye and 4.8 for the right eye, diopter of -3.0D and -2.5D respectively, and normal intraocular pressure; the average daily usage time of the electronic screen exceeds 8 hours, and the user often uses the mobile phone after turning off the lights at night, and the environmental light intensity is often lower than 50 lux. Input these data into the previously constructed health assessment model to comprehensively evaluate the user's vision health status.

[0071] The result shows that the vision condition belongs to mild myopia, and the long-term use of the electronic screen and the poor light environment pose a greater threat to his vision health. And this user is a young office worker and is more inclined to accept simple and fast eye protection methods.

[0072] S4. Generate a health management plan based on the user's vision status.

[0073] Since Xiaoming's vision condition is lower than the preset threshold (such as 5.0), content for vision exercise needs to be added to the plan.

[0074] Considering the user's preference, traditional eye exercises will not be recommended, but some eye exercise methods more in line with the modern life rhythm will be recommended, such as "far and near alternating focus training": let the user first gaze at a distant object (such as a building 20 meters away) for 20 seconds, and then quickly shift the line of sight to a nearby object (such as the mobile phone in hand) for 20 seconds, and repeat this cycle multiple times, and perform 3 - 5 groups every day. At the same time, since the user's eye usage time exceeds the preset threshold (such as 6 hours), a function of timed rest reminder will be added to the plan. For example, every 45 minutes, it is recommended that the user take a 5-minute break with eyes closed or look into the distance. In addition, considering that the light intensity of the user's environment is often lower than the preset threshold (such as 100 lux), suggestions for adjusting the environmental light need to be added to the plan. For example, it is recommended that the user turn on the table lamp when using the mobile phone at night and adjust the brightness of the table lamp to 300 - 500 lux to provide sufficient and appropriate background light. If the light intensity of the user's usage environment is lower than the preset threshold, suggestions for adjusting the environmental light will be added to the visual health management plan.

[0075] The technical solution of the present invention can not only provide real-time vision status monitoring, but also provide targeted vision protection suggestions according to the specific situation of the user, so as to effectively prevent and manage vision health problems. By combining modern technologies, the present invention is expected to bring revolutionary progress to the field of vision health management, improve people's quality of life, and reduce the social and economic burden caused by vision problems.

[0076] It should be noted that the method of the embodiments of the present disclosure can be executed by a single device, such as a computer or a server. The method of this embodiment can also be applied to a distributed scenario and completed by multiple devices cooperating with each other. In this case of a distributed scenario, one of the multiple devices can only execute one or more steps of the method of the embodiments of the present disclosure, and these multiple devices will interact with each other to complete the described method.

[0077] It should be noted that some embodiments of the present disclosure have been described above. Other embodiments are within the scope of the appended claims. In some cases, it should be understood that the magnitudes of the sequence numbers of the steps in the above embodiments do not mean the order of execution. The execution order of each process should be determined by its function and internal logic, and should not constitute any limitation to the implementation process of the embodiments of the present invention. The actions or steps recited in the claims can be executed in an order different from that in the above embodiments and still achieve the desired results. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In certain embodiments, multitasking and parallel processing are also possible or may be advantageous.

[0078] Embodiment 2

[0079] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure further provides a big data-based naked-eye 3D vision health management system, including: a collection module, a construction module, an evaluation module, and a generation module; the construction module is used to collect a high-quality eye data set according to the differences in the user's eye physiological structure and behavior habits; the construction module is used to construct a health evaluation model based on the high-quality eye data set; the evaluation module is used to evaluate the user's vision status by using the health evaluation model; the generation module generates a health management plan based on the user's vision status.

[0080] Among them, the working process of the collection module includes: according to the differences in the user's eye physiological structure and behavior habits, using an adaptive threshold method to screen the quality of the collected eye data, and by comparing with a preset threshold, judging whether the data is abnormal. If it is abnormal, a correction mechanism is started to obtain a high-quality eye data set.

[0081] The collected data is corrected by using the method of linear interpolation:

[0082]

[0083] Among them, P bilink represents the pupil diameter at the moment of blinking; P before represents the pupil diameter at the moment immediately before blinking; P after represents the pupil diameter at the moment immediately after blinking; t before and tafter respectively represent the time points before and after the eyes, and t represents the time point of the blink moment.

[0084] The workflow of the building block includes: using support vector machine, random forest and neural network algorithms, combining with expert knowledge rules, training multiple base classifiers, and using the ensemble learning method to build a health assessment model; among them, the support vector machine is used as the first base classifier, adopting the radial basis function kernel to process the high-dimensional feature space; the random forest is used as the second base classifier to process the non-linear relationship and provide the feature importance ranking; the neural network is used as the third base classifier to capture complex non-linear patterns. The system of the above embodiment is used to implement the corresponding big data-based naked-eye 3D vision health management method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0085] It should be noted that the above big data-based naked-eye 3D vision health management system is embodied in the form of functional units. The term "module" here can be implemented in the form of software and / or hardware, and no specific limitation is made thereto.

[0086] For example, the "module" can be a software program, a hardware circuit or a combination of the two that implements the above functions. The hardware circuit may include an application specific integrated circuit (ASIC), an electronic circuit, a processor (such as a shared processor, a proprietary processor or a group of processors, etc.) for executing one or more software or firmware programs, and a memory, a merged logic circuit and / or other suitable components that support the described functions.

[0087] Embodiment III

[0088] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides an electronic device, including a memory, a processor, and a computer program stored on the memory and executable on the processor. When the processor executes the program, it implements the big data-based naked-eye 3D vision health management method described in any of the above embodiments.

[0089] Figure 2 Fig. shows a more specific schematic diagram of the hardware structure of the electronic device provided in this embodiment. The device may include: a processor 1010, a memory 1020, an input / output interface 1030, a communication interface 1040, and a bus 1050. Among them, the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040 are communicatively connected to each other inside the device through the bus 1050.

[0090] The processor 1010 can be implemented in the form of a general-purpose CPU (Central Processing Unit), a microprocessor, an Application Specific Integrated Circuit (ASIC), or one or more integrated circuits, etc., and is used to execute relevant programs to implement the technical solutions provided in the embodiments of this specification.

[0091] The memory 1020 can be implemented in the form of a ROM (Read Only Memory), a RAM (Random Access Memory), a static storage device, a dynamic storage device, etc. The memory 1020 can store an operating system and other application programs. When implementing the technical solutions provided in the embodiments of this specification through software or firmware, the relevant program codes are stored in the memory 1020 and are called and executed by the processor 1010.

[0092] The input / output interface 1030 is used to connect to the input / output module to realize information input and output. The input / output module can be configured as a component in the device (not shown in the figure) or can be externally connected to the device to provide corresponding functions. Among them, the input device can include a keyboard, a mouse, a touch screen, a microphone, various sensors, etc., and the output device can include a display, a speaker, a vibrator, an indicator light, etc.

[0093] The communication interface 1040 is used to connect to a communication module (not shown in the figure) to realize the communication interaction between this device and other devices. Among them, the communication module can realize communication through a wired method (such as USB (Universal Serial Bus), network cable, etc.) or can also realize communication through a wireless method (such as a mobile network, WIFI (Wireless Fidelity), Bluetooth, etc.).

[0094] The bus 1050 includes a path for transmitting information between various components of the device (such as the processor 1010, the memory 1020, the input / output interface 1030, and the communication interface 1040).

[0095] It should be noted that although only the processor 1010, the memory 1020, the input / output interface 1030, the communication interface 1040, and the bus 1050 are shown in the above device, in the specific implementation process, this device may also include other components necessary for normal operation. In addition, those skilled in the art can understand that the above device may also only include the components necessary to implement the solutions of the embodiments of this specification and does not necessarily include all the components shown in the figure.

[0096] The system of the above embodiment is used to implement the corresponding big data-based naked-eye 3D vision health management method in any of the foregoing embodiments, and has the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0097] Embodiment 4

[0098] Based on the same inventive concept, corresponding to the method of any of the above embodiments, the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions for causing the computer to execute the big data-based naked-eye 3D vision health management method as described in any of the above embodiments.

[0099] The computer-readable medium of this embodiment includes permanent and non-permanent, removable and non-removable media, and information storage can be implemented by any method or technology. The information can be computer-readable instructions, data structures, program modules, or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technologies, compact disc read-only memory (CD-ROM), digital versatile disc (DVD) or other optical storage, magnetic cassette tapes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium that can be used to store information accessible by a computing device.

[0100] The computer instructions stored in the storage medium of the above embodiment are used to cause the computer to execute the big data-based naked-eye 3D vision health management method as described in any of the above embodiments, and have the beneficial effects of the corresponding method embodiments, which will not be elaborated here.

[0101] Those of ordinary skill in the art should understand that the discussion of any of the above embodiments is only exemplary and is not intended to imply that the scope of the present disclosure (including the claims) is limited to these examples; under the concept of the present disclosure, the technical features in the above embodiments or different embodiments can also be combined, the steps can be implemented in any order, and there are many other variations in different aspects of the embodiments of the present disclosure as described above, which are not provided in detail for the sake of brevity.

[0102] In addition, for simplicity of explanation and discussion, and so as not to make the embodiments of the present disclosure difficult to understand, well-known power / ground connections to integrated circuit (IC) chips and other components may or may not be shown in the provided drawings. Further, the devices may be shown in block diagram form in order to avoid making the embodiments of the present disclosure difficult to understand, and this also takes into account the fact that details of the implementation of these block diagram devices are highly dependent on the platform on which the embodiments of the present disclosure are to be implemented (i.e., these details should be entirely within the understanding of those skilled in the art). In cases where specific details (such as circuits) are set forth to describe exemplary embodiments of the present disclosure, it will be apparent to those skilled in the art that the embodiments of the present disclosure may be practiced without these specific details or with variations of these specific details. Accordingly, these descriptions should be regarded as illustrative rather than restrictive.

[0103] Although the present disclosure has been described in connection with specific embodiments thereof, many alternatives, modifications, and variations of these embodiments will be apparent to those of ordinary skill in the art based on the foregoing description. For example, other memory architectures (such as dynamic RAM (DRAM)) may be used with the embodiments discussed.

[0104] Therefore, the units of the examples described in the embodiments of the present application can be implemented in electronic hardware, or in a combination of computer software and electronic hardware. Whether these functions are executed in a hardware or software manner depends on the specific application and design constraints of the technical solution. A person skilled in the art may use different methods for each specific application to implement the described functions, but such implementation should not be considered to exceed the scope of the present application.

[0105] The embodiments of the present disclosure are intended to cover all such alternatives, modifications, and variations that fall within the broad scope of the appended claims. Therefore, any omissions, modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the embodiments of the present disclosure shall be included within the protection scope of the present disclosure.

Claims

1. A naked-eye 3D vision health management method based on big data, characterized in that, The method includes: Collecting a high-quality eye dataset according to the differences in the user's eye physiological structure and behavior habits; Constructing a health assessment model based on the high-quality eye dataset; Evaluating the user's vision status using the health assessment model; Generating a health management plan based on the user's vision status.

2. The method for naked-eye 3D vision health management based on big data according to claim 1, wherein, The method for collecting the high-quality eye dataset includes: according to the differences in the user's eye physiological structure and behavior habits, using an adaptive threshold method to screen the quality of the collected eye data, comparing it with a preset threshold to determine whether the data is abnormal, and if it is abnormal, starting a correction mechanism to obtain the high-quality eye dataset.

3. The method for naked-eye 3D vision health management based on big data according to claim 2, wherein Using the method of linear interpolation to correct the collected data: Among them, P bilink represents the pupil diameter at the moment of blinking; P before represents the pupil diameter at the moment immediately before blinking; P after represents the pupil diameter at the moment immediately after blinking; t before and t after respectively represent the time points of two moments before and after the eye, and t represents the time point at the moment of blinking.

4. The method for naked-eye 3D vision health management based on big data according to claim 1, wherein Using support vector machines, random forests, and neural network algorithms, combined with expert knowledge rules, training multiple base classifiers, and using an ensemble learning method to construct the health assessment model; Among them, the support vector machine is used as the first base classifier, using a radial basis function kernel to process the high-dimensional feature space; The random forest is used as the second base classifier to process non-linear relationships and provide a ranking of feature importance; The neural network is used as the third base classifier to capture complex non-linear patterns.

5. A naked-eye 3D vision health management system based on big data, the system is used to implement the method described in any one of claims 1-4, characterized in that, Including: A collection module, a construction module, an evaluation module, and a generation module; The construction module is used to collect a high-quality eye dataset according to the differences in the user's eye physiological structure and behavior habits; The construction module is used to construct a health assessment model based on the high-quality eye dataset; The evaluation module is used to evaluate the user's vision status using the health assessment model; The generation module generates a health management plan based on the user's vision status.

6. The naked-eye 3D vision health management system based on big data according to claim 5, characterized in that, The working process of the collection module includes: according to the differences in the user's eye physiological structure and behavior habits, using an adaptive threshold method to screen the quality of the collected eye data, comparing it with a preset threshold to determine whether the data is abnormal, and if it is abnormal, starting a correction mechanism to obtain the high-quality eye dataset.

7. The naked-eye 3D vision health management system based on big data according to claim 6, wherein, Using the method of linear interpolation to correct the collected data: Among them, P bilink represents the pupil diameter at the moment of blinking; P before represents the pupil diameter at the moment immediately before blinking; P after represents the pupil diameter at the moment immediately after blinking; t before and t after represent the time points of two moments before and after the eye respectively, and t represents the time point at the moment of blinking.

8. The naked-eye 3D vision health management system based on big data according to claim 5, characterized in that, The working process of the construction module includes: using support vector machines, random forests, and neural network algorithms, combined with expert knowledge rules, training multiple base classifiers, and using an ensemble learning method to construct the health assessment model; Among them, the support vector machine is used as the first base classifier, using a radial basis function kernel to process the high-dimensional feature space; The random forest is used as the second base classifier to process non-linear relationships and provide a ranking of feature importance; The neural network is used as the third base classifier to capture complex non-linear patterns.

9. An electronic device, characterized in that, Including a memory, a processor, and a computer program stored on the memory and executable on the processor, and when the processor executes the program, the method described in any one of claims 1 to 4 is implemented.

10. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, and when the computer program is executed, the method described in any one of claims 1 to 4 is implemented.

Images