Artificial intelligence screening and predicting system and device for presbyopia

Abstract

The invention discloses a presbyopia artificial intelligence screening and prediction method and system, and relates to the technical field of presbyopia prediction. The system comprises a ciliary muscle suitable exercise user screening module, a wearer information acquisition module, a wearer presbyopia analysis module, a wearer wearing parameter evaluation module, a wearer effect evaluation module, a display terminal and a database. The accuracy of analysis of presbyopia caused by ciliary muscles is improved, eye risks of presbyopia personnel are reduced, risks are avoided for follow-up treatment, accurate customers are reduced for a presbyopia user platform, the follow-up work development of the presbyopia user platform is facilitated, the wearing parameters of the wearing personnel are evaluated, personalization is high, and the method is suitable for popularization and application. The method is more suitable for the actual situation of the user, avoids the risk that the amount of exercise is too large or insufficient, improves the efficiency of presbyopia exercise of the user, and guarantees the effect of presbyopia recovery of the user.

Description

Technical Field

[0001] The present invention relates to the field of presbyopia prediction technology, and in particular to an artificial intelligence screening and prediction system and device for presbyopia. Background Art

[0002] Presbyopia in humans is mainly caused by insufficient visual adjustment ability, which used to appear around the age of 50. Nowadays, with the popularity of smart terminals, many people use their eyes for a long time at close range due to using computers for work, using mobile phones, watching short videos, etc. This has led to many people developing presbyopia earlier and at a younger age. More and more people have begun to experience presbyopia around the age of 40.

[0003] Close-up use of the eyes leads to ciliary muscle stiffness, which has gradually become one of the main factors of early presbyopia. For such patients, we can use equipment to exercise the ciliary muscles to improve and delay presbyopia. The earlier the exercise is performed, the more significant the effect of improving and delaying presbyopia will be. Therefore, it is extremely necessary to predict and exercise presbyopia patients.

[0004] The prior art, such as the invention application patent with the announcement number: CN111973412A, discloses a training system for improving naked eye vision. The invention uses the training glasses device body as the training carrier; the main control system of the training glasses device body control circuit board is installed with a control software unit programmed based on the Gabor function theory; the control software unit includes a timing subunit and an output subunit; the output subunit is divided into three positive gears and three negative gears for output, and the refractive power of the vision is changed by 0.25D for each gear movement of the movable lens toward the front side end and the rear side end. The control software of the invention can control the formation of different focal lengths between the movable lens and the fixed lens of the training glasses device body, and each gear movement is completed in a different time, so that the motor reduction mechanism can work under stepless speed regulation, and the eyes can be effectively trained in different focal depths during training, so that the trainee's brain has the ability to process images, and when actually viewing objects with naked eyes, objects can be clearly seen within the focal depth range where objects can be clearly seen, providing technical support for the recovery of trainees.

[0005] Prior art, such as the invention patent application with announcement number: CN111973412B, discloses a training device for restoring vision, which includes: a display component, which is fixedly arranged and intersecting with a preset line of sight; a corrective lens, which is arranged at a position orthogonal to the line of sight and closer to the starting point of the line of sight than the display component; a detection component, which is used to detect changes in the trainee's eye movements or changes in the brain waves of the trainee's brain; and a control component, which is connected to the display component and the detection component and can adjust the visual changes of the display component according to changes in the eye movements or changes in the brain waves of the brain. The training device of the utility model adjusts the visual changes of the display component in real time according to the trainee's observation of changes in the eye movements or changes in the brain waves of the display component, so as to achieve effective training of the trainee's eye muscles, thereby stimulating the flexibility of eye muscle coordination and achieving an ideal vision restoration effect.

[0006] In combination with the above scheme, it can be found that there are still certain defects in the prediction and training of presbyopia in the existing technology, which are specifically reflected in the following aspects: (1) Since early presbyopia does not have a significant impact on people's lives, there are also many patients with low myopia. When using their eyes at close range, the degree of myopia will offset the impact of presbyopia. When using their eyes at close range, they only need to take off their myopia glasses, so they do not realize that they have presbyopia. Most of the existing technologies believe that long-term use of terminal devices leads to early presbyopia, and lack attention to the prediction of people's presbyopia. For example, living environment, genetic conditions and disease conditions all have a certain impact on people's presbyopia caused by ciliary muscles. The neglect of this aspect in the existing technology reduces the accuracy of presbyopia analysis caused by ciliary muscles, and it is difficult to provide follow-up support for people with presbyopia caused by ciliary muscles, thereby increasing the eye risks of presbyopic people and increasing the difficulty of subsequent treatment.

[0007] (2) There are few presbyopia devices customized for users in the prior art for ciliary muscle training. At the same time, there is a lack of attention to judging whether a patient is suitable for using ciliary muscle training to improve presbyopia. It is difficult to fit the actual situation of the user. The lack of targeted exercise plans leads to the risk of excessive or insufficient exercise, thereby increasing the risk of injury or failing to achieve the exercise effect, which in turn affects the efficiency of the user's presbyopia exercise and makes it difficult to ensure the effect of the user's presbyopia recovery, reducing the value of the user's presbyopia exercise and increasing additional medical expenses to a certain extent. Summary of the invention

[0008] The purpose of the present invention is to provide an artificial intelligence screening and prediction method and system for presbyopia, which solves the problems existing in the background technology.

[0009] To solve the above problems, we conducted in-depth research on the principles of human vision and the factors affecting presbyopia, and conducted statistical analysis on a large number of presbyopic people.

[0010] 1. Principle of human eye vision:

[0011] The lens can be understood as a convex lens. According to the Gaussian imaging formula in optics:

[0012] 1 / f = 1 / u + 1 / v, where f is the focal length (positive for convex and negative for concave), u is the object distance, and v is the image distance (positive for real and negative for virtual).

[0013] Normally, the image distance v of our human eye (i.e., the distance between the lens and the retina) is fixed. Therefore, to see objects at different distances, that is, when the object distance u changes, we need to change the focal length f of the lens, which is changed by the deformation of the lens.

[0014] When looking at nearby objects, the ciliary muscle increases the thickness of the lens to reduce the focal length f. And if we keep looking at nearby objects for a long time, the ciliary muscle remains fixed and rigid for a long time, which leads to a decrease in accommodation ability.

[0015] 2. Relationship between the strength of the ciliary muscle, the hardness of the lens, and the deformation of the lens:

[0016] The lens can be understood as an elastic sphere. According to the formula for calculating the bulk modulus of an object in material mechanics and solid physics:

[0017]

[0018] K: Bulk modulus

[0019] ΔP: Change in pressure (positive when the pressure increases and negative when it decreases).

[0020] ΔV: Change in volume (negative when it decreases and positive when it increases).

[0021] V0: Initial volume

[0022] From the above formula, we can define: |ΔV / V0| = V, representing the deformation amount required for the lens to look at nearby objects. Define the maximum natural adjustment pressure of the ciliary muscle as P.

[0023] Then when P / K < V, it is insufficient accommodation ability and presbyopia occurs.

[0024] Under normal circumstances, K increases continuously with age, and P is less affected by age.

[0025] For people who use their eyes at close range for a long time, the ciliary muscle becomes rigid, resulting in a decrease in its maximum strength P. So presbyopia appears earlier.

[0026] 3. We conduct statistical analysis on a large number of presbyopic people.

[0027] Table of the situation of presbyopic people:

[0028] According to a large number of statistical laws:

[0029] a. Daily eye use time is the main factor affecting premature presbyopia.

[0030] b. Myopia degree, outdoor sports activities, etc. also have a certain impact on premature presbyopia.

[0031] c. Genetic factors, living environment and other factors mainly affect the age and degree of normal presbyopia.

[0032] The results of these presbyopic people using ciliary muscle training tools are shown in the table below:

[0033]

[0034] According to a large number of statistical laws:

[0035] a. The longer you use your eyes at close range every day and the younger you are, the better the ciliary muscle training effect will be and the longer it will last.

[0036] According to the above principle exploration and statistical analysis, the present invention adopts the following technical scheme: providing an artificial intelligence screening and prediction method for presbyopia, including a physical explanation of the principle of presbyopia based on optical principles and mechanical principles, establishing an algorithm model based on the characteristics of a large number of presbyopic people and combining statistical laws, predicting the effect of improving and delaying presbyopia through ciliary muscle training, thereby screening out users who are suitable for training their ciliary muscles.

[0037] The second aspect of the present invention provides an artificial intelligence screening and prediction system for presbyopia, including: a screening module for users suitable for ciliary muscle training, which is used to collect basic information uploaded by several users, evaluate the ciliary muscle presbyopia influence coefficients corresponding to the several users, and screen out users suitable for ciliary muscle training, and invite each user suitable for ciliary muscle training to take a test, and record the users who accept the test invitation as wearing users.

[0038] The wearer information acquisition module is used to obtain the basic information uploaded by the wearer, and the wearer wears the presbyopia training device.

[0039] The wearer's presbyopia analysis module is used to obtain the wearer's ciliary muscle presbyopia influence coefficient and analyze the wearer's expected recovery effect evaluation index.

[0040] The wearer's wearing parameter evaluation module is used to evaluate the wearer's corresponding wearing parameters based on the wearer's ciliary muscle presbyopia influence coefficient.

[0041] The wearer effect evaluation module is used to obtain the wearer's eye parameters during each exercise after the wearer has completed a specified period of training, and to determine whether the wearer has entered the enhanced exercise stage. If the wearer has entered the enhanced exercise stage, automatic adjustments will be made when the wearer is performing enhanced exercise, and after the wearer has completed a specified period of enhanced exercise, the wearer's eye parameters during each enhanced exercise will be obtained to determine the wearer's corresponding enhanced exercise eye presbyopia correction value.

[0042] The display terminal is used to display the wearing parameters and exercise enhancement parameters corresponding to the wearer, and the wearer's exercise-enhanced eye presbyopia correction value, and provide voice prompts when the wearer is exercising.

[0043] The beneficial effects of the present invention are:

[0044] (1) In the present invention, in the ciliary muscle training suitable user screening module, based on the basic information uploaded by several users, such as living environment, genetic conditions and disease conditions, the ciliary muscle presbyopia influence coefficients corresponding to several users are first evaluated, so as to screen the users suitable for ciliary muscle training, which makes up for the defect of neglecting this aspect in the prior art, improves the accuracy of presbyopia analysis caused by ciliary muscle, provides follow-up support for people with presbyopia caused by ciliary muscle, reduces the eye risks of presbyopic people, avoids risks for subsequent treatment, and also narrows down the precise customers for the presbyopia user platform, thereby facilitating the subsequent work of the presbyopia user platform.

[0045] (2) In the wearer's presbyopia analysis module, the present invention evaluates the wearer's ciliary muscle presbyopia influence coefficient and the estimated recovery effect evaluation index based on the wearer's basic information and eye information, thereby laying a foundation for the subsequent analysis of the wearer's wearing parameters.

[0046] (3) In the wearer's wearing parameter evaluation module, the present invention evaluates the wearer's wearing parameters according to the wearer's ciliary muscle presbyopia influence coefficient, which is highly personalized. At the same time, it determines whether the patient is suitable for using ciliary muscle training to improve presbyopia, which makes up for the deficiency of the existing technology that there are few ciliary muscle training devices customized for users, is more in line with the user's actual situation, avoids the risk of excessive or insufficient exercise, thereby reducing the risk of injury, reduces the complexity of exercise, greatly improves the exerciser's persistence time, improves the efficiency of the user's presbyopia exercise, ensures the effect of the user's presbyopia recovery, ensures the value of the user's presbyopia exercise, and reduces additional medical expenses to a certain extent. BRIEF DESCRIPTION OF THE DRAWINGS

[0047] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0048] Figure 1 This is a prediction chart of the effect of improving presbyopia accommodation through appropriate ciliary muscle training.

[0049] Figure 2 It is a schematic diagram of the system structure connection of the present invention.

[0050] Figure 3 This is the maximum force curve of the ciliary muscle. DETAILED DESCRIPTION

[0051] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0052] Reference Figure 1 As shown, the first aspect of the present invention provides an artificial intelligence screening and prediction method for presbyopia, which collects and summarizes the characteristics of presbyopic users and establishes a prediction model.

[0053] In a specific embodiment, the basic characteristic parameters of several users are processed. For age, it can be normalized to the interval [0, 1] through numerical normalization, for example, 35 years old and below is 1, 55 years old and above is 0, and the gradient increases between the two. For sports conditions, the frequency of ball sports and outdoor sports is mainly processed through numerical normalization and normalized to the interval [0, 1]. For example, according to daily, frequent, occasional, rarely, never, the gradient increases from 0 to 1. For the latitude of residence, it can be normalized to the interval [0, 1] through binary features, for example, the poles are 0, the equator is 1, and the gradient increases between the two.

[0054] The disease data of several users are processed. For each disease type, it can be quantified into a value in the interval [0, 1] through binary features. For example, if there is a disease type that is the same as each eye-related disease, the binary feature value is recorded as 1, otherwise it is recorded as 0. Similarly, each surgical type and each medication can also be processed through numerical normalization.

[0055] The eye usage information of several users is processed. For the close-range eye usage time, it can be normalized to the interval [0, 1] through numerical normalization, for example, 0 degree is 0, 1000 degrees is 1, and the gradient between the two increases. Similarly, the degree of myopia can also be processed through numerical normalization.

[0056] The genetic information of several users is processed, and the presbyopia feature value of each family member can be quantified into a value in the interval [0, 1] through a binary feature. For example, if the presbyopia feature values ​​of all family members are 0, the binary feature value is recorded as 0. If the presbyopia feature values ​​of all family members are 1, the binary feature value is recorded as 1, and the gradient between the two increases.

[0057] The characteristic values ​​of each data uploaded by several users are summarized, and combined with the influence weight factors of each data stored in the database, the characteristic values ​​of each data uploaded by several users are multiplied by the influence weight factors, and then accumulated to obtain the ciliary muscle presbyopia influence coefficients corresponding to several users.

[0058] It should be noted that the specific screening method for screening out users suitable for ciliary muscle training is: comparing the ciliary muscle presbyopia influence coefficients corresponding to several users with a predefined ciliary muscle presbyopia influence coefficient threshold; if the ciliary muscle presbyopia influence coefficient corresponding to a user is greater than or equal to the ciliary muscle presbyopia influence coefficient threshold, then the user is recorded as a user suitable for ciliary muscle training, and the users suitable for ciliary muscle training are obtained.

[0059] In the screening module for users suitable for ciliary muscle training, the present invention first evaluates the ciliary muscle presbyopia influence coefficients corresponding to several users based on basic information uploaded by several users, such as living environment, genetic conditions and disease conditions, so as to screen users suitable for ciliary muscle training, which makes up for the defect of neglecting this aspect in the prior art, improves the accuracy of presbyopia analysis caused by ciliary muscle, provides follow-up support for people with presbyopia caused by ciliary muscle, reduces the eye risks of presbyopic people, avoids risks for subsequent treatment, and at the same time narrows down the precise customers for the presbyopic user platform, thereby facilitating the subsequent work of the presbyopic user platform.

[0060] Reference Figure 1 and Figure 2 As shown, the second aspect of the present invention provides an artificial intelligence screening and prediction system for presbyopia, including: a screening module for users suitable for ciliary muscle training, used to collect basic information uploaded by several users, evaluate the ciliary muscle presbyopia influence coefficients corresponding to the several users, and screen out users suitable for ciliary muscle training, and invite each user suitable for ciliary muscle training for a test, and record the users who accept the test invitation as wearing users.

[0061] Among them, the maximum strength of the ciliary muscle is roughly as follows Figure 3The middle curve shows that the gray represents normal, and the red represents long-term close-up use of the eyes.

[0062] The wearer information acquisition module is used to obtain the basic information uploaded by the wearer, and collect real-time feedback on eye parameters after the wearer wears the wearer for presbyopia training.

[0063] It should be noted that the basic information uploaded by the wearer includes various collection forms such as online questionnaires and intelligent customer service Q&A.

[0064] The wearer's presbyopia analysis module is used to obtain the wearer's ciliary muscle presbyopia influence coefficient and analyze the wearer's expected recovery effect evaluation index.

[0065] It should be noted that the specific analysis method for analyzing the wearer's expected recovery effect evaluation index is as follows: basic information of each sample person is obtained from the database, which is consistent with the analysis method of the ciliary muscle presbyopia influence coefficient corresponding to a number of users, and the ciliary muscle presbyopia influence coefficient of each sample person is obtained by analysis, and each sample person with the same ciliary muscle presbyopia influence coefficient as the wearer is recorded as a reference sample person, so as to obtain the reference sample persons corresponding to the wearer.

[0066] The recovery effect value corresponding to each sample person is obtained from the database, and the recovery effect value corresponding to each reference sample person corresponding to the wearer is obtained, and the average is processed to obtain the recovery effect evaluation index corresponding to the wearer.

[0067] It should also be added that the recovery effect value corresponding to each sample person is specifically the recovery effect value uploaded by each sample person after training and evaluation by professionals, and the value range of the recovery effect value is [0, 1].

[0068] In the wearer's presbyopia analysis module, the present invention obtains the wearer's ciliary muscle presbyopia influence coefficient and the expected recovery effect evaluation index, thereby laying a foundation for the subsequent analysis of the wearer's wearing parameters.

[0069] The wearer's wearing parameter evaluation module is used to evaluate the wearer's corresponding wearing parameters based on the wearer's ciliary muscle presbyopia influence coefficient.

[0070] In a specific embodiment of the present invention, the wearing parameters corresponding to the wearer are evaluated according to the ciliary muscle presbyopia influence coefficient of the wearer, and the specific analysis method is: based on the ciliary muscle presbyopia influence coefficient of the wearer Combined with the reference ciliary muscle presbyopia influence coefficient stored in the database The initial refractive index Z' and initial suitable training time T' of the corresponding optical lens are used to evaluate the initial refractive index of the corresponding optical lens for the wearer. and initial suitable exercise duration

[0071] Obtain the environmental adjustment parameters of the wearer, where the environmental adjustment parameters include the light intensity in each direction of the glasses, obtain the appropriate display brightness corresponding to each light intensity from the database, filter the appropriate display brightness in each direction of the glasses, and use it as the appropriate adjustment brightness L in each direction of the glasses worn by the wearer p , where p is the number of each direction, p = 1, 2, ..., q, and q is any integer greater than 2.

[0072] According to the appropriate brightness adjustment of the wearer's glasses in each direction, the initial appropriate exercise time of the wearer is corrected to obtain the appropriate exercise time T = T 0 +T″*μ, μ is the brightness stability value of the glasses worn by the wearer, Where L p is the appropriate adjusted brightness of the glasses worn by the wearer in the p-1th direction, and T″ is the corrected training time corresponding to the unit brightness stability value stored in the database.

[0073] According to the initial refractive index of the optical lens corresponding to the wearer, the appropriate exercise time and the appropriate adjustable brightness in each direction of wearing the glasses, the wearing parameters corresponding to the wearer are summarized and obtained.

[0074] In the wearer's wearing parameter evaluation module, the present invention evaluates the wearer's wearing parameters according to the wearer's ciliary muscle presbyopia influence coefficient, which is highly personalized and judges whether the patient is suitable for presbyopia improvement through ciliary muscle training. This makes up for the deficiency of the existing technology that there are few presbyopia devices for ciliary muscle training that are customized for users, is more in line with the user's actual situation, avoids the risk of excessive or insufficient exercise, thereby reducing the risk of injury, reduces the complexity of exercise, greatly improves the exerciser's persistence time, improves the user's presbyopia exercise efficiency, ensures the effect of the user's presbyopia recovery, ensures the value of the user's presbyopia exercise, and reduces additional medical expenses to a certain extent.

[0075] The wearer effect evaluation module is used to evaluate the improvement effect and maintenance time of the user's accommodation ability after training, and to guide the subsequent training intervals and duration. At the same time, after the wearer has completed a specified period of training, the above evaluation results are corrected according to the wearer's eye parameters before and after each exercise. At the same time, after the wearer has completed a specified period of training, the wearer's eye parameters before and after each exercise are obtained, and it is judged whether the wearer has entered the enhanced exercise stage. If the wearer has entered the enhanced exercise stage, it will automatically adjust when the wearer is exercising, and after the wearer has completed a specified period of enhanced exercise, the wearer's eye parameters in each enhanced exercise are obtained to judge the wearer's corresponding enhanced exercise eye presbyopia correction value.

[0076] In a specific embodiment of the present invention, the accommodative power improvement effect and maintenance time are evaluated, and the specific method is: according to the basic parameters of the wearer, the eye parameters of each exercise and the sample data, the wearer's presbyopia constraint parameters are analyzed, and the evaluation maintenance time is taken as the x-axis, and the accommodative power improvement effect is taken as the y-axis, and a training effect prediction curve of the wearer is fitted.

[0077] The specific method for judging whether the wearer has entered the enhanced exercise stage is as follows: obtaining the eye parameters of the wearer during each exercise, analyzing the eye presbyopia constraint parameters of the wearer during each exercise, and fitting a straight line of the wearer's eye presbyopia constraint parameters with each exercise as the x-axis and the eye presbyopia constraint parameters as the y-axis to obtain the slope of the wearer's eye presbyopia constraint parameter straight line.

[0078] It should be noted that based on the eye parameters of the wearer during each exercise and combined with the method of presbyopia analysis in the prior art, the wearer's presbyopia constraint parameters during each exercise are evaluated, wherein the eye parameters include but are not limited to accommodation power, refractive power, intraocular pressure and axial length.

[0079] The slope of the wearer's presbyopia constraint parameter straight line is compared with the qualified slope interval of the eye presbyopia constraint parameter straight line stored in the database, and the wearer's eye presbyopia constraint parameter in the last exercise is compared with the predefined eye presbyopia constraint parameter threshold. If the slope of the wearer's eye presbyopia constraint parameter straight line is within the qualified slope interval of the eye presbyopia constraint parameter straight line, and the wearer's eye presbyopia constraint parameter in the last exercise is greater than or equal to the eye presbyopia constraint parameter threshold, then it is judged that the wearer enters the intensive exercise stage; otherwise, it is judged that the wearer does not enter the intensive exercise stage.

[0080] In a specific embodiment of the present invention, the specific analysis method for judging the enhanced eye training presbyopia correction value corresponding to the wearer is: based on the eye parameters of the wearer in each enhanced exercise, the eye presbyopia constraint parameters of the wearer in each enhanced exercise are analyzed, and the average is processed to obtain the enhanced eye training presbyopia constraint parameter φ of the wearer.

[0081] The wearer's eye presbyopia constraint parameters during each exercise are averaged to obtain the wearer's exercised eye presbyopia constraint parameter φ′.

[0082] Determine the correction value of presbyopia corresponding to the wearer's exercise enhancement eyes Where e is a natural constant, and φ″ represents the expected recovery effect evaluation index of the wearer corresponding to the wearer.

[0083] The display terminal is used to display the wearing parameters and exercise enhancement parameters corresponding to the wearer, and the wearer's exercise-enhanced eye presbyopia correction value, and provide voice prompts when the wearer is exercising.

[0084] It should be noted that the present invention also includes a database for storing the influencing weight factors of various data, the basic information and eye information of each sample person, the allowable characteristic value range of each presbyopic eye data, the initial refractive index and the initial suitable training time of the optical lens corresponding to the reference ciliary muscle presbyopia influence coefficient, the suitable display brightness corresponding to each light intensity, the corrected training time corresponding to the unit brightness stability value, the qualified slope range of the eye presbyopia constraint parameter straight line, the suitable adjustable focal length corresponding to the unit deviation viewing distance in each ciliary muscle presbyopia influence coefficient range, the standard shape of the lens contour, and the recovery effect value corresponding to each sample person.

[0085] It should also be noted that the ciliary muscle suitable training user screening module is connected to the wearer information acquisition module, the wearer information acquisition module is connected to the wearer presbyopia analysis module, the wearer presbyopia analysis module is respectively connected to the wearer wearing parameter evaluation module and the wearer effect evaluation module, the wearer wearing parameter evaluation module is respectively connected to the wearer effect evaluation module and the display terminal, the wearer effect evaluation module is connected to the display terminal, and the database is respectively connected to the ciliary muscle suitable training user screening module, the wearer information acquisition module, the wearer presbyopia analysis module, the wearer wearing parameter evaluation module and the wearer effect evaluation module.

[0086] The above contents are merely examples and explanations of the concept of the present invention. Those skilled in the art may make various modifications or additions to the specific embodiments described or replace them in a similar manner. As long as they do not deviate from the concept of the invention or exceed the scope defined by the present invention, they shall all fall within the protection scope of the present invention.

Claims

1. A method for screening and predicting presbyopia using artificial intelligence, characterized in that: include: The principle of presbyopia is physically explained based on the principles of optics and mechanics, and an algorithm model is established based on the characteristics of a large number of presbyopic people and combined with statistical laws.

2. An artificial intelligence screening and prediction system for presbyopia, characterized in that: include: The ciliary muscle training suitable user screening module is used to collect basic information uploaded by several users, evaluate the ciliary muscle presbyopia influence coefficients corresponding to several users, screen out the ciliary muscle training suitable users, and invite the ciliary muscle training suitable users to test, and record the users who accept the test invitation as wearing users; The wearer information acquisition module is used to acquire the basic information uploaded by the wearer, and the wearer wears the presbyopia training device; The wearer's presbyopia analysis module is used to obtain the wearer's ciliary muscle presbyopia influence coefficient and analyze the wearer's expected recovery effect evaluation index; A wearer's wearing parameter evaluation module, used to evaluate the wearer's corresponding wearing parameters according to the wearer's ciliary muscle presbyopia influence coefficient; The wearer effect evaluation module is used to obtain the wearer's eye parameters at each exercise after the wearer has completed a specified period of training, and to determine whether the wearer has entered the enhanced exercise stage. If the wearer has entered the enhanced exercise stage, the module automatically adjusts the wearer's exercise when the wearer is undergoing enhanced exercise, and obtains the wearer's eye parameters at each enhanced exercise after the wearer has completed a specified period of enhanced exercise, and determines the wearer's corresponding enhanced exercise eye presbyopia correction value; The display terminal is used to display the wearing parameters and exercise enhancement parameters corresponding to the wearer, and the wearer's exercise-enhanced eye presbyopia correction value, and provide voice prompts when the wearer is exercising.

3. The artificial intelligence screening and prediction system for presbyopia according to claim 2, characterized in that: The specific analysis method of the ciliary muscle presbyopia influence coefficients corresponding to the plurality of users is as follows: Based on basic characteristic parameters, disease data, eye use information and genetic information in basic information uploaded by several users, the basic characteristic parameters, disease data, eye use information and genetic information uploaded by several users are processed to obtain characteristic values ​​of each data uploaded by several users after processing; The characteristic values ​​of each data uploaded by several users are summarized, and combined with the influence weight factors of each data stored in the database, the characteristic values ​​of each data uploaded by several users are multiplied by the influence weight factors, and then accumulated to obtain the ciliary muscle presbyopia influence coefficients corresponding to several users.

4. The presbyopia artificial intelligence screening and prediction system according to claim 2, characterized in that: The wearing parameters corresponding to the wearer are evaluated according to the ciliary muscle presbyopia influence coefficient of the wearer, and the specific analysis method is as follows: The influence coefficient of ciliary muscle presbyopia based on the wearer Combined with the reference ciliary muscle presbyopia influence coefficient stored in the database The initial refractive index Z' and initial suitable training time T' of the corresponding optical lens are used to evaluate the initial refractive index of the corresponding optical lens for the wearer. and initial suitable exercise duration Obtain the environmental adjustment parameters of the wearer, where the environmental adjustment parameters include the light intensity in each direction of the glasses, obtain the appropriate display brightness corresponding to each light intensity from the database, filter the appropriate display brightness in each direction of the glasses, and use it as the appropriate adjustment brightness L in each direction of the glasses worn by the wearer p , where p is the number of each direction, p = 1, 2, ..., q, q is any integer greater than 2 According to the appropriate brightness adjustment of the wearer's glasses in each direction, the initial appropriate exercise time of the wearer is corrected to obtain the appropriate exercise time T = T _0 +T″*μ, μ is the brightness stability value of the glasses worn by the wearer, Where L p is the appropriate adjusted brightness of the glasses worn by the wearer in the p-1th direction, and T″ is the corrected training time corresponding to the unit brightness stability value stored in the database; According to the initial refractive index of the optical lens corresponding to the wearer, the appropriate exercise time and the appropriate adjustable brightness in each direction of wearing the glasses, the wearing parameters corresponding to the wearer are summarized and obtained.

5. The artificial intelligence screening and prediction system for presbyopia according to claim 2, characterized in that: The specific method for judging whether the wearer has entered the exercise strengthening stage is as follows: Obtain the eye parameters of the wearer during each exercise, analyze the eye presbyopia constraint parameters of the wearer during each exercise, and fit a straight line of the eye presbyopia constraint parameters of the wearer with each exercise as the x-axis and the eye presbyopia constraint parameters as the y-axis to obtain the slope of the straight line of the eye presbyopia constraint parameters of the wearer; The slope of the wearer's presbyopia constraint parameter straight line is compared with the qualified slope interval of the eye presbyopia constraint parameter straight line stored in the database, and the wearer's eye presbyopia constraint parameter in the last exercise is compared with the predefined eye presbyopia constraint parameter threshold. If the slope of the wearer's eye presbyopia constraint parameter straight line is within the qualified slope interval of the eye presbyopia constraint parameter straight line, and the wearer's eye presbyopia constraint parameter in the last exercise is greater than or equal to the eye presbyopia constraint parameter threshold, then it is judged that the wearer enters the intensive exercise stage; otherwise, it is judged that the wearer does not enter the intensive exercise stage.

6. The artificial intelligence screening and prediction system for presbyopia according to claim 2, characterized in that: The automatic adjustment is performed when the wearer is exercising, and the specific analysis method is as follows: The ciliary muscle presbyopia influence coefficient of the wearer is multiplied by the allowed near vision time and allowed near vision distance corresponding to the preset unit ciliary muscle presbyopia influence coefficient, to obtain the allowed near vision time and allowed near vision distance of the wearer, and the allowed near vision time of the wearer is used as the interval of the detection cycle when the wearer performs training and strengthening; The wearer's viewing distance at each time point in the current detection cycle during exercise is obtained through eye tracking technology to determine whether automatic adjustment is required for the wearer. If necessary, the average viewing distance of the wearer in the current detection cycle during exercise is subtracted from the allowable near viewing distance to obtain the deviation viewing distance of the wearer in the current detection cycle during exercise; Based on the wearer's ciliary muscle presbyopia influence coefficient, a comparison is performed in combination with the suitable adjustable focal lengths corresponding to the unit deviation viewing distances in each ciliary muscle presbyopia influence coefficient interval stored in the database, and the suitable adjustable focal length corresponding to the unit deviation viewing distance of the wearer in the current detection cycle when exercising is screened, and the suitable adjustable focal length is multiplied by the deviation viewing distance of the wearer in the current detection cycle when exercising to obtain the suitable adjustable focal length of the wearer in the current detection cycle when exercising, and the glasses worn by the wearer are automatically adjusted.

7. The artificial intelligence screening and prediction system for presbyopia according to claim 2, characterized in that: The specific analysis method for judging the correction value of presbyopia corresponding to the enhanced eye training of the wearer is as follows: Based on the eye parameters of the wearer during each enhanced training, the wearer's eye presbyopia constraint parameters during each enhanced training are analyzed and averaged to obtain the wearer's enhanced training eye presbyopia constraint parameter φ; The wearer's eye presbyopia constraint parameter in each exercise is averaged to obtain the wearer's exercise eye presbyopia constraint parameter φ′; Determine the correction value of presbyopia corresponding to the wearer's exercise enhancement eyes Where e is a natural constant, and φ″ represents the expected recovery effect evaluation index of the wearer corresponding to the wearer.

Images