A device for relieving juvenile pseudomyopia based on artificial intelligence

Abstract

The present invention relates to a device for alleviating juvenile pseudomyopia based on artificial intelligence, and relates to the field of vision adjustment. It includes: obtaining the eye use distance of the line of sight; when the eye use distance falls within a preset visual range, obtaining the eye use time; when the eye use time exceeds a preset eye fatigue range, determining a far focus according to the eye use distance; determining spectacle control parameters according to the far focus; and controlling a preset variable-focus spectacle to adjust the focal length according to the spectacle control parameters. This application has the effects of improving the treatment effect on patients with pseudomyopia and reducing the situation of fatigued eye use in daily life.

Description

Technical Field

[0001] The present invention relates to the field of vision adjustment, and particularly to a device for alleviating juvenile pseudomyopia based on artificial intelligence. Background Art

[0002] Pseudomyopia, also known as accommodative myopia or functional myopia, is a non-pathological and temporary myopia state mainly caused by abnormal accommodation function of the eyes, rather than substantial changes in the eye structure.

[0003] In the prior art, pseudomyopia is usually caused by continuous contraction of the ciliary muscle due to long-term close-range eye use, resulting in a temporary blurred vision caused by the convexity of the lens. This state can be improved through appropriate rest and treatment, and may even heal on its own.

[0004] When patients with pseudomyopia use their eyes fatiguedly in daily life, it is easy to exacerbate the symptoms of pseudomyopia and even lead to the deterioration of pseudomyopia into true myopia. Summary of the Invention

[0005] In order to improve the treatment effect on patients with pseudomyopia and reduce the situation of fatigued eye use in daily life, the present invention provides a device for alleviating juvenile pseudomyopia based on artificial intelligence.

[0006] In a first aspect, the present invention provides a device for alleviating juvenile pseudomyopia based on artificial intelligence, adopting the following technical solutions:

[0007] A device for alleviating juvenile pseudomyopia based on artificial intelligence, comprising:

[0008] Obtain the eye use distance of the line of sight direction;

[0009] When the eye use distance falls within a preset visual range, obtain the eye use time;

[0010] When the eye use time exceeds the preset eye use fatigue range, determine the far focus according to the eye use distance;

[0011] Determine the glasses control parameter according to the far focus;

[0012] Control the preset varifocal glasses to adjust the focal length according to the glasses control parameter.

[0013] Optionally, it further includes an eye relaxation method, and the eye relaxation method includes:

[0014] When the eye use distance falls within a preset relaxation range, match the relaxation time from a preset relaxation time database according to the eye use time;

[0015] Determine the focal length change curve according to the relaxation time;

[0016] Determine the relaxation control parameters according to the focal length change curve;

[0017] Determine the voice prompt parameters according to the focal length change curve;

[0018] Control the preset zoom glasses to adjust the focal length according to the relaxation control parameters, and control the prompting device preset on the zoom glasses to give voice prompts according to the voice prompt parameters.

[0019] Optionally, it further includes a method for generating an eye fatigue interval, and the method for generating an eye fatigue interval includes:

[0020] Obtain the visual image of the line of sight direction;

[0021] When the eye use distance falls within the preset visual interval, match the reference interval from the preset reference interval database according to the eye use distance;

[0022] Determine whether the patient is watching an electronic screen according to the visual image;

[0023] When it is determined whether the patient is watching an electronic screen, determine the screen influence factor according to the visual image;

[0024] Determine whether the patient is reading text according to the visual image;

[0025] When it is determined whether the patient is reading text, determine the font influence factor according to the visual image;

[0026] Determine the eye fatigue interval according to the reference interval, the screen influence factor and the font influence factor.

[0027] Optionally, the method for generating an eye fatigue interval further includes:

[0028] When the eye use distance falls within the preset visual interval, determine the refractive index according to the visual image;

[0029] Determine the light direction according to the visual image;

[0030] Determine the refraction influence factor according to the light direction and the refractive index;

[0031] Determine the eye fatigue interval according to the reference interval, the screen influence factor, the font influence factor and the refraction influence factor.

[0032] Optionally, it further includes an anti-electromagnetic interference method, and the anti-electromagnetic interference method includes:

[0033] Determine whether there is side-emitted light according to the visual image;

[0034] When there is side-emitted light, determine the photosensitive number according to the visual image;

[0035] Control the photosensitive sensor preset on one side of the zoom glasses according to the photosensitive number to obtain the peak light intensity;

[0036] When the peak light intensity exceeds the preset stimulation range, determine the valley light intensity according to the peak light intensity and the visual image;

[0037] Control the photosensitive sensor preset on the other side of the zoom glasses according to the photosensitive number to obtain the actual light intensity;

[0038] Determine the light intensity deviation from the preset deviation rate calculation method according to the actual light intensity and the valley light intensity;

[0039] When the light intensity deviation does not exceed the preset perturbation range, determine the refraction area based on the side-emitted light;

[0040] Control the preset zoom glasses to adjust the refractive index of the light according to the refraction area.

[0041] By adopting the above technical solution, when strong light is detected on the side of the glasses, predict the light intensity on the other side of the eyes according to the diffusion characteristics of the light, and compare it with the actually detected light intensity to judge whether the detected data is correct, thereby reducing the situation where the photosensitive sensor outputs incorrect data due to electromagnetic interference.

[0042] Optionally, the anti-electromagnetic interference method further includes:

[0043] When the eye use distance falls into the preset visual range, determine whether the eye use distance can be directly recognized according to the visual image;

[0044] When the eye use distance cannot be directly recognized, control the on / off of the reference lamp group preset on the zoom glasses, and obtain the reference image under the irradiation of the reference lamp group;

[0045] Determine the reference distance according to the reference image;

[0046] When the eye use distance can be directly recognized, determine the reference distance according to the visual image;

[0047] Based on the recognized reference distance, calculate the difference between the reference distance and the eye use distance, and define it as the distance deviation;

[0048] When the distance deviation does not exceed the preset deviation range, obtain the eye use time.

[0049] By adopting the above technical solution, judge whether the eye use distance conforms to the actual situation through the image. When it cannot be directly judged by the image, the reference lamp group emits light, and judge the eye use distance according to the diffusion of the light, thereby reducing the situation where the distance sensor outputs incorrect data due to electromagnetic interference.

[0050] Optionally, it further includes a glasses adjustment method, and the glasses adjustment method includes:

[0051] Obtain the wearing image of the glasses;

[0052] Determine the three-dimensional face based on the wearing image;

[0053] Determine the wearing height based on the three-dimensional face;

[0054] Determine the nose bridge parameters based on the three-dimensional face;

[0055] Determine the nose pad control parameters based on the wearing height and the nose bridge parameters;

[0056] Control the nose pad of the preset zoom glasses to adjust according to the nose pad control parameters.

[0057] By adopting the above technical solution, the appropriate wearing position of the glasses is judged according to the eye position of the patient, so as to match the angle required by the nose pad when the glasses reach the wearing position according to the nose bridge shape of the patient, thereby improving the suitability between the glasses and the patient.

[0058] Optionally, the glasses adjustment method further includes:

[0059] Determine the wearing feature point set according to the wearing height and the three-dimensional face;

[0060] Determine the face curve according to the wearing feature point set;

[0061] Determine the lens angle according to the face curve;

[0062] Determine the lens control parameters according to the lens angle;

[0063] Control the preset zoom glasses to adjust the lens angle according to the lens control parameters.

[0064] By adopting the above technical solution, the feature points of the glasses wearing position are extracted from the used face data, so as to fit the concave and convex change curve of the patient's eyes, and then adjust the lens angle according to the concave and convex change curve, thereby further improving the suitability between the glasses and the patient.

[0065] Optionally, the glasses adjustment method further includes:

[0066] Obtain the pressure information of the temple of the zoom glasses;

[0067] Determine whether the temple angle needs to be adjusted according to the pressure information;

[0068] When the temple angle needs to be adjusted, determine the wearing position according to the pressure information and obtain the current angle of the temple;

[0069] Determine the adjustment angle according to the wearing position, the current angle and the pressure information;

[0070] Determine the temple control parameters according to the adjustment angle;

[0071] Control the adjustment angle of the temples preset on the varifocal glasses according to the temple control parameters.

[0072] By adopting the above technical solution, the pressure value on the side of the temple of the glasses is detected to judge whether the angle of the temple of the glasses needs to be adjusted. When the pressure value is too large, it means that the expansion angle of the temple is too small and the glasses are worn too tightly. When the pressure value is too small, it means that the expansion angle of the temple is too large and the glasses are worn too loosely. The angle of the temple is adjusted according to the pressure value and the wearing state of the glasses, so as to improve the suitability between the glasses and the patient.

[0073] In summary, the present application includes at least one of the following beneficial technical effects:

[0074] 1. When the distance to the object in the line of sight is relatively close, it is judged that the patient is using the eyes. At this time, the cumulative eye use time is counted, and when the eye use time is too long, the focal length of the glasses is adjusted, so that the patient cannot see the object clearly, and then the patient is prompted to stop using the eyes and relax the eyes, reducing the situation of fatigue eye use and improving the treatment effect on patients with pseudomyopia;

[0075] 2. When the patient stops using the eyes after using the eyes for a long time, the focal length of the varifocal glasses is controlled to change regularly, so as to assist the patient to control the ciliary muscle, and then relax the eyes, improving the treatment effect on patients with pseudomyopia;

[0076] 3. According to the visual distance of the patient, the basic fatigue interval is matched, and then the basic fatigue interval is corrected according to the refresh frequency of the visual target and the font size of the visual target, so as to lower the fatigue interval of the visual target with a higher refresh frequency and a smaller font size. Brief Description of the Drawings

[0077] Figure 1 is a flowchart of a method for relieving adolescent pseudomyopia based on artificial intelligence;

[0078] Figure 2 is a flowchart of an eye relaxation method;

[0079] Figure 3 is the process of a method for generating an eye fatigue interval Figure 1 ;

[0080] Figure 4 is the process of a method for generating an eye fatigue interval Figure 2 ;

[0081] Figure 5 is the process of an anti-electromagnetic interference method Figure 1 ;

[0082] Figure 6 is the process of an anti-electromagnetic interference method Figure 2 ;

[0083] Figure 7 is the process of the glasses adjustment method Figure 1 ;

[0084] Figure 8 is the process of the glasses adjustment method Figure 2 ;

[0085] Figure 9 is the process of the glasses adjustment method Figure 3 ;

[0086] Figure 10 is the process of the glasses adjustment method Figure 4 . Specific implementation manners

[0087] In order to make the objectives, technical solutions and advantages of the present invention clearer and more understandable, the present invention will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not used to limit the present invention.

[0088] The embodiments of the present application disclose a device for relieving adolescent pseudomyopia based on artificial intelligence, which reduces the fatigue of the patient's eyes by controlling the focal length of the zoom glasses, and assists the patient to relax the eyes through the change of the focal length, thereby improving the treatment effect of pseudomyopia.

[0089] Referring to Figure 1 , a method for relieving adolescent pseudomyopia based on artificial intelligence includes:

[0090] Step 100: Obtain the eye-using distance in the line-of-sight direction.

[0091] The zoom glasses refer to the glasses whose focal length is adjusted by changing the voltage. Generally, the pseudomyopia is relieved by the zoom glasses. The zoom glasses are selected by the staff according to the actual situation and will not be elaborated here. The eye-using distance refers to the distance between the object closest to the zoom glasses in the line-of-sight direction of the zoom glasses and the zoom glasses. The eye-using distance can be obtained by the distance sensor preset on the zoom glasses. The method for obtaining the eye-using distance is selected by the staff according to the actual situation and will not be elaborated here.

[0092] Step 101: When the eye-using distance falls within the preset visual range, obtain the eye-using time.

[0093] The visual range refers to the range of eye - using distances that are likely to cause eye fatigue. The visual range is selected by the staff according to the actual situation and will not be elaborated here. When the eye - using distance falls within the visual range, it means that the eyes are being used at this time. The eye - using time refers to the length of time accumulated since the eye - using distance fell within the visual range. The eye - using time can be obtained through a timer. The method for obtaining the eye - using time is selected by the staff according to the actual situation and will not be elaborated here.

[0094] Step 102: When the eye - using time exceeds the preset eye - fatigue range, determine the away - from - focal length according to the eye - using distance.

[0095] The eye - fatigue range refers to the range of eye - using times that are likely to cause the deterioration of pseudomyopia. The eye - fatigue range is selected by the staff according to the actual situation and will not be elaborated here. When the eye - using time exceeds the eye - fatigue range, it means that the patient has been using the eyes fatiguedly at this time. The away - from - focal length can be obtained through an away - from - focal - length matching model. The away - from - focal - length matching model is a neural network model obtained by prior sample training. The away - from - focal - length matching model can first calculate the difference between the upper limit value of the visual range and the eye - using distance, and define it as the correction distance. Then, according to the correction distance, correct the original focal length of the varifocal glasses. The away - from - focal length is the focal length value obtained after correcting the original focal length of the varifocal glasses according to the correction distance.

[0096] Step 103: Determine the glasses control parameters according to the away - from - focal length using the away - from - focal - length matching model.

[0097] The glasses control parameters refer to the parameters used to control the refractive index of the varifocal glasses to adjust the focal length. The glasses control parameters can be obtained through a glasses control parameter matching model. The glasses control parameter matching model is a neural network model obtained by prior sample training. The glasses control parameter matching model can match the glasses control parameters that can make the focal length of the varifocal glasses reach the away - from - focal length.

[0098] Step 104: Control the preset varifocal glasses to adjust the focal length according to the glasses control parameters.

[0099] When the patient uses the eyes fatiguedly, by adjusting the focal length, the patient needs to adjust the eye - using distance to exceed the visual range to see the visual target, thereby reducing the situation of the patient using the eyes fatiguedly.

[0100] Refer to Figure 2 , the eye relaxation methods include:

[0101] Step 200: When the eye - using distance falls within the preset relaxation range, match the relaxation time from the preset relaxation - time database according to the eye - using time.

[0102] The relaxation interval refers to the eye - using distance interval that can relax the eyes. The relaxation interval is selected by the staff according to the actual situation and will not be elaborated here. When the eye - using distance falls within the relaxation interval, it means that the patient is relaxing the eyes at this time. The relaxation - time database refers to the database that has pre - recorded the eye - using time and its corresponding minimum eye - relaxation duration. The relaxation time is the minimum eye - relaxation duration corresponding to the eye - using time retrieved from the relaxation - time database.

[0103] Step 201: Determine the focal - length change curve according to the relaxation time.

[0104] The focal - length change curve can be obtained through the focal - length change curve matching model. The focal - length change curve matching model is a neural network model obtained by pre - training with samples. The focal - length change curve matching model can match the focal - length change that enables the patient's visual focus to move from near to far, stay at a distance for a period of time, and then move from far to near, and repeat this process within the relaxation time to obtain the focal - length change curve.

[0105] Step 202: Determine the relaxation control parameters according to the focal - length change curve.

[0106] The relaxation control parameters can be obtained through the relaxation control parameter matching model. The relaxation control parameter matching model is a neural network model obtained by pre - training with samples. The relaxation control parameter matching model can match the relaxation control parameters that control the varifocal glasses to adjust the focal length according to the focal - length change curve.

[0107] Step 203: Determine the voice - prompt parameters according to the focal - length change curve.

[0108] The voice - prompt parameters refer to the parameters used to control the varifocal glasses to emit voice prompts. The voice - prompt parameters can be obtained through the voice - prompt parameter matching model. The voice - prompt parameter matching model is a neural network model obtained by pre - training with samples. The voice - prompt parameter matching model can match the voice - prompt parameters that control the varifocal glasses to assist the patient in eye relaxation through voice when adjusting the focal length according to the focal - length change curve. The content of voice assistance can include music for mental relaxation and can also include prompt sounds to remind the patient to change the line - of - sight focus.

[0109] Step 204: Control the preset varifocal glasses to adjust the focal length according to the relaxation control parameters, and control the prompt device preset on the varifocal glasses to give voice prompts according to the voice - prompt parameters.

[0110] When the patient relaxes the eyes after long - term eye use, the varifocal glasses are adjusted to enable the patient to continuously adjust the focal length of the eyes without relying on external objects, so that the ciliary muscle can be relaxed, thereby relieving eye fatigue.

[0111] Refer to Figure 3 , the method for generating the eye - fatigue interval includes:

[0112] Step 300: Obtain a visual image in the line-of-sight direction.

[0113] A visual image refers to a picture in the line-of-sight direction of the zoom glasses. The visual image can be obtained through a camera preset on the zoom glasses. The method for obtaining the visual image is selected by the staff according to the actual situation and will not be elaborated here.

[0114] Step 301: When the eye-using distance falls within a preset visual range, match a reference range from a preset reference range database according to the eye-using distance.

[0115] The reference range database refers to a database that has previously recorded the eye-using distance and its corresponding minimum eye fatigue duration. The reference range is a duration range with the minimum eye fatigue duration corresponding to the eye-using distance as the lower limit value of the range and infinity as the upper limit value of the range, which is matched from the reference range database.

[0116] Step 302: Determine whether the patient is looking at an electronic screen according to the visual image.

[0117] It can be judged whether the patient is looking at an electronic screen through an electronic screen recognition model. The electronic screen recognition model is a neural network model obtained by pre-training with samples. The electronic screen recognition model can judge whether the object closest to the patient in the line-of-sight direction in the visual image is an electronic screen.

[0118] Step 303: When it is determined whether the patient is looking at an electronic screen, determine a screen influence factor according to the visual image.

[0119] The screen influence factor refers to a parameter used to correct the fatigue range. The screen influence factor can be obtained through a screen influence factor matching model. The screen influence factor matching model is a neural network model obtained by pre-training with samples. The screen influence factor matching model can match a screen influence factor that corrects the reference range according to the refresh rate of the electronic screen being viewed by the patient. Among them, the refresh rate of the electronic screen can be estimated by obtaining multiple visual images in a short time and according to the change of the picture on the electronic screen in the image.

[0120] Step 304: Determine whether the patient is reading text according to the visual image.

[0121] It can be judged whether the patient is reading text through a text recognition model. The text recognition model is a neural network model obtained by pre-training with samples. The text recognition model can judge whether there is text on the object closest to the patient in the line-of-sight direction in the visual image.

[0122] Step 305: When it is determined whether the patient is reading text, determine a font influence factor according to the visual image.

[0123] The font influence factor refers to the parameter used to correct the fatigue interval. The font influence factor can be obtained through the font influence factor matching model, which is a neural network model obtained by prior sample training. The font influence factor matching model can match the font influence factor that corrects the reference interval according to the font size, font color, and background color of the text being read by the patient.

[0124] Step 306: Determine the eye fatigue interval according to the reference interval, screen influence factor, and font influence factor.

[0125] The eye fatigue interval can be calculated through the eye fatigue interval matching model, which is a neural network model obtained by prior sample training. The eye fatigue interval matching model can calculate the product of the screen influence factor, font influence factor, and reference interval, and define it as the eye fatigue interval.

[0126] Refer to Figure 4 , the method for generating the eye fatigue interval further includes:

[0127] Step 307: When the eye distance falls within the preset visual interval, determine the refractive index according to the visual image.

[0128] The refractive index can be identified through the refractive index matching model, which is a neural network model obtained by prior sample training. The refractive index matching model can determine the material of the object closest to the patient in the line of sight direction in the visual image, and then match the corresponding refractive index according to the material.

[0129] Step 308: Determine the light direction according to the visual image.

[0130] The light direction can be identified through the light direction matching model, which is a neural network model obtained by prior sample training. The light direction matching model can identify the main direction of the light with the highest light intensity in the visual image.

[0131] Step 309: Determine the refraction influence factor according to the light direction and refractive index.

[0132] The refraction influence factor refers to the parameter used to correct the fatigue interval. The refraction influence factor can be obtained through the refraction influence factor matching model, which is a neural network model obtained by prior sample training. The refraction influence factor matching model can match the refraction influence factor that corrects the reference interval according to the light direction and refractive index of the visual target.

[0133] Step 310: Determine the eye fatigue interval from the reference interval, screen influence factor, font influence factor, and refraction influence factor.

[0134] The eye fatigue interval is the product of the reference interval, the screen impact factor, the font impact factor, and the refraction impact factor calculated through the eye fatigue interval matching model.

[0135] Among them, the reference interval, the screen impact factor, the font impact factor, and the refraction impact factor can be analyzed to generate an eye use report, and the eye use report is sent to the terminal, so as to facilitate personnel to download the eye use report from the terminal, and further facilitate doctors to formulate further treatment plans according to the eye use situation reflected in the eye use report, and facilitate individuals to view the eye use situation.

[0136] Refer to Figure 5 , the electromagnetic interference prevention method includes:

[0137] Step 400: Determine whether there is side-emitted light according to the visual image.

[0138] It can be judged whether there is side-emitted light through the side-emitted light recognition model. The side-emitted light recognition model is a neural network model obtained by prior sample training. The side-emitted light recognition model can judge whether there is light emitted from the side within the visual range of the glasses. Among them, the side refers to the area within the visual range that exceeds the pre-set main visual area.

[0139] Step 401: When there is side-emitted light, determine the photosensitive number according to the visual image.

[0140] The photosensitive sensor is a sensor set on the zoom glasses for obtaining the optical fiber intensity. Photosensitive sensors are set on both sides of each zoom glasses. The photosensitive sensors are selected by the staff according to the actual situation and will not be elaborated here.

[0141] The photosensitive number is a number set in advance for distinguishing photosensitive sensors. The photosensitive number corresponds to the photosensitive sensor one by one. The setting method of the photosensitive number is selected by the staff according to the actual situation and will not be elaborated here. The photosensitive number can be obtained through the photosensitive sensor number matching model. The photosensitive sensor number matching model is a neural network model obtained by prior sample training. The photosensitive sensor number matching model can match the area where the side-emitted light hits the zoom glasses lens in the visual image, and match the photosensitive number of the photosensitive sensor close to this area.

[0142] Step 402: Control the photosensitive sensor preset on one side of the zoom glasses to obtain the peak light intensity according to the photosensitive number.

[0143] The peak light intensity is the light intensity signal obtained by the photosensitive sensor close to the area where the side-emitted light hits the zoom glasses lens. The method for obtaining the peak light intensity is selected by the staff according to the actual situation and will not be elaborated here.

[0144] Step 403: When the peak light intensity exceeds the preset stimulation range, determine the valley light intensity based on the peak light intensity and the visual image.

[0145] The stimulation range refers to the light intensity range where light is likely to stimulate the eyes and cause the deterioration of pseudomyopia. The stimulation range is selected by the staff according to the actual situation and will not be elaborated here.

[0146] The valley light intensity can be obtained through the valley light intensity matching model. The valley light intensity matching model is a neural network model obtained by prior sample training. The valley light intensity matching model can predict the light intensity signal obtained by the photosensor in the area away from the side-emitted light and shooting towards the zoom glasses lens based on the light diffusion of the side-emitted light in the visual image, and define this signal as the valley light intensity.

[0147] Step 404: Control the photosensor preset on the other side of the zoom glasses to obtain the actual light intensity according to the photosensitive number.

[0148] The actual light intensity refers to the light intensity signal obtained by the photosensor in the area away from the side-emitted light and shooting towards the zoom glasses lens. The method for obtaining the actual light intensity is selected by the staff according to the actual situation and will not be elaborated here.

[0149] Step 405: Determine the light intensity deviation from the preset deviation rate calculation method based on the actual light intensity and the valley light intensity.

[0150] The deviation rate calculation method refers to the method for calculating the deviation degree between the actual light intensity and the valley light intensity. Generally, first calculate the difference between the valley light intensity and the actual light intensity, divide the difference by the actual light intensity to obtain the deviation value, and define this deviation value as the light intensity deviation.

[0151] Step 406: When the light intensity deviation does not exceed the preset perturbation range, determine the refraction area based on the side-emitted light.

[0152] The perturbation range refers to the deviation value range allowed between the actual light intensity and the valley light intensity. The perturbation range is selected by the staff according to the actual situation and will not be elaborated here. That the light intensity deviation does not exceed the perturbation range represents that the detection result of the photosensor is reliable. The refraction area can be identified through the refraction area matching model. The refraction area matching model is a neural network model obtained by prior sample training. The refraction area matching model can match the area on the zoom glasses lens where the side-emitted light shoots, and define this area as the refraction area.

[0153] Step 407: Control the preset zoom glasses to adjust the refractive index of the light according to the refraction area.

[0154] When there is strong side-emitted light, increase the refractive index of the refraction area of the zoom glasses to reduce the stimulation of the side-emitted light to the eyes, thereby reducing the situation of eye fatigue.

[0155] When the light intensity deviation exceeds the preset perturbation range, it means that the detection result of the photosensitive sensor is unreliable. At this time, the refractive index of the zoom glasses is not adjusted, so as to reduce the situation of interfering with the detection result of the photosensitive sensor when the patient uses portable devices such as mobile phones.

[0156] Refer to Figure 6 , the anti-electromagnetic interference method further includes:

[0157] Step 408: When the eye use distance falls within the preset visual range, determine whether the eye use distance can be directly recognized according to the visual image.

[0158] It can be judged whether the eye use distance can be directly recognized through an eye use distance judgment model. The eye use distance judgment model refers to a neural network model obtained by prior sample training. The eye use distance judgment model can recognize the reference object in the visual image and judge that the eye use distance can be directly recognized when the reference object is recognized, and judge that the eye use distance cannot be directly recognized when the reference object is not recognized, where the reference object refers to an object preset for judging the eye use distance.

[0159] Step 409: When the eye use distance cannot be directly recognized, control the opening and closing of the reference lamp group preset on the zoom glasses, and obtain a reference image under the irradiation of the reference lamp group.

[0160] The reference lamp group refers to a lamp group composed of at least two lamps set on the zoom glasses. The irradiation directions of the lamps in the reference lamp group are all different. The setting method of the reference lamp group is selected by the staff according to the actual situation and will not be elaborated here.

[0161] The reference image refers to a picture obtained when the reference lamp group is started. The reference image can be obtained through a camera on the zoom glasses. The acquisition method of the reference image is selected by the staff according to the actual situation and will not be elaborated here.

[0162] Step 410: Determine the reference distance according to the reference image.

[0163] The reference distance can be obtained through a reference distance recognition model. The reference distance recognition model refers to a neural network model obtained by prior sample training. The reference distance recognition model can judge the reference distance between the object closest to the zoom glasses in the line of sight direction of the zoom glasses and the zoom glasses from the diffusion situation of the light rays emitted by the reference lamp group in the reference image.

[0164] Step 411: When the eye use distance can be directly recognized, determine the reference distance according to the visual image.

[0165] The reference distance can be obtained through an eye-using distance recognition model, which is a neural network model obtained by prior sample training. The eye-using distance recognition model can identify the reference distance based on the size of the reference object in the visual image.

[0166] Step 412: Based on the recognized reference distance, calculate the difference between the reference distance and the eye-using distance, and define it as the distance deviation.

[0167] The distance deviation refers to the difference between the reference distance and the eye-using distance. Whether the eye-using distance is reliable is judged by the distance deviation.

[0168] Step 413: When the distance deviation does not exceed the preset deviation range, obtain the eye-using time.

[0169] The deviation range refers to the allowable error range between the reference distance and the eye-using distance. The deviation range is selected by the staff according to the actual situation and will not be elaborated here. That the distance deviation does not exceed the deviation range means that the eye-using distance is reliable at this time and subsequent operations can be carried out.

[0170] When the distance deviation exceeds the preset deviation range, it means that the eye-using distance is unreliable, and the sensor for obtaining the eye-using distance may be affected by electromagnetic interference. At this time, no subsequent operations are performed to reduce the abnormal operation of the zoom glasses caused by electromagnetic interference.

[0171] Reference Figure 7 , the glasses adjustment method includes:

[0172] Step 500: Obtain the wearing image of the glasses.

[0173] The wearing image refers to the facial picture of the patient. The wearing image can be obtained through the camera on the zoom glasses. The method for obtaining the wearing image is selected by the staff according to the actual situation and will not be elaborated here.

[0174] Step 501: Determine the three-dimensional face according to the wearing image.

[0175] The three-dimensional face can be established through a three-dimensional face matching model, which is a neural network model obtained by prior sample training. The three-dimensional face matching model can establish a three-dimensional model of the patient's face from the wearing image, where the three-dimensional face is the three-dimensional model of the patient's face.

[0176] Step 501: Determine the wearing height according to the three-dimensional face.

[0177] The wearing height can be obtained through a glasses wearing height matching model, which is a neural network model obtained by prior sample training. The glasses wearing height matching model can identify the eye features in the three-dimensional face and extract the distance from the midpoint of the eye features to the chin as the wearing height.

[0178] Step 503: Determine the nose bridge parameters according to the three-dimensional face.

[0179] The nose bridge parameters can be extracted through a nose bridge parameter matching model, which is a neural network model obtained by prior sample training. The nose bridge parameter matching model can extract the three-dimensional parameters of the part of the nose bridge in contact with the glasses after wearing from the three-dimensional face, and the nose bridge parameters are the obtained three-dimensional parameter results of the matching.

[0180] Step 504: Determine the nose pad control parameters according to the wearing height and the nose bridge parameters.

[0181] The nose pad control parameters refer to the parameters used to control the nose pad angle adjustment of the zoom glasses. The nose pad control parameters can be obtained through conversion by a nose pad angle control model, which is a neural network model obtained by prior sample training. The nose pad angle control model can match the nose pad control parameters that control the nose pad to adapt to the trend of the nose bridge so that the glasses are flush with the eyes at the wearing height.

[0182] Step 505: Control the preset zoom glasses to adjust the nose pad according to the nose pad control parameters.

[0183] Adjust the nose pad of the zoom glasses according to the shape of the patient's nose bridge, so as to improve the wearing comfort of the zoom glasses and make the zoom glasses stably worn at the wearing height.

[0184] Refer to Figure 8 , the glasses adjustment method further includes:

[0185] Step 506: Determine the wearing feature point set according to the wearing height and the three-dimensional face.

[0186] The wearing feature point set can be obtained through a wearing feature point extraction model, which is a neural network model obtained by prior sample training. The wearing feature point extraction model can extract the coordinates of the data points located at the wearing height in the three-dimensional face and define them as the wearing feature point set.

[0187] Step 507: Determine the face curve according to the wearing feature point set.

[0188] The face curve fitting model is a neural network model obtained by prior sample training. The face curve fitting model can fit the face curve according to the wearing feature point set.

[0189] Step 508: Determine the lens angle according to the face curve.

[0190] The lens angle can be obtained through matching by a lens angle fitting model, which is a neural network model obtained by prior sample training. The lens angle fitting model can match the lens angle according to the trend of the eyes in the face curve.

[0191] Step 509: Determine the lens control parameters according to the lens angle.

[0192] The lens control parameters refer to the neural network model obtained by prior sample training for controlling the glasses angle control model. The glasses angle control model can match the glasses control parameters for controlling the lens of the varifocal glasses to adjust according to the lens angle.

[0193] Step 510: Control the preset varifocal glasses to adjust the lens angle according to the lens control parameters.

[0194] Adjust the angle of the lens according to the orientation of the eye, so that the lens is parallel to the eye, thereby improving the wearing comfort of the varifocal glasses and reducing the situation that the vision correction effect of the glasses is reduced due to the non - parallelism between the lens and the eye.

[0195] Refer to Figure 9 , the glasses adjustment method further includes:

[0196] Step 511: Determine the adjustment angle according to the lens control parameters.

[0197] The adjustment angle can be extracted from the lens control parameters through a parameter analysis model. The parameter analysis model is a neural network model obtained by prior sample training. The parameter analysis model can match the adjustment angle that the lens needs to be adjusted from the lens control parameters.

[0198] Step 512: Determine the forward adjustment area and the reverse adjustment area according to the adjustment angle.

[0199] The forward adjustment area and the reverse adjustment area can be segmented by an adjustment area segmentation model. The adjustment area segmentation model is a neural network model obtained by prior sample training. The adjustment area segmentation model can identify the part that needs to apply a force on the lens during the process of adjusting the lens angle according to the adjustment angle as the forward adjustment area, and define the remaining part as the reverse adjustment area.

[0200] Step 513: Match the airbag number and airbag position from the preset airbag number database according to the forward adjustment area.

[0201] The airbag refers to a device preset on the varifocal glasses and used to fix the lens on the frame of the varifocal glasses. There are multiple airbags arranged around the lens, and the airbags are symmetrically arranged with respect to the lens. The airbags are selected by the staff according to the actual situation and will not be elaborated here.

[0202] The airbag number refers to the number set in advance for distinguishing airbags, and each airbag corresponds one-to-one with the airbag number. The method for setting the airbag number is selected by the staff according to the actual situation and will not be elaborated here. The airbag number database refers to the database that has previously recorded the airbag number and its corresponding airbag position. The airbag number and the airbag position are the airbag number and its airbag position of the airbag whose position matched from the airbag number falls into the forward adjustment area.

[0203] Step 514: Determine the adjustment distance according to the airbag position and the adjustment angle.

[0204] The adjustment distance can be obtained through the adjustment distance matching model. The adjustment distance matching model refers to the neural network model obtained by sample training in advance. The adjustment distance matching model can identify the adjustment distance of the airbag position of the lens when the lens is adjusted according to the adjustment angle.

[0205] Step 515: Determine the forward adjustment air volume according to the adjustment distance.

[0206] The forward adjustment air volume can be calculated through the forward adjustment air volume matching model. The forward adjustment air volume matching model refers to the neural network model obtained by sample training in advance. The forward adjustment air volume matching model can match the forward adjustment air volume required to move the airbag of the airbag position of the lens according to the adjustment distance.

[0207] Step 516: Determine the reverse airbag number according to the airbag position.

[0208] The reverse airbag number can be matched through the reverse airbag number matching model. The reverse airbag number matching model refers to the neural network model obtained by sample training in advance. The reverse airbag number matching model can match the reverse airbag number of the airbag with the same airbag position and different airbag numbers.

[0209] Step 517: Control the preset airbag to inflate according to the forward adjustment air volume according to the airbag number, and control the preset airbag to exhaust according to the forward adjustment air volume according to the reverse airbag number.

[0210] Adjust the angle of the lens by the cooperation of airbag inflation and deflation, and at the same time reduce the situation that the center of the lens shifts during angle adjustment, resulting in misalignment between the lens and the eye, thereby improving the convenience of using the zoom glasses.

[0211] Refer to Figure 10 , the glasses adjustment method further includes:

[0212] Step 518: Obtain the pressure information of the temple of the zoom glasses.

[0213] The pressure information refers to the pressure detection information received in the horizontal direction of the temple of the zoom glasses. The pressure information can be obtained through the pressure sensors on the temples. The method for obtaining the pressure information is selected by the staff according to the actual situation and will not be elaborated here.

[0214] Step 519: Determine whether to adjust the temple angle according to the pressure information.

[0215] It can be determined whether to adjust the temple angle through the temple adjustment recognition model. The temple adjustment recognition model refers to a neural network model obtained by prior sample training. The temple adjustment recognition model can convert the pressure information into a pressure value and compare this pressure value with a preset adjustment range. When the pressure value exceeds the preset adjustment range, it is determined that the temple angle needs to be adjusted. The adjustment range is selected by the staff according to the actual situation and will not be elaborated here.

[0216] Step 520: When the temple angle needs to be adjusted, determine the wearing position according to the pressure information and obtain the current angle of the temple.

[0217] The wearing position can be obtained by analyzing the pressure information through the wearing position recognition model. The wearing position recognition model refers to a neural network model obtained by prior sample training. The wearing position recognition model can identify the position of the pressure sensor that obtains the pressure information from the pressure information and use this position as the wearing position.

[0218] The current angle refers to the current angle of the temple. The current angle can be obtained through an angle sensor set between the temple and the frame. The method for obtaining the current angle is selected by the staff according to the actual situation and will not be elaborated here.

[0219] Step 521: Determine the adjustment angle according to the wearing position, the current angle, and the pressure information.

[0220] The adjustment angle can be obtained by calculation through the adjustment angle matching model. The adjustment angle matching model refers to a neural network model obtained by prior sample training. The adjustment angle matching model can match the adjustment angle that rotates the temple so that the pressure value at the wearing position falls within the adjustment range.

[0221] Step 522: Determine the temple control parameter according to the adjustment angle.

[0222] The temple control parameter refers to the parameter used to control the adjustment of the temple angle of the zoom glasses. The temple control parameter can be obtained by matching through the temple control model. The temple control model refers to a neural network model obtained by prior sample training. The temple control model can match the temple control parameter that controls the temple to rotate according to the adjustment angle.

[0223] Step 523: Control the temple adjustment angle preset on the zoom glasses according to the temple control parameter.

[0224] When the temple is too tightly clamped or too loose, control the rotation of the temple, thereby improving the wearing comfort of the varifocal glasses.

[0225] The above-mentioned training methods of the neural network model are all well-known common knowledge to those skilled in the art and will not be elaborated herein.

Claims

1. A device for alleviating pseudomyopia in adolescents based on artificial intelligence, characterized in that: include: Zoom glasses and a distance sensor, a camera and a light sensor arranged on the zoom glasses; Also included is a method for alleviating juvenile pseudomyopia applied to an artificial intelligence-based juvenile pseudomyopia alleviating device, the method for alleviating juvenile pseudomyopia comprising: Obtaining the eye distance in the sight direction, where the eye distance may be obtained by a distance sensor preset on the varifocal glasses; When the eye use distance falls into the preset visual interval, the eye use time is obtained; When the eye use time exceeds the preset eye fatigue range, the distance away from the focus is determined according to the eye use distance; determining eyewear control parameters based on the away focal distance; Controlling the preset varifocal glasses to adjust the focal length according to the glasses control parameters; Also included is an electromagnetic interference prevention method, the electromagnetic interference prevention method comprising: Acquire a visual image in the sight direction, where the visual image may be acquired by a camera preset on the zoom glasses; Determine the presence or absence of side-light based on the visual image; When there is side light, the photosensitive number is determined based on the visual image; According to the photosensitive number, a photosensitive sensor preset on one side of the zoom glasses is controlled to obtain the peak light intensity; When the peak value of light intensity exceeds the preset stimulation interval, the valley value of light intensity is determined based on the peak value of light intensity and the visual image; According to the photosensitive number, the photosensitive sensor preset on the other side of the zoom glasses is controlled to obtain the actual light intensity; Determine the light intensity deviation according to the actual light intensity and the light intensity valley value using a preset deviation rate calculation method; When the light intensity deviation does not exceed a preset disturbance interval, the refraction area is determined based on the side-ray; The preset zoom glasses are controlled to adjust the refractive index of the light according to the refractive area.

2. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 1, characterized in that: It also includes a prompting device preset on the zoom glasses, and an eye relaxation method, which includes: When the eye distance falls into the preset relaxation interval, the relaxation time is matched from the preset relaxation time database according to the eye time; Determine the focus change curve according to the relaxation time; Determine relaxation control parameters according to the focal length variation curve; Determine voice prompt parameters according to the focal length change curve; The preset zoom glasses are controlled to adjust the focal length according to the relaxation control parameters, and the prompt device preset on the zoom glasses is controlled to give voice prompts according to the voice prompt parameters.

3. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 2, characterized in that: The invention also includes a method for generating an eye fatigue interval, wherein the method comprises: When the eye distance falls into the preset visual interval, a reference interval is matched from a preset reference interval database according to the eye distance; Determine whether the patient is viewing an electronic screen based on visual images; When the patient is watching an electronic screen, the screen impact factor is determined based on the visual image; Determine if the patient is reading text based on visual images; The font influence factor was determined based on the visual image when the patient was reading text or not; Determine the eye fatigue interval based on the benchmark interval, screen influence factor and font influence factor.

4. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 3, characterized in that: The method for generating an eye fatigue interval further includes: When the eye distance falls into the preset visual interval, the refractive index is determined according to the visual image; Determine the direction of light based on visual images; Determine the refraction influence factor based on the light direction and refractive index; Determine the eye fatigue interval based on the benchmark interval, screen influence factor, font influence factor and refraction influence factor.

5. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 1, characterized in that: It also includes a reference light group preset on the zoom glasses, and the anti-electromagnetic interference method also includes: When the eye distance falls into the preset visual interval, determining whether the eye distance can be directly identified based on the visual image; When the eye distance cannot be directly identified, the reference light group preset on the zoom glasses is controlled to be turned on and off, and a reference image illuminated by the reference light group is obtained, and the reference image can be obtained by a camera on the zoom glasses; Determine a reference distance based on a reference image; When the eye distance can be directly identified, the reference distance is determined based on the visual image; Based on the identification of the reference distance, the difference between the reference distance and the eye distance is calculated and defined as the distance deviation; When the distance deviation does not exceed the preset deviation range, the eye use time is obtained.

6. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 1, characterized in that: Also included is a glasses adjustment method, the glasses adjustment method comprising: Acquire a wearing image of the glasses, where the wearing image may be acquired by a camera on the zoom glasses; Determine the three-dimensionality of the face based on the worn image; Determine the wearing height based on the three dimensions of the face; Determine the parameters of the bridge of the nose based on the three-dimensional face; Determine nose pad control parameters according to wearing height and nose bridge parameters; The preset zoom glasses are controlled to adjust the nose pads according to the nose pad control parameters.

7. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 6, characterized in that: The glasses adjustment method further comprises: Determine a set of wearing feature points according to wearing height and three-dimensional face; Determine the facial curve according to the wearing feature point set; Determine the lens angle according to the facial curve; Determine lens control parameters according to lens angle; The preset varifocal glasses are controlled to adjust the lens angle according to the lens control parameters.

8. The artificial intelligence-based device for alleviating pseudomyopia in adolescents according to claim 7, characterized in that: The glasses adjustment method further comprises: Obtaining pressure information of the temples of varifocal glasses; Determine whether the temple angle needs to be adjusted based on the pressure information; When the angle of the temple needs to be adjusted, the wearing position is determined according to the pressure information, and the current angle of the temple is obtained; Determine the adjustment angle according to the wearing position, current angle and pressure information; Determine temple control parameters according to adjustment angle; The temple adjustment angles preset on the varifocal glasses are controlled according to the temple control parameters.

Images