Health diagnosis and treatment wearable equipment based on visual regulation and control

Abstract

The invention discloses a health diagnosis and treatment wearable device based on visual regulation and control, and relates to the field of wearable devices, the health diagnosis and treatment wearable device comprises a glasses frame, lenses and glasses legs connected to two sides of the glasses frame, and the lenses are provided with phototherapy units; functional modules are arranged on the glasses legs, and each functional module comprises a control unit, a monitoring unit, a power supply unit and a communication module; monitoring and phototherapy functions are integrated, daily wearing is facilitated, and the problems that existing equipment is single in function and inconvenient to carry are solved; various phototherapy combinations are realized through the micro-nano display screen array and multi-primary-color setting, and a personalized phototherapy scheme can be provided according to the physiological state of a user; the user side supports health data report viewing and expert suggestion receiving, and a closed-loop health service of'monitoring-analysis-treatment-management 'is formed.

Description

Technical Field

[0001] The present invention relates to the technical field of wearable devices, and more particularly to a wearable device for health diagnosis and treatment based on visual control. Background Art

[0002] With the accelerating pace of life and increasing work pressure, health problems such as visual fatigue and insomnia are becoming increasingly common. Existing wearable devices have relatively limited functions. For example, smart bracelets mainly focus on motion monitoring and heart rate detection, and ordinary glasses only have vision correction functions. Although some light therapy devices exist, most of them are used independently, are not easy to carry, and cannot be integrated with users' daily wearable devices, making it difficult to meet users' needs for health diagnosis and treatment anytime, anywhere in daily life scenarios. At the same time, current light therapy devices have shortcomings in light regulation and targeted treatment, and cannot provide personalized light therapy plans based on the health status and needs of different users.

[0003] Therefore, there is an urgent need for a wearable device that integrates multiple functions, is easy to wear, and can achieve personalized visual control and health diagnosis and treatment. Summary of the Invention

[0004] In view of this, the present invention provides a wearable device for health diagnosis and treatment based on visual regulation to solve the problems existing in the background technology.

[0005] In order to achieve the above object, the present invention adopts the following technical solutions:

[0006] A wearable device for health diagnosis and treatment based on visual control, comprising: a frame, lenses, and temples connected to both sides of the frame, wherein the lenses are provided with a light therapy unit; the temples are provided with a functional module, wherein the functional module includes a control unit, a monitoring unit, a power supply unit, and a communication module;

[0007] The monitoring unit is used to monitor the user's physiological index data and transmit the collected data to the control unit in real time;

[0008] The control unit is used to receive data collected by the monitoring unit, analyze and process the data to obtain light control parameters, and control the light therapy unit to emit corresponding combined light according to the light control parameters;

[0009] The light therapy unit forms a combination of light with different therapeutic effects;

[0010] The power supply unit supplies power to the control unit, the phototherapy unit and the monitoring unit;

[0011] The communication module realizes the connection between the device and the user terminal;

[0012] On the user side, view health data reports and set up personalized health treatment plans.

[0013] Optionally, the user terminal allows users to view health data reports, which include visual fatigue level and sleep quality analysis; and receive health advice and treatment plan push from medical experts.

[0014] Optionally, the phototherapy unit is provided with a transparent micro-nano display array, the transparent micro-nano display array includes M micro-nano displays, and the pixel array of the micro-nano display is m×n; wherein, M is a natural number greater than or equal to 2, and m and n are natural numbers greater than or equal to 16.

[0015] Optionally, the micro-nano display screen includes an N-primary color monochrome screen, where N is a natural number greater than or equal to 3; the primary colors of the N-primary color monochrome screen include three primary colors of red, green, and blue, or six primary colors of red, green, blue, cyan, magenta, and yellow; the N-primary color monochrome screen includes a display screen that directly emits light of a specific wavelength, a monochrome display screen achieved through color conversion, and a monochrome display screen achieved through a superstructure surface.

[0016] Optionally, the specific process of the control unit analyzing and processing the data includes:

[0017] The data collected is brain wave data;

[0018] Performing multi-scale wavelet decomposition on the EEG data to obtain sub-bands of different frequencies, and calculating characteristic parameters of each sub-band;

[0019] Normalizing the characteristic parameters to obtain a standardized characteristic vector;

[0020] The standardized feature vector is input into a preset deep convolutional recurrent neural network analysis model. A sliding convolution operation is performed on the standardized feature vector using multiple convolution kernels to extract local correlation information between features. The time series information of the standardized feature vector is processed through the long short-term memory network unit of the recurrent layer to capture the dynamic changes of brain waves over time.

[0021] The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and output the user's current physiological state assessment result;

[0022] According to the physiological status assessment results, the preset database is queried to obtain the corresponding light control parameters.

[0023] Optionally, after controlling the light therapy unit to emit corresponding combined light according to the light control parameters, the method further includes:

[0024] Obtaining user information of the user;

[0025] Based on the light control parameters, a lighting parameter matrix is ​​constructed;

[0026] mutating the illumination parameter matrix based on the user information to obtain a mutated illumination parameter matrix;

[0027] generating a communication key based on the user information and the variation illumination parameter matrix;

[0028] After the variation illumination parameter matrix is ​​encrypted based on the communication key, it is transmitted to the user end through the communication module.

[0029] Optionally, the specific process of the user terminal analyzing the degree of visual fatigue is:

[0030] Setting an eye movement data acquisition unit to collect eye movement data;

[0031] inputting the collected eye movement data into a fatigue detection unit;

[0032] The fatigue detection unit uses a deep learning model to extract, fuse and classify features of eye movement data and output the user's fatigue level.

[0033] Optionally, the deep learning model includes an input layer, a first convolutional layer, a second pooling layer, a third convolutional layer, a fourth pooling layer, a fifth convolutional layer, a sixth fully connected layer, a seventh fully connected layer and an output layer; wherein the activation functions of the first convolutional layer, the second pooling layer, the third convolutional layer, the fourth pooling layer, the fifth convolutional layer and the sixth fully connected layer are ReLU nonlinear activation functions, the activation function of the seventh fully connected layer is a Softmax activation function, and the number of neurons in the output layer is 4, corresponding to the four categories of health, mild fatigue, moderate fatigue and severe fatigue respectively.

[0034] Optionally, the sleep quality analysis may further include a sound collection unit, which monitors and records the user's sound during sleep in real time and pre-processes the sound; analyzes the collected sound features; and establishes a correspondence between the sound features and the sleep stages;

[0035] Evaluate the current sound characteristics and map them into corresponding relationships to determine the user's current sleep quality status.

[0036] It can be seen from the above technical solution that compared with the existing technology, the present invention discloses a wearable health diagnosis and treatment device based on visual regulation, including: a frame, lenses and temples connected to both sides of the frame, and a phototherapy unit is provided on the lenses; a functional module is provided on the temples, and the functional module includes a control unit, a monitoring unit, a power supply unit and a communication module; the monitoring unit is used to monitor the user's physiological indicator data and transmit the collected data to the control unit in real time; the control unit is used to receive the data collected by the monitoring unit, and analyze and process the data to obtain light control parameters, and control the phototherapy unit to emit corresponding combination light according to the light control parameters; the phototherapy unit forms a combination light with different therapeutic effects; the power supply unit supplies power to the control unit, the phototherapy unit and the monitoring unit; the communication module realizes the connection between the device and the user end; the user end views the health data report and sets a personalized health diagnosis and treatment plan. The present invention integrates monitoring and phototherapy functions, making it easy to wear in daily life, and solving the problem of existing devices having single functions and being inconvenient to carry. It realizes various phototherapy combinations through micro-nano display screen array and multi-primary color setting, and can provide personalized phototherapy plans according to the user's physiological state. The user end supports viewing health data reports and receiving expert advice, forming a closed-loop health service of "monitoring-analysis-treatment-management". BRIEF DESCRIPTION OF THE DRAWINGS

[0037] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are merely embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying any creative work.

[0038] Figure 1 This is a schematic diagram of the system structure provided by the present invention.

[0039] Figure 2 This is a schematic diagram of the structure of the deep learning model in the user terminal provided by the present invention. DETAILED DESCRIPTION

[0040] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. 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 making creative efforts are within the scope of protection of the present invention.

[0041] The embodiment of the present invention discloses a wearable device for health diagnosis and treatment based on visual control, such as Figure 1As shown, it includes: a frame, lenses and temples connected to both sides of the frame, the lenses are provided with a light therapy unit; the temples are provided with a functional module, the functional module includes a control unit, a monitoring unit, a power supply unit and a communication module;

[0042] A monitoring unit is used to monitor the user's physiological index data and transmit the collected data to the control unit in real time;

[0043] The control unit is used to receive the data collected by the monitoring unit, analyze and process the data, obtain light control parameters, and control the phototherapy unit to emit corresponding combined light according to the light control parameters;

[0044] Light therapy unit, which forms a combination of light with different therapeutic effects;

[0045] The power supply unit supplies power to the control unit, the phototherapy unit and the monitoring unit;

[0046] Communication module, which realizes the connection between the device and the user end;

[0047] On the user side, view health data reports and set up personalized health treatment plans.

[0048] In a specific embodiment, the user terminal allows users to view health data reports, which include visual fatigue level and sleep quality analysis; and receive health advice and treatment plan push from medical experts.

[0049] In a specific embodiment, the phototherapy unit is provided with a transparent micro-nano display array, which includes M micro-nano display screens, and the pixel array of the micro-nano display screen is m×n; wherein M is a natural number greater than or equal to 2, and m and n are natural numbers greater than or equal to 16.

[0050] In one specific embodiment, the micro-nano display screen includes an N-primary color monochrome screen, where N is a natural number greater than or equal to 3. The primary colors of the N-primary color monochrome screen include red, green, and blue, or red, green, blue, cyan, magenta, and yellow. The N-primary color monochrome screen includes displays that directly emit light of a specific wavelength, monochrome displays achieved through color conversion, and monochrome displays achieved through superstructured surfaces. It should be noted that multi-primary color screens utilize color primitives other than red, green, and blue, such as yellow, to more accurately reproduce and represent the diverse colors of nature. Due to the addition of color primitives, multi-primary color screens can cover a wider color gamut, resulting in a more realistic and vivid display. Multi-primary color technology can be combined with high-resolution displays, enabling the screen to accurately present various color combinations and a sense of depth.

[0051] In a specific embodiment, the specific process of the control unit analyzing and processing the data includes:

[0052] In this embodiment, first, multi-scale wavelet decomposition is performed on the brainwave data to obtain sub-bands of different frequencies, and the characteristic parameters of each sub-band are calculated. The brainwave signal contains different frequency components, and brainwaves of different frequencies are related to different physiological and psychological states of the human body. Multi-scale wavelet decomposition can decompose the brainwave signal into different frequency sub-bands, such as δ waves (0.5-4Hz), θ waves (4-8Hz), α waves (8-13Hz), β waves (13-30Hz) and γ waves (30-100Hz). By calculating the characteristic parameters of each sub-band, such as energy, mean, standard deviation, etc., key information related to the user's physiological state in the brainwave signal can be extracted, providing a basis for subsequent analysis.

[0053] The feature parameters obtained above are normalized to obtain standardized feature vectors. Different feature parameters may have different dimensions and value ranges, which can affect model training and performance. Normalization maps all features to the same scale, eliminating dimensional differences. This allows the model to treat each feature more fairly, improving model convergence speed and stability. The standardized feature vectors prepare for subsequent input into the deep convolutional recurrent neural network analysis model.

[0054] The normalized feature vector is then input into a pre-set deep convolutional recurrent neural network analysis model. Multiple convolution kernels are used to perform sliding convolutions on the normalized feature vector to extract local correlation information between features. A convolution kernel is a small matrix that, when performing a sliding convolution operation on the normalized feature vector, performs a weighted summation of the features in the local region, thereby extracting local correlation information between features. Different convolution kernels can learn different local feature patterns, and the combination of multiple convolution kernels can more comprehensively capture the relationships between features. This local feature extraction method can reduce the number of model parameters and improve the model's generalization ability.

[0055] The Long Short-Term Memory (LSTM) unit in the recurrent layer processes the time series information of the standardized feature vectors, capturing the dynamic changes in brainwaves over time. Brainwave data is a signal with time series characteristics, meaning that there are correlations between data at different times. The LSTM unit has a memory function and can effectively process sequential data. Through the forget gate, input gate, and output gate mechanism, it selectively retains and updates information, thereby capturing the dynamic changes in brainwaves over time. This is crucial for accurately assessing the user's physiological state, which often changes over time.

[0056] The fully connected layer integrates and maps the features extracted by the convolutional and recurrent layers, outputting an assessment of the user's current physiological state. The convolutional and recurrent layers extract local correlation and temporal information, respectively, but this information is dispersed. The fully connected layer integrates all features and, through a series of linear transformations and nonlinear activation functions, maps them into a low-dimensional space to produce an assessment of the user's current physiological state. This assessment can be a classification of the user's physiological state (e.g., relaxed, tense, fatigued, etc.) or a quantitative assessment of their physiological state.

[0057] Finally, based on the physiological state assessment results, the preset database is queried to obtain the corresponding light control parameters. The correction rule base is established based on a large amount of clinical data and medical knowledge, which contains adjustment strategies for light therapy plans under different physiological states. According to the user's current physiological state assessment results, the corresponding light control parameters are searched in the preset database to obtain control parameters for light intensity, start time, color temperature, wavelength, stroboscopic frequency, treatment course, etc. These light control parameters form a light therapy plan to improve the effect and personalization of light therapy. Among them, the characteristic parameters include energy proportion and average frequency;

[0058] In a specific embodiment, after controlling the light therapy unit to emit corresponding combined light according to the light control parameter, the method includes:

[0059] Get the user's user information;

[0060] Based on the light control parameters, a lighting parameter matrix is ​​constructed;

[0061] Based on user information, the lighting parameter matrix is ​​mutated to obtain a mutated lighting parameter matrix;

[0062] Generate communication keys based on user information and the mutated illumination parameter matrix;

[0063] The variation illumination parameter matrix is ​​encrypted based on the communication key and then transmitted to the user end through the communication module.

[0064] In this embodiment, the user information mentioned above includes important individual characteristics such as age, gender, medical history, and lifestyle habits. This information not only reflects the user's physiological and health status but is also closely linked to the effectiveness and safety of the light therapy plan. In subsequent steps, user information will serve as a key factor in mutating the light parameter matrix and generating communication keys, ensuring personalized treatment and secure data transmission throughout the entire process.

[0065] A light therapy plan defines the specific parameters of the light therapy system, such as light intensity, start time, color temperature, wavelength, stroboscopic frequency, and duration of treatment. Organizing these parameters in a matrix format allows for a more systematic and standardized representation of light therapy plan information. As a structured data set, the light parameter matrix facilitates subsequent mathematical operations and processing, and serves as the foundation for personalized adjustments and encrypted transmission.

[0066] Based on user information, the lighting parameter matrix is ​​mutated to obtain a variant lighting parameter matrix. Different users have different physical conditions and needs. By combining user information to mutate the lighting parameter matrix, the lighting parameters can be fine-tuned according to the user's individual characteristics, making it more unique and safe.

[0067] Next, a communication key is generated based on the user information and the mutated illumination parameter matrix. The communication key plays a crucial role in data transmission and is crucial for ensuring data security. Both user information and the mutated illumination parameter matrix are unique and specific. Combining them to generate the communication key ensures a high degree of randomness and complexity. This generated communication key effectively prevents data theft or tampering during transmission, ensuring that only authorized parties with the correct key can decrypt and access the data.

[0068] Finally, the variant light parameter matrix is ​​encrypted using the communication key and transmitted to the user. Using the communication key to encrypt the variant light parameter matrix converts sensitive light therapy data into ciphertext. Even if the data is intercepted during transmission, attackers lacking the correct key cannot access the data. Transmitting the encrypted variant light parameter matrix to the user allows users to view and manage their light therapy plans at any time, while ensuring data security and privacy, meeting the security requirements of modern medical data management.

[0069] In a specific embodiment, the specific process of analyzing the degree of visual fatigue by the user terminal is as follows:

[0070] Setting an eye movement data acquisition unit to collect eye movement data;

[0071] inputting the collected eye movement data into a fatigue detection unit;

[0072] The fatigue detection unit uses a deep learning model to extract, fuse and classify features of eye movement data and output the user's fatigue level.

[0073] In a specific embodiment, Figure 2As shown, the deep learning model includes an input layer (input), three convolutional layers (i.e., conv1, conv2, conv3), two maximum pooling layers (i.e., max pooling1, max pooling2), two fully connected layers (i.e., fc1 and fc2), and an output layer (output). Specifically, the first is the data input layer, where the input is eye movement data. The first layer is a convolutional layer, the second layer is a maximum pooling layer, the third layer is a convolutional layer, the fourth layer is a maximum pooling layer, the fifth layer is a convolutional layer, the sixth and seventh layers are fully connected layers, and the eighth layer is the output layer. The activation function of the first six layers is the ReLU nonlinear activation function, the activation function of the seventh layer is the Softmax activation function, and the number of neurons in the output layer can be set to 4, corresponding to the four categories of health, mild fatigue, moderate fatigue, and severe fatigue.

[0074] Specifically, the number of neurons in the input, hidden, and output layers, as well as the size of the convolution kernel, are set. The weight matrices are randomly initialized, including the weight matrices between the input and hidden layers, between hidden layers, and between hidden layers and the output layer. Eye movement data is fed into the neural network as input. Based on the initialized weight matrices, the weight matrices between each layer of the neural network are trained using forward and backpropagation algorithms and gradient descent. Finally, the loss function for the output layer is the cross-entropy loss function.

[0075] In a specific embodiment, the sleep quality analysis specifically includes:

[0076] A sound collection unit may also be provided to monitor and record the user's sound during sleep in real time, and pre-process the sound; analyze the collected sound features; and establish a correspondence between the sound features and the sleep stages;

[0077] Evaluate the current sound characteristics and map them into corresponding relationships to determine the user's current sleep quality status.

[0078] Specifically, a microphone or other sound collection device is used to monitor and record the user's breathing sounds, snoring sounds, etc. during sleep in real time and perform pre-processing.

[0079] Preprocessing includes preprocessing the collected sound data, such as denoising and segmentation, to extract useful sound features.

[0080] Specifically, the collected original sound data is denoised to eliminate interference such as background noise and current noise; the effective speech segments in the sound signal are detected using methods such as energy criteria, and the breathing sounds and snoring sounds are separated. After segmentation, pure breathing sound segments and snoring sound segments are obtained.

[0081] Analyze the characteristics of breathing sounds and snoring sounds, including parameters such as amplitude, frequency, and duration.

[0082] Specifically, digital signal processing technology is used to analyze the preprocessed sound data and extract key characteristic parameters. For example, the amplitude can be obtained by calculating the peak value or effective value of the sound waveform; the frequency can be obtained through spectrum analysis methods such as Fourier transform. The main frequency of breathing sounds is usually in the range of 200-600Hz, while the main frequency of snoring sounds is lower, in the range of 30-300Hz; the duration can be calculated by detecting the starting and ending points of the sound signal.

[0083] Establish a correspondence between sound characteristics and sleep stages.

[0084] Specifically, through a large number of experiments and data collection, we studied the breathing patterns and snoring patterns during different sleep stages (such as light sleep, deep sleep, rapid eye movement sleep, etc.), analyzed the changing patterns of sound characteristics such as breathing frequency, breathing depth (amplitude), snoring frequency, and duration in each sleep stage, and established a correspondence between sound characteristics and sleep stages for subsequent automatic judgment.

[0085] Specifically, the process of establishing the correspondence between sound features and sleep stages is as follows:

[0086] Use data mining methods to discover potential patterns and regularities from large amounts of data, such as: higher breathing rate and amplitude during light sleep, less regular breathing, lower breathing rate and amplitude during deep sleep, regular breathing, more frequent snoring, and dramatic changes in breathing rate and amplitude during rapid eye movement sleep.

[0087] Build a mapping model between sound features and sleep stages:

[0088] θ=f(S,R,A,D,M)

[0089]

[0090] Among them, S is the sound feature; R is the respiratory rate; A is the respiratory amplitude; D is the snoring frequency; M is the rapid eye movement sleep marker; θ is the sleep stage (the value is light sleep, deep sleep, rapid eye movement sleep); f() represents a complex information filtering function used to process the noise and uncertainty of the data; the combination forms a complex mapping model, which can reflect the relationship between sound features and sleep stages to a certain extent, and can be mapped to different sleep stages according to specific data and parameter values.

[0091] It should be noted that different individuals may have differences in breathing patterns, snoring conditions, etc., which will affect the distribution of sound features. For specific individuals, the parameters of the mapping model can be fine-tuned based on their small amount of sleep data to obtain a personalized classification model.

[0092] In the absence of individual data, techniques such as cluster analysis can be used to divide individuals into different categories and train an adaptive model for each category.

[0093] Evaluate the current sound characteristics and map them to the corresponding relationship to determine the user's current sleep quality status.

[0094] Specifically, the user side receives the detection data from the device in real time and extracts the user's breathing and snoring sound features, inputs the extracted features into the recognition algorithm, continuously judges the current sleep state, and determines the user's entire sleep process and sleep cycle pattern based on changes in the sleep state, thereby forming a health data report.

[0095] In a specific embodiment, the monitoring unit includes a brain wave acquisition unit, an eye movement data acquisition unit, and the above-mentioned sound acquisition unit;

[0096] The EEG acquisition unit includes

[0097] Sensor type: 2 dry electrodes (Ag / AgCl), integrated into the inside of the right eyeglass leg, contacting the temple area;

[0098] Sampling parameters: 1024Hz sampling rate, 0.1-100Hz bandwidth filtering

[0099] Signal processing: built-in low-noise amplifier (gain 1000 times) + 24-bit ADC converter, converting EEG signals into digital quantities in real time;

[0100] Eye movement data acquisition module

[0101] Sensor type: Micro infrared camera (resolution 640×480) + near-infrared LED light source (wavelength 850nm)

[0102] Installation location: Inside the frame, above the bridge of the nose, with the lens facing the user's eyeballs

[0103] Acquisition parameters: 30fps frame rate, capturing blink frequency, pupil diameter changes and eye movement trajectory.

[0104] In a specific embodiment, the monitoring unit may also include an ECG signal acquisition unit, specifically: flexible conductive silicone electrodes (ECG signal acquisition unit) are embedded in the inner side of the left and right temples of the glasses where they touch the temples or the skin behind the ears. By taking advantage of the low skin resistance of the earlobes, temples and other parts of the human body (the resistance value is usually <5kΩ), stable ECG signal (ECG) acquisition can be achieved. This design avoids the inconvenience of wearing traditional chest electrodes. The electrode thickness is ≤0.3mm, and it naturally fits the curvature of the inner side of the temples, so there is no foreign body sensation during daily wear.

[0105] 2. Microelectrode array at the nose pad

[0106] A microelectrode array (such as a 0.1mm thick flexible metal sheet or PEDOT:PSS conductive polymer) is integrated where the nose pads touch the nose bridge. ECG signals are collected through the skin on the nose bridge, which can be coordinated with eye movement monitoring and EEG acquisition to achieve multi-site signal synergy:

[0107] Multi-dimensional data fusion: Synchronously acquire eye movement trajectories (such as blink frequency), EEG alpha wave intensity, and ECG RR interval to provide more comprehensive physiological indicators for fatigue assessment;

[0108] Low-interference design: The electrode array and nose pads are integrated into one, and the surface is covered with a nano-scale biocompatible coating, which does not affect the aesthetics and comfort of wearing glasses.

[0109] 2. Quantum dot technology upgrade for phototherapy units

[0110] The light therapy unit can be combined with quantum dots (QDs) optical technology, and the specific implementation method is as follows:

[0111] By utilizing the exciton confinement effect of quantum dot nanomaterials, narrow-band light-emitting units with a full width at half maximum (FWHM) less than 20nm are prepared and integrated into a transparent micro-nano display array. Compared with traditional LED light therapy, quantum dot light therapy has the following advantages:

[0112] Improved treatment specificity: For example, for visual fatigue, it can accurately emit 550nm green light (half-maximum width 15nm), specifically activate retinal ganglion cells (ipRGCs), and regulate pupillary light reflex and intraocular pressure;

[0113] Energy efficiency optimization: Quantum dot light conversion efficiency is greater than 95%, reducing energy consumption by 40% at the same phototherapy intensity, and avoiding the radiation risk of non-therapeutic bands (such as ultraviolet light);

[0114] Dynamically adjustable spectrum: By regulating the size (2-10nm) and composition (such as CdSe / ZnS core-shell structure) of quantum dots, it covers a wavelength range of 380-1700nm and adapts to different diagnosis and treatment scenarios (such as 660nm red light to promote melatonin secretion and 850nm near-infrared light to improve cerebral blood flow).

[0115] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. Reference can be made to the common and similar parts between the various embodiments. For the devices disclosed in the embodiments, since they correspond to the methods disclosed in the embodiments, the description is relatively simple, and the relevant parts can be referred to the method description.

[0116] The above description of the disclosed embodiments is intended to enable one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be readily apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention is not limited to the embodiments shown herein but is intended to conform to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A wearable device for health diagnosis and treatment based on visual control, characterized in that: include: A frame, lenses, and temples connected to both sides of the frame, wherein the lenses are provided with a light therapy unit; the temples are provided with a functional module, which includes a control unit, a monitoring unit, a power supply unit, and a communication module; The monitoring unit is used to monitor the user's physiological index data and transmit the collected data to the control unit in real time; The control unit is used to receive data collected by the monitoring unit, analyze and process the data to obtain light control parameters, and control the light therapy unit to emit corresponding combined light according to the light control parameters; The light therapy unit forms a combination of light with different therapeutic effects; The power supply unit supplies power to the control unit, the phototherapy unit and the monitoring unit; The communication module realizes the connection between the device and the user terminal; On the user side, view health data reports and set up personalized health treatment plans.

2. A wearable device for health diagnosis and treatment based on visual control according to claim 1, characterized in that: The user terminal allows users to view health data reports, including visual fatigue level and sleep quality analysis; and receive health advice and treatment plan push from medical experts.

3. A wearable device for health diagnosis and treatment based on visual control according to claim 1, characterized in that: The phototherapy unit is provided with a transparent micro-nano display array, which includes M micro-nano display screens. The pixel array of the micro-nano display screen is m×n; wherein M is a natural number greater than or equal to 2, and m and n are natural numbers greater than or equal to 16.

4. A wearable device for health diagnosis and treatment based on visual control according to claim 3, characterized in that: The micro-nano display screen includes an N-primary color monochrome screen, where N is a natural number greater than or equal to 3; the primary colors of the N-primary color monochrome screen include three primary colors of red, green, and blue, or six primary colors of red, green, blue, cyan, magenta, and yellow. The N-primary color monochrome screen includes a display screen that directly emits light of a specific wavelength, a monochrome display screen achieved through color conversion, and a monochrome display screen achieved through a superstructure surface.

5. The wearable device for health diagnosis and treatment based on visual control according to claim 1, characterized in that: The specific process of the control unit analyzing and processing the data includes: The data collected is brain wave data; Performing multi-scale wavelet decomposition on the EEG data to obtain sub-bands of different frequencies, and calculating characteristic parameters of each sub-band; Normalizing the characteristic parameters to obtain a standardized characteristic vector; The standardized feature vector is input into a preset deep convolutional recurrent neural network analysis model. A sliding convolution operation is performed on the standardized feature vector using multiple convolution kernels to extract local correlation information between features. The time series information of the standardized feature vector is processed through the long short-term memory network unit of the recurrent layer to capture the dynamic changes of brain waves over time. The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and output the user's current physiological state assessment result; According to the physiological status assessment results, the preset database is queried to obtain the corresponding light control parameters.

6. A wearable device for health diagnosis and treatment based on visual control according to claim 1, characterized in that: After controlling the light therapy unit to emit corresponding combined light according to the light control parameters, the method includes: Obtaining user information of the user; Based on the light control parameters, a lighting parameter matrix is ​​constructed; mutating the illumination parameter matrix based on the user information to obtain a mutated illumination parameter matrix; generating a communication key based on the user information and the variation illumination parameter matrix; After the variation illumination parameter matrix is ​​encrypted based on the communication key, it is transmitted to the user end through the communication module.

7. The wearable device for health diagnosis and treatment based on visual control according to claim 2, characterized in that: The specific process of analyzing the degree of visual fatigue by the user terminal is as follows: Setting an eye movement data acquisition unit to collect eye movement data; inputting the collected eye movement data into a fatigue detection unit; The fatigue detection unit uses a deep learning model to extract, fuse and classify features of eye movement data and output the user's fatigue level.

8. The wearable device for health diagnosis and treatment based on visual control according to claim 7, characterized in that: The deep learning model includes an input layer, a first convolutional layer, a second pooling layer, a third convolutional layer, a fourth pooling layer, a fifth convolutional layer, a sixth fully connected layer, a seventh fully connected layer and an output layer; wherein the activation functions of the first convolutional layer, the second pooling layer, the third convolutional layer, the fourth pooling layer, the fifth convolutional layer and the sixth fully connected layer are ReLU nonlinear activation functions, the activation function of the seventh fully connected layer is Softmax activation function, and the number of neurons in the output layer is 4, corresponding to the four categories of health, mild fatigue, moderate fatigue and severe fatigue respectively.

9. The wearable device for health diagnosis and treatment based on visual control according to claim 2, characterized in that: The sleep quality analysis specifically includes: providing a sound collection unit, monitoring and recording the user's sound during sleep in real time through the sound collection unit, and pre-processing the sound; analyzing the collected sound features; Establishing a correspondence between sound characteristics and sleep stages; Evaluate the current sound characteristics and map them into corresponding relationships to determine the user's current sleep quality status.

Images