Illumination therapy system control method and equipment based on intelligent analysis and storage medium

Abstract

The invention provides a light therapy system control method and device based on intelligent analysis and a storage medium, and the method comprises the steps: obtaining an MEQ scale test result of a user, and obtaining a sleep mode of the user; detecting basic data of a user; generating an initial illumination scheme based on basic data and the sleep mode; the initial illumination scheme at least comprises initial parameter setting of illumination intensity, starting time, color temperature, wavelength, stroboflash and treatment course of the illumination treatment system; in the illumination process of the user, brain wave data and heart rate data of the user are collected in real time; outputting corresponding correction data by using a preset analysis model; and correcting the initial illumination scheme based on the correction data to obtain a corrected illumination scheme for controlling the illumination treatment system. According to the invention, the defects that the traditional illumination treatment system cannot combine with the multi-dimensional information of the user and cannot automatically adjust the illumination scheme according to the real-time physiological state of the user are overcome.

Description

Technical Field

[0001] The present invention relates to the technical field of light control, and in particular to a light therapy system control method, device and storage medium based on intelligent analysis. Background Art

[0002] Traditional light therapy has many shortcomings in program formulation. In the early days, light therapy mainly set light parameters based on the doctor's experience, lacking scientific quantitative basis. This method is difficult to accurately match the specific needs of each user, and the lighting effects vary. For example, for users with different sleep patterns, a unified light schedule may not effectively improve their sleep conditions. Some users may not only fail to relieve symptoms, but may even aggravate sleep disorders due to improper light timing.

[0003] Some solutions only set the lighting time according to the user's sleep duration, ignoring the user's biological clock type (such as early to bed and early to rise, or late to bed and late to rise), resulting in poor lighting effects.

[0004] In addition, current phototherapy systems lack intelligence and personalization. Most systems cannot automatically adjust the treatment plan according to the user's real-time physiological state, and require manual intervention by doctors, which not only increases the workload of doctors, but may also affect the treatment effect due to untimely adjustments. Summary of the invention

[0005] The main purpose of the present invention is to provide a light therapy system control method, device and storage medium based on intelligent analysis, aiming to overcome the defects of traditional light therapy systems that cannot combine multi-dimensional information of users and cannot automatically adjust the lighting scheme according to the real-time physiological state of users.

[0006] To achieve the above object, the present invention provides a method for controlling a light therapy system based on intelligent analysis, comprising the following steps:

[0007] Obtain the user's MEQ scale test results to obtain the user's sleep pattern; detect the user's basic data; the basic data includes symptoms and severity, strong light acceptance, and contraindication information;

[0008] Based on the basic data and the sleep mode, an initial illumination scheme is generated; the initial illumination scheme at least includes initial parameter settings for the illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system;

[0009] During the illumination process of the user by the illumination therapy system, the user's brain wave data and heart rate data are collected in real time, and the heart rate variability analysis is performed to obtain the heart rate variability analysis result;

[0010] Based on the brain wave data and heart rate variability analysis results, output corresponding correction data using a preset analysis model;

[0011] The initial illumination scheme is modified based on the correction data to obtain a modified illumination scheme; and the light therapy system is controlled based on the modified illumination scheme.

[0012] Furthermore, the initial lighting scheme also includes selecting corresponding videos and music from a pre-stored multimedia resource library.

[0013] Furthermore, based on the brain wave data and the heart rate variability analysis results, a preset analysis model is used to output corresponding correction data, including:

[0014] Perform multi-scale wavelet decomposition on the EEG data to obtain sub-bands of different frequencies, and calculate characteristic parameters of each sub-band; extract time domain features and frequency domain features based on the heart rate variability analysis results;

[0015] Normalizing the characteristic parameters, time domain characteristics, and frequency domain characteristics to obtain a standardized characteristic vector;

[0016] The standardized feature vector is input into the preset deep convolutional recurrent neural network analysis model, and a sliding convolution operation is performed on the standardized feature vector through multiple convolution kernels to extract the local correlation information between the 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 change characteristics of brain waves and heart rate variability over time;

[0017] The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and the user's current physiological state assessment result is output;

[0018] According to the physiological status assessment results, the preset correction rule library is queried to obtain the corresponding correction data.

[0019] Furthermore, the characteristic parameters include energy proportion and average frequency;

[0020] The time domain features include average heart rate, root mean square of adjacent RR interval differences, and percentage of adjacent RR interval differences greater than 50ms; the frequency domain features include low frequency power, high frequency power, and the ratio of low frequency power to high frequency power.

[0021] Furthermore, based on the brain wave data and the heart rate variability analysis results, a preset analysis model is used to output corresponding correction data, including:

[0022] Inputting the EEG data and heart rate variability analysis results into a preset analysis model;

[0023] Through the fuzzy logic in the analysis model, the continuous EEG data and the heart rate variability analysis results are mapped to different fuzzy sets, and the membership in the corresponding fuzzy sets is determined, and the preliminary parameter adjustment direction is inferred based on the fuzzy rules;

[0024] By using the genetic algorithm in the analysis model, based on the preliminary parameter adjustment direction, the adjustment range of light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course is iteratively optimized, and finally the corresponding correction data is output.

[0025] Further, after controlling the light therapy system based on the modified light scheme, the method includes:

[0026] Obtaining user information of the user;

[0027] Based on the modified illumination scheme, construct an illumination parameter matrix;

[0028] Based on the user information, mutating the illumination parameter matrix to obtain a mutated illumination parameter matrix;

[0029] Generate a communication key based on the user information and the variable illumination parameter matrix;

[0030] After the variation illumination parameter matrix is ​​encrypted based on the communication key, it is transmitted to the user's management account.

[0031] Further, generating a communication key based on the user information and the variable illumination parameter matrix includes:

[0032] Extract key feature values ​​from user information, arrange the key feature values ​​in order to form discrete data points; fit the discrete data points to generate a smooth user information feature curve;

[0033] The variation illumination parameter matrix is ​​regarded as a two-dimensional grayscale image, and each element value in the matrix corresponds to the grayscale value of a pixel in the grayscale image; edge detection is performed on the variation illumination parameter matrix through image processing technology to extract edge contour graphics;

[0034] The user information characteristic curve and the edge contour graph are placed in a virtual four-dimensional space-time coordinate system; in the coordinate system, the time dimension uses the milliseconds of the system time as a dynamic parameter, and the space dimension is a three-dimensional Euclidean space;

[0035] According to the current system time in milliseconds, the user information characteristic curve and edge contour graph are subjected to time-space distortion transformation;

[0036] The fused graph after the space-time distortion transformation is sampled, representative points are selected, and combined into a digital sequence according to rules. The digital sequence is processed through a custom nonlinear encryption function to generate a communication key.

[0037] The present invention also provides a light therapy system control device based on intelligent analysis, comprising:

[0038] An acquisition unit is used to acquire the MEQ scale test result of the user and obtain the user's sleep pattern; detect the basic data of the user; the basic data includes symptoms and severity, strong light acceptance, and contraindication information;

[0039] A generating unit, configured to generate an initial illumination scheme based on the basic data and the sleep mode; the initial illumination scheme at least includes initial parameter settings for illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system;

[0040] The collection unit is used to collect the user's brain wave data and heart rate data in real time during the light therapy system's light treatment process, and to perform heart rate variability analysis to obtain a heart rate variability analysis result;

[0041] An analysis unit, configured to output corresponding correction data based on the brain wave data and the heart rate variability analysis results using a preset analysis model;

[0042] A control unit is used to modify the initial illumination scheme based on the correction data to obtain a modified illumination scheme; and control the light therapy system based on the modified illumination scheme.

[0043] The present invention also provides a computer device, comprising a memory and a processor, wherein the memory stores a computer program, and the processor implements the steps of any one of the above methods when executing the computer program.

[0044] The present invention also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the steps of any of the above-mentioned methods are implemented.

[0045] The light therapy system control method, device and storage medium based on intelligent analysis provided by the present invention include: obtaining the MEQ scale test result of the user to obtain the user's sleep pattern; detecting the user's basic data; the basic data include symptoms and severity, strong light acceptance, and contraindication information; generating an initial light scheme based on the basic data and the sleep pattern; the initial light scheme at least includes initial parameter settings for the light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the light therapy system; during the light therapy system's illumination of the user, real-time collection of the user's brain wave data and heart rate data, and heart rate variability analysis to obtain heart rate variability analysis results; based on the brain wave data and heart rate variability analysis results, using a preset analysis model to output corresponding correction data; based on the correction data, correcting the initial light scheme to obtain a corrected light scheme; and controlling the light therapy system based on the corrected light scheme. In the present invention, an initial lighting plan is generated by combining multi-dimensional information including basic user data and sleep patterns. At the same time, the initial lighting plan is corrected based on real-time collection of the user's brain wave data and heart rate data, thereby overcoming the defects of traditional light therapy systems that cannot combine multi-dimensional information of the user and cannot automatically adjust the lighting plan according to the user's real-time physiological state. BRIEF DESCRIPTION OF THE DRAWINGS

[0046] Figure 1 is a schematic diagram of steps of a method for controlling a light therapy system based on intelligent analysis in one embodiment of the present invention;

[0047] Figure 2 is a structural block diagram of a light therapy system control device based on intelligent analysis in one embodiment of the present invention;

[0048] Figure 3 It is a schematic block diagram of the structure of a computer device according to an embodiment of the present invention.

[0049] The implementation, functional features and advantages of the present invention will be further described in conjunction with embodiments and with reference to the accompanying drawings. DETAILED DESCRIPTION

[0050] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with 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 intended to limit the present invention.

[0051] Reference Figure 1 In one embodiment of the present invention, a method for controlling a light therapy system based on intelligent analysis is provided, comprising the following steps:

[0052] Step S1, obtaining the MEQ scale test result of the user to obtain the user's sleep pattern; detecting the user's basic data; the basic data includes symptoms and severity, strong light acceptance, and contraindication information;

[0053] Step S2, generating an initial illumination scheme based on the basic data and the sleep mode; the initial illumination scheme at least includes initial parameter settings for the illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system;

[0054] Step S3, during the illumination process of the user by the illumination therapy system, the user's brain wave data and heart rate data are collected in real time, and heart rate variability analysis is performed to obtain a heart rate variability analysis result;

[0055] Step S4, based on the EEG data and the heart rate variability analysis results, outputting corresponding correction data using a preset analysis model;

[0056] Step S5, modifying the initial illumination scheme based on the modified data to obtain a modified illumination scheme; and controlling the light therapy system based on the modified illumination scheme.

[0057] In this embodiment, as described in step S1 above, user information is comprehensively collected to provide a basis for formulating a personalized light therapy plan. Specifically, the user's MEQ (morning-evening preference questionnaire) scale test results are obtained. The MEQ scale includes questions such as self-planned waking and sleeping time, and the degree of dependence on the alarm clock. By analyzing the user's answers to these questions, their sleep pattern can be accurately judged, that is, whether it is an early bed and early rise type, a late bed and late rise type, or other types. At the same time, the user's basic data is detected (which can be done through inquiries or form filling). Symptoms and severity are determined by professional medical diagnostic standards or evaluation scales to understand the severity of the user's condition; strong light acceptance is obtained through specific light tests to clarify the user's tolerance to light of different intensities; contraindication information is checked based on medical knowledge and the user's past medical history to avoid harm to the user during the treatment process.

[0058] As described in step S2 above, according to the specific situation of the user, the various parameters of light therapy are preliminarily determined to form an initial treatment plan. Based on the data obtained in step S1 above, the initial light plan is generated in combination with clinical experience and the rules summarized by a large amount of experimental data. For example, if the user is an early-to-bed and early-to-rise type with mild symptoms and high acceptance of strong light, a lower light intensity may be set, light exposure may be performed in the morning, a suitable color temperature (such as simulating the color temperature of morning sunlight), a fixed wavelength (the visible light wavelength range set by the system hardware), no flicker, and a shorter course of treatment may be selected; on the contrary, for late-to-bed and late-to-rise users with severe symptoms and low acceptance of strong light, the parameter settings will be different to ensure that the initial plan fits the user's needs as much as possible.

[0059] As described in step S3 above, the user's physiological state is continuously monitored during the treatment process, and real-time data is obtained to evaluate the treatment effect and adjust the plan. During the light therapy, professional equipment is used to collect the user's brain wave data and heart rate data in real time. The head-mounted device for measuring brain waves collects electrical signals emitted by the brain, and obtains stable brain wave data after preprocessing such as denoising to reflect the activity state of the brain; the heart rate data is collected through the heart rate monitoring module integrated in the head-mounted device or the smart watch, and it is verified in real time, and the effective heart rate data is obtained after the abnormal values ​​are eliminated. Subsequently, the heart rate variability analysis is performed on the heart rate data, and the function of the cardiac autonomic nervous system is evaluated by calculating the time domain indicators (such as SDNN, RMSSD, etc.) and frequency domain indicators (such as LF, HF, etc.), reflecting the changes in the user's physiological and psychological state from another perspective.

[0060] As described in step S4 above, the EEG data and heart rate variability analysis results obtained in step S3 above are integrated into a feature vector and input into a preset analysis model. The model can be constructed based on a machine learning algorithm, such as a neural network model, which has been trained with a large amount of historical data and has the ability to analyze the complex relationship between physiological data and light therapy effects. Based on the input data, the model analyzes the difference between the user's current physiological state and the ideal treatment state, and outputs correction data for parameters such as light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course to optimize the treatment plan.

[0061] As described in step S5 above, the initial plan is optimized according to the correction data to achieve more accurate and effective light therapy. The initial light plan is adjusted according to the correction data output in step S4 above. For example, if the correction data shows that the light intensity needs to be increased by 20% and the start time needs to be advanced by 1 hour, these parameters in the initial plan are modified accordingly to obtain a corrected light plan. Then, the corrected light plan is transmitted to the light therapy system, and the light therapy system adjusts the output of the light device according to the new parameters, such as adjusting the brightness, color, flashing frequency, etc. of the light, to ensure that the user receives light that better meets their needs and improves the effect of light.

[0062] In one embodiment, the initial lighting scheme further includes selecting corresponding videos and music from a pre-stored multimedia resource library.

[0063] In this embodiment, the corresponding videos and music are selected from the pre-stored multimedia resource library. Matching is performed according to the user's sleep pattern and symptom characteristics. If the user has anxiety symptoms, soothing and tranquil natural scenery videos, such as gurgling streams, quiet forests, etc., may be selected, accompanied by soft classical music or natural sound effects to help the user relax; for users with poor sleep quality, slow-paced and soft-picture videos are selected, accompanied by sleep-inducing white noise or soft piano music to create an atmosphere that helps fall asleep and enhance the comprehensive effect of light therapy.

[0064] In one embodiment, based on the brain wave data and the heart rate variability analysis results, a preset analysis model is used to output corresponding correction data, including:

[0065] Perform multi-scale wavelet decomposition on the EEG data to obtain sub-bands of different frequencies, and calculate characteristic parameters of each sub-band; extract time domain features and frequency domain features based on the heart rate variability analysis results;

[0066] Normalizing the characteristic parameters, time domain characteristics, and frequency domain characteristics to obtain a standardized characteristic vector;

[0067] The standardized feature vector is input into the preset deep convolutional recurrent neural network analysis model, and a sliding convolution operation is performed on the standardized feature vector through multiple convolution kernels to extract the local correlation information between the 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 change characteristics of brain waves and heart rate variability over time;

[0068] The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and the user's current physiological state assessment result is output;

[0069] According to the physiological status assessment results, the preset correction rule library is queried to obtain the corresponding correction data.

[0070] In this embodiment, first, multi-scale wavelet decomposition is performed on the brain wave data to obtain sub-bands of different frequencies, and the characteristic parameters of each sub-band are calculated. The brain wave signal contains different frequency components, and brain waves of different frequencies are related to different physiological and psychological states of the human body. Multi-scale wavelet decomposition can decompose the brain wave 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., it is possible to extract key information related to the user's physiological state in the brain wave signal, providing a basis for subsequent analysis.

[0071] Based on the results of heart rate variability analysis, time domain features and frequency domain features are extracted. Heart rate variability reflects the regulatory function of the cardiac autonomic nervous system. Time domain features (such as average heart rate, root mean square RMSSD of the difference between adjacent RR intervals, percentage of adjacent RR interval differences greater than 50ms pNN50, etc.) and frequency domain features (such as low frequency power LF, high frequency power HF, LF / HF ratio, etc.) can describe the changes in heart rate from different angles. Extracting these features can provide a more comprehensive understanding of the user's heart's autonomic nervous activity status and assist in judging the user's physiological state.

[0072] Then, the feature parameters, time domain features, and frequency domain features obtained above are normalized to obtain a standardized feature vector. Different feature parameters may have different dimensions and value ranges, which will affect the training effect and performance of the model. Normalization can map all features to the same scale, eliminate dimensional differences, enable the model to treat each feature more fairly, and improve the convergence speed and stability of the model. The standardized feature vector is prepared for subsequent input into the deep convolutional recurrent neural network analysis model.

[0073] Then, the standardized feature vector is input into the preset deep convolutional recurrent neural network analysis model, and a sliding convolution operation is performed on the standardized feature vector through multiple convolution kernels to extract the local correlation information between features. The convolution kernel is a small matrix. When performing a sliding convolution operation on the standardized feature vector, the features of the local area are weighted and summed to extract the local correlation information between the features. Different convolution kernels can learn different local feature patterns. Through the combination of multiple convolution kernels, the relationship between features can be captured more comprehensively. This local feature extraction method can reduce the number of model parameters and improve the generalization ability of the model.

[0074] The time series information of the standardized feature vector is processed by the long short-term memory network (LSTM) unit of the recurrent layer to capture the dynamic changes of brain waves and heart rate variability over time. Brain wave and heart rate variability data are signals with time series characteristics, that is, there is a correlation between data at different times. The LSTM unit has a memory function and can effectively process sequence data. Through the mechanism of forget gate, input gate and output gate, it selectively retains and updates information, thereby capturing the dynamic changes of brain waves and heart rate variability over time. This is very important for accurately evaluating the user's physiological state, because the physiological state often changes over time.

[0075] The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and output the evaluation result of the user's current physiological state. The convolutional layer and the recurrent layer extract the local correlation information and timing information of the features respectively, but this information is scattered. The fully connected layer integrates all the features, and through a series of linear transformations and nonlinear activation functions, the features are mapped to a low-dimensional space to obtain the evaluation result of the user's current physiological state. This evaluation result can be a classification of the user's physiological state (such as relaxation, tension, fatigue, etc.), or a quantitative evaluation of the physiological state.

[0076] Finally, according to the physiological state assessment results, the preset correction rule library is queried to obtain the corresponding correction data. The correction rule library 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 correction rules are searched in the correction rule library to obtain correction data for parameters such as light intensity, start time, color temperature, wavelength, stroboscopic frequency, and course of treatment. These correction data are used to adjust the initial light therapy plan to improve the effect and personalization of light therapy.

[0077] In one embodiment, the characteristic parameters include energy proportion and average frequency;

[0078] The time domain features include average heart rate, root mean square of adjacent RR interval differences, and percentage of adjacent RR interval differences greater than 50ms; the frequency domain features include low frequency power, high frequency power, and the ratio of low frequency power to high frequency power.

[0079] In one embodiment, based on the brain wave data and the heart rate variability analysis results, a preset analysis model is used to output corresponding correction data, including:

[0080] Inputting the EEG data and heart rate variability analysis results into a preset analysis model;

[0081] Through the fuzzy logic in the analysis model, the continuous EEG data and the heart rate variability analysis results are mapped to different fuzzy sets, and the membership in the corresponding fuzzy sets is determined, and the preliminary parameter adjustment direction is inferred based on the fuzzy rules;

[0082] By using the genetic algorithm in the analysis model, based on the preliminary parameter adjustment direction, the adjustment range of light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course is iteratively optimized, and finally the corresponding correction data is output.

[0083] In this embodiment, first, the brain wave data and heart rate variability analysis results are input into a preset analysis model. Brain wave data can reflect the activity state of the brain, and the heart rate variability analysis results reflect the function of the cardiac autonomic nervous system and the stress state of the human body. These two types of data contain important physiological information of the user during the light therapy process. Inputting them into the preset analysis model is the basis for subsequent data processing and decision-making, so that the model can evaluate the user's current physiological state based on these real-time physiological data, and then provide a basis for adjusting the light therapy plan.

[0084] Through the fuzzy logic in the analysis model, the continuous brain wave data and heart rate variability analysis results are mapped to different fuzzy sets, and the membership in the corresponding fuzzy sets is determined. The physiological state in reality is difficult to divide with precise boundaries, and fuzzy logic is suitable for processing such information with uncertainty and ambiguity. Different fuzzy sets represent different physiological states, such as "relaxation", "tension", "fatigue", etc. By mapping continuous brain wave and heart rate variability data to these fuzzy sets and calculating the membership (that is, the degree to which the data belongs to a fuzzy set), the user's physiological state can be described more accurately. For example, the results of brain wave data and heart rate variability analysis show that the user has a 70% chance of being in a "tension" state and a 30% chance of being in a "fatigue" state.

[0085] Then, a preliminary parameter adjustment direction is inferred based on fuzzy rules. Fuzzy rules are pre-set based on medical knowledge and clinical experience, and describe the relationship between different physiological states and the direction of light therapy parameter adjustment. For example, if the user is in a "tense" state, the fuzzy rules may stipulate that the light intensity needs to be reduced, the color temperature needs to be adjusted to a softer tone, etc. Through fuzzy reasoning, combined with the previously determined membership, the preliminary parameter adjustment direction for the current physiological state can be derived, providing a general direction for subsequent precise adjustments.

[0086] Finally, the genetic algorithm in the analysis model is used to iteratively optimize the adjustment range of light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course based on the preliminary parameter adjustment direction. Genetic algorithm is an optimization algorithm that simulates natural selection and genetic mechanisms. It has global search capabilities and can find better solutions in complex parameter spaces. The preliminary parameter adjustment direction is only a rough guide, and the specific adjustment range needs to be further optimized. The genetic algorithm initializes a set of possible parameter adjustment schemes (populations), evaluates each scheme (fitness calculation), selects schemes with higher fitness for crossover and mutation operations, generates new populations, and continuously iterates this process to gradually approach the optimal parameter adjustment range.

[0087] After iterative optimization using genetic algorithms, we obtained the optimal adjustment ranges for parameters such as light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course, which constitute the correction data. Applying the correction data to the initial light therapy plan can make the plan more in line with the user's current physiological state and improve the effect and personalization of light therapy.

[0088] In one embodiment, after controlling the light therapy system based on the modified light scheme, the method includes:

[0089] Obtaining user information of the user;

[0090] Based on the modified illumination scheme, construct an illumination parameter matrix;

[0091] Based on the user information, mutating the illumination parameter matrix to obtain a mutated illumination parameter matrix;

[0092] Generate a communication key based on the user information and the variable illumination parameter matrix;

[0093] After the variation illumination parameter matrix is ​​encrypted based on the communication key, it is transmitted to the user's management account.

[0094] In this embodiment, the user information includes important characteristics related to the individual user, such as age, gender, medical history, living habits, etc. This information not only reflects the user's physiological and health status, but is also closely related to the effect and safety of the light therapy program. In the subsequent steps, the user information will be used as a key factor to perform mutation processing on the light parameter matrix and generate communication keys to ensure the personalization of the entire treatment process and the security of data transmission.

[0095] The modified light treatment plan determines the specific parameters of the light treatment system, such as light intensity, start time, color temperature, wavelength, stroboscopic frequency, treatment course, etc. Organizing these parameters in the form of a matrix can more systematically and normatively represent the information of the light treatment plan. As a structured data set, the light parameter matrix is ​​convenient for subsequent mathematical operations and processing, and is the basis for personalized adjustment and encrypted transmission.

[0096] Based on the user information, the illumination parameter matrix is ​​mutated to obtain a mutated illumination parameter matrix. Different users have different physical conditions and needs. By mutating the illumination parameter matrix in combination with the user information, the illumination parameters can be fine-tuned according to the individual characteristics of the user, making it more unique and safe.

[0097] Then, based on the user information and the variable illumination parameter matrix, a communication key is generated. The communication key plays a vital role in the data transmission process, and it is the key to ensure data security. Both the user information and the variable illumination parameter matrix are unique and specific. Combining the two to generate a communication key can make the key highly random and complex. The communication key generated in this way can effectively prevent the data from being stolen or tampered with during the transmission process, ensuring that only the authorized party with the correct key can decrypt and access the data.

[0098] Finally, the variant illumination parameter matrix is ​​encrypted based on the communication key and then transmitted to the user's management account. By using the communication key to encrypt the variant illumination parameter matrix, sensitive illumination therapy data can be converted into ciphertext. During the transmission process, even if the data is intercepted, the attacker cannot obtain the content because he does not have the correct key. The encrypted variant illumination parameter matrix is ​​transmitted to the user's management account, which is convenient for the user to view and manage his own illumination therapy plan at any time, while ensuring the security and privacy of the data, which meets the security requirements of modern medical data management.

[0099] In one embodiment, generating a communication key based on the user information and the variable illumination parameter matrix includes:

[0100] Extract key feature values ​​from user information, arrange the key feature values ​​in order to form discrete data points; fit the discrete data points to generate a smooth user information feature curve;

[0101] The variation illumination parameter matrix is ​​regarded as a two-dimensional grayscale image, and each element value in the matrix corresponds to the grayscale value of a pixel in the grayscale image; edge detection is performed on the variation illumination parameter matrix through image processing technology to extract edge contour graphics;

[0102] The user information characteristic curve and the edge contour graph are placed in a virtual four-dimensional space-time coordinate system; in the coordinate system, the time dimension uses the milliseconds of the system time as a dynamic parameter, and the space dimension is a three-dimensional Euclidean space;

[0103] According to the current system time in milliseconds, the user information characteristic curve and edge contour graph are subjected to time-space distortion transformation;

[0104] The fused graph after the space-time distortion transformation is sampled, representative points are selected, and combined into a digital sequence according to rules. The digital sequence is processed through a custom nonlinear encryption function to generate a communication key.

[0105] In this embodiment, the user information contains a lot of data related to the individual user, such as age, health indicators, living habits, etc., but not all information is equally important for generating communication keys. Extracting key eigenvalues ​​can focus on the most representative data and reduce the interference of redundant information. After arranging these key eigenvalues ​​into discrete data points, a smooth curve is generated by fitting (conventional curve fitting algorithm) in order to convert discrete individual features into a continuous and analyzable mathematical model. This characteristic curve can reflect the overall characteristics and changing trends of user information, laying the foundation for subsequent fusion with the variable illumination parameter matrix.

[0106] Then, the variant illumination parameter matrix is ​​regarded as a two-dimensional grayscale image, and each element value in the matrix corresponds to the grayscale value of a pixel in the grayscale image; the variant illumination parameter matrix is ​​subjected to edge detection through image processing technology, and the edge contour graph is extracted. The variant illumination parameter matrix contains the specific values ​​of each parameter in the light therapy plan, and converting it into a grayscale image is an innovative way of data visualization. Each matrix element corresponds to the grayscale value of a pixel, so that the matrix information can be presented in the form of an image. The edge contour graph is extracted using the edge detection technology in image processing because the edge contains the most significant feature information in the image, which can highlight the structure and change law of the illumination parameter matrix. This edge contour graph can be used as another important feature and integrated with the user information feature curve to increase the complexity and uniqueness of key generation.

[0107] The user information characteristic curve and edge contour graph are placed in a virtual four-dimensional space-time coordinate system; in the coordinate system, the time dimension uses the milliseconds of the system time as a dynamic parameter, and the space dimension is a three-dimensional Euclidean space. In this embodiment, the introduction of a virtual four-dimensional space-time coordinate system is a major innovation of the technical solution. Traditional key generation methods often only consider static data features, while the time dimension in this coordinate system uses the milliseconds of the system time as a dynamic parameter, making the generated key time-sensitive. This means that the keys generated at different times will be different, greatly increasing the randomness and security of the keys. Placing the user information characteristic curve and edge contour graph in this four-dimensional space-time coordinate system provides a dynamic environment for subsequent space-time distortion transformations, allowing the two features to be correlated and integrated with each other in the space-time dimension.

[0108] The space-time distortion transformation is based on the dynamic parameter of system time in milliseconds. It can perform nonlinear deformation and distortion on the user information feature curve and edge contour graphics according to the change of time. This transformation makes the originally relatively fixed features present different forms at different times, further increasing the complexity and randomness of the key generation process. Since time is constantly changing, the space-time distortion transformation performed each time a key is generated is unique, thus ensuring that the generated key is highly unique and unpredictable.

[0109] Finally, the fused graph after the space-time distortion transformation is sampled, representative points are selected, and combined into a digital sequence according to rules. The digital sequence is processed through a custom nonlinear encryption function to generate a communication key.

[0110] The fused graph after the time-space distortion transformation contains rich feature information, but directly using the entire graph to generate the key will result in too much data and difficult to process. By sampling and selecting representative points, the amount of data can be reduced while retaining key information. After these points are combined into a digital sequence according to the rules, they are processed through a custom nonlinear encryption function, which further enhances the security of the key. The nonlinear encryption function can perform complex transformations on the digital sequence, making the key difficult to crack, thereby ensuring the security of the data during the communication process.

[0111] In one embodiment, generating a communication key based on the user information and the variable illumination parameter matrix includes:

[0112] Extract multiple key feature dimensions from user information, use time as the horizontal axis and each key feature dimension as the vertical axis to construct multiple feature curves; transform each feature curve into the frequency domain through Fourier transform to obtain a frequency domain feature curve;

[0113] Each row of the variable illumination parameter matrix is ​​regarded as a vector, the starting point of each vector is fixed at the origin, and a vector graph is drawn in three-dimensional space to obtain a vector field graph; the length of each vector is determined by the value of the matrix element, and the direction is determined by the proportional relationship between the elements;

[0114] Performing isosurface extraction on the vector field graph to generate a closed three-dimensional isosurface graph;

[0115] The frequency domain characteristic curve is projected into the space where the three-dimensional isosurface graphic is located to perform an entanglement operation to obtain an entanglement result; wherein the light intensity of the current environment is used as a dynamic parameter to adjust the entanglement mode of the frequency domain characteristic curve and the three-dimensional isosurface graphic;

[0116] The entanglement results are sampled to obtain multiple discrete data points, which are sequentially combined into a new data matrix; singular value decomposition is performed on the data matrix to obtain a singular value matrix;

[0117] Select singular values ​​on the diagonal from the singular value matrix, select them according to a preset interval, convert them into binary strings, and string the binary characters together;

[0118] The communication key is obtained by performing a pseudo-random permutation operation on the concatenated binary string using a preset random seed.

[0119] In this embodiment, user information usually includes multiple aspects, such as age, health indicators, living habits and other characteristics that change over time. Extracting key feature dimensions and constructing feature curves can intuitively show the changing trends of these features over time. The Fourier transform converts the feature curve in the time domain to the frequency domain, because the frequency domain can reveal the frequency composition of the signal, and different frequency components may correspond to different physiological or behavioral patterns. The frequency domain feature curve can capture the periodic information hidden in the time domain signal, providing richer feature information for subsequent fusion with the variable illumination parameter matrix.

[0120] Each row of the variable illumination parameter matrix is ​​regarded as a vector, the starting point of each vector is fixed at the origin, and a vector graph is drawn in three-dimensional space to obtain a vector field graph; the length of each vector is determined by the value of the matrix element, and the direction is determined by the proportional relationship between the elements. The elements in the variable illumination parameter matrix represent the various parameters of the light therapy plan. The matrix rows are converted into three-dimensional vectors, and the relationship between the matrix elements is graphically displayed. The length of the vector reflects the size of the parameter, and the direction reflects the proportional relationship between the parameters. The vector field graph can intuitively present the overall characteristics and distribution law of the variable illumination parameter matrix, which is convenient for subsequent fusion with the frequency domain characteristic curve of the user information.

[0121] The vector field graph is subjected to isosurface extraction to generate a closed three-dimensional isosurface graph. Isosurface extraction is a technique for extracting a surface composed of points with the same value in a three-dimensional data field. By performing isosurface extraction on the vector field graph, the information of the vector field can be integrated and abstracted to obtain a closed three-dimensional isosurface graph. This graph can summarize the main features of the vector field, simplify the complex vector field information into a geometric shape that is easy to process and analyze, and provide a suitable object for subsequent entanglement operations with the frequency domain characteristic curve.

[0122] The frequency domain characteristic curve is projected into the space where the three-dimensional isosurface graphic is located to perform an entanglement operation to obtain an entanglement result; wherein, the light intensity of the current environment is used as a dynamic parameter to adjust the entanglement mode of the frequency domain characteristic curve and the three-dimensional isosurface graphic; for example, when the light intensity is higher than a preset threshold, the coordinates of the intersection of the curve and the graphic surface are calculated, and these intersection coordinates are connected in sequence to form a new curve; when the light intensity is lower than the preset threshold, the spatial volume enclosed by the curve and the graphic is calculated, and the volume value is distributed to each point on the curve according to the rules.

[0123] The purpose of entangling the frequency domain characteristic curve with the three-dimensional isosurface graph is to deeply integrate the features of the user information and the variable illumination parameter matrix. The introduction of the illumination intensity of the current environment as a dynamic parameter increases the flexibility and real-time performance of the entangling operation. Different illumination intensities correspond to different entangling methods, so that the generated entangling results can reflect the influence of the current environment. By calculating the intersection coordinates or spatial volume, the features of the curve and the graph are associated and integrated to further explore the potential relationship between the two.

[0124] The entanglement result is sampled to obtain multiple discrete data points, which are sequentially formed into a new data matrix; the data matrix is ​​subjected to singular value decomposition to obtain a left singular matrix, a singular value matrix, and a right singular matrix. The entanglement result is a complex geometric relationship or data set, which is converted into discrete data points through sampling to facilitate subsequent mathematical processing. After these data points are formed into a new data matrix, singular value decomposition is performed. Singular value decomposition is an important matrix decomposition method that can decompose a matrix into the product of three matrices, in which the singular value matrix contains the main characteristic information of the matrix. Through singular value decomposition, the core features of the entanglement result can be extracted to provide key data for generating communication keys.

[0125] Select singular values ​​on the diagonal from the singular value matrix, select them according to the preset interval, convert them into binary strings, and string the binary characters together. The singular values ​​on the diagonal of the singular value matrix represent the important features of the matrix. Selecting singular values ​​according to the preset interval can reduce the amount of data while retaining the main feature information. Convert the selected singular values ​​into binary strings and concatenate them, convert the numerical features into binary codes, and prepare for subsequent encryption operations.

[0126] Finally, the pseudo-random permutation operation is performed on the concatenated binary string through a pre-set random seed to obtain the communication key. The pseudo-random permutation operation is an encryption transformation that rearranges the concatenated binary string through a pre-set random seed. The use of random seeds makes the permutation operation repeatable and deterministic, while increasing the randomness and unpredictability of the key. The communication key obtained after the pseudo-random permutation operation has high security and can effectively protect the transmission security of user information and the variation illumination parameter matrix.

[0127] In one embodiment, based on the user information, the illumination parameter matrix is ​​mutated to obtain a mutated illumination parameter matrix, including:

[0128] Extract key features from user information; such as age, health risk level, previous treatment cycles, etc.

[0129] Based on the key features, a visualization graph is constructed to obtain a user information feature graph.

[0130] Each column of the illumination parameter matrix is ​​regarded as a time series data. For each column of data, a smooth curve is constructed using the spline interpolation method to obtain a curve group.

[0131] The user information feature graph and the curve group are placed in the same coordinate system, and the curve group is initially mutated. The center of the circle in the user information feature graph is used as the reference point, and the curve group is scaled and translated according to the color corresponding to the user's health risk level.

[0132] Based on the number of rows and columns of the illumination parameter matrix, a Sierpinski triangle structure is constructed; the points on the curve group after the initial mutation are mapped to the vertices of the sub-triangles of each level of the Sierpinski triangle according to preset rules.

[0133] The mapped points are transformed by using the self-similarity and recursive properties of the Sierpinski triangle. In each sub-triangle, the vertex positions are adjusted according to specific transformation rules (such as rotation and scaling), and then the adjusted vertex positions are reversely mapped back to the curve to obtain a new curve group.

[0134] The new curve group is sampled, and the coordinate values ​​of the sampling points are rearranged in the order of rows and columns of the illumination parameter matrix to generate a variation illumination parameter matrix.

[0135] In this embodiment, in the field of light therapy, different user information will have different degrees of impact on the treatment plan. After comprehensively collecting all kinds of user information, it is necessary to accurately identify key features closely related to light therapy, such as age, health risk level, etc.

[0136] The purpose of converting the extracted key features into visual graphics is to present the inherent characteristics and interrelationships of user information more intuitively and clearly. Different key features can be represented in different graphical ways. For the feature of age, a bar chart can be used to statistically display the number of users in different age groups, so as to intuitively see the age distribution of the user group. The health risk level can be represented by a pie chart, and the proportion of each part reflects the proportion of users with different health risk levels. Past treatment cycles can be presented by a line chart, which clearly shows the trend of treatment cycles over time. Through this visual method, doctors or therapists can quickly grasp the overall situation of the user, which facilitates the subsequent comparison and analysis with the light parameter curve. At the same time, the graphical display also helps to discover the possible associations and laws between key features, and provide a reference for further optimizing the light treatment plan.

[0137] Each column of the illumination parameter matrix is ​​regarded as a time series data. For each column of data, a smooth curve is constructed by spline interpolation to obtain a curve group. The illumination parameter matrix usually records the values ​​of each illumination parameter. Considering each column of data as time series data is consistent with the actual situation of light therapy progressing over time. Spline interpolation is a powerful curve fitting method. It constructs a piecewise polynomial function between data points so that the fitted curve can accurately pass through the original data points and ensure the smoothness of the curve. In the analysis of illumination parameters, the data will be affected by factors such as measurement errors and environmental interference, and there will be certain noise and fluctuations. Spline interpolation can effectively eliminate these noises, so that the curve can more realistically reflect the changing trend of illumination parameters over time. The obtained curve group integrates the time change information of each illumination parameter, providing a clear and accurate basis for the subsequent analysis of the dynamic characteristics of illumination parameters and their association with user information.

[0138] Placing the user information feature graph and the curve group in the same coordinate system provides a unified platform for comparison and interaction between the two. Through this intuitive comparison, the potential connection between user information and lighting parameters can be clearly observed. Preliminary mutation is a preliminary adjustment of the curve group based on the user information feature graph. For example, if the user information feature graph shows that the user is older and has a higher health risk level, then on the light intensity curve, the value of the curve can be appropriately lowered to reduce the possible stimulation of light to the user; on the light time curve, the length of the curve can be shortened to avoid excessive light exposure causing burden on the user's body. This preliminary mutation is a directional adjustment based on user information, which aims to make the light parameter curve more in line with the user's actual situation, lay the foundation for subsequent more complex mutation operations, and improve the personalization of light therapy plans.

[0139] Based on the number of rows and columns of the illumination parameter matrix, a Sierpinski triangle structure is constructed; the points on the curve group after the initial mutation are mapped to the vertices of the sub-triangles of each level of the Sierpinski triangle according to the preset rules. The Sierpinski triangle is a fractal figure with unique self-similarity and recursive characteristics. The structure is constructed based on the number of rows and columns of the illumination parameter matrix, which can combine the intrinsic information of the illumination parameter matrix with the fractal structure. The number of rows and columns of the matrix determines the scale and complexity of the Sierpinski triangle, so that the triangular structure can reflect the overall characteristics of the illumination parameter matrix. Mapping the points on the curve group after the initial mutation to the vertices of the sub-triangles of each level of the Sierpinski triangle is to further process and transform the illumination parameters using the characteristics of the fractal. The self-similarity of the fractal structure means that the local and the whole of the figure have similar characteristics at different scales. This characteristic provides rich possibilities and diverse patterns for the variation of the illumination parameters. By mapping according to the preset rules, the points on the curve group can establish a corresponding relationship with the fractal structure, creating conditions for subsequent transformation operations using the recursive characteristics of the fractal.

[0140] The self-similarity and recursive properties of the Sierpinski triangle are used to transform the mapped points. In each level of sub-triangles, the vertex positions are adjusted according to specific transformation rules, and then the adjusted vertex positions are reversely mapped back to the curve to obtain a new curve group. The self-similarity and recursive properties of the Sierpinski triangle allow the same transformation operation to be performed in each level of sub-triangles. This characteristic introduces a high degree of complexity and randomness to the variation of lighting parameters. Specific transformation rules can be designed according to actual needs. For example, the vertex positions can be adjusted according to factors such as the position and size of the sub-triangle. Through this transformation, the potential variation pattern of the lighting parameters can be mined, so that the lighting parameters can produce more changes that meet the personalized needs of users while retaining the original characteristics. Reverse mapping converts the adjusted vertex positions back to the curve, so that the curve group is further mutated. This fractal-based transformation and reverse mapping process not only considers the impact of user information on lighting parameters, but also utilizes the unique properties of fractal structure, providing a powerful means for generating more personalized and optimized lighting parameter curves.

[0141] The new curve group is the result obtained after a series of operations such as preliminary mutation and fractal transformation. It contains more lighting parameter information that meets the personalized needs of users. However, the curve is continuous. In order to apply this information to the actual light therapy system, it needs to be discretized. Sampling the curve group is the process of converting the continuous curve into discrete data points. The selection of sampling points needs to be reasonably determined according to actual needs and accuracy requirements to ensure that the characteristics of the curve can be accurately reflected. The coordinate values ​​of the sampling points are rearranged in the order of rows and columns of the lighting parameter matrix so that the mutated lighting parameters can be presented in the form of a matrix. The mutated lighting parameter matrix combines the influence of user information and fractal transformation, which helps to enhance its uniqueness and provide security for the subsequent generation of keys.

[0142] Reference Figure 2 In another embodiment of the present invention, a light therapy system control device based on intelligent analysis is provided, comprising:

[0143] An acquisition unit is used to acquire the MEQ scale test result of the user and obtain the user's sleep pattern; detect the basic data of the user; the basic data includes symptoms and severity, strong light acceptance, and contraindication information;

[0144] A generating unit, configured to generate an initial illumination scheme based on the basic data and the sleep mode; the initial illumination scheme at least includes initial parameter settings for illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system;

[0145] The collection unit is used to collect the user's brain wave data and heart rate data in real time during the light therapy system's light treatment process, and to perform heart rate variability analysis to obtain a heart rate variability analysis result;

[0146] An analysis unit, configured to output corresponding correction data based on the brain wave data and the heart rate variability analysis results using a preset analysis model;

[0147] A control unit is used to modify the initial illumination scheme based on the correction data to obtain a modified illumination scheme; and control the light therapy system based on the modified illumination scheme.

[0148] In this embodiment, for the specific implementation of each unit in the above device embodiment, please refer to the above method embodiment, which will not be repeated here.

[0149] Reference Figure 3 In an embodiment of the present invention, a computer device is also provided. The computer device may be a server, and its internal structure may be as follows: Figure 3As shown. The computer device includes a processor, a memory, a display screen, an input device, a network interface and a database connected through a system bus. Among them, the processor designed by the computer is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program and a database. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store the corresponding data in this embodiment. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, the above method is implemented.

[0150] Those skilled in the art will understand that Figure 3 The structure shown in the figure is merely a block diagram of a portion of the structure related to the solution of the present invention, and does not constitute a limitation on the computer device to which the solution of the present invention is applied.

[0151] An embodiment of the present invention further provides a computer-readable storage medium on which a computer program is stored, and when the computer program is executed by a processor, the above method is implemented. It can be understood that the computer-readable storage medium in this embodiment can be a volatile readable storage medium or a non-volatile readable storage medium.

[0152] In summary, the light therapy system control method, device and storage medium based on intelligent analysis provided in the embodiments of the present invention include: obtaining the MEQ scale test results of the user to obtain the user's sleep pattern; detecting the user's basic data; the basic data include symptoms and severity, strong light acceptance, and contraindication information; generating an initial lighting plan based on the basic data and the sleep pattern; the initial lighting plan at least includes initial parameter settings for the light intensity, start time, color temperature, wavelength, stroboscopic, and treatment course of the light therapy system; during the lighting process of the user by the light therapy system, the user's brain wave data and heart rate data are collected in real time, and heart rate variability analysis is performed to obtain heart rate variability analysis results; based on the brain wave data and heart rate variability analysis results, corresponding correction data is output using a preset analysis model; based on the correction data, the initial lighting plan is corrected to obtain a corrected lighting plan; based on the corrected lighting plan, the light therapy system is controlled. In the present invention, an initial lighting plan is generated by combining multi-dimensional information including basic user data and sleep patterns. At the same time, the initial lighting plan is corrected based on real-time collection of the user's brain wave data and heart rate data, thereby overcoming the defects of traditional light therapy systems that cannot combine multi-dimensional information of the user and cannot automatically adjust the lighting plan according to the user's real-time physiological state.

[0153] Those skilled in the art can understand that all or part of the processes in the above-mentioned embodiment methods can be completed by instructing the relevant hardware through a computer program, and the computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above-mentioned methods. Among them, any reference to memory, storage, database or other media provided by the present invention and used in the embodiments can include non-volatile and / or volatile memory. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM) or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. As an illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double-speed data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), memory bus (Rambus) direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and memory bus dynamic RAM.

[0154] It should be noted that, in this article, the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, device, article or method including a series of elements includes not only those elements, but also includes other elements not explicitly listed, or also includes elements inherent to such process, device, article or method. In the absence of further restrictions, an element defined by the sentence "includes a ..." does not exclude the presence of other identical elements in the process, device, article or method including the element.

[0155] The above description is only a preferred embodiment of the present invention, and does not limit the patent scope of the present invention. Any equivalent structure or equivalent process transformation made by using the contents of the present invention specification and drawings, or directly or indirectly applied in other related technical fields, are also included in the patent protection scope of the present invention.

Claims

1. A method for controlling a light therapy system based on intelligent analysis, characterized in that: The following steps are involved: Obtain the user's MEQ scale test results to obtain the user's sleep pattern; detect the user's basic data; the basic data includes symptoms and severity, strong light acceptance, and contraindication information; Based on the basic data and the sleep pattern, generating an initial lighting plan; The initial illumination scheme at least includes initial parameter settings for the illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system; During the illumination process of the user by the illumination therapy system, the user's brain wave data and heart rate data are collected in real time, and the heart rate variability analysis is performed to obtain the heart rate variability analysis result; Based on the brain wave data and heart rate variability analysis results, output corresponding correction data using a preset analysis model; Modifying the initial illumination scheme based on the correction data to obtain a modified illumination scheme; The light therapy system is controlled based on the modified light regimen.

2. The method for controlling a light therapy system based on intelligent analysis according to claim 1, characterized in that: The initial lighting scheme also includes selecting corresponding videos and music from a pre-stored multimedia resource library.

3. The light therapy system control method based on intelligent analysis according to claim 1, characterized in that: Based on the brain wave data and heart rate variability analysis results, the corresponding correction data is output using a preset analysis model, including: Perform multi-scale wavelet decomposition on the EEG data to obtain sub-bands of different frequencies, and calculate characteristic parameters of each sub-band; extract time domain features and frequency domain features based on the heart rate variability analysis results; Normalizing the characteristic parameters, time domain characteristics, and frequency domain characteristics to obtain a standardized characteristic vector; The standardized feature vector is input into the preset deep convolutional recurrent neural network analysis model, and a sliding convolution operation is performed on the standardized feature vector through multiple convolution kernels to extract the local correlation information between the 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 change characteristics of brain waves and heart rate variability over time; The fully connected layer is used to integrate and map the features extracted by the convolutional layer and the recurrent layer, and the user's current physiological state assessment result is output; According to the physiological status assessment results, the preset correction rule library is queried to obtain the corresponding correction data.

4. The method for controlling a light therapy system based on intelligent analysis according to claim 3, characterized in that: The characteristic parameters include energy proportion and average frequency; The time domain features include average heart rate, root mean square of adjacent RR interval differences, and percentage of adjacent RR interval differences greater than 50ms; the frequency domain features include low frequency power, high frequency power, and the ratio of low frequency power to high frequency power.

5. The light therapy system control method based on intelligent analysis according to claim 1, characterized in that: Based on the brain wave data and heart rate variability analysis results, the corresponding correction data is output using a preset analysis model, including: Inputting the EEG data and heart rate variability analysis results into a preset analysis model; Through the fuzzy logic in the analysis model, the continuous EEG data and the heart rate variability analysis results are mapped to different fuzzy sets, and the membership in the corresponding fuzzy sets is determined, and the preliminary parameter adjustment direction is inferred based on the fuzzy rules; By using the genetic algorithm in the analysis model, based on the preliminary parameter adjustment direction, the adjustment range of light intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course is iteratively optimized, and finally the corresponding correction data is output.

6. The method for controlling a light therapy system based on intelligent analysis according to claim 1, characterized in that: After controlling the light therapy system based on the modified light scheme, the method includes: Obtaining user information of the user; Based on the modified illumination scheme, construct an illumination parameter matrix; Based on the user information, mutating the illumination parameter matrix to obtain a mutated illumination parameter matrix; Generate a communication key based on the user information and the variable illumination parameter matrix; After the variation illumination parameter matrix is ​​encrypted based on the communication key, it is transmitted to the user's management account.

7. The method for controlling a light therapy system based on intelligent analysis according to claim 6, characterized in that: Generating a communication key based on the user information and the variable illumination parameter matrix includes: Extract key feature values ​​from user information, arrange the key feature values ​​in order to form discrete data points; fit the discrete data points to generate a smooth user information feature curve; The variation illumination parameter matrix is ​​regarded as a two-dimensional grayscale image, and each element value in the matrix corresponds to the grayscale value of a pixel in the grayscale image; edge detection is performed on the variation illumination parameter matrix through image processing technology to extract edge contour graphics; The user information characteristic curve and the edge contour graph are placed in a virtual four-dimensional space-time coordinate system; in the coordinate system, the time dimension uses the milliseconds of the system time as a dynamic parameter, and the space dimension is a three-dimensional Euclidean space; According to the current system time in milliseconds, the user information characteristic curve and edge contour graph are subjected to time-space distortion transformation; The fused graph after the space-time distortion transformation is sampled, representative points are selected, and combined into a digital sequence according to rules. The digital sequence is processed through a custom nonlinear encryption function to generate a communication key.

8. A light therapy system control device based on intelligent analysis, characterized in that: include: An acquisition unit, used to acquire the MEQ scale test result of the user and obtain the user's sleep pattern; Detecting the user's basic data; the basic data includes symptoms and severity, strong light acceptance, and contraindication information; A generating unit, configured to generate an initial lighting scheme based on the basic data and the sleep mode; The initial illumination scheme at least includes initial parameter settings for the illumination intensity, start time, color temperature, wavelength, stroboscopic frequency, and treatment course of the illumination therapy system; The collection unit is used to collect the user's brain wave data and heart rate data in real time during the light therapy system's light treatment process, and to perform heart rate variability analysis to obtain a heart rate variability analysis result; An analysis unit, configured to output corresponding correction data based on the brain wave data and the heart rate variability analysis results using a preset analysis model; A control unit, configured to modify the initial illumination scheme based on the correction data to obtain a modified illumination scheme; The light therapy system is controlled based on the modified light regimen.

9. A computer device comprising a memory and a processor, wherein a computer program is stored in the memory, wherein: When the processor executes the computer program, the steps of the method according to any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 7 are implemented.

Images