A transcranial irradiation anti-fatigue method and system based on nano-photosynthesis

Abstract

This invention relates to the field of transcranial irradiation technology and discloses a transcranial irradiation method and system for fatigue relief based on nanophotosynthesis. The method includes: traversing an irradiation database based on irradiation usage data; determining the method for determining irradiation intensity based on the traversal results; determining the irradiation intensity based on the amount of historical data in the irradiation database; determining the irradiation intensity based on the fatigue data of the person to be irradiated and an irradiation fatigue model; assessing the environmental suitability of the irradiation intensity based on ambient light intensity and determining an irradiation fluctuation index based on environmental deviation; determining an irradiation prediction index based on an irradiation adjustment model and environmental deviation; determining an irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index; and irradiating the person to be irradiated with the adjusted irradiation intensity. This invention ensures the reliability of transcranial stimulation by adjusting the irradiation intensity.

Description

Technical Field

[0001] This invention relates to the field of transcranial irradiation technology, and more specifically, to a transcranial irradiation method and system for fatigue relief based on nanophotosynthesis. Background Technology

[0002] With the accelerated pace of modern life, increased work pressure, and frequent use of electronic devices, chronic fatigue has become a significant health issue. Fatigue not only manifests as physical weakness and lethargy, but long-term accumulation can also induce a series of complications such as memory decline, weakened immunity, and endocrine disorders, thereby affecting people's work efficiency and quality of life. Irradiation by nano-light sources can intervene in the brain, thereby improving fatigue caused by metabolic imbalances. However, the irradiation of nano-light sources is usually controlled by human experience. Relying on human experience makes it impossible to dynamically adjust the nano-light source according to the actual situation of ambient light. Due to the lack of feedback regulation mechanisms, the reliability of transcranial stimulation is insufficient.

[0003] Therefore, it is necessary to design a transcranial irradiation method and system based on nanophotosynthesis to solve the problems existing in the current technology. Summary of the Invention

[0004] In view of this, the present invention proposes a transcranial irradiation method and system for fatigue relief based on nanophotosynthesis, aiming to solve the problem that relying on human experience to make judgments cannot dynamically adjust the nano-light source according to the actual situation of environmental irradiation, and the lack of feedback adjustment mechanism leads to insufficient reliability of transcranial stimulation.

[0005] In one aspect, the present invention proposes a transcranial irradiation method for fatigue relief based on nanophotosynthesis, comprising: The irradiation usage data of the person to be irradiated is obtained, and the irradiation database is traversed based on the irradiation usage data. The method for determining the irradiation intensity is determined based on the traversal results. When determining the irradiation intensity based on the irradiation database, the irradiation intensity is determined based on the amount of historical data in the irradiation database. When determining the irradiation intensity based on the fatigue irradiation model, the irradiation intensity is determined based on the fatigue data of the person to be irradiated and the irradiation fatigue model. The ambient light intensity of the person to be irradiated is obtained, and the environmental conditions of the irradiation intensity are judged to be qualified based on the ambient light intensity. When the environmental conditions of the irradiation intensity are not qualified, the environmental deviation is determined based on the standard ambient light intensity and the ambient light intensity, and the irradiation fluctuation index of the irradiation intensity is determined based on the environmental deviation. An environmental sample set of the person to be irradiated is obtained, an irradiation adjustment model is determined based on the environmental sample set, an irradiation prediction index is determined based on the irradiation adjustment model and the environmental deviation, an irradiation adjustment index is determined based on the relationship between the irradiation fluctuation index and the irradiation prediction index, the irradiation intensity is adjusted based on the irradiation adjustment index, and the person to be irradiated is irradiated with the adjusted irradiation intensity.

[0006] Furthermore, when traversing the irradiation database based on the irradiation usage data and determining the method for determining irradiation intensity based on the traversal results, the method includes: The irradiation database includes several historical irradiation usage data and several historical irradiation intensities, and there is a one-to-one correspondence between the historical irradiation usage data and the historical irradiation intensities; The irradiation usage data is compared with all historical irradiation usage data in the irradiation database; If the irradiation database contains historical irradiation usage data that is identical to the irradiation usage data, then the irradiation intensity is determined based on the irradiation database. If no historical irradiation usage data identical to the irradiation usage data exists in the irradiation database, then the irradiation intensity is determined based on the fatigue irradiation model.

[0007] Furthermore, when determining the irradiance intensity based on the irradiance database, the irradiance intensity is determined based on the amount of historical data in the irradiance database, including: When the historical irradiation usage data that is identical to the irradiation usage data is unique in the irradiation database, the historical irradiation intensity corresponding to the historical irradiation usage data is determined as the irradiation intensity. When the historical irradiation usage data in the irradiation database is not unique and is the same as the irradiation usage data, the average value of the historical irradiation intensity corresponding to each historical irradiation usage data is determined as the irradiation intensity.

[0008] Furthermore, when determining the irradiation intensity based on the fatigue irradiation model, the irradiation intensity is determined based on the fatigue data of the person to be irradiated and the irradiation fatigue model, including: Obtain a transcranial sample set and divide the transcranial sample set into a sample training set and a sample test set; The model is built by finding the model building parameters based on grid search and building a random forest model. The random forest model is trained based on cross-validation and the sample training set, and the trained random forest model is tested based on the sample test set to determine the test index value. If the test metric value of the currently trained random forest model is less than the test metric value of the previously trained random forest model, then adjust the learning rate of the currently trained random forest model and continue training. If the test index value of the currently trained random forest model is greater than or equal to the test index value of the previously trained random forest model, then training is stopped, and the currently trained random forest model is determined as the irradiation fatigue model. The fatigue data is substituted into the irradiation fatigue model to determine the irradiation intensity.

[0009] Furthermore, when acquiring the ambient light intensity of the person to be irradiated, and determining the environmental suitability of the irradiation intensity based on the ambient light intensity, the process includes: Obtain the standard ambient light intensity corresponding to the ambient light intensity; When the ambient light intensity is greater than the standard ambient light intensity, the environment of the irradiation intensity is deemed unqualified. When the ambient light intensity is less than or equal to the standard ambient light intensity, the environment of the irradiation intensity is deemed to be qualified.

[0010] Furthermore, when the environment for the irradiance intensity is unqualified, an environmental deviation is determined based on the standard ambient light intensity and the ambient light intensity, and an irradiance fluctuation index for the irradiance intensity is determined based on the environmental deviation, including: The difference in irradiance between the ambient light intensity and the standard ambient light intensity is obtained, and the difference in irradiance is determined as the environmental deviation. Set a first environmental deviation and a second environmental deviation, wherein the first environmental deviation is greater than the second environmental deviation and the second environmental deviation is greater than zero; If the environmental deviation is greater than the first environmental deviation, then the first irradiation fluctuation index is determined as the irradiation fluctuation index. If the environmental deviation is less than or equal to the first environmental deviation and greater than or equal to the second environmental deviation, then the second irradiation fluctuation index is determined as the irradiation fluctuation index. If the environmental deviation is less than the second environmental deviation, then the third irradiation fluctuation index is determined as the irradiation fluctuation index. Wherein, 0 < first irradiation fluctuation index < second irradiation fluctuation index < third irradiation fluctuation index < 1.

[0011] Furthermore, when determining the irradiance adjustment model based on the environmental sample set, and determining the irradiance prediction index based on the irradiance adjustment model and the environmental deviation, the process includes: A convolutional neural network model is pre-obtained, and the irradiation adjustment model is determined based on the environmental sample set using the convolutional neural network model as the architecture; The environmental deviation is substituted into the irradiation adjustment model to determine the irradiation prediction index.

[0012] Furthermore, when determining the irradiance adjustment index based on the relationship between the irradiance fluctuation index and the irradiance prediction index, the following steps are included: Compare the irradiation prediction index with the irradiation fluctuation index; If the irradiation prediction index is equal to the irradiation fluctuation index, then the irradiation prediction index or the irradiation fluctuation index is determined as the irradiation adjustment index. If the irradiation prediction index is not equal to the irradiation fluctuation index, then the average of the irradiation prediction index and the irradiation fluctuation index shall be determined as the irradiation adjustment index.

[0013] Furthermore, when adjusting the irradiance intensity based on the irradiance adjustment index, the following steps are included: The irradiation intensity is directly proportional to the irradiation adjustment index.

[0014] Compared with existing technologies, the advantages of this invention are as follows: By acquiring irradiation usage data of the person to be irradiated and traversing an irradiation database to determine the irradiation intensity, the blindness of human experience is avoided. Utilizing historical data from the irradiation database to determine the irradiation intensity fully utilizes existing data. Furthermore, when determining the irradiation intensity based on a fatigue irradiation model, the irradiation intensity can be dynamically matched to the fatigue data of the person to be irradiated, ensuring that the irradiation intensity is adapted to the individual fatigue state of the person being irradiated. Moreover, the construction of an environment-adaptive irradiation intensity adjustment mechanism enhances the stability of transcranial stimulation. The environmental suitability assessment of the irradiation intensity based on ambient light intensity enables real-time perception and quantification of external irradiation interference, thereby promptly identifying the impact of environmental irradiation changes on transcranial stimulation. This ensures the reliability of transcranial stimulation by the nano-light source under different environmental irradiation conditions, reduces stimulation fluctuations caused by environmental factors, and achieves a data-driven process from environmental perception to irradiation adjustment. This, in turn, guarantees the reliability of transcranial stimulation.

[0015] On the other hand, this application also provides a transcranial irradiation anti-fatigue system based on nanophotosynthesis, for applying the above-mentioned transcranial irradiation anti-fatigue method based on nanophotosynthesis, comprising: The data acquisition and judgment module is configured to acquire the irradiation usage data of the person to be irradiated, traverse the irradiation database based on the irradiation usage data, and determine the method for determining the irradiation intensity based on the traversal results. The irradiation analysis module is configured to determine the irradiation intensity based on the amount of historical data in the irradiation database when it is determined to determine the irradiation intensity based on the irradiation database, and to determine the irradiation intensity based on the fatigue data of the person to be irradiated and the irradiation fatigue model when it is determined to determine the irradiation intensity based on the fatigue data of the person to be irradiated. The irradiation processing module is configured to acquire the ambient light intensity of the person to be irradiated, make a qualified judgment on the environment of the irradiation intensity based on the ambient light intensity, and when the environment of the irradiation intensity is unqualified, determine the environmental deviation amount based on the standard ambient light intensity and the ambient light intensity, and determine the irradiation fluctuation index of the irradiation intensity based on the environmental deviation amount. The fatigue response module is configured to acquire an environmental sample set of the person to be irradiated, determine an irradiation adjustment model based on the environmental sample set, determine an irradiation prediction index based on the irradiation adjustment model and the environmental deviation, determine an irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index, adjust the irradiation intensity based on the irradiation adjustment index, and irradiate the person to be irradiated with the adjusted irradiation intensity.

[0016] It is understandable that the above-mentioned transcranial irradiation anti-fatigue method and system based on nanophotosynthesis has the same beneficial effects, and will not be elaborated further here. Attached Figure Description

[0017] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the drawings used in the embodiments will be briefly introduced below. Obviously, the drawings described below are only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0018] Figure 1 A flowchart of a transcranial irradiation anti-fatigue method based on nanophotosynthesis provided in this embodiment of the invention; Figure 2 A functional block diagram of a transcranial irradiation anti-fatigue system based on nanophotosynthesis provided in an embodiment of the present invention. Detailed Implementation

[0019] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0020] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0021] See Figure 1 As shown in some embodiments of this application, a transcranial irradiation method for fatigue relief based on nanophotosynthesis includes: S100: Obtain the irradiation usage data of the person to be irradiated, traverse the irradiation database based on the irradiation usage data, and determine the method for determining the irradiation intensity based on the traversal results.

[0022] S200: When determining the irradiation intensity based on the irradiation database, the irradiation intensity is determined based on the amount of historical data in the irradiation database. When determining the irradiation intensity based on the fatigue irradiation model, the irradiation intensity is determined based on the fatigue data of the person to be irradiated and the irradiation fatigue model.

[0023] S300: Obtain the ambient light intensity of the person to be irradiated, and make a qualified judgment on the environment of the irradiation intensity based on the ambient light intensity. When the environment of the irradiation intensity is unqualified, determine the environmental deviation based on the standard ambient light intensity and the ambient light intensity, and determine the irradiation fluctuation index of the irradiation intensity based on the environmental deviation.

[0024] S400: Obtain an environmental sample set of the person to be irradiated, determine an irradiation adjustment model based on the environmental sample set, determine an irradiation prediction index based on the irradiation adjustment model and the environmental deviation, determine an irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index, adjust the irradiation intensity based on the irradiation adjustment index, and irradiate the person to be irradiated with the adjusted irradiation intensity.

[0025] Specifically, the irradiation data represents the identity information of the person to be irradiated and the record of irradiation using a nano-light source. Different individuals have different past irradiation experiences and their bodies react differently to irradiation. The irradiation database stores the identity information of various individuals to be irradiated, providing a targeted reference for determining the irradiation intensity. The irradiation intensity represents the intensity of the light source used to irradiate the person to be irradiated by the nano-light source. Nano-light sources include visible light and infrared light, with wavelengths ranging from 350 nanometers to 1 millimeter. When the determination of irradiation intensity is based on an irradiation database, and specifically on the amount of historical data in that database, it indicates that the database contains substantial information about the use of nano-light sources by the irradiated individuals. With sufficient data, this data can reflect the individuals' adaptation to the irradiation intensity, and the resulting irradiation intensity can be matched with past usage data to ensure the reliability of transcranial stimulation, thereby improving the anti-fatigue effect. Conversely, when the determination of irradiation intensity is based on a fatigue irradiation model, it indicates that some individuals lack records of using nano-light sources, making it impossible to measure the degree of transcranial stimulation based on past usage. In this case, the irradiation intensity is determined based on the fatigue data of the irradiated individuals and an irradiation fatigue model. Fatigue data includes physical function indicators such as electrocardiogram, heart rate, and blood pressure. The constructed irradiation fatigue model integrates a large amount of data on the transcranial stimulation of nano-light sources under different fatigue states, providing irradiation intensity information for individuals without prior usage data. This approach compensates for the limitations of missing data. Since ambient light intensity can interfere with the nano-light source, excessively strong ambient light can affect the irradiation of the human body, potentially reducing the reliability of transcranial stimulation. Therefore, the ambient light intensity of the person to be irradiated is first obtained, and the environmental conditions for irradiation intensity are assessed. If the environmental conditions for irradiation intensity are unacceptable, the environmental deviation is determined based on the standard ambient light intensity and the actual ambient light intensity. The standard ambient light intensity is determined by the user manual or experiments of the nano-light source for the scene. The environmental deviation directly reflects the degree to which the ambient light intensity deviates from the standard ambient light intensity, demonstrating the impact on the irradiation effect of the nano-light source. The environmental deviation provides a clear quantitative reference for adjusting the irradiation intensity. The irradiation fluctuation index of the irradiation intensity is dynamically determined based on the environmental deviation, avoiding the blindness of human experience-based settings and ensuring the reliability of transcranial stimulation.

[0026] Understandably, the environmental sample set includes various data on the environment of the person to be irradiated and the nano-light source. By analyzing this data, an irradiation adjustment model is constructed, ensuring its environmental adaptability and enabling the generation of adjustment strategies under various environments. Based on the irradiation adjustment model and environmental deviation, an irradiation prediction index is determined. A deep learning model is used to infer the changes in irradiation effects caused by environmental deviation. The irradiation prediction index reflects the adjustment range of irradiation intensity, as does the irradiation fluctuation index. The irradiation adjustment index is determined based on the relationship between the irradiation fluctuation index and the irradiation prediction index. Combining these two inferences comprehensively considers environmental factors and model inference results, ensuring that the irradiation adjustment index both conforms to actual environmental changes and meets the stimulation requirements for anti-fatigue. Finally, the irradiation intensity is adjusted based on the irradiation adjustment index, and the person to be irradiated is then irradiated with the adjusted intensity. This achieves dynamic and precise control of the nano-light source. By providing real-time feedback on environmental information and making targeted adjustments, the reliability of transcranial stimulation is improved, ensuring that the irradiation of the nano-light source remains stable under different environments.

[0027] In some embodiments of this application, when traversing the irradiation database based on irradiation usage data and determining the method for determining irradiation intensity based on the traversal results, the following steps are taken: the irradiation database includes several historical irradiation usage data and several historical irradiation intensities, and the historical irradiation usage data and historical irradiation intensities correspond one-to-one. The irradiation usage data is compared with all the historical irradiation usage data in the irradiation database. When there is historical irradiation usage data in the irradiation database that is the same as the irradiation usage data, it is determined that the irradiation intensity is determined based on the irradiation database. When there is no historical irradiation usage data in the irradiation database that is the same as the irradiation usage data, it is determined that the irradiation intensity is determined based on the fatigue irradiation model.

[0028] Specifically, the irradiation database contains several one-to-one historical irradiation usage data and historical irradiation intensities. These data are records of the fatigue relief achieved by transcranial stimulation in different individuals. The irradiation usage data of the individuals to be irradiated is compared one by one with all the historical irradiation usage data in the irradiation database. If the irradiation database contains the same historical irradiation usage data, it indicates that the individual to be irradiated has a record of using irradiation to relieve fatigue. The corresponding historical irradiation intensity is a record of nano-irradiation applied to the dorsolateral prefrontal cortex, motor cortex, etc., to relieve fatigue. In this case, the irradiation intensity is determined based on the irradiation database. When the irradiation database does not contain the same historical irradiation usage data, it indicates that the individual to be irradiated has no directly referable historical records. If human experience is still used to determine the intensity, it will lead to a mismatch between the irradiation intensity and the transcranial stimulation requirements. In this case, the irradiation intensity is determined based on the fatigue irradiation model, avoiding the blindness of human experience setting and ensuring the accuracy and reliability of transcranial stimulation.

[0029] In some embodiments of this application, when determining the irradiance intensity based on the irradiance database, the irradiance intensity is determined based on the number of historical data in the irradiance database, including: when the historical irradiance usage data that is the same as the irradiance usage data in the irradiance database is unique, the historical irradiance intensity corresponding to the historical irradiance usage data is determined as the irradiance intensity; when the historical irradiance usage data that is the same as the irradiance usage data in the irradiance database is not unique, the average of the historical irradiance intensities corresponding to each historical irradiance usage data is determined as the irradiance intensity.

[0030] Specifically, the historical irradiation usage data matched in the irradiation database is quantitatively checked. If the historical irradiation usage data that matches the data is unique, it means that the historical irradiation usage data is a single record of transcranial stimulation for fatigue relief for the irradiated person. The corresponding historical irradiation intensity is determined based on the fatigue level of the irradiated person and can meet the needs of transcranial stimulation. Therefore, the historical irradiation intensity corresponding to the unique historical irradiation usage data is determined as the current irradiation intensity. If the historical irradiation usage data that matches the data is not unique, it means that there are multiple records of transcranial stimulation for fatigue relief for the irradiated person. Different historical irradiation intensities will have certain differences due to slight differences in fatigue levels of the irradiated person. In this case, the average of the historical irradiation intensities corresponding to each historical irradiation usage data is taken as the current irradiation intensity. This balances the differences in irradiation from different nano-light sources, avoids possible random deviations in a single usage case, ensures compatibility with transcranial stimulation, and guarantees the consistency of stimulation effects.

[0031] In some embodiments of this application, when determining the irradiation intensity based on the fatigue irradiation model, the determination of the irradiation intensity based on the fatigue data of the person to be irradiated and the irradiation fatigue model includes: acquiring a transcranial sample set and dividing the transcranial sample set into a sample training set and a sample test set; finding model building parameters based on grid search and building a random forest model; training the random forest model based on cross-validation and the sample training set; testing the trained random forest model based on the sample test set and determining the test index value; if the test index value of the currently trained random forest model is less than the test index value of the previously trained random forest model, then adjusting the learning rate of the currently trained random forest model and continuing training; if the test index value of the currently trained random forest model is greater than or equal to the test index value of the previously trained random forest model, then stopping training and determining the currently trained random forest model as the irradiation fatigue model, and substituting the fatigue data into the irradiation fatigue model to determine the irradiation intensity.

[0032] Specifically, the transcranial sample set encompasses data on brain oxygen saturation, electroencephalogram (EEG) neural signal characteristics, heart rate variability, blood cortisol levels, blood lactate levels, body temperature, and respiratory rate under different transcranial irradiation intensities, wavelengths, durations, and target areas for different ages, sexes, heights, and weights. It also includes usage instructions for the nanolight source. Typically, 70%-80% of the data in the transcranial sample set is allocated as the training set, with the remainder used as the test set to ensure the model's generalization ability. The training set is used for model learning, while the test set is used to validate model performance, avoiding overfitting where the model performs well only on training data but fails on new data. Grid search, by traversing various parameter combinations such as the number of decision trees in the random forest model, the minimum number of samples required for decision tree node splitting, and the minimum number of samples contained in leaf nodes, filters out model building parameters that maximize model performance, laying the foundation for model construction. The random forest model is trained based on cross-validation and a sample training set. Cross-validation further divides the sample training set, allowing the model to be repeatedly trained and validated on different sample training subsets to improve its generalization ability to different data. The trained random forest model is then tested using a sample test set to determine test metrics, including accuracy and recall. These metrics measure the model's performance level. By comparing the current test metric values ​​with those of the previous training of the random forest model, if the current training... If the test index value of the random forest model after training is lower than that of the random forest model after training, it indicates that the model has not reached its optimal performance level and there is still room for improvement. The learning rate is adjusted by methods such as cosine annealing so that the model can adjust its learning status in subsequent training. Training continues based on the adjusted learning rate. If the test index value of the current random forest model after training is greater than or equal to that of the random forest model after training, it indicates that the model's performance is improving or has approached its optimal performance. Training can then be stopped, and the current random forest model is identified as an irradiation fatigue model. The irradiation intensity is determined by using fatigue data and the irradiation fatigue model to ensure that the irradiation intensity matches the actual needs of the person being irradiated, thus ensuring the targeted nature of transcranial stimulation.

[0033] In some embodiments of this application, when obtaining the ambient light intensity of the person to be irradiated and judging the environmental compliance of the irradiation intensity based on the ambient light intensity, the following steps are taken: obtaining the standard ambient light intensity corresponding to the ambient light intensity; when the ambient light intensity is greater than the standard ambient light intensity, the irradiation intensity is judged to be unqualified; when the ambient light intensity is less than or equal to the standard ambient light intensity, the irradiation intensity is judged to be qualified.

[0034] In some embodiments of this application, when the environmental irradiance is unqualified, an environmental deviation is determined based on the standard ambient light intensity and the ambient light intensity, and an irradiance fluctuation index is determined based on the environmental deviation. This includes: obtaining the irradiance difference between the ambient light intensity and the standard ambient light intensity, and determining the irradiance difference as the environmental deviation; setting a first environmental deviation and a second environmental deviation, wherein the first environmental deviation is greater than the second environmental deviation and the second environmental deviation is greater than zero; if the environmental deviation is greater than the first environmental deviation, then the first irradiance fluctuation index is determined as the irradiance fluctuation index; if the environmental deviation is less than or equal to the first environmental deviation and greater than or equal to the second environmental deviation, then the second irradiance fluctuation index is determined as the irradiance fluctuation index; if the environmental deviation is less than the second environmental deviation, then the third irradiance fluctuation index is determined as the irradiance fluctuation index, wherein 0 < first irradiance fluctuation index < second irradiance fluctuation index < third irradiance fluctuation index < 1.

[0035] Specifically, a standard ambient light intensity corresponding to the current ambient light intensity is obtained. This standard ambient light intensity is determined by the instructions for use of the nano-light source in the current scene or by experiments. Using the standard ambient light intensity as a benchmark, if the ambient light intensity is greater than the standard ambient light intensity, it indicates that the excessive ambient light will superimpose and interfere with the irradiation of the nano-light source, promoting the generation and recombination of a large number of electron-hole pairs. This causes the irradiation intensity to increase with the increase of the ambient light intensity, thus affecting the reliability of anti-fatigue. In this case, the irradiation intensity is deemed unqualified. When the ambient light intensity is less than or equal to the standard ambient light intensity, the interference of the ambient light on the nano-light source is within an acceptable range and can ensure the reliability of transcranial stimulation. Therefore, the irradiation intensity is deemed qualified, and transcranial stimulation at the current irradiation intensity can ensure the reliability of anti-fatigue. When the environmental irradiance intensity is unsuitable, the difference between the ambient light intensity and the standard ambient light intensity is determined and defined as the environmental deviation. This environmental deviation reflects the degree of ambient light interference, i.e., the extent to which the ambient light intensity deviates from the standard ambient light intensity. Different environmental deviations have varying degrees of interference with the nano-light source. Different irradiance fluctuation indices are dynamically selected based on the magnitude of the environmental deviation. If the environmental deviation is greater than the first environmental deviation, indicating the strongest interference, the smallest first irradiance fluctuation index is selected to avoid the cumulative effect of irradiation. If the environmental deviation is between the first and second environmental deviations, indicating a moderate level of interference, a moderate second irradiance fluctuation index is selected. If the environmental deviation is less than the second environmental deviation, indicating the weakest interference, the largest third irradiance fluctuation index is selected. By dynamically determining the irradiance fluctuation index, the cumulative interference of environmental irradiation on the nano-light source is avoided, ensuring the stability of transcranial stimulation.

[0036] In some embodiments of this application, when determining the irradiance adjustment model based on an environmental sample set and determining the irradiance prediction index based on the irradiance adjustment model and the environmental deviation, the process includes: pre-acquiring a convolutional neural network model, determining the irradiance adjustment model based on the environmental sample set using the convolutional neural network model as the architecture, and substituting the environmental deviation into the irradiance adjustment model to determine the irradiance prediction index.

[0037] Specifically, the environmental sample set includes data such as the spectral composition of ambient light, the rate of change of ambient light intensity, ambient reflectivity, the spectral purity of the nano-light source, and the beam divergence angle, covering various scenarios where environmental deviations affect irradiance. Convolutional neural network (CNN) models excel at capturing complex nonlinear relationships in data. Since there are multi-dimensional influence patterns between environmental deviations and irradiance adjustment strategies, CNN models can accurately uncover these multi-dimensional and complex correspondences. Using a CNN model as the framework, the data in the environmental sample set is divided, and then the CNN model is trained. The training method is consistent with that of the random forest model and will not be repeated here. The resulting irradiance adjustment model learns the adjustment patterns of irradiance under different environmental irradiance conditions. It uses a deep learning model to determine the direction and magnitude of irradiance adjustment reflecting the current environment, providing a data foundation for subsequent irradiance adjustment.

[0038] In some embodiments of this application, when determining the irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index, the method includes: comparing the irradiation prediction index with the irradiation fluctuation index; if the irradiation prediction index is equal to the irradiation fluctuation index, then the irradiation prediction index or the irradiation fluctuation index is determined as the irradiation adjustment index; if the irradiation prediction index is not equal to the irradiation fluctuation index, then the average of the irradiation prediction index and the irradiation fluctuation index is determined as the irradiation adjustment index.

[0039] In some embodiments of this application, when adjusting the irradiance intensity based on the irradiance adjustment index, the irradiance intensity is proportional to the irradiance adjustment index.

[0040] Specifically, the relationship between the irradiance prediction index and the irradiance fluctuation index is determined. If they are equal, it indicates that the irradiance fluctuation index determined by the environmental deviation matches the adjustment requirements predicted by the model, and the current adjustment direction and magnitude are consistent. One of these values ​​can be designated as the irradiance adjustment index. If they are not equal, it indicates a difference between the irradiance fluctuation index determined by the environmental deviation and the adjustment requirements predicted by the model. The mean of the irradiance prediction index and the irradiance fluctuation index is designated as the irradiance adjustment index. The mean balances the deviation between the two indices, avoiding adjustment bias caused by the one-sidedness of a single data point. The irradiance intensity is then adjusted based on the irradiance adjustment index. Assuming the irradiance adjustment index is F and the irradiance intensity is Q, the adjusted irradiance intensity is F*Q. When it is necessary to reduce the irradiation intensity, by establishing a positive proportional relationship between the irradiation intensity and the irradiation adjustment index, the irradiation intensity can be controlled under the influence of high environmental irradiation. This ensures that the irradiation intensity can meet the transcranial stimulation needs of the person being irradiated, so that the output of the nano-light source can both counteract the interference of ambient light and adapt to the fatigue state of the person being irradiated, thus ensuring the stability of transcranial stimulation.

[0041] The above embodiments determine the irradiation intensity by acquiring the irradiation usage data of the person to be irradiated and traversing the irradiation database. This avoids the blindness of human experience and utilizes historical data from the irradiation database to determine the irradiation intensity, making full use of existing data. When determining the irradiation intensity based on the fatigue irradiation model, the irradiation intensity can be dynamically matched with the fatigue data of the person to be irradiated, allowing the irradiation intensity to be adapted to the individual fatigue state of the person to be irradiated. Furthermore, an environmentally adaptive irradiation intensity adjustment mechanism is constructed, enhancing the stability of transcranial stimulation. The environmental conditions for irradiation intensity are judged based on the ambient light intensity, realizing real-time perception and quantification of external irradiation interference. This allows for timely identification of the impact of environmental irradiation changes on transcranial stimulation, ensuring the reliability of transcranial stimulation by the nano-light source under different environmental irradiation conditions, reducing stimulation fluctuations caused by environmental factors, and realizing a data-driven process from environmental perception to irradiation adjustment. This, in turn, ensures the reliability of transcranial stimulation.

[0042] In another preferred embodiment based on the above embodiments, see [reference] Figure 2 As shown, this embodiment provides a transcranial irradiation anti-fatigue system based on nanophotosynthesis, used to apply the above-mentioned transcranial irradiation anti-fatigue method based on nanophotosynthesis, including: The data acquisition and judgment module is configured to acquire the irradiation usage data of the person to be irradiated, traverse the irradiation database based on the irradiation usage data, and determine the method for determining the irradiation intensity based on the traversal results.

[0043] The irradiation analysis module is configured to determine the irradiation intensity based on the amount of historical data in the irradiation database when determining the irradiation intensity based on the irradiation database, and to determine the irradiation intensity based on the fatigue data of the person to be irradiated and the irradiation fatigue model when determining the irradiation intensity based on the fatigue data of the person to be irradiated.

[0044] The irradiation processing module is configured to acquire the ambient light intensity of the person to be irradiated, determine the environmental compliance of the irradiation intensity based on the ambient light intensity, and when the environmental compliance of the irradiation intensity is not met, determine the environmental deviation based on the standard ambient light intensity and the ambient light intensity, and determine the irradiation fluctuation index of the irradiation intensity based on the environmental deviation.

[0045] The fatigue response module is configured to acquire an environmental sample set of the person to be irradiated, determine an irradiation adjustment model based on the environmental sample set, determine an irradiation prediction index based on the irradiation adjustment model and the environmental deviation, determine an irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index, adjust the irradiation intensity based on the irradiation adjustment index, and irradiate the person to be irradiated with the adjusted irradiation intensity.

[0046] This application is described with reference to flowchart illustrations and / or block diagrams of methods, apparatus (systems), and computer program goods according to embodiments of this application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart... Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0047] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0048] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1The steps of the function specified in one or more boxes.

[0049] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and not to limit it. Although the present invention has been described in detail with reference to the above embodiments, those skilled in the art should understand that modifications or equivalent substitutions can still be made to the specific implementation of the present invention. Any modifications or equivalent substitutions that do not depart from the spirit and scope of the present invention should be covered within the scope of protection of the claims of the present invention.

Claims

1. A transcranial irradiation method for fatigue relief based on nanophotosynthesis, characterized in that, include: The irradiation usage data of the person to be irradiated is obtained, and the irradiation database is traversed based on the irradiation usage data. The method for determining the irradiation intensity is determined based on the traversal results. When determining the irradiation intensity based on the irradiation database, the irradiation intensity is determined based on the amount of historical data in the irradiation database. When determining the irradiation intensity based on the fatigue irradiation model, the irradiation intensity is determined based on the fatigue data of the person to be irradiated and the irradiation fatigue model. The ambient light intensity of the person to be irradiated is obtained, and the environmental conditions of the irradiation intensity are judged to be qualified based on the ambient light intensity. When the environmental conditions of the irradiation intensity are not qualified, the environmental deviation is determined based on the standard ambient light intensity and the ambient light intensity, and the irradiation fluctuation index of the irradiation intensity is determined based on the environmental deviation. An environmental sample set of the person to be irradiated is obtained, an irradiation adjustment model is determined based on the environmental sample set, an irradiation prediction index is determined based on the irradiation adjustment model and the environmental deviation, an irradiation adjustment index is determined based on the relationship between the irradiation fluctuation index and the irradiation prediction index, the irradiation intensity is adjusted based on the irradiation adjustment index, and the person to be irradiated is irradiated with the adjusted irradiation intensity.

2. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 1, characterized in that, When traversing the irradiation database based on the irradiation usage data, and determining the method for determining irradiation intensity based on the traversal results, the method includes: The irradiation database includes several historical irradiation usage data and several historical irradiation intensities, and there is a one-to-one correspondence between the historical irradiation usage data and the historical irradiation intensities; The irradiation usage data is compared with all historical irradiation usage data in the irradiation database; If the irradiation database contains historical irradiation usage data that is identical to the irradiation usage data, then the irradiation intensity is determined based on the irradiation database. If no historical irradiation usage data identical to the irradiation usage data exists in the irradiation database, then the irradiation intensity is determined based on the fatigue irradiation model.

3. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 2, characterized in that, When determining the irradiance intensity based on the irradiance database, the irradiance intensity is determined based on the amount of historical data in the irradiance database, including: When the historical irradiation usage data that is identical to the irradiation usage data is unique in the irradiation database, the historical irradiation intensity corresponding to the historical irradiation usage data is determined as the irradiation intensity. When the historical irradiation usage data in the irradiation database is not unique and is the same as the irradiation usage data, the average value of the historical irradiation intensity corresponding to each historical irradiation usage data is determined as the irradiation intensity.

4. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 3, characterized in that, When determining the irradiation intensity based on a fatigue irradiation model, the irradiation intensity is determined based on the fatigue data of the person to be irradiated and the irradiation fatigue model, including: Obtain a transcranial sample set and divide the transcranial sample set into a sample training set and a sample test set; The model is built by finding the model building parameters based on grid search and building a random forest model. The random forest model is trained based on cross-validation and the sample training set, and the trained random forest model is tested based on the sample test set to determine the test index value. If the test metric value of the currently trained random forest model is less than the test metric value of the previously trained random forest model, then adjust the learning rate of the currently trained random forest model and continue training. If the test index value of the currently trained random forest model is greater than or equal to the test index value of the previously trained random forest model, then training is stopped, and the currently trained random forest model is determined as the irradiation fatigue model. The fatigue data is substituted into the irradiation fatigue model to determine the irradiation intensity.

5. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 4, characterized in that, When acquiring the ambient light intensity of the person to be irradiated, and determining the environmental suitability of the irradiation intensity based on the ambient light intensity, the process includes: Obtain the standard ambient light intensity corresponding to the ambient light intensity; When the ambient light intensity is greater than the standard ambient light intensity, the environment of the irradiation intensity is deemed unqualified. When the ambient light intensity is less than or equal to the standard ambient light intensity, the environment of the irradiation intensity is deemed to be qualified.

6. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 5, characterized in that, When the environment for the irradiance intensity is unqualified, an environmental deviation is determined based on the standard ambient light intensity and the ambient light intensity, and an irradiance fluctuation index for the irradiance intensity is determined based on the environmental deviation, including: The difference in irradiance between the ambient light intensity and the standard ambient light intensity is obtained, and the difference in irradiance is determined as the environmental deviation. Set a first environmental deviation and a second environmental deviation, wherein the first environmental deviation is greater than the second environmental deviation and the second environmental deviation is greater than zero; If the environmental deviation is greater than the first environmental deviation, then the first irradiation fluctuation index is determined as the irradiation fluctuation index. If the environmental deviation is less than or equal to the first environmental deviation and greater than or equal to the second environmental deviation, then the second irradiation fluctuation index is determined as the irradiation fluctuation index. If the environmental deviation is less than the second environmental deviation, then the third irradiation fluctuation index is determined as the irradiation fluctuation index. Wherein, 0 < first irradiation fluctuation index < second irradiation fluctuation index < third irradiation fluctuation index < 1.

7. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 6, characterized in that, When determining the irradiance adjustment model based on the environmental sample set, and determining the irradiance prediction index based on the irradiance adjustment model and the environmental deviation, the process includes: A convolutional neural network model is pre-obtained, and the irradiation adjustment model is determined based on the environmental sample set using the convolutional neural network model as the architecture; The environmental deviation is substituted into the irradiation adjustment model to determine the irradiation prediction index.

8. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 7, characterized in that, When determining the irradiance adjustment index based on the relationship between the irradiance fluctuation index and the irradiance prediction index, the following steps are included: Compare the irradiation prediction index with the irradiation fluctuation index; If the irradiation prediction index is equal to the irradiation fluctuation index, then the irradiation prediction index or the irradiation fluctuation index is determined as the irradiation adjustment index. If the irradiation prediction index is not equal to the irradiation fluctuation index, then the average of the irradiation prediction index and the irradiation fluctuation index shall be determined as the irradiation adjustment index.

9. The transcranial irradiation method for fatigue resistance based on nanophotosynthesis according to claim 8, characterized in that, When adjusting the irradiance intensity based on the irradiance adjustment index, the following is included: The irradiation intensity is directly proportional to the irradiation adjustment index.

10. A transcranial irradiation fatigue-relieving system based on nanophotosynthesis, used to apply the transcranial irradiation fatigue-relieving method based on nanophotosynthesis as described in any one of claims 1-9, characterized in that, include: The data acquisition and judgment module is configured to acquire the irradiation usage data of the person to be irradiated, traverse the irradiation database based on the irradiation usage data, and determine the method for determining the irradiation intensity based on the traversal results. The irradiation analysis module is configured to determine the irradiation intensity based on the amount of historical data in the irradiation database when it is determined to determine the irradiation intensity based on the irradiation database, and to determine the irradiation intensity based on the fatigue data of the person to be irradiated and the irradiation fatigue model when it is determined to determine the irradiation intensity based on the fatigue data of the person to be irradiated. The irradiation processing module is configured to acquire the ambient light intensity of the person to be irradiated, make a qualified judgment on the environment of the irradiation intensity based on the ambient light intensity, and when the environment of the irradiation intensity is unqualified, determine the environmental deviation amount based on the standard ambient light intensity and the ambient light intensity, and determine the irradiation fluctuation index of the irradiation intensity based on the environmental deviation amount. The fatigue response module is configured to acquire an environmental sample set of the person to be irradiated, determine an irradiation adjustment model based on the environmental sample set, determine an irradiation prediction index based on the irradiation adjustment model and the environmental deviation, determine an irradiation adjustment index based on the relationship between the irradiation fluctuation index and the irradiation prediction index, adjust the irradiation intensity based on the irradiation adjustment index, and irradiate the person to be irradiated with the adjusted irradiation intensity.

Images