A Smart Scoring Method and System for Meditation Effectiveness Based on Big Data Analysis

Abstract

This invention provides a method and system for intelligent scoring of meditation effects based on big data analysis, belonging to the field of data processing technology. The method includes: Step 1, collecting in real time the user's electroencephalogram (EEG) signals, heart rate variability, skin conductance waveforms, and respiratory rhythm signals during meditation using wearable devices, and acquiring environmental noise decibel values, light intensity, and environmental temperature parameters through environmental sensors to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters; Step 2, generating personalized benchmark features based on the resting state physiological parameters in the multidimensional raw dataset using a Gaussian mixture probability distribution, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters. This invention achieves a comprehensive, accurate, real-time, and individualized quantitative assessment of meditation effects through multi-source data acquisition and fusion, personalized benchmark construction, multi-dimensional physiological and environmental indicator analysis, and dynamic scoring adjustment.

Description

Technical Field

[0001] This invention relates to the field of data processing technology, and in particular to a method and system for intelligent scoring of meditation effects based on big data analysis. Background Technology

[0002] Traditional assessments of meditation effectiveness rely primarily on users' subjective descriptions or professionals' experience-based judgments. For example, after completing a meditation session, a user might simply describe their experience as "feeling relaxed" or "having improved concentration," but such descriptions lack concrete metrics. Different users have vastly different perceptions and expressions of "relaxation"; some consider calm breathing as relaxation, while others perceive inner peace and a lack of distractions. Similarly, professional judgments vary. An experienced meditation instructor might assess a student's meditation effectiveness based on posture and breathing rate, while another instructor, using different criteria, might reach a different conclusion. This approach is highly subjective and individualized, lacking objective, accurate, and quantifiable evaluation standards. Without standardized quantitative indicators, it's difficult to scientifically and systematically analyze and compare the meditation effects of different users at different times, and it's also impossible to provide users with targeted improvement suggestions such as "meditation is more effective when the proportion of alpha waves in the brain reaches XX%."

[0003] While existing methods for evaluating the effectiveness of meditation attempt to analyze physiological signals, most focus only on single or a few physiological indicators, failing to comprehensively reflect the overall changes in the body's physiological state during meditation. For example, some assessment methods rely solely on heart rate variability to judge the effectiveness of meditation; if a user's heart rate decreases and heart rate variability increases during meditation, it is considered a good meditation experience. However, ignoring other important physiological signals such as brain waves and skin conductance may lead to misjudgments. If the user's brain waves show a low proportion of relaxation-related theta waves and alpha waves, they may not actually have entered a deep meditative state.

[0004] Furthermore, some methods lack consideration for individual physiological differences and employ uniform evaluation standards, making it difficult to accurately assess the meditation effects of different users. For example, people of different ages and physical conditions naturally differ in their baseline heart rate, EEG characteristics, etc. Using a uniform standard such as "a heart rate below 70 beats per minute is considered effective meditation" is clearly unfair to users with higher baseline heart rates and cannot accurately assess their true meditation effects. Summary of the Invention

[0005] The technical problem to be solved by this invention is to provide a method and system for intelligent scoring of meditation effects based on big data analysis, so as to achieve objective, accurate and quantitative evaluation of meditation effects and provide users with scientific feedback on meditation effects.

[0006] To solve the above-mentioned technical problems, the technical solution of the present invention is as follows:

[0007] Firstly, a smart scoring method for meditation effectiveness based on big data analysis, the method comprising:

[0008] Step 1: Real-time acquisition of brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals during user meditation using wearable devices, and acquisition of environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters.

[0009] Step 2: Based on the resting state physiological parameters in the multidimensional original dataset, a Gaussian mixture probability distribution is used to generate personalized baseline features, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters.

[0010] Step 3: Decompose the EEG signal in the frequency domain, extract the energy proportions of theta waves and alpha waves respectively, and calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform to form a real-time physiological feature vector.

[0011] Step 4: Calculate the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. Couple the calculation of the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance, and convert the calculation results into a meditation effect score through a piecewise linear mapping algorithm.

[0012] Step 5: Compare the environmental interference level with the preset benchmark threshold. When the environmental interference level is greater than or equal to the benchmark threshold, activate the segmented attenuation mechanism.

[0013] Secondly, a smart scoring system for meditation effectiveness based on big data analysis includes:

[0014] The data acquisition module is used to collect the user's brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals in real time through wearable devices, as well as to obtain environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors, and generate a multidimensional raw dataset that integrates physiological signals and environmental parameters.

[0015] The benchmark generation module is used to generate personalized benchmark features based on the resting state physiological parameters in the multidimensional raw dataset, using a Gaussian mixture probability distribution. These features include the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters.

[0016] The feature extraction module is used to perform frequency domain decomposition on the EEG signal, extract the energy ratio of theta wave and alpha wave respectively, calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform, and form a real-time physiological feature vector.

[0017] The scoring calculation module is used to calculate the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. It couples the calculation of the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance, and converts the calculation results into a meditation effect score value through a piecewise linear mapping algorithm.

[0018] The attenuation processing module compares the environmental interference level with a preset benchmark threshold. When the environmental interference level is greater than or equal to the benchmark threshold, the segmented attenuation mechanism is activated.

[0019] Thirdly, a computing device, comprising:

[0020] One or more processors;

[0021] A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method.

[0022] Fourthly, a computer-readable storage medium storing a program that, when executed by a processor, implements the method.

[0023] The above-described solution of the present invention has at least the following beneficial effects:

[0024] By collecting various physiological signals such as electroencephalogram (EEG) and heart rate variability using wearable devices, and simultaneously acquiring environmental parameters such as noise, light, and temperature using environmental sensors, a multi-dimensional raw dataset is generated. This fusion of multi-source data comprehensively reflects the user's state during meditation from both physiological and environmental dimensions, improving data completeness and accuracy compared to single data sources. Based on the user's resting state physiological parameters, a Gaussian mixture probability distribution is used to generate personalized baseline features, taking into account individual physiological differences. Since different users have different baseline physiological states, the establishment of personalized baselines avoids assessment bias caused by using uniform standards, improving the accuracy and relevance of the assessment.

[0025] Frequency domain decomposition of EEG signals is performed to extract the energy ratios of theta and alpha waves. Combined with chaos sensitivity indices from heart rate variability signals and phase synchronization parameters from raw skin conductance waveforms, the analysis delves into multiple physiological levels, including brain activity, cardiovascular regulation, and nervous system responses, to deeply explore the physiological changes during meditation, making the assessment more comprehensive and professional. Environmental parameters are incorporated into the assessment system, calculating environmental interference levels to fully consider the impact of environmental factors on meditation effectiveness. Environmental factors such as noise, light, and temperature directly affect the user's meditation experience and results. Quantifying environmental interference more accurately reflects the actual meditation state, providing users with more objective assessment results.

[0026] The system generates real-time physiological feature vectors that reflect changes in a user's physiological state during meditation. Since a user's physiological state is dynamic during meditation, real-time monitoring and analysis capture these changes, providing immediate feedback and helping the user adjust their meditation state. The system dynamically calculates neural relaxation, autonomic nervous system balance, and environmental disturbance based on real-time physiological feature vectors and environmental parameters, and performs coupled calculations. Simultaneously, when environmental disturbance reaches a certain threshold, a piecewise decay mechanism is activated, allowing the assessment results to dynamically adjust with changes in the user's physiological state and environment, ensuring the timeliness and accuracy of the assessment. A piecewise linear mapping algorithm converts the calculation results into meditation effect scores, transforming complex physiological and environmental factors into specific numerical scores, making the assessment results more intuitive and easier to understand. This quantitative approach provides users with a clear standard to measure their meditation effectiveness, facilitating self-assessment and comparison. Detailed assessment dimensions and quantitative scores provide users with specific feedback, helping them understand their strengths and weaknesses during meditation. For example, users can adjust their meditation methods and environment in a targeted manner based on scores such as nervous relaxation level and autonomic nervous system balance, thereby improving the effect of meditation and achieving personalized meditation training and improvement. Attached Figure Description

[0027] Figure 1 This is a flowchart illustrating an intelligent scoring method for meditation effects based on big data analysis, provided by an embodiment of the present invention.

[0028] Figure 2 This is a schematic diagram of an intelligent scoring system for meditation effects based on big data analysis, provided by an embodiment of the present invention. Detailed Implementation

[0029] Exemplary embodiments of the present disclosure will now be described in more detail with reference to the accompanying drawings. While exemplary embodiments of the present disclosure are shown in the drawings, it should be understood that the present disclosure may be implemented in various forms and should not be limited to the embodiments set forth herein. Rather, these embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the scope of the disclosure to those skilled in the art.

[0030] like Figure 1 As shown, an embodiment of the present invention proposes an intelligent scoring method for meditation effects based on big data analysis. The method includes the following steps:

[0031] Step 1: Real-time acquisition of brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals during user meditation using wearable devices, and acquisition of environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters.

[0032] Step 2: Based on the resting state physiological parameters in the multidimensional original dataset, a Gaussian mixture probability distribution is used to generate personalized baseline features, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters.

[0033] Step 3: Decompose the EEG signal in the frequency domain, extract the energy proportions of theta waves and alpha waves respectively, and calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform to form a real-time physiological feature vector.

[0034] Step 4: Calculate the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. Couple the calculation of the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance, and convert the calculation results into a meditation effect score through a piecewise linear mapping algorithm.

[0035] Step 5: Compare the environmental interference level with the preset benchmark threshold. When the environmental interference level is greater than or equal to the benchmark threshold, activate the segmented attenuation mechanism.

[0036] In this embodiment of the invention, wearable devices collect multi-dimensional physiological signals in real time, including electroencephalogram (EEG) signals, heart rate variability, raw skin conductance waveforms, and respiratory rhythm signals. Simultaneously, environmental sensors are used to acquire ambient noise levels (decibels), light intensity, and ambient temperature parameters, generating a multi-dimensional raw dataset. This overcomes the limitations of traditional assessments relying on subjective feelings or single indicators, using objective data to comprehensively reflect the physiological state of the body and the influence of environmental factors during meditation. For example, EEG signals reflect brain activity, and raw skin conductance waveforms reflect the excitation level of the autonomic nervous system. Personalized baseline features are generated using resting-state physiological parameters from the multi-dimensional raw dataset, employing a Gaussian mixture probability distribution. Considering the differences in physiological characteristics among users, a uniform standard is no longer used, making the assessment more tailored to individual circumstances. For instance, users of different ages and physical conditions have different basic physiological indicators; personalized baseline features accurately measure the degree of improvement in each user's meditation effect relative to their own, improving the accuracy and reliability of the assessment.

[0037] This method employs frequency domain decomposition of EEG signals to extract the energy proportions of theta and alpha waves, calculates the chaos sensitivity index of heart rate variability signals, and obtains phase synchronization parameters from the original skin conductance waveform, thus uncovering the characteristics of physiological signals from multiple perspectives. Compared to methods that focus on only one or a few indicators, this approach provides a deeper and more comprehensive understanding of changes in the body's physiological state during meditation. For example, theta and alpha waves are closely related to states of relaxation and focus, and analyzing their energy proportions helps in assessing mental state during meditation. The method separately calculates neural relaxation, autonomic nervous system balance, and environmental interference, then couples these three factors and converts them into a meditation effect score using a piecewise linear mapping algorithm. By comprehensively considering physiological state and environmental factors, the method quantifies the meditation effect, avoiding the one-sidedness of single-factor assessments. Furthermore, the piecewise linear mapping algorithm makes the score more realistic, providing users with intuitive and scientific quantitative results of meditation effects.

[0038] The environmental disturbance level is compared with a preset benchmark threshold. When the environmental disturbance level is greater than or equal to the benchmark threshold, a segmented attenuation mechanism is activated. Considering the impact of the environment on meditation effectiveness, the score is dynamically adjusted based on the degree of environmental disturbance, making the evaluation results more accurately reflect the actual meditation effect. For example, in a noisy environment, even if the physiological state is good, the score will decrease accordingly due to significant environmental interference, reminding users of the importance of environmental factors to meditation effectiveness and providing a reference for users to choose a suitable meditation environment.

[0039] In a preferred embodiment of the present invention, step 1 above, which involves real-time acquisition of the user's electroencephalogram (EEG) signals, heart rate variability, raw skin conductance waveforms, and respiratory rhythm signals during meditation via a wearable device, and obtaining environmental noise decibel values, light intensity, and environmental temperature parameters via environmental sensors, to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters, may include:

[0040] In this embodiment of the invention, a headband-type EEG monitoring device is selected. These devices are equipped with multiple electrodes and can accurately collect EEG signals from the scalp surface. For example, the NeuroSky MindWave series uses dry electrode technology, is relatively comfortable to wear, and is suitable for long-term EEG signal acquisition. Smart bracelets, such as the Fitbit bracelet, are also selected. These can monitor heart rate in real time through optical or electrode methods and calculate heart rate variability-related parameters. Skin conductance sensors are used, which work by measuring changes in the resistance of the skin surface to reflect skin conductance. Some professional biofeedback devices integrate skin conductance sensors to accurately acquire raw skin conductance waveforms. Chest-strap respiratory sensors acquire respiratory rhythm signals by detecting chest rise and fall, while nasal airflow sensors acquire signals by monitoring changes in airflow into and out of the nasal cavity.

[0041] Noise sensors, such as B&K's noise sensors, can accurately measure the decibel level of noise in the environment. Light intensity sensors, such as the BH1750, can convert light intensity into an electrical signal, enabling real-time monitoring of ambient light intensity. The DS18B20 ambient temperature sensor is a digital temperature sensor with advantages such as high accuracy and strong anti-interference capabilities, accurately measuring ambient temperature. EEG acquisition devices, heart rate variability acquisition devices, skin conductance acquisition devices, and respiratory rhythm acquisition devices are connected to data acquisition terminals (such as smartphones, tablets, or dedicated data acquisition instruments). Connection methods can be Bluetooth or Wi-Fi, depending on the device's support. For example, the NeuroSky MindWave EEG cap can be paired with a smartphone via Bluetooth.

[0042] Configure the wearable device's parameters, such as setting the sampling frequency and gain, to ensure the acquired signal quality meets requirements. Different devices may have different parameter setting methods; refer to the device's instruction manual. Connect the noise level sensor, light intensity sensor, and ambient temperature sensor to the data acquisition terminal, using Bluetooth or Wi-Fi. Calibrate and configure the environmental sensors to ensure measurement accuracy. For example, the noise level sensor needs calibration before use to eliminate measurement errors. Start the data acquisition program before the user begins meditation. The data acquisition program can be dedicated software installed on the data acquisition terminal. The program will simultaneously acquire EEG signals, heart rate variability, raw skin conductance waveforms, and respiratory rhythm signals, as well as ambient noise level, light intensity, and ambient temperature parameters, according to a pre-set sampling frequency. The acquired physiological signals and environmental parameter data will be transmitted to the data acquisition terminal in real time via the connection. For example, when transmitting via Bluetooth, the device will send the acquired data to the terminal device in a specific Bluetooth protocol format. After receiving the data, the data acquisition terminal will perform preliminary processing and storage, such as arranging the data according to time series and storing it as a file in a specific format (such as CSV, JSON, etc.).

[0043] At the data acquisition terminal, the collected physiological signals and environmental parameter data are integrated. For example, EEG signals, heart rate variability, raw skin conductance waveforms, respiratory rhythm signals, and environmental noise levels (decibels), light intensity, and ambient temperature parameters at the same time point are combined to form a single data record. As data is continuously collected and integrated, all data records are aggregated to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters.

[0044] In a preferred embodiment of the present invention, step 2 above, which generates personalized baseline features based on the resting state physiological parameters in the multidimensional original dataset using a Gaussian mixture probability distribution, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters, may include:

[0045] Step 200: Determine the time interval in which the user is in a resting state from the multidimensional raw dataset, and extract physiological parameter data from the time interval in the resting state, including electroencephalogram (EEG) signals, heart rate variability, skin conductance, and respiratory rhythm parameters.

[0046] Step 201: For each physiological parameter, construct a Gaussian mixture model to model the mean vector and covariance matrix of each physiological parameter.

[0047] Step 202: Combine the mean vector and covariance matrix of each physiological parameter to form personalized baseline features.

[0048] In this embodiment of the invention, the multidimensional raw dataset undergoes preliminary processing, including the removal of outliers and noisy data. For example, for electroencephalogram (EEG) signals, sudden spikes or values ​​exceeding the normal range can be identified as outliers and removed using statistical methods (such as the 3σ principle). For heart rate variability data, noise can be removed using methods such as moving average filtering. Combining user behavior records or sensor-attached information (such as button operation records on the device, user-manual markings, etc.) assists in determining the resting state. Simultaneously, the changing trends of physiological parameters are analyzed. For example, when heart rate variability tends to stabilize, respiratory rhythm is smooth, and EEG signal fluctuations are small, the user can be preliminarily considered to be in a resting state. Using rule-based algorithms, such as setting thresholds for the fluctuation range of heart rate variability and the frequency threshold of respiratory rhythm, when physiological parameters consistently meet these threshold conditions over a period of time, this time period is determined as the resting state time interval. Within the determined resting state time interval, EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters are extracted from the multidimensional raw dataset, respectively. For EEG signals, the values ​​of each sampling point are extracted in chronological order; for heart rate variability, relevant data such as the interval between adjacent heartbeats are extracted; for skin conductance, its original waveform data is extracted; for respiratory rhythm, parameters such as respiratory rate and respiratory depth are extracted.

[0049] Step 201: After acquiring physiological parameter data such as EEG signals, heart rate variability, skin conductance, and respiratory rhythm, standardization is required to eliminate the influence of dimensions and unify the data scale because the numerical ranges of different types of physiological parameters vary greatly (for example, the voltage amplitude of EEG signals may be at the microvolt level, while heart rate variability data is measured in milliseconds). First, calculate the mean of each type of physiological parameter data. Taking heart rate variability data as an example, sum the values ​​of all adjacent heartbeat intervals in the data set, and then divide by the total number of data points to obtain the mean of the heart rate variability data set. Next, calculate the difference between each data point and the mean, square these differences, sum them, divide by the total number of data points, and finally take the square root of the result to obtain the standard deviation of the data set. With the mean and standard deviation, subtract the mean from each original data point and then divide by the standard deviation to complete the standardization. After this processing, the distribution of each type of physiological parameter data becomes a standard normal distribution with a mean of 0 and a standard deviation of 1.

[0050] To find a Gaussian mixture model that describes the distribution of physiological parameter data, the number of Gaussian components needs to be determined. First, a reasonable range for the number of components is set, for example, starting with one component and gradually increasing to ten. For each set number of components, a corresponding Gaussian mixture model is constructed to fit the standardized physiological parameter data. During the fitting process, the Akaike Information Criterion (AIC) is used to evaluate the model's performance. AIC considers both the model's fit to the data and its complexity. Specifically, the better the model fits the data and the fewer parameters it contains, the lower the AIC value. The AIC value is calculated for each model when trying different numbers of components. For example, when trying to build a model with three Gaussian components, one AIC value is calculated based on the model's fit to the data; when building a model with four Gaussian components, another AIC value is obtained. Finally, the number of components corresponding to the model with the lowest AIC value is selected as the final number of components for the Gaussian mixture model describing the distribution of that physiological parameter data.

[0051] After determining the number of components in the Gaussian mixture model, the EM algorithm is used to train the model. In the initial training phase, the model parameters are randomly initialized, including the mean vector, covariance matrix, and component weights for each Gaussian component. Based on the model parameters obtained from the current initialization or the previous iteration, each data point is analyzed. Taking a data point in the electrodermal conductance data as an example, the probability of this data point belonging to each Gaussian component is calculated based on the parameters (mean vector, covariance matrix, and component weights). This process is like calculating the "probability of belonging" of each data point to each Gaussian component. Based on the probabilities of each data point belonging to each Gaussian component calculated in the E-step, the model parameters are re-estimated. Specifically, the weights of each Gaussian component are updated to better reflect the actual distribution of data points within each component; the mean vector of each Gaussian component is recalculated to better represent the central tendency of data points within that component; and the covariance matrix is ​​updated to better describe the dispersion and relationships of data points within the component. The E-step and M-step steps are repeated continuously, with each iteration bringing the model parameters closer to the true distribution of the data. When the pre-set maximum number of iterations is reached, the model parameters are considered converged, and the training process ends. After training, the mean vector and covariance matrix for each Gaussian component are obtained. If the model contains multiple Gaussian components, since each component has different importance in describing the data distribution (reflected by its component weights), a weighted average of the mean vectors and covariance matrices of each component needs to be calculated based on their weights.

[0052] In practice, the mean vector of each component is multiplied by its corresponding weight, and these products are then added together to obtain the final mean vector. A similar weighted calculation is performed on the covariance matrix, taking into account the difference between the component mean and the overall mean, to finally obtain the mean vector and covariance matrix that can comprehensively reflect the distribution characteristics of the physiological parameter data.

[0053] Step 202 involves organizing the mean vectors and covariance matrices of the EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters calculated in Step 201, ensuring consistency in data format and dimensions. These mean vectors and covariance matrices are then combined in a specific order; for example, all mean vectors can be arranged sequentially to form a large vector, and all covariance matrices can be arranged sequentially to form a matrix block. Ultimately, this results in a personalized baseline feature vector containing information on multiple physiological parameters.

[0054] Assume that before a user begins meditation training, they wear a device to collect 30 minutes of physiological and environmental data, forming a multidimensional raw dataset. Analysis reveals that during the 5th-10th minute after data collection begins, the user is in a resting state (sitting quietly without significant physical activity or emotional fluctuations). Data from the 5th-10th minute of the multidimensional raw dataset is extracted to obtain resting brainwave signals (e.g., 300 data points collected per second), heart rate variability data (interval between adjacent heartbeats), skin conductance data (voltage values ​​from the raw waveform), and respiratory rhythm data (respiratory rate and depth). Taking heart rate variability data as an example, after standardization, the Gaussian mixture model is determined to contain two components using the AIC criterion. The model is trained using the EM algorithm, and after multiple iterations, the mean vectors of the two Gaussian components are obtained as [80, 85] (assuming they represent the average levels of two different heart rate variability states), and their covariance matrices are respectively... and After weighted averaging based on component weights, the final mean vector and covariance matrix of heart rate variability are obtained. The same operation is performed on EEG signals, skin conductance, and respiratory rhythm parameters. The mean vectors and covariance matrices of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters are combined to form a personalized benchmark feature containing this information.

[0055] This method generates personalized baseline features based on users' resting state physiological parameters, fully considering individual differences. Different users have different physiological characteristics, and traditional uniform baselines cannot accurately reflect individual realities. This method, however, can tailor a baseline for each user, making the evaluation of meditation effects more aligned with their individual circumstances and improving the accuracy and effectiveness of the assessment. The baseline features are constructed based on resting state data, where physiological parameters are relatively stable and less affected by external interference and temporary factors. Comparative analysis using this baseline reduces errors caused by data fluctuations, improving the stability and reliability of the baseline features. By incorporating multiple physiological parameters such as EEG signals, heart rate variability, skin conductance, and respiratory rhythm, the baseline features comprehensively reflect the user's physiological state from multiple dimensions, providing rich information. Compared to baseline settings based on single or a few physiological indicators, this method can more comprehensively assess the user's physiological changes during meditation, providing more comprehensive data support for a deeper understanding of the impact of meditation on the body. Resting state physiological parameters also change with changes in the user's physical condition, lifestyle, and other factors. By regularly updating the original multidimensional dataset and regenerating personalized benchmark features, the evaluation benchmark can be adapted to these changes, ensuring that the evaluation of meditation effectiveness is always timely and accurate, and continuously providing users with valuable feedback and guidance.

[0056] In a preferred embodiment of the present invention, step 3 above, which involves frequency domain decomposition of the EEG signal, extracting the energy proportions of theta waves and alpha waves respectively, and calculating the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform to form a real-time physiological feature vector, may include:

[0057] Step 300: Convert the EEG signal from the time domain to the frequency domain. In the frequency domain, divide the corresponding frequency bands according to the frequency range of theta waves and alpha waves.

[0058] Step 301: Calculate the energy in each frequency band and obtain the frequency band energy ratio of theta wave and alpha wave through normalization processing to establish the baseline of EEG characteristics of the user in a meditative state.

[0059] Step 302: After establishing the baseline of the EEG characteristics of the user in a meditative state, the current heart rate variability signal is obtained, and the current heart rate variability signal is compared with the personalized baseline characteristics using the dynamic time warping algorithm to obtain the comparison results.

[0060] Step 303: Based on the comparison results, calculate the chaos sensitivity index of the heart rate variability signal to reflect the degree of deviation between the current heart rate fluctuation and the personalized benchmark.

[0061] Step 304: After obtaining the correlation features of EEG and heart rate variability, acquire the original waveform of skin conductance and respiratory rhythm signal, and use the phase-locked value algorithm to analyze the phase synchronization between the original waveform of skin conductance and respiratory rhythm signal to determine the coordinated change features of skin conductance signal and respiratory rhythm.

[0062] Step 305: Combine the frequency band energy ratio of theta wave and alpha wave, the chaos sensitivity index of heart rate variability signal, the original waveform of skin conductance and respiratory rhythm signal to form a real-time physiological feature vector containing energy ratio, chaos sensitivity and phase synchronization.

[0063] In this embodiment of the invention, the EEG signal records voltage values ​​that change over time in the time domain, making it difficult to directly extract the characteristics of different frequency components. To better analyze the theta and alpha waves, it is necessary to convert them from the time domain to the frequency domain. This is accomplished using algorithms such as the Fast Fourier Transform (FFT). These algorithms convert the EEG signal, which is originally time-dependent in the time domain, into a signal with frequency as the independent variable, thus clearly showing the distribution of different frequency components. After obtaining the frequency domain signal, based on the predetermined frequency ranges of theta waves (frequency range 4-7Hz) and alpha waves (frequency range 8-13Hz), the corresponding frequency bands are accurately divided in the frequency domain signal. This is analogous to marking the regions where theta and alpha waves are located according to their frequency ranges in a spectrum diagram. The energy within each frequency band is calculated, and through normalization, the frequency band energy proportions of theta and alpha waves are obtained to establish a baseline of EEG characteristics in the user's meditative state.

[0064] Step 301: Within the defined theta and alpha wave frequency bands, calculate the energy of the signal in each band. Signal energy reflects the intensity of that frequency component within the overall EEG signal. Energy can be calculated by summing the squares of the signal amplitudes within each band. To eliminate differences in EEG signal intensity between individuals and the influence of overall EEG signal intensity variations for the same user at different times, the calculated theta and alpha wave frequency band energies need to be normalized. Normalization involves dividing the energy of each frequency band by the total energy of the entire EEG signal to obtain the energy proportions of the theta and alpha waves. By performing this calculation and processing multiple times during meditation, a baseline of EEG characteristics during meditation can be established, reflecting the typical proportions of theta and alpha wave energy during meditation.

[0065] Step 302: Using a suitable heart rate monitoring device, such as a smart bracelet or heart rate belt, the user's current heart rate variability signal is collected in real time. Heart rate variability refers to the change in the time interval between adjacent heartbeats, reflecting the regulatory function of the autonomic nervous system on the heart. The personalized baseline feature is generated in step 2 based on the user's resting physiological parameters, which includes relevant information on heart rate variability. The Dynamic Time Warping (DTW) algorithm can handle the stretching and distortion of two time series signals on the time axis, and can find the final matching path between the two signals. The currently collected heart rate variability signal is compared with the heart rate variability data in the personalized baseline feature using dynamic time warping, and the comparison result is obtained by calculating indicators such as the distance between the two signals under the optimal matching path.

[0066] Step 303: Based on the comparison results obtained in step 302, a chaos sensitivity index for the heart rate variability signal is calculated using a specific algorithm. The chaos sensitivity index measures the complexity and irregularity of the heart rate variability signal, as well as the degree of difference between the current heart rate fluctuation and the personalized baseline. If the comparison results show a large difference between the current heart rate variability signal and the baseline signal, the value of the chaos sensitivity index will also be relatively large, indicating that the current heart rate fluctuation deviates from the personalized baseline.

[0067] Step 304: Acquire the raw waveform of skin conductance and the respiratory rhythm signal using a skin conductance sensor and a respiratory rhythm sensor, respectively. Skin conductance reflects changes in the activity of sweat glands on the skin surface and is closely related to the activity of the autonomic nervous system; respiratory rhythm reflects changes in the frequency and depth of respiration. The phase-locked value (PLV) algorithm is used to analyze the raw waveform of skin conductance and the respiratory rhythm signal. The phase-locked value algorithm measures the degree of synchronization between two signals in phase. By calculating the phase-locked value of the skin conductance signal and the respiratory rhythm signal, their phase synchronization can be determined. A high phase-locked value indicates strong phase synchronization between the skin conductance signal and the respiratory rhythm signal, meaning they exhibit coordinated changes; conversely, a low phase-locked value indicates weak synchronization.

[0068] Step 305: The frequency band energy ratios of theta and alpha waves obtained in step 301, the chaos sensitivity index of the heart rate variability signal obtained in step 303, and the phase synchronization parameters of the original skin conductance waveform and respiratory rhythm signal obtained in step 304 are combined in a certain order to form a vector. This vector contains multiple aspects of physiological characteristic information and can comprehensively reflect the user's physiological state at the current moment.

[0069] Suppose a user is practicing meditation, and physiological signals are collected in real time using devices such as an EEG cap, a smart bracelet, and a skin conductance sensor. After the EEG signals are collected, they are converted to the frequency domain using a Fast Fourier Transform (FFT), dividing the frequency domain into theta wave (4-7Hz) and alpha wave (8-13Hz) bands. The energy in the theta wave band is calculated to be 10 units, the energy in the alpha wave band to be 20 units, and the total energy of the entire EEG signal to be 50 units. After normalization, the energy proportion of the theta wave band is 10 ÷ 50 = 0.2, and the energy proportion of the alpha wave band is 20 ÷ 50 = 0.4, thus establishing the baseline of the user's EEG characteristics in the meditation state. Simultaneously, the smart bracelet collects the current heart rate variability (HRV) signal. Using a dynamic time warping algorithm, this HRV signal is compared with the HRV data in the personalized baseline features. It is found that the current HRV signal and the baseline signal have some stretching and distortion on the time axis, and the calculated matching distance between the two is relatively large. Based on this comparison, the chaos sensitivity index of the heart rate variability signal was calculated to be 0.8, indicating that the current heart rate fluctuations deviate significantly from the personalized baseline.

[0070] Skin conductance sensor and respiratory sensor acquired raw skin conductance waveform and respiratory rhythm signal, respectively. Analysis using a phase-locked value algorithm revealed a phase-locked value of 0.6, indicating a certain phase synchronization between the skin conductance signal and the respiratory rhythm signal, demonstrating coordinated changes. Finally, the energy proportions of the theta wave band (0.2), the energy proportion of the alpha wave band (0.4), the chaos sensitivity index of the heart rate variability signal (0.8), and the phase synchronization parameter between skin conductance and respiratory rhythm (0.6) were combined to form a real-time physiological feature vector [0.2, 0.4, 0.8, 0.6].

[0071] This study integrates multiple physiological indicators, including electroencephalogram (EEG), heart rate variability (HRV), skin conductance, and respiratory rhythm, to comprehensively reflect the user's physiological state during meditation from different perspectives. While a single physiological indicator may only reflect one aspect of information, this multi-indicator combination allows for a more accurate grasp of the user's overall physiological changes, providing a richer and more comprehensive basis for evaluating meditation effectiveness. When calculating the chaos sensitivity index of the HRV signal, the current signal is compared with personalized baseline features, fully considering individual physiological differences. Different users have different physiological characteristics and baseline states; using personalized baselines allows for a more precise assessment of each user's heart rate fluctuations during meditation, improving the accuracy and specificity of the assessment. By analyzing the phase synchronization between the raw waveform of skin conductance and the respiratory rhythm signal, the synergistic changes between different physiological signals can be captured. The autonomic nervous system regulates multiple physiological systems, and there may be intrinsic correlations between different physiological signals. Understanding this synergistic relationship helps to deepen the understanding of the comprehensive impact of meditation on the human physiological system, providing valuable information for further optimizing meditation training programs. The resulting real-time physiological feature vector can reflect the user's physiological state changes in real time during meditation. This allows for the timely detection of abnormalities or trends in the user's physiological state during meditation, providing real-time feedback and guidance. For example, a sudden increase in the chaos sensitivity index of heart rate variability signals may indicate that the user's current meditation state is being disturbed and requires immediate adjustment.

[0072] In a preferred embodiment of the present invention, step 302, after establishing the baseline of the EEG characteristics of the user in a meditative state, obtains the current heart rate variability signal, and compares the current heart rate variability signal with the personalized baseline characteristics using a dynamic time warping algorithm to obtain the comparison result, may include:

[0073] Step 3020: After establishing the EEG characteristic baseline, the user's current heart rate data during meditation is acquired in real time through a wearable heart rate monitoring device.

[0074] Step 3021: Process the current heart rate data, calculate the heart rate variability index, and obtain the current heart rate variability signal;

[0075] Step 3022: Using the dynamic time warping algorithm, compare the current heart rate variability signal with the heart rate variability baseline data in the personalized baseline features. During the comparison process, calculate the distance between each matching point.

[0076] Step 3023: Determine the final matching path between the two signals based on the distance between each matching point, and sum the distances between each matching point to obtain the total comparison distance, i.e., the comparison result.

[0077] In this embodiment of the invention, after establishing the baseline of brainwave characteristics in the user's meditation state, the real-time monitoring function of the wearable heart rate monitoring device is activated. Wearable heart rate monitoring devices, such as smart bracelets and heart rate monitoring chest straps, continuously collect physiological signals generated by the heartbeat through contact with the skin using photoelectric sensors or electrode pads. Taking a smart bracelet as an example, its built-in photoelectric sensor emits green light to illuminate the skin. Based on changes in the degree of light absorption by the blood, it captures the periodic changes in blood vessel volume during a heartbeat, which are then converted into electrical signals. The device performs preliminary processing on these electrical signals, displays and transmits the current heart rate data in real time in digital or waveform form, ensuring that every heartbeat is recorded promptly and accurately during the user's meditation process.

[0078] Step 3021: The acquired raw heart rate data often contains noise or outliers, so it is first preprocessed. Obvious erroneous data caused by motion artifacts, poor equipment contact, etc., such as suddenly high or low heart rate values ​​appearing within a short period, are removed. Next, a filtering algorithm is used to smooth the data, removing high-frequency noise interference, making the heart rate data more stable and reliable. After preprocessing, heart rate variability indices are calculated. Heart rate variability refers to the small differences between successive heartbeat cycles, measured by calculating the changes in the intervals between adjacent heartbeats (RR intervals). In the calculation process, the time point corresponding to each heartbeat is accurately extracted, and the difference between two adjacent heartbeat time points is calculated, resulting in a series of RR interval data. Based on these RR interval data, various heart rate variability indices are calculated using statistical methods, such as the root mean square of the difference between adjacent RR intervals (RMSSD) and the standard deviation of the RR intervals (SDNN). These indices reflect the characteristics of heart rate variability from different perspectives. Combining the calculated indices forms a heart rate variability signal that comprehensively describes the current heart rate fluctuations.

[0079] Step 3022: The Dynamic Time Warping (DTW) algorithm is used to solve the similarity measurement problem when two time series signals are not perfectly aligned on the time axis. The current heart rate variability signal and the heart rate variability baseline data in the personalized baseline features are considered as two time series. At the start of the comparison, the starting points of the two signals are used as initial matching points. The distance between these two initial points is calculated using methods such as Euclidean distance, i.e., calculating the square root of the sum of the squares of the differences between the corresponding index values ​​of the two points. Then, based on the current matching point, the next possible matching point is explored according to certain rules (such as allowing one unit of movement up, down, left, or right on the time axis), and the distance between the new matching points is calculated again. During the exploration process, multiple possible matching paths are formed. This process is repeated continuously, calculating the distance between each set of possible matching points, until the endpoints of both signals are matched, thus obtaining the distance information between all possible matching points.

[0080] Step 3023: Based on the distances between all matching points calculated in step 3022, find the matching path that minimizes the total distance. This path is the final matching path between the two heart rate variability signals. Specifically, a dynamic programming approach can be used to backtrack from the end point, gradually determining the optimal matching path based on the minimum cumulative distance from each point to the endpoint. After determining the final matching path, the distances between all matching points along that path are summed; the total sum is the total comparison distance between the two heart rate variability signals. This comparison distance directly reflects the degree of difference between the current heart rate variability signal and the personalized baseline heart rate variability data. The smaller the comparison distance, the more similar the current heart rate variability signal is to the baseline data; the larger the comparison distance, the greater the difference between the two.

[0081] Assuming a user is meditating while wearing a smart bracelet, after establishing a baseline of EEG characteristics, the smart bracelet begins collecting heart rate data in real time. During a one-minute meditation session, the smart bracelet records heart rate data at second intervals, obtaining a total of 60 heart rate values, such as [72, 73, 72, 74, 73, ...]. This raw heart rate data is processed by first removing an outlier (value 85) caused by arm movement, and then using a low-pass filter to remove high-frequency noise. Next, the intervals between adjacent heartbeats are calculated. Assuming several adjacent RR intervals are [800ms, 820ms, 810ms, 790ms, ...], heart rate variability indicators such as RMSSD of 15ms and SDNN of 20ms are calculated, forming the current heart rate variability signal [15, 20, ...]. The user's personalized baseline heart rate variability baseline data is [12, 18, ...], which is compared using a dynamic time warping algorithm. During the comparison process, the distance to each possible matching point is calculated. For example, the Euclidean distance between the first matching point (15, 12) is... After continuous exploration and calculation, the final matching path was determined, and the distances of all matching points along the path were summed to obtain a total comparison distance of 12. This indicates that there is a certain difference between the current user's heart rate variability signal during meditation and the personalized baseline.

[0082] By comparing current heart rate variability (HRV) signals with personalized baseline characteristics, this approach fully considers the differences in resting state and physiological regulation capabilities among different users. Each person's baseline heart rate and autonomic nervous system regulation function are different. Using personalized baselines allows for a more accurate assessment of each user's heart rate fluctuations during meditation, avoiding errors caused by using a uniform standard and making the assessment results more closely reflect the individual's actual state. Real-time acquisition and analysis of HRV signals during meditation allows for timely capture of dynamic changes in heart rate. A user's psychological state and environmental factors during meditation can all affect heart rate. Through this dynamic comparative analysis, trends and abnormal fluctuations in heart rate can be identified, providing timely feedback for users to adjust their meditation state or method, helping them achieve better meditation effects. Heart rate variability is an important indicator reflecting autonomic nervous system function and is closely related to the degree of relaxation and psychological state during meditation. The results of comparing HRV signals with baseline data, combined with other physiological indicators such as electroencephalograms (EEGs), allow for a comprehensive assessment of meditation effects from multiple dimensions, making the assessment system more comprehensive and scientific, and providing richer information for a deeper understanding of the physiological impact of meditation.

[0083] In a preferred embodiment of the present invention, after obtaining the correlation features of EEG and heart rate variability in step 304, the original waveform of skin conductance and respiratory rhythm signal are acquired. A phase-locked value algorithm is used to analyze the phase synchronization between the original waveform of skin conductance and the respiratory rhythm signal, and to determine the coordinated change characteristics of skin conductance signal and respiratory rhythm. This may include:

[0084] Step 3040: Convert the skin conductance signal and respiratory rhythm signal from the time domain to the phase domain, acquire the skin conductance signal and respiratory rhythm signal, and calculate the phase difference between the skin conductance signal and respiratory rhythm signal at the same time.

[0085] Step 3041: Based on the phase difference at each moment, set a time window, and within each time window, perform statistical analysis on the phase difference within the corresponding time period, and convert the phase difference at each moment into a complex number representation.

[0086] Step 3042: Fuse the phase difference in complex form at each moment within the time window to obtain the phase lock value within the corresponding time window;

[0087] Step 3043: Summarize the phase lock values ​​for each time window to obtain the summary result;

[0088] Step 3044: Based on the summarized results and in conjunction with the preset evaluation criteria, determine the coordinated change characteristics between skin conductance signals and respiratory rhythm signals.

[0089] In this embodiment of the invention, after obtaining the related features of electroencephalogram (EEG) and heart rate variability, the raw waveforms of skin conductance and respiratory rhythm signals are acquired in real time using skin conductance sensors and respiratory rhythm sensors (such as chest strap respiratory sensors and nasal airflow sensors). Since the raw acquired signals are time-domain signals based on time variations, they need to be converted to the phase domain to analyze the phase relationships between the signals.

[0090] In the specific conversion process, mathematical transformation methods (such as the Hilbert transform) can be used. This transformation can convert the original time-domain signal into a form containing phase information, thereby obtaining the instantaneous phase of the skin conductance signal and the respiratory rhythm signal at each moment. After obtaining the instantaneous phase, the phase difference between the two signals at the same moment is calculated. For example, first determine the instantaneous phase angle of the skin conductance signal at a certain moment, then determine the instantaneous phase angle of the respiratory rhythm signal at the same moment, and subtract the two to obtain the phase difference at that moment. By performing such calculations for each moment, a series of values ​​reflecting the phase difference between the two signals at different moments can be obtained.

[0091] Step 3041: Based on the signal characteristics and analysis requirements, set a suitable time window length, such as 10 seconds or 20 seconds. Within each set time window, perform statistical analysis on the phase difference data within that time period. Convert the phase difference at each moment into a complex number form. The complex number form can more comprehensively retain the phase difference information. The conversion process is based on the complex number expression principle of trigonometric functions, transforming the phase difference angle into a complex number form with real and imaginary parts, making the phase difference information at each moment mathematically more complete and easier to calculate.

[0092] Step 3042: Within a time window, perform a fusion operation on the complex phase differences at all times. During the fusion process, first sum the complex phase differences, then calculate their average value. Finally, take the modulus of the average value (i.e., the absolute value of the complex number) to obtain the phase lock value within the time window. The phase lock value is a value between 0 and 1, reflecting the degree of phase synchronization between the skin conductance signal and the respiratory rhythm signal within this time window. The closer the value is to 1, the better the phase synchronization between the two signals within the time window; the closer the value is to 0, the worse the synchronization.

[0093] Step 3043: As time progresses, multiple time windows and their corresponding phase-lock values ​​will be generated. By summarizing the phase-lock values ​​of these different time windows, the average, median, or other statistical measures of all time window phase-lock values ​​can be calculated to comprehensively reflect the phase synchronization between the skin conductance signal and the respiratory rhythm signal over the entire time period. The summarized results can macroscopically demonstrate the changing trend of the phase relationship between the two signals over a longer period.

[0094] Step 3044 involves pre-setting evaluation criteria based on practical experience. For example, when the average value in the summarized results is ≥0.8, it is determined that the skin conductance signal and respiratory rhythm signal exhibit highly synchronized and coordinated changes, meaning that there is good coordination between the autonomic nervous system and the respiratory system during meditation. If the average value is between 0.5 and 0.8, the two signals are considered to have a certain degree of synchronicity, and the coordinated change characteristics are relatively obvious. When the average value is between 0.2 and 0.5, it indicates poor synchronicity and insignificant coordinated change characteristics. If the average value is <0.2, it indicates that the two signals are almost out of sync, and the coordinated change characteristics are very poor. By comparing the summarized results with the evaluation criteria, the specific coordinated change characteristics between the skin conductance signal and the respiratory rhythm signal are finally determined.

[0095] Suppose that during a meditation monitoring session, data is collected in 15-second time windows. Within the first 15-second window, skin conductance and respiratory rhythm signals are acquired by sensors and converted to the phase domain. The phase difference at each moment is calculated, such as 0.2 radians for the first second, 0.3 radians for the second second, etc., resulting in 15 phase difference data points. These phase differences are converted to complex numbers, summed, averaged, and moduloed to obtain a phase lock value of 0.7 for this time window. Monitoring continues; in the second 15-second window, the phase lock value is calculated to be 0.6, and in the third window, it is 0.8. The phase lock values ​​of these three time windows (0.7, 0.6, 0.8) are summed, and the average value is calculated as follows: According to the preset evaluation criteria, 0.7 is between 0.5 and 0.8, thus determining that during this meditation process, the skin conductance signal and the respiratory rhythm signal have a certain degree of synchronicity and obvious coordinated change characteristics.

[0096] Analyzing the phase synchronicity between skin conductance and respiratory rhythm signals allows us to uncover the intrinsic connections between different physiological signals regulated by the autonomic nervous system. Skin conductance reflects sweat gland activity and sympathetic nerve excitability, while respiratory rhythm is related to the regulation of respiration by the respiratory center and the autonomic nervous system. Determining the synergistic changes between these two signals helps us understand the interaction mechanisms between the body's physiological systems during meditation. These synergistic changes provide a new dimension for evaluating meditation effectiveness. Good synergistic changes between skin conductance and respiratory rhythm often indicate that the meditator is in a relaxed and focused state; conversely, poor synergistic changes may suggest that the meditation process is disturbed or the meditation effect is poor. Compared to single-signal analysis, this multi-signal phase synchronicity analysis can more accurately determine the user's meditation state. Based on the determined synergistic changes, personalized feedback and guidance can be provided to users. If the synergistic changes are poor, users can be guided to adjust their breathing rhythm, relax their mind and body, and improve the coordination of their autonomic nervous system; if the synergistic changes are good, users can be encouraged to maintain their current state, helping them to conduct meditation training more scientifically and improve the meditation effect.

[0097] In a preferred embodiment of the present invention, step 4 above, which calculates the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters, and couples the calculations of neural relaxation, autonomic nervous balance, and environmental disturbance, and converts the calculation results into a meditation effect score using a piecewise linear mapping algorithm, may include:

[0098] Step 400: The baseline relaxation level is dynamically adjusted by the ratio of alpha wave energy proportion to theta wave energy proportion, and the deviation of the current prefrontal EEG coherence status from the baseline status is superimposed to determine the contribution of neural relaxation level to the comprehensive evaluation index; relevant indicators of heart rate variability chaos sensitivity, skin conductance phase synchronization and respiratory rhythm stability are obtained from real-time physiological feature vectors and normalized to obtain the contribution of autonomic nervous balance to the comprehensive evaluation index; real-time noise decibel value, light intensity and ambient temperature are extracted from environmental parameters, and the contribution of environmental interference to the comprehensive evaluation index is determined according to the baseline threshold.

[0099] Step 401: Integrate the contribution values ​​of neural relaxation, autonomic nervous system balance, and environmental disturbance to the comprehensive evaluation index to obtain the final comprehensive index used to evaluate the effect of meditation.

[0100] Step 402: Analyze the value range of the comprehensive index and divide the comprehensive index into several intervals, each interval corresponding to a different level of meditation effect;

[0101] Step 403: For each interval, determine the minimum and maximum values ​​of the comprehensive index within the corresponding interval, and determine the minimum and maximum values ​​of the corresponding meditation effect score. According to the proportional allocation, map each value of the comprehensive index within the interval to the corresponding position of the meditation effect score value.

[0102] In this embodiment of the invention, the proportion of α-wave energy α is first accurately located in the real-time physiological feature vector. r and the proportion of theta wave energy θ r Alpha waves appear in a relaxed and awake state of the brain, with a frequency range of 8-13 Hz, while theta waves are associated with drowsiness and deep relaxation, with a frequency range of 4-7 Hz. Calculate the ratio of the two. The higher this ratio, the more the brain is inclined towards a state of alert relaxation, and it can serve as a core reference for baseline relaxation levels. For example, when... This indicates that the brain is in a relatively ideal state of relaxation and wakefulness. Simultaneously, the current prefrontal cortex electroencephalographic coherence status φ is obtained. c Prefrontal cortex electroencephalogram (EEG) coherence reflects the level of information exchange and collaborative work between different brain regions. (The last part, "φ," appears to be a typo and should be removed.) c Compared with the pre-established baseline condition φ b Compare and calculate the deviation magnitude |φ c -φ b |。If|φ c -φ b A smaller value indicates that the current brain function is close to the baseline level and neural activity is stable; conversely, a larger value indicates that brain function is fluctuating.

[0103] Will With |φ c -φ b | After addition, multiply by the weight w N w N The value ranges from 0.3 to 0.5, which was derived through extensive data analysis.

[0104] Specifically, a multimodal dataset containing over 1000 samples was collected, covering individuals of different ages (18-65 years), genders, and meditation experience (beginners to practitioners with over 5 years of experience). Under a standard meditation experimental environment, physiological data such as EEG signals, heart rate variability, and skin conductance, as well as environmental parameters such as ambient noise and light intensity, were collected simultaneously. Based on this dataset, an exhaustive method was used to analyze w... NDiscretization was performed, with values ​​ranging from 0 to 1 in steps of 0.01, constructing 101 evaluation models with different weight combinations. Each model calculated the meditation effect score for all samples, generating a dataset containing 101 sets of scores. An evaluation system was established with the subjective meditation score (1-10 points) as the gold standard, using root mean square error (RMSE) and mean absolute error (MAE) as quantification metrics. Cross-validation was performed on the 101 models, dividing the dataset into 10 subsets. Nine subsets were used to train the model each time, and the remaining subset was used for testing, repeated 10 times to ensure robustness. Calculations showed that when w... N When w < 0.3, the RMSE between the model-predicted score and the subjective score is > 1.2, and the MAE is > 0.9, indicating that the weight of neural relaxation is too low, causing the assessment results to deviate from reality; when w N When the standard deviation is greater than 0.5, the model's evaluation results fluctuate drastically across different sample sets, with a standard deviation exceeding 0.8, indicating that excessively high weights cause the evaluation system to lose balance in considering other physiological indicators. Meanwhile, w N Within the range of 0.3-0.5, the RMSE stabilizes at 0.7-0.9, and the MAE remains at 0.5-0.7, indicating the best generalization performance of the model.

[0105] To further determine the final value, a genetic algorithm was used to perform a refined search in the 0.3-0.5 range. The population size was set to 50, the number of iterations to 100, and the RMSE after cross-validation was used as the fitness function. After multiple rounds of evolution, the algorithm converged to w. N =0.4, at which point the model achieves its lowest RMSE (0.68) and MAE (0.49) on the independent test set, maintaining stable performance across subsets of different feature distributions. Finally, w was determined to be... N The value was set to 0.4. This yields the contribution of the degree of nervous relaxation to the comprehensive evaluation index.

[0106] Extracting heart rate variability chaos sensitivity S from real-time physiological feature vectors hrv Skin conductance phase synchronization S sc and respiratory rhythm stability S rrs Relevant indicators. To eliminate the influence of dimensions and facilitate comparison and calculation, each indicator was normalized. The heart rate variability chaos sensitivity S was used as an example. hrv For example, the normalization formula is: in and These are the minimum and maximum values ​​obtained based on statistical analysis of a large amount of population data. For example, in a certain database, If the current S hrv =30, then the normalized value is Similarly, for skin conductance phase synchronicity S scand respiratory rhythm stability S rrs Normalize the result. Then multiply by their respective weights ω1, ω2, and ω3.

[0107] First, to determine a reasonable range of weight values, an evaluation model set containing multiple sets of different weight combinations was constructed. From a large amount of real-world sample data, the heart rate variability chaos sensitivity S of different individuals under various states (such as resting, exercise, meditation, etc.) was collected. hrv Skin conductance phase synchronization S sc and respiratory rhythm stability S rrs Data. For example, in a dataset containing 1000 samples, the numerical changes of these three indicators for each sample during meditation were recorded in detail. Using this sample data, evaluation models with different weight combinations were trained and tested. During testing, evaluation metrics such as mean squared error (MSE) and mean absolute error (MAE) were used to measure how closely the model's predicted autonomic balance approximated reality. For heart rate variability chaos sensitivity S... hrv By continuously adjusting the value of ω1, the evaluation effect of the model was observed. When ω1 < 0.2, the model's sensitivity to the heart rate variability chaos sensitivity index was insufficient when predicting autonomic nervous system balance, leading to a large deviation between the evaluation results and the actual situation, with high mean squared error and mean absolute error. When ω1 > 0.3, the model overemphasized the influence of heart rate variability chaos sensitivity, weakening the role of other indicators, which also led to increased error in the evaluation results. After extensive experiments and analysis, it was determined that when the value of ω1 is in the range of 0.2-0.3, the model can more accurately evaluate autonomic nervous system balance.

[0108] For skin conductance phase synchronization S sc The weight ω2 was analyzed similarly. Since skin conductance phase synchronicity is closely related to the activity of the autonomic nervous system and has high sensitivity in reflecting autonomic balance, testing models with different ω2 values ​​revealed that when ω2 < 0.3, the model cannot fully reflect the significant impact of skin conductance phase synchronicity on autonomic balance; when ω2 > 0.4, the weight of skin conductance phase synchronicity is too high, masking the role of other indicators and leading to inaccurate evaluation results. Therefore, the model achieves the best evaluation effect when the ω2 value is between 0.3 and 0.4.

[0109] Similarly, for respiratory rhythm stability S rrsThe weight ω3 was determined through a series of experiments and analyses. It was found that when ω3 < 0.2, the contribution of respiratory rhythm stability to autonomic balance was not fully reflected in the model; when ω3 > 0.3, the weight of respiratory rhythm stability was too large, affecting the overall balance of the model. Finally, it was determined that the range of ω3 was 0.2-0.3, which allowed the model to reasonably assess the impact of respiratory rhythm stability on autonomic balance. After determining the range, to balance the influence of each indicator on autonomic balance, ω1 = 0.25, ω2 = 0.35, and ω3 = 0.25 were chosen. The results were then summed to obtain... Finally, multiply by the weight w A .

[0110] Data on heart rate variability chaos sensitivity, skin conductance phase synchronicity, and respiratory rhythm stability were collected from different populations under various conditions, covering individuals of different ages, genders, health statuses, and meditation experiences. In the experiment, different values ​​of w (w0.1 to 0.9) were tested for calculating autonomic balance. A The value is determined and combined with other evaluation indicators to calculate the comprehensive evaluation index. When w A When the value is <0.3, it was found that the weight of autonomic balance in the comprehensive assessment was too low. This resulted in the comprehensive assessment indicators failing to fully reflect the autonomic state as indicated by indicators such as heart rate variability, skin conductance, and respiratory rhythm, leading to a significant deviation between the assessment results and the actual autonomic balance state. For example, in some samples, even if these physiological indicators showed that the autonomic nervous system was in a good balance state, the comprehensive assessment results failed to accurately reflect this situation due to the low weight. Furthermore, when w... A When the value is greater than 0.4, the weight of autonomic nervous system balance is too high, which overemphasizes the influence of this indicator. This makes the comprehensive evaluation indicators too heavily influenced by autonomic nervous system balance, relatively weakening the role of other important factors such as nervous relaxation and environmental interference, resulting in an incomplete and inaccurate evaluation result. After repeated analysis and comparison of a large amount of experimental data, it was found that when w A When the value is between 0.3 and 0.4, the comprehensive evaluation index can most accurately reflect the actual state of autonomic nervous system balance. Combined with other evaluation factors, it makes the entire evaluation system more scientific and reasonable. Within this range, 0.35 is taken as w. A The value of is used to obtain the contribution value of autonomic nervous system balance to the comprehensive evaluation index.

[0111] Real-time noise levels (decibels), light intensity, and ambient temperature are extracted from environmental parameters and denoted as p1, p2, p3, etc. (i = 1, 2, ..., n, where n is the number of environmental parameters). Each environmental parameter has a corresponding baseline threshold. Such as noise reference threshold Decibels, light intensity reference threshold Lux, ambient temperature reference threshold And the standard deviation σ obtained through statistics of a large amount of environmental data. i Calculate the degree of deviation of each environmental parameter from the baseline threshold. For example, if the noise level p1 = 50 dB and its standard deviation σ1 = 5, then the degree of deviation is... Take the square root of the sum of the squares of all deviations, that is... Multiply by the weight w E Collect relevant data under various environmental conditions, including different noise levels, light intensity, temperature variations, and other environmental factors, as well as corresponding evaluation index data. During the analysis, try different methods... E We will use different values ​​to observe its impact on the comprehensive evaluation index. When w E When the value is <0.1, it was found that the proportion of environmental disturbance in the comprehensive evaluation is too small, resulting in the comprehensive evaluation index being insufficiently sensitive to changes in environmental factors. Even if environmental conditions change significantly, the impact on the comprehensive evaluation results is not significant, failing to accurately reflect the role of environmental disturbance in the overall evaluation. For example, in some scenarios with significant environmental changes, the actual situation is that environmental disturbance has a significant impact on the system, but due to w E The value was too small, and the overall evaluation indicators did not reflect this change.

[0112] And when w E When the value is greater than 0.2, the weight of environmental disturbance is too high, causing the comprehensive evaluation index to rely too heavily on environmental factors and relatively neglect the contributions of other important factors, such as autonomic nervous system balance and nervous relaxation. This leads to excessive fluctuations in the comprehensive evaluation results when environmental factors change, failing to objectively and comprehensively reflect the overall situation. Through repeated experiments and analysis of data under a large number of different environmental conditions, it was found that when w E A value between 0.1 and 0.2 can effectively balance the effects of environmental disturbance and other factors in the comprehensive evaluation. Within this range, 0.15 is chosen as w. E The value of is used to obtain the contribution of environmental disturbance degree to the comprehensive evaluation index.

[0113] Step 401: Add the contribution values ​​of the calculated neural relaxation level, autonomic nervous system balance level, and environmental disturbance level to the comprehensive evaluation index, i.e. The final comprehensive index C used to evaluate the effectiveness of meditation is obtained. This index integrates multiple dimensions of physiological and environmental factors to fully reflect the current state of meditation.

[0114] Step 402: Analyze the value range of the comprehensive index C. Based on statistical analysis of a large amount of user meditation data and practical experience, it is divided into four intervals:

[0115] When C < 0.3, the corresponding meditation effect level is "poor", indicating that the current meditation state is not good and is greatly affected by physiological or environmental factors.

[0116] When 0.3≤C<0.6, the corresponding meditation effect level is "average", indicating that meditation has a certain effect, but there is still room for improvement.

[0117] When 0.6≤C<0.8, the corresponding meditation effect level is "good", indicating that the meditation state is relatively ideal and the physiological and environmental factors work together well.

[0118] When C≥0.8, the corresponding meditation effect level is "excellent", which means that a deep meditation state has been achieved and the mind and body are in a highly coordinated state.

[0119] Step 403: For each interval, determine the minimum and maximum values ​​of the comprehensive index within the interval, as well as the corresponding minimum and maximum values ​​of the meditation effect score.

[0120] In the interval 0.3≤C<0.6, the minimum value C1=0.3, the maximum value C2=0.6, the corresponding minimum meditation effect score=60, and the maximum meditation effect score=80.

[0121] According to the principle of proportional allocation, for each comprehensive index value C within the interval X Through formula

[0122] This assessment comprehensively considers factors such as neural relaxation, autonomic nervous system balance, and environmental disturbance, encompassing multiple aspects including brain activity, autonomic nervous system regulation, and external environmental factors. Compared to assessments based on single or a few indicators, it comprehensively reflects the body's physiological state and the influence of the external environment during meditation, avoiding biased assessments and making the evaluation of meditation effects more accurate and complete. Individual differences are fully considered when determining neural relaxation and autonomic nervous system balance. By comparing with personalized benchmark characteristics (such as the deviation of prefrontal cortex EEG coherence from the benchmark), and by normalizing physiological indicators for different individuals, it adapts to the physiological characteristics of different users, providing each user with an assessment result tailored to their individual circumstances, thus improving the relevance and effectiveness of the assessment. Scientific calculation methods and mathematical models are employed, with weights set to reflect the importance of different factors to the meditation effect. Based on extensive statistical analysis, parameters such as benchmark thresholds and standard deviations are determined, and a piecewise linear mapping algorithm is used to convert comprehensive indicators into scoring values, ensuring the entire assessment process is scientifically grounded and guaranteeing the reliability and credibility of the assessment results. After comprehensively calculating complex physiological and environmental factors, the results are converted into specific meditation effectiveness scores, which are then presented to users in an intuitive way. Users can quickly understand their meditation effects through these scores, facilitating self-assessment and comparison. The scores also provide a clear reference for meditation guidance and training, helping users adjust their meditation strategies and improve their effectiveness.

[0123] In a preferred embodiment of the present invention, step 5 above compares the environmental interference level with a preset benchmark threshold. When the environmental interference level is ≥ the benchmark threshold, a segmented attenuation mechanism is activated. The segmented attenuation mechanism includes:

[0124] Mild attenuation mode: If the baseline threshold ≤ environmental interference < 1.2 times the baseline threshold, a linear attenuation function is used to reduce the meditation effect score by a certain proportion, and the reduction proportion ≥ the preset lower limit proportion;

[0125] Moderate decay mode: If 1.2 times the baseline threshold ≤ environmental disturbance < 1.5 times the baseline threshold, the exponential decay function is enabled to adjust the meditation effect score.

[0126] Severe attenuation mode: If the environmental interference level is ≥1.5 times the baseline threshold, cliff-like attenuation will be activated.

[0127] In this embodiment of the invention, after calculating the comprehensive evaluation index, the calculation result of the environmental interference degree is separated from the comprehensive evaluation index. The environmental interference degree is a value obtained by calculating the deviation of environmental parameters such as real-time noise decibels, light intensity, and ambient temperature from their respective benchmark thresholds, and combining them with corresponding weights. The calculation method is as follows: The preset baseline threshold is a key parameter automatically generated through correlation analysis of environmental disturbance data and corresponding meditation effect scores. Specifically, over 100,000 sets of environmental parameters (including noise levels, light intensity, ambient temperature, etc.) and their corresponding comprehensive meditation effect scores from different users were collected. First, the environmental disturbance data was sorted in ascending order and divided into 100 equally spaced intervals. The average meditation effect score for users within each interval was calculated. Analysis revealed that when the environmental disturbance level was between 0 and 0.5, over 85% of users maintained a meditation effect score of 70 or above (out of 100), with a standard deviation of less than 5. However, when the environmental disturbance level exceeded 0.5, the average score began to show a significant downward trend, and the standard deviation of the score increased to over 15.

[0128] Based on the above data characteristics, a critical point of 0.5 was automatically identified. Below this value, changes in environmental disturbance have less than 3% impact on meditation effectiveness scores, and the score distribution shows a highly concentrated trend. Above this value, for every 0.1 increase in environmental disturbance, the meditation effectiveness score decreases by an average of 8-10 points. Therefore, 0.5 was determined as the baseline threshold, serving as a quantitative standard for distinguishing whether the environment significantly affects meditation effectiveness.

[0129] Mild Attenuation Mode: When the environmental disturbance level meets the condition of ≤ environmental disturbance level < 1.2 times the baseline threshold, mild attenuation mode is entered. Assuming the baseline threshold is 0.5, the environmental disturbance level is between 0.5 and 0.6. A linear attenuation function is used to reduce the meditation effect score. The linear attenuation function can be expressed as S... n =S o ×(1-k), where S n It is the diminished meditation effect score, S o S is the score before attenuation, and k is the attenuation ratio. The attenuation ratio k must be determined to be greater than or equal to a preset lower limit ratio. This lower limit ratio is also set based on extensive experimental data and experience, aiming to avoid excessive attenuation affecting the rationality of the assessment. For example, if the preset lower limit ratio is 0.1, and the current meditation effect score is 80, and k = 0.15 is calculated based on the relationship between the specific environmental interference and the baseline threshold, then the attenuated score S... n =80×(1-0.15)=68.

[0130] Moderate decay mode: When the environmental disturbance level is between 1.2 times the baseline threshold and 1.5 times the baseline threshold, the moderate decay mode is activated. For example, the environmental disturbance level is between 0.6 and 0.75. An exponential decay function is used to adjust the meditation effect score. The exponential decay function can be expressed as S... n =S o ×a b×(干扰度-1.2×基准阈值)Here, 'a' and 'b' are parameters determined based on experimental data. First, from over 100,000 sets of real meditation data collected previously, more than 2,000 sets of valid data with environmental interference levels between 1.2 and 1.5 times the baseline threshold were selected. These data all contain accurately recorded environmental parameters (noise decibels, light intensity, temperature, etc.) and corresponding meditation effect scores. Interference data caused by equipment malfunctions, sudden user actions, etc., have been removed using an outlier detection algorithm. A grid search strategy was used to exhaustively test parameters 'a' and 'b'. The value range of 'a' was set to 0.1-0.9 with a step size of 0.1; the value range of 'b' was set to 1-5 with a step size of 1, resulting in a total of 45 parameter combinations. For each set (a, b), the system substitutes the environmental interference levels from the selected 2,000+ sets of data into an exponential decay function to calculate the predicted meditation effect score.

[0131] The predicted scores were compared with the actual scores one by one, using the Mean Absolute Error (MAE) as the evaluation metric. The MAE is calculated by taking the absolute value of the difference between the predicted and actual scores for each sample, and then averaging the differences across all samples. The closer this value is to 0, the lower the deviation between the predicted and actual scores, indicating a more accurate characterization of the relationship between environmental interference and the meditation effect. After testing 45 parameter combinations, the minimum MAE value of 3.1 was found to be achieved when a = 0.8 and b = 2. Specifically, under this parameter set, the error between the predicted and actual scores for 87% of the samples was controlled within ±5 points, and the error distribution for the remaining 13% of samples showed randomness with no significant bias. For example, when the environmental interference level was 1.3 times the baseline threshold and the original score was 70, substituting these values ​​into the formula yielded a predicted score of 70 × 0.8. 2 ×(1.3-1.2) =70 × 0.8 0.2 The result is approximately 63.7, which is highly consistent with the score fluctuation trend under the same level of interference in the actual data. Therefore, a = 0.8 and b = 2 were finally selected as the final parameter combination of the exponential decay function to ensure that the negative impact of environmental interference on the meditation effect can be accurately quantified within this range.

[0132] Severe Attenuation Mode: When the environmental interference level is ≥1.5 times the baseline threshold, i.e., environmental interference level ≥0.75, a precipitous attenuation is activated. Precipitous attenuation means a significant and rapid reduction in the meditation effect score to highlight the destructive impact of severe environmental interference on meditation effectiveness. The meditation effect score is set to a low, fixed value, such as a direct score of 30; or it is calculated using a very large attenuation ratio, for example, setting the attenuation ratio to 0.7. If the original score is 80, the attenuated score will be 80 × (1 - 0.7) = 24. This method allows users to intuitively recognize that the current environment has severely interfered with their meditation effect, thereby prompting them to improve their meditation environment.

[0133] like Figure 2 As shown, embodiments of the present invention also provide an intelligent scoring system for meditation effects based on big data analysis, comprising:

[0134] The data acquisition module is used to collect the user's brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals in real time through wearable devices, as well as to obtain environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors, and generate a multidimensional raw dataset that integrates physiological signals and environmental parameters.

[0135] The benchmark generation module is used to generate personalized benchmark features based on the resting state physiological parameters in the multidimensional raw dataset, using a Gaussian mixture probability distribution. These features include the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters.

[0136] The feature extraction module is used to perform frequency domain decomposition on the EEG signal, extract the energy ratio of theta wave and alpha wave respectively, calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform, and form a real-time physiological feature vector.

[0137] The scoring calculation module is used to calculate the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. It couples the calculation of the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance, and converts the calculation results into a meditation effect score value through a piecewise linear mapping algorithm.

[0138] The attenuation processing module compares the environmental interference level with a preset benchmark threshold. When the environmental interference level is greater than or equal to the benchmark threshold, the segmented attenuation mechanism is activated.

[0139] It should be noted that this system is a system corresponding to the above method. All implementation methods in the above method embodiments are applicable to this embodiment and can achieve the same technical effect.

[0140] Embodiments of the present invention also provide a computing device, including: a processor and a memory storing a computer program, wherein the computer program, when executed by the processor, performs the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0141] Embodiments of the present invention also provide a computer-readable storage medium storing instructions that, when executed on a computer, cause the computer to perform the method described above. All implementations in the above method embodiments are applicable to this embodiment and can achieve the same technical effects.

[0142] Those skilled in the art will recognize that the units and algorithm steps of the various examples described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are implemented in hardware or software depends on the specific application and design constraints of the technical solution. Those skilled in the art can use different methods to implement the described functions for each specific application, but such implementations should not be considered beyond the scope of this invention.

[0143] Those skilled in the art will understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0144] In the embodiments provided by this invention, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative. For instance, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0145] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0146] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0147] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this invention, essentially, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, ROM, RAM, magnetic disks, or optical disks.

[0148] Furthermore, it should be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent solutions of the present invention. Moreover, the steps performing the above-described series of processes can naturally be executed in the order described, but are not necessarily required to be executed in chronological order; some steps can be executed in parallel or independently of each other. Those skilled in the art will understand that all or any step or component of the method and apparatus of the present invention can be implemented in any computing device (including processors, storage media, etc.) or network of computing devices, in hardware, firmware, software, or a combination thereof. This can be achieved by those skilled in the art using basic programming skills after reading the description of the present invention.

[0149] Therefore, the object of the present invention can also be achieved by running a program or a set of programs on any computing device. The computing device can be a known general-purpose device. Therefore, the object of the present invention can also be achieved simply by providing a program product containing program code implementing the method or apparatus. That is, such a program product also constitutes the present invention, and the storage medium storing such a program product also constitutes the present invention. Obviously, the storage medium can be any known storage medium or any storage medium developed in the future. It should also be noted that in the apparatus and method of the present invention, it is obvious that the components or steps can be decomposed and / or recombined. These decompositions and / or recombinations should be considered equivalent to the present invention. Furthermore, the steps performing the above series of processes can naturally be performed in the order described, but are not necessarily required to be performed in chronological order. Some steps can be performed in parallel or independently of each other.

[0150] The above description represents the preferred embodiments of the present invention. It should be noted that those skilled in the art can make various improvements and modifications without departing from the principles of the present invention, and these improvements and modifications should also be considered within the scope of protection of the present invention.

Claims

1. A method for intelligently scoring the effectiveness of meditation based on big data analysis, characterized in that, The method includes: Step 1: Real-time acquisition of brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals during user meditation using wearable devices, and acquisition of environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors to generate a multidimensional raw dataset that integrates physiological signals and environmental parameters. Step 2: Based on the resting state physiological parameters in the multidimensional original dataset, a Gaussian mixture probability distribution is used to generate personalized baseline features, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters. Step 3: Decompose the EEG signal in the frequency domain, extract the energy proportions of theta waves and alpha waves respectively, and calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform to form a real-time physiological feature vector. The phase synchronization parameter of the original skin conductance waveform is the phase synchronization between the original skin conductance waveform and the respiratory rhythm signal. Step 4: Calculate the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. Couple the calculation of the degree of neural relaxation, the degree of autonomic nervous balance, and the degree of environmental disturbance, and convert the calculation results into a meditation effect score through a piecewise linear mapping algorithm. Step 5: Compare the environmental interference level with a preset baseline threshold. When the environmental interference level is greater than or equal to the baseline threshold, activate the segmented attenuation mechanism. The segmented attenuation mechanism includes: Mild attenuation mode: If the baseline threshold is less than or equal to the environmental interference level but less than 1.2 times the baseline threshold, a linear attenuation function is used to reduce the meditation effect score by a certain proportion, and the reduction proportion is greater than or equal to the preset lower limit proportion; Moderate attenuation mode: If the environmental interference level is less than or equal to 1.2 times the baseline threshold but less than 1.5 times the baseline threshold, an exponential attenuation function is used to adjust the meditation effect score; Severe attenuation mode: If the environmental interference level is greater than or equal to 1.5 times the baseline threshold, a cliff-like attenuation is initiated.

2. The intelligent scoring method for meditation effects based on big data analysis according to claim 1, characterized in that, Based on the resting-state physiological parameters in the multidimensional raw dataset, a Gaussian mixture probability distribution is used to generate personalized baseline features, including the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters, including: The time intervals in which users are in a resting state are determined from the multidimensional raw dataset, and physiological parameter data, including electroencephalogram signals, heart rate variability, skin conductance and respiratory rhythm parameters, are extracted from the time intervals in the resting state. For each physiological parameter, a Gaussian mixture model is constructed to model the mean vector and covariance matrix of each physiological parameter. The mean vector and covariance matrix of each physiological parameter are combined to form personalized benchmark features.

3. The intelligent scoring method for meditation effects based on big data analysis according to claim 2, characterized in that, Frequency domain decomposition of the EEG signal was performed to extract the energy proportions of theta and alpha waves, and the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameters of the original skin conductance waveform were calculated to form a real-time physiological feature vector, including: The brainwave signal is converted from the time domain to the frequency domain, and in the frequency domain, the corresponding frequency bands are divided according to the frequency range of theta waves and alpha waves. The energy within each frequency band is calculated, and the frequency band energy ratios of theta waves and alpha waves are obtained through normalization to establish a baseline of EEG characteristics in the user's meditative state. After establishing the baseline of EEG characteristics in the user's meditation state, the current heart rate variability signal is obtained, and the dynamic time warping algorithm is used to compare the current heart rate variability signal with the personalized baseline characteristics to obtain the comparison results. Based on the comparison results, a chaos sensitivity index for the heart rate variability signal is calculated to reflect the degree of deviation between the current heart rate fluctuation and the personalized baseline. After obtaining the correlation features of EEG and heart rate variability, the raw waveform of skin conductance and respiratory rhythm signal were acquired. The phase-locked value algorithm was used to analyze the phase synchronization between the raw waveform of skin conductance and respiratory rhythm signal, and to determine the coordinated change characteristics of skin conductance signal and respiratory rhythm. The frequency band energy ratios of theta and alpha waves, the chaos sensitivity index of heart rate variability signals, and the original waveforms of skin conductance and respiratory rhythm signals are combined to form a real-time physiological feature vector that includes energy ratio, chaos sensitivity, and phase synchronization.

4. The intelligent scoring method for meditation effects based on big data analysis according to claim 3, characterized in that, After establishing a baseline of EEG characteristics for the user in a meditative state, the current heart rate variability signal is acquired. Using a dynamic time warping algorithm, the current heart rate variability signal is compared with personalized baseline characteristics to obtain the comparison results, including: After establishing the baseline of brainwave characteristics, wearable heart rate monitoring devices are used to acquire the user's current heart rate data in real time during meditation. The current heart rate data is processed to calculate the heart rate variability index and obtain the current heart rate variability signal. The current heart rate variability signal is compared with the heart rate variability baseline data in the personalized baseline features using a dynamic time warping algorithm. During the comparison process, the distance between each matching point is calculated. Based on the distance between each matching point, the final matching path between the two signals is determined, and the distances between each matching point are summed to obtain the total comparison distance, i.e., the comparison result.

5. The intelligent scoring method for meditation effects based on big data analysis according to claim 4, characterized in that, After obtaining the correlation features of EEG and heart rate variability, the raw waveforms of skin conductance and respiratory rhythm signals were acquired. A phase-locked value algorithm was used to analyze the phase synchronization between the raw waveforms of skin conductance and respiratory rhythm signals, determining the coordinated change characteristics of skin conductance signals and respiratory rhythm, including: The skin conductance signal and respiratory rhythm signal are transformed from the time domain to the phase domain to obtain the skin conductance signal and respiratory rhythm signal, and the phase difference between the skin conductance signal and respiratory rhythm signal at the same time is calculated. Based on the phase difference at each moment, a time window is set, and within each time window, the phase difference within the corresponding time period is statistically analyzed, and the phase difference at each moment is converted into a complex number representation. The phase difference in complex form at each moment within the time window is fused to obtain the phase lock value within the corresponding time window; The phase lock values ​​for each time window are summed to obtain the summary result; Based on the summarized results and in conjunction with the preset evaluation criteria, the characteristics of the coordinated changes between skin conductance signals and respiratory rhythm signals were determined.

6. The intelligent scoring method for meditation effects based on big data analysis according to claim 5, characterized in that, Based on real-time physiological feature vectors and environmental parameters, the degree of neural relaxation, autonomic nervous system balance, and environmental disturbance are calculated separately. These three parameters are then coupled in the calculation, and the results are converted into a meditation effect score using a piecewise linear mapping algorithm. The baseline relaxation level is dynamically adjusted by using the ratio of alpha wave energy proportion to theta wave energy proportion, and the deviation of the current prefrontal EEG coherence status from the baseline status is superimposed to determine the contribution of neural relaxation level to the comprehensive assessment index. Heart rate variability chaos sensitivity, skin conductance phase synchronization, and respiratory rhythm stability are obtained from real-time physiological feature vectors and normalized to obtain the contribution of autonomic nervous balance to the comprehensive assessment index. Real-time noise decibel value, light intensity, and ambient temperature are extracted from environmental parameters, and the contribution of environmental interference to the comprehensive assessment index is determined according to the baseline threshold. The contribution values ​​of neural relaxation, autonomic nervous system balance, and environmental disturbance to the comprehensive evaluation index are integrated to obtain the final comprehensive index used to evaluate the effect of meditation. The range of values ​​for the comprehensive index is analyzed, and the comprehensive index is divided into several intervals, each interval corresponding to a different level of meditation effect; For each interval, determine the minimum and maximum values ​​of the comprehensive index within the corresponding interval, and determine the minimum and maximum values ​​of the corresponding meditation effect score. According to the proportional allocation, map each value of the comprehensive index within the interval to the corresponding position of the meditation effect score value.

7. A smart scoring system for meditation effects based on big data analysis, wherein the system implements the method as described in any one of claims 1 to 6, characterized in that, include: The data acquisition module is used to collect the user's brainwave signals, heart rate variability, raw waveforms of skin conductance and respiratory rhythm signals in real time through wearable devices, as well as to obtain environmental noise decibel values, light intensity and environmental temperature parameters through environmental sensors, and generate a multidimensional raw dataset that integrates physiological signals and environmental parameters. The benchmark generation module is used to generate personalized benchmark features based on the resting state physiological parameters in the multidimensional raw dataset, using a Gaussian mixture probability distribution. These features include the mean vector and covariance matrix of EEG signals, heart rate variability, skin conductance, and respiratory rhythm parameters. The feature extraction module is used to perform frequency domain decomposition on the EEG signal, extract the energy ratio of theta wave and alpha wave respectively, calculate the chaos sensitivity index of the heart rate variability signal and the phase synchronization parameter of the original skin conductance waveform, and form a real-time physiological feature vector. The scoring calculation module is used to calculate the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance based on real-time physiological feature vectors and environmental parameters. It couples the calculation of the degree of nerve relaxation, the degree of autonomic nerve balance, and the degree of environmental disturbance, and converts the calculation results into a meditation effect score value through a piecewise linear mapping algorithm. The attenuation processing module compares the environmental interference level with a preset benchmark threshold. When the environmental interference level is greater than or equal to the benchmark threshold, the segmented attenuation mechanism is activated.

8. A computing device, characterized in that, include: One or more processors; A storage device for storing one or more programs that, when executed by one or more processors, cause the one or more processors to implement the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a program that, when executed by a processor, implements the method as described in any one of claims 1 to 6.

Images