Neural feedback intervention system and method based on meditation and meditation

Abstract

The invention discloses a neural feedback intervention system and method based on meditation and meditation, and belongs to the technical field of neural intervention. The problems that existing meditation intervention equipment is mostly based on directional voice guidance or respiratory regulation, personalized and dynamic psychological intervention cannot be performed by fully combining with a neural feedback technology, and an expected standard is difficult to realize are solved, the electroencephalogram signal of an intervention object is monitored in real time, and the meditation intervention accuracy is improved. Mapping the features into a specified interval by using a neural feedback index normalization model to obtain a normalized neural feedback index; converting the audio signal into an audio signal through a time domain signal processing technology; personalized psychological intervention content is provided for an intervention object in combination with a system based on a meditation technology; in the intervention process, the physiological status of the intervention object is monitored in real time, the current intervention scheme can be properly adjusted in time, the effect of meditation training and the experience of the intervention object are effectively improved, and high practicability and market prospects are achieved.

Description

Technical Field

[0001] The present invention relates to the field of neurointervention technology, and in particular to a neurofeedback intervention system and method based on mindfulness meditation. Background Art

[0002] As a psychological adjustment method, mindfulness meditation has been widely used in psychotherapy, stress management and emotion regulation in recent years. However, current mindfulness meditation training is mostly guided or self-practice, lacking real-time monitoring and feedback of individual neural states. Neurofeedback technology can help individuals understand their mental state in real time during meditation by detecting physiological indicators such as brain waves and heart rate variability, and provide corresponding feedback, thereby improving the effect of meditation training.

[0003] In the existing technology, meditation intervention devices are mostly based on directional voice guidance or breathing regulation, and fail to fully combine neurofeedback technology to carry out personalized and dynamic psychological intervention.

[0004] Therefore, the present invention aims to address this technical gap and develop a mindfulness meditation intervention system based on neurofeedback to enhance the effect of meditation training and the experience of the intervention subjects. To this end, we propose a neurofeedback intervention system and method based on mindfulness meditation. Summary of the invention

[0005] The purpose of the present invention is to provide a neurofeedback intervention system and method based on mindfulness meditation, which monitors the EEG signals of the intervention object in real time, maps the features to a specified interval using a neurofeedback index normalization model, and obtains a normalized neurofeedback index; then converts it into an audio signal through time domain signal processing technology; combined with a system based on mindfulness meditation technology, provides personalized psychological intervention content for the intervention object; and during the intervention process, monitors the physiological condition of the intervention object in real time, and can make appropriate adjustments to the current intervention plan in a timely manner to help it optimize the meditation experience and improve the meditation effect, effectively improving the experience of the intervention object, having strong practicality and market prospects, and solving the problems raised in the above-mentioned background technology.

[0006] To achieve the above object, the present invention provides the following technical solutions:

[0007] A neurofeedback intervention system based on mindfulness meditation, including:

[0008] The neural monitoring module is used to monitor the EEG or other physiological signals of the intervention subject in real time through a portable three-lead EEG signal sensor, such as heart rate and skin galvanic response, and transmit the intervention subject data to the data processing module in real time for pre-processing;

[0009] The data processing module is used to pre-process the collected neural signals, including filtering, artifact processing and detrending processing, to reduce the noise and interference of the neural signals, so as to improve the quality of the neural signals;

[0010] Feature extraction module, used to extract features from preprocessed neural signals for analysis; features include: power spectrum density, frequency components;

[0011] The neurofeedback module is used to map the extracted features into a specific interval through a neurofeedback index normalization model to obtain a normalized neurofeedback index; and map the normalized neurofeedback index into auditory neurofeedback based on natural sounds to assist the intervention subject to understand his or her own neural activity status in real time;

[0012] The neuro-guidance module is used to embed a mindfulness meditation guidance program into the system, combine neuro-feedback data, personalize the guidance frequency and content, and provide adaptive training.

[0013] Furthermore, the neural monitoring module includes:

[0014] The factor determination unit is used to screen and confirm the intervention subjects before implementing the neurofeedback intervention based on mindfulness meditation, consider whether the intervention subjects have psychological problems and symptoms, and clarify the intervention goals, such as reducing anxiety and lowering depression levels;

[0015] The terminal selection unit is used to select a suitable neural monitoring terminal according to the intervention target of the intervention object, such as: electroencephalograph, electrocardiograph, respiratory sensor, etc. The above equipment can collect the physiological data of the intervention object in real time when the intervention object is sitting in meditation, and conduct real-time monitoring and recording.

[0016] Furthermore, the data processing module includes:

[0017] The filtering processing unit is used to filter the neural signal using a low-pass filter, apply the coefficient matrix of the low-pass filter to the neural signal for convolution operation, remove the high-frequency signal in the neural signal, and retain the low-frequency signal; the frequency range usually used is: 0.01-1Hz;

[0018] An artifact processing unit, used for performing artifact processing on the collected neural signals by using an independent component analysis method;

[0019] The detrending processing unit is used to subtract the original signal from the neural signal by the detrending method to obtain the detrended neural signal; compare the processed signal with the original signal to check whether the expected detrending effect is achieved, and further adjust it until the detrending requirements are met.

[0020] Furthermore, the neural feedback module includes:

[0021] The model building unit is used to obtain the neural signals of the historical intervention object, and after preprocessing the neural signals, use the minimum-maximum normalization method to linearly transform the historical signals to a specified interval, that is, [0, 1]; then import the normalized historical signals into the neural network model for training and prediction, and obtain the normalized model of neural feedback indicators;

[0022] The auditory mapping module is used to use the normalized index as a new time step, convert it into an audio signal through time domain signal processing technology, and feed it back to the intervention object; for example: align the normalized index with the time axis of the original audio signal, and then pass it through processing circuits such as filters and modulators to generate the sound of auditory nerve feedback.

[0023] Furthermore, the nerve guidance module includes:

[0024] The content setting module is used to set the content and guidance statements of the mindfulness meditation guidance program;

[0025] A signal analysis module is used to analyze and process the neural signals of the intervention subject and identify the ongoing activity state and emotional state of the intervention subject;

[0026] The content setting module is used to provide the intervention subject with appropriate content and guiding statements of the mindfulness meditation guidance program according to the intervention subject's ongoing activity status and emotional state.

[0027] Furthermore, the nerve guidance module further includes:

[0028] The real-time monitoring unit is used to monitor and analyze the subject's physiological data in real time during the neurofeedback process, and provide targeted guidance and feedback based on data changes; for example, when the subject's heart rate is too fast, prompts and suggestions can be given to guide them to relax and slow down their heart rate; when the subject's EEG waveform is abnormal, corrections and guidance can be given to allow them to focus more on the current activity;

[0029] The online adjustment unit is used to appropriately adjust and optimize the content of the mindfulness meditation guidance program of the intervention subject according to the intervention subject's physiological data and response during the neurofeedback process; for example, when the intervention subject under-responds or over-responds to certain instructions, the training plan and intensity can be adjusted.

[0030] Furthermore, the nerve guidance module further includes:

[0031] A first data monitoring module is used to monitor in real time the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject;

[0032] A second data monitoring module is used to monitor in real time the content adjustment duration of the online adjustment unit adjusting the content of the mindfulness meditation guidance program of the intervention subject each time;

[0033] a comparison module, configured to compare the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject with a preset number threshold;

[0034] A first data retrieval module is used to retrieve the number of content adjustments made to the content of the mindfulness meditation guidance program of the intervention subject and its corresponding content adjustment duration each time when the number of content adjustments is lower than a preset number threshold;

[0035] an adjustment execution quality coefficient acquisition module, configured to acquire an adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit by using the content adjustment duration for adjusting the content of the mindfulness meditation guidance program for the intervention subject each time;

[0036] The adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit is obtained by the following formula:

[0037]

[0038] Wherein, J represents the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit; T represents the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit; N represents the number of content adjustments corresponding to each content adjustment performed by the online adjustment unit; T c Indicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; N b It represents the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit; T b T represents the standard deviation of the content adjustment duration corresponding to the current content adjustment performed by the online adjustment unit; max Indicates the maximum allowed content adjustment time under normal operation of the preset online adjustment unit;

[0039] a risk warning module, used to compare the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit with a preset first quality coefficient; when the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit exceeds the preset first quality coefficient, it is determined that the online adjustment unit has an abnormal risk and a risk warning is issued;

[0040] The abnormality determination module is used to determine the operation abnormality by using the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold.

[0041] Furthermore, the abnormality determination module includes:

[0042] A second data retrieval module is used to extract the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold;

[0043] A comprehensive adjustment execution quality coefficient acquisition module, used to acquire the comprehensive adjustment execution quality coefficient by using the number of content adjustments and the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit;

[0044] The comprehensive adjustment execution quality coefficient is obtained by the following formula:

[0045]

[0046] Among them, J z represents the comprehensive adjustment execution quality coefficient; m represents the total number of content adjustments made by the online adjustment unit; N i represents the number of content adjustments corresponding to the i-th content adjustment performed by the online adjustment unit; T i T represents the content adjustment duration corresponding to the i-th content adjustment performed by the online adjustment unit; c Indicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; T bni Indicates that when the online adjustment unit adjusts the content for the i-th time, N i The standard deviation of the content adjustment duration corresponding to the number of content adjustments; N b Indicates the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit;

[0047] A coefficient comparison module, used for comparing the comprehensive adjustment execution quality coefficient with a preset second quality coefficient;

[0048] The abnormality determination and alarm module is used to determine that the operation of the online adjustment unit is abnormal and issue an abnormality alarm when the comprehensive adjustment execution quality coefficient is lower than a preset second quality coefficient.

[0049] Furthermore, the content setting module includes:

[0050] The content revision unit is used to collect the neural signals and intervention plans of different types of intervention subjects, and analyze the status of various types of intervention subjects after the intervention treatment to revise and supplement the content and guidance statements of the original mindfulness meditation guidance program in the system to form new content and guidance statements of the mindfulness meditation guidance program.

[0051] The neurofeedback intervention method based on mindfulness meditation includes the following steps:

[0052] Step 1: Use a portable three-lead EEG sensor to monitor the EEG signals of the intervention subjects in real time, filter, artifact and detrend the neural signals, and reduce the noise and interference of the neural signals;

[0053] Step 2: Extract features from the preprocessed neural signals, and map the features to a specified interval through a neural feedback index normalization model to obtain a normalized neural feedback index; then convert it into an audio signal through time domain signal processing technology, and assist the intervention subject to understand his or her own neural activity status in real time;

[0054] Step 3: Provide the intervention subjects with appropriate mindfulness meditation guidance program content and guidance statements based on their current neural activity state;

[0055] Step 4: During the intervention process, monitor the subject's physiological data and reactions in real time, and appropriately adjust and optimize the content of the subject's mindfulness meditation guidance program based on actual conditions.

[0056] Compared with the prior art, the present invention has the following beneficial effects:

[0057] The present invention monitors the EEG signals of the intervention object in real time, maps the features to a specified interval using a neural feedback index normalization model, and obtains a normalized neural feedback index; then converts it into an audio signal through time domain signal processing technology; combines a system based on mindfulness meditation technology to provide personalized psychological intervention content for the intervention object; and during the intervention process, monitors the physiological condition of the intervention object in real time, and can make appropriate adjustments to the current intervention plan in a timely manner, effectively improving the effect of meditation training and the experience of the intervention object, and has strong practicality and market prospects. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a flow chart of the neurofeedback intervention method based on mindfulness meditation of the present invention;

[0059] Figure 2 This is a diagram showing the composition of the mindfulness meditation-based neurofeedback intervention system of the present invention. DETAILED DESCRIPTION

[0060] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0061] In order to solve the technical problem that most meditation intervention devices are based on directional voice guidance or breathing regulation, and fail to fully combine neurofeedback technology for personalized and dynamic psychological intervention, please refer to Figure 1-Figure 2 , this embodiment provides the following technical solutions:

[0062] A neurofeedback intervention system based on mindfulness meditation, including:

[0063] The neural monitoring module is used to monitor the EEG or other physiological signals of the intervention subject, such as heart rate and skin electrical response, in real time through a portable three-lead EEG signal sensor, and transmit the intervention subject data to the data processing module in real time for preprocessing; specifically, by acquiring the EEG or other physiological signals of the intervention subject, it is convenient to release the very weak electrical signals generated by brain cells, thereby recording the emotional disorders of the intervention subject, and judging whether the intervention subject has anxiety, depression, neurasthenia, etc., so as to analyze and treat the disease, and help the intervention subject regulate his or her own emotions and change his or her physiological state.

[0064] The neuromonitoring module includes: a factor determination unit, which is used to screen and confirm the intervention subjects before implementing the neurofeedback intervention based on mindfulness meditation, consider whether the intervention subjects have psychological problems and symptoms, and clarify the intervention goals; specifically, by screening and confirming the intervention subjects, it is mainly convenient to analyze the purpose of the intervention required by the current intervention subjects, such as: reducing anxiety, reducing depression levels, etc., so as to provide the intervention subjects with appropriate intervention plan content;

[0065] The terminal selection unit is used to select a suitable neural monitoring terminal according to the intervention target of the intervention object, such as: electroencephalograph, electrocardiograph, respiratory sensor, etc. The above equipment can collect the physiological data of the intervention object in real time when the intervention object is sitting in meditation, and conduct real-time monitoring and recording.

[0066] The data processing module is used to pre-process the collected neural signals, including filtering, artifact processing and detrending processing, to reduce the noise and interference of the neural signals, so as to improve the quality of the neural signals; the data processing module includes:

[0067] The filtering processing unit is used to filter the neural signal using a low-pass filter, apply the coefficient matrix of the low-pass filter to the neural signal for convolution operation, remove the high-frequency signal in the neural signal, and retain the low-frequency signal; specifically, the function of the low-pass filter is to remove the high-frequency signal and retain the low-frequency signal, and the frequency range commonly used is: 0.01-1Hz; common low-pass filter types include: Butterworth filter, Chebyshev filter, etc., such as: select Butterworth filter, and set a suitable cutoff frequency according to the characteristics of the neural signal; use Mat l ab and other tools to design the low-pass filter, such as: use Mat l ab's butter function to design the Butterworth low-pass filter, the specific steps include: selecting design parameters, calculating the filter order, designing the filter coefficients, etc.; by writing Mat l ab code, the designed low-pass filter is applied to the neural signal, and the filtered signal is evaluated to check whether the expected filtering effect is achieved, and then the filtering effect is evaluated through the waveform diagrams in the time domain and frequency domain; based on the above steps, the low-pass filter can be effectively used to filter the neural signal, thereby improving the quality and reliability of the neural signal.

[0068] The artifact processing unit is used to perform artifact processing on the collected neural signals using the independent component analysis method; specifically, by importing the neural signals into the independent component analysis application, using the ICA algorithm to perform independent component analysis on the pre-processed data, analyzing the results of ICA, identifying and removing artifact components, such as: checking the time series and spectral characteristics of the independent components, and the correlation with physiological or experimental conditions, thereby completing the artifact processing steps for the neural signals and improving the accuracy and reliability of the neural signal analysis.

[0069] The detrending processing unit is used to subtract the original signal from the neural signal by the detrending method to obtain the detrended neural signal. Since the collected neural signal has external noise, the internal connection function of the neural signal is superimposed with a polynomial trend signal, which makes it impossible to clearly find the internal connection of the neural signal. The detrending method effectively avoids the interference of pseudo-correlation of neural signals due to noise and signal instability by filtering out the trend components of each order in the sequence. Specifically, the average value of the neural signal in adjacent time is calculated, and the time window length usually used is 10 seconds to 1 minute. A window is slid on the time axis, and each window is averaged. The signal in the mouth is averaged. Commonly used filters include simple moving average filter and exponentially weighted moving average filter. The signal is Gaussian smoothed to reduce high-frequency noise. The order of the smoother determines the degree of noise filtering. The signal is median filtered to suppress pulse interference. The appropriate trend type is selected, such as linear, quadratic, etc., and the original signal is subtracted to obtain the detrended signal. The processed signal is compared with the original signal to check whether the expected detrending effect is achieved, and further adjustments are made until the detrending requirements are met. The detrended signal is normalized so that it is distributed in the interval [0, 1] for subsequent analysis.

[0070] The feature extraction module is used to extract features from the preprocessed neural signals for analysis; the features include: power spectral density and frequency components; specifically, after preprocessing the neural signals, representative and relevant features are selected from the original data to reduce redundancy and noise, and screen out features that are useful for subsequent analysis; wavelet transform and fuzzy entropy methods are used to extract representative features from the original neural signals to assist in subsequent classification; the extracted features are then subjected to dimensionality reduction processing to reduce redundancy and noise, and to improve the training speed and accuracy of the normalized model of neural feedback indicators.

[0071] The neurofeedback module is used to map the extracted features into a specific interval through a neurofeedback index normalization model to obtain a normalized neurofeedback index; and map the normalized neurofeedback index into auditory neurofeedback based on natural sounds to assist the intervention subject to understand his or her own neural activity state in real time; the neurofeedback module includes:

[0072] The model building unit is used to obtain the neural signals of the historical intervention object, and after preprocessing the neural signals, the historical signals are linearly transformed to the specified interval, that is, [0, 1] by using the minimum-maximum normalization method; the normalized historical signals are then imported into the neural network model for training and prediction to obtain the normalized model of the neural feedback index; specifically, data is collected from different sound sources, including: human speech, music, noise, etc. These data should cover various characteristics such as frequency, intensity and timbre; the historical data are preprocessed, including: noise reduction, detrending, fractal analysis, filtering and other operations to eliminate the influence of noise and outliers, and extract useful features; select a suitable neural feedback index normalization model, such as: using a convolutional neural network model to normalize the extracted features and map them to a specific interval, such as [-1, 1] or [0, 1]; the normalized index is added, multiplied, and fused with the sound signal to obtain auditory neural feedback, that is, presented to the intervention object in the form of an audio signal.

[0073] Secondly, after the convolutional neural network model is trained, its performance needs to be evaluated to determine its accuracy and robustness. The performance of the convolutional neural network model is evaluated by comparing the performance of different data sets on the convolutional neural network model; if the performance of the convolutional neural network model is not accurate, the structure, hyperparameters, training algorithm and other aspects of the convolutional neural network model need to be adjusted to improve the accuracy and robustness of the convolutional neural network model.

[0074] The auditory mapping module is used to use the normalized index as a new time step, convert it into an audio signal through time domain signal processing technology, and feed it back to the intervention subject; specifically, by aligning the normalized index of the neural signal with the time axis of the original audio signal, and then passing it through processing circuits such as filters and modulators, the sound of auditory nerve feedback is generated, so that the intervention subject can know his or her own neural condition.

[0075] The neuro-guidance module is used to embed a mindfulness meditation guidance program in the system, combine neuro-feedback data, personalize the guidance frequency and content, and provide adaptive training; the neuro-guidance module includes:

[0076] The content setting module is used to set the content and guiding statements of the mindfulness meditation guidance program; specifically, the content of the mindfulness meditation guidance program may include: a quiet family area, under a large tree outdoors, or decorations that can boost the spirit or calm the mind, such as flowers or landscape paintings; guiding statements may include: light and relaxed body, head and body straight, relaxed and at ease, eyes lightly closed, consciousness starting from the head and gradually extending downward to all parts of the body; focus on breathing, pay attention to the feeling of cold air rising into the nasal cavity when inhaling, and the feeling of warm air leaving the nasal cavity when exhaling, pay attention to the rising of the stomach when inhaling and the falling of the stomach when exhaling, and maintain a natural breathing rhythm; based on this, when the system is started, the intervention subject is required to enter his or her basic information, such as age, gender, occupation, and physical activity level, so as to determine the appropriate meditation guidance content and intervention frequency of guiding statements through the above information.

[0077] The content setting module includes: a content revision unit, which is used to collect neural signals and intervention plans of different types of intervention objects, and analyze the status of various intervention objects after the intervention treatment to revise and supplement the content and guidance statements of the original mindfulness meditation guidance program in the system, so as to form new content and guidance statements of the mindfulness meditation guidance program; specifically, the content revision unit is: by constantly combining the intervention plans and effects of different intervention objects, the content and guidance statements of the original mindfulness meditation guidance program are revised and supplemented, so that the content and guidance statements of the mindfulness meditation guidance program are more complete and effective, thereby assisting the intervention objects to experience the physical and mental relaxation and tranquility brought by meditation.

[0078] The signal analysis module is used to analyze and process the neural signals of the intervention subject, and identify the ongoing activity and emotional state of the intervention subject; specifically, for example, by analyzing the EEG waveform of the intervention subject, it is determined whether the intervention subject is currently in a state of concentration; and then combined with the analysis of the heart rate of the intervention subject, the current mental and emotional state of the intervention subject is further determined.

[0079] The content setting module is used to provide the intervention subject with appropriate content and guiding statements of the mindfulness meditation guidance program according to the intervention subject's ongoing activity status and emotional state; specifically, for example, through analysis, it is known that the intervention subject is currently anxious, guilty and nervous, and a quiet home area can be selected for the intervention subject based on the symptoms, so as to reduce the anxiety and uneasiness of the intervention subject.

[0080] The real-time monitoring unit is used to monitor and analyze the subject's physiological data in real time during the neurofeedback process, and provide targeted guidance and feedback based on data changes. Specifically, for example, when the subject's heart rate is too fast, prompts and suggestions can be given to guide them to relax and slow down their heart rate. Another example is that when the subject's EEG waveform is abnormal, corrections and guidance can be given to allow them to focus more on the current activity.

[0081] The online adjustment unit is used to appropriately adjust and optimize the content of the mindfulness meditation guidance program of the intervention subject according to the intervention subject's physiological data and response during the neurofeedback process; for example, when the intervention subject under-responds or over-responds to certain instructions, the training plan and intensity can be adjusted.

[0082] Specifically, the nerve guidance module further includes:

[0083] A first data monitoring module is used to monitor in real time the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject;

[0084] A second data monitoring module is used to monitor in real time the content adjustment duration of the online adjustment unit adjusting the content of the mindfulness meditation guidance program of the intervention subject each time;

[0085] a comparison module, configured to compare the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject with a preset number threshold;

[0086] A first data retrieval module is used to retrieve the number of content adjustments made to the content of the mindfulness meditation guidance program of the intervention subject and its corresponding content adjustment duration each time when the number of content adjustments is lower than a preset number threshold;

[0087] an adjustment execution quality coefficient acquisition module, configured to acquire an adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit by using the content adjustment duration for adjusting the content of the mindfulness meditation guidance program for the intervention subject each time;

[0088] The adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit is obtained by the following formula:

[0089]

[0090] Wherein, J represents the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit; T represents the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit; N represents the number of content adjustments corresponding to each content adjustment performed by the online adjustment unit; T cIndicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; N b It represents the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit; T b T represents the standard deviation of the content adjustment duration corresponding to the current content adjustment performed by the online adjustment unit; max Indicates the maximum allowed content adjustment time under normal operation of the preset online adjustment unit;

[0091] a risk warning module, used to compare the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit with a preset first quality coefficient; when the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit exceeds the preset first quality coefficient, it is determined that the online adjustment unit has an abnormal risk and a risk warning is issued;

[0092] The abnormality determination module is used to determine the operation abnormality by using the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold.

[0093] The technical effect of the above technical solution is: through the first data monitoring module and the second data monitoring module, the content adjustment of the mindfulness meditation guidance program of the intervention object by the online adjustment unit is monitored in real time, including the number of content adjustments and the content adjustment duration. This helps to achieve accurate tracking and recording of the intervention process. The comparison module is used to compare the number of content adjustments with the preset number threshold, which helps to determine whether the online adjustment unit has made sufficient content adjustments, thereby ensuring the flexibility and effectiveness of the intervention. The adjustment execution quality coefficient acquisition module calculates the adjustment execution quality coefficient using the above formula by comprehensively considering the content adjustment duration, the number of content adjustments, the standard deviation of the content adjustment duration and the number of content adjustments, the preset reference value and the maximum allowable content adjustment duration. This coefficient can reflect the execution efficiency and accuracy of the online adjustment unit in the content adjustment process, and provides a scientific basis for quality control. The risk warning module can timely discover the abnormal risks that may exist in the online adjustment unit by comparing the maximum value of the adjustment execution quality coefficient with the preset first quality coefficient, and issue a warning, which helps to take measures in advance to avoid potential problems. When the number of content adjustments is not less than the preset threshold, the abnormality determination module uses the number of content adjustments and their duration to determine the operation abnormality, which helps to identify and handle abnormal situations in the online adjustment unit during the content adjustment process, ensuring the stability and reliability of the intervention process. The entire technical solution realizes the intelligent management and optimization of the online adjustment unit through real-time monitoring, dynamic evaluation, risk warning and abnormality determination. This helps to improve the intervention effect of the mindfulness meditation guidance program while reducing the potential risks caused by abnormalities in the online adjustment unit.

[0094] In summary, this technical solution achieves comprehensive monitoring and management of the online adjustment unit through a series of sophisticated monitoring, evaluation, early warning and judgment mechanisms, thereby ensuring the stability and effectiveness of the mindfulness meditation guidance program and improving the intelligence level and overall effect of the intervention.

[0095] Specifically, the abnormality determination module includes:

[0096] A second data retrieval module is used to extract the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold;

[0097] A comprehensive adjustment execution quality coefficient acquisition module, used to acquire the comprehensive adjustment execution quality coefficient by using the number of content adjustments and the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit;

[0098] The comprehensive adjustment execution quality coefficient is obtained by the following formula:

[0099]

[0100] Among them, J z represents the comprehensive adjustment execution quality coefficient; m represents the total number of content adjustments made by the online adjustment unit; N i represents the number of content adjustments corresponding to the i-th content adjustment performed by the online adjustment unit; T i T represents the content adjustment duration corresponding to the i-th content adjustment performed by the online adjustment unit; c Indicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; T bni Indicates that when the online adjustment unit adjusts the content for the i-th time, N i The standard deviation of the content adjustment duration corresponding to the number of content adjustments; N b Indicates the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit;

[0101] A coefficient comparison module, used for comparing the comprehensive adjustment execution quality coefficient with a preset second quality coefficient;

[0102] The abnormality determination and alarm module is used to determine that the operation of the online adjustment unit is abnormal and issue an abnormality alarm when the comprehensive adjustment execution quality coefficient is lower than a preset second quality coefficient.

[0103] The technical effect of the above technical solution is that the second data retrieval module can accurately extract the specific data of each content adjustment, including the number of content adjustments and the content adjustment duration, when the number of content adjustments reaches or exceeds the preset threshold. This provides a reliable data basis for subsequent comprehensive evaluation. The comprehensive adjustment execution quality coefficient acquisition module comprehensively considers multiple factors such as the total number of content adjustments made by the online adjustment unit, the number of content adjustments each time, the content adjustment duration, the standard deviation of the content adjustment duration, and the standard deviation of the number of content adjustments through the above formula. This comprehensive evaluation method can more comprehensively reflect the overall performance and execution quality of the online adjustment unit in the content adjustment process. The coefficient comparison module compares the comprehensive adjustment execution quality coefficient with the preset second quality coefficient, and can intelligently determine whether the operating state of the online adjustment unit is abnormal. When the comprehensive adjustment execution quality coefficient is lower than the preset second quality coefficient, the abnormal judgment and alarm module will immediately trigger an alarm to remind relevant personnel to take measures in time to ensure the stability and reliability of the intervention process. Through real-time monitoring, comprehensive evaluation, and intelligent abnormal judgment and alarm, the technical solution can timely discover and handle abnormal situations that may occur in the operation of the online adjustment unit, thereby avoiding potential risks and problems. This helps improve the stability and reliability of the entire system and ensure the intervention effect of the mindfulness meditation guidance program. Timely abnormal alarms and processing can reduce user dissatisfaction and complaints caused by system abnormalities, and improve user satisfaction and trust. At the same time, by continuously optimizing the performance and performance of the online adjustment unit, the overall user experience can be further improved.

[0104] In summary, this technical solution achieves comprehensive monitoring and management of online adjustment units through precise data analysis, comprehensive evaluation, and intelligent abnormality judgment and alarm mechanism, improves the stability and reliability of the system, and optimizes the user experience.

[0105] In order to better demonstrate the operation process of the neurofeedback intervention system based on mindfulness meditation, the present invention provides a neurofeedback intervention method based on mindfulness meditation, comprising the following steps:

[0106] Step 1: Use a portable three-lead EEG sensor to monitor the EEG signals of the intervention subjects in real time, filter, artifact and detrend the neural signals, and reduce the noise and interference of the neural signals;

[0107] Step 2: Extract features from the preprocessed neural signals, and map the features to a specified interval through a neural feedback index normalization model to obtain a normalized neural feedback index; then convert it into an audio signal through time domain signal processing technology, and assist the intervention subject to understand his or her own neural activity status in real time;

[0108] Step 3: Provide the intervention subjects with appropriate mindfulness meditation guidance program content and guidance statements based on their current neural activity state;

[0109] Step 4: During the intervention process, monitor the subject's physiological data and reactions in real time, and appropriately adjust and optimize the content of the subject's mindfulness meditation guidance program based on actual conditions.

[0110] The beneficial effects achieved by the above content are: by real-time monitoring of the neural activity of the intervention subject, the system can provide personalized mindfulness meditation guidance based on its status to improve the meditation effect; and combined with neural feedback, the intervention subject can instantly understand its mental state, so as to better adjust and control its emotions and concentration; and the system can be applied to multiple fields such as mental health regulation, stress management, and improvement of learning efficiency, and has broad market demand.

[0111] The present invention monitors the EEG signals of the intervention subjects in real time, maps the features to a specified interval using a neural feedback index normalization model, and obtains normalized neural feedback indicators; it then converts them into audio signals through time domain signal processing technology; combined with a system based on mindfulness meditation technology, it provides personalized psychological intervention content for the intervention subjects; and during the intervention process, it monitors the physiological condition of the intervention subjects in real time, and can make appropriate adjustments to the current intervention plan in a timely manner, effectively improving the effect of meditation training and the experience of the intervention subjects, and has strong practicality and market prospects.

[0112] It should be noted that, in this article, relational terms such as first and second, etc. are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device.

[0113] While the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and alterations may be made to the embodiments without departing from the principles and spirit of the invention.

Claims

1. A neurofeedback intervention system based on mindfulness meditation, characterized by: include: The neural monitoring module is used to monitor the EEG or other physiological signals of the intervention subject in real time, and transmit the intervention subject data to the data processing module for preprocessing in real time; The data processing module is used to pre-process the collected neural signals, including filtering, artifact processing and detrending processing, to reduce the noise and interference of the neural signals; Feature extraction module, used to extract features from preprocessed neural signals for analysis; features include: power spectrum density, frequency components; The neurofeedback module is used to map the extracted features into a specific interval through a neurofeedback index normalization model to obtain a normalized neurofeedback index; and map the normalized neurofeedback index into auditory neurofeedback based on natural sounds to assist the intervention subject to understand his or her own neural activity status in real time; The neuro-guidance module is used to embed a mindfulness meditation guidance program into the system, combine neuro-feedback data, personalize the guidance frequency and content, and provide adaptive training.

2. The mindfulness meditation-based neurofeedback intervention system according to claim 1, characterized in that: The neural monitoring module comprises: The factor determination unit is used to screen and confirm the intervention subjects before implementing the neurofeedback intervention based on mindfulness meditation, consider whether the intervention subjects have psychological problems and symptoms, and clarify the intervention goals; The terminal selection unit is used to select a suitable neural monitoring terminal according to the intervention target of the intervention object.

3. The mindfulness meditation-based neurofeedback intervention system according to claim 1, characterized in that: The data processing module comprises: A filtering processing unit, used to filter the neural signal using a low-pass filter, apply the coefficient matrix of the low-pass filter to the neural signal to perform a convolution operation, remove high-frequency signals in the neural signal, and retain low-frequency signals; An artifact processing unit, used for performing artifact processing on the collected neural signals by using an independent component analysis method; The detrending processing unit is used to subtract the original signal from the neural signal by using the detrending method to obtain the detrended neural signal.

4. The mindfulness meditation-based neurofeedback intervention system according to claim 1, characterized in that: The neural feedback module comprises: The model building unit is used to obtain the neural signals of the historical intervention subjects, and after preprocessing the neural signals, use the minimum-maximum normalization method to linearly transform the historical signals to the specified interval; then import the normalized historical signals into the neural network model for training and prediction, and obtain the normalized model of neural feedback indicators; The auditory mapping module is used to convert the normalized indicators as new time steps into audio signals through time domain signal processing technology and feed them back to the intervention object.

5. The mindfulness meditation-based neurofeedback intervention system according to claim 1, characterized in that: The nerve guidance module comprises: The content setting module is used to set the content and guidance statements of the mindfulness meditation guidance program; A signal analysis module is used to analyze and process the neural signals of the intervention subject and identify the ongoing activity state and emotional state of the intervention subject; The content setting module is used to provide the intervention subject with appropriate content and guiding statements of the mindfulness meditation guidance program according to the intervention subject's ongoing activity status and emotional state.

6. The mindfulness meditation-based neurofeedback intervention system according to claim 5, characterized in that: The nerve guidance module further includes: A real-time monitoring unit is used to monitor and analyze the physiological data of the intervention subject in real time during the neurofeedback process, and provide guidance and feedback based on the data changes; The online adjustment unit is used to appropriately adjust and optimize the content of the mindfulness meditation guidance program of the intervention subject according to the physiological data and response of the intervention subject during the neurofeedback process.

7. The mindfulness meditation-based neurofeedback intervention system according to claim 5, characterized in that: The nerve guidance module further includes: A first data monitoring module is used to monitor in real time the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject; A second data monitoring module is used to monitor in real time the content adjustment duration of the online adjustment unit adjusting the content of the mindfulness meditation guidance program of the intervention subject each time; a comparison module, configured to compare the number of content adjustments made by the online adjustment unit each time on the content of the mindfulness meditation guidance program for the intervention subject with a preset number threshold; A first data retrieval module is used to retrieve the number of content adjustments made to the content of the mindfulness meditation guidance program of the intervention subject and its corresponding content adjustment duration each time when the number of content adjustments is lower than a preset number threshold; an adjustment execution quality coefficient acquisition module, configured to acquire an adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit by using the content adjustment duration for adjusting the content of the mindfulness meditation guidance program for the intervention subject each time; The adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit is obtained by the following formula: Wherein, J represents the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit; T represents the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit; N represents the number of content adjustments corresponding to each content adjustment performed by the online adjustment unit; T c Indicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; N b It represents the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit; T b T represents the standard deviation of the content adjustment duration corresponding to the current content adjustment performed by the online adjustment unit; max Indicates the maximum allowed content adjustment time under normal operation of the preset online adjustment unit; a risk warning module, used to compare the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit with a preset first quality coefficient; when the maximum value of the adjustment execution quality coefficient corresponding to each content adjustment performed by the online adjustment unit exceeds the preset first quality coefficient, it is determined that the online adjustment unit has an abnormal risk and a risk warning is issued; The abnormality determination module is used to determine the operation abnormality by using the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold.

8. The mindfulness meditation-based neurofeedback intervention system according to claim 7, characterized in that: The abnormality determination module comprises: A second data retrieval module is used to extract the content adjustment number and content adjustment duration corresponding to each content adjustment performed by the online adjustment unit when the content adjustment number is not less than a preset number threshold; A comprehensive adjustment execution quality coefficient acquisition module, used to acquire the comprehensive adjustment execution quality coefficient by using the number of content adjustments and the content adjustment duration corresponding to each content adjustment performed by the online adjustment unit; The comprehensive adjustment execution quality coefficient is obtained by the following formula: Among them, J z represents the comprehensive adjustment execution quality coefficient; m represents the total number of content adjustments made by the online adjustment unit; N i represents the number of content adjustments corresponding to the i-th content adjustment performed by the online adjustment unit; T i T represents the content adjustment duration corresponding to the i-th content adjustment performed by the online adjustment unit; c Indicates the preset content adjustment duration reference value; N c Indicates the preset content adjustment number reference value; T bni Indicates that when the online adjustment unit adjusts the content for the i-th time, N i The standard deviation of the content adjustment duration corresponding to the number of content adjustments; N b Indicates the standard deviation of the number of content adjustments corresponding to the current content adjustment performed by the online adjustment unit; A coefficient comparison module, used for comparing the comprehensive adjustment execution quality coefficient with a preset second quality coefficient; The abnormality determination and alarm module is used to determine that the operation of the online adjustment unit is abnormal and issue an abnormality alarm when the comprehensive adjustment execution quality coefficient is lower than a preset second quality coefficient.

9. The mindfulness meditation-based neurofeedback intervention system according to claim 5, characterized in that: The content setting module includes: The content revision unit is used to collect the neural signals and intervention plans of different types of intervention subjects, and analyze the status of various types of intervention subjects after the intervention treatment to revise and supplement the content and guidance statements of the original mindfulness meditation guidance program in the system to form new content and guidance statements of the mindfulness meditation guidance program.

10. A method of neurofeedback intervention based on mindfulness meditation, implemented based on the neurofeedback intervention system based on mindfulness meditation according to any one of claims 1 to 9, characterized in that: The following steps are involved: Step 1: Use a portable three-lead EEG sensor to monitor the EEG signals of the intervention subjects in real time, filter, artifact and detrend the neural signals, and reduce the noise and interference of the neural signals; Step 2: Extract features from the preprocessed neural signals, and map the features to a specified interval through a neural feedback index normalization model to obtain a normalized neural feedback index; then convert it into an audio signal through time domain signal processing technology, and assist the intervention subject to understand his or her own neural activity status in real time; Step 3: Provide the intervention subjects with appropriate mindfulness meditation guidance program content and guidance statements based on their current neural activity state; Step 4: During the intervention process, monitor the subject's physiological data and reactions in real time, and appropriately adjust and optimize the content of the subject's mindfulness meditation guidance program based on actual conditions.

Images