Emotion and stress management system based on brain-computer interface

Abstract

This invention relates to brain-computer interfaces, specifically to a brain-computer interface-based emotion and stress management system. The control unit acquires the user's multimodal signals using a non-invasive multimodal signal acquisition device and preprocesses the EEG signals using an EEG signal processing module. The control unit then estimates the power spectral density of the preprocessed EEG signals using a power spectral density estimation module to obtain the power spectral density of the EEG signals. A relaxation level acquisition module obtains the user's relaxation level based on the power spectral density of the EEG signals, a coefficient of variation acquisition module obtains the coefficient of variation for the corresponding frequency band based on the power spectral density of the EEG signals, and a Schumann resonance energy index acquisition module obtains the Schumann resonance energy index corresponding to the first and second harmonics based on the power spectral density of the EEG signals. The technical solution provided by this invention overcomes the shortcomings of existing technologies, such as the difficulty in accurately identifying the user's emotional state and the inability to provide personalized real-time intervention.

Description

Technical Field

[0001] This invention relates to brain-computer interfaces, and more specifically to a brain-computer interface-based emotion and stress management system. Background Technology

[0002] During their development, adolescents face significant challenges, including academic pressure, social difficulties, and adaptation issues arising from rapid physical and mental growth, making them a high-risk group for mood and stress-related psychological problems. Prolonged negative emotional states not only affect adolescents' learning efficiency and social skills but can also trigger mental disorders such as anxiety and depression, potentially having a profound impact on their mental health in adulthood. Therefore, developing mood and stress management programs suitable for adolescents is of significant practical importance.

[0003] Traditional emotion assessment methods often rely on subjective questionnaires or single physiological indicators, which have limitations such as poor real-time performance and susceptibility to subjective bias, making them unsuitable for dynamic emotion monitoring. In recent years, brain-computer interface (BCI) technology has provided a new approach for objectively assessing emotional states by non-invasively acquiring EEG signals. However, existing BCI devices are mostly used in professional medical settings, and suffer from problems such as large size, complex operation, and poor wearing comfort, making them difficult for adolescents to accept. Furthermore, existing emotion recognition models are mostly based on single EEG features (such as frequency band energy), neglecting the dynamic changes in frequency band energy (coefficient of variation) and the moderating effect of the Earth's natural electromagnetic field (Schumann resonance) on EEG activity, resulting in insufficient emotion recognition accuracy and failing to meet the needs of personalized intervention.

[0004] Therefore, there is an urgent need for a brain-computer interface-based emotion and stress management system designed specifically for adolescents. By integrating multimodal signal acquisition and multidimensional feature analysis technologies, it can achieve accurate identification and real-time intervention of emotional states, providing a lightweight and wearable solution for adolescent mental health. Summary of the Invention

[0005] (a) Technical problems to be solved

[0006] In view of the above-mentioned shortcomings of the existing technology, the present invention provides an emotion and stress management system based on brain-computer interface, which can effectively overcome the shortcomings of the existing technology, such as difficulty in accurately identifying the user's emotional state and inability to provide personalized real-time intervention.

[0007] (II) Technical Solution

[0008] To achieve the above objectives, the present invention provides the following technical solution: The brain-computer interface-based emotion and stress management system includes a control unit. The control unit acquires the user's multimodal signals through a non-invasive multimodal signal acquisition device and preprocesses the EEG signals using an EEG signal processing module. The control unit estimates the power spectral density of the preprocessed EEG signals using a power spectral density estimation module to obtain the power spectral density of the EEG signals. A relaxation level acquisition module obtains the user's relaxation level based on the power spectral density of the EEG signals. A coefficient of variation acquisition module obtains the coefficient of variation of the corresponding frequency band based on the power spectral density of the EEG signals. Simultaneously, a Schumann resonance energy index acquisition module obtains the Schumann resonance energy index corresponding to the first and second harmonics based on the power spectral density of the EEG signals. The control unit constructs an emotion recognition model through an emotion recognition model construction module and trains the emotion recognition model using an emotion recognition model training module to generate a pre-trained emotion recognition model. The control unit outputs the corresponding emotion recognition result based on the pre-trained eye fatigue detection model, combined with relaxation degree, coefficient of variation, and Schumann resonance energy index, through an emotion recognition result output module. The control unit also uses an emotion regulation module to perform personalized emotion classification intervention on the user based on the emotion recognition result.

[0009] Preferably, the non-invasive multimodal signal acquisition device includes an eyeglass frame, an electroencephalogram (EEG) signal acquisition unit, a brain oxygenation signal acquisition unit, a heart rate signal acquisition unit, an optometry monitoring unit, a multimodal auxiliary sensor, and a neuromodulation unit. The eyeglass frame serves as the main structure of the non-invasive multimodal signal acquisition device. The EEG signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. It is set on the inner side of the temple, in the mastoid region behind the ear and the extension of the forehead. It has a total of 8 channels, of which 6 channels acquire EEG and 2 channels acquire EOG, which can accurately acquire EEG signals and eye movement signals. The brain oxygen signal acquisition unit, with the fNIRS sensor set at the forehead of the frame, is used to monitor brain oxygen saturation signals. The heart rate signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. The PPG sensor is located at the end of the temple, behind the ear, and is used to monitor heart rate and heart rate variability signals to assist in emotion assessment. The eye vision monitoring unit includes a distance sensor and an ambient light sensor, which monitors eye distance, duration and light intensity in real time. It is equipped with a dynamic focusing lens, which can initially adjust the focus according to the eye distance to relieve eye fatigue. It also has a reserved interface for monitoring tear physical parameters, and can support monitoring of biochemical indicators of eye fatigue through OTA upgrades in the future. Multimodal auxiliary sensors, including a six-axis gyroscope, a temperature sensor, and a machine vision miniature camera, capture eye features in real time, including scanning speed, gaze duration, pupil dynamic changes, and spontaneous blinking frequency, to achieve multi-dimensional personal data fusion and improve assessment accuracy. The neuromodulation unit, based on the vestibular nerve electrical stimulation (VeNS) technology, uses a low-intensity transcranial electrical stimulation (ES) module, which is placed on the inner side of the temple of the endoscope. It uses a symmetrical biphasic rectangular wave with a current intensity of 0.5~2mA, a frequency of 10~20Hz, and a pulse width of 100~500μs. The electrodes utilize nano-coating technology to improve adhesion to the skin, reduce noise interference during movement, and meet the needs of personal daily activities.

[0010] Preferably, the EEG signal processing module preprocesses the EEG signals, including: The system acquires raw EEG signals from users collected in multiple preset EEG signal acquisition areas, and preprocesses the raw EEG signals to obtain preprocessed raw EEG signals. The preprocessed raw EEG signals were sequentially subjected to artifact removal and rereference processing to obtain the EEG signals.

[0011] Preferably, the step of sequentially performing artifact removal and rereference processing on the preprocessed raw EEG signal to obtain the EEG signal includes: Blind source separation and artifact removal were performed sequentially on the EEG signals to obtain the EEG signals after artifact removal. The EEG signals after artifact removal are subjected to rereference processing to obtain the EEG signals.

[0012] Preferably, the relaxation level acquisition module acquires the user's relaxation level based on the power spectral density of the electroencephalogram (EEG) signal, including: The frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal is determined based on the power spectral density of the EEG signal, thereby obtaining the user's relaxation level.

[0013] Preferably, the coefficient of variation acquisition module acquires the coefficient of variation for the corresponding frequency band based on the power spectral density of the EEG signal, including: The coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal are determined based on the power spectral density of the EEG signal.

[0014] Preferably, the Schumann resonance energy index acquisition module acquires the Schumann resonance energy index corresponding to the first harmonic and the second harmonic based on the power spectral density of the EEG signal, including: Based on the frequency band ranges set for the first harmonic and the second harmonic respectively, the frequency band energy corresponding to the first harmonic and the second harmonic is determined. Based on the frequency band ranges corresponding to the first harmonic and the second harmonic, and the frequency band ranges corresponding to the α wave, θ wave, and β wave, the sub-frequency band ranges corresponding to the α wave, θ wave, and β wave are determined. Based on the sub-frequency ranges and power spectral densities corresponding to α-wave, θ-wave, and β-wave, the energy of the sub-frequency bands corresponding to α-wave, θ-wave, and β-wave is determined. The Schumann resonance energy index is obtained based on the sub-band energies corresponding to α wave, θ wave, and β wave, and the frequency band energies corresponding to the first harmonic and the second harmonic. The sum of the sub-frequency range corresponding to the α wave and the sub-frequency range corresponding to the θ wave includes the frequency range corresponding to the first harmonic, and the sub-frequency range corresponding to the β wave includes the frequency range corresponding to the second harmonic.

[0015] Preferably, obtaining the Schumann resonance energy index based on the sub-frequency band energies corresponding to the α wave, θ wave, and β wave, and the frequency band energies corresponding to the first harmonic and the second harmonic, includes: The ratio of the energy of the frequency band corresponding to the first harmonic to the sum of the energy of the sub-frequency bands corresponding to the α wave and θ wave is taken as the first energy ratio. The ratio of the energy of the frequency band corresponding to the second harmonic to the energy of the sub-frequency band corresponding to the β wave is taken as the second energy ratio. The Schumann resonance energy index is obtained based on the first energy ratio and the second energy ratio.

[0016] Preferably, the emotion recognition result output module, based on a pre-trained eye fatigue detection model, combines relaxation level, coefficient of variation, and Schumann resonance energy index to output the corresponding emotion recognition result, including: The relaxation level, Schumann resonance energy index, and the coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves are input into the pre-trained eye fatigue detection model to obtain the predicted probabilities corresponding to various recognition results. Based on the predicted probabilities corresponding to various recognition results, the user's emotion recognition result is output.

[0017] Preferably, the emotion regulation module performs personalized emotion grading intervention on the user based on the emotion recognition results, including: For mild anxiety: The "Emotional Relief Mode" is automatically activated, which uses low-intensity transcranial electrical stimulation at 10-15Hz to regulate the locus coeruleus-hypothalamus stress pathway and help relieve mild anxiety. At the same time, the app pushes soothing music and guides breathing exercises, and supports manual activation of "Brain Control Relaxation Games". For moderate anxiety: trigger parental alerts, and it is recommended to combine professional psychological counseling; conduct continuous intervention, twice a day, 30 minutes each time, and record the intervention effect simultaneously; automatically connect to the doctor's app to support parents in booking online psychological counseling for their children; For severe anxiety: immediately send an emergency alert to parents and recommend seeking medical diagnosis as soon as possible; at the same time, suspend stimulation interventions and retain only the monitoring function; In addition, for emergency stress: it supports manually activating the "rapid relief mode", which uses 15 minutes of targeted stimulation and soothing music to quickly reduce stress response and solve the pain point of adolescents' on-the-spot tension. Long-term improvement: Based on individual emotional data, personalized focus training tasks are pushed to improve emotional regulation ability through gamification; a monthly personal emotional management report is generated to provide feedback on the intervention effect and improvement suggestions, so that parents can intuitively see the improvement in their child's emotional state.

[0018] (III) Beneficial Effects Compared with existing technologies, the brain-computer interface-based emotion and stress management system provided by this invention has the following beneficial effects:

[0019] 1) Accurate monitoring and assessment to improve the accuracy of emotion recognition. The system utilizes a non-invasive multimodal signal acquisition device, based on physiological signals including EEG, and combines advanced signal processing techniques such as blind source separation and rereference to effectively remove artifact interference and obtain high-quality EEG signals. Based on power spectral density analysis, the system can not only accurately extract the energy of key frequency bands such as alpha, theta, and beta waves to assess the user's relaxation level, but also calculate the coefficient of variation of frequency band energy to capture the dynamic changes of EEG signals. At the same time, by analyzing the interaction between the first and second harmonics of the Schumann resonance and the EEG frequency bands, the system obtains the Schumann resonance energy index, further enriching the physiological indicators of emotion assessment, significantly improving the accuracy and reliability of emotion recognition, and providing a scientific basis for personalized intervention. 2) Personalized intervention and adjustment to enhance the effectiveness of emotion management Based on emotion recognition results, the system designs tiered intervention strategies for different levels of anxiety (mild, moderate, and severe) and emergency stress situations. For mild anxiety, low-intensity transcranial electrical stimulation and music breathing training are automatically initiated to quickly soothe emotions. For moderate anxiety, a parental alert is triggered, combined with professional psychological counseling and continuous intervention, and online psychological counseling appointments are supported. For severe anxiety, an emergency alert is immediately pushed, and medical diagnosis is recommended. In addition, the system provides a "rapid relief mode" to deal with on-the-spot tension, as well as personalized focus training tasks to promote long-term mood improvement. The combination of tiered intervention and personalized adjustment effectively meets the diverse emotion management needs of adolescents, enhancing the pertinence and effectiveness of intervention. 3) Multi-scenario integrated application enhances system usability and convenience. The system uses smart glasses as a carrier, integrating multimodal signal acquisition and neural modulation units. It adopts flexible dry electrodes and nano-coating technology to improve wearing comfort and signal quality, meeting the needs of daily activities. The glasses frame design balances functionality and fashion, making it easy for teenagers to wear for extended periods. At the same time, the system supports APP interaction and doctor-end connection, enabling real-time monitoring of emotional data, feedback on intervention effects, and online psychological counseling appointments. The multi-scenario integrated application design allows the system to be used for daily emotion monitoring and self-regulation as well as to assist in professional psychological treatment, improving the system's practicality and convenience, and providing a comprehensive solution for adolescent mental health management. Attached Figure Description

[0020] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the accompanying drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are merely some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without any creative effort.

[0021] Figure 1 This is a schematic diagram of the system of the present invention; Figure 2 This is a schematic diagram of the process of the present invention. Detailed Implementation

[0022] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some, not all, of the embodiments of the present invention. All other embodiments obtained by those skilled in the art based on the embodiments of the present invention without creative effort are within the scope of protection of the present invention.

[0023] The following describes the specific functional modules of the brain-computer interface-based emotion and stress management system provided by this invention, using concrete examples (such as...). Figure 1 (as shown) and technical effects.

[0024] The system's functional modules include: a control unit, which acquires the user's multimodal signals through a non-invasive multimodal signal acquisition device, preprocesses the EEG signals using an EEG signal processing module, estimates the power spectral density of the preprocessed EEG signals using a power spectral density estimation module, obtains the power spectral density of the EEG signals, obtains the user's relaxation level using a relaxation level acquisition module based on the power spectral density of the EEG signals, obtains the coefficient of variation for the corresponding frequency band using a coefficient of variation acquisition module based on the power spectral density of the EEG signals, and obtains the Schumann resonance energy index corresponding to the first and second harmonics using a Schumann resonance energy index acquisition module based on the power spectral density of the EEG signals. The control unit constructs an emotion recognition model through the emotion recognition model construction module and trains the emotion recognition model using the emotion recognition model training module to generate a pre-trained emotion recognition model. The control unit outputs the corresponding emotion recognition results based on the pre-trained eye fatigue detection model, combined with relaxation level, coefficient of variation and Schumann resonance energy index, through the emotion recognition result output module. The control unit also uses the emotion regulation module to perform personalized emotion classification intervention for users based on the emotion recognition results.

[0025] I. Non-invasive multimodal signal acquisition device The non-invasive multimodal signal acquisition device includes an eyeglass frame, an electroencephalogram (EEG) signal acquisition unit, a brain oxygen signal acquisition unit, a heart rate signal acquisition unit, an optometry monitoring unit, a multimodal auxiliary sensor, and a neuromodulation unit. The eyeglass frame serves as the main structure of the non-invasive multimodal signal acquisition device. The EEG signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. It is set on the inner side of the temple, in the mastoid region behind the ear and the extension of the forehead. It has a total of 8 channels, of which 6 channels acquire EEG and 2 channels acquire EOG, which can accurately acquire EEG signals and eye movement signals. The brain oxygen signal acquisition unit, with the fNIRS sensor set at the forehead of the frame, is used to monitor brain oxygen saturation signals. The heart rate signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. The PPG sensor is located at the end of the temple, behind the ear, and is used to monitor heart rate and heart rate variability signals to assist in emotion assessment. The eye vision monitoring unit includes a distance sensor and an ambient light sensor, which monitors eye distance, duration and light intensity in real time. It is equipped with a dynamic focusing lens, which can initially adjust the focus according to the eye distance to relieve eye fatigue. It also has a reserved interface for monitoring tear physical parameters, and can support monitoring of biochemical indicators of eye fatigue through OTA upgrades in the future. Multimodal auxiliary sensors, including a six-axis gyroscope, a temperature sensor, and a machine vision miniature camera, capture eye features in real time, including scanning speed, gaze duration, pupil dynamic changes, and spontaneous blinking frequency, to achieve multi-dimensional personal data fusion and improve assessment accuracy. The neuromodulation unit, based on the vestibular nerve electrical stimulation (VeNS) technology, uses a low-intensity transcranial electrical stimulation (ES) module, which is placed on the inner side of the temple of the endoscope. It uses a symmetrical biphasic rectangular wave with a current intensity of 0.5~2mA, a frequency of 10~20Hz, and a pulse width of 100~500μs. The electrodes utilize nano-coating technology to improve adhesion to the skin, reduce noise interference during movement, and meet the needs of personal daily activities.

[0026] II. Electroencephalogram (EEG) Signal Processing Module The EEG signal processing module preprocesses the EEG signals, including: The system acquires raw EEG signals from users collected in multiple preset EEG signal acquisition areas, and preprocesses the raw EEG signals to obtain preprocessed raw EEG signals. The preprocessed raw EEG signals were sequentially subjected to artifact removal and rereference processing to obtain the EEG signals.

[0027] Specifically, the preprocessed raw EEG signals are sequentially subjected to artifact removal and rereference processing to obtain EEG signals, including: Blind source separation and artifact removal were performed sequentially on the EEG signals to obtain the EEG signals after artifact removal. The EEG signals after artifact removal are subjected to rereference processing to obtain the EEG signals.

[0028] III. Relaxation Level Acquisition Module The relaxation level acquisition module obtains the user's relaxation level based on the power spectral density of the EEG signal, including: The frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal is determined based on the power spectral density of the EEG signal, thereby obtaining the user's relaxation level.

[0029] IV. Coefficient of Variation Acquisition Module The coefficient of variation acquisition module obtains the coefficient of variation for the corresponding frequency band based on the power spectral density of the EEG signal, including: The coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal are determined based on the power spectral density of the EEG signal.

[0030] V. Schumann Resonance Energy Index Acquisition Module The Schumann resonance energy index acquisition module obtains the Schumann resonance energy indices corresponding to the first and second harmonics based on the power spectral density of the EEG signal, including: Based on the frequency band ranges set for the first harmonic and the second harmonic respectively, the frequency band energy corresponding to the first harmonic and the second harmonic is determined. Based on the frequency band ranges corresponding to the first harmonic and the second harmonic, and the frequency band ranges corresponding to the α wave, θ wave, and β wave, the sub-frequency band ranges corresponding to the α wave, θ wave, and β wave are determined. Based on the sub-frequency ranges and power spectral densities corresponding to α-wave, θ-wave, and β-wave, the energy of the sub-frequency bands corresponding to α-wave, θ-wave, and β-wave is determined. The Schumann resonance energy index is obtained based on the sub-band energies corresponding to α wave, θ wave, and β wave, and the frequency band energies corresponding to the first harmonic and the second harmonic. The sum of the sub-frequency range corresponding to the α wave and the sub-frequency range corresponding to the θ wave includes the frequency range corresponding to the first harmonic, and the sub-frequency range corresponding to the β wave includes the frequency range corresponding to the second harmonic.

[0031] Specifically, based on the sub-frequency energies corresponding to the alpha, theta, and beta waves, and the frequency energies corresponding to the first and second harmonics, the Schumann resonance energy index is obtained, including: The ratio of the energy of the frequency band corresponding to the first harmonic to the sum of the energy of the sub-frequency bands corresponding to the α wave and θ wave is taken as the first energy ratio. The ratio of the energy of the frequency band corresponding to the second harmonic to the energy of the sub-frequency band corresponding to the β wave is taken as the second energy ratio. The Schumann resonance energy index is obtained based on the first energy ratio and the second energy ratio.

[0032] The aforementioned technical solution, through a non-invasive multimodal signal acquisition device, effectively removes artifact interference and obtains high-quality EEG signals based on physiological signals, including EEG, combined with advanced signal processing techniques such as blind source separation and rereference. Based on power spectral density analysis, the system can not only accurately extract the energy of key frequency bands such as alpha, theta, and beta waves to assess the user's relaxation level, but also calculate the coefficient of variation of frequency band energy to capture the dynamic changes of EEG signals. At the same time, by analyzing the interaction between the first and second harmonics of the Schumann resonance and the EEG frequency bands, the Schumann resonance energy index is obtained, further enriching the physiological indicators of emotion assessment, significantly improving the accuracy and reliability of emotion recognition, and providing a scientific basis for personalized intervention.

[0033] VI. Emotion Recognition Result Output Module The emotion recognition output module, based on a pre-trained eye fatigue detection model, combines relaxation level, coefficient of variation, and Schumann resonance energy index to output the corresponding emotion recognition results, including: The relaxation level, Schumann resonance energy index, and the coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves are input into the pre-trained eye fatigue detection model to obtain the predicted probabilities corresponding to various recognition results. Based on the predicted probabilities corresponding to various recognition results, the user's emotion recognition result is output.

[0034] VII. Emotion Regulation Module The emotion regulation module provides personalized emotion grading intervention for users based on emotion recognition results, including: For mild anxiety: The "Emotional Relief Mode" is automatically activated, which uses low-intensity transcranial electrical stimulation at 10-15Hz to regulate the locus coeruleus-hypothalamus stress pathway and help relieve mild anxiety. At the same time, the app pushes soothing music and guides breathing exercises, and supports manual activation of "Brain Control Relaxation Games". For moderate anxiety: trigger parental alerts, and it is recommended to combine professional psychological counseling; conduct continuous intervention, twice a day, 30 minutes each time, and record the intervention effect simultaneously; automatically connect to the doctor's app to support parents in booking online psychological counseling for their children; For severe anxiety: immediately send an emergency alert to parents and recommend seeking medical diagnosis as soon as possible; at the same time, suspend stimulation interventions and retain only the monitoring function; In addition, for emergency stress: it supports manually activating the "rapid relief mode", which uses 15 minutes of targeted stimulation and soothing music to quickly reduce stress response and solve the pain point of adolescents' on-the-spot tension. Long-term improvement: Based on individual emotional data, personalized focus training tasks are pushed to improve emotional regulation ability through gamification; a monthly personal emotional management report is generated to provide feedback on the intervention effect and improvement suggestions, so that parents can intuitively see the improvement in their child's emotional state.

[0035] The above-mentioned technical solution, based on emotion recognition results, designs tiered intervention strategies for different levels of anxiety (mild, moderate, and severe) and emergency stress situations. For mild anxiety, low-intensity transcranial electrical stimulation and music breathing training are automatically initiated to quickly soothe emotions; for moderate anxiety, a parental alert is triggered, combined with professional psychological counseling and continuous intervention, and online psychological counseling appointments are supported; for severe anxiety, an emergency alert is immediately pushed, and medical diagnosis is recommended; in addition, the system also provides a "rapid relief mode" to deal with on-the-spot tension, and personalized focus training tasks to promote long-term mood improvement; the combination of tiered intervention and personalized adjustment effectively meets the diverse emotion management needs of adolescents, enhancing the pertinence and effectiveness of intervention.

[0036] In this technical solution, smart glasses are used as a carrier to integrate multimodal signal acquisition and neural modulation units. Flexible dry electrodes and nano-coating technology are adopted to improve wearing comfort and signal quality, meeting the needs of daily activities. The glasses frame design combines functionality and fashion, making it easy for teenagers to wear for extended periods. At the same time, the system supports APP interaction and doctor-end connection, realizing functions such as real-time monitoring of emotional data, feedback on intervention effects, and online psychological counseling appointments. The multi-scenario integrated application design enables the system to be used for daily emotion monitoring and self-regulation, as well as to assist in professional psychological treatment, improving the system's practicality and convenience, and providing a comprehensive solution for adolescent mental health management.

[0037] The above embodiments are only used to illustrate the technical solutions of the present invention, and are not intended to limit it. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions will not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention.

Claims

1. A brain-computer interface-based emotion and stress management system, characterized by: The system includes a control unit that acquires the user's multimodal signals through a non-invasive multimodal signal acquisition device and preprocesses the EEG signals using an EEG signal processing module. The control unit then estimates the power spectral density of the preprocessed EEG signals using a power spectral density estimation module to obtain the power spectral density of the EEG signals. A relaxation level acquisition module is used to obtain the user's relaxation level based on the power spectral density of the EEG signals. A coefficient of variation acquisition module is used to obtain the coefficient of variation for the corresponding frequency band based on the power spectral density of the EEG signals. Simultaneously, a Schumann resonance energy index acquisition module is used to obtain the Schumann resonance energy index corresponding to the first and second harmonics based on the power spectral density of the EEG signals. The control unit constructs an emotion recognition model through an emotion recognition model construction module and trains the emotion recognition model using an emotion recognition model training module to generate a pre-trained emotion recognition model. The control unit outputs the corresponding emotion recognition result based on the pre-trained eye fatigue detection model, combined with relaxation degree, coefficient of variation, and Schumann resonance energy index, through an emotion recognition result output module. The control unit also uses an emotion regulation module to perform personalized emotion classification intervention on the user based on the emotion recognition result.

2. The brain-computer interface-based emotion and stress management system according to claim 1, characterized in that: The non-invasive multimodal signal acquisition device includes an eyeglass frame, an electroencephalogram (EEG) signal acquisition unit, a brain oxygen signal acquisition unit, a heart rate signal acquisition unit, an optometry monitoring unit, a multimodal auxiliary sensor, and a neuromodulation unit. The eyeglass frame serves as the main structure of the non-invasive multimodal signal acquisition device. The EEG signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. It is set on the inner side of the temple, in the mastoid region behind the ear and the extension of the forehead. It has a total of 8 channels, of which 6 channels acquire EEG and 2 channels acquire EOG, which can accurately acquire EEG signals and eye movement signals. The brain oxygen signal acquisition unit, with the fNIRS sensor set at the forehead of the frame, is used to monitor brain oxygen saturation signals. The heart rate signal acquisition unit uses dry electrodes that incorporate the properties of flexible biomaterials. The PPG sensor is located at the end of the temple, behind the ear, and is used to monitor heart rate and heart rate variability signals to assist in emotion assessment. The eye vision monitoring unit includes a distance sensor and an ambient light sensor, which monitors eye distance, duration and light intensity in real time. It is equipped with a dynamic focusing lens, which can initially adjust the focus according to the eye distance to relieve eye fatigue. It also has a reserved interface for monitoring tear physical parameters, and can support monitoring of biochemical indicators of eye fatigue through OTA upgrades in the future. Multimodal auxiliary sensors, including a six-axis gyroscope, a temperature sensor, and a machine vision miniature camera, capture eye features in real time, including scanning speed, gaze duration, pupil dynamic changes, and spontaneous blinking frequency, to achieve multi-dimensional personal data fusion and improve assessment accuracy. The neuromodulation unit, based on the vestibular nerve electrical stimulation (VeNS) technology, uses a low-intensity transcranial electrical stimulation (ES) module, which is placed on the inner side of the temple of the endoscope. It uses a symmetrical biphasic rectangular wave with a current intensity of 0.5~2mA, a frequency of 10~20Hz, and a pulse width of 100~500μs. The electrodes utilize nano-coating technology to improve adhesion to the skin, reduce noise interference during movement, and meet the needs of personal daily activities.

3. The brain-computer interface-based emotion and stress management system according to claim 1, characterized in that: The EEG signal processing module preprocesses the EEG signals, including: The system acquires raw EEG signals from users collected in multiple preset EEG signal acquisition areas, and preprocesses the raw EEG signals to obtain preprocessed raw EEG signals. The preprocessed raw EEG signals were sequentially subjected to artifact removal and rereference processing to obtain the EEG signals.

4. The brain-computer interface-based emotion and stress management system according to claim 3, characterized in that: The process of sequentially performing artifact removal and rereference processing on the preprocessed raw EEG signals to obtain EEG signals includes: Blind source separation and artifact removal were performed sequentially on the EEG signals to obtain the EEG signals after artifact removal. The EEG signals after artifact removal are subjected to rereference processing to obtain the EEG signals.

5. The brain-computer interface-based emotion and stress management system according to claim 3, characterized in that: The relaxation level acquisition module acquires the user's relaxation level based on the power spectral density of the EEG signal, including: The frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal is determined based on the power spectral density of the EEG signal, thereby obtaining the user's relaxation level.

6. The brain-computer interface-based emotion and stress management system according to claim 5, characterized in that: The coefficient of variation acquisition module obtains the coefficient of variation for the corresponding frequency band based on the power spectral density of the EEG signal, including: The coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves in the EEG signal are determined based on the power spectral density of the EEG signal.

7. The brain-computer interface-based emotion and stress management system according to claim 6, characterized in that: The Schumann resonance energy index acquisition module obtains the Schumann resonance energy index corresponding to the first and second harmonics based on the power spectral density of the EEG signal, including: Based on the frequency band ranges set for the first harmonic and the second harmonic respectively, the frequency band energy corresponding to the first harmonic and the second harmonic is determined. Based on the frequency band ranges corresponding to the first harmonic and the second harmonic, and the frequency band ranges corresponding to the α wave, θ wave, and β wave, the sub-frequency band ranges corresponding to the α wave, θ wave, and β wave are determined. Based on the sub-frequency ranges and power spectral densities corresponding to α-wave, θ-wave, and β-wave, the energy of the sub-frequency bands corresponding to α-wave, θ-wave, and β-wave is determined. The Schumann resonance energy index is obtained based on the sub-band energies corresponding to α wave, θ wave, and β wave, and the frequency band energies corresponding to the first harmonic and the second harmonic. The sum of the sub-frequency range corresponding to the α wave and the sub-frequency range corresponding to the θ wave includes the frequency range corresponding to the first harmonic, and the sub-frequency range corresponding to the β wave includes the frequency range corresponding to the second harmonic.

8. The brain-computer interface-based emotion and stress management system according to claim 7, characterized in that: The process of obtaining the Schumann resonance energy index based on the sub-frequency band energies corresponding to the α wave, θ wave, and β wave, and the frequency band energies corresponding to the first harmonic and the second harmonic, includes: The ratio of the energy of the frequency band corresponding to the first harmonic to the sum of the energy of the sub-frequency bands corresponding to the α wave and θ wave is taken as the first energy ratio. The ratio of the energy of the frequency band corresponding to the second harmonic to the energy of the sub-frequency band corresponding to the β wave is taken as the second energy ratio. The Schumann resonance energy index is obtained based on the first energy ratio and the second energy ratio.

9. The brain-computer interface-based emotion and stress management system according to claim 7, characterized in that: The emotion recognition result output module, based on a pre-trained eye fatigue detection model, combines relaxation level, coefficient of variation, and Schumann resonance energy index to output corresponding emotion recognition results, including: The relaxation level, Schumann resonance energy index, and the coefficients of variation of the frequency band energy corresponding to alpha, theta, and beta waves are input into the pre-trained eye fatigue detection model to obtain the predicted probabilities corresponding to various recognition results. Based on the predicted probabilities corresponding to various recognition results, the user's emotion recognition result is output.

10. The brain-computer interface-based emotion and stress management system according to claim 9, characterized in that: The emotion regulation module provides personalized emotion grading intervention for users based on emotion recognition results, including: For mild anxiety: The "Emotional Relief Mode" is automatically activated, which uses low-intensity transcranial electrical stimulation at 10-15Hz to regulate the locus coeruleus-hypothalamus stress pathway and help relieve mild anxiety. At the same time, the app pushes soothing music and guides breathing exercises, and supports manual activation of "Brain Control Relaxation Games". For moderate anxiety: trigger parental alerts, and it is recommended to combine professional psychological counseling; conduct continuous intervention, twice a day, 30 minutes each time, and record the intervention effect simultaneously; automatically connect to the doctor's app to support parents in booking online psychological counseling for their children; For severe anxiety: immediately send an emergency alert to parents and recommend seeking medical diagnosis as soon as possible; at the same time, suspend stimulation interventions and retain only the monitoring function; In addition, for emergency stress: it supports manually activating the "rapid relief mode", which uses 15 minutes of targeted stimulation and soothing music to quickly reduce stress response and solve the pain point of adolescents' on-the-spot tension; Long-term improvement: Based on individual emotional data, personalized focus training tasks are pushed to improve emotional regulation ability through gamification; a monthly personal emotional management report is generated to provide feedback on the intervention effect and improvement suggestions, so that parents can intuitively see the improvement in their child's emotional state.

Images