A helmet for regulating mental state

Abstract

This invention discloses a helmet for regulating mental state, relating to the field of mental state regulation. The device includes: a helmet, an EEG acquisition module, a signal analysis module, a vagus nerve stimulation module, and a vagus nerve stimulation ear clip mounted on the helmet. The EEG acquisition module is used to acquire EEG signals of a target user in real time and preprocess the acquired EEG signals. The signal analysis module is used to extract features from the preprocessed EEG signals and input the extracted EEG features into a mental state assessment model to obtain the mental state value of the target user. The vagus nerve stimulation module is used to determine the stimulation parameters of the vagus nerve stimulation ear clip based on the mental state value of the target user, and adaptively and dynamically adjust the stimulation parameters by acquiring EEG features in real time. The vagus nerve stimulation ear clip is used to stimulate the percutaneous vagus nerve of the target user. This invention improves the effectiveness of vagus nerve stimulation.

Description

Technical Field

[0001] This invention relates to the field of mental state regulation technology, and in particular to a helmet for mental state regulation. Background Technology

[0002] Diseases closely related to mental function can cause abnormal mental states in their early stages, seriously threatening human mental health. Currently, the clinical diagnosis of mental disorders such as depression mainly relies on medical history, interviews, observation, scale completion, and questionnaire assessment, with polysomnography used to collect patients' physiological responses for auxiliary diagnosis. This testing method depends on the doctor's experience and subjective factors, is easily affected by the surrounding environment, and suffers from drawbacks such as slow questioning speed, low efficiency, expensive and bulky equipment. Furthermore, interventions are mostly drug-based, with significant side effects, high recurrence rates, and difficulty in assessing intervention effectiveness. In addition, the overlap between various abnormal states often leads to poor assessment and intervention outcomes. Therefore, developing universally applicable assessment and non-pharmacological intervention techniques for mental states is crucial. The U.S. Food and Drug Administration (FDA) officially approved vagus nerve stimulation (VNS) for the intervention of treatment-resistant epilepsy in 1997 and as a complementary alternative therapy for treatment-resistant depression in 2005. Clinical practice in recent years has confirmed that acupuncture can effectively improve and intervene in abnormal mental states, with good efficacy and few adverse reactions, and has been included in the latest clinical practice guidelines of the American College of Internal Medicine.

[0003] Although vagus nerve stimulation has some effect on the intervention of abnormal mental states, existing intervention techniques lack effective quantitative assessment methods, have poor robustness, and cannot achieve precise intervention. Biofeedback technology can effectively quantify the intervention of abnormal mental states, but so far, there is no biofeedback-based vagus nerve stimulation intervention and regulation technology either domestically or internationally. Summary of the Invention

[0004] The purpose of this invention is to provide a helmet for regulating mental state, which improves the effectiveness of vagus nerve stimulation.

[0005] To achieve the above objectives, the present invention provides the following solution:

[0006] A helmet for regulating mental state includes: a helmet, an EEG acquisition module, a signal analysis module, a vagus nerve stimulation module, and a vagus nerve stimulation ear clip mounted on the helmet;

[0007] The EEG acquisition module is used to acquire the target user's EEG signals in real time and to preprocess the acquired EEG signals.

[0008] The signal analysis module is used to extract features from the preprocessed EEG signals and input the extracted EEG features into the mental state assessment model to obtain the mental state value of the target user.

[0009] The vagus nerve stimulation module is used to determine the stimulation parameters of the vagus nerve stimulation ear clip based on the mental state value of the target user, and to adaptively and dynamically adjust the stimulation parameters by acquiring EEG characteristics in real time.

[0010] The vagus nerve stimulation ear clip is used to stimulate the percutaneous vagus nerve of the target user.

[0011] Optionally, the EEG acquisition module includes a preprocessing unit; the preprocessing unit is used to sequentially filter and amplify the acquired EEG signals to obtain preprocessed EEG signals.

[0012] Optionally, the EEG features include spectral feature values, alpha brainwave asymmetry, LZC complexity, and sample entropy.

[0013] Optionally, the stimulation parameters include stimulation intensity, frequency, and time, wherein the frequency ranges from 0Hz to 100Hz, and the time ranges from 0min to 60min.

[0014] Optionally, the EEG acquisition module includes an EEG sensor located inside the rear of the helmet.

[0015] Optionally, the vagus nerve stimulation module includes a reinforcement learning-based PID control unit, which is used to input real-time acquired EEG features and dynamically and adaptively adjust stimulation parameters in real time based on the real-time acquired EEG features.

[0016] Optionally, it also includes an audio playback module, which is used to output corresponding music based on the currently collected EEG signals.

[0017] Optionally, the god state evaluation model is established using the XGBoost model.

[0018] According to specific embodiments provided by the present invention, the present invention discloses the following technical effects:

[0019] This invention determines the stimulation parameters of the vagus nerve stimulation ear clip based on the target user's mental state value, and adaptively and dynamically adjusts the stimulation parameters by acquiring EEG characteristics in real time, providing real-time biofeedback on mental state, thereby achieving personalized and precise mental state regulation. Attached Figure Description

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

[0021] Figure 1 A schematic diagram of a helmet structure for regulating mental state provided in an embodiment of the present invention;

[0022] Figure 2 A schematic diagram illustrating the principle of mental state regulation provided in this embodiment of the invention;

[0023] Figure 3 A schematic diagram of a denoising algorithm provided in an embodiment of the present invention;

[0024] Figure 4 A schematic diagram of the PID control vagus nerve stimulation based on reinforcement learning provided in an embodiment of the present invention;

[0025] Figure 5 This is a schematic diagram of the electrodes provided in an embodiment of the present invention;

[0026] Figure 6 A schematic diagram illustrating the workflow of a helmet for regulating mental state, provided as an embodiment of the present invention;

[0027] Figure 7 A schematic diagram showing the placement of the main control module provided in an embodiment of the present invention;

[0028] Figure 8 This is a schematic diagram of the switch button position provided in an embodiment of the present invention;

[0029] Figure 9 This is a schematic diagram of the audio playback unit and the placement of the vagus nerve stimulation ear clip provided in an embodiment of the present invention;

[0030] Figure 10 This is a schematic diagram of the flexible electrode position provided in an embodiment of the present invention. Detailed Implementation

[0031] The technical solutions of the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of the present invention, and not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0032] The purpose of this invention is to provide a helmet for regulating mental state, which improves the effectiveness of vagus nerve stimulation.

[0033] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, the present invention will be further described in detail below with reference to the accompanying drawings and specific embodiments.

[0034] To address the limitations of existing mental health monitoring and non-pharmacological intervention technologies, such as low accuracy, poor robustness, scarcity of effective objective indicators for assessment and intervention, and low universality, this invention provides a helmet for mental state regulation. Its main feature is the provision of vagus nerve stimulation and audio stimulation paradigms based on real-time mental state assessment, forming a closed-loop "assessment-regulation-assessment" biofeedback control mental state intervention technology. This technology is embedded in a helmet worn daily, providing non-intrusive real-time monitoring of the individual's mental state without altering the helmet's basic functions.

[0035] like Figure 1 and Figure 2 As shown, the present invention provides a helmet for regulating mental state, comprising: a helmet (helmet body), an EEG acquisition module, a signal analysis module, a vagus nerve stimulation module, and a vagus nerve stimulation ear clip mounted on the helmet (helmet body).

[0036] The EEG acquisition module is used to acquire the target user's EEG signals in real time and to preprocess the acquired EEG signals.

[0037] The target users are those who wear helmets, specifically the users of the helmet of this invention.

[0038] The EEG acquisition module includes a preprocessing unit; the preprocessing unit is used to filter and amplify the acquired EEG signals sequentially to achieve filtering and noise reduction, and obtain preprocessed EEG signals.

[0039] The preprocessing unit includes a 0-45Hz low-pass FIR filter, which is used to filter the EEG signals. The acquired EEG signals undergo preprocessing such as filtering and amplification, as well as noise reduction algorithms, and are finally continuously monitored through a universal, integrated EEG bio-information acquisition module (EEG acquisition module) to achieve continuous monitoring of the patient's EEG bio-information.

[0040] The preprocessing unit specifically employs an adaptive noise removal algorithm based on wavelet decomposition combined with Kalman filtering. The specific process is as follows: Figure 3 As shown.

[0041] The signal analysis module is used to extract features from the preprocessed EEG signals and input the extracted EEG features into the mental state assessment model to obtain the mental state value of the target user. The mental state of the target user is represented by the mental state value of the target user.

[0042] The EEG characteristics include spectral features, alpha brainwave asymmetry, LZC complexity, and sample entropy. Spectral features refer to power spectral density (PSD).

[0043] After denoising, the data is divided into slices of 2000 sample points each. For each slice, spectral feature values, alpha asymmetry, and other related feature parameters are extracted. Among them, there are four nonlinear feature values: alpha power variation (APV), Lempel-Ziv complexity (LZC), sample entropy, and frontal alpha power asymmetry (FAA).

[0044] The god state evaluation model is established using the XGBoost model.

[0045] The output of the God State Assessment Model is a probability value.

[0046] Figure 2 In Chinese, EEG represents electroencephalography (EEG), EOG represents electrooculography (EOG), EMG represents electromyography (EMG), and ADC represents analog-to-digital converter.

[0047] The vagus nerve stimulation module is used to activate the stimulation paradigm based on the target user's mental state value, determine the stimulation parameters of the vagus nerve stimulation ear clip, and adaptively and dynamically adjust the stimulation parameters by acquiring EEG characteristics in real time.

[0048] The vagus nerve stimulation module includes a reinforcement learning-based PID control unit, which is used to input real-time acquired EEG features and dynamically and adaptively adjust stimulation parameters in real time based on the real-time acquired EEG features.

[0049] Using the aforementioned relevant feature parameters of the EEG signal (EEG features) as input and the probability distribution output by the machine learning model as output, an XGBoost model is established to quantitatively assess the current mental state. Here, the probability distribution represents the probability distribution of the EEG signal. The vagus nerve stimulation module is triggered to perform percutaneous vagus nerve electrical stimulation on the ear. The stimulation parameters, such as intensity, duration, and frequency, are dynamically and adaptively adjusted using PID control based on the quantitative assessment results of the mental state. The feedback adjustment output is Y, which is controlled by a reinforcement learning model. The reinforcement learning model outputs the frequency, intensity, and duration parameters of the vagus nerve stimulation.

[0050] Figure 4To develop a reinforcement learning-based PID control scheme for vagal nerve stimulation modulation, the real-time individual mental state assessment result is first extracted as the input x to the reinforcement learning model. The stimulation paradigm decision module provides initial vagal nerve stimulation parameters based on the input, and simultaneously extracts EEG features as feedback. The reinforcement learning module dynamically controls the PID parameters based on the feature values ​​to achieve personalized and precise modulation. The specific feedback control algorithm flow is as follows:

[0051] (1) Calculate the parameters of the reinforcement learning objective:

[0052]

[0053] Where π represents the policy, Γ represents the set of actions, J(π) represents the long-run optimal value of the state, e represents the expectation, K represents the number of states (number of optimizations), and γ k-1 Let r represent the discount rate for the (k-1)th optimization. k This represents the reward for state k.

[0054] (2) The control signal is generated by the control strategy u, and u satisfies:

[0055]

[0056] Among them, u * Describes the optimal value function. This represents the optimization function.

[0057] Where, x k and u k It represents the state and control signal of the stimulus system at the k-th optimization, Q(x) k ,u k ) is the action value function.

[0058] Q(x k ,u k )=E[R k |x k ,u k ];

[0059]

[0060] Among them, R k Let Q represent the reward function. * (x k ,u k ) represents the optimal action obtained by recursion, and μ represents the policy controller.

[0061] (3) Calculate u through a neural network k and Q(x) k ,u kThe input parameters of the neural network include the parameters of the policy controller, namely the stimulus intensity, frequency and time, as well as the reinforcement learning reward parameters and error parameters.

[0062] (4) The final network output controls the PID parameters Kp, Ki, and Kd. The error adjustment rate is controlled by Kp. Furthermore, it is proportional to the rate of change of the error, which is controlled by Kd. The deviation integral is adjusted by Ki. In the formula dif(t) = dif(t-1) + Δdif, dif(t) represents the current vagal nerve intensity level at time t, dif(t-1) represents the current vagal nerve intensity level at time t-1, and Δdif represents the difference between dif(t) and dif(t-1).

[0063] Vagus nerve stimulation ear clips are used to stimulate the percutaneous vagus nerve of the target user. One vagus nerve stimulation ear clip is placed in each ear. The vagus nerve stimulation ear clips are made of conductive silicone with a resistance of 10KΩ or higher. The paradigmatic characteristics of vagus nerve stimulation are the stimulation parameters.

[0064] The stimulation parameters include stimulation intensity, stimulation frequency, and stimulation duration. The frequency ranges from 0Hz to 100Hz, the duration ranges from 0min to 60min, and the stimulation intensity ranges from 0 to 100.

[0065] This invention aims to achieve "continuous" quantitative perception of mental states, requiring breakthroughs in the technology for effectively acquiring and continuously monitoring biometric information in the general population while wearing helmets, and to realize long-term effective acquisition of biometric information in natural settings. The EEG sensor is located inside the rear of the helmet.

[0066] The EEG acquisition module includes an EEG sensor located inside the rear of the helmet. The electrodes of the EEG sensor are contact-type flexible electrodes. The EEG sensor acquires data at the prefrontal cortex FP1, FP2, and FP2, with reference electrodes A1 and A2. Figure 5 As shown.

[0067] The present invention provides a helmet for regulating mental state, which also includes an audio playback module for outputting corresponding music based on the currently collected EEG signals.

[0068] The audio playback module stores different types of mental state regulation music, with different ranges of EEG signals corresponding to the same type of music. The audio intervention module plays these different types of music and can operate independently based on mental state assessment results or synchronously with the vagus nerve stimulation module. There are at least 10 audio types, with each playback lasting 0-30 minutes.

[0069] The helmet control system's CPU uses a RISC-V core neuromorphic chip. EEG signals are transmitted to the chip and preprocessed using a low-pass FIR filter with a cutoff frequency of 0-45Hz. Five features are then extracted: power spectrum (PSD), LZC complexity, alpha asymmetry, sample entropy, and Renyi entropy. Finally, an XGBoost model is used to establish a mental state assessment model. The main control CPU for the closed-loop vagus nerve stimulation module based on bio-information feedback uses a low-power STM32 microcontroller. The audio playback module is controlled by an STM32 chip and has a built-in replaceable SD memory card.

[0070] All modules are embedded inside the helmet, with only the power buttons for each module located on the outside. The smart helmet's mental state assessment module (signal analysis module), vagus nerve stimulation module, and audio playback module can operate independently or simultaneously. The audio playback of the audio stimulation module is located on the left and right sides of the helmet. The interfaces for the EEG acquisition module, vagus nerve module, and audio playback module are all inside the helmet and do not extend outwards in any way.

[0071] Through the aforementioned intelligent closed-loop "assessment-intervention-assessment" method, real-time biofeedback mental state assessment and intervention technology can be applied to real-life scenarios to achieve personalized and precise mental state assessment and intervention. This provides new theories, methods, and technologies for improving the effectiveness of special personnel and is an original method that integrates theories from multiple disciplines such as information science, brain science, cognitive psychology, and medical electronics.

[0072] The specific implementation steps of the helmet for regulating mental state according to the present invention are as follows.

[0073] The user activates the control system via a switch. The control system includes an EEG acquisition module, a signal analysis module, and a vagus nerve stimulation module. After initialization, the EEG acquisition sensor filters and amplifies the EEG signal in real time, sending it to a dedicated physiological computing chip for further temporal segmentation and quality assessment using Fast Fourier Transform (FFT). Once the EEG signal stabilizes, relevant parameters such as spectral features, alpha wave asymmetry, LZC complexity, and sample entropy are extracted and input into a mental state assessment model. The model outputs a mental state value and notifies the user via vibration. Based on the assessment results, the user wears the vagus nerve stimulation ear clip and activates the vagus nerve stimulation module. The vagus nerve stimulation module calculates the stimulation intensity (0-100), frequency (0-100Hz), and duration (0-60min) based on the assessment results and adaptively adjusts the module parameters dynamically based on real-time EEG characteristics. Simultaneously, an audio intervention module can be activated according to the specific scenario; the smart helmet plays music based on the current EEG signal and adjusts the music type in real-time according to the EEG signal. The audio playback module and the vagus nerve stimulation module can work independently or simultaneously. Through these steps, real-time monitoring and regulation of mental state can be achieved.

[0074] Figure 6 For example, a flowchart of the actual operation process. Figure 6 As shown, the user wears a smart helmet and activates the device according to the actual application scenario. It collects EEG signals and frontal lobe temperature information. The signal quality module assesses the EEG signal quality in real time for 0-2 minutes. After the signal quality stabilizes, the mental state assessment module activates. This module first collects 144 seconds of resting-state EEG signals, then collects 90 seconds of audio stimulation EEG signals. The mental state assessment module outputs a mental state value based on the collected data. Based on the assessment results, the system activates vibration and ringtone prompts. Following the prompts, the user selects to activate the mental state adjustment module, which includes audio adjustment and vagus nerve stimulation, and wears a vagus nerve stimulation ear clip. After activating the audio stimulation module, the system automatically recommends music based on the current mental state assessment results and monitors the EEG signals in real time, adjusting the music type accordingly. The audio adjustment module operates for 30 minutes at a time and can continuously operate for 2 hours. Simultaneously, after activating the vagus nerve stimulation module, the system provides initial vagus nerve stimulation parameters based on the mental state, namely stimulation frequency, stimulation intensity, and stimulation duration. The module then... Figure 4 The method shown adjusts the stimulation paradigm, with each adjustment lasting 0-60 minutes, to achieve refined and personalized mental state regulation.

[0075] The audio playback module includes an audio playback control unit and an audio playback unit. The audio playback control unit is used to control the audio playback unit to play music.

[0076] Figures 7-10 This is a schematic diagram showing the appearance and module distribution of a smart helmet system. Figure 7 This is a schematic diagram showing the placement of the main control module (EEG acquisition module, signal analysis module, vagus nerve stimulation module, and audio playback control unit). Figure 9 The diagram shows the placement of the audio playback unit and the vagus nerve stimulation ear clip, which is connected by a retractable wire and is embedded in the ear clip groove of the helmet by default. Figure 10 This is a schematic diagram of a flexible electrode, in which the three electrodes FP1, FP2 and FPz of the prefrontal cortex conform to the international 10-20 electrode placement rules. Figure 8 The diagram shows a switch, which is a push-button switch. A single press for 2 seconds turns the device on or off. Pressing it twice adjusts the operation of the vagus nerve stimulation module, and pressing it three times adjusts the operation of the audio playback module.

[0077] The various embodiments in this specification are described in a progressive manner, with each embodiment focusing on the differences from other embodiments. The same or similar parts between the various embodiments can be referred to each other.

[0078] This document uses specific examples to illustrate the principles and implementation methods of the present invention. The descriptions of the above embodiments are only for the purpose of helping to understand the device and core ideas of the present invention. Furthermore, those skilled in the art will recognize that, based on the ideas of the present invention, there will be changes in the specific implementation methods and application scope. Therefore, the content of this specification should not be construed as a limitation of the present invention.

Claims

1. A headgear for mental state regulation, characterized in that, The application relates to a headgear, a brain electrical signal acquisition module arranged on the headgear, a signal analysis module, a vagus nerve stimulation module and a vagus nerve stimulation ear clip. The brain electrical signal acquisition module is used for collecting brain electrical signals of a target user in real time and pre-processing the collected brain electrical signals; the brain electrical signal sensor is located at the back of the headgear, the electrode of the brain electrical signal sensor is a contact type flexible electrode, and the brain electrical signal sensor collects signals from the frontal lobe; The signal analysis module is used for extracting features from the pre-processed brain electrical signals and inputting the extracted brain electrical features into a mental state evaluation model to obtain a mental state value of the target user; the brain electrical features include frequency spectrum feature values, alpha brain wave asymmetry, LZC complexity and sample entropy; the mental state evaluation model is established by using an XGBoost model; The vagus nerve stimulation module is used for determining stimulation parameters of the vagus nerve stimulation ear clip according to the mental state value of the target user and dynamically adjusting the stimulation parameters in real time by acquiring brain electrical features in real time; the stimulation parameters include stimulation intensity, frequency and time, the frequency ranges from 0 Hz to 100 Hz, and the time ranges from 0 min to 60 min; The vagus nerve stimulation ear clip is used for stimulating the percutaneous auricular vagus nerve of the target user; The vagus nerve stimulation module comprises a PID control unit based on reinforcement learning, which is used for inputting brain electrical features obtained in real time and dynamically adjusting stimulation parameters in real time through the brain electrical features obtained in real time; the brain electrical features are taken as input, the probability distribution output by the machine learning model is taken as output, an XGBoost model is established to complete quantitative evaluation of the current mental state, wherein the probability distribution is the probability distribution of the brain electrical signals; the vagus nerve stimulation module is triggered to stimulate the auricular percutaneous vagus nerve, and the strength, duration and frequency stimulation parameters of the vagus nerve stimulation are dynamically and adaptively adjusted according to the quantitative evaluation result of the mental state; the feedback adjustment output result Y is controlled by the reinforcement learning model, the reinforcement learning model outputs the frequency, strength and stimulation duration parameters of the vagus nerve stimulation; the PID control vagus nerve stimulation adjustment scheme based on reinforcement learning firstly extracts the real-time individual mental state evaluation result as the input of the reinforcement learning model, the stimulation paradigm decision module provides the initialized vagus nerve stimulation parameters according to the input, meanwhile, the brain electrical features are extracted as feedback, and the reinforcement learning module dynamically controls the PID parameters according to the feature values to realize individualized and accurate adjustment; the specific feedback control algorithm process is as follows: (1) calculating the reinforcement learning target parameters: ​ ； wherein, represents a policy, represents a set of actions, represents a long-term optimized value of a state, represents an expectation, represents a number of states, i.e. optimization times, represents a discount rate of the th optimization, represents a reward of a state; (2) The control signal is generated by a control strategy satisfying: ​ ； wherein, represents an optimal value function, represents an optimization function; wherein, and is the state and control signal of the stimulation system at the next optimization, is the action value function; ； ； wherein, represents a reward function, represents an optimal action solved by a recursive method, represents a policy controller; (3) calculating by a neural network and wherein the input parameters of the neural network comprise the parameters of the policy controller, i.e. the stimulation intensity, frequency and time, as well as the reinforcement learning reward parameters and error parameters; (4) the final network outputs the parameters Kp, Ki and Kd of the control PID; wherein the speed of error adjustment is controlled by Kp; in addition, it is also proportional to the rate of change of error, and the rate of change of error adjustment is controlled by Kd; the deviation integral is adjusted by Ki, and dif(t) in the formula dif(t) = dif(t-1) + Adif represents the current vagus nerve intensity level at t, dif(t-1) represents the current vagus nerve intensity level at t-1, and Adif represents the difference between dif(t) and dif(t-1); The helmet for mental state adjustment also comprises an audio playing module, which is used for outputting corresponding music according to the current real-time collected electroencephalogram signals; the audio playing module comprises an audio playing control unit and an audio playing unit; the audio playing control unit is used for controlling the audio playing unit to play music; the audio playing module stores different types of mental state adjustment music, and different value ranges of electroencephalogram signals correspond to different types of mental state adjustment music; the number of audio types is not less than 10; All the modules are embedded into the helmet, and only the switch buttons of the modules are arranged outside the helmet; the signal analysis module, the vagus nerve stimulation module and the audio playing module of the helmet can work independently or simultaneously; the audio playing of the audio stimulation module is located on the left and right sides of the helmet, and the interfaces of the electroencephalogram collecting module, the vagus nerve stimulation module and the audio playing module are all inside the helmet and do not extend outward in any way; When the signal analysis module is turned on, the signal analysis module first collects 144s of resting-state electroencephalogram signals, and then collects 90s of audio stimulation electroencephalogram signals; the signal analysis module outputs the mental state value according to the collected data; according to the evaluation result, the system turns on the vibration prompt and the bell prompt; the user selects to turn on the mental state adjustment module according to the prompt, that is, to turn on the audio adjustment and the vagus nerve stimulation module, and to wear the vagus nerve stimulation ear clip; after the audio stimulation module is turned on, the system automatically recommends music according to the current mental state evaluation result, and adjusts the music type in real time by monitoring the electroencephalogram signals; at the same time, after the vagus nerve stimulation module is turned on, the system provides the initial vagus nerve stimulation parameters, that is, the stimulation frequency, the stimulation intensity and the stimulation duration, according to the mental state; then, the module adjusts the stimulation paradigm according to the PID control vagus nerve stimulation adjustment scheme based on reinforcement learning, so as to realize fine and personalized mental state adjustment.

2. The headgear for mental state conditioning according to claim 1, wherein, The electroencephalogram collecting module comprises a preprocessing unit; the preprocessing unit is used for sequentially filtering and amplifying the collected electroencephalogram signals to obtain the preprocessed electroencephalogram signals.

Images