Training system and method for improving adaptive capacity of staff in closed narrow environment

Abstract

The invention discloses a training system and method for improving the adaptive capacity of workers in a closed and narrow environment. The system comprises a closed and narrow environment simulation subsystem, an emotional state distribution prediction subsystem and an emotional state regulation and control subsystem. The closed narrow and small environment simulation subsystem is used for simulating a fear virtual-real combination scene, an anxiety virtual-real combination scene and a fatigue virtual-real combination scene in a closed narrow and small space; the emotional state distribution prediction subsystem is used for predicting the fear emotion proportion, the anxiety emotion proportion, the fatigue state proportion and the total emotional state intensity generated by the staff in the selected virtual-real combined scene; the emotional state regulation and control subsystem is used for selecting a targeted regulation and control mode according to the fear emotion proportion, the anxiety emotion proportion and the maximum value in the fatigue state proportion to carry out emotional state regulation and control; the emotional state regulation and control subsystem is further used for judging whether training is stopped or not according to the total emotional state intensity. According to the system, the adaptive capacity of workers in a closed narrow environment can be remarkably improved.

Description

Technical Field

[0001] The present invention relates to the technical field of human factor engineering, and more particularly to a training system and method for improving the adaptability of workers to a closed and narrow environment. Background Art

[0002] At present, special occupations (such as astronauts, divers, etc.) face challenges such as a single environment, narrow and closed areas, and restricted personnel activities. First-time operations are prone to fear, and long-term operations may lead to increased individual anxiety levels and decreased arousal levels, which in turn affects work performance. In severe cases, it may endanger personal and public life and property safety.

[0003] Therefore, how to provide a system and method that can improve the adaptability of workers in a closed and narrow environment is an urgent problem that technical personnel in this field need to solve. Summary of the invention

[0004] In view of this, an object of the present invention is to provide a training system and method for improving the adaptability of workers to closed and narrow environments.

[0005] In order to achieve the above object, the present invention adopts the following technical solution:

[0006] On the one hand, a training system for improving the adaptability of workers to a closed and narrow environment is provided, comprising a closed and narrow environment simulation subsystem, an emotional state distribution prediction subsystem, and an emotional state regulation subsystem;

[0007] The closed and narrow environment simulation subsystem is used to simulate the real and virtual combination scene of fear, the real and virtual combination scene of anxiety and the real and virtual combination scene of fatigue in a closed and narrow space;

[0008] The emotional state distribution prediction subsystem is used to predict the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene, wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity; the selected virtual-real combination scene is one of the fear virtual-real combination scene, the anxiety virtual-real combination scene and the fatigue virtual-real combination scene;

[0009] The emotional state regulation subsystem is used to select a targeted emotional state regulation method to regulate the emotional state according to the maximum value among the fear emotion proportion, the anxiety emotion proportion and the fatigue state proportion;

[0010] The emotional state regulation subsystem is also used to determine whether to stop training according to the overall emotional state intensity.

[0011] Preferably, the closed and narrow environment simulation subsystem includes a physical cabin, a fear virtual reality module, an anxiety virtual reality module and a fatigue virtual reality module;

[0012] The physical cabin and the fear virtual reality module are used together to simulate a fear virtual-real combination scene in a confined and narrow space;

[0013] The physical cabin and the anxiety virtual reality module are used together to simulate an anxiety virtual-real combination scene in a confined and narrow space;

[0014] The physical cabin and the fatigue virtual reality module are used together to simulate a fatigue virtual-reality combined scene in a confined and narrow space.

[0015] Preferably, the emotional state distribution prediction subsystem includes a peripheral physiological data acquisition module, a peripheral physiological data preprocessing module, a feature extraction module, and an emotional state distribution and total intensity prediction module;

[0016] The peripheral physiological data acquisition module is used to collect peripheral physiological data generated by the staff in the selected virtual-real combination scene; wherein the peripheral physiological data includes pulse wave data and skin electricity data;

[0017] The peripheral physiological data preprocessing module is used to remove noise data in the peripheral physiological data and improve its signal-to-noise ratio;

[0018] The feature extraction module is used to extract heart rate, heart rate variability, low-frequency power spectrum density, high-frequency power spectrum density and total energy from the pre-processed pulse wave data;

[0019] The feature extraction module is also used to extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response in the preprocessed skin conductance data;

[0020] The feature extraction module is also used to extract the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level in the preprocessed skin electrical data;

[0021] The emotional state distribution and total intensity prediction module is used to input the features extracted by the feature extraction module into the trained emotional state distribution learning model to obtain the proportion of fear, anxiety, fatigue and total emotional state intensity generated by the staff in the selected virtual-real combination scenario.

[0022] Preferably, the emotional state regulation subsystem includes an emotional state regulation method selection module;

[0023] The emotional state regulation method selection module is used to screen out the maximum values ​​among the fear emotion proportion, the anxiety emotion proportion, and the fatigue state proportion, and select the corresponding emotional state regulation module to perform emotional state regulation based on the emotional state corresponding to the maximum value; wherein, if the fear emotion proportion is the largest, the fear emotion regulation module is selected to perform fear emotion regulation on the staff; if the anxiety emotion proportion is the largest, the anxiety emotion regulation module is selected to perform anxiety emotion regulation on the staff; if the fatigue state proportion is the largest, the fatigue state regulation module is selected to perform fatigue state regulation on the staff.

[0024] Preferably, the emotional state regulation subsystem further includes a fear emotion regulation module, an anxiety emotion regulation module and a fatigue state regulation module;

[0025] The fear emotion regulation module is used to regulate the fear emotions of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy combined with mindfulness;

[0026] The anxiety regulation module is used to regulate the anxiety of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on natural therapy;

[0027] The fatigue state control module is used to control the fatigue state of the staff, specifically using music + transcutaneous ear vagus nerve electrical stimulation that matches the intensity of the music pitch changes.

[0028] Preferably, the emotional state regulation subsystem further includes a module for determining whether to terminate;

[0029] The module for determining whether to terminate is used to determine whether to stop training according to the total emotional state intensity, specifically: if the total emotional state intensity is less than a preset threshold, the training is stopped.

[0030] Preferably, the trained emotional state distribution learning model adopts AA-BP, AA-kNN, PT-Bayes, PT-SVM, SA-IIS or SA-CPNN algorithm.

[0031] On the other hand, a training method for improving the adaptability of workers to a confined and narrow environment is provided, comprising the following steps:

[0032] S1: Acquire peripheral physiological data generated by the staff in a selected virtual-real combination scenario; wherein the peripheral physiological data includes pulse wave data and skin electrical data; the selected virtual-real combination scenario is one of a fear virtual-real combination scenario, an anxiety virtual-real combination scenario, and a fatigue virtual-real combination scenario;

[0033] S2: removing noise data from the peripheral physiological data and improving its signal-to-noise ratio;

[0034] S3: extracting heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy from the preprocessed pulse wave data;

[0035] Extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response from the preprocessed skin electrical data;

[0036] Extracting the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level from the preprocessed skin electrical data;

[0037] S4: Input the data extracted in S3 into the trained emotional state distribution learning model to obtain the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene; wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity;

[0038] S5: Determine whether the total emotional state intensity is less than a preset threshold, if less than, stop training, if greater than, execute S6;

[0039] S6: Screening out the maximum value among the fear emotion proportion, anxiety emotion proportion, and fatigue state proportion, and selecting a corresponding emotion state regulation method to regulate the emotion state based on the emotion state corresponding to the maximum value;

[0040] S7: Repeat S1-S6 until the training is stopped.

[0041] Preferably, the fear virtual reality combined scene is provided by a physical cabin and a fear virtual reality module; wherein the staff is in the physical cabin, and the fear virtual reality module is used to provide the fear virtual reality scene;

[0042] The anxiety virtual-reality combined scene is provided by a physical cabin and an anxiety virtual reality module; wherein the staff is in the physical cabin, and the anxiety virtual reality module is used to provide the anxiety virtual reality scene;

[0043] The fatigue virtual-reality combined scene is provided by a physical cabin and a fatigue virtual reality module; wherein the staff is in the physical cabin, and the fatigue virtual reality module is used to provide a fatigue virtual reality scene.

[0044] Preferably, S6 specifically includes:

[0045] If the fear emotion accounts for the largest proportion, earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy and mindfulness will be selected to regulate the fear emotion of the staff;

[0046] If the anxiety accounts for the largest proportion, earlobe electrical stimulation + natural therapy-based virtual reality intervention scenario is selected to regulate the anxiety of the staff;

[0047] If the fatigue state accounts for the largest proportion, music + transcutaneous auricular vagus nerve stimulation that matches the intensity of the music pitch changes is selected to regulate the fatigue state of the staff.

[0048] It can be seen from the above technical solutions that, compared with the prior art, the present invention discloses a training system and method for improving the adaptability of workers in a closed and narrow environment, which can significantly improve the adaptability of workers in a closed and narrow environment. BRIEF DESCRIPTION OF THE DRAWINGS

[0049] In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are only embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on the provided drawings without paying creative work.

[0050] Figure 1 A schematic diagram of a training system provided by the present invention for improving the adaptability of workers to a closed and narrow environment;

[0051] Figure 2 The figure is a practical effect diagram of the method of the present invention. DETAILED DESCRIPTION

[0052] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions 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.

[0053] On the one hand, if Figure 1 As shown, the embodiment of the present invention discloses a training system for improving the adaptability of workers to a closed and narrow environment, including a closed and narrow environment simulation subsystem, an emotional state distribution prediction subsystem and an emotional state regulation subsystem;

[0054] It can be understood that the staff mentioned in the present invention refers to personnel who need to work in a closed and narrow environment and need training to improve their adaptability in the closed and narrow environment.

[0055] The closed and narrow environment simulation subsystem is used to simulate the real and virtual combination scene of fear, the real and virtual combination scene of anxiety and the real and virtual combination scene of fatigue in a closed and narrow space;

[0056] The emotional state distribution prediction subsystem is used to predict the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene, wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity; the selected virtual-real combination scene is one of the fear virtual-real combination scene, the anxiety virtual-real combination scene and the fatigue virtual-real combination scene;

[0057] The emotional state regulation subsystem is used to select a targeted emotional state regulation method to regulate the emotional state according to the maximum value among the fear emotion proportion, the anxiety emotion proportion and the fatigue state proportion;

[0058] The emotional state regulation subsystem is also used to determine whether to stop training according to the overall emotional state intensity.

[0059] In one embodiment, the closed and narrow environment simulation subsystem includes a physical cabin, a fear virtual reality module, an anxiety virtual reality module, and a fatigue virtual reality module;

[0060] The physical cabin and the fear virtual reality module are used together to simulate a fear virtual-real combination scene in a confined and narrow space;

[0061] The physical cabin and the anxiety virtual reality module are used together to simulate an anxiety virtual-real combination scene in a confined and narrow space;

[0062] The physical cabin and the fatigue virtual reality module are used together to simulate a fatigue virtual-reality combined scene in a confined and narrow space.

[0063] It is understandable that: the combination of fear and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person; the combination of anxiety and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person; the combination of fatigue and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person;

[0064] In this embodiment: the physical cabin includes a main cabin, a lifting bracket and a conveyor slide vehicle. The main cabin will cooperate with the virtual reality module to induce the emotional state of the staff: an emergency door opening button and a surveillance camera are set in the cabin to ensure the safety of the staff in the main cabin. At the same time, a two-way voice communication system is installed inside and outside the cabin to facilitate the staff in the main cabin to communicate with the outside world; a wiring pipeline is set on the side wall of the main cabin to connect the external emotional state regulation subsystem and the emotional state distribution prediction subsystem; a particle filling funnel is set above the main cabin for throwing landfill particles in the experiment, and cooperates with the virtual reality module to simulate the situation of individuals being buried when a typical dangerous situation occurs; a touch screen display is set outside the main cabin, which can control the opening and closing of the door above the cabin and the lifting and lowering of the main cabin through the display screen, and detect the oxygen content in the cabin and the cabin operation status.

[0065] In this embodiment: the fear virtual reality module specifically simulates the following virtual reality scenes: the environment is set to dark and cold colors, the wall graphics are sharp, and horror elements such as mice, spiders and snakes randomly fall from the ventilation duct opening directly above the field of vision. Spider webs are hung on the wall, and spiders crawl back and forth, and horror sound effects are matched. The time and type of the appearance of the fear element can be called up and viewed in the system;

[0066] In this embodiment: the anxiety virtual reality module specifically simulates the following virtual reality scenes: simulates the scene of cabin collapse and oxygen content gradually decreasing. First, the wall in the scene cracks, followed by soil and gravel flying out, and electric sparks appear from time to time on the wires above the head; stones falling from above appear in the field of vision, and the stones slowly accumulate, gradually burying the human body, and dust is everywhere; the ventilation window on the right side of the field of vision is also gradually blocked, accompanied by the decrease of the oxygen progress bar above the field of vision; when the oxygen content reaches 20%, it reaches a dangerous value, the oxygen progress bar turns red, and a sound alarm is triggered;

[0067] In this embodiment: the fatigue virtual reality module specifically simulates the following virtual reality scene: the environment is set to soft warm colors, the wall graphics are rounded and blurred, a dim warm-toned light is set in the lower left corner of the individual's field of vision, brightening and dimming at a lower frequency, accompanied by soft hypnotic background sound effects.

[0068] In one embodiment, the emotional state distribution prediction subsystem includes a peripheral physiological data acquisition module, a peripheral physiological data preprocessing module, a feature extraction module, and an emotional state distribution and total intensity prediction module;

[0069] The peripheral physiological data acquisition module is used to collect peripheral physiological data generated by the staff in the selected virtual-real combination scene; wherein the peripheral physiological data includes pulse wave data and skin electricity data;

[0070] In this embodiment, skin electrical data is collected through surface electrodes at a sampling rate of 40Hz and a resolution of 0.01μs; pulse wave data is accurately collected by using photoplethysmography, that is, using green light with a wavelength of 532nm and measuring reflected light at a sampling rate of 20Hz. The present invention specifically collects peripheral physiological data within the first three minutes after the staff is in the selected virtual-real combination scene. The pulse wave data finally obtained based on the set adoption rate is a pulse wave time series, and the skin electrical data is a skin electrical time series.

[0071] The peripheral physiological data preprocessing module is used to remove noise data in the peripheral physiological data and improve its signal-to-noise ratio;

[0072] In this embodiment, maximum entropy independent component analysis and principal component analysis are used to remove noise data in the peripheral physiological data, and the signal-to-noise ratio of the peripheral physiological data is improved through adaptive filtering and Bayesian learning physiological signal denoising to enhance useful physiological signal components.

[0073] The feature extraction module is used to extract heart rate, heart rate variability, low-frequency power spectrum density, high-frequency power spectrum density and total energy from the pre-processed pulse wave data;

[0074] The feature extraction module is also used to extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response in the preprocessed skin conductance data;

[0075] The feature extraction module is also used to extract the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level in the preprocessed skin electrical data;

[0076] The emotional state distribution and total intensity prediction module is used to input the features extracted by the feature extraction module into the trained emotional state distribution learning model to obtain the proportion of fear, anxiety, fatigue and total emotional state intensity generated by the staff in the selected virtual-real combination scenario.

[0077] In this embodiment, the trained emotional state distribution learning model is obtained based on the following steps:

[0078] Step 1: Obtain the score of the jth emotional state of the ith subject in the xth stage (It should be noted that the emotional state score is the emotional state intensity described in the present invention); and the pulse wave data of the i-th subject in the x-th stage and skin electrical data Where m and n represent the number of samples taken within three minutes;

[0079] It can be understood that: x=1, 2, 3; when x=1, it indicates the stage before the induction of the emotional state, that is, the stage before the emotional state is induced by the selected combination of virtual and real scenes; when x=2, it indicates the stage after the induction of the emotional state, that is, the stage after the emotional state is induced by the selected combination of virtual and real scenes; when x=3, it indicates the stage after the emotional state is regulated; j=1, 2, 3; when j=1, it indicates fear; when j=2, it indicates anxiety; when j=3, it indicates fatigue.

[0080] Step 2: Calculate the proportion of fear emotion of the i-th subject in the x-th stage Anxiety ratio Fatigue status ratio and total emotional state intensity

[0081] Remove pulse wave data and skin electrical data Noisy data in the image and improve its signal-to-noise ratio;

[0082] Extract preprocessed pulse wave data Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density, and total energy in;

[0083] Specific: Extract pre-processed pulse wave data Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy in; obtain features

[0084]

[0085] in, After preprocessing Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy in.

[0086] Extract preprocessed skin electrical data The mean of the skin conductance response, the standard deviation of the skin conductance response, the maximum of the skin conductance response, the minimum of the skin conductance response, the first-order difference of the mean of the skin conductance response, the second-order difference of the mean of the skin conductance response, and the first-order derivative of the mean of the skin conductance response; obtain the features

[0087]

[0088] in, After preprocessing The mean of the skin conductance response, the standard deviation of the skin conductance response, the maximum of the skin conductance response, the minimum of the skin conductance response, the first difference of the mean of the skin conductance response, the second difference of the mean of the skin conductance response, the first derivative of the mean of the skin conductance response.

[0089] Extract preprocessed skin electrical data The mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level are obtained; the features are obtained.

[0090]

[0091] in, After preprocessing The mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first difference of the mean of the skin conductivity level, the second difference of the mean of the skin conductivity level, the first derivative of the mean of the skin conductivity level.

[0092] Step 3: Place {F i PPG 、F i GSR1 、F i GSR2} as input data, As labels, the emotional state distribution learning model is trained. During the training process, the model predicts the output data to be minimized. and tags The distance between the two is used to update the network parameters of the emotional state distribution learning model to obtain a trained emotional state distribution learning model.

[0093] In one embodiment, the emotional state regulation subsystem includes an emotional state regulation method selection module;

[0094] The emotional state regulation method selection module is used to screen out the maximum values ​​among the fear emotion proportion, the anxiety emotion proportion, and the fatigue state proportion, and select the corresponding emotional state regulation module to perform emotional state regulation based on the emotional state corresponding to the maximum value; wherein, if the fear emotion proportion is the largest, the fear emotion regulation module is selected to perform fear emotion regulation on the staff; if the anxiety emotion proportion is the largest, the anxiety emotion regulation module is selected to perform anxiety emotion regulation on the staff; if the fatigue state proportion is the largest, the fatigue state regulation module is selected to perform fatigue state regulation on the staff.

[0095] In one embodiment, the emotional state regulation subsystem further includes a fear emotion regulation module, an anxiety emotion regulation module and a fatigue state regulation module;

[0096] The fear emotion regulation module is used to regulate the fear emotions of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy combined with mindfulness;

[0097] Specific:

[0098] Earlobe electrical stimulation: The frequency of electrical stimulation is 25 Hz, and the pulse width intensity is 250 μs. The intensity of stimulation needs to be adjusted according to individual sensitivity. The intensity is measured by the limit method with a score of 4 (0 means no feeling, 5 means starting to feel pain, and 10 means the maximum pain imaginable). Virtual reality intervention scene: When triggered, the hatch above the physical cabin and its corresponding virtual scene position slide open, and the environment below and on the side walls of the individual's field of vision remain unchanged, so that they do not leave the emotion-inducing environment; this intervention scene uses the forest as the main background, accompanied by the sound of wind blowing through the leaves, the sound of birds singing, and the sound of streams. At the same time, through the guidance language, the individual is guided to conduct mindfulness training, guide the individual to relax the whole body, guide the individual's breathing rhythm, and give positive psychological hints, such as "I am proud and proud of my persistence", "I have a unique inner strength" and "I will face the challenges of life bravely".

[0099] The anxiety regulation module is used to regulate the anxiety of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on natural therapy;

[0100] Specific:

[0101] Earlobe electrical stimulation: The stimulation frequency is 25 Hz, and the pulse width is 250 μs. The stimulation intensity needs to be adjusted according to individual sensitivity. The limit method is used to determine the intensity with a score of 4 (0 means no feeling, 5 means starting to feel pain, and 10 means the maximum pain imaginable). Virtual reality intervention scene: When triggered, the hatch above the physical cabin and its corresponding virtual scene position slide open, and the environment below and on the side walls of the individual's field of vision remain unchanged, so that they do not leave the emotion-inducing environment; this intervention scene uses the beach as the main background, with a warm overall color tone, blue waves below the field of vision, and a vast blue sky above the field of vision, accompanied by the sound of waves rushing to the beach, the sound of seabirds singing, and the sound of sea breeze blowing through branches and leaves.

[0102] The fatigue state control module is used to control the fatigue state of the staff, specifically using music + transcutaneous ear vagus nerve electrical stimulation that matches the intensity of the music pitch changes.

[0103] Specific:

[0104] The music in the present invention is selected from military songs. Music amplitude extraction: The audio file is converted into vector data and short-time Fourier transform is performed to obtain the frequency of the audio at different time points, and different pitch intervals are divided according to the frequency, and the average amplitude and phase difference are calculated, and the amplitude of each pitch interval calculated is adjusted according to the loudness curve. The power threshold is determined using the cumulative distribution function to filter out background noise or irrelevant signals. The total power at each time point is calculated. A time series is generated, and each time point corresponds to the frequency and amplitude intensity of the audio at this moment. Transcutaneous ear vagus nerve electrical stimulation: The electrical stimulation frequency is 25Hz, and the stimulation pulse width intensity is 250μs; the stimulation intensity is first determined by the limit method with a stimulation intensity of 4 points (0 points for no feeling, 5 points for beginning to feel pain, and 10 points for the maximum pain imaginable), and secondly, the amplitude intensity in the previously converted audio time period information is compressed to between 0-1, and the final stimulation intensity received by the individual is the sum of the stimulation intensity of 4 points plus the stimulation intensity array converted by music.

[0105] In one embodiment, the emotional state regulation subsystem further includes a module for determining whether to terminate;

[0106] The module for determining whether to terminate is used to determine whether to stop training according to the total emotional state intensity, specifically: if the total emotional state intensity is less than a preset threshold, the training is stopped.

[0107] In one embodiment, the trained emotional state distribution learning model adopts AA-BP, AA-kNN, PT-Bayes, PT-SVM, SA-IIS or SA-CPNN algorithm.

[0108] On the other hand, an embodiment of the present invention discloses a training method for improving the adaptability of workers to a closed and narrow environment, comprising the following steps:

[0109] S1: Acquire peripheral physiological data generated by the staff in a selected virtual-real combination scenario; wherein the peripheral physiological data includes pulse wave data and skin electrical data; the selected virtual-real combination scenario is one of a fear virtual-real combination scenario, an anxiety virtual-real combination scenario, and a fatigue virtual-real combination scenario;

[0110] It can be understood that the staff mentioned in the present invention refers to personnel who need to work in a closed and narrow environment and need training to improve their adaptability in the closed and narrow environment.

[0111] In this embodiment, skin electrical data is collected through surface electrodes at a sampling rate of 40Hz and a resolution of 0.01μs; pulse wave data is accurately collected by using photoplethysmography, that is, using green light with a wavelength of 532nm and measuring reflected light at a sampling rate of 20Hz. The present invention specifically collects peripheral physiological data within the first three minutes after the staff is in the selected virtual-real combination scene. The pulse wave data finally obtained based on the set adoption rate is a pulse wave time series, and the skin electrical data is a skin electrical time series.

[0112] S2: removing noise data from the peripheral physiological data and improving its signal-to-noise ratio;

[0113] In this embodiment, maximum entropy independent component analysis and principal component analysis are used to remove noise data in the peripheral physiological data, and the signal-to-noise ratio of the peripheral physiological data is improved through adaptive filtering and Bayesian learning physiological signal denoising to enhance useful physiological signal components.

[0114] S3: extracting heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy from the preprocessed pulse wave data;

[0115] Extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response from the preprocessed skin electrical data;

[0116] Extracting the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level from the preprocessed skin electrical data;

[0117] S4: Input the data extracted in S3 into the trained emotional state distribution learning model to obtain the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene; wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity;

[0118] In this embodiment, the trained emotional state distribution learning model is obtained based on the following steps:

[0119] Step 1: Obtain the score of the jth emotional state of the ith subject in the xth stage (It should be noted that the emotional state score is the emotional state intensity described in the present invention); and the pulse wave data of the i-th subject in the x-th stage and skin electrical data Where m and n represent the number of samples taken within three minutes;

[0120] It can be understood that: x=1, 2, 3; when x=1, it indicates the stage before the induction of the emotional state, that is, the stage before the emotional state is induced by the selected combination of virtual and real scenes; when x=2, it indicates the stage after the induction of the emotional state, that is, the stage after the emotional state is induced by the selected combination of virtual and real scenes; when x=3, it indicates the stage after the emotional state is regulated; j=1, 2, 3; when j=1, it indicates fear; when j=2, it indicates anxiety; when j=3, it indicates fatigue.

[0121] Step 2: Calculate the proportion of fear emotion of the i-th subject in the x-th stage Anxiety ratio Fatigue status ratio and total emotional state intensity

[0122] Remove pulse wave data and skin electrical data Noisy data in the image and improve its signal-to-noise ratio;

[0123] Extract preprocessed pulse wave data Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density, and total energy in;

[0124] Specific: Extract pre-processed pulse wave data Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy in; obtain features

[0125]

[0126] in, After preprocessing Heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy in.

[0127] Extract preprocessed skin electrical data The mean of the skin conductance response, the standard deviation of the skin conductance response, the maximum of the skin conductance response, the minimum of the skin conductance response, the first-order difference of the mean of the skin conductance response, the second-order difference of the mean of the skin conductance response, and the first-order derivative of the mean of the skin conductance response; obtain the features

[0128]

[0129] in, After preprocessing The mean of the skin conductance response, the standard deviation of the skin conductance response, the maximum of the skin conductance response, the minimum of the skin conductance response, the first difference of the mean of the skin conductance response, the second difference of the mean of the skin conductance response, the first derivative of the mean of the skin conductance response.

[0130] Extract preprocessed skin electrical data The mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level are obtained; the features are obtained.

[0131]

[0132] in, After preprocessing The mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first difference of the mean of the skin conductivity level, the second difference of the mean of the skin conductivity level, the first derivative of the mean of the skin conductivity level.

[0133] Step 3: Place {F i PPG 、F i GSR1 、F i GSR2} as input data, As labels, the emotional state distribution learning model is trained. During the training process, the model predicts the output data to be minimized. and tags The distance between the two is used to update the network parameters of the emotional state distribution learning model to obtain a trained emotional state distribution learning model.

[0134] S5: Determine whether the total emotional state intensity is less than a preset threshold, if less than, stop training, if greater than, execute S6;

[0135] S6: Screening out the maximum value among the fear emotion proportion, anxiety emotion proportion, and fatigue state proportion, and selecting a corresponding emotion state regulation method to regulate the emotion state based on the emotion state corresponding to the maximum value;

[0136] S7: Repeat S1-S6 until the training is stopped.

[0137] In one embodiment, the fear virtual reality combined scene is provided by a physical cabin and a fear virtual reality module; wherein the staff is in the physical cabin, and the fear virtual reality module is used to provide the fear virtual reality scene;

[0138] The anxiety virtual-reality combined scene is provided by a physical cabin and an anxiety virtual reality module; wherein the staff is in the physical cabin, and the anxiety virtual reality module is used to provide the anxiety virtual reality scene;

[0139] The fatigue virtual-reality combined scene is provided by a physical cabin and a fatigue virtual reality module; wherein the staff is in the physical cabin, and the fatigue virtual reality module is used to provide a fatigue virtual reality scene.

[0140] It is understandable that: the combination of fear and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person; the combination of anxiety and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person; the combination of fatigue and reality can simultaneously induce fear, anxiety and fatigue, and the proportion of the three emotional states varies from person to person;

[0141] In this embodiment: the physical cabin includes a main cabin, a lifting bracket and a conveyor slide vehicle. The main cabin will cooperate with the virtual reality module to induce the emotional state of the staff: an emergency door opening button and a surveillance camera are set in the cabin to ensure the safety of the staff in the main cabin. At the same time, a two-way voice communication system is installed inside and outside the cabin to facilitate the staff in the main cabin to communicate with the outside world; a wiring pipeline is set on the side wall of the main cabin to connect the external emotional state regulation subsystem and the emotional state distribution prediction subsystem; a particle filling funnel is set above the main cabin for throwing landfill particles in the experiment, and cooperate with the virtual scene to induce the feeling of being buried in the individual; a touch screen display is set outside the main cabin, which can control the opening and closing of the door above the cabin and the lifting of the main cabin through the display screen, and detect the oxygen content in the cabin and the operation status of the cabin.

[0142] In this embodiment: the fear virtual reality module specifically simulates the following virtual reality scenes: the environment is set to dark and cold colors, the wall graphics are sharp, and horror elements such as mice, spiders and snakes randomly fall from the ventilation duct opening directly above the field of vision. Spider webs are hung on the wall, and spiders crawl back and forth, and horror sound effects are matched. The time and type of the appearance of the fear element can be called up and viewed in the system;

[0143] In this embodiment: the anxiety virtual reality module specifically simulates the following virtual reality scenes: simulates the scene of cabin collapse and oxygen content gradually decreasing. First, the wall in the scene cracks, followed by soil and gravel flying out, and electric sparks appear from time to time on the wires above the head; stones falling from above appear in the field of vision, and the stones slowly accumulate, gradually burying the human body, and dust is everywhere; the ventilation window on the right side of the field of vision is also gradually blocked, accompanied by the decrease of the oxygen progress bar above the field of vision; when the oxygen content reaches 20%, it reaches a dangerous value, the oxygen progress bar turns red, and a sound alarm is triggered;

[0144] In this embodiment: the fatigue virtual reality module specifically simulates the following virtual reality scene: the environment is set to soft warm colors, the wall graphics are rounded and blurred, a dim warm-toned light is set in the lower left corner of the individual's field of vision, brightening and dimming at a lower frequency, accompanied by soft hypnotic background sound effects.

[0145] In one embodiment, S6 specifically includes:

[0146] If the fear emotion accounts for the largest proportion, earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy and mindfulness will be selected to regulate the fear emotion of the staff;

[0147] Specific:

[0148] Earlobe electrical stimulation: The frequency of electrical stimulation is 25 Hz, and the pulse width intensity is 250 μs. The intensity of stimulation needs to be adjusted according to individual sensitivity. The intensity is measured by the limit method with a score of 4 (0 means no feeling, 5 means starting to feel pain, and 10 means the maximum pain imaginable). Virtual reality intervention scene: When triggered, the hatch above the physical cabin and its corresponding virtual scene position slide open, and the environment below and on the side walls of the individual's field of vision remain unchanged, so that they do not leave the emotion-inducing environment; this intervention scene uses the forest as the main background, accompanied by the sound of wind blowing through the leaves, the sound of birds singing, and the sound of streams. At the same time, through the guidance language, the individual is guided to conduct mindfulness training, guide the individual to relax the whole body, guide the individual's breathing rhythm, and give positive psychological hints, such as "I am proud and proud of my persistence", "I have a unique inner strength" and "I will face the challenges of life bravely".

[0149] If the anxiety accounts for the largest proportion, earlobe electrical stimulation + natural therapy-based virtual reality intervention scenario is selected to regulate the anxiety of the staff;

[0150] Specific:

[0151] Earlobe electrical stimulation: The stimulation frequency is 25 Hz, and the pulse width is 250 μs. The stimulation intensity needs to be adjusted according to individual sensitivity. The limit method is used to determine the intensity with a score of 4 (0 means no feeling, 5 means starting to feel pain, and 10 means the maximum pain imaginable). Virtual reality intervention scene: When triggered, the hatch above the physical cabin and its corresponding virtual scene position slide open, and the environment below and on the side walls of the individual's field of vision remain unchanged, so that they do not leave the emotion-inducing environment; this intervention scene uses the beach as the main background, with a warm overall color tone, blue waves below the field of vision, and a vast blue sky above the field of vision, accompanied by the sound of waves rushing to the beach, the sound of seabirds singing, and the sound of sea breeze blowing through branches and leaves.

[0152] If the fatigue state accounts for the largest proportion, music + transcutaneous auricular vagus nerve stimulation that matches the intensity of the music pitch changes is selected to regulate the fatigue state of the staff.

[0153] Specific:

[0154] The music in the present invention is selected from military songs. Music amplitude extraction: The audio file is converted into vector data and short-time Fourier transform is performed to obtain the frequency of the audio at different time points, and different pitch intervals are divided according to the frequency, and the average amplitude and phase difference are calculated, and the amplitude of each pitch interval calculated is adjusted according to the loudness curve. The power threshold is determined using the cumulative distribution function to filter out background noise or irrelevant signals. The total power at each time point is calculated. A time series is generated, and each time point corresponds to the frequency and amplitude intensity of the audio at this moment. Transcutaneous ear vagus nerve electrical stimulation: The electrical stimulation frequency is 25Hz, and the stimulation pulse width intensity is 250μs; the stimulation intensity is first determined by the limit method with a stimulation intensity of 4 points (0 points for no feeling, 5 points for beginning to feel pain, and 10 points for the maximum pain imaginable), and secondly, the amplitude intensity in the previously converted audio time period information is compressed to between 0-1, and the final stimulation intensity received by the individual is the sum of the stimulation intensity of 4 points plus the stimulation intensity array converted by music.

[0155] In one embodiment, the trained emotional state distribution learning model adopts AA-BP, AA-kNN, PT-Bayes, PT-SVM, SA-IIS or SA-CPNN algorithm.

[0156] like Figure 2As shown, it provides the actual effect effect diagram of the method of the present invention. Figure A shows the anxiety score before and after anxiety regulation; Figure B shows the fear score before and after fear regulation; Figure C shows the fatigue score before and after fatigue regulation. It can be seen that the present invention can significantly improve the adaptability of workers in a closed and narrow environment.

[0157] In this specification, each embodiment is described in a progressive manner, and each embodiment focuses on the differences from other embodiments. The same or similar parts between the embodiments can be referred to each other. For the device disclosed in the embodiment, since it corresponds to the method disclosed in the embodiment, the description is relatively simple, and the relevant parts can be referred to the method part.

[0158] The above description of the disclosed embodiments enables one skilled in the art to implement or use the present invention. Various modifications to these embodiments will be apparent to one skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of the present invention. Therefore, the present invention will not be limited to the embodiments shown herein, but rather to the widest scope consistent with the principles and novel features disclosed herein.

Claims

1. A training system for improving workers' adaptability to confined and narrow environments, characterized in that: It includes a closed and narrow environment simulation subsystem, an emotional state distribution prediction subsystem, and an emotional state regulation subsystem; The closed and narrow environment simulation subsystem is used to simulate the real and virtual combination scene of fear, the real and virtual combination scene of anxiety and the real and virtual combination scene of fatigue in a closed and narrow space; The emotional state distribution prediction subsystem is used to predict the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene, wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity; the selected virtual-real combination scene is one of the fear virtual-real combination scene, the anxiety virtual-real combination scene and the fatigue virtual-real combination scene; The emotional state regulation subsystem is used to select a targeted emotional state regulation method to regulate the emotional state according to the maximum value among the fear emotion proportion, the anxiety emotion proportion and the fatigue state proportion; The emotional state regulation subsystem is also used to determine whether to stop training according to the overall emotional state intensity.

2. A training system for improving workers' adaptability to a closed and narrow environment according to claim 1, characterized in that: The closed and narrow environment simulation subsystem includes a physical cabin, a fear virtual reality module, an anxiety virtual reality module and a fatigue virtual reality module; The physical cabin and the fear virtual reality module are used together to simulate a fear virtual-real combination scene in a confined and narrow space; The physical cabin and the anxiety virtual reality module are used together to simulate an anxiety virtual-real combination scene in a confined and narrow space; The physical cabin and the fatigue virtual reality module are used together to simulate a fatigue virtual-reality combined scene in a confined and narrow space.

3. A training system for improving workers' adaptability to a closed and narrow environment according to claim 1, characterized in that: The emotional state distribution prediction subsystem includes a peripheral physiological data acquisition module, a peripheral physiological data preprocessing module, a feature extraction module, and an emotional state distribution and total intensity prediction module; The peripheral physiological data acquisition module is used to collect peripheral physiological data generated by the staff in the selected virtual-real combination scene; wherein the peripheral physiological data includes pulse wave data and skin electricity data; The peripheral physiological data preprocessing module is used to remove noise data in the peripheral physiological data and improve its signal-to-noise ratio; The feature extraction module is used to extract heart rate, heart rate variability, low-frequency power spectrum density, high-frequency power spectrum density and total energy from the pre-processed pulse wave data; The feature extraction module is also used to extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response in the preprocessed skin conductance data; The feature extraction module is also used to extract the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level in the preprocessed skin electrical data; The emotional state distribution and total intensity prediction module is used to input the features extracted by the feature extraction module into the trained emotional state distribution learning model to obtain the proportion of fear, anxiety, fatigue and total emotional state intensity generated by the staff in the selected virtual-real combination scenario.

4. A training system for improving workers' adaptability to a closed and narrow environment according to claim 1, characterized in that: The emotional state regulation subsystem includes an emotional state regulation method selection module; The emotional state regulation method selection module is used to screen out the maximum values ​​among the fear emotion proportion, the anxiety emotion proportion, and the fatigue state proportion, and select the corresponding emotional state regulation module to perform emotional state regulation based on the emotional state corresponding to the maximum value; wherein, if the fear emotion proportion is the largest, the fear emotion regulation module is selected to perform fear emotion regulation on the staff; if the anxiety emotion proportion is the largest, the anxiety emotion regulation module is selected to perform anxiety emotion regulation on the staff; if the fatigue state proportion is the largest, the fatigue state regulation module is selected to perform fatigue state regulation on the staff.

5. A training system for improving the adaptability of workers to a closed and narrow environment according to claim 4, characterized in that: The emotional state regulation subsystem also includes a fear emotion regulation module, an anxiety emotion regulation module and a fatigue state regulation module; The fear emotion regulation module is used to regulate the fear emotions of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy combined with mindfulness; The anxiety regulation module is used to regulate the anxiety of the staff, specifically using earlobe electrical stimulation + virtual reality intervention scenario based on natural therapy; The fatigue state control module is used to control the fatigue state of the staff, specifically using music + transcutaneous ear vagus nerve electrical stimulation that matches the intensity of the music pitch changes.

6. A training system for improving workers' adaptability to a closed and narrow environment according to claim 5, characterized in that: The emotional state regulation subsystem also includes a module for determining whether to terminate; The module for determining whether to terminate is used to determine whether to stop training according to the total emotional state intensity, specifically: if the total emotional state intensity is less than a preset threshold, the training is stopped.

7. A training system for improving workers' adaptability to a closed and narrow environment according to claim 3, characterized in that: The trained emotional state distribution learning model adopts AA-BP, AA-kNN, PT-Bayes, PT-SVM, SA-IIS or SA-CPNN algorithm.

8. A training method for improving the adaptability of workers to a confined and narrow environment, characterized in that: The following steps are involved: S1: Acquire peripheral physiological data generated by the staff in a selected virtual-real combination scenario; wherein the peripheral physiological data includes pulse wave data and skin electrical data; the selected virtual-real combination scenario is one of a fear virtual-real combination scenario, an anxiety virtual-real combination scenario, and a fatigue virtual-real combination scenario; S2: removing noise data from the peripheral physiological data and improving its signal-to-noise ratio; S3: extracting heart rate, heart rate variability, low-frequency power spectral density, high-frequency power spectral density and total energy from the preprocessed pulse wave data; Extract the mean of skin conductance response, the standard deviation of skin conductance response, the maximum value of skin conductance response, the minimum value of skin conductance response, the first-order difference of the mean of skin conductance response, the second-order difference of the mean of skin conductance response, and the first-order derivative of the mean of skin conductance response from the preprocessed skin electrical data; Extracting the mean of the skin conductivity level, the standard deviation of the skin conductivity level, the maximum value of the skin conductivity level, the minimum value of the skin conductivity level, the first-order difference of the mean of the skin conductivity level, the second-order difference of the mean of the skin conductivity level, and the first-order derivative of the mean of the skin conductivity level from the preprocessed skin electrical data; S4: Input the data extracted in S3 into the trained emotional state distribution learning model to obtain the proportion of fear emotion, anxiety emotion, fatigue state and total emotional state intensity generated by the staff in the selected virtual-real combination scene; wherein the total emotional state intensity is the sum of the fear emotion intensity, the anxiety emotion intensity and the fatigue state intensity; the fear emotion proportion is equal to the fear emotion intensity divided by the total emotional state intensity; the anxiety emotion proportion is equal to the anxiety emotion intensity divided by the total emotional state intensity; the fatigue state proportion is equal to the fatigue state intensity divided by the total emotional state intensity; S5: Determine whether the total emotional state intensity is less than a preset threshold, if less than, stop training, if greater than, execute S6; S6: Screening out the maximum value among the fear emotion proportion, anxiety emotion proportion, and fatigue state proportion, and selecting a corresponding emotion state regulation method to regulate the emotion state based on the emotion state corresponding to the maximum value; S7: Repeat S1-S6 until the training is stopped.

9. A training method for improving workers' adaptability to a confined and narrow environment according to claim 8, characterized in that: The fear virtual reality combined scene is provided by a physical cabin and a fear virtual reality module; wherein the staff is in the physical cabin, and the fear virtual reality module is used to provide the fear virtual reality scene; The anxiety virtual-reality combined scene is provided by a physical cabin and an anxiety virtual reality module; wherein the staff is in the physical cabin, and the anxiety virtual reality module is used to provide the anxiety virtual reality scene; The fatigue virtual-reality combined scene is provided by a physical cabin and a fatigue virtual reality module; wherein the staff is in the physical cabin, and the fatigue virtual reality module is used to provide a fatigue virtual reality scene.

10. According to the training method for improving the adaptability of workers to a closed and narrow environment as claimed in claim 8, S6 specifically comprises: If the fear emotion accounts for the largest proportion, earlobe electrical stimulation + virtual reality intervention scenario based on forest therapy and mindfulness will be selected to regulate the fear emotion of the staff; If the anxiety accounts for the largest proportion, earlobe electrical stimulation + natural therapy-based virtual reality intervention scenario is selected to regulate the anxiety of the staff; If the fatigue state accounts for the largest proportion, music + transcutaneous auricular vagus nerve stimulation that matches the intensity of the music pitch changes is selected to regulate the fatigue state of the staff.

Images