Psychological decompression system and device for working personnel in special environment

Abstract

The invention provides a psychological decompression system and device for working personnel in a special environment, and relates to the technical field of psychological decompression, and the system mainly comprises a data acquisition module, a data processing module and a virtual reality generation module which are arranged in sequence; the data acquisition module comprises an SAM unit, a virtual scene unit, an electrocardio unit and an electroencephalogram unit which are respectively used for acquiring SAM scale data, virtual scene information, electrocardio data and electroencephalogram data of a testee and sending the SAM scale data, the virtual scene information, the electrocardio data and the electroencephalogram data to the data processing module; the data processing module comprises a database, a first classification unit, a second classification unit and a prediction model unit; and the virtual reality generation module comprises a vision generation unit and is used for generating a virtual reality image through the NeRF neural network model based on the second alternative material. According to the scheme, the two-dimensional material can be selected in a targeted manner, and the three-dimensional virtual reality image is generated in real time through the NeRF neural network model, so that the immersion sense and the dynamic sense are effectively improved, and the psychological decompression efficiency and effect are improved.

Description

Technical Field

[0001] The invention relates to the technical field of psychological decompression, and in particular to a psychological decompression system and device for workers in special environments. Background Art

[0002] In the field of special environment operations, operators are in a high-intensity, high-risk operating environment for a long time, facing complex and changeable emergency tasks and continuous psychological pressure challenges. Studies have shown that the anxiety index of operators in special environments is generally 3-5 times higher than that in conventional working environments, and the cumulative effect of psychological pressure is significant. If there is a lack of timely and effective psychological intervention measures, it will not only affect the operating efficiency, but also may lead to the occurrence of serious psychological problems such as post-traumatic stress disorder (PTSD) and anxiety.

[0003] However, the existing psychological decompression systems that use the Chinese emotional material library and the international emotional material library generally use traditional two-dimensional images as emotional stimulation sources, which have technical bottlenecks such as insufficient immersion, lack of dynamic feedback, and low personalized adaptability, making it difficult for the actual decompression effect to exceed the critical value of 40%. Therefore, the development of a virtual reality psychological decompression system based on multi-dimensional physiological data feedback and scale feedback, with high immersion and dynamic adaptability, has become an urgent need to improve the mental health level of workers in special environments. Summary of the invention

[0004] The purpose of the present invention is to provide a psychological decompression system and device for workers in special environments to solve at least one of the above-mentioned technical problems existing in the prior art.

[0005] In the first aspect, in order to solve the above technical problems, the present invention provides a psychological decompression system for workers in special environments, including a data acquisition module, a data processing module and a virtual reality generation module arranged in sequence: The data acquisition module includes a SAM unit, a virtual scene unit, an ECG unit and an EEG unit, which are respectively used to collect the SAM scale data, virtual scene information, ECG data and EEG data of the subject and send them to the data processing module; The data processing module includes a database, a first classification unit, a second classification unit and a prediction model unit: The database stores two-dimensional picture materials and corresponding sound effect materials; The first classification unit selects the first candidate material based on the virtual scene information; The second classification unit calculates the stress reduction index based on the SAM scale data, the electrocardiogram data and the electroencephalogram data, which is used to evaluate the stress reduction effect of the current material in the database on the current subject and mark the current material; The prediction model unit stores a prediction model, which is used to predict the stress reduction effect of unlabeled materials in the database on the current subject. The stress reduction effect includes positive stress reduction, zero stress reduction, and negative stress reduction, and sends the first alternative material with positive stress reduction to the virtual reality generation module as the second alternative material. The virtual reality generation module includes a visual generation unit, which generates virtual reality images based on the second alternative material through a NeRF neural network model. The virtual reality images are used for image-assisted positive stress reduction for the current subject.

[0006] Through the above system, based on the scale data, virtual scene data, and physiological data of special environment operators as subjects, appropriate two-dimensional materials can be selected through targeted classification. Then, through the NeRF neural network model, three-dimensional virtual reality images can be generated in real time, which can effectively improve the immersion, dynamic sense, and pertinence of the materials, and further improve the efficiency and effect of psychological stress reduction.

[0007] In a feasible implementation manner, the SAM scale data includes dimensions such as pleasantness, arousal, and sense of control.

[0008] In a feasible implementation manner, the virtual scene information includes natural scenery categories, natural animal categories, and warm reunion categories of scenes, etc.

[0009] In a feasible implementation manner, the specific method for obtaining the first alternative material in the first classification unit includes: After identifying the patterns of the materials in the database through a pre-trained image classification model, classify them: add materials without elements such as heat, summer, and islands to the stress reduction set for hot environments; add materials without elements such as ice and snow, and withered grass to the stress reduction set for cold environments; add materials without elements such as darkness, narrowness, tunnels, and crowding to the stress reduction set for narrow spaces; Then, based on the virtual scene information of the subject, the materials in the corresponding stress reduction set are used as the first alternative materials; In this way, the materials can be automatically classified, avoiding special environment operators from coming into contact with pattern materials that are likely to cause them to be highly tense, thus ensuring that they start psychological stress reduction with a peaceful state of mind; Of course, when the number of materials in the database is small, the above classification of materials can also be carried out manually.

[0010] In a feasible implementation manner, the specific method for calculating the stress reduction index in the second classification unit includes: Step a1: Construct evaluation indicators, specifically including the SAM index, heart rate coefficient, and EEG index: The SAM index is used to evaluate the subjective relaxation degree of the subject. Its construction method includes converting the relaxation PAD value in the PAD emotion scale into a positive value range to obtain the relaxation standard value; collecting the SAM scale data of the subject for different materials; calculating the Euclidean distance d between the SAM scale data and the relaxation standard value as the SAM index (the smaller the value, the more relaxed), and the specific formula can be: ; where x0, y0, and z0 respectively represent the relaxation standard values in the x, y, and z directions; xd, yd, and zd respectively represent the SAM scale data values in the x, y, and z directions; The heart rate coefficient is used to evaluate the inner stability degree of the subject. The more unstable the heart rate, the greater the fluctuation of the heart rate coefficient, indicating that the subject's inner is more unstable; its specific calculation formula can be: ; where, represents the heart rate coefficient of the th subject regarding the th material; represents the heart rate standard deviation of the th subject regarding the th material; represents the heart rate average value of the th subject regarding the th material; The specific calculation formula of the can be: ; where, represents the statistical quantity of the subjects; represents the heart rate of the th subject regarding the th material; represents the preset heart rate average value of the th material; The specific calculation formula of the can be: ; In addition, for the average heart rate coefficient of the th material, the specific formula can be: ; The electroencephalogram (EEG) index is used to evaluate the objective emotional state of the subject. Its construction method includes: preprocessing the EEG data through an EEG data processing software to reduce interference noise; dividing the EEG data according to emotional types through ERP component analysis and quantifying it into emotional values. For example, if the emotional types are divided into tense, neutral, and relaxed, the emotional value of tense is set to -1, the emotional value of neutral is set to 0, and the emotional value of relaxed is set to 1; according to the measurement time, the EEG data is evenly divided into several time periods, sorted according to the size of the emotional values in each time period, and then calculate the th subject's emotional average value for the th material The specific formula is: ; where, represents the maximum emotional value; represents the median emotional value; represents the minimum emotional value; For each material, calculate the average value of the emotional values of the subject, and map it to the interval [0, 1] through the min-max normalization method. The specific formula can be: ; where, represents the original value of the current emotional value; represents the minimum value among the average emotional values corresponding to each material; represents the maximum value among the average emotional values corresponding to each material; represents the conversion result of the current emotional value; Step a2: Divide the EEG index into positive indicators, and divide the SAM index and heart rate coefficient into negative indicators, and perform positive transformation respectively to obtain a positive transformation matrix : The positive transformation formula for positive indicators is: ; The positive transformation formula for negative indicators is: ; where, represents the th (row) material and the th (column) dimension index, ranges from 1 to (the total number of material statistics), ranges from 1 to 3 (i.e., EEG index, SAM index, and heart rate coefficient); represents 's positive transformation value; represents the The minimum index of a material; Indicates the maximum index of the th material; Step a3: Standardize the positive matrix to obtain the standardized matrix . The calculation formula for the elements of the standardized matrix can be: ; Step a4: Calculate the entropy of the th dimension index in the standardized matrix . The specific formula can be: Among them, represents the proportion of the index value of the th material in the th dimension to all index values of this material. The specific calculation formula is: ; represents the check coefficient. The specific calculation formula is: ; Step a5: Calculate the difference coefficient of the th dimension. The specific formula can be: ; Then calculate the weight of the th dimension. The specific formula can be: ; Then calculate the comprehensive score of the th material. The specific formula can be: ; Step a6: The maximum index value of each dimension in the standardized matrix forms the optimal decompression vector ; The minimum index value of each dimension in the standardized matrix forms the worst decompression vector ; Step a7: Define the distance between the th material and the optimal decompression vector and the distance between the th material and the worst decompression vector respectively. The specific formula can be: ; ; Step a8: Calculate the Stress relief index of each material , whose value range is [0,1]: when The closer it is to 1, the better the decompression effect of the corresponding material; The closer it is to 0, the worse the decompression effect of the corresponding material. The specific formula can be: ; In this way, we can use the relationship between information entropy and the probability of random events to measure the degree of discreteness of an indicator. The greater the degree of discreteness of the indicator, the greater the impact of the indicator on the comprehensive evaluation and the greater its weight. Then, we can conduct a comprehensive evaluation and obtain a stress relief index based on data and ideal conditions.

[0011] In a feasible implementation, the training method of the prediction model includes: Based on the materials with labeled stress relief index, a training set and a test set are constructed; based on the training set and the test set, prediction models (such as RNN models, LSTM models, and attention models, etc.) are trained and tested to predict the stress relief effect of the materials.

[0012] In a feasible implementation manner, the loss function of the prediction model includes a decompression index so that the prediction model can perform self-iteration according to the decompression effect.

[0013] In a feasible implementation, the NeRF neural network model belongs to the existing technology, including establishing a local polar coordinate system at the virtual viewpoint V on the surface of the material during model training, performing a ±30° lateral fan perturbation on the original training line of sight OV perpendicular to the surface of the material, and generating a number of random lines of sight OV' in real time through the RRC (random ray casting) strategy, adding them to the training set, and training the NeRF neural network model to improve the display effect of the three-dimensional virtual reality image under the condition of small-angle change of viewing angle; in this way, the three-dimensional virtual reality image can be suitable for the visual clarity requirements of the subject when he or she is in a lying position for psychological decompression treatment and slightly swinging his or her head to observe the material.

[0014] In the second aspect, based on the same inventive concept, the present application also provides a method for psychological decompression of workers in special environments using the above system, which specifically includes the following steps: Step b1, collecting the subjects' initial SAM scale data and virtual scene information; Step b2: Select the first alternative material in the database based on the virtual scene information; then, construct a virtual reality image through the NeRF neural network model and play it to the subject. Step b3: Collect the current SAM scale data, electrocardiogram (ECG) data, and electroencephalogram (EEG) data of the subject. Step b4: Calculate the stress reduction index of the current material based on the current SAM scale data, ECG data, and EEG data, which is used to evaluate the stress reduction effect of the current material on the current subject in the database and mark the current material; select the second alternative material in the database through the prediction model; then, reconstruct the virtual reality image through the NeRF neural network model and play it to the subject, and iteratively execute Step b3 until the iteration end condition is reached.

[0015] Through the above steps, materials can be selectively chosen based on the virtual scene information, SAM scale data, ECG data, and EEG data of the subject through a pre-trained prediction model; then, a three-dimensional psychological stress reduction scene can be generated in real time through the NeRF neural network model, thereby effectively enhancing the immersion, dynamics, and pertinence of the materials, and further improving the psychological stress reduction effect and efficiency.

[0016] In a feasible implementation manner, the iteration end condition is that the SAM scale data, ECG data, and EEG data of the subject respectively conform to the SAM scale data range, ECG data range, and EEG data range defined in the Chinese Emotional Material Library and / or the International Emotional Material Library for a relaxed mental state.

[0017] In a third aspect, based on the same inventive concept, the present application further provides a psychological stress reduction device for special environment operators to implement the above system, including a VR headset, an ECG device, an EEG device, and a computing platform that are electrically connected to each other; The VR headset is used to display the VR scene; The ECG device refers to an electrocardiogram monitoring device and is used to monitor the heart rate in real time; The EEG device refers to an electroencephalogram monitoring device and is used to record the brain waves in real time; The computing platform includes a processor, a memory, and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory, and the bus is connected between each functional component to transmit information; in this way, it can be implemented through (wearable) devices and (mobile) application methods, which is beneficial for the subject to perform self-psychological stress reduction treatment at any time.

[0018] In a feasible implementation, the device includes a mobile cabin, and multiple groups of decompression seats are arranged in parallel in the mobile cabin so that multiple special environment operator subjects can undergo psychological decompression therapy simultaneously, which can avoid the sense of loneliness generated by a single subject during self-decompression and the sense of fear in a closed environment.

[0019] In a feasible implementation, a VR headset, an ECG device, an EEG device, and a computing platform are provided at each decompression seat; the computing platforms are electrically connected to each other for data interaction so that each subject can see each other through the VR headset, which is beneficial to relaxing the subjects' minds and eliminating the sense of loneliness and fear.

[0020] In a feasible implementation, the mobile cabin further includes an air conditioning system, and the air conditioning system is electrically connected to the computing platform; the air conditioning system includes a number of independent air outlets, and each air outlet points to a decompression seat; in this way, the air supply wind speed, air supply temperature, and air supply humidity can be configured according to the materials played by each computing platform, which is beneficial to increasing the sense of immersion.

[0021] In a feasible implementation, the mobile cabin further includes an audio system, and the audio system is electrically connected to the computing platform; the audio system includes a number of independent headphones; in this way, the music and sound effects can be configured according to the materials played by each computing platform, which is beneficial to increasing the sense of immersion.

[0022] In a feasible implementation, the inner wall of the mobile cabin is provided with sound insulation materials, which is beneficial to excluding external interference and increasing the sense of immersion of the subjects.

[0023] Adopting the above technical solutions, the present invention has the following beneficial effects: A psychological decompression system and device for special environment operators provided by the present invention can, based on the scale data, virtual scene data, and physiological data of special environment operator subjects, select appropriate two-dimensional materials through targeted classification; and then, through the NeRF neural network model, generate three-dimensional virtual reality images in real time, thereby effectively improving the immersion, dynamic sense, and pertinence of the materials, and further improving the psychological decompression efficiency and effect; at the same time, by building a multi-person companion decompression atmosphere for special environment operators and a virtual reality scene with multiple sensory experiences, the psychological pressure brought by the psychological decompression treatment behavior itself of the subjects can be reduced. Description of the Drawings

[0024] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following will briefly introduce the drawings required for the description of the specific embodiments or the prior art. Obviously, the drawings in the following description are some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0025] Figure 1 It is a diagram of a psychological stress reduction system for special environment operators provided by an embodiment of the present invention; Figure 2 It is a specific method flowchart for calculating the stress reduction index provided by an embodiment of the present invention; Figure 3 It is a flowchart of a psychological stress reduction method for special environment operators provided by an embodiment of the present invention; Figure 4 It is a schematic diagram of the internal layout of a mobile cabin provided by an embodiment of the present invention; Figure 5 It is a schematic diagram of the airbag layout provided by an embodiment of the present invention.

[0026] Reference numerals: 1 - Stress reduction seat; 11 - Lower airbag; 12 - Upper airbag; 2 - ECG device; 3 - EEG device; 4 - Air supply port; 5 - VR headset. Specific embodiments

[0027] The following will clearly and completely describe the technical solutions of the present invention in conjunction with the drawings. Obviously, the described embodiments are some, but not all, of the embodiments of the present invention. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without creative efforts fall within the scope of protection of the present invention.

[0028] In the description of the present invention, it should be noted that the orientation or positional relationship indicated by the terms "center", "upper", "lower", "left", "right", "vertical", "horizontal", "inner", "outer", etc. is based on the orientation or positional relationship shown in the drawings, and is only for the convenience of describing the present invention and simplifying the description, rather than indicating or implying that the device or element referred to must have a specific orientation, be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of the present invention. In addition, the terms "first", "second", "third" are only used for descriptive purposes and cannot be construed as indicating or implying relative importance.

[0029] In the description of the present invention, it should be noted that unless otherwise clearly specified and defined, the terms "installation", "connection", and "coupling" should be understood in a broad sense. For example, it can be a fixed connection, a detachable connection, or an integral connection; it can be a mechanical connection or an electrical connection; it can be a direct connection or an indirect connection through an intermediate medium, and it can be the communication inside two components. For those of ordinary skill in the art, the specific meanings of the above terms in the present invention can be understood according to specific circumstances.

[0030] The following further explains and illustrates the present invention in conjunction with specific embodiments.

[0031] It should also be noted that the following specific embodiments or specific implementation manners are a series of optimized setting manners listed by the present invention to further explain the specific invention content, and these setting manners can be combined with each other or used in association with each other.

[0032] Embodiment 1: As Figure 1 shown, this embodiment provides a psychological stress reduction system for special environment operators, including a data acquisition module, a data processing module, and a virtual reality generation module arranged in sequence: The data acquisition module includes a SAM unit, a virtual scene unit, an electrocardiogram unit, and an electroencephalogram unit, which are respectively used to collect the SAM scale data of the subject, virtual scene information (i.e., information about the special operation environment), electrocardiogram data, and electroencephalogram data and send them to the data processing module; The data processing module includes a database, a first classification unit, a second classification unit, and a prediction model unit: The database can store two-dimensional picture materials with a valence above 6.5, an arousal below 3.5, and a dominance between 5 and 7 in the Chinese emotion material library and / or the international emotion material library, as well as corresponding sound effect materials; The first classification unit screens the first alternative materials based on the virtual scene information; The second classification unit calculates a stress reduction index based on the SAM scale data, electrocardiogram data, and electroencephalogram data, which is used to evaluate the stress reduction effect of the current material in the database on the current subject and mark the current material; The prediction model unit stores a prediction model, which is used to predict the stress reduction effect of the unmarked materials in the database on the current subject. The stress reduction effect includes positive stress reduction, zero stress reduction, and negative stress reduction, and sends the first alternative materials with positive stress reduction as the second alternative materials to the virtual reality generation module; The virtual reality generation module includes a visual generation unit that generates virtual reality images based on the second alternative material through a NeRF neural network model. The virtual reality images are used for image-assisted positive decompression for the current subject.

[0033] Through the above system, based on the scale data, virtual scene data, and physiological data of the subjects of special environment workers, appropriate two-dimensional materials can be selected through targeted classification. Then, through the NeRF neural network model, three-dimensional virtual reality images can be generated in real time, effectively enhancing the immersion, dynamics, and pertinence of the materials, thereby improving the efficiency and effect of psychological decompression.

[0034] Further, the SAM scale data includes dimensions such as pleasantness, arousal, and sense of control.

[0035] Further, the virtual scene information includes scenes of natural scenery, natural animals, and warm reunions.

[0036] Further, the specific method for obtaining the first alternative material in the first classification unit includes: After identifying the patterns of the materials in the database through a pre-trained image classification model and classifying them: adding the materials without the elements of extreme heat, summer, and island to the decompression set for extreme heat environment; adding the materials without the elements of ice and snow, and withered grass to the decompression set for extreme cold environment; adding the materials without the elements of darkness, narrowness, tunnel, and crowd to the decompression set for narrow space; Then, based on the virtual scene information of the subject, the materials in the corresponding decompression set are used as the first alternative materials; In this way, the materials can be automatically classified, preventing the subjects of special environment workers from coming into contact with the pattern materials that are likely to cause their high tension, thus ensuring that they can start psychological decompression with a peaceful state of mind; Of course, when the number of materials in the database is small, the above classification of the materials can also be carried out manually.

[0037] Further, as Figure 2 shown, the specific method for calculating the decompression index in the second classification unit includes: Step a1: Construct evaluation indicators, specifically including the SAM index, heart rate coefficient, and EEG index: The SAM index is used to evaluate the subjective relaxation degree of the subject. Its construction method includes converting the relaxation PAD value in the PAD emotion scale into a positive value range to obtain the relaxation standard value (x0; y0; z0); collecting the SAM scale data (xd; yd; zd) of the subject for different materials; calculating the Euclidean distance d between the SAM scale data and the relaxation standard value as the SAM index (the smaller the value, the more relaxed), and the specific formula can be: ; The heart rate coefficient is used to evaluate the inner stability of the subject. The more unstable the heart rate is, the greater the fluctuation of the heart rate coefficient, indicating that the subject is more unstable inside. Its specific calculation formula can be: ; wherein, represents the heart rate coefficient of the th subject regarding the th material; represents the standard deviation of the heart rate of the th subject regarding the th material; represents the average heart rate of the th subject regarding the th material; The specific calculation formula of the can be: ; wherein, represents the statistical quantity of the subjects; represents the heart rate of the th subject regarding the th material; represents the preset average heart rate of the th material; The specific calculation formula of the can be: ; In addition, for the average heart rate coefficient of the th material, the specific formula can be: ; The EEG index is used to evaluate the objective emotional state of the subject. Its construction method includes: preprocessing the EEG data through an EEG data processing software to reduce interference noise; dividing and quantifying the EEG data into emotional values according to emotional types through ERP component analysis. For example, if the emotional types are divided into tense, neutral, and relaxed, the emotional value of tense is set to -1, the emotional value of neutral is set to 0, and the emotional value of relaxed is set to 1; dividing the EEG data into several time periods on average according to the measurement time, sorting according to the size of the emotional values in each time period, and then calculating the emotional average value of the th subject regarding the th material. The specific formula is: ; wherein, Represents the maximum emotional value; Represents the median emotional value; Represents the minimum emotional value; For each piece of material, calculate the average emotional value of the subjects, and map it to the interval [0, 1] through the min-max normalization method. The specific formula can be: ; Among them, Represents the original value of the current emotional value; Represents the minimum value among the average emotional values corresponding to each piece of material; Represents the maximum value among the average emotional values corresponding to each piece of material; Represents the conversion result of the current emotional value; Step a2: Divide the EEG index into positive indicators, and divide the SAM index and heart rate coefficient into negative indicators, and perform positive normalization respectively to obtain a positive normalization matrix : The positive normalization formula for positive indicators is: ; The positive normalization formula for negative indicators is: ; Among them, Represents the th (row) piece of material and the th (column) dimension index. The value range of (total number of material statistics), The value range of is from 1 to 3 (i.e., EEG index, SAM index, and heart rate coefficient); Represents the positive normalization value of Represents the th minimum index of the material; Represents the th maximum index of the material; Step a3: Perform standardization processing on the positive normalization matrix to obtain a standardized matrix , and the calculation formula for the elements of the standardized matrix can be: ; Step a4: Calculate the entropy of the th dimension index in the standardized matrix , and the specific formula can be: ; Among them, Represents the The proportion of the index value of the rd material in each dimension to all the index values of this material, and the specific calculation formula is: ; represents the calibration coefficient, and the specific calculation formula is: ; Step a5: Calculate the coefficient of variation of the th dimension. The specific formula can be: ; Then calculate the weight of the th dimension. The specific formula can be: ; Then calculate the comprehensive score of the th material. The specific formula can be: ; Step a6: Compose the maximum index value of each dimension in the standardized matrix into the optimal decompression vector ; Compose the minimum index value of each dimension in the standardized matrix into the worst decompression vector ; Step a7: Define the distance between the th material and the optimal decompression vector and the distance between the th material and the worst decompression vector respectively. The specific formula can be: ; ; Step a8: Calculate the decompression index of the th material. Its value range is [0, 1]: When is closer to 1, the decompression effect of the corresponding material is better; when is closer to 0, the decompression effect of the corresponding material is worse. The specific formula can be: ; In this way, the relationship between information entropy and the probability of random events can be utilized to measure the dispersion degree of an index. The greater the dispersion degree of the index, the greater the impact of the index on the comprehensive evaluation, and the greater the weight. Then, a comprehensive evaluation is carried out to obtain a decompression index measured based on data and the ideal situation.

[0038] Further, the training method of the prediction model includes: Based on the materials with marked decompression indices, a training set and a test set are constructed. Based on the training set and the test set, the prediction model (such as RNN model, LSTM model, and attention model, etc.) is trained and tested to predict the decompression effect of the materials.

[0039] Further, the loss function of the prediction model includes the decompression index, so that the prediction model can perform self-iteration according to the decompression effect.

[0040] Further, the NeRF neural network model belongs to the prior art. During model training, a local polar coordinate system is established at the virtual viewpoint V on the surface of the material. The original training line of sight OV perpendicular to the surface of the material is perturbed by ±30° in the lateral fan-shaped surface, and through the RRC (random ray casting) strategy, several random lines of sight OV’ are generated in real time and added to the training set to train the NeRF neural network model, so as to improve the display effect of three-dimensional virtual reality images in the case of small-angle transformed viewpoints. In this way, the three-dimensional virtual reality images can meet the visual clarity requirements of the subjects when observing the materials with small head swings in the lying position during psychological decompression treatment.

[0041] Embodiment 2: As Figure 3 shown, this embodiment provides a psychological decompression method for special environment operators using the above system, which specifically includes the following steps: Step b1: Collect the initial SAM scale data and virtual scene information of the subject; Step b2: Based on the virtual scene information, select the first alternative material in the database; then, through the NeRF neural network model, construct a virtual reality image and play it to the subject; Step b3: Collect the current SAM scale data, electrocardiogram data, and electroencephalogram data of the subject; Step b4: Based on the current SAM scale data, electrocardiogram data, and electroencephalogram data, calculate the decompression index of the current material to evaluate the decompression effect of the current material in the database on the current subject and mark the current material; through the prediction model, select the second alternative material in the database; then, through the NeRF neural network model, reconstruct the virtual reality image and play it to the subject, and iteratively execute step b3 until the iteration end condition is reached.

[0042] Through the above steps, based on the virtual scene information, SAM scale data, psychological data, and EEG data of the subject, materials can be selectively targeted through a pre-trained prediction model; then, through the NeRF neural network model, a three-dimensional psychological stress reduction scene can be generated in real time, thereby effectively enhancing the immersion, dynamic sense, and pertinence of the materials, and further improving the psychological stress reduction effect and efficiency.

[0043] Furthermore, the iteration end condition is that the SAM scale data, electrocardiogram (ECG) data, and EEG data of the subject respectively conform to the SAM scale data range, ECG data range, and EEG data range defined for a relaxed mental state in the Chinese emotion material library and the international emotion material library.

[0044] Embodiment Three: This embodiment provides a psychological stress reduction device for special environment operators to implement the above system, including a VR headset, an ECG device, an EEG device, and a computing platform that are electrically connected to each other; The VR headset is used to display a VR scene and can adopt a conventional device; The ECG device refers to an electrocardiogram monitoring device that attaches electrodes to the chest and other parts of the subject to monitor the heart rate in real time and can adopt a conventional device; The EEG device refers to an electroencephalogram monitoring device that is worn on the head of the subject to record brain waves in real time and can adopt a conventional device; The computing platform includes a processor, a memory, and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory. The bus is connected between each functional component to transmit information; this can be achieved through (wearable) devices and (mobile) application methods, thus facilitating the subject to perform self-psychological stress reduction treatment at any time.

[0045] Embodiment Four: As Figure 4 shown, on the basis of Embodiment Three, this embodiment provides a shelter. Three groups of decompression seats 1 are arranged in parallel in the shelter so that three special environment operator subjects can simultaneously perform psychological stress reduction treatment, which can avoid the sense of loneliness generated by a single subject during self-stress reduction and the sense of fear generated in a closed environment.

[0046] Furthermore, a VR headset 5, an ECG device 2, an EEG device 3, and a computing platform are arranged at the head of each decompression seat 1; the computing platforms are electrically connected to each other for data interaction so that the three subjects can see each other through the VR headset 5, which is conducive to relaxing the subjects' minds and eliminating the sense of loneliness and fear.

[0047] Further, the mobile cabin further includes an air conditioning system, and the air conditioning system is electrically connected to the computing platform; the air conditioning system includes three independent air supply outlets 4, each air supply outlet 4 is arranged above the head of a decompression seat 1 and points to this decompression seat 1; in this way, the air supply wind speed, air supply temperature and air supply humidity can be configured according to the materials played by each computing platform, which is beneficial to increasing the immersion feeling.

[0048] Further, the mobile cabin further includes an audio system, and the audio system is electrically connected to the computing platform; the audio system includes a number of independent headphones; in this way, the music and sound effects can be configured according to the materials played by each computing platform, which is beneficial to increasing the immersion feeling.

[0049] Further, the inner wall of the mobile cabin is provided with sound insulation materials, which is beneficial to eliminating external interference and increasing the immersion feeling of the test subject.

[0050] Embodiment 5: As Figure 5 shown, on the basis of Embodiment 4, a lower airbag 11 and an upper airbag 12 are further arranged on the decompression seat 1, which are used to wrap the torso of the test subject in a combined way of up and down and can independently adjust the air pressure according to the control of the computing platform; The lower airbag 11 is laid on the upper surface of the backrest of the decompression seat 1; one end of the upper airbag 12 is connected to the side wall of the backrest of the decompression seat 1 through a hinge, which is used to be able to open, align and lock with the lower airbag 11; in this way, when the upper airbag 12 is opened, the test subject can lean on the lower airbag 11, and when the upper airbag 12 is closed, positioned and locked, the body of the test subject can be wrapped.

[0051] Further, the upper airbag 12 is arranged in a semi-cylindrical cover body, the upper end of the cover body is provided with a first opening for the neck of the test subject to pass through, and the lower end of the cover body is provided with a second opening for the torso of the test subject to pass through.

[0052] Further, both the lower airbag 11 and the upper airbag 12 include an air pump and a barometric pressure sensor, and the air pump and the barometric pressure sensor are respectively electrically connected to the computing platform, which is used to program and control the air pressure of each airbag; in this way, the sense of restraint and pressure brought to the body by special environment operators wearing different special environment work clothes (such as fire fighting clothes, explosion-proof clothes, mine clothes, etc.) can be accurately simulated for psychological decompression treatment, and the air pressure of each airbag can be controlled by the program, and combined with psychological decompression means such as virtual reality images and audio to assist in psychological decompression.

[0053] Furthermore, both the lower airbag 11 and the upper airbag 12 include a number of mutually parallel and independent cylindrical airbags, and each cylindrical airbag includes an air pump and a barometric pressure sensor, so as to apply a wrapping force to the subject more evenly and simulate the wearing feelings of different special environment work clothes by adjusting the air pressure of different cylindrical airbags.

[0054] For example, in the initial stage of psychological decompression, by increasing the air pressure of each airbag, the subject will feel as if wearing a heavy special environment work clothes; as the psychological decompression progresses, gradually reduce the air pressure of each airbag, so that the subject will have a feeling of relief, which helps to improve the effect of psychological decompression. Of course, the air pressure can also be adjusted in cooperation with the materials in the virtual reality image to enhance the immersion and further improve the effect of psychological decompression. It should be noted that the airbag should be used at intervals with the ECG device 2 to avoid damage or failure of the electrocardiogram monitoring patch (electrode) attached to the subject's chest.

[0055] Finally, it should be noted that: the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, those of ordinary skill in the art should understand that: they can still modify the technical solutions recorded in the foregoing embodiments, or perform equivalent replacements on some or all of the technical features; and these modifications or replacements do not make the essence of the corresponding technical solutions deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A psychological stress reduction system for operators working in special environments, characterized in that, It includes a data acquisition module, a data processing module, and a virtual reality generation module arranged in sequence: The data acquisition module includes a SAM unit, a virtual scene unit, an electrocardiogram unit, and an electroencephalogram unit, which are respectively used to collect the SAM scale data, virtual scene information, electrocardiogram data, and electroencephalogram data of the subject and send them to the data processing module; The data processing module includes a database, a first classification unit, a second classification unit, and a prediction model unit: The database stores two-dimensional picture materials and corresponding sound effect materials; The first classification unit screens the first alternative materials based on the virtual scene information; The second classification unit calculates a decompression index based on the SAM scale data, electrocardiogram data, and electroencephalogram data, which is used to evaluate the decompression effect of the current material in the database on the current subject and mark the current material; The prediction model unit stores a prediction model, which is used to predict the decompression effect of the unmarked materials in the database on the current subject. The decompression effect includes positive decompression, zero decompression, and negative decompression, and sends the first alternative materials with positive decompression to the virtual reality generation module as the second alternative materials; The virtual reality generation module includes a visual generation unit, which generates virtual reality images based on the second alternative materials through the NeRF neural network model; the virtual reality images are used for image-assisted positive decompression for the current subject.

2. The system according to claim 1, wherein The specific method for obtaining the first alternative materials in the first classification unit includes: After identifying the patterns of the materials in the database through a pre-trained image classification model and classifying them: adding the materials without the elements of heat, summer, and island to the decompression set for hot environments; adding the materials without the elements of ice, snow, and withered grass to the decompression set for cold environments; adding the materials without the elements of darkness, narrowness, tunnels, and crowding to the decompression set for narrow spaces; Then, based on the virtual scene information of the subject, the materials in the corresponding decompression set are used as the first alternative materials.

3. The system according to claim 1, characterized in that, The specific method for calculating the decompression index in the second classification unit includes: Step a1: Construct evaluation indicators, specifically including the SAM index, heart rate coefficient, and electroencephalogram index: The SAM index is used to evaluate the subjective relaxation degree of the subject. Its construction method includes converting the relaxed PAD value in the PAD emotion scale into a positive value range to obtain a relaxed standard value; collecting the SAM scale data of the subject for different materials; calculating the Euclidean distance d between the SAM scale data and the relaxed standard value as the SAM index. The specific formula is: ； Where x0, y0, and z0 respectively represent the relaxed standard values in the x, y, and z directions; xd, yd, and zd respectively represent the SAM scale data values in the x, y, and z directions; The heart rate coefficient is used to evaluate the inner stability degree of the subject. The more unstable the heart rate, the greater the fluctuation of the heart rate coefficient; its specific calculation formula is: ； Among them, represents the heart rate coefficient of the th subject regarding the th material; represents the standard deviation of the heart rate of the th subject regarding the th material; represents the average heart rate of the th subject regarding the th material. The specific calculation formula is as follows: ； Among them, represents the statistical quantity of the subjects; represents the th subject's heart rate regarding the th material; represents the preset average heart rate of the th material; The specific calculation formula is as follows: ； In addition, for the average heart rate coefficient of the th material, the specific formula is as follows: ； The electroencephalogram index is used to evaluate the objective emotional state of the subject, and its construction method includes: preprocessing the electroencephalogram data through an electroencephalogram data processing software; dividing and quantifying the electroencephalogram data into emotional values according to emotional types through ERP component analysis; evenly dividing the electroencephalogram data into several time periods according to the measurement time, sorting according to the magnitude of the emotional values of each time period, and then calculating the emotional average value of the th subject for the th material The specific formula is: ； Among them, represents the maximum emotion value; represents the median emotion value; represents the minimum emotion value; For each material, calculate the average value of the subject's emotional values and map it to the interval [0,1] through the min-max normalization method. The specific formula is: ; Among them, represents the original value of the current emotion value; represents the minimum value among the average emotion values corresponding to each material; represents the maximum value among the average emotion values corresponding to each material; represents the conversion result of the current emotion value; Step a2: Divide the EEG index into positive indicators, divide the SAM index and the heart rate coefficient into negative indicators, and perform positive processing on them respectively to obtain a positive matrix : The positive formula for positive indicators is: ； The positive formula for reverse indicators is: ； Among them, represents the th index of the th dimension in the th material, represents the total count of materials, whose value range is from 1 to 3; represents the positive value; represents the minimum index of the th material; represents the maximum index of the th material; Step a3: Normalize the forward matrix to obtain the normalized matrix . The calculation formula for the elements of the normalized matrix is: ; Step a4, calculate the standardization matrix in the entropy of the th dimension index, and the specific formula is: ; Among them, represents the proportion of the index value of the th material in the th dimension to all index values of this material. The specific calculation formula is: ； Indicates the verification coefficient, and the specific calculation formula is as follows: ； Step a5, calculate the coefficient of variation of the th dimension , and the specific formula is: ； Then calculate the weight of the th dimension , and the specific formula is: ; Then calculate the comprehensive score of the th material , and the specific formula is: ； Step a6: The maximum value of each dimension index in the standardized matrix is used to form the optimal decompression vector ; The minimum value of each dimension index in the standardized matrix is used to form the worst decompression vector ; Step a7: Define the distances between the th material and the optimal decompression vector and the distance between the th material and the worst decompression vector , and the specific formula is as follows: ； ； Step a8, calculate the decompression index of the th material, and its value range is [0, 1]; the specific formula is: 。 4. The system according to claim 3, wherein The training method of the prediction model includes: constructing a training set and a test set based on the materials with marked decompression indexes; training and testing the prediction model based on the training set and the test set for predicting the decompression effect of the materials; the loss function of the prediction model includes the decompression index.

5. The system according to claim 3, characterized in that, When training the NeRF neural network model, a local polar coordinate system is established at the virtual view point V on the surface of the material, the original training line of sight OV perpendicular to the surface of the material is perturbed by a lateral fan surface of ±30°, and several random lines of sight OV' are generated in real time through the RRC strategy and added to the training set to train the NeRF neural network model.

6. A psychological stress reduction device for special environment operators implementing the system described in any one of claims 1-5, characterized in that, It includes a VR headset, an ECG device, an EEG device and a computing platform that are electrically connected to each other; The VR headset is used to display the VR scene; The ECG device refers to an electrocardiogram monitoring device for real-time heart rate monitoring; The EEG device refers to an electroencephalogram monitoring device for real-time electroencephalogram recording; The computing platform includes a processor, a memory and a bus. The memory stores instructions and data read by the processor. The processor is used to call the instructions and data in the memory, and the bus is connected between each functional component for transmitting information.

7. The device according to claim 6, characterized in that, It further includes a shelter. Multiple groups of decompression seats are arranged in parallel in the shelter; a VR headset, an ECG device, an EEG device and a computing platform are arranged at each decompression seat; the computing platforms are electrically connected to each other for data interaction.

8. The device according to claim 7, wherein The shelter further includes an air conditioning system that is electrically connected to the computing platform; the air conditioning system includes several independent air supply outlets, and each air supply outlet points to a decompression seat.

9. The device according to claim 8, characterized in that, A lower airbag and an upper airbag are further arranged on the decompression seat; the lower airbag is laid on the upper surface of the backrest of the decompression seat; one end of the upper airbag is hinged to the side wall of the backrest of the decompression seat and can be opened and closed and locked with the lower airbag.

10. The device according to claim 9, characterized in that, Both the lower airbag and the upper airbag include an air pump and a pressure sensor. The air pump and the pressure sensor are respectively electrically connected to the computing platform for program control of the air pressure of each airbag.

Images