A personalized psychological stress relief intervention system and device

Abstract

The present invention provides a personalized psychological stress reduction intervention system and device, relating to the field of psychological stress reduction technology. The system primarily comprises a data acquisition module, a data processing module, and a result generation module. The data acquisition module is constructed based on the Apache Storm system and includes a Spout component and several Bolt components. The Bolt components store a pre-trained three-category model and are used to output three correction signals: enhanced intervention, maintained intervention, or weakened intervention. The data processing module includes a stress index unit, a VR generation unit, a feedback adjustment unit, and an evaluation and analysis unit. The result generation module is used to externalize the evaluation and analysis results. This solution utilizes VR technology to provide immersive stress reduction for subjects. Through big data technology and machine learning, the system collects the subject's physiological data in real time, provides feedback on the effects of the psychological stress reduction intervention, intelligently corrects VR material, generates a stress index change curve and an intervention effect evaluation report, and provides personalized stress assessment and stress reduction recommendations.

Description

Technical Field

[0001] The present invention relates to the technical field of psychological decompression, and in particular to a personalized psychological decompression intervention system and device. Background Art

[0002] As the pace of life becomes faster and faster, everyone often faces various life pressures, which leads to more serious psychological problems. To this end, many psychological stress assessment and intervention methods have emerged, such as psychological scale method and biofeedback method.

[0003] Although these methods can, to a certain extent, assess and intervene in the psychological stress of subjects, they often use static assessment and single adjustment means, lacking real-time closed-loop feedback on the intervention effect on the adjustment means; and cannot take into account the individual physical and mental characteristics of different subjects; and in terms of intervention methods, most of them are based on two-dimensional display and lack immersion, resulting in unsatisfactory psychological stress relief intervention effects. Summary of the Invention

[0004] The purpose of the present invention is to provide a personalized psychological stress relief intervention system and device to solve at least one of the above-mentioned technical problems existing in the prior art.

[0005] In a first aspect, in order to solve the above technical problems, the present invention provides a personalized psychological stress reduction intervention system, including a data acquisition module, a data processing module and a result generation module;

[0006] The data collection module is built based on the Apache Storm system, including Spout components and several Bolt components:

[0007] The Spout component is used to receive the subject's physiological data and basic information in real time; the physiological data includes electrocardiogram (ECG) data, electroencephalogram (EEG) data, and skin conductance data; the basic information includes age, gender, social attributes, stress environment characteristics, and psychological scale results (such as the SAM scale, the Psychological Resilience Recovery Scale, and the Positive and Negative Psychology Scale);

[0008] The Bolt component stores a pre-trained three-classification model for outputting three correction signals: enhancing intervention, maintaining intervention, or weakening intervention;

[0009] The three classification models specifically include a tree model, a time series classification model, and an integrated model;

[0010] The tree model outputs a basic pressure classification result based on the basic information;

[0011] The time series classification model, such as RNN, LSTM, and attention model, outputs an electrocardiogram (ECG) stress classification result, an electroencephalogram (EEG) stress classification result, and a skin conduction stress classification result based on the normalized values ​​of the ECG data, EEG data, and skin conduction data, respectively; each classification result is set as an integer between 0 and 10, with a larger value indicating greater psychological stress;

[0012] The integrated model is used to assign weights to the basic stress classification results, the electrocardiographic stress classification results, the electroencephalographic stress classification results, and the skin conductivity stress classification results, and then perform summation calculations, compare the calculated results with a preset intervention threshold, and output three correction signals: enhanced intervention, maintained intervention, or weakened intervention, so as to dynamically correct the psychological decompression intervention plan; the preset intervention threshold includes a first intervention threshold and a second intervention threshold, and the first intervention threshold is less than the second intervention threshold: when the calculated result is less than the first intervention threshold, a correction signal for weakening intervention is output; when the calculated result is greater than or equal to the first intervention threshold and less than the second intervention threshold, a correction signal for maintaining intervention is output; when the calculated result is greater than or equal to the second intervention threshold, a correction signal for enhancing intervention is output;

[0013] The data processing module includes a pressure index unit, a database, a VR (virtual reality) generation unit, a feedback adjustment unit, and an evaluation and analysis unit;

[0014] The stress index unit calculates the subject's stress index (Stress Index) based on the physiological data and the basic information, so as to assess the subject's psychological stress level;

[0015] The database stores two-dimensional image materials; the two-dimensional image materials may be selected based on the IAPS International Emotional Image System and the CAPS Chinese Emotional Image System, with a pleasure level (Valence) of 6.5 or higher, an arousal level of 3.5 or lower, and a dominance level of 5-7, so as to serve as a reference for constructing VR scenes;

[0016] The VR generation unit selects two-dimensional image materials from a database based on the psychological stress reduction intervention program, converts the two-dimensional image materials into three-dimensional images using 3D modeling software, such as Meshroom open source software, and constructs a VR scene to play to the subject; the VR scene includes images and sounds;

[0017] The feedback adjustment unit adjusts the psychological stress reduction intervention plan based on the correction signal, thereby obtaining a personalized psychological stress reduction intervention plan; the psychological stress reduction intervention plan includes the category type, playback order, stress reduction index, and playback frequency of the material; the category type may include natural scenery, warm family scenes, pets and animals, and other categories that can achieve stress reduction and relaxation effects;

[0018] The evaluation and analysis unit generates a pressure index change curve and an intervention effect evaluation report based on the pressure index; the intervention effect evaluation report determines an intervention conclusion, such as "pressure reduction intervention is effective" or "pressure reduction intervention is ineffective," based on the pressure index change curve and a preset pressure index threshold;

[0019] The result generation module is used to send out the pressure index change curve and the intervention effect evaluation report.

[0020] Through the above system, VR technology can be used to immerse subjects in stress relief. And through big data technology and machine learning, the physiological data of the subjects can be collected in real time, the effects of psychological stress relief intervention can be fed back, VR materials can be intelligently corrected, stress index change curves and intervention effect evaluation reports can be generated, and personalized stress assessment and stress relief suggestions can be provided.

[0021] In a feasible implementation, the Spout component initializes the data stream through the initialize method, so that the Spout component accurately receives the physiological data and basic information of the subject; and connects to the Bolt component through the nextTuple method, so that the Spout component effectively transmits the data stream to the next Bolt component in the topology.

[0022] In a feasible implementation, in the Bolt component, the three-classification model is called through the execute method to perform three-classification on the subject's physiological data and basic information in real time.

[0023] In a feasible implementation, the EEG data includes alpha waves and / or beta waves, both of which are related to psychological stress: alpha waves often indicate that the brain is in a relaxed state; beta waves often indicate that the brain is in a tense state.

[0024] In a feasible implementation, the training process of the three-classification model includes:

[0025] Step a1: collecting the basic information initially input by the subject, calculating the initial stress index, and constructing an initial psychological stress reduction intervention plan;

[0026] Step a2: Based on the psychological stress reduction intervention program, a number of two-dimensional image materials are searched from the database, and a VR scene is constructed through 3D modeling, such as Meshroom open source software, to be played to the subject, thereby initiating a set of psychological stress reduction interventions; physiological data of the subject is collected in real time; the materials are labeled according to a stress reduction index; the stress reduction index can be the inverse of the stress index;

[0027] Step a3: After playing each material, collect the SAM psychological scale results currently input by the subject, update the basic information, and calculate the current stress index until all materials in this group of psychological stress reduction intervention programs are played;

[0028] Step a4: Based on the basic information and current physiological data, a three-classification model is input and a correction signal is output;

[0029] Step a5: adjusting the psychological stress reduction intervention plan based on the correction signal;

[0030] Step a6: iteratively execute step a2 until the pressure index is less than the preset pressure index threshold.

[0031] Through the above method, a reliable three-class classification model can be trained.

[0032] In a feasible implementation, the calculation formula of the pressure index may specifically be:

[0033] SI=σ1*BD+σ2*PD;

[0034] Among them, SI represents the stress index; BD represents the basic information index; σ1 represents the weight of the basic information index; PD represents the physiological data index; σ2 represents the weight of the physiological data index.

[0035] In a feasible implementation manner, the basic information index includes a SAM scale index, and the specific calculation method is:

[0036] After converting the PAD value of ease in the PAD emotional scale to a positive value range, the standard value of ease was obtained; the SAM scale data of the subjects for different materials were collected; the Euclidean distance d between the SAM scale data and the standard value of ease was calculated as the SAM index. The specific formula is:

[0037] ;

[0038] in, 、 and Respectively represent the scale data values ​​of the subjects for different materials; 、 and They respectively represent the numerical values ​​of the relaxed standard.

[0039] In a feasible implementation manner, the basic information index further includes an age coefficient, which is used to perform a multiplication operation correction on the basic information index. The specific value determination method is:

[0040] 0-18 years old is divided into low pressure zone, with a value of 1;

[0041] The age group of 18-60 years old is classified as high-stress zone, with a value of 1.6;

[0042] Those aged 60 and above are classified as the medium pressure zone, with a value of 1.2;

[0043] In this way, it can be reflected that the psychological pressure of middle-aged people is significantly greater than that of the elderly and teenagers, so as to subsequently enhance the intensity of psychological stress relief intervention for middle-aged people.

[0044] In a feasible implementation manner, the physiological data index includes an EEG index, and the specific calculation method is:

[0045] Preprocess the EEG data; divide the EEG data into emotion types and quantify them into emotion values; divide the EEG data into several time periods according to the measurement time, sort them according to the size of the emotion value in each time period, and calculate the first The subjects about The average sentiment of the material The specific formula is:

[0046] ;

[0047] in, Indicates the maximum emotion value; Indicates the median sentiment value; Indicates the minimum sentiment value;

[0048] For each material, the average emotional value of the subjects is calculated and mapped to the [0,1] interval through the maximum value normalization method. The specific formula is:

[0049] ;

[0050] in, Indicates the original value of the current emotion value; Indicates the minimum value among the average emotion values ​​corresponding to each material; Indicates the maximum value of the average emotion values ​​corresponding to each material; Indicates the current sentiment value conversion result.

[0051] In a feasible implementation, the physiological data index further includes a heart rate variability coefficient, which is used to perform a multiplication operation correction on the physiological data index to reflect the subject's inner stability. The specific calculation formula is:

[0052] ;

[0053] in, Indicates the The subjects about Heart rate variability coefficient of each material; Indicates the The subjects about The standard deviation of the heart rate of each material; Indicates the The subjects about The average heart rate of each material;

[0054] described The specific calculation formula is:

[0055] ;

[0056] in, Indicates the statistical number of subjects; Indicates the The subjects about The heart rate of each material; Indicates the The preset heart rate average value of each material;

[0057] described The specific calculation formula is:

[0058] ;

[0059] For the Average heart rate variation coefficient of the material The specific formula is:

[0060] .

[0061] In a feasible implementation, the physiological data index also includes an electrocardiogram index, which is also used to perform product operation correction on the physiological data index to further reflect the subject's inner stability. The specific calculation method is:

[0062] Preprocess the ECG data; perform HRV data analysis on the ECG data and calculate HRV feature values, including SDNN value (standard deviation of all normal sinus beat intervals), RMSSD value (root mean square value of the difference between all adjacent normal sinus beat intervals), and LF / HF ratio (ratio between low-frequency power and high-frequency power). Since the SDNN value, RMSSD value, and LF / HF ratio are related to the degree of emotional stress, high values ​​can reflect increased sympathetic nerve activity, corresponding to emotional classification characteristics such as tension and anxiety, while low values ​​can correspond to emotional classification characteristics such as calmness and tranquility, and significantly reduce anxiety. Therefore, based on the correspondence between the above emotional classification characteristics, an emotional model is constructed: HRV feature values ​​are quantified into emotional values; the emotional values ​​are mapped to the [0,1] interval using the maximum value normalization method to quantify the emotional state and provide reliable physiological data support for emotional analysis. The specific formula is:

[0063] ;

[0064] in, Indicates the current HRV characteristic value; Indicates the minimum value among all HRV characteristic values; Indicates the maximum value among all HRV characteristic values; Represents the normalized result.

[0065] In a feasible implementation, the Spout component is also used to receive the subject's eye movement data, which includes binocular coordinates and eye movement speed; in the Bolt component, the subject's eye movement data is also transmitted backward in real time through the execute method; the feedback adjustment unit also collects the image playback coordinate range of the display area in the VR generation unit, converts the eye movement data into the human eye gaze coordinate range of the display area, and then compares the image playback coordinate range with the human eye gaze coordinate range to calculate the subject's concentration, and adjusts the psychological decompression intervention plan based on the concentration; in this way, eye tracking technology can be used to correlate the focus position of the human eye with the position of the image material in the VR scene, obtain the attractiveness of the image material to the subject and the subject's current concentration level, and synchronously adjust the psychological decompression intervention plan, which is conducive to obtaining a personalized psychological decompression intervention plan that is more suitable for the subject.

[0066] In a feasible implementation, the specific method for calculating concentration is:

[0067] Step b1, collecting the image playback coordinate range D1 of the current frame; based on the standard timing, collecting the current binocular coordinates, and calculating the current human eye gaze coordinate range D2 in the display area through the principle of stereo geometry;

[0068] Step b2: Calculate the number MT of identical coordinates in D1 and D2; calculate the number MX of coordinates of the smaller of D1 and D2; use the ratio of MT to MX as the degree of overlap CH, and perform a determination: if the degree of overlap CH is greater than a preset threshold value, it is determined that the human eye is looking at the image, indicating that the image has attracted the subject's attention and the psychological decompression intervention effect is effective; if the degree of overlap CH is less than or equal to the preset threshold value, it is determined that the human eye is not looking at the image, indicating that the subject may have been distracted and has not entered the psychological decompression intervention state, the image has not attracted the subject's attention, and the psychological decompression intervention effect is weakened or ineffective;

[0069] Step b3: collect the playback coordinate range D1' of the image after time t, and calculate the image displacement speed VS between D1 and D1'. The specific calculation formula can be:

[0070] VS=L / t;

[0071] Wherein, L represents the relative displacement between D1 and D1';

[0072] Step b4, based on the standard timing, collect eye velocity VY at time t;

[0073] Step b5: The ratio of VS to VY is used as the tracking degree SD, and a determination is made: if the tracking degree SD is greater than a preset tracking degree threshold, it is determined that the human eye always follows the movement of the image, indicating that the image is attractive to the subject and the psychological stress reduction intervention effect is effective; if the tracking degree SD is less than or equal to the preset tracking degree threshold, it is determined that the human eye does not always follow the movement of the image, indicating that the image is not attractive to the subject and the psychological stress reduction intervention effect is ineffective;

[0074] Step b6: Calculate the concentration ZZ based on the overlap CH and the follow-up SD. The specific formula can be:

[0075] ZZ=q1*CH+q2*SD;

[0076] Among them, q1 represents the preset weight of the overlap degree; q2 represents the preset weight of the follow-up degree.

[0077] In a feasible implementation, the specific method of adjusting the psychological stress reduction intervention program based on the concentration level is:

[0078] When the concentration ZZ is greater than the preset concentration threshold, it means that the current image material can attract the subject's attention, and the number of times the current image material and the image material with the same stress reduction index are played is increased according to a preset ratio; when the concentration ZZ is less than or equal to the preset concentration threshold, it means that the current image material is less able to attract the subject's attention, and the number of times the current image material and the image material with the same stress reduction index are played is reduced according to a preset ratio.

[0079] In a feasible implementation, the Spout component is further configured to receive the subject's facial expression data, where the facial expression data includes infrared images of glabellar lines and infrared images of crow's feet lines; the three-classification model further includes a convolutional neural network model (CNN), which inputs the glabellar line images and infrared images of crow's feet lines and outputs the facial expression stress classification result; the integrated model is further configured to assign weights to the basic stress classification result, electrocardiogram stress classification result, electroencephalogram stress classification result, skin conductance stress classification result, and facial expression stress classification result, and then output three correction signals, namely enhanced intervention, maintenance intervention, or weakened intervention, so as to dynamically correct the psychological stress reduction intervention plan;

[0080] The glabellar line, also known as the inter-brow line, is a wrinkle formed between the two eyebrows due to the active corrugator supercilii muscle and depressor supercilii muscle. This wrinkle is commonly seen in cases of high psychological stress;

[0081] The crow's feet line refers to the radial wrinkles at the outer corners of the eyes. This wrinkle is commonly seen in cases of a happy mood; [[ID=۸]]

[0082] In this way, the characteristics that facial expression features such as glabellar lines and crow's feet lines are easy to reflect the subject's psychological state can be utilized. Compared with physiological data such as electrocardiogram, electroencephalogram, and skin conductance data, facial expression features are basically not interfered by other factors such as the body state and self-diseases, and can effectively and directly feedback the effect of the psychological stress reduction intervention plan.

[0083] In a feasible implementation, the training process of the convolutional neural network model includes: collecting infrared images of glabellar lines and infrared images of crow's feet lines of several subjects in different psychological states and marking them according to the facial expression stress classification result as a data set; the psychological states include joy, sadness, relaxation, tension, fatigue, and attention, etc.; randomly dividing the data set into a training set and a test set; inputting the training set and the test set into the convolutional neural network model respectively, outputting the facial expression stress classification result, and performing iterative training and testing until the evaluation index requirements are met; the evaluation indexes include mean average precision (mAP), etc.

[0084] In a second aspect, based on the same inventive concept, the present application further provides a personalized psychological stress reduction intervention device for implementing the above personalized psychological stress reduction intervention system, including a VR headset, an ECG device, an EEG device, and a computing platform that are electrically connected to each other;

[0085] The VR headset is used to display a VR scene to enhance the subject's immersive experience;

[0086] The ECG device refers to a wearable electrocardiogram monitoring device, which is used to monitor heart rate variability (HRV) in real time to evaluate the cardiac stress response;

[0087] The EEG device refers to a wearable electroencephalogram (EEG) monitoring device used to record brain waves in real time;

[0088] 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 connects the functional components to transmit information.

[0089] In a feasible embodiment, the VR head display includes an eye tracking sensor for collecting eye movement data of the subject.

[0090] In a feasible embodiment, the VR headset also includes an infrared camera, which is arranged inside the VR headset and is used to capture infrared images of the subject's wrinkles and crow's feet areas; in this way, real-time images of the wrinkles and crow's feet areas can be collected without affecting the VR display effect, and the psychological decompression effect can be fed back and the psychological decompression intervention plan can be corrected.

[0091] By adopting the above technical solution, the present invention has the following beneficial effects:

[0092] The present invention provides a personalized psychological stress reduction intervention system and device, which can immerse subjects in stress reduction through VR technology; and through big data technology and machine learning, collect the subjects' physiological data in real time, provide feedback on the psychological stress reduction intervention effect, intelligently correct VR materials, generate a stress index change curve and an intervention effect evaluation report, and provide personalized stress assessment and stress reduction suggestions; and can also use eye tracking to correlate the focus position of the human eye with the position of the image material in the VR scene to obtain the attractiveness of the image material to the subject and the subject's current concentration level; and can further modify the psychological stress reduction intervention plan by adding facial expression recognition. BRIEF DESCRIPTION OF THE DRAWINGS

[0093] In order to more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the following briefly introduces the drawings required for use in the specific embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0094] Figure 1 A diagram of a personalized psychological stress reduction intervention system provided by an embodiment of the present invention;

[0095] Figure 2 A flow chart of the training process of the three-category model provided in an embodiment of the present invention;

[0096] Figure 3A flowchart of a specific method for calculating concentration provided by an embodiment of the present invention;

[0097] Figure 4 Examples of facial expression data provided by the embodiments of the present invention: Figure a shows an image of crow's feet in a tired state; Figure b shows an image of crow's feet in a relaxed state; Figure c shows an image of crow's feet in a happy state; Figure d shows an image of a "Chuan" (cross) wrinkle in a sad state; Figure e shows an image of a "Chuan" (cross) wrinkle in a focused state; and Figure f shows an image of a "Chuan" (cross) wrinkle in a tense state.

[0098] Figure 5 A schematic diagram of the main structure of a VR head-mounted display provided by an embodiment of the present invention;

[0099] Figure 6 A schematic diagram of the structure of an ECG device provided in an embodiment of the present invention;

[0100] Reference numerals:

[0101] 1-VR headset; 11-first acquisition unit; 12-second acquisition unit; 2-ECG device; 21-reference electrode; 22-active electrode. DETAILED DESCRIPTION

[0102] The technical solution of the present invention will be clearly and completely described below with reference to the accompanying drawings. Obviously, the embodiments described are only some embodiments of the present invention, not all embodiments. All other embodiments obtained by ordinary technicians in this field based on the embodiments of the present invention without making any creative efforts shall fall within the scope of protection of the present invention.

[0103] In the description of the present invention, it should be noted that the terms "center," "upper," "lower," "left," "right," "vertical," "horizontal," "inner," and "outer," etc., indicating orientations or positional relationships, are based on the orientations or positional relationships shown in the accompanying drawings and are intended solely to facilitate and simplify the description of the present invention. They are not intended to indicate or imply that the devices or components referred to must have, be constructed, or operate in a specific orientation, and therefore should not be construed as limitations on the present invention. Furthermore, the terms "first," "second," and "third" are used for descriptive purposes only and should not be construed as indicating or implying relative importance.

[0104] In the description of the present invention, it should be noted that, unless otherwise expressly specified or limited, the terms "mounted," "connected," and "connected" should be understood in a broad sense. For example, they may refer to fixed, detachable, or integral connections; mechanical or electrical connections; direct or indirect connections through an intermediate medium; and internal communication between two components. Those skilled in the art will understand the specific meanings of the above terms in the present invention based on the specific circumstances.

[0105] It should also be noted that the following specific embodiments or specific implementations are a series of optimized settings listed in the present invention to further explain the specific content of the invention, and these settings can be combined or used in association with each other.

[0106] The present invention will be further explained below with reference to specific embodiments.

[0107] Example 1:

[0108] like Figure 1 As shown, this embodiment provides a personalized psychological stress reduction intervention system, including a data acquisition module, a data processing module and a result generation module;

[0109] The data collection module is built based on the Apache Storm system, including Spout components and several Bolt components:

[0110] The Spout component is used to receive the subject's physiological data and basic information in real time; the physiological data includes electrocardiogram (ECG) data, electroencephalogram (EEG) data, and skin conductance data; the basic information includes age, gender, social attributes, stress environment characteristics, and psychological scale results (such as the SAM scale, the Psychological Resilience Recovery Scale, and the Positive and Negative Psychology Scale);

[0111] The Bolt component stores a pre-trained three-classification model for outputting three correction signals: enhancing intervention, maintaining intervention, or weakening intervention;

[0112] The three classification models specifically include a tree model, a time series classification model, and an integrated model;

[0113] The tree model outputs a basic pressure classification result based on the basic information;

[0114] The time series classification model, such as RNN, LSTM, and attention model, outputs an electrocardiogram (ECG) stress classification result, an electroencephalogram (EEG) stress classification result, and a skin conduction stress classification result based on the normalized values ​​of the ECG data, EEG data, and skin conduction data, respectively; each classification result is set as an integer between 0 and 10, with a larger value indicating greater psychological stress;

[0115] The integrated model is used to assign weights to the basic stress classification results, the electrocardiographic stress classification results, the electroencephalographic stress classification results, and the skin conductivity stress classification results, and then perform summation calculations, compare the calculated results with a preset intervention threshold, and output three correction signals: enhanced intervention, maintained intervention, or weakened intervention, so as to dynamically correct the psychological decompression intervention plan; the preset intervention threshold includes a first intervention threshold and a second intervention threshold, and the first intervention threshold is less than the second intervention threshold: when the calculated result is less than the first intervention threshold, a correction signal for weakening intervention is output; when the calculated result is greater than or equal to the first intervention threshold and less than the second intervention threshold, a correction signal for maintaining intervention is output; when the calculated result is greater than or equal to the second intervention threshold, a correction signal for enhancing intervention is output;

[0116] The data processing module includes a pressure index unit, a database, a VR (virtual reality) generation unit, a feedback adjustment unit, and an evaluation and analysis unit;

[0117] The stress index unit calculates the subject's stress index (Stress Index) based on the physiological data and the basic information, so as to assess the subject's psychological stress level;

[0118] The database stores two-dimensional image materials; the two-dimensional image materials are selected based on the IAPS International Emotional Image System and the CAPS Chinese Emotional Image System, with a pleasure level (Valence) of 6.5 or higher, an arousal level of 3.5 or lower, and a dominance level of 5-7, so as to serve as a reference for constructing VR scenes;

[0119] The VR generation unit, based on the psychological stress reduction intervention program, selects two-dimensional image materials from the database, converts the two-dimensional image materials into three-dimensional images using Meshroom open source software, and constructs a VR scene to play to the subject; the VR scene includes images and sounds;

[0120] The feedback adjustment unit adjusts the psychological stress reduction intervention plan based on the correction signal, thereby obtaining a personalized psychological stress reduction intervention plan; the psychological stress reduction intervention plan includes the category of the material, the play order, the stress reduction index and the number of plays;

[0121] The evaluation and analysis unit generates a pressure index change curve and an intervention effect evaluation report based on the pressure index; the intervention effect evaluation report determines an intervention conclusion, such as "pressure reduction intervention is effective" or "pressure reduction intervention is ineffective," based on the pressure index change curve and a preset pressure index threshold;

[0122] The result generation module is used to send out the pressure index change curve and the intervention effect evaluation report.

[0123] Through the above system, VR technology can be used to immerse subjects in stress relief. And through big data technology and machine learning, the physiological data of the subjects can be collected in real time, the effects of psychological stress relief intervention can be fed back, VR materials can be intelligently corrected, stress index change curves and intervention effect evaluation reports can be generated, and personalized stress assessment and stress relief suggestions can be provided.

[0124] Furthermore, the Spout component initializes the data stream through the initialize method, so that the Spout component accurately receives the physiological data and basic information of the subject; and connects to the Bolt component through the nextTuple method, so that the Spout component effectively transmits the data stream to the next Bolt component in the topology.

[0125] Furthermore, in the Bolt component, the three-classification model is called through the execute method to perform three-classification on the subject's physiological data and basic information in real time.

[0126] Furthermore, the EEG data includes alpha waves and / or beta waves, and these two wave bands are related to psychological stress: alpha waves can often indicate that the brain is in a relaxed state; beta waves can often indicate that the brain is in a tense state.

[0127] Furthermore, if Figure 2 As shown, the training process of the three-classification model includes:

[0128] Step a1: collecting the basic information initially input by the subject, calculating the initial stress index, and constructing an initial psychological stress reduction intervention plan;

[0129] Step a2: Based on the psychological stress reduction intervention program, a number of two-dimensional image materials are searched from the database, and a VR scene is constructed using Meshroom open source software and played to the subject, thereby initiating a set of psychological stress reduction interventions; the subject's physiological data is collected in real time; the materials are labeled according to a stress reduction index; the stress reduction index can be the inverse of the stress index;

[0130] Step a3: After playing each material, collect the SAM psychological scale results currently input by the subject, update the basic information, and calculate the current stress index until all materials in this group of psychological stress reduction intervention programs are played;

[0131] Step a4: Based on the basic information and current physiological data, a three-classification model is input and a correction signal is output;

[0132] Step a5: adjusting the psychological stress reduction intervention plan based on the correction signal;

[0133] Step a6: iteratively execute step a2 until the pressure index is less than the preset pressure index threshold.

[0134] Through the above method, a reliable three-class classification model can be trained.

[0135] Furthermore, the calculation formula of the pressure index may be specifically:

[0136] SI=σ1*BD+σ2*PD;

[0137] Among them, SI represents the stress index; BD represents the basic information index; σ1 represents the weight of the basic information index; PD represents the physiological data index; σ2 represents the weight of the physiological data index.

[0138] Furthermore, the basic information index includes the SAM scale index, and the specific calculation method is:

[0139] After converting the PAD value of ease in the PAD emotional scale to a positive value range, the standard value of ease was obtained; the SAM scale data of the subjects for different materials were collected; the Euclidean distance d between the SAM scale data and the standard value of ease was calculated as the SAM index. The specific formula is:

[0140] ;

[0141] in, 、 and Respectively represent the scale data values ​​of the subjects for different materials; 、 and They respectively represent the numerical values ​​of the relaxed standard.

[0142] Furthermore, the basic information index also includes an age coefficient, which is used to perform a multiplication operation correction on the basic information index. The specific value determination method is:

[0143] 0-18 years old is divided into low pressure zone, with a value of 1;

[0144] The age group of 18-60 years old is classified as high-stress zone, with a value of 1.6;

[0145] Those aged 60 and above are classified as the medium pressure zone, with a value of 1.2;

[0146] In this way, it can be reflected that the psychological pressure of middle-aged people is significantly greater than that of the elderly and teenagers, so as to subsequently enhance the intensity of psychological stress relief intervention for middle-aged people.

[0147] Furthermore, the physiological data index includes an EEG index, and the specific calculation method is:

[0148] Preprocess the EEG data; divide the EEG data into emotion types and quantify them into emotion values; divide the EEG data into several time periods according to the measurement time, sort them according to the size of the emotion value in each time period, and calculate the first The subjects about The average sentiment of the material The specific formula is:

[0149] ;

[0150] in, Indicates the maximum emotion value; Indicates the median sentiment value; Indicates the minimum sentiment value;

[0151] For each material, the average emotional value of the subjects is calculated and mapped to the [0,1] interval through the maximum value normalization method. The specific formula is:

[0152] ;

[0153] in, Indicates the original value of the current emotion value; Indicates the minimum value among the average emotion values ​​corresponding to each material; Indicates the maximum value of the average emotion values ​​corresponding to each material; Indicates the current sentiment value conversion result.

[0154] Furthermore, the physiological data index also includes a heart rate variability coefficient, which is used to perform a multiplication operation on the physiological data index to reflect the subject's inner stability. The specific calculation formula is:

[0155] ;

[0156] in, Indicates the The subjects about Heart rate variability coefficient of each material; Indicates the The subjects about The standard deviation of the heart rate of each material; Indicates the The subjects about The average heart rate of each material;

[0157] described The specific calculation formula is:

[0158] ;

[0159] in, Indicates the statistical number of subjects; Indicates the The subjects about The heart rate of each material; Indicates the The preset heart rate average value of each material;

[0160] described The specific calculation formula is:

[0161] ;

[0162] For the Average heart rate variation coefficient of the material The specific formula is:

[0163] .

[0164] Furthermore, the physiological data index also includes an electrocardiogram index, which is also used to perform product calculation correction on the physiological data index to further reflect the subject's inner stability. The specific calculation method is:

[0165] Preprocess the ECG data; perform HRV data analysis on the ECG data and calculate HRV feature values, including SDNN value (standard deviation of all normal sinus beat intervals), RMSSD value (root mean square value of the difference between all adjacent normal sinus beat intervals), and LF / HF ratio (ratio between low-frequency power and high-frequency power). Since the SDNN value, RMSSD value, and LF / HF ratio are related to the degree of emotional stress, high values ​​can reflect increased sympathetic nerve activity, corresponding to emotional classification characteristics such as tension and anxiety, while low values ​​can correspond to emotional classification characteristics such as calmness and tranquility, and significantly reduce anxiety. Therefore, based on the correspondence between the above emotional classification characteristics, an emotional model is constructed: HRV feature values ​​are quantified into emotional values; the emotional values ​​are mapped to the [0,1] interval using the maximum value normalization method to quantify the emotional state and provide reliable physiological data support for emotional analysis. The specific formula is:

[0166] ;

[0167] in, Indicates the current HRV characteristic value; Indicates the minimum value among all HRV characteristic values; Indicates the maximum value among all HRV characteristic values; Represents the normalized result.

[0168] Furthermore, the Spout component is also used to receive the subject's eye movement data, which includes binocular coordinates and eye movement speed; in the Bolt component, the subject's eye movement data is also transmitted backward in real time through the execute method; the feedback adjustment unit also collects the image playback coordinate range of the display area in the VR generation unit, converts the eye movement data into the human eye gaze coordinate range of the display area, and then compares the image playback coordinate range with the human eye gaze coordinate range to calculate the subject's concentration, and adjusts the psychological decompression intervention plan based on the concentration; in this way, eye tracking technology can be used to correlate the focus position of the human eye with the position of the image material in the VR scene, obtain the attractiveness of the image material to the subject and the subject's current concentration level, and synchronously adjust the psychological decompression intervention plan, which is conducive to obtaining a personalized psychological decompression intervention plan that is more suitable for the subject.

[0169] Furthermore, if Figure 3 As shown in the figure, the specific calculation method of concentration is:

[0170] Step b1, collecting the image playback coordinate range D1 of the current frame; based on the standard timing, collecting the current binocular coordinates, and calculating the current human eye gaze coordinate range D2 in the display area through the principle of stereo geometry;

[0171] Step b2: Calculate the number MT of identical coordinates in D1 and D2; calculate the number MX of coordinates of the smaller of D1 and D2; use the ratio of MT to MX as the degree of overlap CH, and perform a determination: if the degree of overlap CH is greater than a preset threshold value, it is determined that the human eye is looking at the image, indicating that the image has attracted the subject's attention and the psychological decompression intervention effect is effective; if the degree of overlap CH is less than or equal to the preset threshold value, it is determined that the human eye is not looking at the image, indicating that the subject may have been distracted and has not entered the psychological decompression intervention state, the image has not attracted the subject's attention, and the psychological decompression intervention effect is weakened or ineffective;

[0172] Step b3: collect the playback coordinate range D1' of the image after time t, and calculate the image displacement speed VS between D1 and D1'. The specific calculation formula can be:

[0173] VS=L / t;

[0174] Wherein, L represents the relative displacement between D1 and D1';

[0175] Step b4, based on the standard timing, collect eye velocity VY at time t;

[0176] Step b5: Take the ratio of VS to VY as the follow-up degree SD and make a determination. If the follow-up degree SD is greater than the preset follow-up degree threshold, it is determined that the human eye always follows the image movement, indicating that the image is attractive to the subject and the psychological stress reduction intervention is effective. If the follow-up degree SD is less than or equal to the preset follow-up degree threshold, it is determined that the human eye does not always follow the image movement, indicating that the image is not attractive to the subject and the psychological stress reduction intervention fails.

[0177] Step b6: Calculate the concentration degree ZZ based on the coincidence degree CH and the follow-up degree SD. The specific formula can be:

[0178] ZZ = q1 * CH + q2 * SD;

[0179] Where, q1 represents the preset weight of the coincidence degree; q2 represents the preset weight of the follow-up degree.

[0180] Further, the specific method for adjusting the psychological stress reduction intervention plan based on the concentration degree is as follows:

[0181] When the concentration degree ZZ is greater than the preset concentration degree threshold, it indicates that the current image material can attract the attention of the subject. Then, increase the playback times of the current image material and the image materials with the same stress reduction index by a preset ratio. When the concentration degree ZZ is less than or equal to the preset concentration degree threshold, it indicates that the current image material is not very attractive to the subject. Then, reduce the playback times of the current image material and the image materials with the same stress reduction index by a preset ratio.

[0182] Further, the Spout component is also used to receive the expression data of the subject. The expression data includes the infrared image of the glabellar lines and the infrared image of the crow's feet lines. The three-classification model also includes a convolutional neural network model (CNN). Input the glabellar line image and the infrared image of the crow's feet lines, and output the expression stress classification result. The integrated model is also used to assign weights to the basic stress classification result, the electrocardiogram stress classification result, the electroencephalogram stress classification result, the skin conductance stress classification result, and the expression stress classification result, and then output three correction signals, namely enhanced intervention, maintenance intervention, or weakened intervention, so as to dynamically correct the psychological stress reduction intervention plan.

[0183] The glabellar lines, also known as the inter-brow lines, are the wrinkles formed between the two eyebrows due to the activation of the corrugator supercilii muscle and the depressor supercilii muscle. These wrinkles are common in cases of high psychological stress.

[0184] The crow's feet lines refer to the radial wrinkles at the outer corners of the eyes. These wrinkles are common in cases of a happy mood.

[0185] In this way, facial expression features such as glabellar lines and crow's feet can be utilized, which are easy to reflect the psychological state of the subjects. Compared with physiological data such as electrocardiogram, electroencephalogram, and skin conductance data, facial expression features are basically not interfered by other factors such as the body state and self-diseases, and can effectively and directly feedback the effect of the psychological decompression intervention plan.

[0186] Further, the training process of the convolutional neural network model includes:

[0187] Collect infrared images of glabellar lines and crow's feet of several subjects in different psychological states and mark them according to the classification results of expression stress as a data set;

[0188] The psychological states include joy, sadness, relaxation, tension, fatigue, and attention, etc.;

[0189] Exemplarily, as Figure 4 shown, where Figure a is an infrared image of crow's feet in a fatigue state; Figure b is an infrared image of crow's feet in a relaxed state; Figure c is an infrared image of crow's feet in a joy state; Figure d is an infrared image of glabellar lines in a sad state; Figure e is an infrared image of glabellar lines in an attention state; Figure f is an infrared image of glabellar lines in a tense state;

[0190] Randomly divide the data set into a training set and a test set;

[0191] Input the training set and the test set into the convolutional neural network model respectively, output the classification results of expression stress, and perform iterative training and testing until the requirements of the evaluation index are met;

[0192] The evaluation index includes mean average precision (mAP), etc.

[0193] Example 2:

[0194] This embodiment provides a personalized psychological decompression intervention device for implementing the above personalized psychological decompression intervention system, including a VR headset, an ECG device, an EEG device, and a computing platform;

[0195] The VR headset is used to display a VR scene to enhance the immersive experience of the subject;

[0196] The ECG device refers to a wearable electrocardiogram monitoring device, and the electrodes are attached to the chest of the subject, etc., for real-time monitoring of heart rate variability (HRV) to evaluate the cardiac stress response;

[0197] The EEG device refers to a wearable electroencephalogram monitoring device, which is worn on the head of the subject for real-time recording of brain waves, and conventional devices can be used;

[0198] 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 connects the functional components to transmit information.

[0199] Furthermore, if Figure 5 As shown, a first acquisition unit 11 is provided at the center of the front end of the VR head display 1; a second acquisition unit 12 is provided on both sides of the VR head display 1;

[0200] The first acquisition unit 11 is provided with an eye tracking sensor and a first infrared camera: the eye tracking sensor is used to collect the subject's eye movement data; the first infrared camera is used to capture an infrared image of the subject's ridge area;

[0201] The second collecting unit 12 is provided with a second infrared camera for capturing an infrared image of the subject's crow's feet area;

[0202] In this way, the subject's eye movement data, infrared images of the Sichuan character line area and infrared images of the crow's feet area can be collected in real time without affecting the VR display effect, which is conducive to feedback on the psychological decompression effect and correction of the psychological decompression intervention plan.

[0203] Furthermore, if Figure 6 As shown, the surface of the ECG device 2 is provided with a reference electrode 21 and an active electrode 22 for collecting the subject's heart rate electrical signal in real time; the shell of the ECG device 2 is made of medical-grade silicone to provide a comfortable touch.

[0204] 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 above embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the above embodiments, or replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A personalized psychological stress relief intervention system, characterized in that: It includes data acquisition module, data processing module and result generation module; The data collection module is built based on the Apache Storm system, including Spout components and several Bolt components: The Spout component is used to receive the subject's physiological data and basic information in real time; the physiological data includes electrocardiogram data, electroencephalogram data, and skin conductance data; the basic information includes age, gender, social attributes, stress environment characteristics, and psychological scale results; The Bolt component stores a pre-trained three-classification model for outputting three correction signals: enhancing intervention, maintaining intervention, or weakening intervention; The three classification models specifically include a tree model, a time series classification model, and an integrated model; The tree model outputs a basic pressure classification result based on the basic information; The time series classification model outputs electrocardiographic pressure classification results, electroencephalographic pressure classification results, and skin conductivity pressure classification results based on the normalized values ​​of the electrocardiographic data, the electroencephalographic data, and the skin conductivity data; Each classification result is set as an integer between 0 and 10, with a larger value indicating greater psychological stress; The integrated model is used to assign weights to the basic stress classification results, the electrocardiographic stress classification results, the electroencephalographic stress classification results, and the skin conductivity stress classification results, and then perform summation calculations, compare the calculated results with a preset intervention threshold, and output three correction signals: enhanced intervention, maintained intervention, or weakened intervention, so as to dynamically correct the psychological decompression intervention plan; the preset intervention threshold includes a first intervention threshold and a second intervention threshold, and the first intervention threshold is less than the second intervention threshold: when the calculated result is less than the first intervention threshold, a correction signal for weakening intervention is output; when the calculated result is greater than or equal to the first intervention threshold and less than the second intervention threshold, a correction signal for maintaining intervention is output; when the calculated result is greater than or equal to the second intervention threshold, a correction signal for enhancing intervention is output; The data processing module includes a pressure index unit, a database, a VR generation unit, a feedback adjustment unit, and an evaluation and analysis unit; The stress index unit calculates the stress index of the subject based on the physiological data and the basic information, so as to assess the psychological stress level of the subject; The database stores two-dimensional image materials; The VR generation unit selects two-dimensional image materials from a database based on the psychological stress reduction intervention program, converts the two-dimensional image materials into three-dimensional images through 3D modeling, and constructs a VR scene to play to the subject; the VR scene includes images and sounds; The feedback adjustment unit adjusts the psychological stress reduction intervention plan based on the correction signal, thereby obtaining a personalized psychological stress reduction intervention plan; the psychological stress reduction intervention plan includes the category of the material, the play order, the stress reduction index and the number of plays; The evaluation and analysis unit generates a stress index change curve and an intervention effect evaluation report based on the stress index; The result generation module is used to send out the pressure index change curve and intervention effect evaluation report; The Spout component is also used to receive the subject's eye movement data, which includes binocular coordinates and eye movement speed; in the Bolt component, the subject's eye movement data is also transmitted backward in real time through the execute method; the feedback adjustment unit also collects the image playback coordinate range of the display area in the VR generation unit, converts the eye movement data into the human eye gaze coordinate range of the display area, and then compares the image playback coordinate range with the human eye gaze coordinate range to calculate the subject's concentration, and adjusts the psychological decompression intervention plan based on the concentration.

2. The system according to claim 1, wherein: The Spout component initializes the data stream through the initialize method, so that the Spout component accurately receives the physiological data and basic information of the subject; and connects to the Bolt component through the nextTuple method, so that the Spout component effectively transmits the data stream to the next Bolt component in the topology structure.

3. The system according to claim 1, wherein: The training process of the three-classification model includes: Step a1: collecting the basic information initially input by the subject, calculating the initial stress index, and constructing an initial psychological stress reduction intervention plan; Step a2: Based on the psychological stress reduction intervention program, a number of two-dimensional image materials are searched from the database, and a VR scene is constructed through 3D modeling and played to the subject to initiate a set of psychological stress reduction interventions; physiological data of the subject is collected in real time; the materials are labeled according to the stress reduction index; the stress reduction index is the opposite of the stress index; Step a3: After playing each material, collect the SAM psychological scale results currently input by the subject, update the basic information, and calculate the current stress index until all materials in this group of psychological stress reduction intervention programs are played; Step a4: Based on the basic information and current physiological data, a three-classification model is input and a correction signal is output; Step a5: adjusting the psychological stress reduction intervention plan based on the correction signal; Step a6: iteratively execute step a2 until the pressure index is less than the preset pressure index threshold.

4. The system according to claim 1, wherein: The calculation formula of the pressure index is: SI=σ1*BD+σ2*PD; Among them, SI represents the stress index; BD represents the basic information index; σ1 represents the weight of the basic information index; PD represents the physiological data index; σ2 represents the weight of the physiological data index.

5. The system according to claim 1, wherein: The basic information index includes the SAM scale index, and the specific calculation method is: After converting the PAD value of ease in the PAD emotional scale to a positive value range, the standard value of ease was obtained; the SAM scale data of the subjects for different materials were collected; the Euclidean distance d between the SAM scale data and the standard value of ease was calculated as the SAM index. The specific formula is: Among them, xd, yd and zd represent the scale data values ​​of the subjects for different materials; x0, y0 and z0 represent the standard values ​​of ease.

6. The system according to claim 1, wherein: The physiological data index includes the EEG index, and the specific calculation method is: Preprocess the EEG data; divide the EEG data into emotion types and quantify them into emotion values; divide the EEG data into several time periods according to the measurement time, sort them according to the size of the emotion value in each time period, and calculate the average emotion S of the i-th subject for the m-th material. mi The specific formula is: <h2 style=";text-align:left;direction:ltr">S<h2 style=";text-align:left;direction:ltr"> mi <h2 style=";text-align:left;direction:ltr"> (S1+S2+S3) / 3 Among them, S1 represents the maximum emotion value; S2 represents the median emotion value; S3 represents the minimum emotion value; For each material, the average emotional value of the subjects is calculated and mapped to the [0,1] interval through the maximum value normalization method. The specific formula is: A scale =(A-A min ) / (A max -A min ) Among them, A represents the original value of the current emotion value; A min Indicates the minimum value among the average emotion values ​​corresponding to each material; A max Indicates the maximum value of the average emotion values ​​corresponding to each material; A scale Indicates the current emotional value conversion result; The physiological data index also includes an electrocardiogram index, and the specific calculation method is as follows: Preprocess the ECG data; perform HRV data analysis on the ECG data and calculate HRV feature values, including SDNN value, RMSSD value, and LF / HF ratio; high HRV feature values ​​correspond to emotional classification features of tension and anxiety, while low HRV feature values ​​correspond to emotional classification features of calmness and tranquility. Based on the correspondence between emotional classification features, construct an emotional model: quantize the HRV feature values ​​into emotional values; use the maximum value normalization method to map the emotional values ​​to the range [0,1]. The specific formula is: HRV norm =(HRV current -HRV min ) / (HRV max -HRV min ) Among them, HRV current Indicates the current heart rate variability characteristic value; HRV min Represents the minimum value of all heart rate variability characteristic values; HRV max Represents the maximum value of all heart rate variability characteristic values; HRV norm Represents the normalized result.

7. The system according to claim 1, wherein: The specific calculation method of concentration is: Step b1, collecting the image playback coordinate range D1 of the current frame; based on the standard timing, collecting the current binocular coordinates, and calculating the current human eye gaze coordinate range D2 in the display area through the principle of stereo geometry; Step b2: Calculate the number MT of identical coordinates in D1 and D2; calculate the number MX of coordinates of the smaller of D1 and D2; use the ratio of MT to MX as the degree of overlap CH, and perform a determination: if the degree of overlap CH is greater than a preset threshold, it is determined that the human eye is looking at the image; if the degree of overlap CH is less than or equal to the preset threshold, it is determined that the human eye is not looking at the image; Step b3: Collect the playback coordinate range D1' of the image after time t, and calculate the image displacement speed VS between D1 and D1'. The specific calculation formula is: VS = L / t; Wherein, L represents the relative displacement between D1 and D1'; Step b4: Based on the standard time sequence, collect the eye movement velocity VY at time t; Step b5: Using the ratio of VS to VY as the tracking degree SD, and performing a determination: if the tracking degree SD is greater than a preset tracking degree threshold, it is determined that the human eye always follows the movement of the image; if the tracking degree SD is less than or equal to the preset tracking degree threshold, it is determined that the human eye does not always follow the movement of the image; Step b6: Calculate the concentration ZZ based on the overlap CH and the follow-up SD. The specific formula is: ZZ=q1*CH+q2*SD; Among them, q1 represents the preset weight of the overlap degree; q2 represents the preset weight of the follow-up degree.

8. The system according to claim 1, wherein: The Spout component is also used to receive the subject's facial expression data, which includes infrared images of Sichuan wrinkles and infrared images of crow's feet. The three-classification model also includes a convolutional neural network model, which inputs the infrared images of Sichuan wrinkles and infrared images of crow's feet and outputs facial expression stress classification results. The integrated model is also used to assign weights to the basic pressure classification results, electrocardiographic pressure classification results, electroencephalographic pressure classification results, skin conductivity pressure classification results, and facial expression stress classification results, and output three correction signals: enhanced intervention, maintained intervention, or weakened intervention.

9. A personalized psychological stress reduction intervention device implementing the system according to any one of claims 1 to 8, characterized in that: including a VR headset, an ECG device, an EEG device, and a computing platform electrically connected to each other; The VR head display is used to display the VR scene; The ECG device refers to a wearable electrocardiogram monitoring device used to monitor heart rate variability in real time; The EEG device refers to a wearable electroencephalogram (EEG) monitoring device used to record 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. The bus connects the functional components to transmit information.

Images