A method and system for screening student mental health groups

Abstract

The present invention discloses a method for screening a group of students' mental health, which relates to the technical field of mental health prevention and treatment, and includes the following steps: a front-end high-frequency camera collects videos of students' facial and neck muscle groups; obtains the frequency and amplitude parameters of tiny vibrations generated by subtle movements of head muscles from the video; obtains mapping parameters and brain wave information through a psychological and physiological parameter extraction algorithm; compares with an emotional algorithm model to quickly calculate the emotional state of students; evaluates the emotional state of students and creates archives; screens out high-risk suspicious students with abnormal emotions and automatically issues an early warning; records and tracks abnormal students and conducts consultation and communication. The present invention also proposes a group screening system for student mental health. It can realize non-contact AI emotion recognition, rapid detection, and large-scale group screening, and can timely grasp group cognition and psychological changes, improve governance capabilities and levels, and effectively maintain the psychological stability of campus groups.

Description

Technical Field

[0001] The present invention belongs to the technical field of online psychological cloud platforms, and specifically relates to a method and system for screening a group of students' mental health. Background Art

[0002] At present, psychological scales and brain wave detectors are commonly used for college students' mental health screening, but they have the following shortcomings: psychological scales, 1. Most of the scales currently used (SCL-90, UPI, EPQ, 16PF, etc.) are foreign translation scales, which cannot fully reflect the characteristics of college students in my country. There is a lack of basis and verification for the establishment of screening standards for questionnaires introduced from abroad. The existing norms of some scales are too old. In actual applications, the test results vary greatly and need to be tested once every three months; 2. The tools used by various universities to screen college students' psychological problems are not unified, which is not conducive to the Ministry of Education and other relevant departments and institutions to understand and grasp the current situation of college students' mental health in my country; 3. Group detection is time-consuming and labor-intensive, and requires special guidance. Although the brain wave detector can be used for small-scale detection and the test results are accurate, it is a touch detection and cannot be used for large-scale detection. For this reason, the present invention proposes a student mental health group screening system according to demand. Summary of the invention

[0003] The purpose of the present invention is to solve the above shortcomings in the prior art and propose a method and system for group screening of student mental health, which can realize non-contact AI emotion recognition, 30-60s rapid detection, and large-scale group screening.

[0004] In order to achieve the above object, the present invention adopts the following technical solutions:

[0005] Design a method for screening student mental health groups, which includes the following steps:

[0006] Step 1: Use the front-end high-frequency camera to collect 30-60 seconds of video of the student's facial and neck muscle groups;

[0007] Step 2: Obtain the frequency and amplitude parameters of tiny vibrations generated by the vestibular organs controlling the subtle movements of the head muscles;

[0008] Step 3: According to the mapping relationship between brain waves and psychological and physiological parameters, the vibration frequency and amplitude parameters obtained in step 2 are converted between video and electroencephalogram, and between video image and HRV through the psychological and physiological parameter extraction algorithm to obtain mapping parameters and brain wave information;

[0009] Step 4: Compare the mapping parameters and brain wave information obtained in step 3 with the emotion algorithm model in the basic feature database, and quickly calculate the student's emotional state;

[0010] Step 5: Evaluate the emotional state of students counted in step 4 and create a profile;

[0011] Step 6: Screen out high-risk suspicious students with abnormal emotions, and test the screened students once a week. If the students have abnormal emotions for three consecutive times, the system will mark the students with abnormal emotions and automatically issue an early warning;

[0012] Step 7: Record and track the abnormal students in Step 5, and conduct online and / or offline face-to-face communication until their emotions stabilize and the tracking and testing is terminated.

[0013] Furthermore, in step 1, before the video is captured, the camera needs to set the video capture filter and the video screenshot format to debug the image.

[0014] Furthermore, in step 2, the minute vibration frequency and amplitude parameters are motion parameters of the head points, and there are differences in optical contrast between points, forming vibration imaging at each point.

[0015] Further, the optical contrast difference includes the following:

[0016] The change in the amplitude of the signal at each point in space;

[0017] The formula is:

[0018] Among them: U x，y，i The signal at point (x, y) in the i-th frame, U x，y，(i+1) The signal amount at the point (x, y) in the i+1th frame, N is the number of frames of the accumulated vibration image amplitude component;

[0019] The frequency of the signal changes at each point in space;

[0020] The formula is:

[0021] Where: Δ i is the inter-frame difference of the image at the i-th point (1 for difference and 0 for no difference), and N is the number of frames of the accumulated vibration image amplitude component;

[0022] The emotion algorithm model is derived from formula (1) and formula (2):

[0023]

[0024] Among them, E i For a certain emotional state, is the temporal variation (frequency) of work done by a person's head in the form of micro-vibrations, is the spatial distribution of work done by a person's head in the form of micro-vibrations (displacement); i For the corresponding relationship.

[0025] Furthermore, in step 4, the emotion model algorithm includes an aggression model algorithm, a stress model algorithm, a suspicion model algorithm, a balance model algorithm, a charm model algorithm, a vitality model algorithm, a self-regulation model algorithm, an inhibition model algorithm, a neuroticism model algorithm, a depression model algorithm, a happiness model algorithm, an extroversion model algorithm and a stability model algorithm.

[0026] Among them, the model algorithm equation of the aggressiveness value is:

[0027]

[0028] Where m is the maximum frequency in the frequency distribution density histogram; F i is the i-th frequency in the frequency distribution density histogram; F in is the input processing vibration frequency; n is the count of the frame difference within N frames that is greater than the threshold;

[0029] The model algorithm equation for the pressure value is:

[0030]

[0031] in, is the total amplitude of the i-th line vibration frequency component on the left side of the object; is the total amplitude of the frequency component of the ith line vibration on the right side of the object; for The maximum value between is the maximum frequency of the vibration frequency component of the i-th row on the left side of the object; is the maximum frequency of the vibration frequency component of the i-th row on the right side of the object for The maximum value between ; n is the number of rows occupied by the image;

[0032] The model algorithm equation for anxiety value is:

[0033]

[0034] Among them, P i (f) is the spectral power of the vibration frequency distribution; f max is the maximum frequency in the vibration frequency distribution spectrum;

[0035] The model algorithm equation for suspicious values ​​is:

[0036]

[0037] Among them, E1 is the level of aggression; E2 is the level of stress; E3 is the level of anxiety;

[0038] The equation for the equilibrium value is:

[0039] E5 = Bl = (100 - 2Va)%, (Formula 8)

[0040] Among them, Va is the calculated sum of the variability of emotion parameters;

[0041] The model algorithm equation of charm value is:

[0042]

[0043] Among them, W li -W ri is the difference between the left and right average amplitudes of the vibration image amplitude component of each line; C li -C ri is the difference between the maximum frequency values ​​on the left and right sides of the amplitude component of the vibration image for each line; N is the number of frames in the processing process;

[0044] The model algorithm equation of vitality value is:

[0045]

[0046] Where M is the maximum value of the count on the frequency histogram; σ is the standard deviation of the vibration frequency, calculated from the frequency histogram; F ps Enter the maximum value of the frequency for the vibration image;

[0047] The model algorithm equation for the self-regulating value is:

[0048]

[0049] Wherein, E5 is the average value of the balance parameter during the measurement process; dE5 is the variation range of the balance parameter; E6 is the average value of the charm value parameter during the measurement process; dE6 is the variation range of the charm value parameter;

[0050] The model algorithm equation for the inhibition value is:

[0051]

[0052] Where F1 is the vibration change frequency; T m is the average period of vibration frequency change; T: vibration period measurement;

[0053] The model algorithm equation for neuroticism is:

[0054] E10=Nr=10σ(E9), (Formula 13)

[0055] Where, σ(E9) is the standard deviation of the E9 (inhibition) value;

[0056] The model algorithm equation for depression value is:

[0057]

[0058] Wherein, σ is the standard deviation of the vibration frequency in the frequency histogram; M is the average value of the vibration frequency in the frequency histogram;

[0059] The model algorithm equation of happiness value is:

[0060]

[0061] Where I is the information validity of the psychological and physiological state; E is the energy reduction characteristic of the psychological and physiological state; dI is the change in the information validity of the psychological and physiological state; dE is the change in the energy reduction characteristic of the psychological and physiological state;

[0062] The model algorithm equation for the extraversion value is:

[0063]

[0064] Among them, R IE is the Pearson correlation coefficient between information efficiency (I) and energy consumption (E).

[0065] The model algorithm equation for the stability value is:

[0066]

[0067] Among them, K is the normalization coefficient of the frequency histogram, and y' is the normal distribution density;

[0068]

[0069]

[0070] Furthermore, the students’ emotional states are parameters calculated from the calculated values, standard deviations, and variance values.

[0071] The present invention also proposes a student mental health group screening system, comprising:

[0072] High-frequency camera, used to collect videos of the front-end students’ faces and neck muscles;

[0073] AI emotion recognition module, used for rapid analysis and processing of group data and image signals, to obtain the motion parameters of the students’ head vibration points;

[0074] A psychophysiological parameter extraction module is used to obtain mapping parameters and brain wave information according to the mapping relationship between brain waves and psychophysiological parameters and the mapping relationship between brain wave detection and video detection;

[0075] Vibration imaging module, used for optical contrast, the change of signal amplitude at each point in space and the change of signal frequency at each point in space, acquiring each point to form vibration imaging;

[0076] The algorithm model comparison module is used to compare with the emotion algorithm model in the basic feature database to quickly calculate the student's emotional state;

[0077] The evaluation module is used to comprehensively evaluate the mental health status of students and use data to quantify whether various indicators are normal;

[0078] Screening module, used to screen high-risk suspicious students with abnormal emotions;

[0079] The early warning module is used to automatically warn students who have abnormal emotions after three consecutive detections;

[0080] The file creation module is used to manage the files of students who have taken the test and to monitor the key students who have been screened out;

[0081] Tracking service module: conduct online and / or offline face-to-face tracking of key students screened out, and provide psychological communication and consultation;

[0082] The recording module is used to keep historical records of each test of key students screened out, so as to promptly discover the trend of emotional changes.

[0083] Furthermore, the assessment module assesses the comprehensive data of aggression, stress, suspicion, balance, charm, vitality, self-regulation, inhibition, neuroticism, depression, happiness, extroversion and stability of the students' emotional state, as well as the proportion of negative emotions, positive emotions and physiological emotions in the comprehensive data of the psychological state;

[0084] Also assessed are energy, concentration, and fatigue.

[0085] Furthermore, the file creation module includes a detection time unit, a name unit, a number unit, an age unit, a unit unit, a class unit, a comprehensive evaluation unit and an operation unit.

[0086] Furthermore, the recording module includes a history record of brain fatigue and a history record of concentration.

[0087] Compared with the existing technology, the method and system for screening student mental health groups proposed by the present invention have the following beneficial effects: through artificial intelligence and AI emotion recognition technology, group data and image signals collected from sensors are quickly analyzed and processed, non-contact and accurate perception is achieved, and group cognition and psychological changes are grasped in a timely manner, so as to predict, warn, and make active decisions and responses, improve governance capabilities and levels, and effectively maintain the psychological stability of campus groups. Specifically:

[0088] (1) It is simple and easy to use. The test only takes 1 minute and can visualize the psychological state. There is no need for medical interviews or form filling during the whole process.

[0089] (2) Non-contact method: just sit in front of the camera to measure or take mobile snapshots under multiple cameras. No contact is required and there is no other burden on the body.

[0090] (3) Because it is a test of unconscious psychological state, it can grasp the psychological state more objectively. Compared with questionnaires, the subjects cannot control it through their own consciousness.

[0091] (4) Through regular testing, psychological changes can be detected in advance so that appropriate measures can be taken to intervene as early as possible. BRIEF DESCRIPTION OF THE DRAWINGS

[0092] The accompanying drawings are used to provide a further understanding of the present invention and constitute a part of the specification. Together with the embodiments of the present invention, they are used to explain the present invention and do not constitute a limitation of the present invention. In the accompanying drawings:

[0093] Figure 1 It is a flowchart of the present invention regarding group screening of student mental health. DETAILED DESCRIPTION

[0094] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention; it is obvious that the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments, and all other embodiments obtained by ordinary technical students in this field based on the embodiments of the present invention without making creative work are within the scope of protection of the present invention.

[0095] The structural features of the present invention are now described in detail with reference to the accompanying drawings.

[0096] See also Figure 1 , a method for screening student mental health groups, specifically comprising the following steps:

[0097] 1) Video acquisition: Use the front-end high-frequency camera to obtain 30-60 seconds of video of the student's face and neck muscle groups. Among them, in order to ensure the accuracy of the system detection, the camera must be set before video acquisition, the camera's video acquisition filter and video screenshot format must be set, and the image must be debugged. The camera's video acquisition filter can be set according to different detection conditions. You can choose to automatically or manually set the "focus" and "exposure". If the lighting is constant, use manual configuration. If the light is not constant (for example, using natural light), use automatic configuration. Because electronic zoom will reduce the frame rate of the camera, the parameters "zoom" and "focus" are set manually. When adjusting this parameter, pay attention to the input frame rate, which must be greater than 25 frames / second. For the setting of the video screenshot format, the frame rate must be set to 30, and the frame size is set to 640×480, which can ensure the quality of the screenshot.

[0098] 2) Obtain the frequency and amplitude parameters of micro-vibration of the head: Obtain the frequency and amplitude parameters of micro-vibration generated by the vestibular organs controlling the subtle movement of the head muscles from the videos of the students' facial and neck muscles. The frequency and amplitude parameters of micro-vibration are the movement parameters of the head points. There are differences in optical contrast between points, and vibration imaging is formed at each point.

[0099] The optical contrast differences include the following:

[0100] The change in the amplitude of the signal at each point in space;

[0101] The formula is:

[0102] Among them: U x，y，i The signal at point (x, y) in the i-th frame, U x，y，(i+1) The signal amount at the point (x, y) in the i+1th frame, N is the number of frames of the accumulated vibration image amplitude component;

[0103] The frequency of the signal changes at each point in space;

[0104] The formula is:

[0105] Where: Δ i is the inter-frame difference of the image at the i-th point (1 for difference and 0 for no difference), and N is the number of frames of the accumulated vibration image amplitude component;

[0106] The emotion model algorithm is derived from formula (1) and formula (2):

[0107]

[0108] Among them, E i For a certain emotional state, is the temporal variation (frequency) of work done by a person's head in the form of micro-vibrations, is the spatial distribution of work done by a person's head in the form of micro-vibrations (displacement); i : Corresponding relationship.

[0109] The emotion model algorithms include aggression model algorithm, stress model algorithm, suspicion model algorithm, balance model algorithm, charm model algorithm, vitality model algorithm, self-regulation model algorithm, inhibition model algorithm, neuroticism model algorithm, depression model algorithm, happiness model algorithm, extroversion model algorithm and stability model algorithm.

[0110] Among them, the model algorithm equation of the aggressiveness value is:

[0111]

[0112] Where m is the maximum frequency in the frequency distribution density histogram; F i is the i-th frequency in the frequency distribution density histogram; F in is the input processing vibration frequency; n is the count of N frames with inter-frame differences greater than the threshold; the aggressiveness is determined by the vibration frequency histogram, which reflects the maximum value of the frequency distribution density and the standard deviation of the person's vibration.

[0113] The model algorithm equation for the pressure value is:

[0114]

[0115] in, is the total amplitude of the i-th line vibration frequency component on the left side of the object; is the total amplitude of the frequency component of the ith line vibration on the right side of the object; for The maximum value between is the maximum frequency of the vibration frequency component of the i-th row on the left side of the object; is the maximum frequency of the vibration frequency component of the i-th row on the right side of the object for The maximum value between; n is the number of rows occupied by the image; the asymmetry of the external frequency vibration reflects the level of pressure.

[0116] The model algorithm equation for anxiety value is:

[0117]

[0118] Among them, P i (f) is the spectral power of the vibration frequency distribution; f max It is the maximum frequency in the vibration frequency distribution spectrum; high-density high-frequency vibrations reflect high anxiety levels.

[0119] The model algorithm equation for suspicious values ​​is:

[0120]

[0121] Among them, E1 is the aggressiveness level; E2 is the stress level; E3 is the anxiety level; aggressiveness, stress, and anxiety reflect the suspiciousness level.

[0122] The equation for the equilibrium value is:

[0123] E5=Bl=(100-2Va)%

[0124] Among them, Va is the calculated sum of the variability of emotion parameters; the ratio of standard deviation and mathematical expectation reflects the variability of emotion parameters.

[0125] The model algorithm equation of charm value is:

[0126]

[0127] Among them, W li -W ri is the difference between the left and right average amplitudes of the vibration image amplitude component of each line; C li -C ri is the difference between the maximum frequency values ​​on the left and right sides of the amplitude component of the vibration image for each line; N is the number of frames in the processing process; the symmetry of the head micro-motion reflects the charm value.

[0128] The model algorithm equation of vitality value is:

[0129]

[0130] Where M is the maximum value of the count on the frequency histogram; σ is the standard deviation of the vibration frequency, calculated from the frequency histogram; F ps The maximum value of the input frequency for the vibration image; the difference between the maximum density and the standard deviation of the vibration frequency.

[0131] The model algorithm equation for the self-regulating value is:

[0132]

[0133] Among them, E5 is the average value of the balance parameter during the measurement process; dE5 is the variation range of the balance parameter; E6 is the average value of the charm value parameter during the measurement process; dE6 is the variation range of the charm value parameter; the self-regulation level reflects the stability of positive emotions (vitality value and charm value).

[0134] The model algorithm equation for the inhibition value is:

[0135]

[0136] Where F1 is the vibration change frequency; T m is the average period of vibration frequency change; T: vibration period measurement; inhibition level comes from human reaction time to stimulation.

[0137] The model algorithm equation for neuroticism is:

[0138] E10=Nr=10σ(E9),

[0139] Where σ(E9) is the standard deviation of the E9 (inhibition) value; the standard deviation of the inhibition parameter reflects the level of neuroticism.

[0140] The model algorithm equation for depression value is:

[0141]

[0142] Among them, σ is the standard deviation of the vibration frequency in the frequency histogram; M is the average value of the vibration frequency in the frequency histogram; the standard deviation and average value of the vibration frequency in the frequency histogram reflect the depression level.

[0143] The model algorithm equation of happiness value is:

[0144]

[0145] Among them, I is the information effectiveness of the psychological and physiological state; E is the energy reduction characteristic of the psychological and physiological state; dI is the change in the information effectiveness of the psychological and physiological state; dE is the change in the energy reduction characteristic of the psychological and physiological state; information efficiency and energy consumption reflect the level of happiness.

[0146] The model algorithm equation for the extraversion value is:

[0147]

[0148] Among them, R IE is the Pearson correlation coefficient between information efficiency (I) and energy expenditure (E); the correlation between information efficiency and energy expenditure reflects the level of extraversion.

[0149] The model algorithm equation for the stability value is:

[0150]

[0151] Among them, K is the normalization coefficient of the frequency histogram, and y' is the normal distribution density;

[0152] The similarity between the frequency histogram and the normal distribution law reflects the level of stability.

[0153] 3) Obtain mapping parameters and brain wave information: According to the mapping relationship between brain waves and psychological and physiological parameters, the above-obtained vibration frequency and amplitude parameters are converted between video and electroencephalogram, and between video image and HRV through the psychological and physiological parameter extraction algorithm to obtain mapping parameters and brain wave information. In the generated vibration image state, a real-time image with a halo can be generated. The length of the halo line of the vibration image depends on the center line of the vibration amplitude, and the color of the halo line depends on the maximum vibration frequency within the range of the vibration image.

[0154] 4) Model comparison: Compare the mapping parameters and brain wave information obtained above with the emotional algorithm model in the basic feature database, and quickly calculate the student's emotional state. The student's emotional state includes aggression, stress tension / anxiety, suspicion, balance, charm, vitality, self-regulation, inhibition, neuroticism, depression, happiness model, extroversion and stability. The student's emotional state is a parameter calculated by the average value within the set detection time, the root mean square error of the parameter and the parameter variability. After the data collection is completed, the corresponding table can be opened on the main interface of the system, including the vibration frequency analysis histogram and the psychological and physiological state analysis chart. After a certain test time, the person's psychological energy state can be intuitively displayed through the curve chart.

[0155] 5) Emotional status assessment: Evaluate the emotional status of students collected in the above statistics and create files. File management is done for students who participate in the test, and key personnel are monitored.

[0156] 6) Screening and early warning: Screen out high-risk suspicious students with abnormal emotions, and test the screened students once a week. If the emotions are abnormal for three consecutive times, the system will mark the students with abnormal emotions and automatically issue an early warning.

[0157] Keep a historical record of each test of key personnel to promptly detect trends in emotional changes

[0158] 7) Follow-up consultation: Record and track the abnormal students mentioned above, and conduct online and / or offline face-to-face communication until their emotions stabilize and the follow-up test is terminated. Keep a historical record of each test of key personnel to detect emotional changes in a timely manner.

[0159] For further explanation, the present invention also proposes a student mental health group screening system, comprising:

[0160] The high-frequency camera is used to collect videos of the front-end students' faces and neck muscle groups. During the collection, the high-frequency camera needs to face the students' faces.

[0161] The AI ​​emotion recognition module is used to quickly analyze and process group data and image signals to obtain the motion parameters of the student's head vibration point.

[0162] The psychophysiological parameter extraction module is used to obtain mapping parameters and brain wave information according to the mapping relationship between brain waves and psychophysiological parameters and the mapping relationship between brain wave detection and video detection.

[0163] The vibration imaging module is used for optical contrast, the change of the signal amplitude at each point in space and the change of the signal frequency at each point in space, and acquires each point to form vibration imaging.

[0164] The algorithm model comparison module is used to compare with the emotion algorithm model in the basic feature database to quickly calculate the student's emotional state. The student's emotional state includes comprehensive data on aggression, stress, suspicion, balance, charm, vitality, self-regulation, inhibition, neuroticism, depression, happiness, extroversion and stability.

[0165] The assessment module is used to comprehensively evaluate the mental health status of students, using data to quantify whether various indicators are normal; the assessment module evaluates the comprehensive data of students' emotional state, including aggression, stress, suspicion, balance, charm, vitality, self-regulation, inhibition, neuroticism, depression, happiness, extroversion and stability, as well as the proportion of negative emotions, positive emotions and physiological emotions in the comprehensive data of the psychological state.

[0166] The screening module is used to screen high-risk and suspicious students with abnormal emotions.

[0167] The early warning module is used to automatically warn students who have abnormal emotions after three consecutive detections.

[0168] The file creation module is used to create files for students who take the test and to monitor the key students who are screened out; the file creation module includes a test time unit, a name unit, a number unit, an age unit, a unit unit, a class unit, a comprehensive evaluation unit and an operation unit.

[0169] The tracking service module provides online and / or offline face-to-face tracking for the key students screened out, and provides psychological communication and consultation.

[0170] The recording module is used to record the history of each test of the key students screened out, and timely discover the trend of emotional changes. The recording module includes the history of brain fatigue and the history of concentration.

[0171] The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Although the present invention has been described in detail with reference to the aforementioned embodiments, technical students in the field can still modify the technical solutions recorded in the aforementioned embodiments, or replace some of the technical features therein with equivalents. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present invention shall be included in the protection scope of the present invention.

Claims

1. A method for screening student mental health groups, characterized in that: The specific steps include: S1: Obtain 30-60 seconds of video of students’ facial and neck muscle groups through the front-end high-frequency camera; S2: Obtain the frequency and amplitude parameters of tiny vibrations generated by the vestibular organs controlling the subtle movements of the head muscles; S3: According to the mapping relationship between brain waves and psychological and physiological parameters, the vibration frequency and amplitude parameters obtained in S2 are converted between video and electroencephalogram, and between video image and HRV through the psychological and physiological parameter extraction algorithm to obtain mapping parameters and brain wave information. The mapping parameters and brain wave information are obtained by generating a real-time image with a halo under the generated vibration image state. The length of the halo line of the vibration image depends on the center line of the vibration amplitude, and the color of the halo line depends on the maximum vibration frequency within the range of the vibration image. S4: Compare the mapping parameters and brain wave information obtained in S3 with the emotion algorithm model in the basic feature database, and quickly calculate the student's emotional state; S5: Evaluate the emotional state of students counted in S4 and create a profile; S6: Screen out high-risk suspicious students with abnormal emotions, and test the screened students once a week. If the students have abnormal emotions for three consecutive times, the system will mark the students with abnormal emotions and automatically issue an early warning; S7: Record and track the abnormal students in S6, and conduct online and / or offline face-to-face communication until their emotions stabilize and the tracking test is terminated; In S2, the frequency and amplitude parameters of the tiny vibration are the motion parameters of the head points, and there are differences in optical contrast between points, forming a vibration image at each point; The differences in optical contrast include the following: The change in the amplitude of the signal at each point in space; The formula is: ,Formula (1) in: is the change in the signal amplitude at the point (x, y) in space, is the signal at point (x, y) in the i-th frame, is the signal amount at the point (x, y) in the i+1th frame, and N is the number of frames of the accumulated vibration image amplitude component; The frequency of the signal changes at each point in space; The formula is: ,Formula (2) in: is the change in the frequency of the signal at the point (x, y) in space, is the maximum frequency in the frequency distribution density histogram; is the inter-frame difference of the image at point i, where difference is 1 and no difference is 0, and N is the number of frames of the accumulated vibration image amplitude component; The emotion model algorithm is derived from formula (1) and formula (2): ,Formula (3) in, For a certain emotional state, is the time variation of work done by a person's head in the form of micro-vibration, i.e., frequency, The spatial distribution of work done by a person's head in the form of micro-vibrations, i.e., displacement; () is the corresponding relationship.

2. The method for screening student mental health groups according to claim 1, characterized in that: In S1, before the video is captured, the camera needs to set the video capture filter and the video capture format to debug the image.

3. The method for screening student mental health groups according to claim 1, characterized in that: The emotion model algorithm includes an aggression model algorithm, a stress model algorithm, a suspicion model algorithm, a balance model algorithm, a charm model algorithm, a vitality model algorithm, a self-regulation model algorithm, an inhibition model algorithm, a neuroticism model algorithm, a depression model algorithm, a happiness model algorithm, an extroversion model algorithm and a stability model algorithm.

4. The method for screening student mental health groups according to claim 3, characterized in that: The parameters of students’ emotional state are calculated by the calculated value, standard deviation and variance value.

5. A student mental health group screening system, used for the student mental health group screening method as claimed in claim 1, characterized in that: include: High-frequency camera, used to collect videos of the front-end students’ faces and neck muscles; AI emotion recognition module, used for rapid analysis and processing of group data and image signals, to obtain the motion parameters of the students’ head vibration points; A psychophysiological parameter extraction module is used to obtain mapping parameters and brain wave information according to the mapping relationship between brain waves and psychophysiological parameters and the mapping relationship between brain wave detection and video detection, wherein the mapping parameters and brain wave information are obtained by generating a real-time image with a halo under the generated vibration image state, the length of the halo line of the vibration image depends on the center line of the vibration amplitude, and the color of the halo line depends on the maximum vibration frequency within the range of the vibration image; Vibration imaging module, used for optical contrast, the change of signal amplitude at each point in space and the change of signal frequency at each point in space, acquiring each point to form vibration imaging; The algorithm model comparison module is used to compare with the emotion algorithm model in the basic feature database to quickly calculate the student's emotional state; The evaluation module is used to comprehensively evaluate the mental health status of students and use data to quantify whether various indicators are normal; Screening module, used to screen high-risk suspicious students with abnormal emotions; The early warning module is used to automatically warn students who have abnormal emotions after three consecutive detections; The file creation module is used to manage the files of students who have taken the test and to monitor the key students who have been screened out; Tracking service module: conduct online and / or offline face-to-face tracking of key students screened out, and provide psychological communication and consultation; The recording module is used to keep historical records of each test of key students screened out, so as to promptly discover the trend of emotional changes.

6. The student mental health group screening system according to claim 5 is characterized in that: The assessment module includes comprehensive data of students' emotional states, including aggression, stress, suspicion, balance, charm, vitality, self-regulation, inhibition, neuroticism, depression, happiness, extroversion and stability, as well as the proportion of negative emotions, positive emotions and physiological emotions in the comprehensive data of psychological states; Also assessed are energy, concentration, and fatigue.

7. The student mental health group screening system according to claim 5 is characterized in that: The file creation module includes a detection time unit, a name unit, a number unit, an age unit, a unit unit, a class unit, a comprehensive evaluation unit and an operation unit.

8. The student mental health group screening system according to claim 5 is characterized in that: The recording module includes a history record of brain fatigue and a history record of concentration.

Images