Student mental health assessment method, device, equipment and storage medium

Abstract

The present application discloses a method, device, equipment and storage medium for evaluating student mental health. The method collects students' answer sheet data and brain-computer data, and calculates the credibility score of the answer sheet data based on the brain-computer data to improve the credibility of the student's answer sheet data. If the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data, so as to use the machine learning model to intelligently analyze the student's individual psychological state in multiple psychological evaluation items to achieve multi-dimensional analysis. Finally, based on each student's individual psychological state information, the group psychological state information of the group to which the student belongs is analyzed to achieve analysis of the student group's psychological state, so that the teacher can understand the class psychological state in a timely manner, so that the teacher can provide timely and concentrated tutoring.

Description

Technical Field

[0001] The present application relates to the field of artificial intelligence technology, and in particular to a student mental health assessment method, method, device and storage medium. Background Art

[0002] Mental health refers to all aspects of the mind and its activities being in a good or normal state, a state of maintaining a perfect character, normal intelligence, correct cognition, appropriate emotions, reasonable will, positive attitude, appropriate behavior and good adaptation. In contrast, mental abnormality is a disorder in the structure or function of the brain or a disorder and distortion of a person's reflection of objective reality, which reflects the abnormality of a person's self-concept and certain abilities, as well as the adaptation disorder in social interpersonal relationships and personal life.

[0003] With the accelerated pace of life and increased academic pressure, psychological problems are gradually becoming younger, and adolescent students, as the future pillars of the country, are the focus of mental health assessment. At present, adolescent mental health assessment is mainly conducted through questionnaires, but the accuracy of the assessment results is questioned due to the limitations of students' misunderstanding of the description of the questionnaire content, concealed answers, and the inability of the questionnaire to be detailed. In addition, the current questionnaire assessment method is more focused on the mental health assessment of each individual student, and rarely pays attention to the mental health of the student group. In fact, the mental health status of a class group / grade group is an important factor affecting the mental health development of each individual student. Summary of the invention

[0004] The present application provides a student mental health assessment method, device, equipment and storage medium to solve the technical problem of low credibility of assessment results in current psychological assessment methods.

[0005] In order to solve the above technical problems, in the first aspect, the present application provides a student mental health assessment method, comprising:

[0006] Collecting students' original psychological data, including students' answer data and brain-computer data when answering psychological survey questions, and psychological survey questions include questionnaires with multiple psychological assessment items;

[0007] Calculate the credibility score of the answer sheet data based on the brain-computer data;

[0008] If the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data. The individual psychological state information includes the individual item psychological state information corresponding to each psychological assessment item and the total individual psychological state information based on all psychological assessment items.

[0009] Based on each student's individual psychological state information, analyze the group psychological state information of the group to which the student belongs.

[0010] In some of the embodiments, collecting the original psychological data of the students includes:

[0011] Obtain psychological survey questions corresponding to various psychological assessment items;

[0012] Displaying psychological survey test questions, wherein one test question of the psychological survey test question is displayed each time, when the answer countdown ends and the student finishes answering a test question, the next test question will be displayed;

[0013] Collect answer sheet data corresponding to the test questions and brain-computer data of students when answering the test questions;

[0014] For each test question, the answer sheet data and brain-computer data corresponding to the test question are combined to obtain combined data. The combined data of multiple test questions are original psychological data.

[0015] In some of the embodiments, calculating the credibility score of the answer sheet data based on the brain-computer data includes:

[0016] For each test question in the psychological survey test, the deep learning network is used to extract the EEG feature data of the students when answering the test questions based on the brain-computer data corresponding to the test questions, and the feature score of the EEG feature data is output;

[0017] The feature scores corresponding to all test questions are weighted and summed to obtain the credibility scores corresponding to the answer data of the psychological survey test questions.

[0018] In some embodiments, if the credibility score is greater than a preset score, a machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data, including:

[0019] If the credibility score is greater than the preset score, then for each psychological assessment item, the preset decision tree model is used to evaluate the individual psychological state information corresponding to each student's psychological assessment item based on the original psychological data;

[0020] For each student, all the individual items of the student's psychological state information are integrated to obtain the student's total individual psychological state information.

[0021] In some embodiments, for each psychological assessment item, a preset decision tree model is used to assess the individual psychological state information corresponding to the psychological assessment item of each student based on the original psychological data, including:

[0022] For each psychological assessment item of each student, a preset decision tree model is used to extract answer sheet feature data of the answer sheet data and EEG feature data of the brain-computer data, and the answer sheet feature score of the answer sheet feature data and the weight corresponding to the EEG feature data are output;

[0023] Based on the weights corresponding to the EEG feature data, the answer sheet feature scores are weighted to obtain the psychological scores corresponding to the student's psychological assessment items;

[0024] Determine the individual item psychological state information corresponding to the psychological score.

[0025] In some embodiments, analyzing the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student includes:

[0026] Using the preset hierarchical analysis model, according to the individual psychological state information of each student in the target group, the judgment matrix and hierarchical single ranking are constructed. The hierarchical analysis model uses multiple preset team psychological levels as the program layer, multiple psychological assessment items as the quasi-measurement layer, and team psychological state information as the target layer.

[0027] According to the judgment matrix and the hierarchical single ranking, the hierarchical total ranking is constructed, and the consistency of the hierarchical ranking is tested;

[0028] If the total hierarchical ordering satisfies the consistency check, the group psychological state information of the target group is output.

[0029] In some embodiments, if the credibility score is greater than a preset score, after evaluating the student's individual psychological state information based on the original psychological data using a machine learning model, the method further includes:

[0030] For each student, obtain the student's historical psychological state information;

[0031] Analyze students' psychological growth trends based on historical psychological state and individual psychological state information.

[0032] In a second aspect, the present application also provides a student mental health assessment device, comprising:

[0033] The collection module is used to collect students' original psychological data, which includes students' answer data and brain-computer data when answering psychological survey questions. The psychological survey questions include questionnaires for multiple psychological assessment items.

[0034] A calculation module, used to calculate the credibility score of the answer sheet data based on the brain-computer data;

[0035] An evaluation module, for evaluating the student's individual psychological state information using a machine learning model based on the original psychological data if the credibility score is greater than a preset score, wherein the individual psychological state information includes individual item psychological state information corresponding to each psychological evaluation item and total individual psychological state information based on all psychological evaluation items;

[0036] The analysis module is used to analyze the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student.

[0037] In a third aspect, the present application also provides a computer device, including a processor and a memory, the memory being used to store a computer program, and when the computer program is executed by the processor, the student mental health assessment method as in the first aspect is implemented.

[0038] In a fourth aspect, the present application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the student mental health assessment method as in the first aspect.

[0039] Compared with the prior art, this application has at least the following beneficial effects:

[0040] By collecting students' original psychological data, the original psychological data includes answer data and brain-computer data when students answer psychological survey questions. The psychological survey questions include questionnaires for multiple psychological assessment items. Based on the brain-computer data, the credibility score of the answer data is calculated to improve the credibility of the student's answer data, thereby improving the credibility of the student's psychological assessment. If the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data. The individual psychological state information includes the individual project psychological state information corresponding to each psychological assessment item, and the total individual psychological state information based on all psychological assessment items, so as to use the machine learning model to intelligently analyze the psychological state of individual students in multiple psychological assessment items and realize multi-dimensional analysis. Finally, based on the individual psychological state information of each student, the group psychological state information of the group to which the student belongs is analyzed to realize the analysis of the student group's psychological state, so that the teacher can understand the class psychological state in a timely manner, so that the teacher can provide timely and concentrated tutoring. BRIEF DESCRIPTION OF THE DRAWINGS

[0041] Figure 1 A flow chart of a student mental health assessment method shown in an embodiment of the present application;

[0042] Figure 2 This is a schematic diagram of the structure of a student mental health assessment device shown in an embodiment of the present application;

[0043] Figure 3 A schematic diagram of the structure of a computer device shown in an embodiment of the present application. DETAILED DESCRIPTION

[0044] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of this application.

[0045] Please refer to Figure 1 , Figure 1 The flowchart of a student mental health assessment method provided in the embodiment of the present application is shown in FIG. The student mental health assessment method in the embodiment of the present application can be applied to computer devices, including but not limited to smart phones, laptops, tablet computers, desktop computers, physical servers, and cloud servers. Figure 1 As shown, the student mental health assessment method of this embodiment includes steps S101 to S104, which are described in detail as follows:

[0046] Step S101, collecting original psychological data of students, wherein the original psychological data includes answer sheet data and brain-computer data of students when answering the psychological survey questions, and the psychological survey questions include questionnaires of multiple psychological assessment items.

[0047] In this step, the psychological survey questions include test questions in the form of text, images, audio and video. The psychological assessment items include but are not limited to somatization, obsessive-compulsive symptoms, interpersonal sensitivity, depression, anxiety, hostility, terror, paranoia and psychosis. The test questions in the psychological survey questions can be from the symptom self-rating scale (such as SCL90). Brain-computer data is EEG data. When students take psychological tests, the test questions are shown to the students, and the brain-computer interface device is used to collect the brain-computer data and answer data of the students when answering the test questions.

[0048] Step S102, calculating the credibility score of the answer sheet data based on the brain-computer data.

[0049] In this step, brain-computer data can represent people's psychological activities. By collecting students' brain-computer data when answering the test paper, that is, analyzing students' psychological activities, it is possible to analyze whether students have dishonest psychological behaviors such as concealing their answers. Optionally, a deep learning network is used to analyze students' EEG features based on brain-computer data, and a feature score is output based on the EEG features, which is used as the credibility score of the answer paper data.

[0050] Step S103, if the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data, and the individual psychological state information includes the individual item psychological state information corresponding to each of the psychological assessment items, and the total individual psychological state information based on all the psychological assessment items.

[0051] In this step, the individual psychological state information includes the mental health level and mental health characteristic information. The machine learning model includes a logistic regression model, a decision tree model, a random forest model, a neural network model, and an improved deep learning model. The individual psychological state information includes the individual project psychological state information of each psychological assessment project corresponding to the student and the total individual psychological state information, which can be classified based on the symptom self-assessment scale SCL90. For example, somatization includes the psychological states numbered 1, 4, 12, 27, 40, 42, 48, 49, 52, 53, 56 and 58 in the self-assessment project. The score of this project is between 12 and 60 points. When the score is greater than 36 points, the individual psychological state information is that the individual has obvious discomfort in the body, and is often accompanied by symptoms such as headaches and muscle aches. When the score is below 24 points, the individual psychological state information is that the physical symptoms are not obvious.

[0052] This embodiment pre-constructs machine learning models corresponding to multiple psychological assessment items, and trains each machine learning model using preset psychological data samples until the machine learning model converges; then uses the trained machine learning model to predict the student's original psychological data, output the student's psychological score, and determine the individual psychological state information corresponding to the psychological score.

[0053] Step S104: analyzing the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student.

[0054] In this step, for students in a class, students study and live in the same time and space for a long time. When a student has a psychological problem, it is very likely to affect other students. For example, for anxiety, when some students have anxiety problems, the students' behavior style will change, thereby affecting other students to feel anxious, and then affecting the anxiety of the entire class, so this embodiment also analyzes the student group. The group to which the student belongs can be a class, grade, and campus, etc. The group psychological state information includes the group psychological state information of the group in each psychological assessment project and the total group psychological state information. Optionally, according to the individual project psychological state information of each student, the group project psychological state information of the student group in the corresponding psychological assessment project is analyzed, and according to the total individual psychological state information of each student, the total group psychological state information of the student group is analyzed.

[0055] This embodiment uses the brain-computer data of students answering psychological survey questions to verify the credibility of the students' answer data to ensure the credibility of the original psychological data for analyzing the learning psychological state, thereby improving the credibility of the psychological state analysis results. By analyzing the individual psychological state and group psychological state of students, it is possible to comprehensively analyze the psychological state of students and the psychological health impact between students, so that teachers can understand the psychological state of individual students and the class in a timely manner, so that psychological teachers can timely counsel students and correct the psychological state of the class.

[0056] In some embodiments, the step S101 includes:

[0057] Obtaining psychological survey test questions corresponding to a plurality of psychological assessment items;

[0058] Displaying the psychological survey test questions, wherein one test question of the psychological survey test questions is displayed each time, and when the answer countdown ends and the student finishes answering a test question, the next test question is displayed;

[0059] Collecting answer sheet data corresponding to the test questions and brain-computer data of students when answering the test questions;

[0060] For each of the test questions, the answer sheet data and the brain-computer data corresponding to the test question are combined to obtain combined data, and the combined data of multiple test questions are the original psychological data.

[0061] In this embodiment, the answer sheet data is matched with the brain-computer data one by one, so as to use the brain-computer data to verify the credibility of the corresponding answer sheet data, and to facilitate the machine learning network to perform correlation analysis on the answer sheet data and the brain-computer data, thereby improving the accuracy and credibility of the analysis results. Optionally, the test questions displayed each time can be test questions in different forms, for example, the test questions currently displayed are in text form, the test questions displayed last time were in audio form, and the test questions displayed next time are in the form of a combination of images and text.

[0062] In some embodiments, the step S102 includes:

[0063] For each test question in the psychological survey test, using a deep learning network, based on the brain-computer data corresponding to the test question, extract the EEG feature data of the student when answering the test question, and output a feature score of the EEG feature data;

[0064] The feature scores corresponding to all the test questions are weighted and summed to obtain the credibility scores corresponding to the answer data of the psychological survey test questions.

[0065] In this embodiment, the deep learning network includes but is not limited to a convolutional neural network, a generative adversarial network, an autoencoder or a recurrent neural network, etc. The deep learning network can introduce an attention mechanism and a residual structure, such as a convolutional neural network based on an attention mechanism. Exemplarily, by presetting the collected user brain-computer data, a brain-computer data sample for the user's deceptive behavior and concealment behavior is constructed, and the convolutional neural network is trained using the brain-computer data sample until the loss function of the convolutional neural network is less than a preset value, and the training is completed; the convolutional layer of the trained convolutional neural network is used to extract features from the brain-computer data when the student answers the test questions to obtain EEG feature data; the fully connected layer and pooling layer of the trained convolutional neural network are used to pool and fully connect the EEG feature data, and output the feature score of the EEG feature data; each test question corresponds to a feature score, and the feature scores corresponding to all the test questions of the student are weighted and summed to obtain a credibility score to verify the credibility of the answer sheet data.

[0066] Optionally, if the feature score corresponding to each test question is greater than the preset score, and the credibility score is greater than the preset score, the answer data is judged to meet the credibility requirements to ensure that the answer data for each test question is credible, and the answer data for the psychological survey questions is also credible, thereby improving the credibility of the final psychological assessment results.

[0067] In some embodiments, the step S103 includes:

[0068] If the credibility score is greater than the preset score, for each of the psychological assessment items, using a preset decision tree model, based on the original psychological data, the individual item psychological state information corresponding to the psychological assessment item of each student is assessed;

[0069] For each student, all the individual items of psychological state information of the student are integrated to obtain the total individual psychological state information of the student.

[0070] In this embodiment, each psychological assessment item has multiple test questions, each test question corresponds to an answer sheet data and brain-computer data, and a decision tree model is constructed based on the psychological assessment item. The decision tree model is trained using the preset original psychological data until the decision tree model converges; the converged decision tree model is used to process the original psychological data of the student and output the student's individual item psychological state information.

[0071] Optionally, according to preset weights corresponding to the psychological assessment items, the psychological state information of all individual items of the student is integrated. Specifically, the psychological state information of all individual items is weightedly summed to obtain the total individual psychological state information of the student.

[0072] It should be noted that this embodiment uses both the answer sheet data and brain-computer data as input data for the decision tree model, and can use the answer sheet data as shallow features and the brain-computer data as deep features to more comprehensively analyze the students' psychological state.

[0073] In some embodiments, the process of evaluating the psychological state information of an individual item includes:

[0074] For each psychological assessment item of each student, using the preset decision tree model, extracting answer sheet feature data of the answer sheet data and electroencephalogram feature data of the brain-computer data, and outputting answer sheet feature scores of the answer sheet feature data and weights corresponding to the electroencephalogram feature data;

[0075] Based on the weight corresponding to the EEG feature data, the answer sheet feature score is weighted to obtain the psychological score corresponding to the psychological assessment item of the student;

[0076] Determine the individual item psychological state information corresponding to the psychological score.

[0077] In this embodiment, the answer sheet feature data and the EEG feature data are used as child nodes of a preset decision tree. Each student's psychological assessment project corresponds to a plurality of answer sheet feature data and EEG feature data. The answer sheet feature score is output according to the answer sheet feature data in a preset decision tree manner, and the weight is output according to the EEG feature data. The weight range is 0-1, 1 represents the credibility of the answer sheet data corresponding to the EEG feature data, and the larger the weight, the more credible it is. Since the answer sheet data of students are forged when they conceal the facts, the students have mental health problems at this time. Therefore, the psychological scores of students are treated with low scores in a weighted manner, so that it is convenient for psychological teachers to pay attention to the psychological problems of students, which is more in line with the actual psychological survey situation.

[0078] In some embodiments, the step S104 includes:

[0079] Using a preset hierarchical analysis model, according to the individual psychological state information of each student in the target group, a judgment matrix and a hierarchical single ranking are constructed, wherein the hierarchical analysis model uses a plurality of preset team psychological levels as a program layer, a plurality of psychological assessment items as a quasi-measurement layer, and the team psychological state information as a target layer;

[0080] According to the judgment matrix and the hierarchical single ranking, a hierarchical total ranking is constructed, and a consistency check is performed on the hierarchical ranking;

[0081] If the total hierarchical ordering satisfies the consistency check, the group psychological state information of the target group is output.

[0082] In this embodiment, the consistent matrix method is used to construct the judgment matrix of the criterion layer and the hierarchical single sorting of the criterion layer by the scheme layer according to the individual psychological state information corresponding to the psychological assessment items, and the maximum eigenvalue and its corresponding eigenvector are calculated for each judgment matrix, and the consistency index, random consistency index and consistency ratio are used for consistency test; if the test passes, the eigenvector (normalized) is the weight vector; if it fails, the pairwise comparison matrix needs to be reconstructed. According to the judgment matrix and the hierarchical single sorting, the hierarchical total sorting of the scheme layer is determined, and the consistency ratio CR of the hierarchical total sorting is calculated, and CR<0.1 is used for testing. If it passes, the decision can be made according to the result represented by the total sorting weight vector, otherwise the judgment matrix with a larger consistency ratio CR needs to be reconstructed.

[0083] This embodiment uses multiple psychological assessment items as the reference layer for hierarchical analysis, and can analyze the group psychological state information that is more in line with the actual situation. For example, there is somatization in the psychological assessment items. Although the somatization problem has a great impact on the psychological state of individual students, it has little impact on the psychological state of the group. Through hierarchical analysis, the factors (psychological assessment items) that have a greater impact on the group can be determined to be more in line with the actual situation and improve the analysis accuracy of the group psychological state information.

[0084] In some embodiments, after step S103, the method further includes:

[0085] For each student, obtain the student's historical psychological state information;

[0086] The psychological growth trend of the student is analyzed according to the historical psychological state and the individual psychological state information.

[0087] In this embodiment, the historical psychological state information and the current personal psychological state information of each student are comprehensively analyzed to analyze the psychological growth of the student. Optionally, the psychological growth trend includes the psychological growth trend corresponding to each psychological assessment item and the total psychological growth trend corresponding to all psychological assessment items. Since the long-term existence of certain mental health problems may lead to extreme behaviors in students, this embodiment can accurately assess the psychological state of students through psychological growth trend analysis, and pay special attention to students with certain mental health problems for a long time to prevent students from engaging in extreme behaviors.

[0088] In order to implement the student mental health assessment method corresponding to the above method embodiment, to achieve the corresponding functions and technical effects. Figure 2 , Figure 2 The structural block diagram of a student mental health assessment device provided by an embodiment of the present application is shown. For the convenience of explanation, only the parts related to the present embodiment are shown. The student mental health assessment device provided by the embodiment of the present application includes:

[0089] The collection module 201 is used to collect the original psychological data of the students, wherein the original psychological data includes the answer data and brain-computer data of the students when answering the psychological survey questions, and the psychological survey questions include a questionnaire of multiple psychological assessment items;

[0090] A calculation module 202, used for calculating the credibility score of the answer sheet data according to the brain-computer data;

[0091] An evaluation module 203 is used to evaluate the student's individual psychological state information based on the original psychological data by using a machine learning model if the credibility score is greater than a preset score, wherein the individual psychological state information includes individual item psychological state information corresponding to each of the psychological evaluation items and total individual psychological state information based on all the psychological evaluation items;

[0092] The analysis module 204 is used to analyze the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student.

[0093] In some embodiments, the acquisition module 201 is specifically used for:

[0094] Obtaining psychological survey test questions corresponding to a plurality of psychological assessment items;

[0095] Displaying the psychological survey test questions, wherein one test question of the psychological survey test questions is displayed each time, and when the answer countdown ends and the student finishes answering a test question, the next test question is displayed;

[0096] Collecting answer sheet data corresponding to the test questions and brain-computer data of students when answering the test questions;

[0097] For each of the test questions, the answer sheet data and the brain-computer data corresponding to the test question are combined to obtain combined data, and the combined data of multiple test questions are the original psychological data.

[0098] In some embodiments, the calculation module 202 is specifically configured to:

[0099] For each test question in the psychological survey test, using a deep learning network, based on the brain-computer data corresponding to the test question, extract the EEG feature data of the student when answering the test question, and output a feature score of the EEG feature data;

[0100] The feature scores corresponding to all the test questions are weighted and summed to obtain the credibility scores corresponding to the answer data of the psychological survey test questions.

[0101] In some embodiments, the evaluation module 203 includes:

[0102] An evaluation unit, configured to evaluate the individual item psychological state information corresponding to the psychological evaluation item of each student according to the original psychological data using a preset decision tree model for each psychological evaluation item if the credibility score is greater than a preset score;

[0103] The fusion unit is used to fuse all the individual psychological state information of each student to obtain the total individual psychological state information of the student.

[0104] In some embodiments, the evaluation unit comprises:

[0105] For each psychological assessment item of each student, using the preset decision tree model, extracting answer sheet feature data of the answer sheet data and electroencephalogram feature data of the brain-computer data, and outputting answer sheet feature scores of the answer sheet feature data and weights corresponding to the electroencephalogram feature data;

[0106] Based on the weight corresponding to the EEG feature data, the answer sheet feature score is weighted to obtain the psychological score corresponding to the psychological assessment item of the student;

[0107] Determine the individual item psychological state information corresponding to the psychological score.

[0108] In some embodiments, the analysis module 204 includes:

[0109] Using a preset hierarchical analysis model, according to the individual psychological state information of each student in the target group, a judgment matrix and a hierarchical single ranking are constructed, wherein the hierarchical analysis model uses a plurality of preset team psychological levels as a program layer, a plurality of psychological assessment items as a quasi-measurement layer, and the team psychological state information as a target layer;

[0110] According to the judgment matrix and the hierarchical single ranking, a hierarchical total ranking is constructed, and a consistency check is performed on the hierarchical ranking;

[0111] If the total hierarchical ordering satisfies the consistency check, the group psychological state information of the target group is output.

[0112] In some embodiments, the system further comprises:

[0113] An acquisition module is used to acquire historical psychological state information of each student;

[0114] The analysis module is used to analyze the psychological growth trend of the student according to the historical psychological state and the individual psychological state information.

[0115] The above-mentioned student mental health assessment device can implement the student mental health assessment method of the above-mentioned method embodiment. The options in the above-mentioned method embodiment are also applicable to this embodiment and will not be described in detail here. The rest of the contents of the embodiment of this application can refer to the contents of the above-mentioned method embodiment, and will not be repeated in this embodiment.

[0116] Figure 3 This is a schematic diagram of the structure of a computer device provided in one embodiment of the present application. Figure 3 As shown, the computer device 3 of this embodiment includes: at least one processor 30 ( Figure 3 Only one is shown in the figure), a memory 31, and a computer program 32 stored in the memory 31 and executable on the at least one processor 30, wherein the processor 30 implements the steps of any of the above method embodiments when executing the computer program 32.

[0117] The computer device 3 may be a computing device such as a smart phone, a tablet computer, a desktop computer, a cloud server, etc. The computer device may include but is not limited to a processor 30 and a memory 31. Those skilled in the art will understand that Figure 3 It is only an example of computer device 3 and does not constitute a limitation on computer device 3. It may include more or fewer components than shown in the figure, or a combination of certain components, or different components, for example, it may also include input and output devices, network access devices, etc.

[0118] The processor 30 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. A general-purpose processor may be a microprocessor or any conventional processor, etc.

[0119] In some embodiments, the memory 31 may be an internal storage unit of the computer device 3, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 31 may also be an external storage device of the computer device 3, such as a plug-in hard disk, a smart media card (SMC), a secure digital (SD) card, a flash card, etc. equipped on the computer device 3. Further, the memory 31 may also include both an internal storage unit and an external storage device of the computer device 3. The memory 31 is used to store an operating system, an application program, a boot loader (BootLoader), data, and other programs, such as the program code of the computer program. The memory 31 may also be used to temporarily store data that has been output or is to be output.

[0120] In addition, an embodiment of the present application further provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps in any of the above method embodiments are implemented.

[0121] An embodiment of the present application provides a computer program product. When the computer program product is run on a computer device, the computer device implements the steps in the above-mentioned method embodiments when executing the computer device.

[0122] In several embodiments provided in the present application, it is understood that each box in the flow chart or block diagram can represent a module, a program segment or a part of a code, and the module, a program segment or a part of a code contains one or more executable instructions for realizing the specified logical function. It should also be noted that in some alternative implementations, the functions marked in the box can also occur in a different order from that marked in the accompanying drawings. For example, two consecutive boxes can actually be executed substantially in parallel, and they can sometimes be executed in the opposite order, depending on the functions involved.

[0123] If the functions are implemented in the form of software function modules and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present application can be essentially or partly embodied in the form of a software product that contributes to the prior art. The computer software product is stored in a storage medium and includes several instructions for a computer device to execute all or part of the steps of the methods described in the various embodiments of the present application. The aforementioned storage media include: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, and other media that can store program codes.

[0124] The specific embodiments described above further describe the purpose, technical solutions and beneficial effects of the present application in detail. It should be understood that the above description is only a specific embodiment of the present application and is not intended to limit the scope of protection of the present application. It is particularly pointed out that for those skilled in the art, any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of protection of the present application.

Claims

1. A method for evaluating students' mental health, characterized in that: include: Collecting original psychological data of students, wherein the original psychological data includes answer data and brain-computer data when students answer psychological survey questions, wherein the psychological survey questions include questionnaires of multiple psychological assessment items; Calculating the credibility score of the answer sheet data according to the brain-computer data; If the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data, wherein the individual psychological state information includes individual item psychological state information corresponding to each psychological assessment item and total individual psychological state information based on all the psychological assessment items; Analyzing the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student; The step of analyzing the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student includes: Using a preset hierarchical analysis model, according to the individual psychological state information of each student in the target group, a judgment matrix and a hierarchical single ranking are constructed, wherein the hierarchical analysis model uses a plurality of preset team psychological levels as a program layer, a plurality of psychological assessment items as a quasi-measurement layer, and the group psychological state information as a target layer; According to the judgment matrix and the hierarchical single ranking, a hierarchical total ranking is constructed, and a consistency check is performed on the hierarchical total ranking; If the total hierarchical ordering satisfies the consistency check, the group psychological state information of the target group is output.

2. The student mental health assessment method according to claim 1, characterized in that: The collection of students' original psychological data includes: Obtaining psychological survey test questions corresponding to a plurality of psychological assessment items; Displaying the psychological survey test questions, wherein one test question of the psychological survey test questions is displayed each time, and when the answer countdown ends and the student finishes answering a test question, the next test question is displayed; Collecting answer sheet data corresponding to the test questions and brain-computer data of students when answering the test questions; For each of the test questions, the answer sheet data and the brain-computer data corresponding to the test question are combined to obtain combined data, and the combined data of multiple test questions are the original psychological data.

3. The student mental health assessment method according to claim 1, characterized in that: Calculating the credibility score of the answer sheet data according to the brain-computer data includes: For each test question in the psychological survey test, using a deep learning network, based on the brain-computer data corresponding to the test question, extract the EEG feature data of the student when answering the test question, and output a feature score of the EEG feature data; The feature scores corresponding to all the test questions are weighted and summed to obtain the credibility scores corresponding to the answer data of the psychological survey test questions.

4. The student mental health assessment method according to claim 1, characterized in that: If the credibility score is greater than the preset score, the machine learning model is used to evaluate the student's individual psychological state information based on the original psychological data, including: If the credibility score is greater than the preset score, for each of the psychological assessment items, using a preset decision tree model, based on the original psychological data, the individual item psychological state information corresponding to the psychological assessment item of each student is assessed; For each student, all the individual items of psychological state information of the student are integrated to obtain the total individual psychological state information of the student.

5. The student mental health assessment method according to claim 4, characterized in that: For each of the psychological assessment items, using a preset decision tree model, based on the original psychological data, assessing the individual psychological state information corresponding to the psychological assessment item of each student, including: For each psychological assessment item of each student, using the preset decision tree model, extracting answer sheet feature data of the answer sheet data and electroencephalogram feature data of the brain-computer data, and outputting answer sheet feature scores of the answer sheet feature data and weights corresponding to the electroencephalogram feature data; Based on the weight corresponding to the EEG feature data, the answer sheet feature score is weighted to obtain the psychological score corresponding to the psychological assessment item of the student; Determine the individual item psychological state information corresponding to the psychological score.

6. The student mental health assessment method according to claim 1, characterized in that: If the credibility score is greater than the preset score, after evaluating the student's individual psychological state information based on the original psychological data using a machine learning model, the method further includes: For each student, obtain the student's historical psychological state information; The psychological growth trend of the student is analyzed according to the historical psychological state and the individual psychological state information.

7. A student mental health assessment device, characterized in that: include: A collection module, used to collect original psychological data of students, wherein the original psychological data includes answer data and brain-computer data when students answer psychological survey questions, wherein the psychological survey questions include questionnaires of multiple psychological assessment items; A calculation module, used for calculating the credibility score of the answer sheet data according to the brain-computer data; An evaluation module, configured to evaluate the student's individual psychological state information using a machine learning model based on the original psychological data if the credibility score is greater than a preset score, wherein the individual psychological state information includes individual item psychological state information corresponding to each of the psychological evaluation items and total individual psychological state information based on all the psychological evaluation items; An analysis module, used for analyzing the group psychological state information of the group to which the student belongs based on the individual psychological state information of each student; The analysis module is specifically used for: Using a preset hierarchical analysis model, according to the individual psychological state information of each student in the target group, a judgment matrix and a hierarchical single ranking are constructed, wherein the hierarchical analysis model uses a plurality of preset team psychological levels as a program layer, a plurality of psychological assessment items as a quasi-measurement layer, and the team psychological state information as a target layer; According to the judgment matrix and the hierarchical single ranking, a hierarchical total ranking is constructed, and a consistency check is performed on the hierarchical total ranking; If the total hierarchical ordering satisfies the consistency check, the group psychological state information of the target group is output.

8. A computer device, characterized in that: It includes a processor and a memory, the memory is used to store a computer program, and when the computer program is executed by the processor, it implements the student mental health assessment method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that: It stores a computer program, which, when executed by a processor, implements the student mental health assessment method as described in any one of claims 1 to 6.

Images