Metacosmic psychological assessment system based on moving automatic vehicle

Abstract

The utility model discloses a meta universe psychological assessment system based on a sports bicycle, which is characterized in that the sports bicycle, a virtual reality helmet, a display module and a monitoring module are connected with a psychological assessment module; the virtual reality helmet and the monitoring module are connected with the display module; the sports bicycle is connected with the virtual reality helmet. The monitoring module is used for collecting and processing physiological signals of a user; the virtual reality helmet is used for displaying riding scene information and psychological test information; the display module is used for displaying the information; and the psychological assessment module is used for performing assessment processing on the rotating speed information, the collection information set of the monitoring module and the feedback information to obtain psychological assessment result information of the user. According to the utility model, by introducing a bicycle exercise scene, multi-modal data such as physiological data and exercise data are acquired in the exercise scene, so that the psychological state of a user can be quickly and accurately evaluated.

Description

Technical Field

[0001] The utility model relates to the technical field of virtual reality and psychological assessment, in particular to a metaverse psychological assessment system based on a sports automatic vehicle. Background Art

[0002] In recent years, with the rapid development of social economy and the increase of work and life pressure, the various psychological pressures faced by people have generally increased. As a base for cultivating talents, campuses should not only pay attention to the enrollment rate of students, but also pay attention to the mental health of students, and shoulder the responsibility of delivering healthy and well-rounded talents for the motherland and society. At present, some college students have psychological disorders of varying degrees. The more common psychological problems in colleges and universities are mainly environmental adaptability problems, interpersonal relationship problems, academic and test anxiety problems, family problems, and college career choices. These problems have begun to become more significant and have also put forward new demands for mental health education. The construction of mental health education venues needs to be more standardized and professional to meet the needs of students and schools.

[0003] How to quickly and accurately assess the mental health of high-stress groups such as students and effectively relieve psychological stress is an issue that needs to be addressed urgently. Utility Model Content

[0004] The technical problem to be solved by the utility model is to provide a metaverse psychological assessment system based on a sports automatic vehicle, so as to achieve a rapid and accurate assessment of the mental health of high-stress groups such as students, and to effectively alleviate the psychological pressure.

[0005] In order to solve the above technical problems, the first aspect of the embodiment of the utility model discloses a metaverse psychological assessment system based on a sports bicycle, including a sports bicycle, a virtual reality helmet, a display module, a psychological assessment module and a monitoring module;

[0006] The sports bicycle, virtual reality helmet, display module and monitoring module are connected to the psychological assessment module;

[0007] The virtual reality helmet and the monitoring module are connected to the display module;

[0008] The sports bicycle is connected with a virtual reality helmet.

[0009] The monitoring module is used to collect and process the user's physiological signals to obtain a collection information set;

[0010] The virtual reality helmet is used to display riding scene information and psychological test information;

[0011] The display module is used to display riding scene information, the collected information set of the monitoring module, psychological test information, feedback information and psychological assessment result information of the psychological assessment module;

[0012] The psychological assessment module is used to collect the speed information of the sports bicycle, the collection information set of the monitoring module and the feedback information, and evaluate and process the speed information, the collection information set of the monitoring module and the feedback information to obtain the user's psychological assessment result information.

[0013] The monitoring module includes an eye movement detection module, a heart rate detector, an electroencephalogram detector and a near infrared detector;

[0014] The eye movement detection module is used to detect the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of the user's gaze points, and the frequency of gaze point switching;

[0015] The heart rate detector is used to monitor the user's heart rate and obtain the user's heart rate information;

[0016] The EEG detector is used to monitor the user's EEG signals and obtain the user's EEG information;

[0017] The near-infrared detector is used to detect the user's blood parameters to obtain the user's oxygenated hemoglobin concentration information, deoxygenated hemoglobin concentration information, and total hemoglobin concentration information;

[0018] The collected information set includes the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of user gaze points, the frequency of gaze point switching, user heart rate information, user electroencephalogram information, user oxygenated hemoglobin concentration information, user deoxyhemoglobin concentration information, and user total hemoglobin concentration information.

[0019] The sports bicycle comprises a sports bicycle body and a rotation speed sensor; the rotation speed sensor is installed on the crank of the bicycle pedal; the rotation speed sensor is used to collect the rotation speed information of the sports bicycle pedal when the user rides the sports bicycle.

[0020] The virtual reality helmet is used to display corresponding riding scene information and psychological test information according to user instruction information, and send the riding scene information and psychological test information to the display module; receive user feedback information on the psychological test information, and send the psychological test information and feedback information to the psychological evaluation module and the display module; receive the speed information of the speed sensor, and display the speed information in the riding scene information.

[0021] The psychological evaluation module is used to collect the speed information of the sports bicycle, the collection information set of the monitoring module and the feedback information, and evaluate and process the speed information, the collection information set of the monitoring module and the feedback information to obtain the user's psychological evaluation result information, including:

[0022] S31, performing time alignment processing on the speed information and the collection information set of the monitoring module to obtain a collection information sequence set; the collection information sequence set includes a collection information sequence;

[0023] S32, constructing a collection information matrix set using the collection information sequence set; the collection information matrix set includes a plurality of collection information matrices; the collection information matrix is ​​composed of collection information sequences collected in the same collection time period; the row vector of the collection information matrix is ​​the collection information sequence;

[0024] S33, performing reference vector calculation processing on the collection information matrix set to obtain a reference vector r;

[0025] S34, performing weight calculation processing on the collection information matrix set to obtain a weighted vector

[0026] S35, the reference vector r and the weighted vector Perform weighted calculation processing to obtain the user's psychological assessment result information.

[0027] The step of performing reference vector calculation processing on the collection information matrix set to obtain a reference vector r includes:

[0028] S331, performing feature calculation processing on each collected information matrix of the collected information matrix set to obtain a corresponding weight factor vector;

[0029] S332, performing DEMON spectrum transformation processing on the weight factor vectors corresponding to all the collected information matrices, to obtain a DEMON spectrum sequence corresponding to the weight factor vectors;

[0030] S333, calculate the value distribution of each DEMON spectrum sequence respectively to obtain a quantized distribution matrix The expression for calculating the value distribution is:

[0031]

[0032] Among them, h k,i Represents the quantized distribution matrix The element value of the kth row and ith column of k(i) represents the i-th value of the DEMON spectrum sequence of the k-th weight factor vector, and N0 is the total number of elements of the DEMON spectrum sequence of the weight factor vector;

[0033] S334, quantizing the distribution matrix Perform the mean operation in the column direction to obtain the reference vector r, r = [r1, r2, ..., r n ]; where r i is the i-th element of the reference vector r, which is obtained by The average value of the elements in the i-th column of is obtained, where n is the number of elements contained in the reference vector r.

[0034] The performing feature calculation processing on each collected information matrix of the collected information matrix set to obtain a corresponding weight factor vector includes:

[0035] For each collected information matrix, its eigenvalue and eigenvector are calculated;

[0036] Determine the eigenvector corresponding to the maximum eigenvalue as the standard eigenvector;

[0037] The standard feature vector is normalized to obtain a weight factor vector corresponding to the acquisition information matrix.

[0038] The weighted vector is obtained by performing weight calculation on the collected information matrix set. include:

[0039] S341, performing factor normalization processing on the elements in the weight factor vectors corresponding to all the collected information matrices of the collected information matrix set to obtain a standardized matrix S;

[0040] The calculation expression of the factor normalization process is:

[0041]

[0042] Among them, s ki represents the element in the kth row and ith column of the normalized matrix S, q ki Represents the kth collected information matrix B k The i-th element of the weight factor vector, m represents the number of rows of the standardized matrix S, and n represents the number of columns of the standardized matrix S;

[0043] S342, performing correlation calculation processing on the standardized matrix S and the reference vector r to obtain a correlation matrix V;

[0044] S343, performing correlation normalization calculation processing on the correlation matrix V to obtain a correlation vector y;

[0045] S344, performing weighted normalization processing on the association vector y to obtain a weighted vector

[0046] The calculation expression of the weighted normalization process is:

[0047]

[0048] in, is the weight vector The ith element of .

[0049] The calculation expression of the associated calculation process is:

[0050]

[0051] Among them, v ki represents the element in the kth row and ith column of the association matrix, and ρ is the association calculation factor.

[0052] The expression of the association normalization calculation process is:

[0053]

[0054] Among them, y i Represents the i-th element of the association vector y.

[0055] The beneficial effects of the utility model are:

[0056] The utility model develops bicycle sports scenes through programming, collects multi-modal data such as physiological data and sports data in the sports scenes, and realizes the rapid and accurate evaluation of the user's psychological state;

[0057] The utility model establishes a matrix for the user's collected information, and uses the collection matrices of different time periods to perform reference vector calculation processing, thereby effectively suppressing the influence of noise and ensuring the accuracy of the evaluation result; by performing feature calculation processing on each collection information matrix of the collection information matrix set, the corresponding weight factor vector is obtained, which effectively eliminates the images of wild values ​​and environmental interference values ​​and ensures the objectivity of the evaluation result. BRIEF DESCRIPTION OF THE DRAWINGS

[0058] Figure 1 This is a schematic diagram of the composition of the device of the utility model;

[0059] Figure 2 This is a system framework diagram of the indoor bicycle-based psychological assessment system disclosed in the utility model;

[0060] Figure 3 This is a flow chart of data analysis of EEG signals of the present invention;

[0061] Figure 4 Schematic diagram of the use scenario of the device of the utility model. DETAILED DESCRIPTION

[0062] In order to better understand the content of the present utility model, two embodiments are given here.

[0063] Figure 1 It is the composition principle diagram of the utility model device.

[0064] Embodiment 1:

[0065] The first embodiment of the utility model discloses a metaverse psychological assessment system based on a sports automatic vehicle, comprising:

[0066] Sports bikes, virtual reality helmets, display modules, psychological assessment modules, and monitoring modules;

[0067] The sports bicycle, virtual reality helmet, display module and monitoring module are connected to the psychological assessment module;

[0068] The virtual reality helmet and the monitoring module are connected to the display module;

[0069] The sports bicycle is connected with a virtual reality helmet.

[0070] The monitoring module is used to collect and process the user's physiological signals to obtain a collection of information; the monitoring module includes an eye movement detection module, a heart rate detector, an electroencephalogram detector and a near infrared detector;

[0071] The eye movement detection module is used to detect the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of the user's gaze points, and the frequency of gaze point switching;

[0072] The heart rate detector is used to monitor the user's heart rate and obtain the user's heart rate information;

[0073] The EEG detector is used to monitor the user's EEG signals and obtain the user's EEG information;

[0074] The near-infrared detector is used to detect the user's blood parameters to obtain the user's oxygenated hemoglobin concentration information, deoxygenated hemoglobin concentration information, and total hemoglobin concentration information;

[0075] The near infrared detector can be implemented by using Artinis' PortaLite MKII.

[0076] The eye movement detection module can be implemented by an eye tracker or a Pico Neo 3Pro Eye Enterprise Edition eye tracking system;

[0077] The collected information set includes the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of user gaze points, the frequency of gaze point switching, user heart rate information, user electroencephalogram information, user oxygenated hemoglobin concentration information, user deoxyhemoglobin concentration information, and user total hemoglobin concentration information.

[0078] The collected information in the collected information set is recorded in a time series manner.

[0079] The sports bicycle comprises a sports bicycle body and a rotation speed sensor; the rotation speed sensor is installed on the crank of the bicycle pedal; specifically, it is installed on the inner side of the crank connecting the pedal to the central axis of the bicycle body; the rotation speed sensor is used to collect the rotation speed information of the sports bicycle pedal when the user rides the sports bicycle.

[0080] The sports bicycle can be implemented by using a V2 indoor sports bicycle of the Hummer brand.

[0081] The virtual reality helmet is used to display corresponding riding scene information and psychological test information according to user instruction information, and send the riding scene information and psychological test information to the display module; receive user feedback information on the psychological test information, and send the psychological test information and feedback information to the psychological evaluation module and the display module; receive the speed information of the speed sensor, and display the speed information in the riding scene information.

[0082] The virtual reality helmet can be implemented using Huawei VR Glass or the Pico Neo 3Pro Eye enterprise version eye tracking system.

[0083] The virtual reality helmet includes an input device; the input device is used to receive user instruction information and user feedback information on psychological test information; the input device can be a handle, a gesture recognition device, a virtual keyboard, etc.

[0084] The input device can be implemented by a brainwave bracelet; the electrophysiological (EMG) technology used in the brainwave bracelet senses the neural electrical signals transmitted from the brain through the wrist to the fingers. This technology can achieve zero or even negative latency, perfect accuracy, and can work stably under any lighting conditions and is not affected by occlusion. Recent breakthroughs have made it possible to decode the activity of individual neurons, thereby achieving "almost unlimited control" of the machine.

[0085] Psychological test information used for the virtual reality helmet, including the Self-Rating Depression Scale (SDS), the Beck Depression Inventory (BDI) and the Hamilton Depression Rating Scale (HAMD);

[0086] The virtual reality helmet can be implemented using Pico Neo 3;

[0087] The display module is used to display riding scene information, the collection information set of the monitoring module, psychological test information, feedback information and psychological assessment result information of the psychological assessment module;

[0088] The psychological evaluation module is used to collect the speed information of the sports bicycle, the collection information set of the monitoring module and the feedback information, and evaluate and process the speed information, the collection information set of the monitoring module and the feedback information to obtain the user's psychological evaluation result information, which specifically includes:

[0089] S31, performing time alignment processing on the speed information and the collection information set of the monitoring module to obtain a collection information sequence set; the collection information sequence set includes a collection information sequence;

[0090] S32, constructing a collection information matrix set using the collection information sequence set; the collection information matrix set includes a plurality of collection information matrices; the collection information matrix is ​​composed of collection information sequences collected in the same collection time period; the row vector of the collection information matrix is ​​the collection information sequence;

[0091] Specifically, the collection time periods include [T0, T1], [T1, T2], and [T2, T3]; the collection information sequence collected within the collection time period [T0, T1] constitutes a first collection information matrix; the collection information sequence collected within the collection time period [T1, T2] constitutes a second collection information matrix; the collection information sequence collected within the collection time period [T2, T3] constitutes a third collection information matrix.

[0092] S33, performing reference vector calculation processing on the collection information matrix set to obtain a reference vector r;

[0093] S34, performing weight calculation processing on the collection information matrix set to obtain a weighted vector

[0094] S35, the reference vector r and the weighted vector Perform weighted calculation processing to obtain the user's psychological assessment result information;

[0095] The step of performing reference vector calculation processing on the collection information matrix set to obtain a reference vector r includes:

[0096] S331, performing feature calculation processing on each collected information matrix of the collected information matrix set to obtain a corresponding weight factor vector;

[0097] S332, performing DEMON spectrum transformation processing on the weight factor vectors corresponding to all the collected information matrices, to obtain a DEMON spectrum sequence corresponding to the weight factor vectors;

[0098] S333, calculate the value distribution of each DEMON spectrum sequence respectively to obtain a quantized distribution matrix The expression for calculating the value distribution is:

[0099]

[0100] Among them, h k,i Represents the quantized distribution matrix The element value of the kth row and ith column of k (i) represents the i-th value of the DEMON spectrum sequence of the k-th weight factor vector, and N0 is the total number of elements of the DEMON spectrum sequence of the weight factor vector;

[0101] S334, quantizing the distribution matrix Perform the mean operation in the column direction to obtain the reference vector r, r = [r1, r2, ..., r n ]; where r i is the i-th element of the reference vector r, which is obtained by The average value of the elements in the i-th column of is obtained, where n is the number of elements contained in the reference vector r.

[0102] The operation of finding the average value in the column direction is Take the mean of each column of , and combine all the means to get the reference vector;

[0103] The performing feature calculation processing on each collected information matrix of the collected information matrix set to obtain a corresponding weight factor vector includes:

[0104] For each collected information matrix, its eigenvalue and eigenvector are calculated;

[0105] Determine the eigenvector corresponding to the maximum eigenvalue as the standard eigenvector;

[0106] The standard feature vector is normalized to obtain a weight factor vector corresponding to the acquisition information matrix.

[0107] The feature calculation process is performed on each collected information matrix of the collected information matrix set to obtain a corresponding weight factor vector, and the method may also be:

[0108] Decompose each collected information matrix to obtain the corresponding left decomposition matrix, feature matrix and right decomposition matrix;

[0109] The decomposition process is calculated as follows:

[0110] Y=UAV,

[0111] Among them, U is the left decomposition matrix, A is the characteristic matrix, V is the right decomposition matrix, U and V are both orthogonal matrices, and A is a diagonal matrix;

[0112] The decomposition process can be implemented by using a matrix singular value decomposition algorithm.

[0113] The diagonal elements of the feature matrix are extracted to obtain a feature vector; the feature vector is represented by I a , I a =[λ1,λ2,…,λ N1 ], N1 is the number of elements contained in the eigenvector;

[0114] Performing linear fitting processing on the elements and element sequence values ​​of the eigenvector to obtain the best consistent approximation polynomial;

[0115] The linear fitting process uses the characteristic vector element serial number value Ix as a known independent variable and the characteristic vector element value as a known dependent variable, and constructs the curve to be approximated using the known independent variable and the known dependent variable, and uses the function approximation method to perform curve fitting on the curve to be approximated to obtain the best consistent approximation polynomial f(Ix).

[0116] The curve fitting of the curve to be approximated by the function approximation method may be performed by using the best consistent linear approximation method. The best consistent approximation polynomial f(Ix) is expressed as:

[0117] f(Ix)=α P1 (Ix) P1 +α P1-1 (Ix) P1-1 +…+α2(Ix) 2 +α1(Ix)+α0,

[0118] Wherein, P1 is the order of the best consistent approximation polynomial f(Ix), α0, α1, α2, …, α P1 are the coefficients of the optimal consistent approximation polynomial f(Ix);

[0119] For the collected information matrix, calculating its eigenvalue and eigenvector;

[0120] The eigenvector corresponding to the maximum eigenvalue is normalized and rounded up to obtain a sequence of eigennumber values;

[0121] The normalization and rounding-up processing is to divide each element of the feature vector by the maximum element in the feature vector, take the absolute value of the calculation result, and then round it up.

[0122] The characteristic sequence of serial numbers is used as input values, and the best consistent approximation polynomial is used for calculation and processing to obtain a weight factor vector corresponding to the acquisition information matrix.

[0123] The weight calculation process is performed on the collection information matrix set to obtain the weighted vector y, including:

[0124] S341, performing factor normalization processing on the elements in the weight factor vectors corresponding to all the collected information matrices of the collected information matrix set to obtain a standardized matrix S;

[0125] The calculation expression of the factor normalization process is:

[0126]

[0127] Among them, s ki represents the element in the kth row and ith column of the normalized matrix S, q ki Represents the kth collected information matrix B k The i-th element of the weight factor vector;

[0128] S342, performing association calculation processing on the standardized matrix S and the reference vector r to obtain an association matrix V; the calculation expression of the association calculation processing is:

[0129]

[0130] Among them, v ki represents the element in the kth row and ith column of the association matrix, and ρ is the association calculation factor, which can be 0.5.

[0131] S343, performing correlation normalization calculation processing on the correlation matrix V to obtain a correlation vector y;

[0132] The expression of the association normalization calculation process is:

[0133]

[0134] Among them, y i represents the i-th element of the association vector y;

[0135] S344, performing weighted normalization processing on the association vector y to obtain a weighted vector

[0136] The calculation expression of the weighted normalization process is:

[0137]

[0138] in, is the weight vector The ith element of .

[0139] The S333 may also be:

[0140] The elements and row vectors in the quantization distribution matrix are subjected to inequality group discrimination, and the expression of the inequality group discrimination is:

[0141] |h ki |≤a k , i=1,2,…,n,

[0142]

[0143] Among them, a k and b k respectively represent the first judgment threshold and the second judgment threshold of the kth row; when an element in the quantization distribution matrix does not satisfy the first inequality in the expression for discriminating the inequality group, the element value is set to 0; when a row in the quantization distribution matrix does not satisfy the second inequality in the expression for discriminating the inequality group, each element of the row is subtracted from a k / 2, complete the update of the row.

[0144] Embodiment 2:

[0145] The utility model intends to establish a psychological assessment system for indoor cycling, which combines different immersive virtual environment (VR) sports scenes, sets the exercise type, intensity, time and other parameters of the user subjects, and then uses the depression behavior scale test data, and monitors physiological indicators such as the activation degree of emotion-dominant brain areas through electroencephalogram (EEG) and functional near-infrared spectroscopy (fNIRS) to achieve the purpose of visualizing, interesting and scientifically intervening and evaluating the user's depression.

[0146] Sports scenes can be set by wearing a portable VR system, including different natural environments and single / multi-person sports modes; the intensity of exercise can be selected through different load buttons on the bicycle, and the exercise load and cardiac autonomic nervous system function can be monitored by wearing a heart rate variability monitor; by wearing a portable dual-channel electroencephalogram (EEG) and a portable functional near-infrared spectroscopy (fNIRS) to detect the changing characteristics of EEG signals and blood oxygen signals in the prefrontal lobe-related brain areas, the dynamic changes and activation of the subjects' emotion-dominated brain areas can be monitored, and then the mechanism of brain function improvement can be evaluated; the exercise mood inventory (EFI) and the subjective fatigue perception scale (RPE) are used to judge the emotional changes and physical fatigue of the subjects in different time periods of exercise; the self-rating depression scale (CESD) and the depression scale (PHQ-9) are used to evaluate the screening of users' depressive symptoms before exercise intervention and the improvement of users' depressive symptoms after long-term exercise intervention.

[0147] The electroencephalogram (EEG) monitor can be implemented through a brain-computer interface.

[0148] The utility model intends to establish a psychological assessment system based on indoor bicycles, such as the system framework Figure 2 As shown in FIG. 1 , it includes a virtual reality scene module, a scale answering and analysis module, and an EEG signal acquisition module. The virtual reality scene module is a virtual scene specially developed for subjects, through which subjects can take depression scale tests, view assessment results, and watch related videos; the scale answering and analysis module provides subjects with depression scale test questions and performs data analysis on the subjects' answer results; the EEG signal acquisition module is responsible for real-time acquisition and recording of the subjects' EEG signals.

[0149] The virtual reality scene module, in this design, is a general term for hardware and software that can provide virtual reality scenes for subjects, including virtual reality scenes, VR glasses that present scenes, and terminal devices that run scenes. The virtual reality scene is built using the Unity development engine and developed using C# as the development language. The successfully compiled mobile installation package (APK) is installed and run on a mobile phone terminal equipped with the Hongmeng operating system, and the scene is presented through the Huawei VR glass scene, and the scene interaction is performed through the handle or data cable that comes with the Huawei VR glass. After the subject wears VR glasses and related equipment, he or she can enter the virtual reality scene for subsequent operations. The virtual reality scene module communicates data with the scale answering and analysis module via WIFI, and communicates data with the EEG signal acquisition module via Bluetooth.

[0150] For the design and implementation of the virtual reality scene, the utility model names the virtual reality scene "state of mind". It expresses that the virtual reality scene is a psychological state and is also related to the assessment of depression. The scene was finally built using the Unity development engine. Unity is a cross-platform game engine that provides powerful and easy-to-use tools to create, operate and transform real-time content. Unity supports a variety of AR / VR devices and code libraries. Unity also has a large and active developer community that provides rich tutorials, plug-ins, resources and technical support. Unity includes but is not limited to the following systems: rendering engine, physics engine, collision detection system, sound engine, script engine, animation system, artificial intelligence, network engine, scene management, etc. Unity is suitable for the development of a wide range of fields such as games, automobiles, construction engineering, film and television animation, etc. Using Unity3D to generate an Android installation package (APK) has high portability and can improve the utilization rate of the system.

[0151] The construction of the virtual reality scene is ultimately realized in a movie theater; the subjects can take a depression scale test and view the analysis results on the front screen of the movie theater; the subjects can watch the EEG signals collected in real time by the EEG signal acquisition module through the rear screen of the movie theater; and the subjects can watch related videos through the front screen of the movie theater.

[0152] After the virtual reality scene is built, it is necessary to select VR glasses for presenting the scene and terminal devices for running the scene. In order to meet the original objective, efficient and portable design concept of this design, the selected VR glasses and terminal devices need to meet the conditions of efficient construction and light carrying. After consulting the parameters of VR glasses of different brands, Huawei VR glass was finally selected as the device for presenting the VR scene. Huawei VR glass has the following advantages over other VR glasses: (1) Huawei VR glass weighs only 166 grams (wearing part) and the body thickness is only 26.6mm, which is light, thin and comfortable; (2) Huawei VR glass uses Fast LCD with a resolution of 3200*1600 and a pixel density of 1058PPI, with clear and delicate image quality; (3) Huawei VR glass supports wireless or wired connection to Huawei mobile phones or computers, so you can enjoy a large amount of VR content; (4) Huawei VR glass can be upgraded to a 6DoF VR device through the 6DoF game package to achieve more free spatial interaction. It can be seen that Huawei VR glass is a VR product that focuses on watching movies and less on games, which meets the needs and definitions of this design. The mobile terminal device chosen was the Honor V20 equipped with the Hongmeng operating system to run the constructed virtual reality scene.

[0153] The scale answering and analysis module in this design is a psychological assessment system that provides subjects with depression scale test questions and evaluation scale results. The system is a server-side program. The program is developed and implemented in PHP (Hypertext Preprocessor, PHP) programming language, and the final program runs on the server. When the server and the mobile terminal are in the same local area network, the virtual reality scene module can communicate with the scale answering and analysis module. The virtual reality scene module is the client, and the subject can access the IP address in the virtual reality scene "mood" to answer the depression scale, view the analysis results, and watch related videos; the scale answering and analysis module is the server, providing depression scale test questions and answer result data analysis.

[0154] The scale answering and analysis module conducts depression analysis based on the subjects' depression scale answers and generates evaluation results. The depression scale is a psychological measurement tool used to evaluate depression symptoms. There are currently many different scales to evaluate whether a subject suffers from depression. Different depression scales have different compilation methods and scoring criteria, and are used to measure different aspects or levels of depression symptoms. Common depression scales include the Self-Rating Depression Scale (SDS), the Beck Depression Inventory (BDI), and the Hamilton Depression Rating Scale (HAMD). Among them, SDS and BDI are filled out by the patients themselves, reflecting the patients' subjective feelings about themselves; HAMD is scored by doctors or psychologists based on the patients' answers and observations, reflecting the objective conditions of the patients; SDS and BDI are compiled based on clinical experience and psychological theories, while HAMD is compiled based on biological, neurochemical and other factors.

[0155] Different depression rating scales also have different scopes of application and advantages and disadvantages. For example: (1) The Hamilton Depression Rating Scale is mainly used for clinical diagnosis and treatment effect evaluation, and has high reliability and validity. However, it also has some limitations, such as over-emphasizing physical symptoms and ignoring cognitive and emotional aspects; requiring face-to-face interviews by professionals and not being able to be filled out by oneself; and having low sensitivity to mild to moderate depressive disorders. (2) Another commonly used depression rating scale, the Beck Depression Inventory, is mainly used to screen people who may have depressive disorders or monitor changes during treatment. Compared with the Hamilton Depression Rating Scale, it can better reflect cognitive and emotional aspects, and can be filled out by the subjects themselves without the guidance of professionals. However, it also has some problems, such as the possibility of being affected by social expectations and leading to deviations; and poor applicability to certain special populations such as the elderly, children, and patients with non-psychological problems.

[0156] Different depression scales have different principles and structures, and have their own characteristics and applicable scenarios. However, they are generally designed based on the clinical characteristics and diagnostic criteria of depression to reflect depressive emotions, thoughts, behaviors and physical symptoms, and the subjects are asked to choose or score according to their actual situation. Then, a total score or a classification result is calculated according to the scoring rules of the scale to reflect the subject's depression level or whether he or she suffers from a depressive disorder. Therefore, this design only needs to enter the corresponding questions and their scoring rules in different scales, and calculate the total score or classification results of the answer results to obtain the corresponding evaluation results.

[0157] The utility model names the psychological assessment system on the server side "Smile". This name conveys positive and optimistic emotions, and it is also hoped that it can inspire patients to face difficulties and challenges. The program was finally developed using the PHP programming language, which is an open source and completely free multi-purpose scripting language with a large developer community and a rich resource library. PHP is mainly used for Web development, can be embedded in HTML and is compatible with various databases and Web servers. The PHP syntax draws on the characteristics of languages ​​such as C, Java and Perl, and is easy to learn and use. PHP can implement dynamic web pages, database operations, file processing, email sending and other functions. Install "Smile" on a laptop, and the system will monitor port 61112 in real time after it is running. The client can access the psychological assessment system by accessing the server IP. When conducting a depression assessment, the subjects can access the psychological assessment system IP and enter the "Smile" system login page by interacting with the virtual reality scene "Mood"; after logging into the account, the subjects will enter the account homepage, and the subjects can choose a depression scale for assessment; before the subjects conduct a depression assessment, the system will pop up an assessment informed consent form; after obtaining the subject's consent, the system will conduct a depression scale psychological assessment on the subject; after the subject finishes answering the questions, the system will promptly produce the subject's depression scale report, which contains the subject's basic information, depression score, report instructions and guidance.

[0158] The EEG signal acquisition module in this design is a portable dual-channel brain-computer interface that can collect the wearer's EEG signals in real time. This utility model designs an EEG signal acquisition device called "BlueBrain-Link". The EEG signal acquisition module communicates with the virtual reality scene module via Bluetooth. The BlueBrain-Link device encodes and modulates the collected EEG signals in a specific format and sends them via Bluetooth. The virtual reality scene demodulates the obtained EEG data and displays them in the scene.

[0159] BlueBrain-Link is developed based on NeuroSky's TRAM EEG acquisition module and ThinkGear chip. The acquisition position of BlueBrain-Link is Fp1 and Fp2 on the forehead of the brain, with a data accuracy of 24-bit ADC, a sampling rate of 250Hz, and a hardware response time of less than 2ms. The virtual reality scene module communicates with the EEG signal acquisition module through the Bluetooth serial port, sending 512 data packets containing EEG data per second. The acquisition electrodes of the BlueBrain-Link device are dry electrodes, so there is no need to add or apply any conductive medium when wearing it. The TGAM module will collect the EEG signal and use NeuroSky's patented algorithm to extract the relevant parameters of the EEG signal, and then encode it into a digital signal in the Bluetooth serial port transmission format through the ThinkGear processor, and transmit it wirelessly by sending data packets. In order to receive and use raw brain wave data, you must fully understand the composition of the data packet. The data packet consists of three parts: header, payload, and payload check. The frame format is as follows:

[0160] AA AA 04 80 02xxHigh xxLow xxCheckSum

[0161] Each frame contains 8 bytes, which are introduced in two steps: 1) The first 5 bytes "AA AA 04 80 02" are the frame format flags, where "AA AA" represents the start of the frame, "04" means that the data in the frame is 4 bytes long, "80" means that the frame data packet is the original brain wave data, and "02" means that the original data is 2 bytes long; 2) The last "xxHigh xxLow xxCheckSum" is the original brain wave data, where "xxHigh xxLow" are the high and low 8 bits of the data respectively, and "xxCheckSum" represents the checksum.

[0162] After understanding the encoding method, we can write the corresponding demodulation program. The virtual reality scene module uses the data analysis program to extract the original EEG signal, and finally the calculated original EEG signal is processed in the next step. The flowchart of EEG signal data analysis is as follows Figure 3 shown.

[0163] The utility model also discloses a method for performing user psychological evaluation by using the psychological evaluation system of the indoor bicycle, comprising:

[0164] ① The subjects do necessary preparatory activities;

[0165] ② Turn on the bicycle and preheat it for 5 minutes; turn on the computer and connect to Wi-Fi;

[0166] ③ The subjects wear VR, heart rate monitor, EEG monitor or near-infrared monitor;

[0167] ④Start the detection program, select the exercise scene and exercise load;

[0168] ⑤ The subject starts pedaling. During the ride, the experimenter asks the subject every 10 minutes based on the emotional scale and the self-perceived fatigue scale. The exercise can be ended when the level of the self-perceived fatigue scale reaches level 16 or the subject completes the exercise task.

[0169] ⑥Save the test data, shut down the machine, turn off the power, and end the test.

[0170] Figure 4 Schematic diagram of the use scenario of the device of the utility model.

[0171] The above is only an embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the present application may have various changes and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application should be included in the scope of the claims of the present application.

Claims

1. A metaverse psychological assessment system based on a sports car, characterized in that: It includes a sports bike, a virtual reality helmet, a display module, a psychological assessment module and a monitoring module; The sports bicycle, virtual reality helmet, display module and monitoring module are connected to the psychological assessment module; The virtual reality helmet and the monitoring module are connected to the display module; The sports bicycle is connected to a virtual reality helmet; The monitoring module is used to collect and process the user's physiological signals to obtain a collection information set; The virtual reality helmet is used to display riding scene information and psychological test information; The display module is used to display riding scene information, the collection information set of the monitoring module, psychological test information, feedback information and psychological assessment result information of the psychological assessment module; The psychological assessment module is used to collect the speed information of the sports bicycle, the collection information set of the monitoring module and the feedback information, and evaluate and process the speed information, the collection information set of the monitoring module and the feedback information to obtain the user's psychological assessment result information.

2. The Metaverse Psychological Assessment System based on a Sports Autonomous Vehicle as claimed in claim 1, characterized in that: The monitoring module includes an eye movement detection module, a heart rate detector, an electroencephalogram detector and a near infrared detector; The eye movement detection module is used to detect the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of the user's gaze points, and the frequency of gaze point switching; The heart rate detector is used to monitor the user's heart rate and obtain the user's heart rate information; The EEG detector is used to monitor the user's EEG signals and obtain the user's EEG information; The near-infrared detector is used to detect the user's blood parameters to obtain the user's oxygenated hemoglobin concentration information, deoxygenated hemoglobin concentration information, and total hemoglobin concentration information; The collected information set includes the region of interest ROI of the user's eyes, the user's gaze time on the ROI area, the number of user gaze points, the frequency of gaze point switching, user heart rate information, user electroencephalogram information, user oxygenated hemoglobin concentration information, user deoxyhemoglobin concentration information, and user total hemoglobin concentration information.

3. The Metaverse Psychological Assessment System based on a Sports Autonomous Vehicle as claimed in claim 2, characterized in that: The sports bicycle comprises a sports bicycle body and a rotation speed sensor; the rotation speed sensor is installed on the crank of the bicycle pedal; the rotation speed sensor is used to collect the rotation speed information of the sports bicycle pedal when the user rides the sports bicycle.

Images