Remote education system and method based on virtual reality

Abstract

The invention discloses a remote education system and method based on virtual reality, relates to the technical field of education, and can dynamically adjust the stimulation intensity in a virtual environment by monitoring and analyzing the physiological indexes of students in real time in combination with the motion stimulation intensity in virtual education, thereby avoiding motion sickness or discomfort caused by a virtual reality scene, and improving the education experience. The personalized environment adjustment is beneficial to improving the comfort of the students, so that the students can be immersed in the virtual education environment for a long time, and learning interruption caused by physiological discomfort is effectively avoided. According to the vestibular sensitivity difference of each student, through vestibular sensitivity test and analysis, the adaptability of the students to virtual environment stimulation can be accurately identified, so that the exercise intensity of the virtual environment is adjusted in real time in the education process.

Description

Technical Field

[0001] The present invention relates to the field of educational technology, and in particular to a remote education system and method based on virtual reality. Background Art

[0002] As an important branch of information technology, virtual reality technology has been widely used in education, medical care, entertainment and other fields in recent years. Virtual reality creates an immersive experience by digitally constructing a three-dimensional environment and simulating real-world interactions through sensory feedback. Especially in the field of distance education, virtual reality technology can provide students with an immersive learning experience, breaking the limitations of time and space, and enabling learners to interact, learn and practice through a virtual environment.

[0003] At present, distance education based on virtual reality has significant advantages in teaching content presentation, learning interaction, etc., but it still faces some technical and experience challenges in practical applications. Some students are prone to discomfort caused by movement, such as motion sickness, when participating in virtual education due to their high vestibular sensitivity. This phenomenon not only affects learning effects and experience comfort, but may also reduce students' acceptance and trust in virtual education. In the current virtual reality education system, there is usually a lack of a mechanism for dynamic adjustment based on individual differences, which greatly reduces students' learning experience. Therefore, effective analysis and adjustment of vestibular sensitivity differences has become an important part of improving the quality of virtual reality distance education.

[0004] Among them, the visual system displays movement in the virtual environment (such as objects or scene changes in the picture), but the student's vestibular system (inner ear) does not perceive the corresponding movement. This inconsistent information will cause confusion in the brain, resulting in symptoms of motion sickness. Everyone's vestibular system is differently sensitive to movement. Students with stronger vestibular sensitivity are more likely to feel discomfort in virtual reality. In a virtual reality environment, factors such as movement speed, screen refresh rate, latency, and resolution will affect students' sensory conflicts, and thus affect the occurrence of motion sickness. Summary of the invention

[0005] In view of the deficiencies of the prior art, the present invention provides a remote education system and method based on virtual reality, which solves the problems in the above-mentioned background technology.

[0006] To achieve the above objectives, the present invention is implemented through the following technical solutions: a distance education method based on virtual reality, comprising the following steps:

[0007] S1: Use 3D modeling technology to build a virtual education environment for students to conduct distance education. During the distance education process, use physiological monitoring technology to monitor students' physiological indicators, and adjust the intensity of sports stimulation in the virtual education environment in combination with the degree of sports stimulation in distance education. ad ;

[0008] S2: Based on the human physiological system, analyze the conflict between the visual system and the vestibular system of students in the virtual education environment, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1. Perform vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ;

[0009] S3: Use supervised learning methods to build a machine learning model and convert vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user ;

[0010] S4: Based on historical data, set the threshold and compare it with the individual feedback coefficient I user Comparison is made to identify the personalized regulation effect of the cloud platform on students.

[0011] Preferably, the specific steps of S1 include:

[0012] S11. According to the needs of distance education, use 3D modeling software in 3D modeling technology to build a virtual education environment that meets the needs of distance education. Building the virtual education environment includes creating a 3D template, editing basic parameters of the virtual education environment, designing a space framework of the virtual scene, adding environmental elements and adding motion stimulation elements. Among them, editing the basic parameters of the virtual education environment includes resolution FL, lighting effects, movement speed V of virtual objects, delay D lat , frame rate ZL and motion duration SC; and send the virtual teaching content and the teacher's teaching information to the student's terminal device in the form of digital signals through the network transmission protocol, and transmit the student's operation and feedback information in the virtual education environment back to the teacher and the teaching server through the network;

[0013] S12. When students are receiving distance education, physiological monitoring technology is used to monitor students' physiological indicators, where physiological monitoring technology includes electrocardiogram, optical respiratory monitoring technology, skin conductance response technology, and needle electromyography. Based on students' physiological indicators, physiological parameters of each student are obtained, and the physiological parameters include heart rate HR, respiratory rate RR, skin conductance FB, and intensity of muscle activity JH of each student in the corresponding learning period. After data cleaning, data extraction, and dimensionless processing, the physiological parameters are processed to generate physiological groups.

[0014] Preferably, the specific step S1 also includes:

[0015] S121. Based on the physiological groups of each student, measure the adaptability of each student's physiological response to virtual reality to obtain the physiological adaptation index P adapt , specifically:

[0016]

[0017] In the formula, α 1 , α 2 , α 3 and α 4 Indicates the influence of each physiological parameter on the adaptability, β 1 and β 2 is the average adjustment coefficient, β 1 control Contribution of some physiological responses to the physiological adaptation index, β 2 control Contribution of some physiological responses to the physiological adaptation index.

[0018] Preferably, the specific step S1 also includes:

[0019] S13. According to the physiological adaptation state of students and the basic parameters of the virtual education environment, the intensity of exercise stimulation in the virtual education environment is dynamically adjusted. ad , specifically:

[0020]

[0021] In the formula, V represents the speed of movement, C 1 represents a constant, which indicates the threshold value of each student's physiological adaptation to exercise stimulation; γ represents the adjustment factor 1, which affects the relationship between physiological adaptation and exercise intensity; exp(*) represents an exponential function with e as the base.

[0022] Preferably, the specific steps of S2 include:

[0023] S21. Based on S13, according to the vestibular system and visual system in the human physiological system, the conflict between the visual system and the vestibular system of students in the virtual education environment is analyzed to measure the impact of visual stimulation and the response of the vestibular system. After dimensionless processing, the sensory conflict factor Gyz is obtained, which is:

[0024]

[0025] In the formula, FL represents the resolution, ZL represents the frame rate, and D lat Indicates delay, represents the visual perception term, θ represents the modulatory factor affecting the delay, SC represents the motion duration, C2 represents the vestibular sensitivity adjustment constant, P sens Vestibular sensitivity, represents the motion perception term, Indicates a sensitive adjustment item.

[0026] Preferably, the specific step S2 also includes:

[0027] S22, based on the sensory conflict factor Gyz obtained in S21, combined with the physiological adaptation index P obtained in S121 adapt , after dimensionless processing, the intensity of motion stimulation S in the virtual education environment is adjusted. ad On the basis of , the performance of the virtual education environment is further adjusted to obtain the environmental adaptability Hs, specifically:

[0028]

[0029] In the formula, C 3 represents the fitness threshold, reflecting the critical value of students' adaptation to the virtual environment; μ represents the adjustment factor 2, which controls the response speed between physiological adaptation and virtual environment adaptation.

[0030] Preferably, the specific step S2 also includes:

[0031] S23. Conduct vestibular sensitivity tests on each student, record the physiological changes of each student according to different intensity of motion stimulation conditions, analyze each student's response ability to their own vestibular system stimulation, and obtain each student's vestibular sensitivity P sens , specifically:

[0032]

[0033] In the formula, HR Δ , j represents the heart rate change amplitude under the jth exercise stimulation condition, FB Δ，j represents the change amplitude of skin conductance under the jth motion stimulus condition, JH Δ，j represents the change in muscle activity intensity under the j-th exercise stimulus condition, RR Δ , j represents the amplitude of respiratory rate change under the jth motion stimulation condition, m represents the total number of tests, j represents the test number, and K represents the correction constant.

[0034] Preferably, the specific steps of S3 include:

[0035] S31, by vestibular sensitivity P sens , environmental adaptability Hs and physiological adaptability index P adapt As the input value of the trained machine learning model, after fitting and dimensionless processing, the individualized feedback coefficient I of each student is outputuser , specifically:

[0036]

[0037] In the formula, represents regulatory factor three, influencing the interaction between the vestibular system and physiological adaptation.

[0038] Preferably, the specific steps of S4 include:

[0039] S41. Using the individualized feedback coefficient I of the corresponding students obtained in the historical period user , set the threshold, and transform the individual feedback coefficient I user Compare with the threshold to identify the personalized adjustment effect of the cloud platform on students. The specific identification content is as follows:

[0040] If the individualized feedback coefficient I user If the threshold is exceeded, it means that the personalized adjustment effect of the current cloud platform on the corresponding student is qualified. At this time, the current personalized adjustment settings will be maintained and automatically used as the standard configuration for the corresponding student through the cloud platform.

[0041] S42, if the individualized feedback coefficient I user If the threshold is not exceeded, it means that the current cloud platform's personalized adjustment effect on the corresponding students is unsatisfactory. At this time, the learning content and tasks of the corresponding students will be dynamically adjusted.

[0042] A distance education system based on virtual reality, including a first analysis subsystem, a second analysis subsystem and a third analysis subsystem;

[0043] The No. 1 analysis subsystem will use 3D modeling technology to build a virtual education environment for students to conduct distance education. During the distance education process, it will use physiological monitoring technology to monitor students' physiological indicators and adjust the intensity of sports stimulation in the virtual education environment based on the degree of sports stimulation in distance education. ad ;

[0044] The second analysis subsystem will analyze the conflict between the visual system and the vestibular system of students in the virtual education environment based on the human physiological system, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1, and conduct vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ;

[0045] The third analysis subsystem will use supervised learning methods to build a machine learning model and convert the vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user, and according to the individualized feedback coefficient I user Numerical,identification of the personalized adjustment effect of the cloud platform on students.

[0046] The present invention provides a remote education system and method based on virtual reality, which has the following beneficial effects:

[0047] (1) Through real-time monitoring and analysis of students' physiological indicators, combined with the intensity of motion stimulation in virtual education, the intensity of stimulation in the virtual environment can be dynamically adjusted to avoid motion sickness or discomfort caused by virtual reality scenes. This personalized environmental adjustment helps to improve students' comfort, allowing them to immerse themselves in the virtual education environment for a long time, and effectively avoid learning interruptions caused by physiological discomfort. According to the vestibular sensitivity differences of each student, through vestibular sensitivity tests and analysis, the students' adaptability to virtual environment stimulation can be accurately identified, so that the motion intensity of the virtual environment can be adjusted in real time during the education process. This personalized adjustment mechanism helps to improve the learning efficiency of each student and reduce the negative impact caused by discomfort. Through the supervised learning method, the vestibular sensitivity, environmental adaptability and students' physiological data are input into the machine learning model, and the student's individualized feedback coefficient is output after fitting. This method can more accurately model the physiological response and learning adaptation of each student, realize personalized adjustment for individuals, and further optimize the effect of distance education. In summary, the present invention realizes precise control and optimization in virtual reality distance education through personalized physiological monitoring and virtual environment adjustment, combined with advanced machine learning technology, further improves students' learning effects and educational experience, avoids the discomfort in traditional education methods, and ensures the efficiency and comfort of virtual education.

[0048] (2) By calculating the sensory conflict factor Gyz, the degree of conflict between students' visual stimulation and vestibular system response in the virtual education environment is objectively evaluated. The introduction of this factor combines multiple factors such as the resolution, frame rate, delay and vestibular sensitivity of the visual system, which can effectively quantify the degree of conflict between different sensory information and provide a scientific basis for adjusting motion stimulation in the virtual environment. By analyzing the conflict between the visual and vestibular systems and adjusting motion stimulation in the virtual environment in combination with the physiological adaptation state, the discomfort caused by sensory incoordination can be reduced, and students' learning concentration and sense of participation can be improved.

[0049] (3) Through the vestibular sensitivity test, based on the changes in heart rate, skin conductance, muscle activity and respiratory rate recorded under different motion stimulation conditions, students' response to motion stimulation in the virtual education environment can be evaluated in many aspects. The differences in physiological responses of each student are standardized to ensure the accuracy and reliability of the vestibular sensitivity value. By obtaining the vestibular sensitivity of each student, the system can dynamically adjust the intensity of motion stimulation in the virtual education environment in real time to ensure that students with different sensitivities can learn in a comfortable environment, thereby improving their sense of participation and learning effects.

[0050] (4) Through the joint monitoring of vision, vestibular and students' physiological states by machine learning models, sensory conflicts can be reduced, students' adaptability can be improved, and the probability of motion sickness can be reduced. The system can dynamically adjust each student's virtual environment experience to meet their individual needs. The higher the individual feedback coefficient, the better the adjustment effect. The virtual education environment is more in line with students' physiological and psychological adaptation needs, enhancing learning comfort. Dynamic feedback mechanism: Through real-time monitoring of the individual feedback coefficient and comparison with the threshold, it can be judged in real time whether the adjustment of the virtual education environment has achieved the expected effect. If the feedback coefficient exceeds the threshold, the system will maintain the current adjustment setting to ensure the stability of the learning process; if the feedback coefficient does not reach the threshold, the learning content or tasks will be dynamically adjusted to further optimize the students' learning experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] Figure 1 It is a flow chart of the distance education method based on virtual reality of the present invention;

[0052] Figure 2 It is a logic display diagram of the distance education method based on virtual reality of the present invention;

[0053] Figure 3 It is a schematic diagram of the timing adjustment trend in the present invention;

[0054] Figure 4 This is a block diagram of the virtual reality-based distance education system of the present invention. DETAILED DESCRIPTION

[0055] The following will be combined with the drawings in the embodiments of the present invention to clearly and completely describe the technical solutions in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0056] Example 1

[0057] See also Figures 1 to 3The present invention provides a distance education method based on virtual reality. S1: Using 3D modeling technology to build a virtual education environment for students to conduct distance education, and using physiological monitoring technology to monitor students' physiological indicators during the distance education process, and preliminarily adjusting the intensity of motion stimulation in the virtual education environment S according to the degree of motion stimulation in the distance education. ad ;

[0058] S2: Based on the human physiological system, analyze the conflict between the visual system and the vestibular system of students in the virtual education environment, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1. Perform vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ;

[0059] S3: Use supervised learning methods to build a machine learning model and convert vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user ;

[0060] S4: Based on historical data, set the threshold and compare it with the individual feedback coefficient I user Comparison is made to identify the personalized regulation effect of the cloud platform on students.

[0061] Among them, vestibular sensitivity refers to the ability of the human vestibular system to respond to movement. Different individuals have different sensitivities to the same motion stimulus or changes in the virtual environment. In distance education based on virtual reality, vestibular sensitivity significantly affects students' learning experience. Higher vestibular sensitivity may cause motion stimuli in a virtual reality environment to induce motion sickness, interfere with the learning process, and even cause serious physical discomfort. This involves the sensory conflict theory: the human body's balance perception mainly depends on the vestibular system, visual system, and proprioceptive system of the inner ear. In a virtual reality environment, the visual system sees a virtual motion scene, but the vestibular system does not receive the corresponding motion signal. This inconsistency in sensory information causes confusion in the brain, thereby causing motion sickness.

[0062] In this embodiment, by accurately analyzing and adjusting the vestibular sensitivity, environmental adaptability and physiological indicators of each student, the intensity of motion stimulation in the virtual education environment can be dynamically adjusted according to the physiological response differences of different students, and the discomfort symptoms (such as motion sickness) caused by excessive motion stimulation or excessive environmental changes can be further reduced. This personalized adjustment ensures that each student's learning process in the virtual education environment can maintain immersion and avoid learning interference caused by discomfort. By accurately adjusting the intensity of motion stimulation in the virtual education environment, combined with vestibular sensitivity tests and physiological monitoring data, it is possible to effectively control and reduce the discomfort caused by environmental stimulation during the learning process of students, thereby improving learning comfort and enhancing learning effects. Using machine learning models for data fitting and prediction, the settings in the virtual education environment can be adjusted and optimized in real time according to the individualized feedback coefficients of students. By comparing historical data with feedback coefficients, the personalized adjustment effect of the cloud platform on students can be automatically identified to ensure that each student obtains a relatively suitable educational environment. In summary, the present invention can effectively improve the quality and comfort of distance education based on virtual reality, solve the problem of discomfort caused by differences in vestibular sensitivity in existing distance education methods, and provide each student with a more adaptive and personalized learning experience.

[0063] Example 2

[0064] Please refer to Figure 1 , specifically: S1 specific steps include:

[0065] S11. Based on the needs of distance education, use 3D modeling software in 3D modeling technology to build a virtual education environment that meets the needs of distance education. 3D modeling software includes but is not limited to Unity, Unreal Engine, etc. Building a virtual education environment includes creating a 3D template, editing basic parameters of the virtual education environment, designing a space framework for the virtual scene, adding environmental elements and adding motion stimulation elements. Among them, editing the basic parameters of the virtual education environment includes resolution FL, lighting effects, virtual object movement speed V, delay D lat , frame rate ZL and motion duration SC; and send the virtual teaching content and the teacher's teaching information (such as video, audio and operation instructions, etc.) to the student's terminal device in the form of digital signals through the network transmission protocol, and transmit the student's operation and feedback information (interaction results) in the virtual education environment to the teacher and the teaching server through the network to realize the two-way flow of data;

[0066] In Unity or Unreal Engine, first create a new project, select a 3D template suitable for the virtual education scene, and use the resource manager of Unity or Unreal Engine to import 3D model resources. For example, you can download models of virtual classrooms, tables and chairs, podiums, etc. from online resource libraries (such as Unity Asset Store or Unreal Marketplace).

[0067] Designing the spatial framework of virtual scenes includes defining classrooms, laboratories, outdoor learning spaces, etc. These scenes can be created by creating 3D terrain or importing ready-made scenes from existing model libraries;

[0068] In the virtual education scene, in addition to the basic buildings, other educational environment elements need to be added, such as interactive screens, projectors, virtual books, computers, whiteboards, etc. These elements can be created through 3D modeling software or imported directly from the resource library.

[0069] By setting different light sources (such as point light, spotlight, ambient light, etc.), lighting effects are added to the virtual education environment.

[0070] To add animations to virtual characters (such as teachers, students, and lecturers), such as walking, writing, and interacting, you can use animation software (such as Maya or 3D Max) to create the character's movements and import them into Unity or Unreal Engine.

[0071] In the virtual education environment, add sports stimulation elements. For example, if you are designing a physical education scene, you can simulate dynamic elements such as running, jumping, and ball games.

[0072] S12. When students are receiving distance education, physiological monitoring technology is used to monitor students' physiological indicators, where physiological monitoring technology includes electrocardiogram (ECG), optical respiratory monitoring technology (PPG), skin conductance response technology (GSR), and needle electromyography (iEMG); based on students' physiological indicators, physiological parameters of each student are obtained, and the physiological parameters include heart rate HR, respiratory rate RR, skin conductance FB, and intensity of muscle activity JH of each student in the corresponding learning period, and the physiological parameters are processed through data cleaning, data extraction, and dimensionless processing to generate physiological groups.

[0073] In this embodiment, by using 3D modeling technology, a virtual scene that meets the course content can be customized according to the specific needs of distance education. This process not only involves the spatial framework design of the virtual environment and the integration of educational elements, but also includes the adjustment of environmental parameters such as lighting effects and motion stimulation elements to ensure that the immersion of the virtual environment is highly consistent with educational needs. By integrating physiological monitoring technologies such as electrocardiogram, optical respiratory monitoring technology, skin conductance response technology, and needle electromyography, students' physiological data can be obtained in real time. This process can provide an important basis for the adjustment of the educational environment, thereby making personalized adjustments based on the physiological conditions of each student.

[0074] Example 3

[0075] Please refer to Figure 1 and Figure 2 Specifically: S1 includes the following steps:

[0076] S121. Based on the physiological groups of each student, measure the adaptability of each student's physiological response to virtual reality to obtain the physiological adaptation index P adapt , specifically:

[0077]

[0078] In the formula, α 1 , α 2 , α 3 and α 4 Indicates the influence of each physiological parameter on the adaptability, β 1 and β 2 is the average adjustment coefficient, β 1 control Contribution of some physiological responses to the physiological adaptation index, β 2 control Contribution of some physiological responses to the physiological adaptation index.

[0079] Specifically, the physiological adaptation index P adapt The larger it is, the heavier the physical burden on students and the stronger the stimulation of the virtual environment, which requires appropriate adjustments.

[0080] The specific steps of S1 also include:

[0081] S13. According to the physiological adaptation state of students and the basic parameters of the virtual education environment, the intensity of exercise stimulation in the virtual education environment is dynamically adjusted. ad , specifically:

[0082]

[0083] In the formula, V represents the speed of movement, C 1represents a constant, which indicates the threshold of each student's physiological adaptation to exercise stimulation; γ represents the adjustment factor, which affects the relationship between physiological adaptation and exercise intensity and determines the degree of "smoothness" of the adaptation process; exp(*) represents an exponential function with e as the base.

[0084] P adapt Represents the physiological adaptation of students. The increase of this index usually means that the students' physiological system has gradually adapted to the motion stimulation in the virtual environment. The higher the physiological adaptation index, the stronger the students' physical adaptability is when facing the motion stimulation in the virtual environment, and the less discomfort they feel.

[0085] In this formula, P adapt With C 1 Working together, through the exponential function To adjust the intensity of exercise stimulation. adapt is smaller (when the student's physiological fitness is low), the exponential part of the formula will tend to a larger value, resulting in S ad If γ is large, the intensity of exercise stimulation is high and the speed of exercise is fast, which will bring students a strong sense of exercise stimulation and increase the pressure of adaptation. γ realizes nonlinear adjustment. If γ is large, the adaptation process will be faster, while if γ is small, the adaptation process will be slower and smoother.

[0086] In this embodiment, by measuring the adaptability of students' physiological reactions to virtual reality and generating a physiological adaptation index in combination with physiological parameters, the physiological burden of students in a virtual education environment can be evaluated in real time. The introduction of this physiological adaptation index helps to identify students' adaptability to motion stimulation in a virtual environment and provide a scientific basis for subsequent personalized adjustments. The calculation and adjustment of the physiological adaptation index effectively avoids the physiological pressure caused by students' discomfort during virtual education and improves students' comfort and learning efficiency. According to the students' physiological adaptation state and combined with the basic parameters in the virtual education environment, the intensity of motion stimulation in the virtual environment is dynamically adjusted. Specifically, by introducing the nonlinear relationship between the adjustment factor and the physiological adaptation index, the motion stimulation in the virtual environment can be finely adjusted according to the actual adaptation of each student, avoiding students from feeling uncomfortable due to excessive or weak stimulation in the virtual environment. This nonlinear adjustment mechanism ensures that the students' physiological adaptation process in the virtual environment is smoother and more efficient, avoiding excessive or insufficient stimulation.

[0087] Example 4

[0088] Please refer to Figure 1 and Figure 2 , specifically: S2 specific steps include:

[0089] S21. Based on S13, according to the vestibular system and visual system in the human physiological system, the conflict between the visual system and the vestibular system of students in the virtual education environment is analyzed to measure the impact of visual stimulation and the response of the vestibular system. After dimensionless processing, the sensory conflict factor Gyz is obtained, which is:

[0090]

[0091] In the formula, FL represents the resolution, ZL represents the frame rate, and D lat Indicates delay, represents the visual perception term, θ represents the moderating factor affecting the delay, SC represents the motion duration, i.e., the duration of continuous learning in the virtual education environment, and C 2 represents the vestibular sensitivity adjustment constant, P sens Vestibular sensitivity, represents the motion perception term, exp Indicates a sensitive adjustment item.

[0092] Delay D lat It refers to the time interval between the generation of visual stimulation and the response of the vestibular system in a virtual reality environment. The delay can be inferred through the time synchronization of physiological signals (heart rate, skin electrical response, etc.) and virtual reality stimulation.

[0093] It reflects how the technical parameters of virtual reality equipment (the basic parameters of the virtual education environment) affect the quality of visual perception. The resolution increases the visual clarity and smoothness in proportion to the frame rate, while the delay affects the students' visual experience. As the delay increases, the perceived quality decreases. The delay is nonlinearly adjusted through an exponential function.

[0094] The formula for obtaining the sensory conflict factor Gyz evaluates the risk of motion sickness caused by virtual reality to the corresponding students by calculating the degree of conflict between visual stimulation and vestibular system feedback in the virtual environment. Movement speed, duration, and delay have a direct impact on the degree of conflict, and the sensitivity of the vestibular system determines the intensity of the student's response to the conflict. When the conflict is high, the system will automatically adjust the movement speed, duration, and delay to reduce the student's motion sickness symptoms, thereby preparing for further realization of a comfortable educational environment.

[0095] Consider the relationship between movement speed, duration, and delay. According to this item, as the movement speed and duration increase, the visual vestibular conflict will increase, while the increase in delay will reduce the conflict. The delay plays a role in balancing the perception of movement. If the delay is too large, there may be a mismatch between the movement in virtual reality and the response of the vestibular system, which will lead to an increased sense of conflict.

[0096] The nonlinear effect of vestibular sensitivity on visual-vestibular conflict is realized. As the vestibular sensitivity increases, the exponential term decreases, which increases the final conflict. Therefore, when students with high vestibular sensitivity face motion stimulation in the virtual environment, the conflict between the visual and vestibular systems will be more obvious, leading to increased discomfort.

[0097] The vestibular system and the visual system are both physiological systems of the human body, responsible for different perceptual functions respectively. The vestibular system and the visual system play an especially important role in interactive environments such as virtual reality (VR).

[0098] The specific steps of S2 also include:

[0099] S22, based on the sensory conflict factor Gyz obtained in S21, combined with the physiological adaptation index P obtained in S121 adapt , after dimensionless processing, the intensity of motion stimulation S in the virtual education environment is adjusted. ad On the basis of , the performance of the virtual education environment is further adjusted to obtain the environmental adaptability Hs, specifically:

[0100]

[0101] In the formula, C 3 represents the fitness threshold, reflecting the critical value of students' adaptation to the virtual environment; μ represents the adjustment factor 2, which controls the response speed between physiological adaptation and virtual environment adaptation.

[0102] This formula describes how to adjust the performance of the virtual environment based on physiological adaptation and conflict situations. The adaptability of the virtual environment Hs will gradually increase as the students' physiological adaptability increases. The system will automatically optimize the visual performance and movement intensity of the virtual environment. The larger the environmental adaptability Hs, the more the system adapts to the students' status and can provide a higher intensity virtual experience.

[0103] In this embodiment, the coordination of sensory stimulation is optimized: by calculating the sensory conflict factor Gyz, the degree of conflict between the student's visual system and vestibular system can be measured in real time. This factor reflects the coordination of visual and motion stimulation in the virtual environment, thereby avoiding students from having discomfort due to excessive stimulation. For example, the conflict between visual stimulation and motion perception in the virtual environment is promptly identified and adjusted to ensure the physical and mental comfort of students in virtual education. Personalized adaptation adjustment: combining the physiological adaptation index and the sensory conflict factor, the environmental adaptability Hs is further optimized after dimensionless processing. This adjustment not only considers the student's physiological response, but also integrates the interactive effect of visual and motion perception to provide each student with a personalized virtual education environment. Through dynamic adjustment, the negative impact caused by sensory conflict can be effectively alleviated, and the student's learning concentration and learning effect can be improved. Accurately control the adaptability of the virtual environment: The adjustment of the environmental adaptability Hs is based on the sensitivity of the vestibular system and the balance of visual stimulation, ensuring that students can adapt to the virtual environment in a relatively suitable state. This precise control helps to avoid fatigue or discomfort caused by sensory overload in students during long-term learning, thereby improving learning efficiency and comfort. Improve learning experience and physical and mental health: By adjusting the intensity of motion stimulation and the coordination of the visual and vestibular systems in the virtual education environment, it can provide students with a more balanced learning experience, optimize physical and mental health, reduce discomfort, and enhance the immersion of virtual learning and the motivation for continuous learning.

[0104] Example 5

[0105] Please refer to Figure 1 and Figure 2 Specifically: S2 includes the following specific steps:

[0106] S23. Conduct vestibular sensitivity tests on each student, record the physiological changes of each student according to different intensity motion stimulation conditions (basic parameters of the virtual education environment), analyze each student's response ability to the stimulation of his or her vestibular system, and obtain the vestibular sensitivity P of each student. sens , specifically:

[0107]

[0108] In the formula, HR Δ , j represents the heart rate change amplitude under the jth exercise stimulation condition, FB Δ，j represents the change amplitude of skin conductance under the jth motion stimulus condition, JH Δ，j represents the change in muscle activity intensity under the j-th exercise stimulus condition, RR Δ , j represents the amplitude of respiratory rate change under the jth motion stimulation condition, m represents the total number of tests, j represents the test number, and K represents the correction constant.

[0109] Vestibular sensitivity P sens Reflecting students' sensitivity to motion stimuli in virtual educational environments.

[0110] Get the vestibular sensitivity P of each student sens The denominator of the formula uses the maximum value max(|HR Δ，j |,|FB Δ，j |,|JH Δ，j |,|RR Δ，j |), this is to normalize the differences between various physiological responses. Even if the change range of a parameter is small, it can still be normalized by dividing it by the maximum change range, so that the final vestibular sensitivity value reflects the overall strength of the individual's physiological response, rather than a specific response. sens The higher the value, the more sensitive the corresponding student's vestibular system is, making them more likely to experience discomfort or motion sickness symptoms.

[0111] Example: Assume that the data related to a student's physiological changes are as follows: HR Δ , j = 15 times / min; RR Δ , j = 10 times / min; FB Δ，j =0.5 microsiemens; JH Δ，j =2 microvolts; here we take a motion stimulation condition as an example; the correction constant K is 0.1;

[0112] First, calculate the absolute change of each parameter:

[0113] |HR Δ , j|=15;|RR Δ , j|=10;|FB Δ，j |=0.5;|JH Δ，j |=2;

[0114] Then find the maximum value:

[0115] max(15,10,0.5,2)=15;

[0116] Finally, substitute into the formula:

[0117]

[0118] Therefore, the student's vestibular sensitivity P sens The value is 1.93, which represents the intensity of the student's vestibular system response in the virtual environment. The higher the value, the more sensitive it is and the more likely it is to feel uncomfortable.

[0119] In this embodiment, by recording the physiological responses of students under motion stimulation of different intensities, the vestibular sensitivity of each student can be accurately measured. This process enables the virtual education environment to be personalized according to the physiological responses of individual students, avoiding discomfort or motion sickness caused by excessive stimulation, and improving students' learning experience and comfort. Standardized physiological response differences: By normalizing the amplitude of physiological response changes, it is ensured that the differences between different physiological parameters will not affect the final vestibular sensitivity assessment. This standardization process enables the sensitivity of each student to comprehensively reflect the intensity of its overall physiological response, thereby improving the accuracy and consistency of the assessment. Reduce the risk of motion sickness: The calculation of vestibular sensitivity values ​​can effectively identify students who are sensitive to motion stimulation in the virtual environment. For these students, the intensity of motion stimulation in the virtual environment can be appropriately reduced to reduce the occurrence of discomfort or motion sickness, and ensure comfort and concentration during the learning process. Accurately adjust the virtual environment: Based on the evaluation results of vestibular sensitivity, the virtual education environment can be dynamically adjusted to match the motion stimulation with the students' physiological fitness and vestibular system response, provide a personalized learning experience, and optimize the design of the virtual environment.

[0120] Example 6

[0121] Please refer to Figure 1 , specifically: S3 specific steps include:

[0122] S31, by vestibular sensitivity P sens , environmental adaptability Hs and physiological adaptability index P adapt As the input value of the trained machine learning model, after fitting and dimensionless processing, the individualized feedback coefficient I of each student is output user , specifically:

[0123]

[0124] In the formula, represents the third regulatory factor, which affects the interaction between the vestibular system and physiological adaptation; this formula takes into account individual differences, especially the sensitivity of the vestibular system. As the individual's physiological fitness and environmental fitness change, the system will adjust the feedback strategy according to the sensitivity of the vestibular system to ensure that each student's experience in the virtual environment is optimized. user The higher the value, the better the individual adjustment effect is and the more accurate the regulation and feedback of the virtual environment is.

[0125] The specific steps of S4 include:

[0126] S41. Using the individualized feedback coefficient I of the corresponding students obtained in the historical period user , set the threshold, and transform the individual feedback coefficient I userCompare with the threshold to identify the personalized adjustment effect of the cloud platform on students. The specific identification content is as follows:

[0127] If the individualized feedback coefficient I user If the threshold is exceeded, it means that the current cloud platform’s personalized adjustment effect on the corresponding students is qualified, and the experience of the virtual education environment is more in line with the students’ comfort and needs. At this time, the current personalized adjustment settings will be maintained, and the cloud platform will automatically use the current personalized adjustment settings as the standard configuration for the corresponding students to ensure that the subsequent learning process maintains this state and avoid unnecessary adjustments;

[0128] S42, if the individualized feedback coefficient I user If the threshold is not exceeded, it means that the current cloud platform's personalized adjustment effect on the corresponding students is unsatisfactory, and the current personalized adjustment fails to fully meet the needs of the students. At this time, the learning content and tasks of the corresponding students will be dynamically adjusted. For example, if feedback shows that students feel too much pressure or lack of interest in certain courses, the cloud platform will automatically reduce the learning difficulty, provide content that better meets the needs of students, or add more guidance and feedback support.

[0129] Specifically, the individualized feedback coefficient I of the corresponding students obtained in the historical period is used user , the specific contents of setting the threshold are as follows:

[0130] The individualized feedback coefficient I of the corresponding students obtained in the historical period user Through statistical algorithms, the mean and standard deviation are obtained respectively, and based on the individualized feedback coefficient I user The mean and standard deviation of the threshold are set: threshold = individualized feedback coefficient I user The mean of + k* individualized feedback coefficient I user The standard deviation of ; where k is a constant, with a value of 1-3, corresponding to different confidence levels, and the specific value is set by the user (according to the actual situation).

[0131] like Figure 3 As shown, the individualized feedback coefficient I of each student at the corresponding time point user Different values ​​will be generated due to personalized adjustment. If the value is above the threshold, it means that the personalized adjustment effect of the current cloud platform on the corresponding students is qualified. On the contrary, if it does not exceed the threshold, it means that the personalized adjustment effect of the current cloud platform on the corresponding students is unqualified.

[0132] In this embodiment, through the machine learning model, vestibular sensitivity, environmental adaptability and physiological adaptation index are used as input values ​​to calculate the individualized feedback coefficient of each student, thereby optimizing the motion stimulation and learning content in the virtual environment to ensure that the physiological and psychological needs of each student are met. The individualized feedback coefficient is closely related to the student's vestibular system, environmental adaptability and physiological adaptation index. As the student's learning progress and adaptation situation change, the system can adjust the feedback strategy in real time to ensure that the student's comfort is continuously optimized and avoid overstimulation or too low stimulation intensity. When the individualized feedback coefficient fails to reach the threshold, the system will automatically identify the student's adaptation problem, adjust the learning content, task difficulty or provide additional support. Through dynamic adjustment, the student's learning pressure can be reduced, interest and participation can be increased, thereby improving the overall learning effect. Continuously optimize the learning experience: Through continuous monitoring of historical data and feedback, the cloud platform can continuously learn and adjust, so that each student can maintain a relatively good personalized adjustment setting in the future learning process, avoid interference caused by excessive adjustment, and maintain the consistency and stability of the learning state.

[0133] Example 7

[0134] Please refer to Figure 4 ,Specifically: the distance education system based on virtual reality includes the first ,analysis subsystem two and the third analysis subsystem;

[0135] The No. 1 analysis subsystem will use 3D modeling technology to build a virtual education environment for students to conduct distance education. During the distance education process, it will use physiological monitoring technology to monitor students' physiological indicators and adjust the intensity of sports stimulation in the virtual education environment based on the degree of sports stimulation in distance education. ad ;

[0136] The second analysis subsystem will analyze the conflict between the visual system and the vestibular system of students in the virtual education environment based on the human physiological system, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1, and conduct vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ;

[0137] The third analysis subsystem will use supervised learning methods to build a machine learning model and convert the vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user , and according to the individualized feedback coefficient I user Numerical,identification of the personalized adjustment effect of the cloud platform on students.

[0138] Although embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the appended claims and their equivalents.

Claims

1. A distance education method based on virtual reality, characterized in that: The following steps are included: S1: Use 3D modeling technology to build a virtual education environment for students to conduct distance education. During the distance education process, use physiological monitoring technology to monitor students' physiological indicators, and adjust the intensity of sports stimulation in the virtual education environment in combination with the degree of sports stimulation in distance education. ad ; S2: Based on the human physiological system, analyze the conflict between the visual system and the vestibular system of students in the virtual education environment, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1. Perform vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ; S3: Use supervised learning methods to build a machine learning model and convert vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user ; S4: Based on historical data, set the threshold and compare it with the individual feedback coefficient I user Comparison is made to identify the personalized regulation effect of the cloud platform on students.

2. The distance education method based on virtual reality according to claim 1, characterized in that: The specific steps of S1 include: S11. According to the needs of distance education, use 3D modeling software in 3D modeling technology to build a virtual education environment that meets the needs of distance education. Building the virtual education environment includes creating a 3D template, editing basic parameters of the virtual education environment, designing a space framework of the virtual scene, adding environmental elements and adding motion stimulation elements. Among them, editing the basic parameters of the virtual education environment includes resolution FL, lighting effects, movement speed V of virtual objects, delay D lat , frame rate ZL and motion duration SC; and send the virtual teaching content and the teacher's teaching information to the student's terminal device in the form of digital signals through the network transmission protocol, and transmit the student's operation and feedback information in the virtual education environment back to the teacher and the teaching server through the network; S12. When students are receiving distance education, physiological monitoring technology is used to monitor students' physiological indicators, where physiological monitoring technology includes electrocardiogram, optical respiratory monitoring technology, skin conductance response technology, and needle electromyography; based on students' physiological indicators, physiological parameters of each student are obtained, and the physiological parameters include heart rate HR, respiratory rate RR, skin conductance FB, and intensity of muscle activity JH of each student in the corresponding learning period, and the physiological parameters are processed through data cleaning, data extraction, and dimensionless processing to generate physiological groups.

3. The distance education method based on virtual reality according to claim 2, characterized in that: The specific steps of S1 also include: S121. Based on the physiological groups of each student, measure the adaptability of each student's physiological response to virtual reality to obtain the physiological adaptation index P adapt , specifically: In the formula, α1, α2, α3 and α4 represent the influence of each physiological parameter on the adaptability, β1 and β2 are adjustment coefficients, and β1 controls Contribution of some physiological responses to the physiological adaptation index, β2 control Contribution of some physiological responses to the physiological adaptation index.

4. The distance education method based on virtual reality according to claim 3, characterized in that: The specific steps of S1 also include: S13. According to the physiological adaptation state of students and the basic parameters of the virtual education environment, the intensity of exercise stimulation in the virtual education environment is dynamically adjusted. ad , specifically: In the formula, V represents the movement speed, C1 represents a constant, which indicates the threshold of the influence of each student's physiological adaptation on the exercise stimulus; γ represents the adjustment factor 1, which affects the relationship between physiological adaptation and exercise intensity; exp(*) represents an exponential function with e as the base.

5. The virtual reality-based distance education method according to claim 4, characterized in that: The specific steps of S2 include: S21. Based on S13, according to the vestibular system and visual system in the human physiological system, the conflict between the visual system and the vestibular system of students in the virtual education environment is analyzed to measure the impact of visual stimulation and the response of the vestibular system. After dimensionless processing, the sensory conflict factor Gyz is obtained, which is: In the formula, FL represents the resolution, ZL represents the frame rate, and D lat Indicates delay, represents the visual perception term, θ represents the regulatory factor affecting the delay, SC represents the motion duration, C2 represents the vestibular sensitivity regulatory constant, and P sens Vestibular sensitivity, represents the motion perception term, Indicates a sensitive adjustment item.

6. The distance education method based on virtual reality according to claim 5, characterized in that: The specific steps of S2 also include: S22, based on the sensory conflict factor Gyz obtained in S21, combined with the physiological adaptation index P obtained in S121 adapt , after dimensionless processing, the intensity of motion stimulation S in the virtual education environment is adjusted. ad On the basis of , the performance of the virtual education environment is further adjusted to obtain the environmental adaptability Hs, specifically: Where C3 represents the fitness threshold, which reflects the critical value of students' adaptation to the virtual environment; μ represents the adjustment factor 2, which controls the response speed between physiological adaptation and virtual environment adaptation.

7. The distance education method based on virtual reality according to claim 6, characterized in that: The specific steps of S2 also include: S23. Conduct vestibular sensitivity tests on each student, record the physiological changes of each student according to different intensity of motion stimulation conditions, analyze each student's response ability to their own vestibular system stimulation, and obtain each student's vestibular sensitivity P sens , specifically: In the formula, HR Δ , j represents the heart rate change amplitude under the jth exercise stimulation condition, FB Δ，j represents the change amplitude of skin conductance under the jth motion stimulus condition, JH Δ，j represents the change in muscle activity intensity under the j-th exercise stimulus condition, RR Δ , j represents the amplitude of respiratory rate change under the jth motion stimulation condition, m represents the total number of tests, j represents the test number, and K represents the correction constant.

8. The distance education method based on virtual reality according to claim 7, characterized in that: The specific steps of S3 include: S31, by vestibular sensitivity P sens , environmental adaptability Hs and physiological adaptability index P adapt As the input value of the trained machine learning model, after fitting and dimensionless processing, the individualized feedback coefficient I of each student is output user , specifically: In the formula, represents regulatory factor three, influencing the interaction between the vestibular system and physiological adaptation.

9. The virtual reality-based distance education method according to claim 8, characterized in that: The specific steps of S4 include: S41. Using the individualized feedback coefficient I of the corresponding students obtained in the historical period user , set the threshold, and transform the individual feedback coefficient I user Compare with the threshold to identify the personalized adjustment effect of the cloud platform on students. The specific identification content is as follows: If the individualized feedback coefficient I user If the threshold is exceeded, it means that the personalized adjustment effect of the current cloud platform on the corresponding student is qualified. At this time, the current personalized adjustment settings will be maintained and automatically used as the standard configuration for the corresponding student through the cloud platform. S42, if the individualized feedback coefficient I user If the threshold is not exceeded, it means that the current cloud platform's personalized adjustment effect on the corresponding students is unsatisfactory. At this time, the learning content and tasks of the corresponding students will be dynamically adjusted.

10. A virtual reality-based distance education system, used to implement the virtual reality-based distance education method according to any one of claims 1 to 9, characterized in that: It includes analysis subsystem No.1, analysis subsystem No.2 and analysis subsystem No.3; The No. 1 analysis subsystem will use 3D modeling technology to build a virtual education environment for students to conduct distance education. During the distance education process, it will use physiological monitoring technology to monitor students' physiological indicators and adjust the intensity of sports stimulation in the virtual education environment based on the degree of sports stimulation in distance education. ad ; The second analysis subsystem will analyze the conflict between the visual system and the vestibular system of students in the virtual education environment based on the human physiological system, and adjust the environmental adaptability Hs again in combination with the preliminary adjustment work in S1, and conduct vestibular sensitivity tests on each student to identify the vestibular sensitivity P of each student. sens ; The third analysis subsystem will use supervised learning methods to build a machine learning model and convert the vestibular sensitivity P sens , environmental adaptability Hs and students' physiological indicators are used as the input of the machine learning model, and the individualized feedback coefficient I of each student is output after fitting. user , and according to the individualized feedback coefficient I user Numerical,identification of the personalized adjustment effect of the cloud platform on students.

Images