Virtual rich real environment training system based on benign stress

Abstract

The invention belongs to the technical field of virtual reality, and discloses a virtual rich real environment training system based on benign stress, comprising: a database module for storing cognitive tasks and virtual scenes; the acceptance testing module is used for testing a preset cognitive task of the user and generating a scene acceptance index; and the initial training task generation module is used for generating a training task comprising two groups of scene parameters and one cognitive task according to the index. And the training execution module is used for constructing a dynamically changing virtual training scene according to the two groups of parameters and executing a cognitive task in the virtual training scene. And the training task updating module is used for generating a new training task based on the execution result and the acceptability index. And the training planning module formulates an overall training plan and controls an execution process. Personalized training content is provided by evaluating individual differences of the users, it is ensured that the training difficulty is matched with the capabilities of the users, and the training effect is optimized while the user participation degree and the possibility of insisting in training for a long time are improved.

Description

Technical Field

[0001] The present invention relates to the field of virtual reality technology, and more specifically, to a virtual rich reality environment training system based on benign stress. Background Art

[0002] Ischemic stroke is one of the major neurological impairment syndromes that endangers human health. Ischemic stroke not only has high morbidity, high disability and high mortality, but is also often accompanied by a variety of sequelae such as post-stroke depression (PSD), cognitive impairment, limb movement disorders, etc., which seriously limit the patient's ability to return to the community and bring huge burdens to patients, families and society.

[0003] In recent years, with the rapid development of virtual reality (VR) technology, cognitive training systems based on virtual environments have shown great potential in the field of neurorehabilitation. Such systems provide stroke patients with an immersive training experience by simulating real scenes, which helps improve cognitive function, enhance the ability to cope with stress, and promote mental health recovery.

[0004] However, the existing virtual environment cognitive training system still has significant deficiencies in achieving personalized and adaptive training. The existing technology lacks in-depth analysis and quantitative evaluation of the sensitivity of stroke patients to various environmental elements in virtual scenes. Due to the different degrees and types of neurological damage in stroke patients, there are significant differences in their response and tolerance to different stimuli in the virtual environment. For example, some patients may be particularly sensitive to visual stimulation and relatively insensitive to auditory stimulation; however, when adjusting the virtual space according to the training results, the existing system usually adopts a general adjustment template or a simple linear increase and decrease mode. This simple adjustment method may cause the adjusted virtual scene to have an inappropriate degree of stimulation for stroke patients, either excessive stimulation causing unnecessary stress and anxiety, causing users to give up training; or insufficient stimulation, resulting in poor training results. Summary of the invention

[0005] In order to overcome the problem that the prior art easily causes users to give up training and the training effect is poor, the present invention proposes a virtual rich reality environment training system based on benign stress to solve the above problems.

[0006] The present invention provides the following technical solutions: A virtual rich reality environment training system based on benign stress, comprising: A database module, used to store cognitive tasks and virtual scenes under different scene parameters; The acceptance test module is used to test the user's preset cognitive tasks in a preset test virtual scene and obtain the evaluation results, and generate the user's scene acceptance index according to the evaluation results; An initial training task generation module, used to generate a training task according to the user's scenario acceptance index, wherein the training task includes two sets of scenario parameters and a cognitive task; A training execution module is used to execute a training task; the execution of the training task includes: constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task, and using cognitive tasks in the training scene to train the user and obtain evaluation results; A training task update module, used to generate new training tasks based on the executed training tasks, evaluation results and parameter acceptance indicators; The training planning module is used to formulate training plans, determine the execution time and frequency of training tasks, and control the training execution module and the training task update module according to the training plan.

[0007] Preferably, the cognitive task includes task content and task level, and the task level includes five levels from 1 to 5; the scene parameters include personnel density, obstacle density, environmental noise and brightness; wherein the parameter value of each scene parameter is expressed as a value between 0 and 100 after standardized processing; the evaluation result includes task completion and physiological score.

[0008] Preferably, the physiological score is obtained by collecting physiological indicators of the user, and the physiological indicators include heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation; The calculation formula of the physiological score is as follows: , In the formula, represents the physiological score, , , and They represent heart rate variability, galvanic skin response, respiratory rate, and blood oxygen saturation, respectively; , , and Respectively represent the preset baseline values ​​of heart rate variability, galvanic skin response, respiratory rate and blood oxygen saturation; , , and Respectively represent the preset maximum change values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation. , , and They represent the weight values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation respectively.

[0009] Preferably, the preset test virtual scenes include a personnel test scene, an obstacle test scene, a noise test scene, a brightness test scene and a standard test scene; wherein, in the personnel test scene, the value of the personnel density parameter is , the values ​​of the other three parameters are ; In the obstacle test scenario, the value of the obstacle density parameter is , the values ​​of the other three parameters are ; In the noise test scenario, the value of the environmental noise parameter is , the values ​​of the other three parameters are ; In the brightness test scene, the value of the brightness parameter is , the values ​​of the other three parameters are ; Standard test scenario, the values ​​of the four parameters are ;in, , ; The preset cognitive task is any cognitive task with a task level of 1; The evaluation results under five test scenarios were obtained, and the test scores were obtained by multiplying the task completion degree by the physiological score, which were recorded as personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; According to the test scores, the personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance are calculated respectively. The calculation formula is as follows: , In the formula, , , and They represent personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance respectively. , , , and They represent the personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; The scene acceptance index is obtained by combining personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance.

[0010] Preferably, generating a training task according to the user's scenario acceptance index includes: Acquire initial scene parameters, wherein the values ​​of each parameter in the initial scene parameters are preset values; Use the value of each parameter in the initial scene parameter plus the corresponding value in the scene acceptance index to obtain the new scene parameter recorded as the target parameter; Obtain any cognitive task with a task level of 1 as the target task; The initial scene parameters, target parameters and target tasks are combined to obtain the training task.

[0011] Preferably, the step of constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task includes: Compare the parameter values ​​of the two groups of scene parameters in the training task, and use the scene parameter with the smaller sum of the parameter values ​​as the starting scene parameter, and the other group as the ending scene parameter; Determine the total length of virtual space , and divide it into intervals of equal length; Calculate the difference between the starting scene parameters and the ending scene parameters to obtain the scene parameter difference vector ; Use the formula Calculate the parameter increment vector for each interval ; For each interval, the scene parameter vector is calculated using the following formula: , In the formula, Indicates The scene parameter vector of intervals, , A vector representing the values ​​of the starting scene parameters; According to the scene parameter vector of each interval Generate corresponding scene parameters and retrieve corresponding virtual scene elements from the database module; The virtual scene elements of each interval are continuously arranged along a predefined path to construct a continuously changing virtual space as a training scene.

[0012] Preferably, the step of generating a new training task based on the executed training task, the evaluation result and the parameter acceptance index comprises: Determine the scene adjustment direction based on the physiological scores in the evaluation results; Generate two new sets of scenario parameters based on the scenario adjustment direction, the scenario parameters in the executed training task, and the scenario acceptance index; Determine the direction of task adjustment based on the task completion degree in the evaluation results; Selecting new cognitive tasks based on the task adjustment orientation and cognitive tasks in the training task performed; The new two sets of scene parameters and the new cognitive tasks are combined to generate new training tasks.

[0013] Preferably, the step of determining the scene adjustment direction includes: When the physiological score is lower than the preset lower limit, the scene adjustment direction is determined to reduce the difficulty; when the physiological score is higher than the preset upper limit, the scene adjustment direction is determined to increase the difficulty; when the physiological score is between the preset lower limit and the upper limit, the scene adjustment direction is determined to maintain the difficulty; The step of generating two new sets of scene parameters based on the scene adjustment direction, the scene parameters in the executed training task and the scene acceptance index comprises: If the scene adjustment direction is to reduce the difficulty, the set of parameter values ​​of the two sets of scene parameters in the executed training task with the smaller sum is selected as the baseline parameter; the mitigation parameter is calculated, where the mitigation parameter is equal to the baseline parameter minus the scene acceptance index; the baseline parameter is used as the new first set of scene parameters, and the mitigation parameter is used as the new second set of scene parameters; If the scene adjustment direction is to increase the difficulty, then select the larger sum of the parameter values ​​of the two sets of scene parameters in the executed training task as the baseline parameter; calculate the enhanced parameter, where the enhanced parameter is equal to the baseline parameter plus the scene acceptance index; use the baseline parameter as the new first set of scene parameters, and the enhanced parameter as the new second set of scene parameters; If the scene adjustment direction is to maintain the difficulty, the two sets of scene parameters in the executed training task remain unchanged.

[0014] Preferably, the step of determining the task adjustment direction includes: When the task completion rate is lower than the preset lower limit, the task adjustment direction is determined to reduce the difficulty; when the task completion rate is higher than the preset upper limit, the task adjustment direction is determined to increase the difficulty; when the task completion rate is between the preset lower limit and the upper limit, the task adjustment direction is determined to maintain the difficulty; The step of selecting a new cognitive task based on the task adjustment direction and the cognitive task in the executed training task comprises: If the task adjustment direction is to reduce the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level minus 1 is selected as a new cognitive task; if the current level is already 1, another cognitive task with a level of 1 is selected as a new cognitive task; If the task adjustment direction is to increase the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level plus 1 is selected as a new cognitive task. If the current level is already 5, another cognitive task with a level of 5 is selected as a new cognitive task; If the task adjustment direction is to maintain the difficulty, the task level of the cognitive task in the executed training task is recorded as the current level, and other cognitive tasks with the current level are selected as new cognitive tasks.

[0015] The present invention provides a virtual rich reality environment training system based on benign stress, which has the following beneficial effects: Through the acceptance test module, the sensitivity of each user to different environmental elements can be accurately quantified in terms of multiple dimensions such as personnel density, obstacle density, environmental noise and brightness. This fine-grained evaluation method overcomes the problem of insufficient analysis of individual differences of users in the existing technology, and provides accurate personalized basic data for subsequent training. The training execution module constructs a continuously changing virtual space to achieve dynamic adjustment of the training environment. This method can not only comprehensively evaluate the performance of users in different environments, but also help users gradually adapt to more challenging scenarios. At the same time, the training task update module adjusts the scene parameters and cognitive task difficulty in real time based on the user's physiological response and task completion. This closed-loop feedback mechanism ensures that the training can provide sufficient cognitive load without causing excessive stress, thereby optimizing the training effect. By providing personalized and progressive training content, it can continuously stimulate the interest and participation of users, help reduce frustration during training, and increase the possibility of long-term persistence in training. BRIEF DESCRIPTION OF THE DRAWINGS

[0016] Figure 1 The module diagram of a virtual rich reality environment training system based on benign stress of the present invention. DETAILED DESCRIPTION

[0017] 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.

[0018] Example 1 See also Figure 1 In this embodiment, a virtual rich reality environment training system based on benign stress includes: A database module, used to store cognitive tasks and virtual scenes under different scene parameters; The cognitive task includes task content and task level, and the task level includes five levels from 1 to 5; the scene parameters include personnel density, obstacle density, environmental noise and brightness; wherein the parameter value of each scene parameter is expressed as a value between 0 and 100 after standardized processing; the evaluation result includes task completion and physiological score.

[0019] The physiological score is obtained by collecting the user's physiological indicators, including heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation; The calculation formula of the physiological score is as follows: , In the formula, represents the physiological score, , , and They represent heart rate variability, galvanic skin response, respiratory rate, and blood oxygen saturation, respectively; , , and Respectively represent the preset baseline values ​​of heart rate variability, galvanic skin response, respiratory rate and blood oxygen saturation; , , and Respectively represent the preset maximum change values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation. , , and They represent the weight values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation respectively.

[0020] In this embodiment, the database module is used to store cognitive tasks and virtual scenes under different scene parameters. Cognitive tasks include two main attributes: task content and task level. The task level is divided into five levels from 1 to 5. The higher the level, the greater the difficulty of the task. The level of cognitive tasks is determined by manual grading. For example, level 1 can be walking along a fixed path; level 2 can be walking along a fixed path while performing simple counting (such as counting from 1 to 10); level 3 can be walking along a fixed path while completing simple graphic shape judgments, etc. This grading method gradually increases according to the complexity of the task and the cognitive load, ensuring the gradualness and adaptability of the training.

[0021] The scene parameters include four dimensions: personnel density, obstacle density, environmental noise, and brightness. To ensure the comparability of the data and the convenience of calculation, each parameter value is standardized and expressed as a value between 0 and 100. This embodiment adopts the maximum and minimum standardization method for processing, and the formula is: standardized value = (original value-minimum value) / (maximum value-minimum value)*100. Take personnel density as an example: the personnel density is expressed as the number of people per 10 square meters, the minimum value is 0 people / 10 square meters, and the maximum value is set to 20 people / 10 square meters. Through this standardized processing, parameters of different dimensions are uniformly mapped to the range of 0-100, which is convenient for subsequent comparison and calculation.

[0022] The stored virtual scenes can be manually created according to the scene parameters, or they can be automatically generated and then manually optimized. By pre-storing high-quality virtual scenes, the user's sense of immersion can be significantly improved, ensuring the consistency and reliability of the training effect.

[0023] The evaluation results include two indicators: task completion and physiological score. Task completion is measured as a percentage of task completion, which directly reflects the user's performance. The physiological score is obtained by collecting the user's heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation weighted. In the initial state, the weights of these four indicators are set to 0.25 to form a balanced evaluation benchmark. These weights can be adjusted by professionals according to specific training goals or individual differences to optimize the accuracy and pertinence of the evaluation. These indicators can reflect the user's physiological state and stress level, and can reflect the degree of stimulation of the user by virtual scenes and cognitive tasks. These physiological indicators can reflect the user's physiological state and stress level, and then through comprehensive analysis of these indicators, the system can accurately evaluate the degree of stimulation of virtual scenes and cognitive tasks on users, and provide a reference for subsequent adjustments to virtual scenes and cognitive tasks.

[0024] The acceptance test module is used to test the user's preset cognitive tasks in a preset test virtual scene and obtain the evaluation results, and generate the user's scene acceptance index according to the evaluation results; The preset test virtual scenes include personnel test scenes, obstacle test scenes, noise test scenes, brightness test scenes and standard test scenes; wherein, in the personnel test scene, the value of the personnel density parameter is , the values ​​of the other three parameters are ; In the obstacle test scenario, the value of the obstacle density parameter is , the values ​​of the other three parameters are ; In the noise test scenario, the value of the environmental noise parameter is , the values ​​of the other three parameters are ; In the brightness test scene, the value of the brightness parameter is , the values ​​of the other three parameters are ; Standard test scenario, the values ​​of the four parameters are ;in, ,

[0025] The preset cognitive task is any cognitive task with a task level of 1; The evaluation results under five test scenarios were obtained, and the test scores were obtained by multiplying the task completion degree by the physiological score, which were recorded as personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; According to the test scores, the personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance are calculated respectively. The calculation formula is as follows: , In the formula, , , and They represent personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance respectively. , , , and They represent the personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; The scene acceptance index is obtained by combining personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance.

[0026] In this embodiment, a pre-set virtual scene is used for user testing. These test scenes are constructed based on pre-designed scene parameters, including five types of test scenes: personnel test scene, obstacle test scene, noise test scene, brightness test scene, and standard test scene. Each scene is evaluated for specific scene parameters to comprehensively test the user's adaptability to different environmental factors.

[0027] For example, in the human test scenario, the human density parameter is set to an intermediate level (e.g., 50), while the other three parameters (obstacle density, ambient noise, and brightness) are kept at a low level (e.g., 20). This differentiated setting can effectively isolate and evaluate the user's sensitivity to specific scenario parameters. The standard test scenario sets all parameters to a low level (20) as a benchmark for evaluation.

[0028] During the test, the system selected simple cognitive tasks with a task level of 1, such as walking along a fixed path. The purpose of selecting low-difficulty tasks is to minimize the interference of task complexity on the test results and ensure that the test results can accurately reflect the impact of scenario parameters on users.

[0029] In each test scenario, the system collects the user's task completion and physiological scores as evaluation results. By multiplying these two indicators, the system obtains the comprehensive test score of each scenario. Subsequently, the system calculates the user's acceptance of the parameters of each scenario by comparing the score difference between each test scenario and the standard test scenario and considering the range of parameter value changes. This calculation method can effectively reflect the user's adaptability to specific scenario parameters. The higher the acceptance value, the stronger the user's tolerance to the corresponding scenario stimulation.

[0030] Finally, the system combines the acceptance of people, obstacles, noise and brightness into an overall index, namely the user's scene acceptance index. This comprehensive index fully reflects the user's adaptability to various environmental factors and provides a data basis for the design and optimization of subsequent personalized training tasks.

[0031] An initial training task generation module, used to generate a training task according to the user's scenario acceptance index, wherein the training task includes two sets of scenario parameters and a cognitive task; Generating a training task according to the user's scenario acceptance index includes: Acquire initial scene parameters, wherein the values ​​of each parameter in the initial scene parameters are preset values; Use the value of each parameter in the initial scene parameter plus the corresponding value in the scene acceptance index to obtain the new scene parameter recorded as the target parameter; Obtain any cognitive task with a task level of 1 as the target task; The initial scene parameters, target parameters and target tasks are combined to obtain the training task.

[0032] In this embodiment, each training task consists of two sets of scene parameters and a cognitive task. This structural design allows the creation of a dynamically changing training environment.

[0033] The generation process first obtains the initial scene parameters, which serve as the starting point for the training task. The values ​​in the initial scene parameters are set to preset values, usually low values ​​(such as 10) to ensure that the training starts from a relatively simple environment. This setting helps users gradually adapt to the training environment and reduce the frustration caused by the initial difficulty.

[0034] Next, the value of the initial scene parameter is added to the corresponding value in the user's scene acceptance index to generate a new scene parameter, called the target parameter. For example, if the user's crowd density acceptance is 18, then the crowd density value in the target parameter will be 28. This approach ensures that the difficulty of the training task matches the user's personal adaptability and provides a moderate challenge.

[0035] In order to achieve a gradual training process, any cognitive task with a task level of 1 is selected as the target task. The purpose of selecting low-difficulty tasks is to allow users to start from the basics and gradually adapt to the training environment and task requirements. This method is in line with the principle of gradual cognitive training, allowing users to gradually transition to more complex tasks and environments based on mastering basic skills.

[0036] Finally, the initial scenario parameters, target parameters, and target tasks are combined to form a complete training task. This combination creates a training environment that gradually transitions from simple to complex while maintaining the stability of cognitive tasks. Through this personalized training task generation method, it is possible to create training content that best suits each user's current ability level. This not only improves the effectiveness of training, but also enhances user engagement and motivation.

[0037] A training execution module is used to execute a training task; the execution of the training task includes: constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task, and using cognitive tasks in the training scene to train the user and obtain evaluation results; The step of constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task includes: Compare the parameter values ​​of the two groups of scene parameters in the training task, and use the scene parameter with the smaller sum of the parameter values ​​as the starting scene parameter, and the other group as the ending scene parameter; Determine the total length of virtual space , and divide it into intervals of equal length; Calculate the difference between the starting scene parameters and the ending scene parameters to obtain the scene parameter difference vector ; Use the formula Calculate the parameter increment vector for each interval ; For each interval, the scene parameter vector is calculated using the following formula: , In the formula, Indicates The scene parameter vector of intervals, , A vector representing the values ​​of the starting scene parameters; According to the scene parameter vector of each interval Generate corresponding scene parameters and retrieve corresponding virtual scene elements from the database module; The virtual scene elements of each interval are continuously arranged along a predefined path to construct a continuously changing virtual space as a training scene.

[0038] In this embodiment, the training execution module constructs a dynamically changing virtual training scene according to two sets of scene parameters in the training task, and performs cognitive task training in this scene. The process of constructing the virtual training scene is as follows; First, the system compares the sum of the parameter values ​​of the two sets of scene parameters in the training task, and defines the set with the smaller sum of parameter values ​​as the starting scene parameters, and the other set as the ending scene parameters. This setting is to ensure that the training scene gradually transitions from relatively simple to complex.

[0039] Next, the system determines the total length of the virtual space, which is usually no more than 5 kilometers, and divides it evenly into n equal-length intervals. The value of n can be set according to actual needs, such as 10 or 20, to achieve a smooth transition of the scene. This division method provides the basis for subsequent parameter interpolation.

[0040] The system then calculates the difference between the starting scene parameters and the ending scene parameters to obtain the scene parameter difference vector. By dividing the difference vector by the number of intervals n, the system obtains the parameter increment vector for each interval. This calculation method ensures that the scene parameters change linearly in the entire virtual space.

[0041] According to the calculated scene parameter vector of each interval, the system retrieves the corresponding virtual scene from the database module. These virtual scenes include crowd models of different densities, various obstacles, and environmental sound and lighting effects of different intensities.

[0042] Finally, the system arranges the virtual scene elements of each interval continuously along a predefined path to construct a continuously changing virtual space as a training scene. This predefined path can be a straight line, a curve, or a more complex shape to meet different training needs.

[0043] The training scenarios constructed by this method have the characteristics of dynamic changes, which can simulate the process of environmental changes from simple to complex. This can not only comprehensively evaluate the user's performance in different environments, but also help users gradually adapt to more challenging scenarios, thereby achieving more effective cognitive ability training.

[0044] In the constructed training scenario, the system uses preset cognitive tasks to train users and obtains evaluation results in real time. These results will be used for subsequent training adjustments and user progress evaluation to ensure that the training plan can continue to adapt to the user's ability level and progress speed.

[0045] A training task update module, used to generate new training tasks based on the executed training tasks, evaluation results and parameter acceptance indicators; The step of generating a new training task based on the executed training task, the evaluation result and the parameter acceptance index comprises: Determine the scene adjustment direction based on the physiological scores in the evaluation results; Generate two new sets of scenario parameters based on the scenario adjustment direction, the scenario parameters in the executed training task, and the scenario acceptance index; Determine the direction of task adjustment based on the task completion degree in the evaluation results; Selecting new cognitive tasks based on the task adjustment orientation and cognitive tasks in the training task performed; The new two sets of scene parameters and the new cognitive tasks are combined to generate new training tasks.

[0046] The step of determining the scene adjustment direction includes: When the physiological score is lower than the preset lower limit, the scene adjustment direction is determined to reduce the difficulty; when the physiological score is higher than the preset upper limit, the scene adjustment direction is determined to increase the difficulty; when the physiological score is between the preset lower limit and the upper limit, the scene adjustment direction is determined to maintain the difficulty; The step of generating two new sets of scene parameters based on the scene adjustment direction, the scene parameters in the executed training task and the scene acceptance index comprises: If the scene adjustment direction is to reduce the difficulty, the set of parameter values ​​of the two sets of scene parameters in the executed training task with the smaller sum is selected as the baseline parameter; the mitigation parameter is calculated, where the mitigation parameter is equal to the baseline parameter minus the scene acceptance index; the baseline parameter is used as the new first set of scene parameters, and the mitigation parameter is used as the new second set of scene parameters; If the scene adjustment direction is to increase the difficulty, then select the larger sum of the parameter values ​​of the two sets of scene parameters in the executed training task as the baseline parameter; calculate the enhanced parameter, where the enhanced parameter is equal to the baseline parameter plus the scene acceptance index; use the baseline parameter as the new first set of scene parameters, and the enhanced parameter as the new second set of scene parameters; If the scene adjustment direction is to maintain the difficulty, the two sets of scene parameters in the executed training task remain unchanged.

[0047] The step of determining the task adjustment direction includes: When the task completion rate is lower than the preset lower limit, the task adjustment direction is determined to reduce the difficulty; when the task completion rate is higher than the preset upper limit, the task adjustment direction is determined to increase the difficulty; when the task completion rate is between the preset lower limit and the upper limit, the task adjustment direction is determined to maintain the difficulty; The step of selecting a new cognitive task based on the task adjustment direction and the cognitive task in the executed training task comprises: If the task adjustment direction is to reduce the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level minus 1 is selected as a new cognitive task; if the current level is already 1, another cognitive task with a level of 1 is selected as a new cognitive task; If the task adjustment direction is to increase the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level plus 1 is selected as a new cognitive task. If the current level is already 5, another cognitive task with a level of 5 is selected as a new cognitive task; If the task adjustment direction is to maintain the difficulty, the task level of the cognitive task in the executed training task is recorded as the current level, and other cognitive tasks with the current level are selected as new cognitive tasks.

[0048] In this embodiment, during the scene adjustment process, the scene adjustment direction is first determined according to the physiological score in the evaluation result, wherein the scene adjustment direction is determined according to the physiological score, and the preset lower limit can be 0.6 and the upper limit can be 0.8; then two new sets of scene parameters are generated based on this direction. This adjustment method uses the user's scene acceptance index to accurately control the magnitude of the difficulty change. For example, when the difficulty needs to be increased, the scene acceptance index is directly added to the baseline parameter to form a new reinforcement parameter. This ensures that the increase in difficulty is based on the user's personal adaptability, rather than a fixed increment. Similarly, when reducing the difficulty, the parameters are also adjusted according to the scene acceptance index, making the reduction in difficulty more accurate and personalized.

[0049] The task adjustment process mainly focuses on the task completion and the preset upper and lower limits in the evaluation results, where the lower limit of the task completion can be 60% and the upper limit can be 80%; based on this, it is determined whether the difficulty level of the cognitive task needs to be changed. Different cognitive tasks will be selected within the same difficulty level, or the task level will be adjusted up or down as needed. This method can not only adjust the difficulty, but also keep the freshness and diversity of training through task changes. By combining the user's physiological response, task performance and scene acceptance indicators, each user can be provided with the training content that best suits their current ability level, which can improve the effectiveness of training; by using the scene acceptance indicator to adjust the scene parameters, it is ensured that the magnitude of the scene change will neither exceed the user's adaptation threshold nor fall below the effective stimulation level. This precise adjustment method allows the change in training difficulty to provide sufficient cognitive load without causing excessive psychological pressure, thereby creating a suitable training environment.

[0050] The training planning module is used to formulate training plans, determine the execution time and frequency of training tasks, and control the training execution module and the training task update module according to the training plan.

[0051] In this embodiment, the training plan is usually formulated by professionals after understanding the specific situation of the user. A typical training plan usually includes core elements such as training frequency, single training duration, and training schedule. The training frequency clearly stipulates the number of training sessions per week, the single training duration stipulates the duration of each training session, and the training schedule lists in detail the allocation of training days and rest days. The formulated training plan is stored in the system database in the form of a structured schedule. The training planning module coordinates and controls the operation of the training execution module and the training task update module according to this schedule.

[0052] In the several embodiments provided by the present invention, it should be understood that the disclosed systems, devices and methods can be implemented in other ways. For example, the device embodiments described above are only schematic, for example, the division of the units is only one, and there may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0053] The above description is only a specific implementation mode of the present invention, but the protection scope of the present invention is not limited thereto. Any technician familiar with the technical field can easily think of changes or substitutions within the technical scope disclosed by the present invention, which should be covered by the protection scope of the present invention.

[0054] Finally: The above description is only a preferred embodiment of the present invention and is not intended to limit the present invention. Any modifications, equivalent substitutions, improvements, etc. made within the spirit and principles of the present invention should be included in the protection scope of the present invention.

Claims

1. A virtual rich reality environment training system based on benign stress, characterized in that: include: A database module, used to store cognitive tasks and virtual scenes under different scene parameters; The acceptance test module is used to test the user's preset cognitive tasks in a preset test virtual scene and obtain the evaluation results, and generate the user's scene acceptance index according to the evaluation results; An initial training task generation module, used to generate a training task according to the user's scenario acceptance index, wherein the training task includes two sets of scenario parameters and a cognitive task; A training execution module, used to execute training tasks; The executing the training task includes: constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task, and using cognitive tasks to train the user in the training scene and obtain evaluation results; A training task update module, used to generate new training tasks based on the executed training tasks, evaluation results and parameter acceptance indicators; The training planning module is used to formulate training plans, determine the execution time and frequency of training tasks, and control the training execution module and the training task update module according to the training plan.

2. A virtual rich reality environment training system based on benign stress according to claim 1, characterized in that: The cognitive task includes task content and task level, and the task level includes five levels from 1 to 5; the scene parameters include personnel density, obstacle density, environmental noise and brightness; wherein the parameter value of each scene parameter is expressed as a value between 0 and 100 after standardized processing; the evaluation result includes task completion and physiological score.

3. A virtual rich reality environment training system based on benign stress according to claim 2, characterized in that: The physiological score is obtained by collecting the user's physiological indicators, including heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation; The calculation formula of the physiological score is as follows: ， In the formula, represents the physiological score, , , and They represent heart rate variability, galvanic skin response, respiratory rate, and blood oxygen saturation, respectively; , , and Respectively represent the preset baseline values ​​of heart rate variability, galvanic skin response, respiratory rate and blood oxygen saturation; , , and Respectively represent the preset maximum change values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation. , , and They represent the weight values ​​of heart rate variability, skin galvanic response, respiratory rate and blood oxygen saturation respectively.

4. A virtual rich reality environment training system based on benign stress according to claim 3, characterized in that: The preset test virtual scenes include personnel test scenes, obstacle test scenes, noise test scenes, brightness test scenes and standard test scenes; wherein, in the personnel test scene, the value of the personnel density parameter is , the values ​​of the other three parameters are ; In the obstacle test scenario, the value of the obstacle density parameter is , the values ​​of the other three parameters are ; In the noise test scenario, the value of the environmental noise parameter is , the values ​​of the other three parameters are ; In the brightness test scene, the value of the brightness parameter is , the values ​​of the other three parameters are ; Standard test scenario, the values ​​of the four parameters are ;in, , ; The preset cognitive task is any cognitive task with a task level of 1; The evaluation results under five test scenarios were obtained, and the test scores were obtained by multiplying the task completion degree by the physiological score, which were recorded as personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; According to the test scores, the personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance are calculated respectively. The calculation formula is as follows: ， In the formula, , , and They represent personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance respectively. , , , and They represent the personnel test score, obstacle test score, noise test score, brightness test score and standard test score respectively; The scene acceptance index is obtained by combining personnel acceptance, obstacle acceptance, noise acceptance and brightness acceptance.

5. The virtual rich reality environment training system based on benign stress according to claim 2, characterized in that: Generating a training task according to the user's scenario acceptance index includes: Acquire initial scene parameters, wherein the values ​​of each parameter in the initial scene parameters are preset values; Use the value of each parameter in the initial scene parameter plus the corresponding value in the scene acceptance index to obtain the new scene parameter recorded as the target parameter; Obtain any cognitive task with a task level of 1 as the target task; The initial scene parameters, target parameters and target tasks are combined to obtain the training task.

6. A virtual rich reality environment training system based on benign stress according to claim 5, characterized in that: The step of constructing a virtual scene to obtain a training scene according to two sets of scene parameters in the training task includes: Compare the parameter values ​​of the two groups of scene parameters in the training task, and use the scene parameter with the smaller sum of the parameter values ​​as the starting scene parameter, and the other group as the ending scene parameter; Determine the total length of virtual space , and divide it into intervals of equal length; Calculate the difference between the starting scene parameters and the ending scene parameters to obtain the scene parameter difference vector ; Use the formula Calculate the parameter increment vector for each interval ; For each interval, the scene parameter vector is calculated using the following formula: ， In the formula, Indicates The scene parameter vector of intervals, , A vector representing the values ​​of the starting scene parameters; According to the scene parameter vector of each interval Generate corresponding scene parameters and retrieve corresponding virtual scene elements from the database module; The virtual scene elements of each interval are continuously arranged along a predefined path to construct a continuously changing virtual space as a training scene.

7. A virtual rich reality environment training system based on benign stress according to claim 6, characterized in that: The step of generating a new training task based on the executed training task, the evaluation result and the parameter acceptance index comprises: Determine the scene adjustment direction based on the physiological scores in the evaluation results; Generate two new sets of scenario parameters based on the scenario adjustment direction, the scenario parameters in the executed training task, and the scenario acceptance index; Determine the direction of task adjustment based on the task completion degree in the evaluation results; Selecting new cognitive tasks based on the task adjustment orientation and cognitive tasks in the training task performed; The new two sets of scene parameters and the new cognitive tasks are combined to generate new training tasks.

8. The virtual rich reality environment training system based on benign stress according to claim 7, characterized in that: The step of determining the scene adjustment direction includes: When the physiological score is lower than the preset lower limit, the scene adjustment direction is determined to reduce the difficulty; when the physiological score is higher than the preset upper limit, the scene adjustment direction is determined to increase the difficulty; when the physiological score is between the preset lower limit and the upper limit, the scene adjustment direction is determined to maintain the difficulty; The step of generating two new sets of scene parameters based on the scene adjustment direction, the scene parameters in the executed training task and the scene acceptance index comprises: If the scene adjustment direction is to reduce the difficulty, the set of parameter values ​​of the two sets of scene parameters in the executed training task with the smaller sum is selected as the baseline parameter; the mitigation parameter is calculated, where the mitigation parameter is equal to the baseline parameter minus the scene acceptance index; the baseline parameter is used as the new first set of scene parameters, and the mitigation parameter is used as the new second set of scene parameters; If the scene adjustment direction is to increase the difficulty, then select the larger sum of the parameter values ​​of the two sets of scene parameters in the executed training task as the baseline parameter; calculate the enhanced parameter, where the enhanced parameter is equal to the baseline parameter plus the scene acceptance index; use the baseline parameter as the new first set of scene parameters, and the enhanced parameter as the new second set of scene parameters; If the scene adjustment direction is to maintain the difficulty, the two sets of scene parameters in the executed training task remain unchanged.

9. The virtual rich reality environment training system based on benign stress according to claim 7, characterized in that: The step of determining the task adjustment direction includes: When the task completion rate is lower than the preset lower limit, the task adjustment direction is determined to reduce the difficulty; when the task completion rate is higher than the preset upper limit, the task adjustment direction is determined to increase the difficulty; when the task completion rate is between the preset lower limit and the upper limit, the task adjustment direction is determined to maintain the difficulty; The step of selecting a new cognitive task based on the task adjustment direction and the cognitive task in the executed training task comprises: If the task adjustment direction is to reduce the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level minus 1 is selected as a new cognitive task; if the current level is already 1, another cognitive task with a level of 1 is selected as a new cognitive task; If the task adjustment direction is to increase the difficulty, the task level of the cognitive task in the training task to be executed is recorded as the current level; a cognitive task with a level equal to the current level plus 1 is selected as a new cognitive task. If the current level is already 5, another cognitive task with a level of 5 is selected as a new cognitive task; If the task adjustment direction is to maintain the difficulty, the task level of the cognitive task in the executed training task is recorded as the current level, and other cognitive tasks with the current level are selected as new cognitive tasks.

Images