Virtual reality processing method and system in emergency training simulator

Abstract

The invention provides a virtual reality processing method and system in an emergency training simulator. The method comprises the following steps: constructing a highly-simulated virtual first-aid scene, obtaining immersive first-aid training experience of seamless interaction between a user and a virtual environment, and generating interaction feedback data; according to the interaction feedback data, carrying out dynamic adjustment processing on a development track of the first-aid event, and generating a personalized first-aid scene branch; on the basis of the personalized first-aid scene branch, personalized guidance information is generated in real time, and a personalized guidance and psychological support scheme is generated; and designing vivid resource limiting conditions, carefully configuring virtual props and environment settings according to the personalized guidance and psychological support scheme, simulating first-aid resource constraints in the real world, and generating an actual combat ability strengthening training environment under team cooperation. According to the technical scheme provided by the invention, the reality, individuation, immediate feedback and actual drill effects of first-aid training are greatly improved.

Description

Technical Field

[0001] The embodiments of the present application relate to the field of virtual reality technology, and in particular to a virtual reality processing method and system in a first aid training simulator. Background Art

[0002] In the field of first aid training, building highly simulated virtual first aid scenarios is crucial to improving training effectiveness. With the rapid development of medical technology and information technology, modern first aid training not only requires trainees to master theoretical knowledge, but also emphasizes practical operation skills and the ability to deal with emergencies. Therefore, a technical solution is needed that can accurately capture the user's multi-dimensional actions in the physical space and map these actions to the virtual character in real time. In addition, the system should also have the ability to dynamically adjust the response behavior of objects in the virtual environment to provide a seamless and interactive immersive training experience. This highly simulated environment helps trainees better understand the first aid process and enhance their confidence and ability to deal with emergencies in the real world.

[0003] At present, common first aid training methods mainly include traditional classroom lectures, simulator training, and video-based learning platforms. Among them, simulator training has introduced a certain degree of virtual reality (VR) elements, trying to improve the actual operation ability of trainees by simulating real first aid scenarios. However, these existing solutions usually adopt preset scenarios and fixed development trajectories, and lack the ability to dynamically adjust according to user performance. At the same time, although some advanced simulators can capture some of the user's movements, they often cannot achieve multi-dimensional motion acquisition and real-time feedback, resulting in a user experience that is not realistic enough and difficult to truly reflect the complex and changing first aid scenes.

[0004] Although the existing first aid training programs have met the basic educational needs to a certain extent, there are still several significant defects: most simulator training adopts a unified scenario setting and development path, fails to fully consider individual differences, and cannot provide personalized training content for trainees of different levels and backgrounds; in the existing programs, the interaction between the virtual environment and the user is relatively limited, and the response behavior of objects is often preset and cannot be adjusted synchronously according to the user's real-time operation, which reduces the realism and immersion of the training; traditional training methods pay less attention to the psychological state of trainees, such as mood swings and stress management, which may seriously affect the effectiveness of decision-making and operations in actual first aid. Therefore, the existing programs fail to fully cover all the key elements of first aid training, limiting the overall effect of training. Summary of the invention

[0005] The embodiments of the present application provide a virtual reality processing method and system in a first aid training simulator, so as to solve the problem of limited interaction between the virtual environment and the user in the prior art.

[0006] In a first aspect, an embodiment of the present application provides a virtual reality processing method in a first aid training simulator, comprising:

[0007] Build a highly simulated virtual first aid scene, collect the multi-dimensional actions of users in the physical space and map these actions to virtual characters, synchronously adjust the response behaviors of objects in the virtual environment, obtain an immersive first aid training experience in which users interact seamlessly with the virtual environment, and generate interactive feedback data;

[0008] According to the interactive feedback data, the development trajectory of the emergency event is dynamically adjusted, and the difficulty level of the emergency event is evaluated by using an adaptive event evolution algorithm combined with scenario complexity analysis technology to generate personalized emergency scenario branches;

[0009] Based on the personalized first aid scenario branch, personalized guidance information is generated and processed in real time, the Bayesian network algorithm is introduced to predict and identify the problems that the user may encounter, and the user's emotional fluctuations are analyzed through emotional state monitoring technology to generate personalized guidance and psychological support plans;

[0010] Design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under teamwork.

[0011] Optionally, the development trajectory of the emergency event is dynamically adjusted according to the interactive feedback data, an adaptive event evolution algorithm is used, and a scenario complexity analysis technology is combined to evaluate the difficulty level of the emergency event, and a personalized emergency scenario branch is generated, including:

[0012] The interactive feedback data is used to analyze and process the user's behavior pattern and decision path in the virtual first aid scenario to obtain the user's behavior feature set; based on the behavior feature set, an adaptive event evolution algorithm is used to dynamically adjust the development trajectory of the first aid event to generate an initial event evolution plan; according to the initial event evolution plan, combined with the scenario complexity analysis technology, a difficulty assessment is performed on each possible first aid event branch to obtain a difficulty score for each branch; based on the difficulty score, each potential development path of the first aid event is screened and optimized to generate a personalized first aid scenario branch.

[0013] Optionally, the interactive feedback data is used to analyze and process the user's behavior pattern and decision path in the virtual first aid scenario to obtain the user's behavior feature set, including:

[0014] Using the interactive feedback data, fine-grained analysis is performed on the user's action sequence and decision-making choices in the virtual first aid scenario to obtain the user's behavioral event record;

[0015] Based on the user's behavioral event records, a behavioral pattern recognition algorithm is used to summarize the user's action patterns and decision-making habits to generate a preliminary behavioral pattern model;

[0016] Based on the preliminary behavior pattern model, combined with the user's historical training data, deep learning optimization processing is performed to obtain an optimized behavior pattern model;

[0017] Based on the optimized behavior pattern model, the user's behavior characteristics are quantified, representative behavior characteristic parameters are extracted, and the user's behavior characteristic set is generated.

[0018] Optionally, the initial event evolution scheme is combined with scenario complexity analysis technology to perform difficulty assessment processing on each possible emergency event branch to obtain a difficulty score for each branch, including:

[0019] According to the initial event evolution plan, scenario construction processing is performed on each possible emergency event branch to obtain a scenario model of each branch;

[0020] Utilizing the scenario models of each branch and combining scenario complexity analysis techniques, the variables and factors in each scenario are quantified to obtain a scenario complexity index;

[0021] Based on the scenario complexity index, a difficulty assessment algorithm is used to comprehensively evaluate the challenge of each emergency event branch and generate a preliminary difficulty score;

[0022] According to the preliminary difficulty score, the user's historical performance data is introduced for calibration processing, and the score is adjusted to reflect the user's actual coping ability to obtain the difficulty score of each branch.

[0023] Optionally, based on the personalized first aid scenario branch, personalized guidance information is generated and processed in real time, a Bayesian network algorithm is introduced to predict and identify the problems that the user may encounter, and the user's emotional fluctuations are analyzed through emotional state monitoring technology to generate personalized guidance and psychological support plans, including:

[0024] Based on the personalized first aid scenario branch, key nodes and potential problem points in first aid training are identified and processed to obtain a set of key nodes and problem points;

[0025] By using the key nodes and problem point set, a Bayesian network algorithm is introduced to predict the problem points that users may encounter in different scenarios and generate a predicted problem point list;

[0026] Based on the predicted problem point list and in combination with the user's historical performance data, the user's ability to cope with the problem is evaluated to obtain a user ability evaluation result;

[0027] Based on the user ability assessment result, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report;

[0028] The emotional fluctuation analysis report is used to customize the personalized guidance information, formulate corresponding psychological support strategies, and generate personalized guidance and psychological support plans.

[0029] Optionally, based on the user capability assessment result, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report, including:

[0030] Using the user's expected performance model, combined with the real-time collected user physiological signals and behavior data, and through the emotional state monitoring technology, the user's emotional state is dynamically captured and processed to generate original emotional state data;

[0031] According to the original emotional state data, an emotion recognition algorithm is used to classify and quantify the user's emotional fluctuations to obtain an emotional fluctuation index;

[0032] Based on the emotion fluctuation index, a comparative analysis is performed with a standard emotion pattern library to determine the type and intensity of the user's emotion fluctuation and generate an emotion fluctuation feature description;

[0033] By using the emotion fluctuation feature description and combining it with the user's historical emotion records, the causes and influencing factors of the current emotion fluctuation are deeply analyzed and processed to obtain an emotion fluctuation analysis report.

[0034] Optionally, the design of realistic resource constraints, according to the personalized guidance and psychological support program, carefully configures virtual props and environment settings, simulates emergency resource constraints in the real world, and generates a combat capability enhancement training environment under teamwork, including:

[0035] According to the personalized guidance and psychological support program, resource constraint conditions that need to be simulated in first aid training are defined and processed to obtain a resource constraint condition list;

[0036] Based on the resource restriction list, combined with the equipment availability and environmental factors in the actual emergency scene, the virtual props and environment settings are designed and processed to generate a realistic virtual resource configuration model;

[0037] Using the realistic virtual resource configuration model, simulating the first aid resource constraints in the real world through simulation technology, adjusting the number, position and state of props in the virtual environment, and the physical characteristics of the environment, to obtain a simulated resource-constrained environment;

[0038] Based on the simulated resource-constrained environment, a team collaboration mechanism is introduced to optimize the interaction mode and task allocation strategy between users and generate team collaboration rules;

[0039] According to the team collaboration rules and combined with the performance data of users under resource-constrained conditions, the actual combat capability enhancement training environment is finally configured to generate the actual combat capability enhancement training environment under team collaboration.

[0040] In a second aspect, an embodiment of the present application provides a virtual reality processing system in a first aid training simulator, comprising:

[0041] The construction module is used to build a highly simulated virtual first aid scene, collect the multi-dimensional actions of the user in the physical space and map these actions to the virtual character, synchronously adjust the response behavior of the objects in the virtual environment, obtain an immersive first aid training experience in which the user interacts seamlessly with the virtual environment, and generate interactive feedback data;

[0042] An adjustment module is used to dynamically adjust the development trajectory of the emergency event according to the interactive feedback data, adopt an adaptive event evolution algorithm, combine the scenario complexity analysis technology to evaluate the difficulty level of the emergency event, and generate personalized emergency scenario branches;

[0043] An analysis module is used to instantly generate and process personalized guidance information based on the personalized first aid scenario branch, introduce a Bayesian network algorithm to predict and identify possible problems that users may encounter, and analyze the user's emotional fluctuations through emotional state monitoring technology to generate personalized guidance and psychological support plans;

[0044] The configuration module is used to design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

[0045] In a third aspect, an embodiment of the present application provides a computing device, comprising a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a virtual reality processing method in a first aid training simulator as described in the first aspect.

[0046] In a fourth aspect, an embodiment of the present application provides a computer storage medium storing a computer program, and when the computer program is executed by a computer, it implements a virtual reality processing method in a first aid training simulator as described in the first aspect.

[0047] In an embodiment of the present application, a highly simulated virtual first aid scenario is constructed, the multi-dimensional actions of the user in the physical space are collected and mapped to the virtual character, and the response behavior of the objects in the virtual environment is synchronously adjusted to obtain an immersive first aid training experience in which the user interacts seamlessly with the virtual environment, and interactive feedback data is generated; according to the interactive feedback data, the development trajectory of the first aid event is dynamically adjusted, and an adaptive event evolution algorithm is used, combined with the scenario complexity analysis technology to evaluate the difficulty level of the first aid event, and a personalized first aid scenario branch is generated; based on the personalized first aid scenario branch, personalized guidance information is instantly generated and processed, a Bayesian network algorithm is introduced to predict and identify the problem points that the user may encounter, and the user's emotional fluctuations are analyzed through the emotional state monitoring technology to generate personalized guidance and psychological support plans; realistic resource constraints are designed, and according to the personalized guidance and psychological support plans, the virtual props and environment settings are carefully configured to simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

[0048] The technical solution of this application has the following beneficial effects:

[0049] A highly simulated virtual first aid scenario is constructed, and through multi-dimensional motion acquisition and mapping technology, users can interact seamlessly with virtual characters. This immersive first aid training experience not only enhances the user's sense of participation, but also improves their cognition and adaptability to the actual first aid environment, making the training closer to the real situation; using interactive feedback data, combined with adaptive event evolution algorithm and scenario complexity analysis technology, the system can evaluate and adjust the development trajectory of first aid events in real time. This not only ensures the uniqueness and challenge of each training, but also generates personalized first aid scenario branches based on the user's performance, thereby providing tailored training content for users of different levels, significantly improving the effectiveness and pertinence of the training; based on personalized first aid scenario branches, the system can instantly generate personalized guidance information and use Bayesian network algorithms to predict the problems that users may encounter. At the same time, by analyzing the user's emotional fluctuations through emotional state monitoring technology, the system can provide timely psychological support solutions. This instant and personalized feedback mechanism helps users quickly improve their skills, enhance their confidence in dealing with emergencies, and reduce operational errors caused by tension or anxiety; design realistic resource constraints, carefully configure virtual props and environmental settings according to personalized guidance and psychological support solutions, and simulate first aid resource constraints in the real world. This process not only tests the user's decision-making and resource management capabilities under limited resources, but also emphasizes the importance of teamwork, encouraging users to cooperate with each other to jointly solve complex emergency tasks. In this way, users can practice under constraints close to reality, effectively improving their actual combat capabilities and teamwork levels; the entire system integrates multi-dimensional motion capture, dynamic event adjustment, personalized guidance, psychological support, and resource limitation simulation functions to form a complete set of emergency training solutions. Compared with traditional static or semi-simulation training methods, this system can more comprehensively cover the needs of emergency training, significantly improve the overall efficiency and quality of training, help users master emergency skills faster and better, and be fully prepared to deal with real-world emergencies.

[0050] Furthermore, the adaptive event evolution algorithm based on the user behavior feature set enables the development trajectory of emergency events to be dynamically adjusted according to the user's real-time performance, ensuring the uniqueness and challenge of each training. At the same time, it combines the scenario complexity analysis technology to evaluate the difficulty level of emergency events and generate personalized emergency scenario branches, thereby providing tailored training content for users of different levels, significantly improving the effectiveness and pertinence of the training.

[0051] Furthermore, through in-depth analysis of key nodes and problem points, and the introduction of Bayesian network algorithms to predict the problem points that users may encounter, the system can instantly generate personalized guidance information and provide accurate response strategies. In addition, by analyzing the user's emotional fluctuations through emotional state monitoring technology, the system not only provides psychological support solutions, but also enhances the user's psychological resilience and decision-making ability when facing emergencies. This instant and personalized feedback mechanism helps users quickly improve their skills, enhance their confidence in dealing with emergencies, and reduce operational errors caused by tension or anxiety.

[0052] These and other aspects of the present application will become more clearly understood in the description of the following embodiments. BRIEF DESCRIPTION OF THE DRAWINGS

[0053] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, a brief introduction will be given below to the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0054] Figure 1 A flowchart of a virtual reality processing method in a first aid training simulator provided in an embodiment of the present application;

[0055] Figure 2 A schematic diagram of the structure of a virtual reality processing system in a first aid training simulator provided in an embodiment of the present application;

[0056] Figure 3 A schematic diagram of the structure of a computing device provided in an embodiment of the present application. DETAILED DESCRIPTION

[0057] In order to enable those skilled in the art to better understand the solution of the present application, the technical solution in the embodiments of the present application will be clearly and completely described below in conjunction with the drawings in the embodiments of the present application.

[0058] In some of the processes described in the specification and claims of this application and the above-mentioned figures, multiple operations that appear in a specific order are included, but it should be clearly understood that these operations may not be executed in the order in which they appear in this article or executed in parallel. The serial numbers of the operations, such as 101, 102, etc., are only used to distinguish between different operations, and the serial numbers themselves do not represent any execution order. In addition, these processes may include more or fewer operations, and these operations may be executed in sequence or in parallel. It should be noted that the descriptions of "first", "second", etc. in this article are used to distinguish different messages, devices, modules, etc., do not represent the order of precedence, and do not limit the "first" and "second" to be different types.

[0059] The following will be combined with the drawings in the embodiments of the present application to clearly and completely describe the technical solutions in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all of the embodiments. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative work are within the scope of protection of this application.

[0060] Figure 1 A flowchart of a virtual reality processing method in a first aid training simulator is provided for an embodiment of the present application. Figure 1 As shown, the method includes:

[0061] 101. Build a highly simulated virtual first aid scene, collect the multi-dimensional actions of users in the physical space and map these actions to virtual characters, synchronously adjust the response behaviors of objects in the virtual environment, obtain an immersive first aid training experience in which users interact seamlessly with the virtual environment, and generate interactive feedback data;

[0062] In this step, building a highly simulated virtual first aid scenario includes using multi-dimensional motion capture equipment to collect the user's motion data in the physical space, such as position, speed, posture, etc., and mapping this data to the virtual character in real time. The system should also have the ability to synchronously adjust the response behavior of objects in the virtual environment to ensure that the interaction of virtual objects is consistent with user operations. Interaction feedback data refers to all information recorded by sensors and algorithms about the user's interaction with the virtual environment, which is used to evaluate the user's performance and optimize the training content.

[0063] In the embodiment of the present application, first, the motion capture device installed on the user collects the user's multi-dimensional movements in the physical space, and then the software is used to accurately map these movements to the virtual character. At the same time, the system adjusts the behavior of objects in the virtual environment in real time according to the user's operation, such as moving a stretcher or opening a first aid kit, thereby providing a seamless and interactive immersive first aid training experience. The interactive feedback data finally generated provides the basis for subsequent analysis and personalized adjustments.

[0064] For example, in a first aid training at a simulated car accident scene, the motion capture suit worn by the trainee can accurately record every action, from approaching the injured to performing cardiopulmonary resuscitation (CPR). The car wreckage and first aid equipment in the virtual environment will respond to the trainee's actions, such as the stretcher moving with the trainee's movements and the first aid kit showing the contents when it is opened. This realistic interactive experience makes the trainee feel as if they are at a real first aid scene, enhancing the training effect.

[0065] 102. According to the interactive feedback data, dynamically adjust the development trajectory of the emergency event, use an adaptive event evolution algorithm, combine the scenario complexity analysis technology to evaluate the difficulty level of the emergency event, and generate personalized emergency scenario branches;

[0066] In this step, dynamically adjusting the development trajectory of emergency events includes using an adaptive event evolution algorithm to adjust the order and difficulty of events based on the user's interactive feedback data in the virtual environment. Scenario complexity analysis technology is used to evaluate the difficulty level of each emergency event branch, and combined with the user's historical performance and current operations, generate personalized emergency scenario branches to ensure that the training is both challenging and suitable for the user's skill level.

[0067] In the embodiment of the present application, the system uses an adaptive event evolution algorithm to adjust the development of emergency events in real time based on the interactive feedback data of users in virtual emergency scenarios. At the same time, the difficulty of each event branch is evaluated through scenario complexity analysis technology, and personalized emergency scenario branches are generated accordingly. This process ensures the uniqueness and challenge of each training, while also taking into account the individual differences and progress of users.

[0068] For example, in a simulated heart attack training, if the trainee quickly and correctly makes the initial diagnosis and initiates the emergency procedure, the system will automatically increase the complexity of subsequent tasks, such as introducing more patients or more complex changes in their condition. On the contrary, if the trainee encounters difficulties, the system will simplify some steps or provide more prompts to ensure that the training can both test the trainee and gradually improve their skills.

[0069] Optionally, in step 102, dynamically adjusting the development trajectory of the emergency event according to the interactive feedback data, using an adaptive event evolution algorithm, combined with scenario complexity analysis technology to evaluate the difficulty level of the emergency event, and generating personalized emergency scenario branches, including:

[0070] Utilizing the interactive feedback data, analyzing and processing the user's behavior pattern and decision path in the virtual first aid scenario to obtain the user's behavior feature set;

[0071] Based on the behavioral feature set, an adaptive event evolution algorithm is used to dynamically adjust the development trajectory of the emergency event to generate an initial event evolution plan;

[0072] According to the initial event evolution plan, combined with scenario complexity analysis technology, difficulty assessment is performed on each possible emergency event branch to obtain a difficulty score for each branch;

[0073] Based on the difficulty score, various potential development paths of the emergency incident are screened and optimized to generate personalized emergency scenario branches.

[0074] In this step, dynamically adjusting the development trajectory of the emergency event includes using interactive feedback data to analyze and process the user's behavior pattern and decision path in the virtual emergency scenario, thereby obtaining the user's behavior feature set. These data are used to evaluate the user's operating habits, reaction speed, and decision-making quality. Based on this behavioral feature set, the system uses an adaptive event evolution algorithm to adjust the development of events, and combines scenario complexity analysis technology to evaluate the difficulty of each branch, and finally generates personalized emergency scenario branches.

[0075] In the embodiment of the present application, first, the system uses interactive feedback data to analyze in detail the user's behavior patterns and decision-making paths in the virtual first aid scenario, and extracts the user's behavior feature set; second, based on these feature sets, the system uses an adaptive event evolution algorithm to dynamically adjust the development trajectory of the first aid event, and generates an initial event evolution plan; third, based on the initial plan, the system combines scenario complexity analysis technology to evaluate the difficulty of each possible first aid event branch, and obtains a difficulty score for each branch; finally, the system screens and optimizes potential development paths based on the difficulty score, and generates personalized first aid scenario branches to ensure that the training is both challenging and suitable for the user's skill level.

[0076] In a first aid training simulated chemical leak accident, trainees need to quickly identify hazardous substances and take appropriate protective measures. First, the system uses motion capture devices and sensors to record a series of operations performed by trainees in the virtual environment, such as the speed of putting on protective clothing, choosing the correct gas mask, etc., and monitors their decision-making path, such as whether the isolation area is correctly selected. Second, the system analyzes the trainees' behavior patterns based on these interactive feedback data and generates a behavioral feature set including reaction time, operation accuracy and decision-making efficiency. Third, based on this feature set, the system uses an adaptive event evolution algorithm to adjust the development of events, such as introducing new sources of danger or adding the task of evacuating people, to generate an initial event evolution plan. Then, based on the initial plan, the system combines scenario complexity analysis technology to evaluate the difficulty of each possible branch and scores each branch, such as the difficulty score of high-risk chemical handling is 8, while the difficulty score of low-risk chemical handling is 5. Finally, based on these difficulty scores, the system screens and optimizes potential development paths and generates personalized first aid scenario branches to ensure that the challenges faced by trainees are neither too simple nor too complex, and gradually improve their ability to deal with complex situations.

[0077] Through the above steps, this embodiment not only provides a highly simulated training environment, but also dynamically adjusts the training content according to the actual performance of the trainees, ensuring the uniqueness and pertinence of each training, and significantly improving the trainees' practical ability and emergency handling skills.

[0078] Optionally, the interactive feedback data is used to analyze and process the user's behavior pattern and decision path in the virtual first aid scenario to obtain the user's behavior feature set, including:

[0079] The interactive feedback data is used to perform fine-grained analysis on the user's action sequence and decision-making choices in the virtual first aid scenario to obtain the user's behavior event record; based on the user's behavior event record, a behavior pattern recognition algorithm is used to summarize the user's action patterns and decision-making habits to generate a preliminary behavior pattern model; based on the preliminary behavior pattern model, combined with the user's historical training data, deep learning optimization processing is performed to obtain an optimized behavior pattern model; based on the optimized behavior pattern model, the user's behavior characteristics are quantified, representative behavior characteristic parameters are extracted, and the user's behavior feature set is generated.

[0080] Optionally, the initial event evolution scheme is combined with scenario complexity analysis technology to perform difficulty assessment processing on each possible emergency event branch to obtain a difficulty score for each branch, including:

[0081] According to the initial event evolution plan, scenario construction is performed on each possible emergency event branch to obtain a scenario model for each branch; using the scenario model for each branch, combined with scenario complexity analysis technology, the variables and factors in each scenario are quantified to obtain a scenario complexity index; based on the scenario complexity index, a difficulty assessment algorithm is used to comprehensively evaluate the challenge of each emergency event branch to generate a preliminary difficulty score; based on the preliminary difficulty score, the user's historical performance data is introduced for calibration, and the score is adjusted to reflect the user's actual coping ability to obtain a difficulty score for each branch.

[0082] In this step, the interactive feedback data is used to analyze and process the user's behavior pattern and decision path to generate a behavioral feature set. Specifically, the interactive feedback data includes the user's action sequence (such as operation speed and accuracy) and decision choices (such as choosing the correct first aid steps) in the virtual environment. These data are used to analyze each user's action and decision in a fine-grained manner to generate a behavioral event record. Based on this record, the system uses a behavioral pattern recognition algorithm to summarize the user's action rules and decision-making habits to form a preliminary behavioral pattern model. By combining the user's historical training data, deep learning optimization is performed to finally obtain the optimized behavioral pattern model, and representative behavioral feature parameters are quantitatively extracted to generate the user's behavioral feature set. For difficulty assessment, the system constructs a scenario model for each possible first aid event branch based on the initial event evolution plan. The scenario complexity analysis technology is used to quantify the variables and factors in each scenario and obtain the scenario complexity index. Then, the difficulty assessment algorithm is used to comprehensively evaluate the challenge of each first aid event branch to generate a preliminary difficulty score. Finally, the user's historical performance data is introduced for calibration, and the score is adjusted to reflect the user's actual coping ability, thereby obtaining the difficulty score of each branch.

[0083] In the embodiment of the present application, firstly, the system uses the interactive feedback data to perform fine-grained analysis on the user's action sequence and decision-making choices in the virtual emergency scene, and generates the user's behavior event record; secondly, based on these behavior event records, the system uses the behavior pattern recognition algorithm to summarize the user's action rules and decision-making habits, and generates a preliminary behavior pattern model; thirdly, the system combines the user's historical training data to perform deep learning optimization processing to obtain the optimized behavior pattern model; finally, the system quantifies the user's behavior characteristics, extracts representative behavior characteristic parameters, and generates the user's behavior characteristic set. For difficulty assessment, firstly, the system constructs a scenario for each possible emergency event branch according to the initial event evolution scheme, and obtains the scenario model of each branch; secondly, using the scenario model of each branch, combined with the scenario complexity analysis technology, quantifies the variables and factors in each scenario, and obtains the scenario complexity index; thirdly, based on the scenario complexity index, the difficulty assessment algorithm is used to comprehensively evaluate the challenge of each emergency event branch, and generates a preliminary difficulty score; finally, according to the preliminary difficulty score, the user's historical performance data is introduced for calibration processing, and the score is adjusted to reflect the user's actual coping ability, and the difficulty score of each branch is obtained.

[0084] In a simulated fire rescue first aid training, trainees need to quickly judge the fire and take appropriate fire-fighting measures. First, the system records a series of trainees' actions through sensors, such as quickly moving to a safe location and choosing a suitable fire extinguisher, while monitoring their decision-making paths, such as whether the escape route is correctly selected. Second, based on these interactive feedback data, the system performs fine-grained analysis of the trainees' action sequences and decision-making choices to generate detailed behavioral event records. Third, based on these behavioral event records, the system uses behavioral pattern recognition algorithms to summarize the trainees' action patterns and decision-making habits to generate a preliminary behavioral pattern model. Then, the system combines the trainees' historical training data with deep learning optimization processing to obtain an optimized behavioral pattern model. Next, the system quantifies the trainees' behavioral characteristics and extracts representative behavioral patterns. The system generates a set of behavioral characteristics for students based on characteristic parameters, such as reaction time, operation accuracy, and decision-making efficiency. For difficulty assessment, first, the system constructs scenarios for each possible emergency event branch according to the initial event evolution plan, such as different types of fires and different building layouts, to obtain scenario models for each branch. Secondly, these scenario models are combined with scenario complexity analysis technology to quantify the variables and factors in each scenario, such as flame spread speed, smoke concentration, etc., to obtain scenario complexity indicators. Thirdly, based on the scenario complexity indicators, the difficulty assessment algorithm is used to comprehensively evaluate the challenge of each emergency event branch to generate a preliminary difficulty score. Finally, based on the preliminary difficulty score, the student's historical performance data is introduced for calibration processing, and the score is adjusted to reflect the student's actual response ability to obtain the difficulty score of each branch.

[0085] Through the above steps, this embodiment not only records in detail every action and decision of the trainees in the virtual first aid scene, but also generates highly personalized first aid training content through in-depth analysis and optimization of behavior patterns. At the same time, the system ensures the uniqueness and challenge of each training through scenario complexity analysis and difficulty assessment, significantly improving the trainees' practical ability and emergency handling skills.

[0086] The present application takes into account that in the prior art, first aid training systems are deficient in terms of dynamically adjusting the development trajectory of events and personalized training content. Traditional simulator training usually uses preset scenarios and fixed development paths, and lacks the ability to dynamically adjust according to the user's real-time performance, resulting in an unrealistic user experience and difficulty in truly reflecting the complex and ever-changing first aid scenes. In addition, existing solutions give less consideration to factors such as user behavior patterns, historical performance, and teamwork, which affects the authenticity and pertinence of the training results. Therefore, the embodiment of the present invention proposes this optional solution to solve the above-mentioned problems. By introducing an adaptive event evolution algorithm and a behavioral feature set, it is possible to achieve intelligent adjustment of the development trajectory of first aid events and improve the realism and personalization of training.

[0087] Optionally, based on the behavior feature set, an adaptive event evolution algorithm is used to dynamically adjust the development trajectory of the emergency event to generate an initial event evolution plan, including:

[0088] Before calculating the event evolution intensity E(t), the user behavior pattern is analyzed to evaluate the behavior variability, historical performance influencing factors, scenario complexity indicators, and the social interaction score of team collaboration to provide a basis for the calculation of E(t);

[0089] E(t)=α·B(t)·(1+λ·V(t))+(1-α)·H(t)-β·C(t) 2 +ζ·S(t)·(1+μ·G(t))

[0090] Wherein, E(t) is the intensity of event evolution at time t; B(t) is the behavioral feature score at time t, which is extracted from the behavioral feature set; α is the weight coefficient of the behavioral feature score; λ is the variability coefficient, which is used to adjust the degree of change of user behavior in different scenarios; V(t) is the behavioral variability at time t, which reflects the diversity of user behavior patterns; H(t) is the user's historical performance influencing factor, which is calculated based on the user's past performance data; β is the influence coefficient of scenario complexity; C(t) is the scenario complexity index, which evaluates the difficulty of the emergency event branch at a specific time point t; ζ is the social interaction coefficient, which is used to measure the impact of teamwork on event evolution; S(t) is the social interaction score at time t, which indicates the degree of cooperation between the user and other participants; μ is the group dynamics coefficient, which is used to adjust the change of teamwork effect over time; G(t) is the group dynamics score at time t, which reflects the change of teamwork efficiency;

[0091] After calculating E(t), the exponential decay function is used to adjust the event probability distribution P(t+1) based on the complexity of the decision path, the external factor score, and the emergency score. At the same time, resource availability and user adaptability are considered to ensure that the model can reflect the uncertainty of the real world.

[0092] P(t+1)=P(t)·e -(γ·E(t)+δ·D(t)+θ·F(t)+φ·Q(t)) +∈·R(t)·(1+η·A(t)+κ·L(t))

[0093] Among them, P(t) is the event probability distribution at time t; γ is the influence coefficient of event evolution intensity; E(t) is the event evolution intensity at time t; δ is the influence coefficient of decision path complexity; D(t) is the decision path complexity, which reflects the difficulty of the user's decision path at a specific time point t; θ is the external factor influence coefficient; F(t) is the external factor score of the time poem, which takes into account the impact of external variables such as weather and location on emergency events; φ is the emergency coefficient, which is used to adjust the impact of emergencies on event probability; Q(t) is the emergency score of the time poem, reflecting The probability of an emergency; ∈ is a small positive number, ensuring that there is a certain probability of a new event even when resources are limited; R(t) is the resource availability index, which reflects the availability of resources in the virtual environment at time t; η is the adaptability coefficient, which is used to adjust the user's adaptability to environmental changes; A(t) is the adaptability score at time t, which reflects the user's ability to cope with changes; κ is the learning curve coefficient, which is used to measure the user's learning speed and skill improvement; L(t) is the learning progress score at time t, which reflects the user's learning progress and skill growth;

[0094] After obtaining P(t+1), a detailed action guide is formulated by prioritizing and optimizing possible event paths in combination with the user's learning progress. Finally, the information is integrated to generate an initial event evolution plan, thereby improving the user's practical ability and confidence in dealing with emergencies.

[0095] This formula aims to overcome the limitations of existing technologies. First, it analyzes user behavior patterns to evaluate behavior variability, historical performance influencing factors, and scenario complexity indicators, and combines the social interaction score of team collaboration to provide a basis for calculating the event evolution intensity E(t); second, it uses an exponential decay function to adjust the event probability distribution P(t+1), combined with the complexity of the decision path, external factor scores, and emergency scores to ensure that the model can reflect the uncertainty of the real world. Finally, the information is integrated to generate an initial event evolution plan to improve users' practical capabilities and confidence in dealing with emergencies.

[0096] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0097] E(t)=α·B(t)·(1+λ·V(t))+(1-α)·H(t)-β·C(t) 2 +ζ·S(t)·(1+μ·G(t))

[0098] Behavioral feature score and its variability: α·B(t)·(1+λ·V(t)): measures the quality of the user's current operation and takes into account the diversity of their behavior; historical performance impact: (1-α)·H(t): adjusts the weight based on the user's past performance data; scenario complexity impact: -β·C(t)2 : Evaluate the difficulty of emergency event branches; Teamwork impact: (·S(t)·(1+μ·G(t)): Measures the impact of teamwork on event evolution;

[0099] The following is a brief introduction to how to obtain the parameters of the formula:

[0100] B(t) is extracted from the behavioral feature set; λ is set through experiments or expert evaluation; V(t) is obtained through sensor and data analysis; H(t) is calculated based on the user's historical performance data; β is set through experiments or expert evaluation; C(t) is obtained through situational evaluation tools; ζ is set through experiments or expert evaluation; S(t) is obtained through social interaction analysis tools; μ is set through experiments or expert evaluation; G(t) is obtained through team collaboration evaluation tools;

[0101] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0102] P(t+1)=P(t)·e -(γ·E(t)+δ·D(t)+θ·F(t)+φ·Q(t)) +∈·R(t)·(1+η·A(t)+κ·L(t))

[0103] The impact of event evolution intensity: γ·E(t): the key factor affecting the development of events; the impact of decision path complexity: δ·D(t): evaluating the difficulty of the user's decision path; the impact of external factors: θ·F(t): considering the impact of external variables such as weather and location on emergency events; the impact of emergencies: φ·Q(t): adjusting the impact of emergencies on the possibility of events; the impact of resource availability: ∈·R(t): reflecting the availability of resources in the virtual environment; the impact of user adaptability: η·A(t): adjusting the user's ability to adapt to environmental changes; the impact of learning progress: κ·L(t): measuring the user's learning speed and skill improvement;

[0104] The following is a brief introduction to how to obtain the parameters of the formula:

[0105] E(t) is calculated by the above formula; γ is set by experiment or expert evaluation; δ is set by experiment or expert evaluation; D(t) is obtained by decision path evaluation tool; θ is set by experiment or expert evaluation; F(t) is obtained by external factor evaluation tool; φ is set by experiment or expert evaluation; Q(t) is obtained by emergency event evaluation tool; R(t) is obtained by resource management tool; ∈ is set by experiment or expert evaluation; η is set by experiment or expert evaluation; A(t) is obtained by user feedback and evaluation tool; κ is set by experiment or expert evaluation; L(t) is obtained by learning progress evaluation tool;

[0106] In a simulated earthquake rescue first aid training, trainees need to quickly assess injuries and allocate limited medical resources. First, the system uses motion capture devices and sensors to record a series of trainees' operations, such as the speed of putting on protective clothing and choosing the right gas mask, while monitoring their decision-making paths, such as whether the isolation area is correctly selected. Then, the system uses these interactive feedback data to perform fine-grained analysis of the trainees' behavior patterns and generate detailed behavioral event records. Next, based on these behavioral event records, the system uses behavioral pattern recognition algorithms to summarize the trainees' action patterns and decision-making habits to form a preliminary behavioral pattern model. Subsequently, the system combines the trainees' historical training data and performs deep learning optimization processing to obtain an optimized behavioral pattern model. After that, the system quantifies the trainees' behavioral characteristics, extracts representative behavioral characteristic parameters, such as reaction time, operation accuracy, and decision-making efficiency, and generates a behavioral feature set for the trainees.

[0107] Next, the system defines the resource constraints that need to be simulated in first aid training, such as the limited number of stretchers and drug supply, based on the personalized guidance and psychological support plan, and forms a list of resource constraints; then, based on this list, combined with the equipment availability and environmental factors in the actual first aid scenario, such as terrain obstacles and weather conditions, the system designs and processes virtual props and environmental settings to generate a realistic virtual resource configuration model; then, using this virtual resource configuration model, the simulation technology is used to simulate the first aid resource constraints in the real world, and the number, position and status of props in the virtual environment are adjusted, such as reducing the number of stretchers or setting up road blockades, as well as the physical properties of the environment, such as light and temperature changes, to obtain a simulated resource-constrained environment; finally, based on the simulated resource-constrained environment, the system introduces a team collaboration mechanism, optimizes the interaction mode and task allocation strategy between trainees, and generates team collaboration rules, such as clear division of labor and information sharing processes; and combined with the trainees' performance data under resource constraints, such as decision-making speed and team communication efficiency, the actual combat capability enhancement training environment is finally configured and processed to generate an actual combat capability enhancement training environment under team collaboration;

[0108] Assuming that the threshold is set to 0.7, the system performs numerical calculations to verify the effectiveness of the model. Assume that α = 0.6, λ = 0.3, V(t) = 0.5, H(t) = 0.8, β = 0.4, C(t) = 1.2, ( = 0.7, S(t) = 0.9, μ = 0.5, G(t) = 0.8, substitute into the formula E(t) = α·B(t)·(1+λ·V(t))+(1-α)·H(t)-β·C(t) 2 +ζ·S(t)·(1+μ·G(t)), where B(t)=0.9, we get E(t)=0.6·0.9·(1+0.3·0.5)+(1-0.6)·0.8-0.4·1.2 2+0.7·0.9·(1+0.5·0.8)=0.84; Since the calculated result of E(t) is greater than the set threshold of 0.7, it indicates that the current scenario is highly challenging and the trainees’ coping ability needs to be further enhanced;

[0109] Furthermore, let γ = 0.5, δ = 0.3, D(t) = 0.7, θ = 0.4, F(t) = 0.6, φ = 0.3, Q(t) = 0.5, ∈ = 0.1, R(t) = 0.9, η = 0.6, A(t) = 0.8, κ = 0.4, L(t) = 0.7, and substitute into the formula P(t+1) = P(t)·e -(γ·E(t)+δ·D(t)+θ·F(t)+φ·Q(t)) +∈·R(t)·(1+η·A(t)+κ·L(t)), where P(t)=0.8, we get P(t+1)=0.8·e -(0.5·0.84+0.3·0.7+0.4·0.6+0.3·0.5) +0.1·0.9·(1+0.6·0.8+0.4·0.7)=0.65; and the calculation result of P(t+1) shows that the adjustment of event possibility distribution is effective, making the training closer to the actual situation and significantly improving the trainees’ practical ability and confidence in dealing with emergencies.

[0110] Through the above steps, this embodiment not only provides a highly simulated training environment, but also ensures the uniqueness and challenge of each training through in-depth analysis of behavioral patterns and accurate simulation of resource constraints, thereby significantly improving the trainees' practical ability and emergency handling skills.

[0111] 103. Based on the personalized first aid scenario branch, the personalized guidance information is generated and processed in real time, the Bayesian network algorithm is introduced to predict and identify the problems that the user may encounter, and the emotional fluctuations of the user are analyzed through the emotional state monitoring technology to generate personalized guidance and psychological support plans;

[0112] In this step, the instant generation of personalized guidance information involves using the Bayesian network algorithm to predict the problem points that users may encounter, and combining emotional state monitoring technology to analyze the user's emotional fluctuations. Based on these prediction and analysis results, the system can generate targeted personalized guidance and psychological support plans to help users better deal with emergencies and reduce operational errors caused by tension or anxiety.

[0113] In the embodiment of the present application, the system predicts the problems that users may encounter in different scenarios through the Bayesian network algorithm, and uses the emotional state monitoring technology to analyze the user's emotional fluctuations in real time. Based on this information, the system instantly generates personalized guidance information and psychological support plans, providing specific suggestions and support to help users improve their skills and enhance their psychological resilience.

[0114] For example, in a training session simulating the treatment of severe trauma, if the system detects that a trainee is anxious and hesitant at a key step, it will immediately push an encouraging message and provide detailed operation instructions, such as how to bandage a wound correctly. This not only relieves the trainee's stress, but also improves the accuracy of their operation.

[0115] Optionally, in step 103, based on the personalized first aid scenario branch, personalized guidance information is generated in real time, a Bayesian network algorithm is introduced to predict and identify the problem points that the user may encounter, and the user's emotional fluctuations are analyzed through emotional state monitoring technology to generate personalized guidance and psychological support plans, including:

[0116] Based on the personalized first aid scenario branch, key nodes and potential problem points in first aid training are identified and processed to obtain a set of key nodes and problem points; using the set of key nodes and problem points, a Bayesian network algorithm is introduced to predict the problem points that users may encounter in different scenarios and generate a predicted problem point list; based on the predicted problem point list and in combination with the user's historical performance data, the user's ability to cope with problems is evaluated and processed to obtain a user ability evaluation result; based on the user ability evaluation result, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report; using the emotional fluctuation analysis report, personalized guidance information is customized and generated, corresponding psychological support strategies are formulated, and personalized guidance and psychological support plans are generated.

[0117] In this step, generating personalized guidance information based on personalized first aid scenario branches includes identifying key nodes and potential problem points in first aid training, forming a set of key nodes and problem points. These data are used to predict the problems that users may encounter and evaluate their coping capabilities in combination with their historical performance. By analyzing the user's emotional fluctuations through emotional state monitoring technology, the system can customize and generate personalized guidance information and psychological support strategies to ensure that users receive timely and effective help and support when facing complex first aid scenarios.

[0118] In the embodiment of the present application, firstly, the system identifies key nodes and potential problem points in first aid training based on personalized first aid scenario branches, and obtains a set of key nodes and problem points; secondly, the set is used to introduce a Bayesian network algorithm to predict and process the problem points that the user may encounter in different scenarios, and generate a predicted problem point list; thirdly, based on the predicted problem point list, combined with the user's historical performance data, the user's ability to cope with problems is evaluated to obtain a user ability evaluation result; finally, based on the user ability evaluation result, the user's emotional fluctuations are analyzed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report, and this report is used to customize and generate personalized guidance information, formulate corresponding psychological support strategies, and generate personalized guidance and psychological support plans.

[0119] In a first aid training that simulates a large-scale traumatic event, trainees need to complete multiple first aid tasks within a limited time. First, based on the personalized first aid scenario branches, the system identifies key nodes in the first aid training, such as the classification of the wounded, wound treatment, etc., as well as potential problem points, such as insufficient equipment or complex injuries, to form a set of key nodes and problem points. Second, the system uses this set to introduce the Bayesian network algorithm to predict the problem points that trainees may encounter in different scenarios, such as how to give priority to the treatment of seriously injured people, and generate a list of predicted problem points. Third, based on the predicted problem point list and combined with the trainees' historical performance data, their ability to cope with problems is evaluated, such as whether they can make correct decisions under pressure, to obtain the user's ability assessment results. Then, based on the user's ability assessment results, the system uses emotional state monitoring technology to analyze the trainees' emotional fluctuations in real time, such as anxiety level or concentration, to obtain an emotional fluctuation analysis report. Finally, using the emotional fluctuation analysis report, the system customizes and generates personalized guidance information, such as providing immediate operation prompts or psychological counseling suggestions, formulating corresponding psychological support strategies, and generating personalized guidance and psychological support plans.

[0120] Through the above steps, this embodiment not only accurately identifies the key nodes and potential problem points in first aid training, but also uses the Bayesian network algorithm to predict the problems that trainees may encounter, and combines historical performance and real-time emotional fluctuation analysis to provide highly personalized guidance information and psychological support. This not only enhances the trainees' practical skills, but also effectively relieves their psychological pressure in a high-pressure environment, significantly improving the training effect and the trainees' coping ability.

[0121] Optionally, based on the user capability assessment result, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report, including:

[0122] Utilizing the user's expected performance model, combined with the user's physiological signals and behavioral data collected in real time, and through the emotional state monitoring technology, the user's emotional state is dynamically captured and processed to generate original emotional state data; based on the original emotional state data, an emotion recognition algorithm is used to classify and quantify the user's emotional fluctuations to obtain an emotional fluctuation index; based on the emotional fluctuation index, a comparative analysis is performed with a standard emotional pattern library to determine the type and intensity of the user's emotional fluctuations and generate an emotional fluctuation feature description; using the emotional fluctuation feature description, combined with the user's historical emotional records, the causes and influencing factors of the current emotional fluctuations are deeply analyzed and processed to obtain an emotional fluctuation analysis report.

[0123] In this step, based on the user ability assessment results, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to generate an emotional fluctuation analysis report. Specifically, the user's expected performance model is combined with real-time collected physiological signals (such as heart rate, skin conductance) and behavioral data (such as operation speed, decision accuracy) to dynamically capture the user's emotional state and generate raw emotional state data. These data are classified and quantified through the emotion recognition algorithm to obtain emotional fluctuation indicators. The system compares these indicators with the standard emotional pattern library to determine the type and intensity of emotional fluctuations and generate emotional fluctuation feature descriptions. Finally, combined with the user's historical emotional records, the causes and influencing factors of the current emotional fluctuations are deeply analyzed to form a detailed emotional fluctuation analysis report.

[0124] In the embodiment of the present application, first, the system utilizes the user's expected performance model, combined with the physiological signals and behavioral data collected in real time, and dynamically captures the user's emotional state through emotional state monitoring technology to generate original emotional state data; secondly, based on the original emotional state data, an emotion recognition algorithm is used to classify and quantify the user's emotional fluctuations to obtain an emotion fluctuation index; thirdly, based on the emotion fluctuation index, a comparative analysis is performed with a standard emotion pattern library to determine the type and intensity of the user's emotional fluctuations, and generate an emotion fluctuation feature description; finally, the emotion fluctuation feature description is used, combined with the user's historical emotion records, to conduct an in-depth analysis of the causes and influencing factors of the current emotional fluctuations to obtain an emotion fluctuation analysis report.

[0125] In a first aid training that simulates emergency medical rescue, trainees need to make a series of key decisions quickly under high-pressure conditions. First, the system uses the user's expected performance model, combined with real-time collected physiological signals such as heart rate and skin conductance, as well as behavioral data such as operation speed and decision accuracy, to dynamically capture the trainees' emotional state through emotional state monitoring technology and generate raw emotional state data. Second, based on these raw emotional state data, the system uses emotion recognition algorithms to classify and quantify the trainees' emotional fluctuations, such as distinguishing between emotions such as anxiety, tension or calmness, and calculating their intensity to obtain emotional fluctuation indicators. Third, based on these emotional fluctuation indicators, the system conducts comparative analysis with the standard emotional pattern library to determine the specific type and intensity of the trainees' emotional fluctuations and generate emotional fluctuation feature descriptions, such as "high anxiety" or "moderate tension". Finally, using these emotional fluctuation feature descriptions, the system combines the trainees' historical emotional records to deeply analyze the causes and influencing factors of the current emotional fluctuations, such as whether anxiety is caused by increased task complexity or insufficient resources, thereby generating a detailed emotional fluctuation analysis report.

[0126] Through the above steps, this embodiment not only captures the emotional state of trainees in a high-pressure environment in real time, but also provides a comprehensive analysis of trainees' emotional fluctuations through accurate emotion recognition and historical data analysis. This enables the system to provide trainees with targeted psychological support and personalized guidance, helping them maintain the best psychological state when facing complex emergency scenarios, significantly improving the training effect and trainees' actual coping ability.

[0127] The present application takes into account that in the prior art, first aid training systems are deficient in predicting the problems that users may encounter and generating personalized guidance. Traditional simulator training usually uses preset scenarios and fixed development paths, and lacks the ability to dynamically adjust according to the user's real-time performance, resulting in an unrealistic user experience and difficulty in truly reflecting the complex and ever-changing first aid scenes. In addition, existing solutions pay little attention to factors such as user behavior patterns, historical performance, and teamwork, which affects the authenticity and pertinence of the training results. Therefore, the embodiment of the present invention proposes this optional solution to solve the above problems. By introducing a Bayesian network algorithm and a set of key nodes and problem points, it is possible to achieve intelligent prediction of the problem points that users may encounter, thereby improving the realism and personalization of training.

[0128] Optionally, the key nodes and problem point set are used to introduce a Bayesian network algorithm to predict the problem points that users may encounter in different scenarios and generate a predicted problem point list, including:

[0129] Calculate the probability score P of the user encountering a problem point iPreviously, we provided a comprehensive foundation for the calculation of Pi by analyzing key nodes and problem points, evaluating scenario complexity, reviewing user historical performance, calculating social interaction scores, and considering the impact of time pressure and background knowledge;

[0130]

[0131] Among them, P i is the probability score of a user encountering a specific problem point in the i-th scenario; K i is the key node impact factor in the i-th scenario; a is the weight coefficient of the key node impact factor; C i is the scenario complexity index of the i-th scenario; b is the impact coefficient of scenario complexity; H i is the user's historical performance impact factor; c is the weight coefficient of the historical performance impact factor; S i is the social interaction score; d is the weight coefficient of the social interaction score; T i is the time pressure score; l is the weight coefficient of the time pressure score; B i is the background knowledge score; r is the weight coefficient of the background knowledge score.

[0132] After calculating P i Finally, the probability scores of all scenarios are integrated, and combined with resource availability and user adaptability scores, the score sensitivity is adjusted using a power function, and the influence of behavioral variability and emotional fluctuations is considered to generate a comprehensive prediction score Q j ;

[0133]

[0134] Among them, Q j is the comprehensive prediction score of the user on the jth type of problem point; P i is the probability score of a user encountering a specific problem point in the i-th scenario; N is the total number of all considered scenarios; η′ is the impact coefficient of resource availability; R i is the resource availability index in the i-th scenario; A′ j is the user's adaptability score for the jth type of problem point; (1-η′) is the weight coefficient of the adaptability score; θ′ is the coefficient of variation; V j is the behavioral variability of the j-th problem point; φ′ is the emotion fluctuation coefficient; E′ j is the emotional fluctuation score of the th type of problem point; ψ′ is the power coefficient of the comprehensive prediction score.

[0135] Based on Q jBased on the results, possible problem points are prioritized, predictions are optimized in combination with the user's learning progress, and a detailed action guide is developed. Finally, the information is integrated to generate a list of predicted problem points, thereby improving the user's practical ability and confidence in dealing with emergencies.

[0136] This formula aims to overcome the limitations of existing technologies. This solution designs a set of prediction processing methods based on key nodes and problem point sets. First, by analyzing and evaluating the key nodes and problem point sets, the influence of scenario complexity, user historical performance, social interaction score, time pressure and background knowledge is used to calculate the probability score P of users encountering problem points. i Provide a comprehensive foundation; secondly, integrate the probability scores of all scenarios, combine resource availability and user adaptability scores, use power functions to adjust the score sensitivity, consider the impact of behavioral variability and emotional fluctuations, and generate a comprehensive prediction score Q j . Finally, the information is integrated to generate a list of predicted problem points, improving the user's practical ability and confidence in dealing with emergencies.

[0137] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0138]

[0139] Key node impact: a·log(1+K i ): measure the impact of key nodes on the occurrence of problem points; the impact of scenario complexity: Assess the impact of scenario complexity on problem points; historical performance impact: Adjust weights based on user past performance data; Social interaction influence: d·sin(S i ): Measures the impact of social interaction on problem points; Time pressure impact: Assess the impact of time pressure on problem points; influence of background knowledge: -r·ln(1+B i ): Consider the impact of user background knowledge on problem points;

[0140] The following is a brief introduction to how to obtain the parameters of the formula:

[0141] K i Extracted from a set of key nodes and problem points; a set through experiments or expert evaluation; C i Obtained through scenario assessment tools; b set through experiments or expert assessment; H i Calculated based on the user's historical performance data; c set through experiments or expert evaluation; SS i Obtained through social interaction analysis tools; d set through experiments or expert evaluation; T i Obtained through time pressure assessment tools; l set through experiments or expert assessment; Bi Obtained through background knowledge assessment tools; r set through experiments or expert assessment;

[0142] The following is a brief introduction to the design reasons of each sub-item of the formula:

[0143]

[0144] Probability score impact: P i : The probability score of a user encountering a specific problem point in the i-th scenario; Resource availability impact: η′·R i :Evaluate the impact of resource availability on the problem point; Adaptability impact: (1-η′)·A′ j : Adjust the weight based on the user's adaptability score for a specific problem point; Variability impact: θ′·V j : Measures the impact of behavioral variability on problem points; Impact of emotional fluctuations: φ′·E′ j : Consider the impact of emotional fluctuations on question points; score sensitivity adjustment: (·) ψ′ : Use power function to adjust the score sensitivity;

[0145] The following is a brief introduction to how to obtain the parameters of the formula:

[0146] P i : Calculated by the above formula; R i Obtained through resource management tools; η′ is set through experiments or expert evaluation; A′ j Obtained through user feedback and evaluation tools; η′ is set through experiments or expert evaluation; V j Obtained through behavioral variability assessment tools; θ′ is set through experiments or expert evaluation; E′ j Obtained through the emotion fluctuation assessment tool; φ′ is set through experiments or expert assessment; ψ′ is set through experiments or expert assessment;

[0147] In a first aid training that simulates a large-scale traumatic event, trainees need to make a series of key decisions quickly under high pressure. First, the system analyzes the key nodes and problem points, evaluates the complexity of the scenario, reviews the user's historical performance, calculates the social interaction score, and considers the influence of time pressure and background knowledge. This provides a comprehensive basis for calculating the probability score Pi of the user encountering a problem point. Assuming the threshold is set to 0.7, and a = 0.6, K i =0.8, b=0.4, C i =0.9, c=0.5, H i =0.7, d=0.3, S i =0.8, l=0.4, T i =0.6, r=0.2, B i =0.5, substitute into the formula get Because P i The calculated result is greater than the set threshold of 0.7, indicating that the current scenario is highly challenging and the trainees’ coping ability needs to be further enhanced;

[0148] Next, the system integrates the probability scores of all scenarios, combines the resource availability and the user's adaptability score, uses a power function to adjust the score sensitivity, considers the influence of behavioral variability and emotional fluctuations, and generates a comprehensive prediction score Q j ; Assume N = 5, η′ = 0.6, R i =0.8, A′ j =0.7,θ′=0.4,V j =0.6,φ′=0.3,E′ j =0.5, ψ′=0.5, substitute into the formula Where P i =0.82, we get And Q j The calculation results show that the adjustment of the comprehensive prediction score is effective, making the training closer to the actual situation and significantly improving the trainees' practical ability and confidence in dealing with emergencies;

[0149] Based on Q j As a result, the system prioritizes possible problem points, optimizes predictions based on the user's learning progress, develops detailed action guidelines, and finally integrates information to generate a list of predicted problem points to help students better prepare for and respond to actual emergency scenarios.

[0150] Through the above steps, this embodiment not only provides a highly simulated training environment, but also ensures the uniqueness and challenge of each training through intelligent prediction and personalized guidance of possible problems that users may encounter, thereby significantly improving the students' practical ability and emergency handling skills.

[0151] 104. Design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

[0152] In this step, designing realistic resource constraints means simulating the limited emergency resources in the real world, such as the number of medical equipment, the types and availability of medicines, etc. According to the personalized guidance and psychological support plan, the system carefully configures virtual props and environmental settings to create a practical ability enhancement training environment under teamwork, so that trainees can practice decision-making and resource management capabilities under close-to-real constraints.

[0153] In the embodiment of the present application, the system adjusts the virtual props and environment settings according to the personalized guidance and psychological support program to simulate the real-world emergency resource limitations. This includes controlling the number, position and state of props in the virtual environment, as well as the physical characteristics of the environment. In this way, the system creates a realistic combat capability enhancement training environment to help users practice teamwork and emergency response skills under resource-constrained conditions.

[0154] For example, in a post-earthquake rescue simulation, the system limited the number of stretchers and medical supplies available, forcing trainees to rationally allocate limited resources and work closely with other team members. This realistic resource restriction allows trainees to practice effective resource management and teamwork in a near-real situation, significantly improving their practical ability and confidence in dealing with emergencies.

[0155] Optionally, the step 104 of designing realistic resource constraints, according to the personalized guidance and psychological support program, carefully configuring virtual props and environment settings, simulating first aid resource constraints in the real world, and generating a combat capability enhancement training environment under teamwork, includes:

[0156] According to the personalized guidance and psychological support program, the resource constraints that need to be simulated in the first aid training are defined and processed to obtain a list of resource constraints; based on the list of resource constraints, combined with the equipment availability and environmental factors in the actual first aid scenario, the virtual props and environment settings are designed and processed to generate a realistic virtual resource configuration model; using the realistic virtual resource configuration model, the first aid resource constraints in the real world are simulated through simulation technology, the number, position and state of props in the virtual environment, and the physical characteristics of the environment are adjusted to obtain a simulated resource-constrained environment; based on the simulated resource-constrained environment, a team collaboration mechanism is introduced to optimize the interaction mode and task allocation strategy between users to generate team collaboration rules; according to the team collaboration rules, combined with the performance data of users under resource constraints, the actual combat capability enhancement training environment is finally configured to generate a actual combat capability enhancement training environment under team collaboration.

[0157] In this step, the design of realistic resource constraints includes defining the resource constraints that need to be simulated in first aid training according to the personalized guidance and psychological support plan, and forming a list of resource constraints. These data are used to ensure that the virtual props and environment settings can truly reflect the equipment availability and environmental factors in the actual first aid scenario, and generate a realistic virtual resource configuration model. The number, location and status of props in the virtual environment and the physical characteristics of the environment are adjusted through simulation technology to create a simulated resource-constrained environment. The team collaboration mechanism is introduced to optimize the interaction mode and task allocation strategy between users, and finally configure the actual combat capability enhancement training environment under team collaboration.

[0158] In the embodiment of the present application, first, the system defines the resource constraints that need to be simulated in the first aid training according to the personalized guidance and psychological support plan, and obtains a list of resource constraints; secondly, based on the list, combined with the equipment availability and environmental factors in the actual first aid scenario, the virtual props and environment settings are designed and processed to generate a realistic virtual resource configuration model; thirdly, the virtual resource configuration model is used to simulate the first aid resource constraints in the real world through simulation technology, and the number, position and state of the props in the virtual environment, as well as the physical characteristics of the environment, to obtain a simulated resource-constrained environment; finally, based on the simulated resource-constrained environment, a team collaboration mechanism is introduced to optimize the interaction mode and task allocation strategy between users, generate team collaboration rules, and combine the performance data of users under resource-constrained conditions to perform final configuration processing on the actual combat capability enhancement training environment to generate an actual combat capability enhancement training environment under team collaboration.

[0159] In a first aid training simulating large-scale disaster rescue, trainees need to work in a team in a complex environment. First, the system defines the resource constraints that need to be simulated in the first aid training, such as the limited number of medical equipment and the supply of specific types of drugs, based on the personalized guidance and psychological support plan, and forms a list of resource constraints. Second, based on this list, combined with the equipment availability and environmental factors in the actual first aid scene, such as terrain obstacles and weather conditions, the system designs and processes virtual props and environmental settings to generate a realistic virtual resource configuration model. Third, using this virtual resource configuration model, the simulation technology is used to simulate the first aid resource constraints in the real world, and the number, position and status of props in the virtual environment are adjusted, such as reducing the number of stretchers or setting up road blockades, as well as the physical properties of the environment, such as light and temperature changes, to obtain a simulated resource-constrained environment. Finally, based on the simulated resource-constrained environment, the system introduces a team collaboration mechanism, optimizes the interaction mode and task allocation strategy between trainees, and generates team collaboration rules, such as clear division of labor and information sharing processes. Combined with the performance data of trainees under resource constraints, such as decision-making speed and team communication efficiency, the system performs final configuration processing on the actual combat capability enhancement training environment to generate an actual combat capability enhancement training environment under team collaboration.

[0160] Through the above steps, this embodiment not only accurately simulates the resource constraints in actual emergency scenarios, but also provides a highly realistic training environment through realistic virtual resource configuration and team collaboration mechanism optimization. This allows trainees to practice resource management and team collaboration skills in a situation close to the real world, significantly improving their actual combat capabilities and confidence in dealing with complex situations.

[0161] Through the comprehensive application of steps 101 to 104, this system not only provides a highly simulated virtual first aid scenario and realizes seamless interaction between users and the virtual environment, but also ensures the uniqueness and pertinence of each training by dynamically adjusting the development trajectory of first aid events and the instant generation of personalized guidance information. In addition, by simulating realistic resource constraints, the system creates a practical ability enhancement training environment under teamwork, which comprehensively improves the practical ability and psychological quality of users. These functions work together to significantly improve the realism, personalization, interactivity and psychological support level of first aid training, and provide users with an efficient and high-quality first aid skills training platform, so that they can respond more calmly when facing real-world emergencies.

[0162] Figure 2 A structural diagram of a virtual reality processing system in a first aid training simulator is provided for an embodiment of the present application. Figure 2 As shown, the device comprises:

[0163] Construction module 21 is used to construct a highly simulated virtual first aid scene, collect the multi-dimensional actions of the user in the physical space and map these actions to the virtual character, synchronously adjust the response behavior of the objects in the virtual environment, obtain an immersive first aid training experience in which the user interacts seamlessly with the virtual environment, and generate interactive feedback data;

[0164] An adjustment module 22 is used to dynamically adjust the development trajectory of the emergency event according to the interactive feedback data, adopt an adaptive event evolution algorithm, combine the scenario complexity analysis technology to evaluate the difficulty level of the emergency event, and generate a personalized emergency scenario branch;

[0165] The analysis module 23 is used to generate and process personalized guidance information in real time based on the personalized first aid scenario branch, introduce the Bayesian network algorithm to predict and identify the problem points that the user may encounter, and analyze the user's emotional fluctuations through the emotional state monitoring technology to generate personalized guidance and psychological support plans;

[0166] The configuration module 24 is used to design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

[0167] Figure 2 The virtual reality processing system in the first aid training simulator can perform Figure 1 The implementation principle and technical effect of the virtual reality processing method in a first aid training simulator described in the illustrated embodiment will not be described in detail. The specific manner in which each module and unit performs operations in the virtual reality processing system in a first aid training simulator in the above embodiment has been described in detail in the embodiment of the method, and will not be described in detail here.

[0168] In one possible design, Figure 2 The virtual reality processing system in a first aid training simulator of the illustrated embodiment may be implemented as a computing device, such as Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0169] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are called and executed by the processing component 32 .

[0170] The processing component 32 is used to: construct a highly simulated virtual first aid scenario, collect the multi-dimensional actions of the user in the physical space and map these actions to the virtual character, synchronously adjust the response behavior of the objects in the virtual environment, obtain an immersive first aid training experience in which the user interacts seamlessly with the virtual environment, and generate interactive feedback data; dynamically adjust the development trajectory of the first aid event according to the interactive feedback data, use an adaptive event evolution algorithm, combine the scenario complexity analysis technology to evaluate the difficulty level of the first aid event, and generate personalized first aid scenario branches; based on the personalized first aid scenario branches, instantly generate and process personalized guidance information, introduce a Bayesian network algorithm to predict and identify the problem points that the user may encounter, and analyze the user's emotional fluctuations through emotional state monitoring technology to generate personalized guidance and psychological support plans; design realistic resource constraints, and according to the personalized guidance and psychological support plans, carefully configure virtual props and environmental settings to simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

[0171] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above method. Of course, the processing component may also be implemented by one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors or other electronic components to perform the above method.

[0172] The storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic memory, flash memory, magnetic disk or optical disk.

[0173] Of course, the computing device may also include other components, such as input / output interfaces, display components, communication components, etc.

[0174] The input / output interface provides an interface between the processing component and the peripheral interface module, which may be an output device, an input device, etc.

[0175] The communication component is configured to facilitate, among other things, wired or wireless communications between the computing device and other devices.

[0176] Among them, the computing device can be a physical device or an elastic computing host provided by a cloud computing platform, etc. In this case, the computing device can refer to a cloud server, and the above-mentioned processing components, storage components, etc. can be basic server resources rented or purchased from the cloud computing platform.

[0177] The present application also provides a computer storage medium storing a computer program, wherein the computer program can achieve the above-mentioned Figure 1 A virtual reality processing method in a first aid training simulator of the illustrated embodiment.

[0178] Those skilled in the art can clearly understand that, for the convenience and brevity of description, the specific working processes of the systems, devices and units described above can refer to the corresponding processes in the aforementioned method embodiments and will not be repeated here.

[0179] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0180] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0181] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present application, rather than to limit it. Although the present application has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the embodiments of the present application.

Claims

1. A virtual reality processing method in a first aid training simulator, characterized in that: include: Build a highly simulated virtual first aid scene, collect the multi-dimensional actions of users in the physical space and map these actions to virtual characters, synchronously adjust the response behaviors of objects in the virtual environment, obtain an immersive first aid training experience in which users interact seamlessly with the virtual environment, and generate interactive feedback data; According to the interactive feedback data, the development trajectory of the emergency event is dynamically adjusted, and the difficulty level of the emergency event is evaluated by using an adaptive event evolution algorithm combined with scenario complexity analysis technology to generate personalized emergency scenario branches; Based on the personalized first aid scenario branch, personalized guidance information is generated and processed in real time, the Bayesian network algorithm is introduced to predict and identify the problems that users may encounter, and the emotional fluctuations of users are analyzed through emotional state monitoring technology to generate personalized guidance and psychological support plans; Design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under teamwork.

2. The method according to claim 1, characterized in that According to the interactive feedback data, the development trajectory of the emergency event is dynamically adjusted, an adaptive event evolution algorithm is used, and the difficulty level of the emergency event is evaluated in combination with the scenario complexity analysis technology to generate personalized emergency scenario branches, including: Utilizing the interactive feedback data, analyzing and processing the user's behavior pattern and decision path in the virtual first aid scenario to obtain the user's behavior feature set; Based on the behavioral feature set, an adaptive event evolution algorithm is used to dynamically adjust the development trajectory of the emergency event to generate an initial event evolution plan; According to the initial event evolution plan, combined with scenario complexity analysis technology, difficulty assessment is performed on each possible emergency event branch to obtain a difficulty score for each branch; Based on the difficulty score, various potential development paths of the emergency incident are screened and optimized to generate personalized emergency scenario branches.

3. The method according to claim 2, characterized in that The interactive feedback data is used to analyze and process the user's behavior pattern and decision path in the virtual emergency scene to obtain the user's behavior feature set, including: Using the interactive feedback data, fine-grained analysis is performed on the user's action sequence and decision-making choices in the virtual first aid scenario to obtain the user's behavioral event record; Based on the user's behavioral event records, a behavioral pattern recognition algorithm is used to summarize the user's action patterns and decision-making habits to generate a preliminary behavioral pattern model; Based on the preliminary behavior pattern model, combined with the user's historical training data, deep learning optimization processing is performed to obtain an optimized behavior pattern model; Based on the optimized behavior pattern model, the user's behavior characteristics are quantified, representative behavior characteristic parameters are extracted, and the user's behavior characteristic set is generated.

4. The method according to claim 2, characterized in that: According to the initial event evolution plan, combined with the scenario complexity analysis technology, each possible emergency event branch is evaluated for difficulty to obtain the difficulty score of each branch, including: According to the initial event evolution plan, scenario construction processing is performed on each possible emergency event branch to obtain a scenario model of each branch; Utilizing the scenario models of each branch and combining scenario complexity analysis techniques, the variables and factors in each scenario are quantified to obtain a scenario complexity index; Based on the scenario complexity index, a difficulty assessment algorithm is used to comprehensively evaluate the challenge of each emergency event branch and generate a preliminary difficulty score; According to the preliminary difficulty score, the user's historical performance data is introduced for calibration processing, and the score is adjusted to reflect the user's actual coping ability to obtain the difficulty score of each branch.

5. The method according to claim 1, characterized in that Based on the personalized first aid scenario branch, personalized guidance information is generated and processed in real time, the Bayesian network algorithm is introduced to predict and identify the problems that the user may encounter, and the emotional fluctuations of the user are analyzed through the emotional state monitoring technology to generate personalized guidance and psychological support plans, including: Based on the personalized first aid scenario branch, key nodes and potential problem points in first aid training are identified and processed to obtain a set of key nodes and problem points; By using the key nodes and problem point set, a Bayesian network algorithm is introduced to predict the problem points that users may encounter in different scenarios and generate a predicted problem point list; Based on the predicted problem point list and in combination with the user's historical performance data, the user's ability to cope with the problem is evaluated to obtain a user ability evaluation result; Based on the user ability assessment result, the user's emotional fluctuations are analyzed and processed in real time through emotional state monitoring technology to obtain an emotional fluctuation analysis report; The emotional fluctuation analysis report is used to customize the personalized guidance information, formulate corresponding psychological support strategies, and generate personalized guidance and psychological support plans.

6. The method according to claim 5, characterized in that Based on the user capability assessment result, the user's emotional fluctuations are analyzed and processed in real time through the emotional state monitoring technology to obtain an emotional fluctuation analysis report, including: Using the user's expected performance model, combined with the real-time collected user physiological signals and behavior data, and through the emotional state monitoring technology, the user's emotional state is dynamically captured and processed to generate original emotional state data; According to the original emotional state data, an emotion recognition algorithm is used to classify and quantify the user's emotional fluctuations to obtain an emotional fluctuation index; Based on the emotion fluctuation index, a comparative analysis is performed with a standard emotion pattern library to determine the type and intensity of the user's emotion fluctuation and generate an emotion fluctuation feature description; By using the emotion fluctuation feature description and combining it with the user's historical emotion records, the causes and influencing factors of the current emotion fluctuation are deeply analyzed and processed to obtain an emotion fluctuation analysis report.

7. The method according to claim 1, characterized in that The realistic resource constraints are designed, and virtual props and environment settings are carefully configured according to the personalized guidance and psychological support plan to simulate the first aid resource constraints in the real world and generate a practical ability enhancement training environment under teamwork, including: According to the personalized guidance and psychological support program, resource constraint conditions that need to be simulated in first aid training are defined and processed to obtain a resource constraint condition list; Based on the resource restriction list, combined with the equipment availability and environmental factors in the actual emergency scene, the virtual props and environment settings are designed and processed to generate a realistic virtual resource configuration model; Using the realistic virtual resource configuration model, simulating the first aid resource constraints in the real world through simulation technology, adjusting the number, position and state of props in the virtual environment, and the physical characteristics of the environment, to obtain a simulated resource-constrained environment; Based on the simulated resource-constrained environment, a team collaboration mechanism is introduced to optimize the interaction mode and task allocation strategy between users and generate team collaboration rules; According to the team collaboration rules and combined with the performance data of users under resource-constrained conditions, the actual combat capability enhancement training environment is finally configured to generate the actual combat capability enhancement training environment under team collaboration.

8. A virtual reality processing system in a first aid training simulator, characterized in that: include: The construction module is used to build a highly simulated virtual first aid scene, collect the multi-dimensional actions of the user in the physical space and map these actions to the virtual character, synchronously adjust the response behavior of the objects in the virtual environment, obtain an immersive first aid training experience in which the user interacts seamlessly with the virtual environment, and generate interactive feedback data; An adjustment module is used to dynamically adjust the development trajectory of the emergency event according to the interactive feedback data, adopt an adaptive event evolution algorithm, combine the scenario complexity analysis technology to evaluate the difficulty level of the emergency event, and generate personalized emergency scenario branches; An analysis module is used to instantly generate and process personalized guidance information based on the personalized first aid scenario branch, introduce a Bayesian network algorithm to predict and identify possible problems that users may encounter, and analyze the user's emotional fluctuations through emotional state monitoring technology to generate personalized guidance and psychological support plans; The configuration module is used to design realistic resource constraints, carefully configure virtual props and environmental settings according to the personalized guidance and psychological support plan, simulate the first aid resource constraints in the real world, and generate a practical ability enhancement training environment under team collaboration.

9. A computing device, characterized in that It comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to implement a virtual reality processing method in a first aid training simulator as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that: A computer program is stored, and when the computer program is executed by a computer, a virtual reality processing method in a first aid training simulator as claimed in any one of claims 1 to 7 is implemented.

Images