Biological safety event emergency response virtual simulation training system

Abstract

The invention relates to the technical field of public health safety, and discloses a biological safety event emergency response virtual simulation training system, which comprises a virtual environment construction module, a practical operation training management module, an intelligent evaluation feedback module, a case teaching engine module, a self-adaptive optimization module and an evaluation report generation module, a light source self-calibration module is arranged, optical response models made of different materials are configured for different protective devices, and the authenticity reference of visual presentation of various protective devices is guaranteed; meanwhile, by comparing the wavelength of the virtual light source with a preset spectrum reference value in real time and dynamically monitoring the illumination color temperature deviation of an operation area, the accuracy of aerosol leakage risk assessment is ensured, the misjudgment risk of emergency training is further reduced, and by calculating the spatial position deviation value of a virtual viewpoint of a user and a pollution core area, the risk assessment accuracy is improved. Whether the observation visual angle deviates from the biosafety observation standard axis or not is judged in real time, so that the system can effectively avoid the situation of key pollution path recognition omission.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of public health safety, in particular to a virtual simulation training system for emergency response to biological safety incidents. BACKGROUND

[0002] Biological safety refers to the state that the country effectively prevents and responds to the threat of dangerous biological factors and related factors, that biological technology can develop stably and healthily, that people's life and health and the ecological system are relatively safe and not threatened, and that the biological field has the ability to maintain national security and sustainable development.

[0003] At present, in the field of biological safety incident emergency training, the existing virtual simulation system has technical limitations: when performing protective equipment dressing and undressing drills, the virtual environment light source rendering engine cannot monitor the illumination color temperature deviation of the operation area in real time, the protective clothing material color presents abnormally due to the distortion of the illumination model, which may cause aerosol leakage risk assessment error, and thus reduce the reliability of the training result; at the same time, when performing occupational exposure emergency disposal, there is a lack of dynamic detection mechanism for the virtual visual angle deviation of the trainee, when the user's operation visual angle deviates from the key pollution area observation point, the system cannot automatically correct the spatial positioning deviation, which leads to inaccurate pollution diffusion path identification; in addition, when responding to composite biological safety incidents, the fixed process simulation module is difficult to realize multi-thread crisis grading response training, which causes chaotic emergency disposal time sequence logic and resource allocation decision error, and seriously restricts the effect of real combat emergency response ability training.

[0004] Therefore, the present application provides a virtual simulation training system for emergency response to biological safety incidents to solve the above problems. SUMMARY

[0005] (2) Technical problems solved In view of the deficiencies of the prior art, the present application provides a virtual simulation training system for emergency response to biological safety incidents to solve the problems proposed in the background.

[0006] (2) Technical solutions To achieve the above purpose, the present application provides the following technical solutions: a virtual simulation training system for emergency response to biological safety incidents, comprising: a virtual environment construction module, which generates a multi-scene virtual environment by using a clinical scene three-dimensional reconstruction unit, sets operation specifications by using a biological safety rule configuration unit, and outputs environment data by using a sudden event generation unit; a practical training management module, which receives the environment data, collects user operation instructions by using a multi-modal interaction unit, executes training actions by using a physical engine simulation unit, and outputs user operation data by using a pollution diffusion calculation unit; The intelligent evaluation feedback module receives the operation data, constructs a dynamic evaluation matrix through an operation data acquisition unit, outputs an evaluation result through an evaluation matrix generation unit, and provides real-time error feedback through a real-time error correction unit; The case teaching engine module receives the evaluation result, generates a teaching instruction through a case feature extraction unit and a similarity matching unit, and feeds back to the virtual environment construction module through a decision deduction unit to adjust the environment parameters; The adaptive optimization module receives the evaluation result output by the intelligent evaluation feedback module, analyzes the user's ability characteristics through an ability portrait construction unit, identifies weak training items through a short board analysis unit, and generates optimization instructions through a scene complexity regulation unit; The evaluation report generation module integrates the evaluation result and the user data, and generates a visual ability evaluation report through a multi-dimensional index fusion unit and a weight calculation unit.

[0007] Preferably, the real-time error correction unit includes a holographic projection controller, a decision tree backtracker, and an infection deduction simulator; The holographic projection controller is suitable for starting a three-dimensional standard operation demonstration for instrument operation type errors; The decision tree backtracker is suitable for generating a flow logic error backtracking animation with time annotation; The infection deduction simulator deduces the virtual propagation path of pollution control errors based on the Monte Carlo method.

[0008] Preferably, the scene complexity regulation unit includes a protective operation intensifier, a pollution control interferer, and a pathogen variation engine; The protective operation intensifier dynamically increases the sealing failure threshold of the protective clothing by ±15% stress value; The pollution control interferer generates a random interference factor of aerosol diffusion through a turbulent flow algorithm; The pathogen variation engine adjusts the R0 value range of the virus in real time to 0.8-12.5.

[0009] Preferably, the virtual environment construction module includes a light source self-calibration unit, which is suitable for: Configuring a differential material optical response model, including 8 types of protective clothing material spectral reflection parameters; Real-time monitoring of color temperature deviation of the operation area, with a calibration threshold set to ±5% of the spectral reference value; Triggering a 5500K standard light source holographic guide when the N95 mask ear band stress exceeds the limit.

[0010] Preferably, the real operation training management module includes a dynamic perspective corrector, which is suitable for: Solving the spatial pose deviation amount of the user's virtual viewpoint and the pollution core area; The coordinate conversion matrix is activated when the axial offset exceeds 15°; By enhancing the pollutant rendering intensity by 300% and correcting the visual focus by laser positioning reticle.

[0011] Preferably, the intelligent evaluation feedback module performs: Construct a four-dimensional evaluation tensor: Wherein represents the operation timing compliance degree, represents the spatial path deviation value, represents the biological pollution risk index, represents the emergency decision-making timeliness coefficient; Extract key frames of operation video stream through convolutional neural network, and identify sterile area crossing violation; Trigger real-time sound and light alarm when sharp instrument operation exceeds 2 seconds.

[0012] Preferably, the case teaching engine module performs: Construct a clinical case feature cube: Wherein is the pathogen characteristic dimension parameter, is the spatial environment dimension parameter, is the time pressure dimension parameter; Wherein contains 0-15 minute time pressure parameters; Based on Match cases with similarity>90%, wherein represents the training scene feature vector, represents the case library feature vector; Dynamically generate an infection rate evolution branch tree containing 12 decision nodes.

[0013] Preferably, the adaptive optimization module performs: Construct an ability evaluation matrix: Wherein the row vector represents the operation skill dimension, and the column vector represents the emergency decision-making dimension, represents the score parameter of the mth operation skill in the nth emergency decision-making dimension, wherein m≥5 operation skill dimensions; Calculate the short board index by principal component analysis: represents the individual ability standard deviation parameter, represents the group ability benchmark standard deviation parameter, when Greater than 0.3 activates special reinforcement training.

[0014] Preferably, the evaluation report generation module executes: A three-dimensional radar chart evaluation model is constructed, and the O, K and E axes correspond to operation, knowledge and response dimensions respectively; The weight is calculated by the entropy weight method: Wherein represents the weight coefficient of the ith evaluation dimension, represents the index information entropy parameter, represents the total number of evaluation dimensions parameter; Generate a heat map to mark the operation trajectory deviating from the continuous path at more than three places.

[0015] Preferably, the system comprises a multi-thread hierarchical trigger, which is suitable for: Decompose the composite event into 12 independent crisis nodes and assign a disposal channel; Based on deep reinforcement learning, dynamically adjust the allocation proportion of 70%-90% virtual resources; When the protective equipment is detached for more than 30 seconds, insert the sharp instrument recovery emergency disposal branch.

[0016] (Three) beneficial effects Compared with the prior art, the present application provides a biosafety event emergency response virtual simulation training system, which has the following beneficial effects: 1. In the present application, by setting the light source self-calibration module, when performing protective equipment dressing and undressing virtual training, the light specification parameter set is established based on the biosafety standard, the differential material optical response model is configured for different protective equipment, and the authenticity benchmark of visual presentation of various protective equipment is ensured; At the same time, by comparing the virtual light source wavelength with the preset spectrum reference value in real time, the lighting color temperature deviation of the operation area is dynamically monitored, which can identify whether there is rendering distortion phenomenon in the key sealing part of the protective equipment in real time, ensure the accuracy of aerosol leakage risk assessment, and further reduce the misjudgment risk of emergency training.

[0017] 2. In the present application, by setting the dynamic visual angle corrector, when performing occupational exposure emergency disposal, the spatial pose deviation amount of the user's virtual viewpoint and the pollution core area is calculated, the observation visual angle is judged whether it deviates from the biosafety observation standard axis in real time, so that the system can effectively avoid the situation that the key pollution path is missed; When the user's operation visual angle exceeds the safety threshold, the visual focus is automatically corrected based on the preset spatial coordinate conversion matrix, so that the pollution diffusion monitoring blind area can be eliminated in time, and the accuracy of path tracking of the pathogen is ensured.

[0018] 3. In the present application, by setting multi-thread hierarchical trigger, when dealing with complex bio-safety events, the emergency response hierarchical activation is realized by intelligently analyzing the crisis priority of event elements, and the independent disposal channels of multi-thread events such as pathogen leakage, sharp instrument injury and group infection are generated in real time, so that the system can establish parallel disposal logic for complex events; according to the real-time evolution state of each event chain, the resource allocation strategy is dynamically adjusted to avoid the time sequence conflict and decision resource consumption of emergency disposal process, and further improve the coordination efficiency and disposal efficiency of real combat emergency response. BRIEF DESCRIPTION OF DRAWINGS

[0019] Figure 1 It is a schematic diagram of the overall system architecture of the present application. DETAILED DESCRIPTION

[0020] The technical solutions in the embodiments of the present application will be described clearly and completely below with reference to the drawings in the embodiments of the present application. Obviously, the described embodiments are only part of the embodiments of the present application, not all. Based on the embodiments in the present application, all other embodiments obtained by those skilled in the art without creative labor are within the scope of protection of the present application.

[0021] Please refer to Figure 1 The bio-safety event emergency response virtual simulation training system comprises: A virtual environment construction module generates a multi-scene virtual environment by a clinical scene three-dimensional reconstruction unit, sets operation specifications by a bio-safety rule configuration unit, and outputs environment data by a sudden event generation unit; A practical operation training management module receives the environment data, collects user operation instructions by a multi-modal interaction unit, executes training actions by a physical engine simulation unit, and outputs user operation data by a pollution diffusion calculation unit; An intelligent evaluation feedback module receives the operation data, constructs a dynamic evaluation matrix by an operation data collection unit, outputs evaluation results by an evaluation matrix generation unit, and provides real-time error feedback by a real-time error correction unit; A case teaching engine module receives the evaluation results, generates teaching instructions by a case feature extraction unit and a similarity matching unit, and feeds back to the virtual environment construction module by a decision deduction unit to adjust the environment parameters; An adaptive optimization module receives the evaluation results output by the intelligent evaluation feedback module, analyzes user capability characteristics by a capability portrait construction unit, identifies weak training items by a short board analysis unit, and generates optimization instructions by a scene complexity regulation unit; An evaluation report generation module integrates the evaluation results and user data, generates a visual capability evaluation report by a multi-dimensional index fusion unit and a weight calculation unit.

[0022] Real-time error correction unit contains holographic projection controller, decision tree backtracker and infection deduction simulator; Holographic projection controller is used to start three-dimensional standard operation demonstration for instrument operation type error; Decision tree backtracker is used to generate time-labeled process logic error backtracking animation; Infection deduction simulator deduces virtual propagation path of pollution control error based on Monte Carlo method.

[0023] Scenario complexity regulation unit contains protective operation intensifier, pollution control interferer and pathogen variation engine; Protective operation intensifier dynamically increases protective clothing sealing failure threshold by ±15% stress value; Pollution control interferer generates random interference factor of aerosol diffusion through turbulence algorithm; Pathogen variation engine adjusts R0 value range of virus in real time.

[0024] Virtual environment construction module contains light source self-calibration unit, which is used for: Configuring differentiated material optical response model, including 8 types of protective clothing material spectral reflection parameters; Real-time monitoring of color temperature deviation of operation area, with calibration threshold set to 5% of spectral reference value; Triggering 5500K standard light source holographic guidance when N95 mask ear band stress exceeds limit.

[0025] Practical operation training management module contains dynamic visual angle corrector, which is used for: Solving spatial pose deviation amount of user virtual viewpoint and pollution core area; Activating coordinate conversion matrix when axial deviation exceeds 15°; Correcting visual focus by enhancing pollution rendering intensity by 300% and laser positioning mark.

[0026] Intelligent evaluation feedback module performs: Constructing four-dimensional evaluation tensor: Wherein represents operation timing compliance degree, represents spatial path deviation value, represents biological pollution risk index, represents emergency decision-making timeliness coefficient; Extracting key frames of operation video stream through convolutional neural network to identify sterile area crossing violation; Triggering real-time sound and light alarm when sharp instrument operation exceeds 2 seconds.

[0027] Case teaching engine module performs: Constructing the clinical case feature cube: wherein is the pathogen characteristic dimension parameter, is the spatial environment dimension parameter, is the time pressure dimension parameter; wherein contains a 0-15 minute time pressure parameter; based on matching cases with a similarity of > 90%, wherein represents the training scene feature vector, represents the case library feature vector; dynamically generating an infection rate evolution branch tree containing 12 decision nodes.

[0028] The adaptive optimization module performs: Constructing the ability evaluation matrix: wherein the row vector represents the operation skill dimension and the column vector represents the emergency decision dimension, represents the mth operation skill score parameter in the nth emergency decision dimension, wherein m ≥ 5 operation skill dimensions; Calculate the short board index by principal component analysis: represents the individual ability standard deviation parameter, represents the group ability benchmark standard deviation parameter, when greater than 0.3 activates the special strengthening training.

[0029] The evaluation report generation module performs: Constructing a three-dimensional radar chart evaluation model, with axes O, K, and E corresponding to operation, knowledge, and response dimensions; Calculate the weight by entropy method: wherein represents the ith evaluation dimension weight coefficient, represents the index information entropy parameter, represents the total number of evaluation dimensions parameter; Generate a heat map to mark operation trajectories that deviate from the continuous path by more than 3.

[0030] The system contains multi-threaded hierarchical triggers, suitable for: Decomposing complex events into 12 independent crisis nodes and assigning disposal channels; Based on deep reinforcement learning, dynamically adjust the 90% virtual resource allocation ratio; Insert the sharp instrument recycling emergency disposal branch when the protective equipment is detached for 30 seconds.

[0031] comprising the steps of: S1, constructing a multi-scene biosafety event virtual simulation environment, generating interactive operation scenes of protective equipment dressing and undressing, medical waste treatment and sudden infection event disposal through a three-dimensional modeling engine; S2, receiving user operation instructions and performing virtual operation training, and simulating the deformation, displacement and pollution diffusion effect of the operation object in real time based on a physical engine; S3, collecting user operation data through a multi-modal perception module to generate a dynamic evaluation matrix containing operation trajectory, timing logic and biosafety specification compliance; S4, comparing the dynamic evaluation matrix with a preset standard operation protocol library based on a reinforcement learning algorithm to generate real-time error feedback and correction guidance information; S5, calling a case reasoning engine to match similar biosafety event cases from a clinical case library to generate an interactive teaching module containing pathogen transmission path visualization, disposal decision tree and consequence deduction; S6, constructing an individualized ability portrait according to user historical training data, and dynamically adjusting the complexity of the virtual simulation environment and the examination and evaluation weight factor; S7, outputting a biosafety ability three-dimensional evaluation report containing operation specification score, emergency decision-making ability evaluation and knowledge weak point analysis.

[0032] Example 1: Protective equipment dressing and undressing training scene Start the virtual simulation engine to load the three-level biosafety laboratory scene, reconstruct the negative pressure ward space topology through laser point cloud scanning, and perform protective clothing dressing and undressing training by the user wearing force feedback gloves and a VR headset. The system collects glove pose data in real time and inputs it into the physical engine, and calculates the stress distribution curve of the elbow and wrist of the protective clothing based on finite element analysis.

[0033] When the wrist seal bar pressure value is detected to be lower than the safety threshold, the light source self-calibration module automatically triggers the holographic projection correction instruction: project a translucent standard operation instruction animation within a 30° range of the user's field of view, and simultaneously adjust the virtual light source color temperature to 5500K standard spectrum.

[0034] After the training is completed, the multi-thread evaluation unit generates a sealing failure risk heat map, marks 3 stress weak points in the operation trajectory, and pushes a targeted reinforcement training scheme.

[0035] Example 2: Occupational exposure emergency disposal scene When simulating an HIV-contaminated sharp injury event, the dynamic perspective corrector calculates the user's virtual viewpoint coordinates in real time. When the user's line of sight deviates from the contaminated core area by more than 15° axial deviation, the system immediately activates the spatial coordinate conversion matrix: increases the dynamic rendering intensity of the pathogen diffusion particle cloud by 300%, and superimposes red laser positioning lines on the surface of the biological safety cabinet.

[0036] Meanwhile, the case teaching engine calls the clinical exposure case library for the past three years, matches the 92% similarity of the disposal scheme to generate a decision tree branch, and after the user selects the flushing and disinfection operation, the physical engine simulates the trajectory of the body fluid splashing in real time, calculates the contamination radius diffusion to 1.2 meters through the turbulent flow algorithm, triggers the emergency disposal timeout alarm and generates a priority list of post-exposure prophylaxis drugs.

[0037] Embodiment 3: Composite biological safety event deduction Initialize the Ebola virus leakage and critical patient transfer superimposed event, and automatically decompose the event chain into 12 crisis nodes through multi-threaded hierarchical triggers. The pathogen variation engine increases the virus R0 value to 8.2 in real time, driving the aerosol diffusion model to generate an orange pollution cloud in the virtual negative pressure corridor.

[0038] The resource scheduling algorithm dynamically adjusts based on deep reinforcement learning: 70% of the virtual manpower is preferentially deployed to the patient isolation cabin, and the remaining resources are allocated to the contaminated area for killing. When the system detects that the protective equipment disassembly process is overdue, an emergency disposal branch for sharp instrument recovery is automatically inserted, and five occupational exposure risk paths are deduced through the Monte Carlo method.

[0039] After the deduction is completed, a three-dimensional capability evaluation radar chart is generated, which marks a 32% decision lag defect in emergency response dimensions and pushes a cross-department collaboration training module.

[0040] It should be noted that, in this text, relationship terms such as first and second are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between the entities or operations. Moreover, the term "includes", "contains" or any other variant thereof is intended to cover non-exclusive inclusion, so that the process, method, article or equipment including a series of elements not only includes those elements, but also includes other elements not explicitly listed or inherent to such process, method, article or equipment. Without more limitations, the element defined by the statement "includes a" does not exclude the presence of another identical element in the process, method, article or equipment that includes the element.

[0041] While embodiments of the application have been shown and described, it is to be understood that the embodiments described are merely exemplary of the principles and application of the present application. Numerous modifications and adaptions can be effected without departing from the spirit and scope of the present application, which is not limited to the exact construction and arrangement described. It is intended, therefore, to cover all modifications and adaptions that fall within the scope of the claims and their equivalents.

Claims

1. A biosafety incident emergency response virtual simulation training system, characterized by: include: The virtual environment construction module generates a multi-scenario virtual environment using the clinical scenario 3D reconstruction unit, sets operational specifications through the biosafety rule configuration unit, and outputs environmental data through the emergency event generation unit; a practical training management module, which receives the environmental data, collects user operation instructions through a multimodal interaction unit, executes training actions using a physical engine simulation unit, and outputs user operation data through a pollution diffusion calculation unit; an intelligent evaluation feedback module, which receives the operation data, constructs a dynamic evaluation matrix through an operation data acquisition unit, outputs an evaluation result through an evaluation matrix generation unit, and provides real-time error feedback through a real-time error correction unit; The case teaching engine module receives the evaluation results, generates teaching instructions by calling the case library through the case feature extraction unit and the similarity matching unit, and feeds back to the virtual environment construction module through the decision deduction unit to adjust the environment parameters; An adaptive optimization module receives the evaluation results output by the intelligent evaluation feedback module, analyzes the user's ability characteristics through the ability profile construction unit, identifies training weaknesses through the shortcoming analysis unit, and generates optimization instructions through the scenario complexity control unit; The evaluation report generation module integrates the evaluation results and user data, and generates a visualization capability evaluation report through a multi-dimensional indicator fusion unit and a weight calculation unit.

2. A biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The real-time error correction unit includes a holographic projection controller, a decision tree backtracker, and an infection deduction simulator; The holographic projection controller is suitable for the demonstration of three-dimensional standard operation when the instrument operation type error is started; The decision tree backtracker is suitable for generating a backtracking animation of process logic errors with time annotations; The infection simulation simulator simulates the virtual propagation path of the contamination control error based on the Monte Carlo method.

3. A biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The scenario complexity control unit includes a protection operation enhancer, a pollution control disruptor, and a pathogen mutation engine; The protective operation intensifier dynamically increases the protective clothing seal failure threshold by ±15% stress value; The pollution control interferer generates aerosol diffusion random interference factors through a turbulence algorithm; The pathogen mutation engine adjusts the virus R0 value range from 0.8 to 12.5 in real time.

4. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The virtual environment construction module includes a light source self-calibration unit, which is suitable for: Configure differentiated material optical response models, including spectral reflectance parameters for 8 types of protective clothing materials; Real-time monitoring of color temperature deviation in the operating area, with the calibration threshold set to ±5% of the spectral reference value; When the ear strap stress of the N95 mask exceeds the limit, the 5500K standard light source holographic guidance is triggered.

5. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The practical training management module includes a dynamic visual angle corrector, which is applicable to: Calculate the spatial posture deviation between the user's virtual viewpoint and the pollution core area; Activate the coordinate transformation matrix when the axial offset exceeds 15°; Correct visual focus by increasing pollutant rendering intensity by 300% and laser positioning markings.

6. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The intelligent assessment feedback module performs: Construct a 4D evaluation tensor: in Indicates the operation timing compliance, Indicates the spatial path deviation value, represents the biological contamination risk index, represents the time efficiency coefficient of emergency decision-making; Extract key frames from the operation video stream using a convolutional neural network to identify violations of sterile area crossings; A real-time sound and light alarm will be triggered when the sharp instrument operation timeout exceeds 2 seconds.

7. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The case teaching engine module performs: Constructing clinical case feature cube: in is the pathogen characteristic dimension parameter, is the spatial environment dimension parameter, is the time pressure dimension parameter; in Contains 0-15 minute time pressure parameters; based on Matching similarity > 90% of the cases, represents the training scene feature vector, represents the case library feature vector; Dynamically generate an infection rate evolution branch tree containing 12 decision nodes.

8. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The adaptive optimization module performs: Constructing a Capability Assessment Matrix: The row vector represents the operational skill dimension, and the column vector represents the emergency decision-making dimension. represents the scoring parameter of the mth operating skill in the nth emergency decision-making dimension, where m ≥ 5 operating skill dimensions; Calculate the short board index through principal component analysis: represents the standard deviation parameter of individual ability, Represents the standard deviation parameter of the group ability benchmark, when When it is greater than 0.3, special intensive training is activated.

9. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The evaluation report generation module performs: Construct a three-dimensional radar chart evaluation model, where axes O, K, and E correspond to the operation, knowledge, and response dimensions respectively; Calculate the weights using the entropy weight method: in represents the weight coefficient of the i-th evaluation dimension, represents the indicator information entropy parameter, Indicates the total number of evaluation dimensions parameter; Generate a heat map to mark the operation trajectory with more than 3 consecutive path deviations.

10. The biosafety incident emergency response virtual simulation training system according to claim 1, characterized in that: The system includes multi-threaded hierarchical triggers, suitable for: Disassemble the complex event into 12 independent crisis nodes and assign disposal channels; Dynamically adjust the virtual resource allocation ratio between 70% and 90% based on deep reinforcement learning; When the protective equipment is removed for 30 seconds, insert the sharps recovery emergency disposal branch.

Images