Method and system for analyzing first aid effectiveness based on simulated human

Abstract

The present invention provides a method and system for analyzing the effectiveness of first aid based on a simulated person, and relates to the technical field of simulation analysis. The method and system include using a three-dimensional reconstruction algorithm to generate a triangular patch mesh model of soft tissue, tetrahedralizing the triangular patch mesh model of the soft tissue, and generating a discretized model suitable for first aid simulation; using a collision detection algorithm to detect the contact state between a user's hand and the first aid simulation discretized model in real time, modeling a virtual finger as a particle-spring system with stiffness and damping, and using a position-based dynamics method to calculate multi-point tactile feedback force in real time according to the contact state between the virtual finger and the soft tissue surface. When a collision event is detected, the collision force is applied to the first aid simulation discretized model as a boundary condition to drive the soft tissue to deform; extracting the operation features corresponding to the user's hand when a collision event occurs, combining with a preset operation evaluation rule library, and determining the first aid operation quality score through a preset quality evaluation model.

Description

Technical Field

[0001] The present invention relates to simulation analysis technology, and in particular to a method and system for analyzing the effectiveness of first aid based on simulated persons. Background Art

[0002] Traditional first aid training mainly relies on theoretical learning and simulator training, which has problems such as high training cost, poor interactivity, and difficulty in objective evaluation.

[0003] At present, virtual reality technology has been applied to some extent in the field of medical education, such as surgical simulation training systems, anatomical visualization platforms, etc. These systems provide an immersive learning experience by building realistic virtual scenes and interactive methods, improving learning efficiency and enthusiasm. However, the existing virtual reality medical education system mainly focuses on the process training of specific medical operations and lacks an evaluation and feedback mechanism for the comprehensive ability of trainees.

[0004] In the field of first aid training, manikins are a commonly used teaching tool. They provide trainees with a close-to-real training environment by simulating the physiological characteristics and pathological reactions of the human body. However, traditional manikins lack intelligent interaction and feedback capabilities, and cannot give objective evaluation and guidance based on the performance of trainees. In addition, manikins are expensive to use and difficult to maintain and update, which limits their promotion and application in first aid training. Summary of the invention

[0005] The embodiments of the present invention provide a method and system for analyzing the effectiveness of first aid based on a simulated person, which can solve the problems in the prior art.

[0006] According to a first aspect of the embodiments of the present invention,

[0007] Provides a method for analyzing the effectiveness of first aid based on a simulator, including:

[0008] Using medical imaging equipment to collect tomographic data of key parts of the human body, extracting contour information of soft tissue from the tomographic data through medical image processing technology, and using a three-dimensional reconstruction algorithm to generate a triangular patch mesh model of the soft tissue, tetrahedralizing the triangular patch mesh model of the soft tissue, and using an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation;

[0009] A collision detection algorithm is used to detect the contact state between the user's hand and the first aid simulation discretization model in real time, and a virtual finger is modeled as a mass-spring system with stiffness and damping. According to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform.

[0010] The operation features corresponding to the user's hand when a collision event occurs are extracted, and the operation features include operation position, operation speed, operation force and operation trajectory. Combined with a preset operation evaluation rule library, the first aid operation quality score is determined through a preset quality evaluation model; personalized operation prompts and improvement strategies are adaptively generated according to the first aid operation quality score, wherein the preset quality evaluation model is constructed based on a machine learning algorithm.

[0011] In an optional embodiment,

[0012] The method further comprises:

[0013] According to the nonlinear, anisotropic and incompressible mechanical characteristics of human soft tissue, a high-order hyperelastic constitutive model is used to set the material parameters of the first aid simulation discretization model, and the nonlinear control equation of soft tissue deformation is established. The finite element method is used to spatially discretize the nonlinear control equation to obtain the deformation response of the first aid simulation discretization model under the action of external force.

[0014] In an optional embodiment,

[0015] The tomographic data of key parts of the human body are collected by medical imaging equipment, the contour information of soft tissue is extracted from the tomographic data by medical image processing technology, and a triangular patch mesh model of the soft tissue is generated by a three-dimensional reconstruction algorithm. The triangular patch mesh model of the soft tissue is tetrahedronized, and an adaptive mesh encryption strategy and a mesh smoothing algorithm are used to generate a discretized model suitable for emergency simulation, including:

[0016] Use medical imaging equipment to perform tomography on the target organ to obtain a series of two-dimensional tomographic images;

[0017] Preprocessing and segmenting the two-dimensional tomographic image, using image enhancement technology to improve the image contrast and signal-to-noise ratio, and combining a threshold segmentation algorithm to extract two-dimensional contour information of the soft tissue region of interest;

[0018] According to the two-dimensional contour information, the contours in adjacent tomographic images are triangulated using the Marching Cubes algorithm to generate a triangulated mesh model of the soft tissue;

[0019] The triangular patch mesh model is optimized and subdivided, and the irregular boundaries of the surface of the triangular patch mesh model are eliminated by using a Laplace smoothing algorithm; the optimized triangular patch mesh model is converted into a volume mesh model, and a tetrahedral mesh inside the soft tissue is generated according to the shape and topology of the volume mesh model by using a tetrahedral partitioning algorithm as a discretization model for first aid simulation.

[0020] In an optional embodiment,

[0021] A collision detection algorithm is used to detect the contact state between the user's hand and the first aid simulation discretization model in real time, and the virtual finger is modeled as a mass-spring system with stiffness and damping. According to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time, including:

[0022] The motion capture device collects the 3D position and posture information of the user's hand in real time to obtain the motion data of the virtual finger; the virtual finger is divided into bounding boxes, and a bounding box tree is constructed. By traversing the bounding box tree, areas where collision is unlikely to occur are excluded, and the calculation range of collision detection is narrowed to local leaf nodes;

[0023] Precalculate and store the distance field of the soft tissue surface to obtain the distance field voxel grid. During collision detection, map the vertices of the virtual finger to the distance field voxel grid. Use trilinear interpolation to obtain the directed distance from the vertex to the distance field voxel grid. If the distance is less than a given distance threshold, it is determined that a collision occurs.

[0024] The virtual finger is abstracted into a discretized model consisting of mass points and springs. By adjusting the mass of the mass points, the stiffness and damping coefficient of the springs, virtual fingers of different materials and shapes can be simulated.

[0025] After a collision is detected, a position-based dynamics method is used to iteratively optimize the position of the virtual finger mass to satisfy the collision constraint and spring constraint, and calculate the tactile feedback force at each contact point;

[0026] The magnitude and direction of the friction force at each contact point are calculated according to Coulomb's friction law, the sliding and viscosity effects between the finger and the soft tissue surface are simulated, and the changes in the surface normal and curvature caused by the deformation of the soft tissue are incorporated into the calculation of the feedback force.

[0027] In an optional embodiment,

[0028] The position-based dynamics method is used to iteratively optimize the position of the virtual finger mass point to satisfy the collision constraint and spring constraint. The tactile feedback force at each contact point is calculated, including:

[0029] The virtual finger is modeled as a discretized model consisting of mass points and springs. The mass points represent the joints and surface feature points of the finger, and the springs represent the elastic connections between the mass points.

[0030] The soft tissue is voxelized and segmented to obtain a uniform hexahedral mesh, where each voxel contains material properties and stress-strain relationships;

[0031] In the collision detection phase, it is determined whether the mass point of the virtual finger is in contact with the soft tissue surface, and the local deformation of the soft tissue at the collision point is calculated;

[0032] According to the deformation at the collision point and the motion state of the virtual finger mass point, a group of dynamic equations based on position is established to solve the displacement and velocity of the mass point;

[0033] According to the estimated position of the virtual finger mass point, the penetration depth between the virtual finger mass point and the soft tissue surface is calculated, and the penetration depth is introduced into the dynamic equations as a position constraint;

[0034] According to the initial length and stiffness coefficient of the virtual finger spring, the elastic displacement of the spring is calculated, and the elastic displacement is introduced into the dynamic equations as an internal force constraint;

[0035] By solving the dynamic equations through iterative optimization, the position and velocity of the virtual finger mass are updated while satisfying the collision constraint and spring constraint;

[0036] According to the displacement and velocity of the virtual finger mass point, the interaction force exerted on the soft tissue is calculated. The interaction force includes the normal pressure along the surface normal direction and the friction force along the tangential direction.

[0037] The calculated interaction force is reacted to the voxel nodes corresponding to the soft tissue surface, causing deformation and stress redistribution of the soft tissue;

[0038] The interaction force between the virtual finger and soft tissue is calculated and updated in real time until the user stops the operation or the preset simulation time is reached.

[0039] In an optional embodiment,

[0040] The operation features corresponding to the user's hand when a collision event occurs are extracted. The operation features include the operation position, operation speed, operation force and operation trajectory. Combined with the preset operation evaluation rule library, the first aid operation quality score is determined through the preset quality evaluation model, including:

[0041] During virtual first aid training, the collision event between the user's hand and the virtual soft tissue is detected in real time, and the timestamp and duration of the collision are recorded;

[0042] Extract the three-dimensional coordinates of the virtual finger mass point in the collision event, map it to the local coordinate system of the virtual soft tissue, and obtain the operation position characteristics relative to the soft tissue surface;

[0043] According to the position change and time difference of the virtual finger mass point at the beginning and end of the collision event, the operation speed characteristics, including the speed magnitude and direction, are calculated;

[0044] The collision penalty force is calculated by the penetration depth and contact speed of the virtual finger mass point and the soft tissue. At the same time, the spring force is calculated according to the elastic displacement and damping coefficient of the virtual finger mass point. The two are superimposed to obtain the operation force characteristics.

[0045] During the collision event, the three-dimensional coordinate sequence of the virtual finger mass point is recorded at a fixed sampling frequency, and smoothed and interpolated to obtain a continuous operation trajectory characteristic curve;

[0046] The extracted operation position features, operation speed features, operation force features and operation trajectory features are input into the pre-trained quality assessment model. The model is trained on expert demonstration operations and operation sample data of users of different levels using a supervised learning algorithm to establish a mapping relationship between operation features and operation quality scores.

[0047] The quality assessment model calculates the quality score of the current operation in real time based on the input information.

[0048] According to a second aspect of the embodiments of the present invention,

[0049] Provides a system for analyzing the effectiveness of first aid based on simulators, including:

[0050] The first unit is used to collect tomographic data of key parts of the human body using medical imaging equipment, extract contour information of soft tissue from the tomographic data using medical image processing technology, generate a triangular patch mesh model of the soft tissue using a three-dimensional reconstruction algorithm, tetrahedralize the triangular patch mesh model of the soft tissue, and use an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation;

[0051] The second unit is used to use a collision detection algorithm to detect the contact state between the user's hand and the first aid simulation discretization model in real time, model the virtual finger as a mass-spring system with stiffness and damping, and calculate the multi-point tactile feedback force in real time according to the contact state between the virtual finger and the soft tissue surface using a position-based dynamics method. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform;

[0052] The third unit is used to extract the operation features corresponding to the user's hand when a collision event occurs, wherein the operation features include operation position, operation speed, operation force and operation trajectory, and determine the first aid operation quality score through a preset quality assessment model in combination with a preset operation evaluation rule library; and adaptively generate personalized operation prompts and improvement strategies based on the first aid operation quality score, wherein the preset quality assessment model is constructed based on a machine learning algorithm.

[0053] According to a third aspect of the embodiments of the present invention,

[0054] An electronic device is provided, comprising:

[0055] processor;

[0056] a memory for storing processor-executable instructions;

[0057] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0058] A fourth aspect of the embodiments of the present invention is:

[0059] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0060] By collecting human tomography data through medical imaging equipment, and applying medical image processing and 3D reconstruction technology, a high-precision, high-fidelity discretized model of human soft tissue is generated, which provides an anatomically accurate virtual environment for emergency simulation training and improves the authenticity and effectiveness of training. The soft tissue model is optimized using an adaptive mesh encryption strategy and mesh smoothing algorithm to generate a discretized model suitable for real-time simulation, taking into account both computational efficiency and model quality, and ensuring the fluency and stability of simulation training.

[0061] The position-based dynamics method is introduced to calculate the multi-point tactile feedback force between the virtual fingers and soft tissue in real time, and the collision detection algorithm is combined to drive the deformation of the soft tissue, realizing realistic force tactile interaction and tissue response, and enhancing the immersion and sense of substitution of simulation training. The user's hand operation characteristics, including position, speed, strength and trajectory, are extracted, combined with the preset operation evaluation rule library and the quality evaluation model based on machine learning, to evaluate the user's first aid operation quality in real time, provide users with objective and accurate feedback and guidance, and help users find deficiencies in time and make improvements.

[0062] Based on the user's first aid operation quality score, personalized operation prompts and improvement strategies are adaptively generated to provide targeted learning guidance for users of different levels, thereby improving the efficiency and pertinence of first aid skills training. BRIEF DESCRIPTION OF THE DRAWINGS

[0063] Figure 1 It is a flowchart of a method for analyzing first aid effectiveness based on a simulated person according to an embodiment of the present invention;

[0064] Figure 2 It is a structural schematic diagram of a system for analyzing first aid effectiveness based on a simulated person according to an embodiment of the present invention. DETAILED DESCRIPTION

[0065] In order to make the purpose, technical solution and advantages of the embodiments of the present invention clearer, the technical solution in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.

[0066] The technical solution of the present invention is described in detail with specific embodiments below. The following specific embodiments can be combined with each other, and the same or similar concepts or processes may not be described in detail in some embodiments.

[0067] Figure 1 FIG. 1 is a flow chart of a method for analyzing the effectiveness of first aid based on a simulated person according to an embodiment of the present invention. Figure 1 As shown, the method includes:

[0068] S101. Collect tomographic data of key parts of the human body using medical imaging equipment, extract contour information of soft tissue from the tomographic data using medical image processing technology, generate a triangular patch mesh model of the soft tissue using a three-dimensional reconstruction algorithm, perform tetrahedral decomposition on the triangular patch mesh model of the soft tissue, and use an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation;

[0069] S102. Using a collision detection algorithm, the contact state between the user's hand and the first aid simulation discretization model is detected in real time, the virtual finger is modeled as a mass-spring system with stiffness and damping, and according to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform;

[0070] S103. Extract the operation features corresponding to the user's hand when a collision event occurs, wherein the operation features include operation position, operation speed, operation force and operation trajectory, and determine the first aid operation quality score through a preset quality assessment model in combination with a preset operation assessment rule library; adaptively generate personalized operation prompts and improvement strategies based on the first aid operation quality score, wherein the preset quality assessment model is constructed based on a machine learning algorithm.

[0071] By collecting human tomography data through medical imaging equipment, and applying medical image processing and 3D reconstruction technology, a high-precision, high-fidelity discretized model of human soft tissue is generated, which provides an anatomically accurate virtual environment for emergency simulation training and improves the authenticity and effectiveness of training. The soft tissue model is optimized using an adaptive mesh encryption strategy and mesh smoothing algorithm to generate a discretized model suitable for real-time simulation, taking into account both computational efficiency and model quality, and ensuring the fluency and stability of simulation training.

[0072] The position-based dynamics method is introduced to calculate the multi-point tactile feedback force between the virtual fingers and soft tissue in real time, and the collision detection algorithm is combined to drive the deformation of the soft tissue, realizing realistic force tactile interaction and tissue response, and enhancing the immersion and sense of substitution of simulation training. The user's hand operation characteristics, including position, speed, strength and trajectory, are extracted, combined with the preset operation evaluation rule library and the quality evaluation model based on machine learning, to evaluate the user's first aid operation quality in real time, provide users with objective and accurate feedback and guidance, and help users find deficiencies in time and make improvements.

[0073] Based on the user's first aid operation quality score, personalized operation prompts and improvement strategies are adaptively generated to provide targeted learning guidance for users of different levels, thereby improving the efficiency and pertinence of first aid skills training.

[0074] In an optional embodiment,

[0075] The method further comprises:

[0076] According to the nonlinear, anisotropic and incompressible mechanical characteristics of human soft tissue, a high-order hyperelastic constitutive model is used to set the material parameters of the first aid simulation discretization model, and the nonlinear control equation of soft tissue deformation is established. The finite element method is used to spatially discretize the nonlinear control equation to obtain the deformation response of the first aid simulation discretization model under the action of external force.

[0077] Exemplarily, for the nonlinear mechanical properties of human soft tissue, a high-order hyperelastic constitutive model is selected to describe the stress-strain relationship of soft tissue. Commonly used high-order hyperelastic constitutive models include Ogden model, Mooney-Rivlin model, Yeoh model, etc. Taking the Ogden model as an example, its strain energy function is composed of principal stretch ratio, volume ratio and material parameters, which is used to characterize the nonlinear and incompressible characteristics of soft tissue.

[0078] According to the literature or experimental test data, the material parameters of the selected high-order hyperelastic constitutive model are determined. The material parameters are fitted using an optimization algorithm (such as genetic algorithm, particle swarm algorithm, etc.) so that the prediction results of the constitutive model are consistent with the experimental data.

[0079] Based on the high-order hyperelastic constitutive model, the nonlinear control equation of soft tissue deformation is established. The equilibrium equation and constitutive equation of soft tissue deformation are derived by using the virtual work principle or the minimum potential energy principle to form a set of nonlinear partial differential equations. Taking the virtual work principle as an example, the control equation of soft tissue deformation takes into account factors such as strain, stress, displacement, body force and surface force, and describes the mechanical equilibrium relationship in the soft tissue deformation process.

[0080] The nonlinear control equations are spatially discretized using the finite element method. The soft tissue area is divided into tetrahedral unit grids, and the displacement field inside the unit is approximated by selecting appropriate interpolation functions (such as linear interpolation, quadratic interpolation, etc.). Using the Galerkin method, the nonlinear control equations are transformed into a set of nonlinear algebraic equations, in which the stiffness matrix is ​​nonlinearly related to the displacement field, and the external force load vector reflects the force condition of the soft tissue.

[0081] Solve the nonlinear algebraic equations to obtain the displacement field and stress-strain distribution of soft tissue deformation. Commonly used nonlinear solution methods include Newton-Raphson iteration method, modified Newton-Raphson iteration method, arc length method, etc. Considering the large deformation and large rotation characteristics of soft tissue deformation, the total Lagrangian method or updated Lagrangian method is used to deal with nonlinear geometric effects.

[0082] The solved displacement field is applied to the nodes of the first aid simulation discretization model to update the coordinates of the soft tissue surface and body mesh to realize the deformation response of the soft tissue under the action of external force. At the same time, according to the stress-strain distribution, the physical quantities such as strain energy, stress-strain and so on in the soft tissue deformation process are calculated for subsequent collision detection, tactile feedback and quality assessment.

[0083] In order to improve the computational efficiency of soft tissue deformation response, numerical techniques such as reduced integration, hourglass control, and mass reduction can be used to reduce the number of unit integration points, suppress zero-energy modes, and simplify the mass matrix. In addition, GPU parallel computing and preprocessing techniques can be used to accelerate the nonlinear finite element solution process and realize real-time interactive simulation of soft tissue deformation.

[0084] Through the above technical solutions, the nonlinear deformation behavior of human soft tissue under external force can be accurately and efficiently simulated, providing realistic visual and force feedback for emergency simulation training, and improving the authenticity and effectiveness of training. At the same time, the physical quantity of soft tissue deformation response also provides an important basis for operation quality evaluation, which helps to realize intelligent skill evaluation and personalized guidance.

[0085] In an optional embodiment,

[0086] The tomographic data of key parts of the human body are collected by medical imaging equipment, the contour information of soft tissue is extracted from the tomographic data by medical image processing technology, and a triangular patch mesh model of the soft tissue is generated by a three-dimensional reconstruction algorithm. The triangular patch mesh model of the soft tissue is tetrahedronized, and an adaptive mesh encryption strategy and a mesh smoothing algorithm are used to generate a discretized model suitable for emergency simulation, including:

[0087] Use medical imaging equipment to perform tomography on the target organ to obtain a series of two-dimensional tomographic images;

[0088] Preprocessing and segmenting the two-dimensional tomographic image, using image enhancement technology to improve the image contrast and signal-to-noise ratio, and combining a threshold segmentation algorithm to extract two-dimensional contour information of the soft tissue region of interest;

[0089] According to the two-dimensional contour information, the contours in adjacent tomographic images are triangulated using the Marching Cubes algorithm to generate a triangulated mesh model of the soft tissue;

[0090] The triangular patch mesh model is optimized and subdivided, and the irregular boundaries of the surface of the triangular patch mesh model are eliminated by using a Laplace smoothing algorithm; the optimized triangular patch mesh model is converted into a volume mesh model, and a tetrahedral mesh inside the soft tissue is generated according to the shape and topology of the volume mesh model by using a tetrahedral partitioning algorithm as a discretization model for first aid simulation.

[0091] For example, a medical imaging device (such as CT, MRI, etc.) is used to perform a tomographic scan on a target organ (such as the heart, liver, etc.) to obtain a series of two-dimensional tomographic images. During the scanning process, appropriate scanning parameters (such as layer thickness, layer spacing, resolution, etc.) are selected to ensure image quality and data integrity.

[0092] The obtained two-dimensional tomographic images are preprocessed and segmented. First, image enhancement techniques (such as histogram equalization, median filtering, etc.) are used to improve the image contrast and signal-to-noise ratio, highlighting the edges and details of soft tissue. Then, the two-dimensional contour information of the soft tissue region of interest is extracted by combining the threshold segmentation algorithm (such as Otsu threshold method, region growing method, etc.). According to the gray value range and morphological characteristics of the soft tissue, the optimal threshold or seed point is determined to achieve automatic segmentation of soft tissue and background.

[0093] According to the extracted two-dimensional contour information, the Marching Cubes algorithm is used to triangulate the contours in adjacent tomographic images to generate a triangular mesh model of soft tissue. The Marching Cubes algorithm traverses the voxels in adjacent tomographic images, determines the topological relationship of the isosurface according to the grayscale value of the voxel vertices, generates local triangular patches, and finally constructs a complete three-dimensional surface mesh model.

[0094] The generated triangular mesh model is optimized and subdivided. The Laplace smoothing algorithm is used to eliminate irregular boundaries and jagged noise on the surface of the triangular mesh model. Laplace smoothing makes the mesh surface smooth and uniform by iteratively moving mesh vertices to the average position of adjacent vertices. At the same time, according to the curvature and detail features of the mesh model, the triangular facets are adaptively subdivided to increase the mesh density and improve the accuracy and authenticity of the model.

[0095] The optimized triangular mesh model is converted into a volume mesh model. According to the shape and topological relationship of the triangular mesh model, a tetrahedral mesh inside the soft tissue is generated using a tetrahedral partitioning algorithm. Commonly used tetrahedral partitioning algorithms include Delaunay tetrahedralization, advancing front method, eight-tree method, etc. During the tetrahedral partitioning process, the mesh density and unit size are adaptively adjusted according to the mesh quality criteria (such as minimum dihedral angle, volume ratio, etc.) to ensure that the generated tetrahedral mesh has good shape and numerical stability.

[0096] Perform quality assessment and optimization on the generated tetrahedral mesh model. Calculate the quality indicators of tetrahedral elements (such as condition number, distortion, etc.), identify and delete low-quality elements. Use mesh smoothing algorithms (such as Laplacian smoothing, optimized smoothing, etc.) to improve the quality of tetrahedral meshes and improve the regularity and orthogonality of elements. If necessary, re-divide or refine the mesh in local areas to meet the accuracy requirements of numerical simulation.

[0097] The optimized tetrahedral mesh model is used as a discretization model for emergency simulation and subsequent physical modeling and numerical simulation. According to the node coordinates and unit topology of the tetrahedral mesh, the material properties, boundary conditions and load conditions of the soft tissue are defined, and the finite element equations are constructed. The dynamic response of the soft tissue under external force is solved by explicit or implicit time integration method to obtain physical field quantities such as deformation, stress and strain.

[0098] Through the above technical solution, a high-precision and high-fidelity discretized model of human soft tissue can be constructed from medical imaging data through a series of steps such as image processing, 3D reconstruction, and mesh generation. This model can not only accurately describe the anatomical structure and morphological characteristics of soft tissue, but also reflect the mechanical properties and deformation behavior of soft tissue, providing a reliable physical basis and data support for emergency simulation training.

[0099] In an optional embodiment,

[0100] A collision detection algorithm is used to detect the contact state between the user's hand and the first aid simulation discretization model in real time, and the virtual finger is modeled as a mass-spring system with stiffness and damping. According to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time, including:

[0101] The motion capture device collects the 3D position and posture information of the user's hand in real time to obtain the motion data of the virtual finger; the virtual finger is divided into bounding boxes, and a bounding box tree is constructed. By traversing the bounding box tree, areas where collision is unlikely to occur are excluded, and the calculation range of collision detection is narrowed to local leaf nodes;

[0102] Precalculate and store the distance field of the soft tissue surface to obtain the distance field voxel grid. During collision detection, map the vertices of the virtual finger to the distance field voxel grid. Use trilinear interpolation to obtain the directed distance from the vertex to the distance field voxel grid. If the distance is less than a given distance threshold, it is determined that a collision occurs.

[0103] The virtual finger is abstracted into a discretized model consisting of mass points and springs. By adjusting the mass of the mass points, the stiffness and damping coefficient of the springs, virtual fingers of different materials and shapes can be simulated.

[0104] After a collision is detected, a position-based dynamics method is used to iteratively optimize the position of the virtual finger mass to satisfy the collision constraint and spring constraint, and calculate the tactile feedback force at each contact point;

[0105] The magnitude and direction of the friction force at each contact point are calculated according to Coulomb's friction law, the sliding and viscosity effects between the finger and the soft tissue surface are simulated, and the changes in the surface normal and curvature caused by the deformation of the soft tissue are incorporated into the calculation of the feedback force.

[0106] For example, the three-dimensional position and posture information of the user's hand is collected in real time through a motion capture device (such as a data glove, an optical tracking system, etc.) to obtain the motion data of the virtual finger, and the virtual finger is mapped to the virtual environment so that it is synchronized with the user's hand movement.

[0107] The bounding box of the virtual finger is divided into hierarchical levels to build a bounding box tree. Using methods such as AABB (Axis-Aligned Bounding Box) or OBB (Oriented Bounding Box), the virtual finger is recursively divided into multiple levels of bounding boxes according to its geometric shape and spatial distribution. During collision detection, by traversing the bounding box tree and using the intersection test between bounding boxes, the area where collision is unlikely to occur is quickly excluded, and the calculation range of collision detection is narrowed to local leaf nodes, thereby improving detection efficiency.

[0108] Pre-calculate and store the distance field of the soft tissue surface. Use algorithms such as Fast Marching Method or Distance Transform to calculate the shortest distance from each vertex to other vertices on the soft tissue surface and generate a distance field voxel grid. During collision detection, map the vertices of the virtual finger to the distance field voxel grid, and obtain the directed distance from the vertex to the soft tissue surface through trilinear interpolation. If the distance is less than the given distance threshold, it is determined that the vertex collides with the soft tissue.

[0109] The virtual finger is abstracted into a discretized model consisting of mass points and springs. According to the geometric shape and topological structure of the virtual finger, it is discretized into multiple mass points, which are connected by springs. By adjusting the mass of the mass point, the stiffness of the spring and the damping coefficient, virtual fingers of different materials and shapes can be simulated. The movement of the mass point is affected by the spring force, damping force and external force, and the position and velocity of the mass point are updated by numerical integration methods (such as explicit Euler method, implicit Euler method, etc.).

[0110] After detecting the collision between the virtual finger and the soft tissue, the position-based dynamic method is used to calculate the tactile feedback force. The mass point position of the virtual finger is iteratively optimized to satisfy the collision constraint and spring constraint. The collision constraint ensures that the virtual finger does not penetrate the soft tissue surface, and the spring constraint maintains the shape and mechanical properties of the virtual finger. At each contact point, the normal feedback force and tangential friction force are calculated based on the relative position and velocity of the virtual finger and the soft tissue. The normal feedback force is related to the penetration depth and contact stiffness, and the tangential friction force is calculated according to the Coulomb friction law.

[0111] The changes in surface normal and curvature caused by soft tissue deformation are included in the calculation of feedback force. When the virtual finger contacts the soft tissue, the soft tissue will deform, resulting in changes in the surface normal and curvature at the contact point. The deformation of the soft tissue is simulated by the finite element method or the mass-spring method to obtain the surface normal and curvature information after deformation. This information is used to correct the normal feedback force at the contact point to adapt it to the deformed soft tissue surface and improve the realism of tactile feedback.

[0112] According to the calculated tactile feedback force, the tactile feedback device (such as force feedback gloves, tactile vibrators, etc.) is driven to provide tactile stimulation to the user. The feedback force is mapped to the degrees of freedom of the tactile feedback device, and the motor or vibration element is controlled to produce the corresponding force or vibration effect to simulate the touch feeling when the virtual finger contacts the soft tissue. At the same time, according to the contact state and material properties, audio feedback such as contact sound and friction sound can be added to enhance the multi-sensory immersion.

[0113] The above technical solutions can realize real-time collision detection and tactile feedback between virtual fingers and soft tissues. The collision detection is accelerated by hierarchical bounding boxes and distance fields to improve the computational efficiency; the deformation and force of virtual fingers are simulated by the mass-spring model and position-based dynamics method; the realism of tactile feedback is improved by considering the influence of soft tissue deformation on contact force. The comprehensive application of these technologies can provide users with a realistic and natural tactile interaction experience, and enhance the immersion and teaching effect of emergency simulation training.

[0114] In an optional embodiment,

[0115] The position-based dynamics method is used to iteratively optimize the position of the virtual finger mass point to satisfy the collision constraint and spring constraint. The tactile feedback force at each contact point is calculated, including:

[0116] The virtual finger is modeled as a discretized model consisting of mass points and springs. The mass points represent the joints and surface feature points of the finger, and the springs represent the elastic connections between the mass points.

[0117] The soft tissue is voxelized and segmented to obtain a uniform hexahedral mesh, where each voxel contains material properties and stress-strain relationships;

[0118] In the collision detection phase, it is determined whether the mass point of the virtual finger is in contact with the soft tissue surface, and the local deformation of the soft tissue at the collision point is calculated;

[0119] According to the deformation at the collision point and the motion state of the virtual finger mass point, a group of dynamic equations based on position is established to solve the displacement and velocity of the mass point;

[0120] According to the estimated position of the virtual finger mass point, the penetration depth between the virtual finger mass point and the soft tissue surface is calculated, and the penetration depth is introduced into the dynamic equations as a position constraint;

[0121] According to the initial length and stiffness coefficient of the virtual finger spring, the elastic displacement of the spring is calculated, and the elastic displacement is introduced into the dynamic equations as an internal force constraint;

[0122] By solving the dynamic equations through iterative optimization, the position and velocity of the virtual finger mass are updated while satisfying the collision constraint and spring constraint;

[0123] According to the displacement and velocity of the virtual finger mass point, the interaction force exerted on the soft tissue is calculated. The interaction force includes the normal pressure along the surface normal direction and the friction force along the tangential direction.

[0124] The calculated interaction force is reacted to the voxel nodes corresponding to the soft tissue surface, causing deformation and stress redistribution of the soft tissue;

[0125] The interaction force between the virtual finger and soft tissue is calculated and updated in real time until the user stops the operation or the preset simulation time is reached.

[0126] For example, the virtual finger is modeled as a discretized model consisting of mass points and springs. The mass points represent the joints and surface feature points of the finger and are used to describe the shape and motion state of the finger. The mass points are connected by springs, and the stiffness and damping coefficient of the springs determine the elasticity and damping characteristics of the finger. By adjusting the mass and position of the mass points and the parameters of the springs, virtual fingers of different shapes and materials can be simulated.

[0127] The soft tissue is voxelized and discretized into a uniform hexahedral grid. Each voxel contains material properties (such as density, Young's modulus, etc.) and stress-strain relationships (such as hyperelastic model, viscoelastic model, etc.). The physical model of soft tissue is established through the finite element method or the mass-spring method to calculate the deformation and stress distribution of soft tissue under external force.

[0128] In the collision detection stage, it is determined whether the virtual finger's mass point contacts the soft tissue surface. Acceleration algorithms such as hierarchical bounding box and distance field are used to quickly screen out mass points and voxels that may collide. For the contacting mass points, the depth and direction of their penetration into the soft tissue surface are calculated, and the local deformation of the soft tissue at the contact point is estimated based on the penetration depth.

[0129] According to the deformation at the collision point and the motion state of the virtual finger mass, a group of dynamic equations based on position is established. The group of dynamic equations includes the Newtonian motion equations of the mass and the Hooke's law of the spring, which describes the motion law of the mass under the action of external force and constraint force. The group of dynamic equations is solved by numerical integration methods (such as explicit Euler method, implicit Euler method, etc.) to obtain the displacement and velocity of the mass.

[0130] Based on the estimated position of the virtual finger mass point, the penetration depth between the virtual finger and the soft tissue surface is calculated. The penetration depth is introduced into the dynamic equations as a position constraint to ensure that the virtual finger does not over-penetrate the soft tissue. The product of the penetration depth and the contact stiffness can be used to calculate the normal contact force as an external constraint on the motion of the mass point.

[0131] According to the initial length and stiffness coefficient of the virtual finger spring, the elastic displacement of the spring is calculated. The elastic displacement is introduced into the dynamic equations as an internal force constraint to maintain the shape and mechanical properties of the virtual finger. The product of the elastic force and elastic displacement of the spring can be used to calculate the internal constraint force between the mass points at both ends of the spring.

[0132] The dynamic equations are solved by iterative optimization, and the position and velocity of the virtual finger mass are updated while satisfying the collision constraint and spring constraint. Common optimization algorithms include sequential quadratic programming (SQP) and Lagrange multiplier method. Through multiple iterations, the virtual finger reaches a balanced state under the action of external force and constraint force, and obtains a stable and realistic interaction effect.

[0133] According to the displacement and velocity of the virtual finger mass point, the interaction force exerted on the soft tissue is calculated. The interaction force includes the normal pressure along the surface normal direction and the friction force along the tangential direction. The normal pressure is related to the penetration depth and contact stiffness, and the friction force is calculated according to Coulomb's friction law and is proportional to the normal pressure and friction coefficient. The calculated interaction force is applied to the voxel node corresponding to the soft tissue surface, causing deformation and stress redistribution of the soft tissue.

[0134] The interaction force is applied as an external load to the physical model of the soft tissue, and the deformation response of the soft tissue is calculated by the finite element method or the mass-spring method. The deformation of the soft tissue will cause the surface normal and curvature to change, which will affect the collision detection and interaction force calculation of the next time step. By updating the shape and mechanical state of the soft tissue in real time, a two-way coupling interaction between the virtual finger and the soft tissue is achieved.

[0135] The interaction force between the virtual finger and the soft tissue is calculated and updated in real time until the user stops the operation or the preset simulation time is reached. During the interaction process, the parameters of collision detection, constraint solving and physical simulation are dynamically adjusted according to the movement of the virtual finger and the deformation of the soft tissue to balance the calculation efficiency and realism. At the same time, the calculated interaction force is fed back to the force feedback device, such as tactile gloves or tactile pens, so that users can get a real touch experience.

[0136] The above technical solution can realize realistic and stable interactive simulation between virtual fingers and soft tissues. The position-based dynamics method realizes bidirectional coupling between fingers and soft tissues by introducing collision constraints and spring constraints, while considering the deformation and motion state of virtual fingers, as well as the physical properties and deformation response of soft tissues. Iterative optimization solves the dynamics equations to ensure the natural movement and realistic touch of fingers under physical constraints. This technical solution is of great significance for improving the simulation quality and user experience in application fields such as medical surgery training and product design evaluation.

[0137] In an optional embodiment,

[0138] The operation features corresponding to the user's hand when a collision event occurs are extracted. The operation features include the operation position, operation speed, operation force and operation trajectory. Combined with the preset operation evaluation rule library, the first aid operation quality score is determined through the preset quality evaluation model, including:

[0139] During virtual first aid training, the collision event between the user's hand and the virtual soft tissue is detected in real time, and the timestamp and duration of the collision are recorded;

[0140] Extract the three-dimensional coordinates of the virtual finger mass point in the collision event, map it to the local coordinate system of the virtual soft tissue, and obtain the operation position characteristics relative to the soft tissue surface;

[0141] According to the position change and time difference of the virtual finger mass point at the beginning and end of the collision event, the operation speed characteristics, including the speed magnitude and direction, are calculated;

[0142] The collision penalty force is calculated by the penetration depth and contact speed of the virtual finger mass point and the soft tissue. At the same time, the spring force is calculated according to the elastic displacement and damping coefficient of the virtual finger mass point. The two are superimposed to obtain the operation force characteristics.

[0143] During the collision event, the three-dimensional coordinate sequence of the virtual finger mass point is recorded at a fixed sampling frequency, and smoothed and interpolated to obtain a continuous operation trajectory characteristic curve;

[0144] The extracted operation position features, operation speed features, operation force features and operation trajectory features are input into the pre-trained quality assessment model. The model is trained on expert demonstration operations and operation sample data of users of different levels using a supervised learning algorithm to establish a mapping relationship between operation features and operation quality scores.

[0145] The quality assessment model calculates the quality score of the current operation in real time based on the input information.

[0146] For example, during the virtual first aid training, the collision event between the user's hand (virtual finger) and the virtual soft tissue is detected in real time through the collision detection algorithm. When the collision is detected, the timestamp and duration of the collision are recorded for subsequent operation feature extraction and quality assessment.

[0147] The three-dimensional coordinates of the virtual finger mass point in the collision event are extracted and converted from the global coordinate system to the local coordinate system of the virtual soft tissue. By calculating the position of the virtual finger mass point relative to the soft tissue surface, the operation position feature is obtained, which represents the contact position and depth of the finger on the soft tissue.

[0148] The operation speed feature is calculated based on the position change and time difference of the virtual finger mass point at the beginning and end of the collision event. The change in the mass point position on the three coordinate axes is divided by the time difference to obtain the components of the speed in each direction, and then the magnitude and direction of the speed are calculated. The operation speed feature reflects the speed and direction of the user's hand movement.

[0149] The collision penalty force is calculated based on the penetration depth and contact speed between the virtual finger mass and the soft tissue. The greater the penetration depth and the faster the contact speed, the greater the penalty force, which is used to prevent the finger from excessively penetrating the soft tissue. At the same time, the spring force is calculated based on the elastic displacement (displacement relative to the initial position) and damping coefficient of the virtual finger mass. The greater the elastic displacement, the greater the spring force, which is used to maintain the shape and mechanical properties of the finger. The collision penalty force and the spring force are superimposed to obtain the operation force characteristics, which reflect the magnitude of the force applied by the user on the soft tissue.

[0150] During the collision event, the 3D coordinate sequence of the virtual finger mass point is recorded at a fixed sampling frequency (e.g., 30 times per second). The acquired coordinate sequence is smoothed to remove high-frequency noise and jitter, and a continuous trajectory curve is generated between the sampling points through an interpolation algorithm (e.g., spline interpolation). The smoothed and interpolated coordinate sequence constitutes the operation trajectory feature, reflecting the path and continuity of the user's hand movement.

[0151] The extracted operation position features, operation speed features, operation force features, and operation trajectory features are input into the pre-trained quality assessment model. The model uses supervised learning algorithms, such as support vector machine (SVM) and random forest, to train sample data of expert demonstration operations and user operations of different levels. By establishing a mapping relationship between operation features and operation quality scores given by experts, the association between different operation feature combinations and operation quality is learned.

[0152] The quality assessment model calculates the quality score of the current operation in real time based on the input operation characteristics. The score can be a continuous value (such as 0-100 points) or a discrete level (such as excellent, good, qualified, unqualified). The score reflects the similarity and quality level between the user operation and the standard operation, and can be used to provide timely feedback and guide users to improve their operations.

[0153] In order to improve the accuracy and robustness of quality assessment, multiple evaluation indicators can be introduced, such as operation completion time, operation accuracy, operation smoothness, etc., and the scores of different indicators can be weighted and combined to obtain a comprehensive quality score. At the same time, through cross-validation, data enhancement and other technologies, the generalization ability and adaptability of the quality assessment model can be improved so that it can meet the evaluation needs of different users and different operation scenarios.

[0154] In virtual first aid training, the quality assessment results are displayed in real time, and visual, auditory and other feedback methods are combined to guide users to optimize operations. For example, visual elements such as color coding and progress bars can be used to intuitively display the quality of operations; voice prompts and warning sounds can be used to remind users to pay attention to key steps and common errors in operations. Multimodal feedback helps to enhance users' operational awareness and learning effects.

[0155] After the training, a detailed quality assessment report is generated, including the scores of various indicators of the operation, comparative analysis with standard operations, and summary of advantages and disadvantages. The report can help users comprehensively review their own operation performance, identify areas that need improvement, and provide references and goals for the next training. Through continuous training and assessment, users can gradually improve the quality of their operations and reach a standardized and proficient level.

[0156] The above technical solution realizes the automatic evaluation and feedback of virtual first aid operations by extracting user operation features in real time and combining it with a pre-trained quality assessment model. The solution integrates collision detection, feature extraction, machine learning and other technologies, and can comprehensively evaluate key factors such as the position, speed, strength and trajectory of the operation, providing users with objective and accurate quality evaluation. At the same time, through multimodal feedback and detailed reports, it helps users intuitively understand the operation performance, improve training in a targeted manner, and improve learning efficiency and effectiveness. This technical solution is of great value in improving the intelligence level and teaching quality of virtual first aid training.

[0157] Figure 2 FIG. 1 is a schematic diagram of a system for analyzing the effectiveness of first aid based on a simulated person according to an embodiment of the present invention. Figure 2 As shown, the system comprises:

[0158] The first unit is used to collect tomographic data of key parts of the human body using medical imaging equipment, extract contour information of soft tissue from the tomographic data using medical image processing technology, generate a triangular patch mesh model of the soft tissue using a three-dimensional reconstruction algorithm, tetrahedralize the triangular patch mesh model of the soft tissue, and use an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation;

[0159] The second unit is used to use a collision detection algorithm to detect the contact state between the user's hand and the first aid simulation discretization model in real time, model the virtual finger as a mass-spring system with stiffness and damping, and calculate the multi-point tactile feedback force in real time according to the contact state between the virtual finger and the soft tissue surface using a position-based dynamics method. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform;

[0160] The third unit is used to extract the operation features corresponding to the user's hand when a collision event occurs, wherein the operation features include operation position, operation speed, operation force and operation trajectory, and determine the first aid operation quality score through a preset quality assessment model in combination with a preset operation evaluation rule library; and adaptively generate personalized operation prompts and improvement strategies based on the first aid operation quality score, wherein the preset quality assessment model is constructed based on a machine learning algorithm.

[0161] According to a third aspect of the embodiments of the present invention,

[0162] An electronic device is provided, comprising:

[0163] processor;

[0164] a memory for storing processor-executable instructions;

[0165] The processor is configured to call the instructions stored in the memory to execute the aforementioned method.

[0166] A fourth aspect of the embodiments of the present invention is:

[0167] A computer-readable storage medium is provided, on which computer program instructions are stored. When the computer program instructions are executed by a processor, the aforementioned method is implemented.

[0168] The present invention may be a method, an apparatus, a system and / or a computer program product. The computer program product may include a computer-readable storage medium carrying computer-readable program instructions for executing various aspects of the present invention.

[0169] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention, rather than to limit it. Although the present invention 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 replace some or all of the technical features therein with equivalents. However, these modifications or replacements do not cause the essence of the corresponding technical solutions to deviate from the scope of the technical solutions of the embodiments of the present invention.

Claims

1. A method for analyzing the effectiveness of first aid based on a simulated person, characterized in that: include: Using medical imaging equipment to collect tomographic data of key parts of the human body, extracting contour information of soft tissue from the tomographic data through medical image processing technology, and using a three-dimensional reconstruction algorithm to generate a triangular patch mesh model of the soft tissue, tetrahedralizing the triangular patch mesh model of the soft tissue, and using an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation; A collision detection algorithm is used to detect the contact state between the user's hand and the first aid simulation discretization model in real time, and a virtual finger is modeled as a mass-spring system with stiffness and damping. According to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform. The operation features corresponding to the user's hand when a collision event occurs are extracted, and the operation features include operation position, operation speed, operation force and operation trajectory. Combined with a preset operation evaluation rule library, the first aid operation quality score is determined through a preset quality evaluation model; personalized operation prompts and improvement strategies are adaptively generated according to the first aid operation quality score, wherein the preset quality evaluation model is constructed based on a machine learning algorithm.

2. The method according to claim 1, characterized in that The method further comprises: According to the nonlinear, anisotropic and incompressible mechanical characteristics of human soft tissue, a high-order hyperelastic constitutive model is used to set the material parameters of the first aid simulation discretization model, and the nonlinear control equation of soft tissue deformation is established. The finite element method is used to spatially discretize the nonlinear control equation to obtain the deformation response of the first aid simulation discretization model under the action of external force.

3. The method according to claim 1, characterized in that The tomographic data of key parts of the human body are collected by medical imaging equipment, the contour information of soft tissue is extracted from the tomographic data by medical image processing technology, and a triangular patch mesh model of the soft tissue is generated by a three-dimensional reconstruction algorithm. The triangular patch mesh model of the soft tissue is tetrahedronized, and an adaptive mesh encryption strategy and a mesh smoothing algorithm are used to generate a discretized model suitable for emergency simulation, including: Use medical imaging equipment to perform tomography on the target organ to obtain a series of two-dimensional tomographic images; Preprocessing and segmenting the two-dimensional tomographic image, using image enhancement technology to improve the image contrast and signal-to-noise ratio, and combining a threshold segmentation algorithm to extract two-dimensional contour information of the soft tissue region of interest; According to the two-dimensional contour information, the contours in adjacent tomographic images are triangulated using the Marching Cubes algorithm to generate a triangulated mesh model of the soft tissue; The triangular patch mesh model is optimized and subdivided, and the irregular boundaries of the surface of the triangular patch mesh model are eliminated by using a Laplace smoothing algorithm; the optimized triangular patch mesh model is converted into a volume mesh model, and a tetrahedral mesh inside the soft tissue is generated according to the shape and topology of the volume mesh model by using a tetrahedral partitioning algorithm as a discretization model for first aid simulation.

4. The method according to claim 1, characterized in that A collision detection algorithm is used to detect the contact state between the user's hand and the first aid simulation discretization model in real time, and the virtual finger is modeled as a mass-spring system with stiffness and damping. According to the contact state between the virtual finger and the soft tissue surface, a position-based dynamic method is used to calculate the multi-point tactile feedback force in real time, including: The motion capture device collects the 3D position and posture information of the user's hand in real time to obtain the motion data of the virtual finger; the virtual finger is divided into bounding boxes, and a bounding box tree is constructed. By traversing the bounding box tree, areas where collision is unlikely to occur are excluded, and the calculation range of collision detection is narrowed to local leaf nodes; Precalculate and store the distance field of the soft tissue surface to obtain the distance field voxel grid. During collision detection, map the vertices of the virtual finger to the distance field voxel grid. Use trilinear interpolation to obtain the directed distance from the vertex to the distance field voxel grid. If the distance is less than a given distance threshold, it is determined that a collision occurs. The virtual finger is abstracted into a discretized model consisting of mass points and springs. By adjusting the mass of the mass points, the stiffness and damping coefficient of the springs, virtual fingers of different materials and shapes can be simulated. After a collision is detected, a position-based dynamics method is used to iteratively optimize the position of the virtual finger mass to satisfy the collision constraint and spring constraint, and calculate the tactile feedback force at each contact point; The magnitude and direction of the friction force at each contact point are calculated according to Coulomb's friction law, the sliding and viscosity effects between the finger and the soft tissue surface are simulated, and the changes in the surface normal and curvature caused by the deformation of the soft tissue are incorporated into the calculation of the feedback force.

5. The method according to claim 4, characterized in that The position-based dynamics method is used to iteratively optimize the position of the virtual finger mass point to satisfy the collision constraint and spring constraint. The tactile feedback force at each contact point is calculated, including: The virtual finger is modeled as a discretized model consisting of mass points and springs. The mass points represent the joints and surface feature points of the finger, and the springs represent the elastic connections between the mass points. The soft tissue is voxelized and segmented to obtain a uniform hexahedral mesh, where each voxel contains material properties and stress-strain relationships; In the collision detection phase, it is determined whether the mass point of the virtual finger is in contact with the soft tissue surface, and the local deformation of the soft tissue at the collision point is calculated; According to the deformation at the collision point and the motion state of the virtual finger mass point, a group of dynamic equations based on position is established to solve the displacement and velocity of the mass point; According to the estimated position of the virtual finger mass point, the penetration depth between the virtual finger mass point and the soft tissue surface is calculated, and the penetration depth is introduced into the dynamic equations as a position constraint; According to the initial length and stiffness coefficient of the virtual finger spring, the elastic displacement of the spring is calculated, and the elastic displacement is introduced into the dynamic equations as an internal force constraint; By solving the dynamic equations through iterative optimization, the position and velocity of the virtual finger mass are updated while satisfying the collision constraint and spring constraint; According to the displacement and velocity of the virtual finger mass point, the interaction force exerted on the soft tissue is calculated. The interaction force includes the normal pressure along the surface normal direction and the friction force along the tangential direction. The calculated interaction force is reacted to the voxel nodes corresponding to the soft tissue surface, causing deformation and stress redistribution of the soft tissue; The interaction force between the virtual finger and soft tissue is calculated and updated in real time until the user stops the operation or the preset simulation time is reached.

6. The method according to claim 1, characterized in that The operation features corresponding to the user's hand when a collision event occurs are extracted. The operation features include the operation position, operation speed, operation force and operation trajectory. Combined with the preset operation evaluation rule library, the first aid operation quality score is determined through the preset quality evaluation model, including: During virtual first aid training, the collision event between the user's hand and the virtual soft tissue is detected in real time, and the timestamp and duration of the collision are recorded; Extract the three-dimensional coordinates of the virtual finger mass point in the collision event, map it to the local coordinate system of the virtual soft tissue, and obtain the operation position characteristics relative to the soft tissue surface; According to the position change and time difference of the virtual finger mass point at the beginning and end of the collision event, the operation speed characteristics, including the speed magnitude and direction, are calculated; The collision penalty force is calculated by the penetration depth and contact speed of the virtual finger mass point and the soft tissue. At the same time, the spring force is calculated according to the elastic displacement and damping coefficient of the virtual finger mass point. The two are superimposed to obtain the operation force characteristics. During the collision event, the three-dimensional coordinate sequence of the virtual finger mass point is recorded at a fixed sampling frequency, and smoothed and interpolated to obtain a continuous operation trajectory characteristic curve; The extracted operation position features, operation speed features, operation force features and operation trajectory features are input into the pre-trained quality assessment model. The model is trained on expert demonstration operations and operation sample data of users of different levels using a supervised learning algorithm to establish a mapping relationship between operation features and operation quality scores. The quality assessment model calculates the quality score of the current operation in real time based on the input information.

7. A system for analyzing the effectiveness of first aid based on simulated human beings, used to implement the method according to any one of claims 1 to 6, characterized in that: include: The first unit is used to collect tomographic data of key parts of the human body using medical imaging equipment, extract contour information of soft tissue from the tomographic data using medical image processing technology, generate a triangular patch mesh model of the soft tissue using a three-dimensional reconstruction algorithm, tetrahedralize the triangular patch mesh model of the soft tissue, and use an adaptive mesh encryption strategy and a mesh smoothing algorithm to generate a discretized model suitable for emergency simulation; The second unit is used to use a collision detection algorithm to detect the contact state between the user's hand and the first aid simulation discretization model in real time, model the virtual finger as a mass-spring system with stiffness and damping, and calculate the multi-point tactile feedback force in real time according to the contact state between the virtual finger and the soft tissue surface using a position-based dynamics method. When a collision event is detected, the collision force is applied to the first aid simulation discretization model as a boundary condition to drive the soft tissue to deform; The third unit is used to extract the operation features corresponding to the user's hand when a collision event occurs, wherein the operation features include operation position, operation speed, operation force and operation trajectory, and determine the first aid operation quality score through a preset quality assessment model in combination with a preset operation evaluation rule library; and adaptively generate personalized operation prompts and improvement strategies based on the first aid operation quality score, wherein the preset quality assessment model is constructed based on a machine learning algorithm.

8. An electronic device, characterized in that: include: processor; a memory for storing processor-executable instructions; The processor is configured to call the instructions stored in the memory to execute the method according to any one of claims 1 to 6.

9. A computer-readable storage medium having computer program instructions stored thereon, characterized in that: When the computer program instructions are executed by a processor, the method according to any one of claims 1 to 6 is implemented.

Images