VR-based cardio-pulmonary resuscitation simulation system and method

Abstract

The invention relates to the technical field of electronic digital data processing, in particular to a cardio-pulmonary resuscitation simulation system and method based on VR (virtual reality), a hand data acquisition module is used for acquiring hand spatial position data generated when a student presses a dummy; the VR display module is used for displaying the cardio-pulmonary resuscitation teaching model and reading and displaying simulated human data and hand space position data at the same time; the feature extraction module is used for extracting a pressing feature value group based on the hand space position data; the deviation calculation module is used for calculating a deviation value based on the pressing characteristic value and the reference characteristic value; and the deviation visualization module is used for visualizing the deviation value and then displaying the deviation value in the VR display module in real time. Through a highly-simulated VR environment, trainees can practice CPR skills in an approximate real situation, and the actual combat ability is enhanced.

Description

Technical Field

[0001] The present invention relates to the technical field of electronic digital data processing, and in particular, to a VR-based cardiopulmonary resuscitation simulation system and method. Background Art

[0003] Cardiopulmonary Resuscitation (CPR) is a first aid technique used in cases of cardiac arrest, aiming to maintain blood circulation and respiratory function through artificial means to keep the oxygen supply to vital organs until more advanced medical care can be provided. CPR usually includes steps such as chest compressions, airway opening, and artificial respiration.

[0004] The existing cardiopulmonary resuscitation training methods mainly involve students pressing on a mannequin, and then the trainer will patrol among groups to provide immediate guidance and correct incorrect actions. In this way, the trainer has a relatively high work intensity during training, and at the same time, students are difficult to receive timely and effective guidance, reducing the training efficiency. Summary of the Invention

[0006] The purpose of the present invention is to provide a VR-based cardiopulmonary resuscitation simulation system and method, aiming to enable students to practice CPR skills in a nearly real scenario through a highly simulated VR environment, enhance practical combat capabilities, and improve training efficiency.

[0007] To achieve the above purpose, in the first aspect, the present invention provides a VR-based cardiopulmonary resuscitation simulation system, including a hand data acquisition module, a VR display module, a feature extraction module, a deviation calculation module, and a deviation visualization module; The hand data acquisition module is used to acquire the hand spatial position data generated by the student when pressing the mannequin; The VR display module is used to display the cardiopulmonary resuscitation teaching model, and at the same time read and display the mannequin data and the hand spatial position data; The feature extraction module is used to extract a set of pressing feature values based on the hand spatial position data; The deviation calculation module is used to calculate the deviation value based on the pressing feature value and the reference feature value; The deviation visualization module is used to visualize the deviation value and display it in real time on the VR display module.

[0008] Among them, the hand data acquisition module includes a wearable data detection unit, an initialization unit, a data collection unit, and a storage unit; The wearable data detection unit is used to be worn on the pressing part of the mannequin and is provided with a sensor array to acquire the hand spatial position data; The initialization unit is used to initialize the sensor array after the wearable data detection unit is installed; The data collection unit is used to generate hand spatial position data when the trainee presses the wearable data detection unit; The storage unit is used to store the generated hand spatial position data.

[0009] Among them, the wearable data detection unit includes a mounting band, an adjustment unit, and a sensor array. The adjustment unit is connected to the mounting band and is used to adjust the length of the mounting band. The mounting band is made of an elastic material, and the sensor array is arranged on the mounting band.

[0010] Among them, the VR display module includes a scene creation unit, a data conversion unit, a display unit, and a fixing unit: The scene creation unit is used to create a 3D teaching scene and import the installed virtual human data into the teaching scene; The data conversion unit is used to obtain the hand spatial position data and convert it to the 3D teaching scene to obtain a target scene; The display unit is used to display the target scene using VR technology; The fixing unit is used to fix the display unit to the position of the trainee's eyes.

[0011] Among them, the feature extraction module includes a noise processing unit, a time series synchronization unit, a feature setting unit, and a numerical calculation unit; the noise processing unit is used to remove the noise values in the hand spatial position data; The time series synchronization unit is used to align the position data of multiple sensors; The feature setting unit is used to set the extracted feature types, and the feature types include pressing depth, pressing speed, pressing area, pressing force, and repetition frequency; The numerical calculation unit is used to calculate specific values for each selected feature type to obtain a set of pressing feature values.

[0012] Among them, the time series synchronization unit includes a time reference system conversion subunit, an interpolation subunit, and a space reference system conversion subunit; The time reference system conversion subunit is used to convert the timestamps of all sensors to a common time reference system; The interpolation subunit is used to fill in the missing data points by linear interpolation so that all data has the same sampling frequency; The space reference system conversion subunit is used to convert all the obtained hand position data to a common coordinate system.

[0013] Among them, the deviation calculation module includes a reference value setting unit and a deviation calculation unit; The reference value setting unit is used to set reference characteristic values; The deviation calculation unit is used to calculate the deviation value of each selected characteristic one by one according to the absolute difference method.

[0014] Among them, the deviation visualization module includes a visual element setting unit, a data matching unit and a rendering unit; the visual element setting unit is used to set a variety of visualization data elements; The data matching unit is used to match the deviation values of each feature type with the visualization data elements to obtain target elements; The rendering unit is used to render the target elements into the target scene.

[0015] In a second aspect, the present invention also provides a VR-based cardiopulmonary resuscitation simulation method, including: Obtain the hand spatial position data generated by the trainee when pressing the simulation man; Display the cardiopulmonary resuscitation teaching model, and at the same time read and display the simulation man data and the hand spatial position data; Extract the pressing characteristic value group based on the hand spatial position data; Calculate the deviation value based on the pressing characteristic value and the reference characteristic value; Visualize the deviation value and display it in real time in the VR display module.

[0016] A VR-based cardiopulmonary resuscitation simulation system and method of the present invention, in which a hand data acquisition module captures high-precision hand spatial position data generated by a trainee during cardiopulmonary resuscitation pressing operations. It adopts advanced hand tracking technologies, such as optical tracking, inertial measurement units (IMUs), or electromagnetic induction, etc., to ensure the accuracy and stability of the data. The VR display module, as the core part of the user interface, not only reproduces a realistic cardiopulmonary resuscitation teaching scenario, but also includes a simulated human model and the changes in its internal physiological parameters. In addition, it also has the function of reading and synchronously displaying the status information of the simulated human (such as heart rate, blood pressure, etc.) and the hand movements of the trainee. The trainee enters the virtual world by wearing a VR headset, where they can see the interaction between their hands and the simulated human. This intuitive visual presentation helps to deepen understanding and memory. The feature extraction module is based on the hand spatial position data. The feature extraction module uses algorithms to identify and quantify the key attributes of each press, forming a set of pressing feature values. These features may cover multiple dimensions such as pressing depth, speed, area, angle, etc. The deviation calculation module receives the pressing feature values from the feature extraction module and compares them with predefined reference standards to calculate the actual deviation values of each feature. This step is crucial for evaluating the performance of the trainee. According to the deviation values, the system can generate personalized improvement suggestions for each trainee, pointing out the specific aspects that need to be strengthened in practice, and promoting the rapid improvement of skills. In order to enable the trainee to more clearly understand their operation deviations, the deviation visualization module converts the calculated deviation values into an easy-to-understand graphical representation and presents it in real time in the VR environment. The trainee can immediately see the differences between their pressing actions and the ideal state during the training process, such as in the form of color coding, arrow indication, or numerical labels, etc., so as to adjust their postures and techniques in a timely manner. Thus, through a highly simulated VR environment, the trainee can practice CPR skills in a situation close to the real one, enhancing their actual combat ability. Combining multiple sensing technologies and intelligent algorithms, the system can capture subtle movement changes and provide detailed performance evaluations. The immediately visible deviation visualization enables the trainee to quickly correct mistakes and improve learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] In order to more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the following will briefly introduce the drawings required for the description of the embodiments or the prior art. Obviously, the drawings in the following description are only some embodiments of the present invention. For those of ordinary skill in the art, without creative efforts, other drawings can also be obtained based on these drawings.

[0019] Figure 1 It is a structural diagram of a VR-based cardiopulmonary resuscitation simulation system of the present invention.

[0020] Figure 2 It is the structural diagram of the hand data acquisition module of the present invention.

[0021] Figure 3 It is the structural diagram of the wearable data detection unit of the present invention.

[0022] Figure 4 It is the structural diagram of the VR display module of the present invention.

[0023] Figure 5 It is the structural diagram of the feature extraction module of the present invention.

[0024] Figure 6 It is the structural diagram of the time series synchronization unit of the present invention.

[0025] Figure 7 It is the structural diagram of the deviation calculation module of the present invention.

[0026] Figure 8 It is the structural diagram of the deviation visualization module of the present invention.

[0027] Figure 9 It is the flowchart of a VR-based cardiopulmonary resuscitation simulation method of the present invention.

[0028] Hand data acquisition module 101, VR display module 102, feature extraction module 103, deviation calculation module 104, deviation visualization module 105, wearable data detection unit 106, initialization unit 107, data collection unit 108, storage unit 109, mounting belt 110, adjustment unit 111, sensor array 112, scene creation unit 113, data conversion unit 114, display unit 115, fixing unit 116, noise processing unit 117, time series synchronization unit 118, feature setting unit 119, numerical calculation unit 120, time reference system conversion sub-unit 121, interpolation sub-unit 122, space reference system conversion sub-unit 123, reference value setting unit 124, deviation calculation unit 125, visual element setting unit 126, data matching unit 127, rendering unit 128. Detailed implementation manners

[0030] The embodiments of the present invention will be described in detail below. The examples of the embodiments are shown in the accompanying drawings, where the same or similar reference numerals denote the same or similar elements or elements having the same or similar functions from beginning to end. The embodiments described below by referring to the accompanying drawings are exemplary and are intended to explain the present invention, and should not be construed as limiting the present invention.

[0031] First embodiment Please refer to Figures 1 to 8, the present invention provides a VR-based cardiopulmonary resuscitation simulation system, including a hand data acquisition module 101, a VR display module 102, a feature extraction module 103, a deviation calculation module 104, and a deviation visualization module 105; the hand data acquisition module 101 is used to acquire the hand spatial position data generated by the trainee when pressing the simulation manikin; the VR display module 102 is used to display the cardiopulmonary resuscitation teaching model, and at the same time read and display the manikin data and the hand spatial position data; the feature extraction module 103 is used to extract a set of pressing feature values based on the hand spatial position data; the deviation calculation module 104 is used to calculate the deviation value based on the pressing feature value and the reference feature value; the deviation visualization module 105 is used to visualize the deviation value and then display it in real time in the VR display module 102.

[0032] In this embodiment, the hand data acquisition module 101 captures the high-precision hand spatial position data generated by the trainee during the cardiopulmonary resuscitation pressing operation. It adopts advanced hand tracking technologies, such as optical tracking, inertial measurement units (IMUs), or electromagnetic induction, etc., to ensure the accuracy and stability of the data.

[0033] As the core part of the user interface, the VR display module 102 not only reproduces a realistic cardiopulmonary resuscitation teaching scene, but also includes the manikin model and the changes in its internal physiological parameters. In addition, it also has the function of reading and synchronously displaying the manikin status information (such as heart rate, blood pressure, etc.) and the trainee's hand movements. The trainee wears a VR headset to enter the virtual world, where they can see the interaction between their hands and the manikin. This intuitive visual presentation helps to deepen understanding and memory.

[0034] Based on the hand spatial position data, the feature extraction module 103 uses algorithms to identify and quantify the key attributes of each press, forming a set of pressing feature values. These features may cover multiple dimensions such as pressing depth, speed, area, angle, etc.

[0035] The deviation calculation module 104 receives the pressing feature values from the feature extraction module 103 and compares them with the predefined reference standards, thereby calculating the actual deviation value of each feature. This step is crucial for evaluating the performance of the trainee. According to the deviation value, the system can generate personalized improvement suggestions for each trainee, point out the specific aspects that need to be strengthened in practice, and promote the rapid improvement of skills.

[0036] To help trainees better understand their own operational deviations, the Deviation Visualization Module 105 converts the calculated deviation values into easy-to-understand graphical representations and presents them in real time within the VR environment. During training, trainees can immediately see the differences between their pressing movements and the ideal state, using color coding, arrow indicators, or numerical labels, allowing them to make timely adjustments to their posture and technique.

[0037] Through this approach, trainees can practice CPR techniques in a highly simulated VR environment, enhancing their practical skills. Combining multiple sensing technologies and intelligent algorithms, the system can capture subtle movements and provide detailed performance assessments. Immediately visible deviations allow trainees to quickly correct errors, improving learning efficiency.

[0038] The hand data acquisition module 101 includes a wearing data detection unit 106, an initialization unit 107, a data collection unit 108 and a storage unit 109; the wearing data detection unit 106 is used to be worn on the pressing part of the simulated person and is provided with a sensor array 112 to obtain hand spatial position data; the initialization unit 107 is used to initialize the sensor array 112 after the wearing data detection unit 106 is installed; the data collection unit 108 is used to generate hand spatial position data when the trainee presses the wearing data detection unit 106; the storage unit 109 is used to store the generated hand spatial position data.

[0039] The hand data acquisition module 101 is one of the core components of the cardiopulmonary resuscitation (CPR) simulation system, and is designed to accurately capture the spatial position data of the trainee's hands when performing compression operations.

[0040] The wearable data detection unit 106 is designed for a simulator. Its main function is to be worn on the simulator's pressing part and obtain high-precision hand spatial position data through the built-in sensor array 112. The sensor array 112 uses multi-point distributed sensing technology, such as inertial measurement units (IMUs), pressure sensors or optical tracking markers, to fully cover the hand contact area and provide three-dimensional coordinate information and the distribution of applied pressure. The wearable structure is designed to be easy to install and disassemble, such as ergonomic protective gear or flexible fabrics, which ensures wearing comfort without affecting natural movements. When the trainee starts to simulate pressing, these sensors can sense the position changes, angle adjustments and force of the fingers in real time, providing detailed basic information for subsequent data analysis.

[0041] After the wearing data detection unit 106 is correctly installed, the initialization unit 107 calibrates and initializes all sensors.

[0042] First, check whether each sensor has been successfully connected to the system to ensure no omission or misconfiguration. According to specific application requirements, set important parameters such as the working mode and sampling rate of the sensor to adapt to different types of pressing operations. Perform a one-time zero calibration to eliminate any initial deviation and make the subsequent data more accurate and reliable. Finally, through a series of self-check procedures, verify that the entire sensor network is in good condition and ready to enter the formal use stage.

[0043] The data collection unit 108 continuously operates throughout the pressing process and is specifically used to record the hand spatial position data generated by the trainee when interacting with the wearable data detection unit 106.

[0044] The time series data includes dynamic information such as finger coordinates and attitude angular velocity at each moment, reflecting the time evolution characteristics of the pressing action. Static feature data such as pressing depth, area, and center point, which are fixed attributes, help to evaluate the quality of a single press.

[0045] The storage unit 109 stores all the hand spatial position data generated by the data collection unit 108.

[0046] The wearable data detection unit 106 includes a mounting band 110, an adjustment unit 111, and a sensor array 112. The adjustment unit 111 is connected to the mounting band 110 and is used to adjust the length of the mounting band 110. The mounting band 110 is made of an elastic material, and the sensor array 112 is arranged on the mounting band 110.

[0047] The mounting band 110 is made of an elastic material, which has good elasticity and durability. Due to its high elasticity characteristics, the mounting band 110 can closely fit the pressing part of the simulated person. Whether it is the chest or other areas, it can maintain a stable position and will not shift due to the movements of the trainee.

[0048] The adjustment unit 111 is combined with the mounting band 110 through a firm mechanical connection to ensure that there will be no loosening or detachment during the adjustment process.

[0049] The adjustment unit 111 is built-in with a self-locking mechanism. After setting the appropriate length, it automatically locks to prevent accidental sliding, ensuring stability throughout the training process.

[0050] The sensor array 112 is evenly distributed on the mounting band 110 and is scientifically arranged according to ergonomic principles to ensure coverage of the entire pressing area and accurately capture the movement details of each part of the finger.

[0051] The sensor types include, but are not limited to, inertial measurement units (IMUs), pressure sensors, and optical tracking markers.

[0052] Inertial measurement units (IMUs) are used to detect the spatial posture and movement trajectory of the hand and provide three-dimensional coordinate information.

[0053] The pressure sensor records the magnitude of the pressure applied during pressing and its distribution, helping to evaluate whether the pressing depth and force meet the standards.

[0054] Optical tracking markers assist in locating the specific positions of the fingers, enhancing the accuracy of the data.

[0055] All sensors transmit the collected data to the system main control unit in real time via wireless or wired means, ensuring the continuity and reliability of the data stream.

[0056] The VR display module 102 includes a scene creation unit 113, a data conversion unit 114, a display unit 115, and a fixing unit 116: The scene creation unit 113 is used to create a 3D teaching scene and import the installed simulated human data into the teaching scene; the data conversion unit 114 is used to obtain the hand spatial position data and convert it to the 3D teaching scene to obtain the target scene; the display unit 115 is used to display the target scene using VR technology; the fixing unit 116 is used to fix the display unit 115 to the eye position of the trainee.

[0057] The scene creation unit 113 uses 3D modeling software and technologies such as Unity or Unreal Engine to build realistic teaching scenes. These scenes not only include the appearance models of simulated humans but also cover the surrounding environments such as hospital wards, first aid scenes, etc. to increase the sense of reality. The installed simulated human data (such as physiological parameters, internal structures, etc.) is seamlessly imported into the teaching scene to ensure that the virtual simulated human can accurately reflect its physical characteristics and reaction behaviors. Interactive elements such as operable medical devices, prompt messages, etc. are added to the teaching scene to enable trainees to conduct more realistic training in the virtual environment.

[0058] The data conversion unit 114 receives real-time hand spatial position data from the hand data acquisition module 101. This data contains information such as the positions, angles of the fingers, and the applied pressure distribution. The original hand spatial position data is converted to the coordinate system of the 3D teaching scene to ensure the accurate reproduction of hand movements in the virtual world. This involves complex geometric transformations and time synchronization processing to maintain data consistency. An efficient dynamic update mechanism is established so that each movement of the trainee can be immediately reflected in the virtual environment, providing smooth visual feedback.

[0059] The display unit 115 adopts modern virtual reality (VR) technologies, such as devices like Oculus Rift and HTC Vive, to render and display the converted target scene with high resolution and low latency. In addition to visual presentation, auditory and tactile feedback devices can also be integrated to enhance the immersion. For example, play a heartbeat sound effect or provide a slight vibration feedback when pressing. Design a simple and clear UI / UX interface to facilitate the trainees to view important information (such as deviation visualization, physiological parameter changes) and perform necessary interaction operations.

[0060] The fixing unit 116 firmly fixes the display unit 115 to the eye position of the trainee to ensure that there is no displacement or detachment during the whole training process. It adopts an ergonomic design considering the needs of different head sizes and shapes.

[0061] The feature extraction module 103 includes a noise processing unit 117, a time series synchronization unit 118, a feature setting unit 119, and a numerical calculation unit 120; the noise processing unit 117 is used to remove the noise values in the hand spatial position data; the time series synchronization unit 118 is used to align the position data of multiple sensors; the feature setting unit 119 is used to set the types of features to be extracted, and the feature types include pressing depth, pressing speed, pressing area, pressing force, and repetition frequency; the numerical calculation unit 120 is used to calculate specific values for each selected feature type to obtain a set of pressing feature values.

[0062] The noise processing unit 117 preprocesses the hand spatial position data, identifies and removes the outliers or interference signals therein. These noises may come from the errors of the sensors themselves, environmental factors, or unexpected changes in the actions of the trainees. Digital filtering algorithms, such as low-pass filters and Kalman filters, are used to smooth the data curve and eliminate the influence of high-frequency noises. At the same time, combined with the adaptive threshold method, the filtering parameters are dynamically adjusted to meet the requirements in different scenarios.

[0063] The time series synchronization unit 118 precisely aligns the position data from multiple sensors to solve the out-of-sync problem caused by sampling rate differences or transmission delays. Convert the timestamps of all sensors to a common time reference system, such as UTC time, and correct the clock drift to ensure the consistency between various data sources. For the case of inconsistent sampling frequencies, fill in the gaps through techniques such as linear interpolation and spline interpolation. Extract synchronization features (such as the occurrence time of specific events), and use algorithms such as dynamic time warping (DTW) to minimize the distance between two sequences and find the optimal alignment path.

[0064] The feature setting unit 119 allows users to select the types of features to be extracted according to specific application requirements. Common feature types include but are not limited to: Pressing depth: The maximum displacement of the finger relative to the initial position.

[0065] Pressing speed: The speed at which the finger moves during pressing.

[0066] Pressing area: The size of the contact area.

[0067] Pressing force: The distribution of the applied pressure.

[0068] Repetition frequency: The number of presses per unit time.

[0069] Support users to customize new feature types or combine existing features to meet specific teaching and assessment criteria.

[0070] The numerical calculation unit 120 performs specific numerical calculations on each selected feature type, and finally forms a set of pressing feature values. The calculation methods include but are not limited to geometric calculation, time series analysis, statistical analysis, etc. Through precise numerical calculations, the numerical calculation unit 120 assigns specific quantitative indicators to each feature, which is not only easy to understand but also provides a scientific basis for subsequent deviation calculation and improvement guidance.

[0071] In summary, through the collaborative work of the four major units, the feature extraction module 103 not only realizes the in-depth excavation of the hand spatial position data, but also injects powerful technical support into the overall performance and user experience of the cardiopulmonary resuscitation simulation system.

[0072] The time series synchronization unit 118 includes a time reference system conversion subunit 121, an interpolation subunit 122, and a spatial reference system conversion subunit 123; the time reference system conversion subunit 121 is used to convert the timestamps of all sensors to a common time reference system; the interpolation subunit 122 is used to fill in the missing data points through linear interpolation to make all data have the same sampling frequency; the spatial reference system conversion subunit 123 is used to convert all the obtained hand position data to a common coordinate system.

[0073] The time reference system conversion subunit 121 converts the timestamps of all sensors to a common time reference system (such as UTC time). This step is crucial for eliminating the time differences between different sensors. Since each sensor may use a different internal clock, there is a certain clock drift phenomenon. This subunit estimates and corrects these clock biases through linear regression or other methods to ensure that the timestamps of all data are as consistent as possible. To solve the problem that accurate timestamps cannot be directly obtained in some cases, a synchronization mark (such as the trigger signal for starting training) can be introduced as a reference point for relative time adjustment.

[0074] Through strict time reference system conversion, this sub-unit ensures the perfect alignment of multi-modal data in the time dimension, providing a solid foundation for subsequent data processing.

[0075] The interpolation sub-unit 122 fills in the missing data points caused by inconsistent sampling rates or transmission delays through interpolation algorithms. Common interpolation methods include linear interpolation, quadratic spline interpolation, etc., and the specific choice depends on the requirements of the application scenario. By reasonably estimating the missing data points, the interpolation sub-unit 122 ensures the continuity and integrity of the entire time series data, avoiding analysis errors caused by data interruptions.

[0076] The spatial reference system conversion sub-unit 123 converts all the obtained hand position data into a common coordinate system, usually the local coordinate system based on the simulated human model. This step ensures that the spatial position information captured by different sensors can be compared and analyzed within the same framework.

[0077] Using rotation and translation matrices, the spatial reference system conversion sub-unit 123 can accurately map the data of each sensor from its local coordinate system to the common coordinate system. This method is applicable not only to two-dimensional planes but also to handle position transformations in three-dimensional spaces.

[0078] The deviation calculation module 104 includes a reference value setting unit 124 and a deviation calculation unit 125; the reference value setting unit 124 is used to set reference feature values; the deviation calculation unit 125 is used to calculate the deviation value of each selected feature one by one according to the absolute difference method.

[0079] The reference value setting unit 124 defines and sets a series of reference feature values, which are usually based on the best practices of expert operations, medical guidelines, or samples with excellent performance in historical data. They reflect the key attributes of the ideal cardiopulmonary resuscitation compression action. Common reference feature values include but are not limited to compression depth, compression speed, compression area, compression force, and repetition frequency, etc. Each feature value represents an important aspect of the compression action, comprehensively covering all aspects of the compression quality.

[0080] The deviation calculation unit 125 calculates the deviation value of each selected feature type one by one according to the absolute difference method. Specifically, it compares the feature value generated by the trainee's actual operation with the corresponding reference feature value and calculates the absolute gap between the two.

[0081] For numerical features, the deviation calculation unit 125 uses the following formula to calculate the absolute difference: Deviation = Trainee feature value - Reference feature value.

[0082] The deviation visualization module 105 includes a visual element setting unit 126, a data matching unit 127, and a rendering unit 128. The visual element setting unit 126 is used to set various visualization data elements. The data matching unit 127 is used to match the deviation values of each feature type with the visualization data elements to obtain target elements. The rendering unit 128 is used to render the target elements into the target scene.

[0083] The visual element setting unit 126 designs and configures various types of visualization data elements to represent the deviation values of different feature types. Common visualization elements include but are not limited to: Color coding: Different colors (such as green, yellow, red) are used to represent the degree of deviation. Green indicates close to the standard, yellow indicates a slight deviation, and red indicates a significant deviation.

[0084] Transparency change: Adjust the transparency of an object or area according to the deviation size, making the parts with larger deviations more prominent.

[0085] Arrow or indicator: Used to show the directional deviation. For example, when the pressing angle is incorrect, the arrow can point in the correct direction.

[0086] Numeric label: Directly display the specific deviation value at the relevant position to provide accurate quantitative feedback.

[0087] Heat map: Use color gradients to show the deviation distribution of the entire pressing area to help trainees intuitively understand the overall performance.

[0088] The task of the data matching unit 127 is to accurately match the deviation values of each feature type with the pre-set visualization data elements. For example: Pressing depth: If the deviation is large, it can be highlighted by changing the color of the pressing point or increasing the transparency.

[0089] Pressing speed: Use an arrow to indicate the ideal movement trajectory and show the change trend of the actual speed through a dynamic line.

[0090] Pressing area: Use a heat map to show the coverage of the contact area to help trainees adjust the position of their fingers.

[0091] Pressing force: Real-time display the force value through a numeric label and combine color changes to reflect its deviation from the standard.

[0092] According to different deviation ranges, set corresponding thresholds to classify the deviations. For example, slight deviations can be represented by lighter colors, while severe deviations are emphasized by more prominent colors or larger transparency changes.

[0093] The rendering unit 128 adopts advanced graphics rendering technologies, such as high-quality rendering pipelines in Unity or Unreal Engine, to ensure that all visual elements can be presented in the virtual environment with the best resolution and smoothness.

[0094] Second Embodiment Please refer to Figure 9 , the present invention also provides a VR-based cardiopulmonary resuscitation simulation method, including: S201 Obtain the hand spatial position data generated by the trainee when pressing the simulation man; Start the hand data acquisition module to prepare to capture the hand spatial position data of the trainee during cardiopulmonary resuscitation pressing operation. The trainee wears a special glove or uses a VR controller, which are built-in with a sensor array that can accurately record the position, angle of the fingers, and the applied pressure distribution. The system initializes and calibrates the sensors to ensure the accuracy of data collection. When the trainee starts pressing the simulation man, the system continuously collects high-frequency time series data, including three-dimensional coordinate information and pressure changes, to form a complete hand movement trajectory.

[0095] S202 Display the cardiopulmonary resuscitation teaching model, and at the same time read and display the simulation man data and the hand spatial position data; Use the scene creation unit in the VR display module to build a realistic 3D teaching scene, and import the installed simulation man data into this environment. The simulation man not only has a real appearance but also has the dynamic simulation function of internal physiological parameters (such as heart rate, blood pressure, etc.). Through the data conversion unit, the hand spatial position data is converted into the 3D teaching scene, so that the trainee can see the interaction between his hands and the simulation man in the virtual environment. At the same time, the status information of the simulation man, such as the changes in vital signs, is read and displayed in real time to help the trainee better understand the operation effect.

[0096] S203 Extract the pressing eigenvalue group based on the hand spatial position data; First, the noise processing unit in the feature extraction module removes the noise values in the hand spatial position data, and the time series synchronization unit aligns the data of multiple sensors to ensure the consistency and accuracy of the data. According to specific requirements, the feature setting unit defines the types of features to be extracted, such as pressing depth, speed, area, strength, and repetition frequency, etc. Each feature type represents an important aspect of the pressing action. The numerical calculation unit performs specific numerical calculations on each selected feature type to finally form a set of pressing eigenvalue.

[0097] S204 Calculate the deviation value based on the pressing eigenvalue and the reference eigenvalue; Through the reference value setting unit in the deviation calculation module, a series of reference characteristic values are predefined. These reference values reflect the key attributes of an ideal cardiopulmonary resuscitation (CPR) pressing action, usually based on the best practices of expert operations or medical guidelines. The deviation calculation unit calculates the deviation values of each characteristic type one by one using the absolute difference method, that is, the absolute gap between the characteristic values generated by the trainee's actual operation and the corresponding reference characteristic values.

[0098] S205 Visualizes the deviation values and displays them in real time on the VR display module.

[0099] Through the visual element setting unit in the deviation visualization module, various types of visualization data elements are designed, such as color coding, transparency change, arrow indicators, numerical labels, etc., to visually represent the deviation values. The data matching unit precisely matches the deviation values of each characteristic type with the predefined visualization data elements to generate the corresponding target elements. For example, when the deviation of the pressing depth is large, it can be highlighted by changing the color of the pressing point or increasing the transparency. The rendering unit efficiently renders the generated target elements into the teaching scenario created by the VR display module to ensure that all visualization elements can be presented in the virtual environment with the best resolution and smoothness. The trainee can immediately see the difference between their pressing action and the ideal standard during the training process and obtain immediate feedback.

[0100] The above-disclosed is only a preferred embodiment of the present invention. Of course, the scope of the rights of the present invention cannot be limited thereby. Those of ordinary skill in the art can understand all or part of the processes of implementing the above embodiments, and the equivalent changes made according to the claims of the present invention still fall within the scope covered by the invention.

Claims

1. A VR-based cardiopulmonary resuscitation simulation system, characterized in that, It includes a hand data acquisition module, a VR display module, a feature extraction module, a deviation calculation module, and a deviation visualization module; The hand data acquisition module is used to acquire the hand spatial position data generated by the trainee when pressing the mannequin; The VR display module is used to display the cardiopulmonary resuscitation teaching model, and at the same time read and display the mannequin data and the hand spatial position data; The feature extraction module is used to extract a set of pressing feature values based on the hand spatial position data; The deviation calculation module is used to calculate the deviation value based on the pressing feature value and the reference feature value; The deviation visualization module is used to visualize the deviation value and display it in real time on the VR display module.

2. The cardiopulmonary resuscitation simulation system based on VR according to claim 1, wherein, The hand data acquisition module includes a wearable data detection unit, an initialization unit, a data collection unit, and a storage unit; The wearable data detection unit is used to be worn on the pressing part of the mannequin, and is provided with a sensor array to acquire the hand spatial position data; The initialization unit is used to initialize the sensor array after the wearable data detection unit is installed; The data collection unit is used to generate hand spatial position data when the trainee presses the wearable data detection unit; The storage unit is used to store the generated hand spatial position data.

3. A VR-based cardiopulmonary resuscitation simulation system according to claim 2, wherein The wearable data detection unit includes a mounting band, an adjustment unit, and a sensor array. The adjustment unit is connected to the mounting band and is used to adjust the length of the mounting band. The mounting band is made of an elastic material, and the sensor array is arranged on the mounting band.

4. A VR-based cardiopulmonary resuscitation simulation system according to claim 3, wherein The VR display module includes a scene creation unit, a data conversion unit, a display unit, and a fixing unit: The scene creation unit is used to create a 3D teaching scene and import the installed mannequin data into the teaching scene; The data conversion unit is used to acquire the hand spatial position data and convert it to the 3D teaching scene to obtain a target scene; The display unit is used to display the target scene by using VR technology; The fixing unit is used to fix the display unit to the position of the trainee's eyes.

5. A VR-based cardiopulmonary resuscitation simulation system according to claim 4, wherein The feature extraction module includes a noise processing unit, a time series synchronization unit, a feature setting unit, and a numerical calculation unit; The noise processing unit is used to remove the noise values in the hand spatial position data; The time series synchronization unit is used to align the position data of multiple sensors; The feature setting unit is used to set the extracted feature types, and the feature types include pressing depth, pressing speed, pressing area, pressing force, and repetition frequency; The numerical calculation unit is used to calculate the specific values for each selected feature type to obtain a set of pressing feature values.

6. A VR-based cardiopulmonary resuscitation simulation system according to claim 5, wherein The time series synchronization unit includes a time reference system conversion subunit, an interpolation subunit, and a spatial reference system conversion subunit; The time reference system conversion subunit is configured to convert the timestamps of all sensors to a common time reference system; The interpolation subunit is configured to fill in the missing data points by linear interpolation so that all data has the same sampling frequency; The spatial reference system conversion subunit is configured to convert all the obtained hand position data to a common coordinate system.

7. The VR-based cardiopulmonary resuscitation simulation system according to claim 6, wherein The deviation calculation module includes a reference value setting unit and a deviation calculation unit; The reference value setting unit is configured to set a reference feature value; The deviation calculation unit is configured to calculate the deviation value of each selected feature one by one according to the absolute difference method.

8. The VR-based cardiopulmonary resuscitation simulation system according to claim 7, wherein The deviation visualization module includes a visual element setting unit, a data matching unit, and a rendering unit; the visual element setting unit is configured to set a variety of visualization data elements; The data matching unit is configured to match the deviation values of each feature type with the visualization data elements to obtain target elements; The rendering unit is configured to render the target elements into the target scene.

9. A VR-based cardiopulmonary resuscitation simulation method, which uses a VR-based cardiopulmonary resuscitation simulation system according to any one of claims 1 to 8, characterized in that, including: Obtain the hand spatial position data generated by the trainee when pressing the mannequin; Display the cardiopulmonary resuscitation teaching model, and at the same time read and display the mannequin data and the hand spatial position data; Extract a set of pressing feature values based on the hand spatial position data; Calculate the deviation value based on the pressing feature value and the reference feature value; Visualize the deviation value and display it in real time on the VR display module.

Images