Cardio-pulmonary resuscitation training control method and system and cardio-pulmonary resuscitation simulation equipment

Abstract

The invention provides a cardiopulmonary resuscitation training control method, a cardiopulmonary resuscitation training control system and cardiopulmonary resuscitation simulation equipment, and relates to the technical field of medical equipment. Operation indexes such as pressing depth, frequency and springback of a cardio-pulmonary resuscitation simulation person and related physiological parameters are converted into holographic 3D images in real time, visual and synchronous presentation of operation data is achieved, and the training effect and teaching efficiency are remarkably improved.

Description

Technical Field

[0001] This invention relates to the field of medical device technology, and in particular to a cardiopulmonary resuscitation (CPR) training control method, system, and CPR simulation device. Background Technology

[0002] While existing CPR mannequins can simulate basic human physiological structures and responses, they have significant limitations in providing feedback on operational indicators. During training, compression depth, compression rate, chest recoil, airway occupancy, ventilation volume, ventilation rate, and various physiological parameters are core quantitative indicators for evaluating the quality of CPR procedures, directly impacting the realism of the simulation and the effectiveness of the training. However, current technologies rely on traditional methods for providing feedback on these indicators, largely depending on the mannequin's own display screen, indicator lights, or simple external data loggers.

[0003] Specifically, when learners perform chest compressions, the mannequin can usually only display the real-time compression depth on the screen, or use different colored indicator lights to roughly indicate whether the compression depth is up to standard. As for compression frequency, feedback is mostly provided through sound prompts or statistical data generated afterward, and it is impossible to display the frequency change curve in real time. Furthermore, chest recoil, airway occlusion, ventilation volume, and ventilation rate often require trainees to observe the mannequin's chest movement with their naked eyes, or rely on simple signal feedback from the mannequin's internal sensors, lacking precise quantitative data and visualization.

[0004] Therefore, traditional training feedback methods suffer from two main problems: First, feedback information is fragmented, requiring learners to simultaneously focus on multiple signals such as the mannequin, display screen, and sound, making it difficult to quickly integrate key information and affecting real-time judgment and adjustment of operational quality. Second, feedback is delayed, with some indicators only generating statistical results after the operation is completed, making it impossible to correct non-standard movements in a timely manner during the operation, resulting in low training efficiency. Furthermore, for novice learners, abstract numerical values ​​and single prompts are insufficient to help them develop an intuitive understanding of the force and rhythm of the operation, hindering the formation of high-quality CPR skills. Simultaneously, in team training scenarios, existing feedback methods cannot allow all trainees to simultaneously and clearly observe operational indicators, hindering collective guidance and analysis by trainers and limiting the effectiveness of collaborative training. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a cardiopulmonary resuscitation (CPR) training control method, system, and CPR simulation device. This solution adds a holographic 3D projection feedback function to the CPR training process. By converting the CPR manipulator's compression depth, frequency, rebound, and other operational indicators and related physiological parameters into holographic 3D images in real time, the operational data is presented intuitively and synchronously, significantly improving the training effect and teaching efficiency, thereby effectively solving the above-mentioned problems existing in the prior art.

[0006] In a first aspect, embodiments of the present invention provide a method for controlling cardiopulmonary resuscitation training, the method comprising: Initiation process: Control the cardiopulmonary resuscitation (CPR) manikin and holographic projector to be in working condition; wherein, the CPR manikin is connected to the holographic projector; the CPR manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor, and an end-tidal carbon dioxide sensor; Training procedure: Perform chest compressions on a CPR manikin, using pressure and acceleration sensors to acquire compression data in real time, and using a bidirectional flow sensor, blood oxygen saturation sensor, electrocardiogram monitoring sensor, and end-tidal carbon dioxide sensor to acquire simulated physiological data in real time. Data processing steps: Generate 3D image data corresponding to the holographic projector based on the pressure data and simulated physiological data, and control the display of the 3D image data on the holographic projector.

[0007] Optionally, pressure and accelerometer sensors can be used to acquire compression data in real time, including: The compression depth corresponding to the cardiopulmonary resuscitation manikin is acquired in real time using pressure sensors. The height and color values ​​of the bar chart corresponding to the compression depth are calculated according to a preset linear mapping relationship. The compression depth data corresponding to the cardiopulmonary resuscitation manikin is determined based on the compression depth, bar height and color values. Accelerometers are used to acquire the compression interval time of the cardiopulmonary resuscitation (CPR) manikin in real time. The compression frequency of the CPR manikin is determined based on the Fourier transform curve corresponding to the compression interval time. The compression frequency data of the CPR manikin is determined based on the compression interval time, Fourier transform curve and compression frequency. The rebound velocity and rebound height of the cardiopulmonary resuscitation manikin are acquired in real time using an accelerometer. The arrow length and arrow color value corresponding to the rebound velocity and rebound height are calculated according to a preset velocity threshold relationship. The rebound data corresponding to the cardiopulmonary resuscitation manikin are determined based on the rebound velocity, rebound height, arrow length and arrow color value. The compression data is determined based on the compression depth data, compression frequency data, and rebound data.

[0008] Optionally, simulated physiological data can be acquired in real time using a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor, and an end-tidal carbon dioxide sensor, including: The instantaneous flow data of the cardiopulmonary resuscitation (CPR) manikin during chest compressions is acquired in real time using a bidirectional flow sensor, and the ventilation rate data corresponding to the CPR manikin is determined based on the instantaneous flow data. The pulse oximetry waveform of the cardiopulmonary resuscitation manikin is acquired in real time using a blood oxygen saturation sensor. The peripheral tissue region and filling color are determined based on the peripheral perfusion simulation calculation results corresponding to the pulse oximetry waveform. The cardiopulmonary resuscitation quality index data corresponding to the cardiopulmonary resuscitation manikin are determined based on the changes in pulse oximetry waveform, peripheral tissue region and filling color. The ECG monitoring sensor is used to acquire the ECG activity heart rate value corresponding to the cardiopulmonary resuscitation (CPR) manikin in real time. Based on the ECG activity heart rate value, the ECG activity frequency of the heart model of the CPR manikin and its corresponding heart color value and heart model beat frequency are determined. Based on the ECG activity heart rate value, heart model ECG activity frequency, heart color value and heart model beat frequency, the linkage data of the heart model corresponding to the CPR manikin is determined. The ECG data of the cardiopulmonary resuscitation manikin is acquired in real time using an ECG monitoring sensor. The spectral area of ​​the ECG data and its corresponding display strategy parameters are determined based on the fast Fourier transform results of the ECG data. The ECG spectral data of the cardiopulmonary resuscitation manikin is determined based on the ECG data, the spectral area of ​​the ECG data and the display strategy parameters. The end-tidal carbon dioxide sensor is used to acquire the end-tidal carbon dioxide partial pressure value of the cardiopulmonary resuscitation (CPR) manikin in real time. The display area corresponding to the lung model is determined based on the surface data of the lung model of the CPR manikin. The display effects and display colors corresponding to the end-tidal carbon dioxide partial pressure value in the display area are determined by a preset partial pressure threshold relationship. The end-tidal carbon dioxide partial pressure data is determined based on the end-tidal carbon dioxide partial pressure value, display area, display effects and display colors. Simulated physiological data were determined based on ventilation rate data, cardiopulmonary resuscitation quality index data, cardiac model linkage data, electrocardiogram spectrum data, and end-tidal carbon dioxide partial pressure data.

[0009] Optionally, the cardiopulmonary resuscitation quality index corresponding to the cardiopulmonary resuscitation manikin can be obtained in real time using a blood oxygen saturation sensor, including: The pulse oxygen saturation, pulse oxygen waveform, and area under the curve of the cardiopulmonary resuscitation manipulator were obtained in real time using a pulse oxygen saturation sensor. The cardiopulmonary resuscitation quality index is determined by pulse oxygen saturation, pulse oxygen waveform, and area under the curve.

[0010] Optional data processing steps include: The bottom layer display area, lower middle layer display area, middle layer display area, and top layer display area are determined based on the height value of the display area in the holographic projector. The first display parameters corresponding to the bar chart, fluctuation curve and rebound arrow in the underlying display area are determined based on the press data, and the underlying image data corresponding to the press data is generated based on the first display parameters. The second display parameters corresponding to the end-tidal carbon dioxide waveform data and the lung model associated image in the middle and lower layer display area are determined based on the end-tidal carbon dioxide partial pressure data, and the middle and lower layer image data corresponding to the end-tidal carbon dioxide waveform data are generated based on the second display parameters. Based on the cardiac model linkage data, the blood oxygen tissue image in the middle layer display area and the third display parameters corresponding to the cardiac model are determined, and the middle layer image data corresponding to the cardiac model linkage data is generated based on the third display parameters. Acquire warning information contained in compression data, cardiac model linkage data, and end-tidal carbon dioxide partial pressure data, and generate warning image data corresponding to the top display area based on the warning information; The 3D image data corresponding to the holographic projector is determined based on the bottom layer image data, the middle and lower layer image data, the middle layer image data, and the early warning image data. The holographic projector displays 3D image data on the display area according to the preset refresh rate.

[0011] Optionally, the cardiopulmonary resuscitation manikin may also include defibrillation electrodes; The training operation steps also include: Defibrillation electrodes were used to defibrillate the cardiopulmonary resuscitation manikin, and electrocardiogram monitoring sensors were used to collect simulated electrocardiogram data in real time. The defibrillation energy, timing, and amplitude spectral area of ​​the cardiopulmonary resuscitation (CPR) manikin are determined based on the simulated electrocardiogram (ECG) data, and the defibrillation data corresponding to the simulated ECG data are determined using the CPR manikin's defibrillation energy, timing, and amplitude spectral area.

[0012] Optionally, the data processing steps may also include: Based on the defibrillation data, the fourth display parameter corresponding to the defibrillation current path and amplitude spectrum area change in the middle layer display area is determined, and defibrillation image data corresponding to simulated physiological data is generated based on the fourth display parameter. Acquire the fitting misalignment data and energy warning data contained in the defibrillation data, and generate defibrillation warning image data corresponding to the top display area based on the fitting misalignment data and energy warning data; Based on defibrillation image data and defibrillation warning image data, the corresponding three-dimensional image data of the holographic projector is determined, and the holographic projector is controlled to display the three-dimensional image data in the middle display area according to the preset same refresh rate.

[0013] Optionally, the CPR manikin can also be connected to a projection screen; The data processing steps also include: Two-dimensional image data corresponding to the projection screen is generated based on the pressure data and simulated physiological data, and the two-dimensional image data is controlled to be displayed on the projection screen.

[0014] Secondly, the present invention provides a cardiopulmonary resuscitation training and control system, the system comprising: Startup processing control module: used to control the cardiopulmonary resuscitation (CPR) manikin and holographic projector to be in working state; wherein, the CPR manikin is connected to the holographic projector; the CPR manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor and an end-tidal carbon dioxide sensor; Training operation control module: used to control the compression of the cardiopulmonary resuscitation manikin, using pressure and acceleration sensors to acquire compression data in real time, and using bidirectional flow sensor, blood oxygen saturation sensor, electrocardiogram monitoring sensor and end-tidal carbon dioxide sensor to acquire simulated physiological data in real time; Data processing and control module: used to generate three-dimensional image data corresponding to the holographic projector based on the pressure data and simulated physiological data, and to control the display of the three-dimensional image data in the holographic projector.

[0015] Thirdly, embodiments of the present invention also provide a cardiopulmonary resuscitation (CPR) simulation device, which includes: a CPR manikin, a holographic projector, and a data processing module; wherein the data processing module is connected to both the CPR manikin and the holographic projector. The data processing module includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the steps of the cardiopulmonary resuscitation training control method provided in the first aspect.

[0016] Fourthly, embodiments of the present invention also provide a storage medium storing computer-executable instructions, which, when invoked and executed by a processor, cause the processor to implement the steps of the cardiopulmonary resuscitation training control method provided in the first aspect.

[0017] This invention provides a cardiopulmonary resuscitation (CPR) training control method, system, and CPR simulation device. During CPR training, the CPR manifold and holographic projector are first controlled to be in working condition. The CPR manifold is connected to the holographic projector. The CPR manifold is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram (ECG) monitoring sensor, and an end-tidal carbon dioxide (UTC) sensor. After compressions are applied to the CPR manifold, the pressure and acceleration sensors acquire compression data in real time, and the bidirectional flow, blood oxygen saturation, ECG, and UTC sensors acquire simulated physiological data in real time. Finally, based on the compression data and simulated physiological data, three-dimensional image data corresponding to the holographic projector is generated and displayed on the holographic projector. This solution adds a holographic 3D projection feedback function to the CPR training process. By converting the compression depth, frequency, rebound, and other operational indicators and related physiological parameters of the CPR manifold into holographic 3D images in real time, the operational data is presented intuitively and synchronously, significantly improving training effectiveness and teaching efficiency.

[0018] Other features and advantages of the invention will be set forth in the description which follows, and will be apparent in part from the description, or may be learned by practicing the invention. The objects and other advantages of the invention are realized and obtained in accordance with the structures particularly pointed out in the description, claims and drawings.

[0019] To make the above-mentioned objects, features and advantages of the present invention more apparent and understandable, preferred embodiments are described below in detail with reference to the accompanying drawings. Attached Figure Description

[0020] To more clearly illustrate the specific embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the specific embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For those skilled in the art, other drawings can be obtained from these drawings without creative effort.

[0021] Figure 1 A flowchart of a cardiopulmonary resuscitation training control method provided in an embodiment of the present invention; Figure 2 A flowchart illustrating the training operation steps S102 of a cardiopulmonary resuscitation training control method provided in this embodiment of the invention, which uses a pressure sensor and an acceleration sensor to acquire compression data in real time; Figure 3In the training operation step S102 of the cardiopulmonary resuscitation training control method provided in this embodiment of the invention, a flowchart is shown showing how simulated physiological data is acquired in real time using a blood oxygen saturation sensor, an electrocardiogram monitoring sensor, and an end-tidal carbon dioxide sensor. Figure 4 In the training operation step S301 of the cardiopulmonary resuscitation training control method provided in this embodiment of the invention, a flowchart is shown in which the cardiopulmonary resuscitation quality index corresponding to the cardiopulmonary resuscitation manikin is obtained in real time using a blood oxygen saturation sensor. Figure 5 A flowchart of data processing step S103 of a cardiopulmonary resuscitation training control method provided in an embodiment of the present invention; Figure 6 A flowchart of training operation steps S102 of another cardiopulmonary resuscitation training control method provided in an embodiment of the present invention; Figure 7 A flowchart of data processing step S103 of another cardiopulmonary resuscitation training control method provided in an embodiment of the present invention; Figure 8 This is a schematic diagram of the structure of a cardiopulmonary resuscitation training and control system provided in an embodiment of the present invention; Figure 9 This is a schematic diagram of the structure of a cardiopulmonary resuscitation simulation device provided in an embodiment of the present invention; Figure 10 This is a schematic diagram of the data processing module in a cardiopulmonary resuscitation simulation device provided in an embodiment of the present invention.

[0022] icon: 810 - Startup Processing Control Module; 820 - Training Operation Control Module; 830 - Data Processing Control Module; 1-Cardiopulmonary resuscitation manikin; 2-Pressure sensor; 3-Acceleration sensor; 4-Data processing module; 5-Holographic projector; 6-Projection screen; 7-Power supply module; 8-Blood oxygen saturation sensor; 9-ECG monitoring sensor; 10-End-tidal carbon dioxide sensor; 11-Defibrillation electrode pads; 12-High-voltage pulse simulator; 101 - Processor; 102 - Memory; 103 - Bus; 104 - Communication interface. Detailed Implementation

[0023] To make the objectives, technical solutions, and advantages of the embodiments of the present invention clearer, the technical solutions of the present invention will be clearly and completely described below in conjunction with the embodiments. Obviously, the described embodiments are only some embodiments of the present invention, not all embodiments. Based on the embodiments of the present invention, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of the present invention.

[0024] To facilitate understanding of this embodiment, a detailed description of a cardiopulmonary resuscitation (CPR) training control method disclosed in this invention will be provided first. This CPR training control method aims to achieve precise data collection and intuitive visual feedback during the training process through the coordinated operation of a "simulated human + holographic projection," helping trainees quickly master standardized CPR operations. Its specific steps can be summarized in three core stages: "device startup - operation execution - data feedback." Figure 1 As shown, the method includes: Initiation processing step S101: Control the cardiopulmonary resuscitation manikin and holographic projector to be in working state; wherein, the cardiopulmonary resuscitation manikin is connected to the holographic projector; the cardiopulmonary resuscitation manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor and an end-tidal carbon dioxide sensor.

[0025] The core of this step is to initialize and integrate the hardware required for training, laying the foundation for subsequent data collection and visualization feedback. The specific operations and logic are as follows: First, the CPR manikin and holographic projector should be started simultaneously to ensure both are in normal working order. The manikin needs to complete self-checks (such as sensor calibration and power stability testing), and the holographic projector needs to complete optical path debugging and projection area positioning (such as determining the spatial correspondence between the projected image and the manikin). Furthermore, ensure a stable connection between the CPR manikin and the holographic projector via wired (e.g., USB, Ethernet) or wireless (e.g., Bluetooth, Wi-Fi) means this connection is crucial for transmitting various training data collected by the manikin to the holographic projector's control module in real time, providing a data source for subsequent 3D image generation.

[0026] The multiple sensors built into the cardiopulmonary resuscitation manikin are key to achieving "precision training." The functions of each sensor are clearly defined, as follows: Two-way flow sensor: mainly installed at the end of the airway simulation channel, using a thermal flow sensor with an accuracy of ±5mL / min, used to detect the gas flow rate entering and leaving the airway during ventilation; Pressure sensor: mainly deployed in the chest compression area of ​​the simulated human to monitor the force (unit: N) applied by the trainee during compression and to determine whether the compression force meets the standard requirement of "100-120N for adults"; Accelerometer: Working in conjunction with the pressure sensor, it calculates the compression depth (unit: cm) and compression frequency (unit: times / minute) by sensing the rate of displacement change during chest compressions. The core monitoring focuses on two key indicators: "compression depth 5-6 cm and frequency 100-120 times / minute". Blood oxygen saturation sensor: Usually deployed in the "extremities" such as simulated human fingers or earlobes, it is used to simulate the changes in blood oxygen saturation in a real human body during cardiopulmonary resuscitation, reflecting the effect of compression on the support of "circulatory function"; ECG monitoring sensor: By using electrodes that mimic the human chest, it generates simulated electrocardiogram signals, which can simulate scenarios such as "cardiac arrest" and "heart rhythm recovery after compression", helping trainees understand the relationship between cardiopulmonary resuscitation and circulatory function; End-tidal carbon dioxide sensor: Integrated into the simulated human respiratory tract component (such as the endotracheal intubation interface), it is used to collect simulated end-tidal carbon dioxide (PetCO2) concentration and waveform data. Its core function is to determine the effectiveness of ventilation operation (e.g., a normal PetCO2 waveform can indicate smooth ventilation, while the absence of a waveform may indicate airway obstruction).

[0027] Training operation step S102: Press the cardiopulmonary resuscitation manikin, use pressure sensors and acceleration sensors to acquire compression data in real time, and use bidirectional flow sensors, blood oxygen saturation sensors, electrocardiogram monitoring sensors and end-tidal carbon dioxide sensors to acquire simulated physiological data in real time.

[0028] This step is the core operational process for the trainee. Through "actual pressing + real-time data collection," the trainee's operational behavior is transformed into quantifiable data. The specific process is as follows: Trainees perform chest compressions on a CPR manikin according to the standard CPR procedure (if the training includes ventilation, artificial respiration or bag-valve ventilation should also be used). During real-time data acquisition of compressions, the built-in pressure and accelerometer sensors of the mannequin work synchronously during the trainee's compressions. The pressure sensor collects compression intensity data multiple times per second to avoid problems such as "insufficient force leading to ineffective cycle support" or "excessive force leading to rib fractures." The accelerometer calculates compression depth (such as the distance the chest sinks during compression) and compression frequency (such as the number of compressions per minute) through displacement changes, ensuring that the time resolution of the collected data meets the "real-time feedback" requirement (usually a sampling frequency ≥ 50Hz). The simulated physiological data acquisition process needs to be synchronized with the chest compressions. The instantaneous flow rate data (unit: mL / s) collected by the bidirectional flow sensor is converted into a ventilation rate parameter, which is expressed as the "rate of change of ventilation volume per unit time," i.e., the ventilation rate value = instantaneous flow rate / cross-sectional area of ​​the simulated airway (the cross-sectional area of ​​the simulated airway is preset to 3-5 cm). 2(Matching adult airway dimensions); the blood oxygen saturation sensor and the electrocardiogram monitoring sensor continuously generate simulated physiological indicators. The blood oxygen saturation sensor dynamically adjusts the blood oxygen saturation value according to the compression effect, while the electrocardiogram monitoring sensor outputs the corresponding simulated electrocardiogram waveform. During the end-tidal carbon dioxide waveform data acquisition process, if the training includes ventilation steps, the end-tidal carbon dioxide sensor will capture the PetCO2 waveform and concentration value of the simulated person during "exhalation" in real time. Under normal circumstances, a complete PetCO2 waveform (ascending phase, plateau phase, descending phase) will appear after each ventilation, and the concentration is usually between 35-45 mmHg. If ventilation is insufficient or the airway is blocked, the waveform will become lower, flatter, or even disappear, intuitively reflecting the standardization of the ventilation operation, used to characterize the amount and rate of ventilation, which can be correlated with intrathoracic pressure, and will not be elaborated further.

[0029] Data processing step S103: Generate three-dimensional image data corresponding to the holographic projector based on the pressing data and simulated physiological data, and control the display of the three-dimensional image data in the holographic projector.

[0030] This step is the core process of transforming "quantitative data" into "intuitive images." Through data processing and holographic projection, trainees can instantly understand the strengths and weaknesses of their own operations. The specific process is as follows: Data integration and analysis: The main body executing this method, such as the data processing module, can clean the data after receiving three types of data from the simulated human (press data, simulated physiological data, and end-tidal carbon dioxide waveform data), remove abnormal values ​​falsely reported by the sensor, and then perform correlation analysis.

[0031] 3D Image Data Generation: Based on the integrated analysis results, 3D image data adapted to the holographic projector is generated. This image data is not a single image, but rather contains dynamic content with "multi-dimensional information overlay." Common presentation formats include: Visualization of compression action: Simulates the trainee's compression position, force, and depth using a 3D model (e.g., using different colors to mark the compression area: green for the standard position and red for the off-center position; using a bar chart to display in real time whether the pressure / depth is within the standard range). Dynamic display of physiological indicators: Dynamic curves of simulated physiological data are superimposed on the 3D images, such as the real-time change curve of blood oxygen saturation, the ECG waveform, and the end-tidal carbon dioxide waveform, and the standard reference range is marked (e.g., the normal range of "35-45 mmHg" is marked next to the PetCO2 waveform). Operation prompts and annotations: For non-standard operations, text or icon prompts will be added to the 3D image (e.g., if the pressure is insufficient, display "Insufficient pressure, please increase the pressure"; if the pressing frequency is too fast, display "Frequency > 120 times / minute, please slow down").

[0032] Holographic projection display control: The generated 3D image data is sent to a holographic projector, which then projects the image onto the trainee's visible area. Trainees can see directly through the holographic image whether their pressing movements are correct and whether their physiological indicators have improved due to effective operation, without needing to look down at data reports. This achieves an instant "operation-feedback" closed loop, helping to quickly adjust techniques and improve training efficiency.

[0033] Optionally, pressure and accelerometer sensors can be used to acquire compression data in real time, such as... Figure 2 As shown, it includes: Step S201: Use pressure sensors to acquire the compression depth corresponding to the cardiopulmonary resuscitation manikin in real time, calculate the bar chart height value and bar chart color value corresponding to the compression depth according to the preset linear mapping relationship, and determine the compression depth data corresponding to the cardiopulmonary resuscitation manikin based on the compression depth, bar chart height value and bar chart color value.

[0034] When the trainee performs CPR on the manikin, pressure sensors are used to obtain the corresponding compression depth in real time. This depth is then converted into a 3D histogram using a preset linear mapping relationship. Assuming a standard depth range of 5-6 cm, the histogram height (in pixels) is calculated as compression depth × 50 (1 cm corresponds to 50 pixels), thus yielding the histogram height value.

[0035] The corresponding bar chart color value can also be determined through a preset linear mapping relationship. For example, when the pressing depth is <5cm, the HSL color conversion is triggered, and the bar chart fill color is set to (H:30, S:100%, L:50%), which is yellow; when the pressing depth is 5-6cm, the fill color is set to (H:120, S:100%, L:50%), which is green; when the pressing depth is >6cm, the fill color is set to (H:0, S:100%, L:50%), which is red, and flashing is triggered (flashing frequency = 2Hz).

[0036] Step S202: Use an accelerometer to acquire the compression interval time corresponding to the cardiopulmonary resuscitation (CPR) manifold in real time, determine the compression frequency of the CPR manifold based on the Fourier transform curve corresponding to the compression interval time, and determine the compression frequency data corresponding to the CPR manifold based on the compression interval time, Fourier transform curve, and compression frequency.

[0037] This step utilizes an accelerometer to acquire the compression interval time corresponding to the CPR manikin in real time, and determines the compression frequency of the CPR manikin based on the compression interval time. The compression frequency data (unit: compressions / minute) can be used to extract the periodic characteristics of the compression interval time using a Fourier transform algorithm and convert it into a fluctuation curve. Specifically, assuming a sampling frequency of 100Hz, spectral analysis is performed on the compression interval time within a continuous 5-second interval. The curve amplitude is positively correlated with the frequency deviation (standard frequency 100-120 compressions / minute). When the compression frequency is <100 compressions / minute, the curve wavelength is lengthened (wavelength = 1.2 × standard wavelength); when the compression frequency is >120 compressions / minute, the curve wavelength is shortened (wavelength = 0.8 × standard wavelength).

[0038] Step S203: Use an accelerometer to acquire the rebound velocity and rebound height of the cardiopulmonary resuscitation manikin in real time, calculate the arrow length and arrow color value corresponding to the rebound velocity and rebound height according to the preset velocity threshold relationship, and determine the rebound data corresponding to the cardiopulmonary resuscitation manikin based on the rebound velocity, rebound height, arrow length and arrow color value.

[0039] This step utilizes an accelerometer to acquire the rebound velocity and rebound height of the CPR manikin in real time. The rebound velocity (unit: cm / s) is converted into an arrow animation based on a threshold range: a acceptable rebound velocity is set to >2 cm / s. When the velocity meets the standard, an upward green arrow is generated (arrow length = velocity × 10 pixels); when the rebound velocity is <2 cm / s, a downward red arrow is generated (arrow length = (2 - velocity) × 20 pixels), and the arrow flashing frequency increases as the velocity decreases (flashing frequency = 3Hz at the lowest velocity). The rebound height represents the degree of rebound; therefore, the corresponding rebound data can be obtained by integrating the above data.

[0040] Step S204: Determine the press data based on the press depth data, press frequency data, and rebound data.

[0041] The compression depth data is determined based on the compression depth, bar height value, and bar color value; the compression frequency data is determined based on the compression interval time, Fourier transform curve, and compression frequency; the rebound data is determined based on the rebound speed, rebound velocity, arrow length, and arrow color value. The compression data can be obtained by integrating the above data.

[0042] Optionally, simulated physiological data can be acquired in real time using a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor, and an end-tidal carbon dioxide sensor, such as... Figure 3 As shown, it includes: Step S301: Use a bidirectional flow sensor to acquire the instantaneous flow data of the cardiopulmonary resuscitation manipulator during chest compressions in real time, and determine the ventilation rate data of the cardiopulmonary resuscitation manipulator based on the instantaneous flow data.

[0043] In real-world scenarios, the acquisition of ventilation rate data in a cardiopulmonary resuscitation (CPR) manipulator can be achieved using an angle sensor installed in the manipulator's neck and a pressure-triggered sensor installed within the simulated airway channel. The angle sensor is installed at the joint connecting the manipulator's head and neck to detect the head tilt angle; the pressure-triggered sensor is embedded in the inner wall of the simulated airway channel (corresponding to the location of the human throat), employing a thin-film pressure sensor with a sensitivity set to 5-10 kPa.

[0044] When the trainee performs the head tilt and chin tuck maneuver, the angle sensor collects the head tilt angle data in real time. If the angle reaches 15-30° (which meets the standard angle range for human airway opening), and the pressure trigger sensor detects no foreign object blockage in the simulated airway causing abnormal pressure (i.e., the pressure value is within the normal range of 0-2 kPa), the airway is determined to be "fully open". If the head tilt angle is between 5-15°, or the pressure trigger sensor detects a slight pressure abnormality (2-5 kPa), the airway is determined to be "partially open". If the head tilt angle is less than 5°, or the pressure trigger sensor detects a pressure value greater than 5 kPa, the airway is determined to be "not open".

[0045] During ventilation, a bidirectional flow sensor collects real-time instantaneous flow data of gas inflow and outflow, transmitting the data to a relevant data processing module for integration to obtain the real-time ventilation flow integral value. Simultaneously, a volume sensor detects the displacement of the elastic diaphragm in the simulated lung cavity and, combined with preset volume parameters (e.g., the initial volume of the simulated lung cavity in an adult is set to 2-3L), calculates the real-time volume change of the simulated lung cavity. The data processing module performs a weighted fusion of the "flow integral value" and the "volume change" (weights set to 0.6 and 0.4 respectively, adjustable based on actual calibration data) to eliminate the influence of factors such as gas leakage and diaphragm elasticity errors, ultimately obtaining an accurate tidal volume detection value (detection range 50-1000mL, error controlled within ±3%).

[0046] The instantaneous flow rate data (unit: mL / s) collected by the bidirectional flow sensor is transmitted in real time to the data processing module. The module converts the instantaneous flow rate data into ventilation rate parameters using an algorithm—expressed as the "rate of change of ventilation volume per unit time," i.e., velocity value = instantaneous flow rate / cross-sectional area of ​​the simulated airway (the cross-sectional area of ​​the simulated airway is preset to 3-5 cm). 2(Matching adult airway size). At the same time, the module sets a standard range for ventilation rate (10-20 mL / s for adults and 5-15 mL / s for children). If the detected rate value exceeds the standard range, it will mark "too fast ventilation" or "too slow ventilation" in real time and record the duration of the abnormal rate.

[0047] Step S302: Use a blood oxygen saturation sensor to acquire the pulse blood oxygen waveform corresponding to the cardiopulmonary resuscitation manikin in real time. Determine the peripheral tissue area and filling color based on the peripheral perfusion simulation calculation results corresponding to the pulse blood oxygen waveform. Determine the cardiopulmonary resuscitation quality index data corresponding to the cardiopulmonary resuscitation manikin based on the pulse blood oxygen waveform, peripheral tissue area and filling color.

[0048] In a real-world scenario, the peripheral tissue region and fill color are determined based on the peripheral perfusion simulation calculation results corresponding to the pulse oximetry waveform. Then, based on the peripheral tissue region and fill color, the CPR quality index data corresponding to the CPR manikin is determined, while simultaneously displaying changes in the pulse oximetry waveform and determining blood oxygen saturation data based on the set disease state. This step utilizes a blood oxygen saturation sensor to acquire the CPR quality index (CQI) corresponding to the CPR manikin in real time. This is an indicator for assessing the quality of CPR, evaluating the operational quality of emergency responders by monitoring various parameters during the CPR process. Three-dimensional tissue images are obtained using the CQI results and a peripheral perfusion simulation algorithm.

[0049] When CQI ≥ 80, peripheral tissues (such as the finger projection area) are filled with pink (transparency = 30%); when CQI is 60-80, they are filled with orange (transparency = 50%); when CQI < 60, they are filled with blue (transparency = 70%) and a vascular texture blurring effect is superimposed (blurring = (90-SpO2) × 1%).

[0050] Specifically, the blood oxygen saturation sensor obtains the pulse blood oxygen waveform, and the area under the waveform curve is used to obtain the cardiopulmonary resuscitation quality index. The blood oxygen saturation value is the percentage of oxygenated hemoglobin. During cardiopulmonary resuscitation, the cardiopulmonary resuscitation quality index can reflect the quality of compressions, while blood oxygen saturation will decrease, but this is related to the underlying disease state, which will not be elaborated further.

[0051] Step S303: Use an electrocardiogram (ECG) monitoring sensor to acquire the ECG activity heart rate value corresponding to the cardiopulmonary resuscitation (CPR) manikin in real time. Based on the ECG activity heart rate value, determine the ECG activity frequency of the heart model of the CPR manikin and its corresponding heart color value and heart model beating frequency. Based on the ECG activity heart rate value, heart model ECG activity frequency, heart color value and heart model beating frequency, determine the heart model linkage data corresponding to the CPR manikin.

[0052] Specifically, this step utilizes electrocardiogram (ECG) monitoring sensors to acquire the real-time heart rate and electrical activity values ​​of the cardiopulmonary resuscitation (CPR) manikin. Based on these values, the ECG frequency of the CPR manikin's cardiac model is determined. Then, according to the established disease state, the corresponding heart color value and cardiac model beat frequency are determined. Finally, the linked data for the CPR manikin's cardiac model are determined based on the ECG heart rate and activity values, cardiac model ECG frequency, heart color value, and cardiac model beat frequency. It is worth noting that the heart rate value displayed by the ECG monitor only represents the state of electrical activity, not the actual heartbeat state, which depends on the actual contraction and relaxation capacity of the myocardium. One ECG manifestation of cardiac arrest is pulseless electrical activity (PEA), where there is electrical activity but no myocardial contraction.

[0053] In real-world scenarios, data collected by electrocardiogram (ECG) monitoring sensors can be processed to obtain results characterizing the degree of coronary artery blood supply, and these results can be integrated into the cardiac model's linked data.

[0054] This step mainly realizes the linkage between heart rate (HR, unit: beats / minute) and the heart model. The heart model's beating frequency can be controlled by a dynamic mesh deformation algorithm. When HR is between 60 and 100 beats / minute, the heart model's contraction amplitude is 5mm (mesh vertex displacement); when HR > 100 beats / minute, the contraction amplitude increases to 8mm and the color becomes reddish (H:0, S:30%, L:70%); when HR < 60 beats / minute, the contraction amplitude decreases to 3mm and the color becomes purplish (H:270, S:30%, L:70%).

[0055] Step S304: Use an ECG monitoring sensor to acquire ECG data corresponding to the cardiopulmonary resuscitation manikin in real time. Determine the spectral area of ​​the ECG data and its corresponding display strategy parameters based on the fast Fourier transform results of the ECG data. Determine the ECG spectral data corresponding to the cardiopulmonary resuscitation manikin based on the ECG data, the spectral area of ​​the ECG data, and the display strategy parameters.

[0056] The ECG waveform spectral area in this step is calculated using a frequency integral correlation algorithm. The original waveform (sampling rate 500Hz) acquired by the ECG monitoring sensor is subjected to a Fast Fourier Transform, and the power spectrum integral of the 0.5-30Hz frequency band is taken as the amplitude spectral area. When the area is <0.5mV·s, the 3D ECG waveform projection is fragmented (segment breakage rate = 50%); when it is 0.5-1.5mV·s, the waveform is continuous and smooth (radius of curvature = 50 pixels); when it is >1.5mV·s, the waveform is thickened (line width = 3 pixels) and highlighted.

[0057] Step S305: Use the end-tidal carbon dioxide sensor to acquire the end-tidal carbon dioxide partial pressure value of the cardiopulmonary resuscitation manikin in real time, and determine the display area corresponding to the lung model based on the surface data of the lung model of the cardiopulmonary resuscitation manikin; determine the display effect and display color corresponding to the end-tidal carbon dioxide partial pressure value in the display area through the preset partial pressure threshold relationship; determine the end-tidal carbon dioxide partial pressure data based on the end-tidal carbon dioxide partial pressure value, display area, display effect and display color.

[0058] The end-tidal carbon dioxide partial pressure (PetCO2, mmHg) is converted into a three-dimensional dynamic image using a respiratory-circulatory correlation algorithm: When PetCO2 is between 35-45 mmHg (normal range), a smooth blue waveform (wavelength = 200 pixels, amplitude = 30 pixels) is generated and superimposed on the surface of the 3D lung model (fluctuating synchronously with respiratory movements); when PetCO2 < 35 mmHg (e.g., hyperventilation or circulatory failure), the waveform turns light blue and the amplitude decreases to 15 pixels, while a white hazy effect appears at the edge of the lung model (haze concentration = (35 - PetCO2) × 2%); when PetCO2 > 45 mmHg (e.g., hypoventilation), the waveform turns dark blue and the amplitude increases to 45 pixels, and orange warning stripes are superimposed on the surface of the lung model (stripe density = (PetCO2 - 45) × 5 stripes / cm). 2 When PetCO2 < 10 mmHg (e.g., poor resuscitation quality), the waveform turns gray and the amplitude drops to 5 pixels, while orange warning stripes are superimposed on the surface of the lung model (stripe density = (PetCO2 - 45) × 5 stripes / cm). 2 ).

[0059] Step S306: Determine the simulated physiological data based on ventilation rate data, cardiopulmonary resuscitation quality index data, cardiac model linkage data, electrocardiogram spectrum data, and end-tidal carbon dioxide partial pressure data.

[0060] The cardiopulmonary resuscitation quality index data is determined based on the cardiopulmonary resuscitation quality index, peripheral tissue area, and fill color; the cardiac model linkage data is determined based on heart rate value, cardiac model beat frequency, heart color value, and cardiac model beat frequency; the electrocardiogram (ECG) spectrum data is determined based on ECG data, ECG data spectrum area, and display strategy parameters; and the end-tidal carbon dioxide partial pressure (UTC) data is determined based on end-tidal UTC value, display area, display effects, and display color. By integrating the above data, simulated physiological data can be obtained.

[0061] Optionally, a blood oxygen saturation sensor can be used to obtain the cardiopulmonary resuscitation quality index corresponding to the cardiopulmonary resuscitation manikin in real time, such as... Figure 4 As shown, it includes: Step S401: Use a blood oxygen saturation sensor to acquire the pulse blood oxygen saturation, pulse blood oxygen waveform and area under the curve of the cardiopulmonary resuscitation manikin in real time. Step S402: Determine the cardiopulmonary resuscitation quality index by measuring the pulse oxygen waveform and its area under the curve.

[0062] In determining the quality index of cardiopulmonary resuscitation, this method integrates pulse oximetry waveforms and other data, converting them into three-dimensional images displayed on a holographic projector. This data can be wirelessly transmitted to the holographic projector for display.

[0063] Optionally, data processing step S103, such as Figure 5 As shown, it includes: Step S501: Determine the bottom display area, lower middle display area, middle display area and top display area corresponding to the display area based on the height value of the display area in the holographic projector; Step S502: Determine the first display parameters corresponding to the bar chart, fluctuation curve and rebound arrow in the underlying display area based on the press data, and generate the underlying image data corresponding to the press data based on the first display parameters; Step S503: Determine the second display parameters corresponding to the end-tidal carbon dioxide waveform data and the lung model associated image in the middle and lower layer display area based on the end-tidal carbon dioxide partial pressure data, and generate the middle and lower layer image data corresponding to the end-tidal carbon dioxide waveform data based on the second display parameters. Step S504: Determine the blood oxygen tissue image in the mid-layer display area and the third display parameter corresponding to the heart model based on the heart model linkage data, and generate the mid-layer image data corresponding to the heart model linkage data based on the third display parameter; Step S505: Obtain the warning information contained in the compression data, cardiac model linkage data and end-tidal carbon dioxide partial pressure data, and generate the warning image data corresponding to the top display area based on the warning information; Step S506: Determine the three-dimensional image data corresponding to the holographic projector based on the bottom layer image data, the middle and lower layer image data, the middle layer image data, and the early warning image data; Step S507: Control the holographic projector to display the three-dimensional image data in the display area according to the preset refresh rate.

[0064] The above steps primarily enable the display of compression data and simulated physiological data on a holographic projector. Compression data is displayed in real-time as a bar chart showing compression depth, as a fluctuation curve showing frequency changes, and as an arrow animation showing rebound speed. Simulated physiological data displays pulse oximetry parameters related to peripheral tissue perfusion, presents heart rate in a combination of digital and 3D cardiac data, and presents electrocardiogram changes as a waveform. End-tidal carbon dioxide waveform data is presented as waveforms, digital and 3D respiratory movements, and circulatory changes, and can be displayed together with existing operational indicator images.

[0065] Specifically, a spatial layered rendering strategy can be adopted, which determines the bottom layer, lower middle layer, middle layer, and top layer of the display area based on the height value of the display area in the holographic projector, thus obtaining four display layers.

[0066] Specifically, the bottom display area (Z=0) displays operation indicators (bar chart, fluctuation curve, rebound arrow), aligned according to the anatomical position of the chest (the bar chart is located in the sternal projection area, and the curve is located in the right thoracic cage). The lower-middle display area (Z=30 pixels) displays the end-tidal carbon dioxide waveform and related lung images, which are spatially aligned with the 3D heart model (middle layer) (the waveform is located directly in front of the lung model, at a distance of 20 pixels) to ensure the visual relevance of "cardiopulmonary interaction" (e.g., when compression is effective, the PetCO2 waveform amplitude changes synchronously with the heart rate). The middle layer display area (Z=50 pixels) displays physiological parameters (blood oxygen tissue images, 3D heart model), superimposed on the corresponding anatomical locations (finger, chest cavity); The top-level display area (Z=100 pixels) displays warning information (such as a flashing red border). When any indicator exceeds the threshold, a semi-transparent warning box (transparency=60%) is rendered on the top layer of the corresponding area.

[0067] Each layer maintains a consistent frame rate (30fps) through a synchronous rendering engine, ensuring that operation and image latency is ≤0.1 seconds.

[0068] Trainees can adjust their operations in real time through the holographic images of the holographic projector. For example, when the compression depth is insufficient, the bar graph will show a red warning and flash. When the frequency is too fast, the curve will show fluctuations. When the pulse oxygenation-related parameters are lower than the preset standard, the peripheral perfusion will turn orange and flash. When the heart rate is abnormal, the corresponding numbers and 3D heart will show obvious color changes and fluctuations. When the end-tidal carbon dioxide is abnormal, circulation abnormalities and obvious waveform changes will appear. Trainees can adjust their operations based on the feedback from these physiological parameters.

[0069] During the processing and display of ventilation rate data, preset algorithms (such as Kalman filtering algorithm and weighted fusion algorithm) are used for data noise reduction, calibration and calculation to obtain the final detection results of airway opening and closing status, tidal volume, ventilation rate and intrathoracic pressure; holographic 3D images display the numerical values, dynamic curves and operation scores of each ventilation data in real time (the scoring standard is set according to the degree of deviation between the data and the standard value, with a full score of 100 points), so that trainees can intuitively see their own operation problems; the wireless communication module supports the real-time transmission of data to the teacher's terminal device (such as computer, tablet), which facilitates remote guidance by teachers and batch comparison and analysis of trainees' operation data.

[0070] Optionally, the CPR manikin also includes defibrillation electrodes; in this case, the training procedure S102 is as follows: Figure 6 As shown, it also includes: Step S601: Defibrillate the cardiopulmonary resuscitation manikin using defibrillation electrode pads, and collect simulated electrocardiogram data in real time using an electrocardiogram monitoring sensor; Step S602: Determine the defibrillation energy, defibrillation timing, and amplitude spectral area of ​​the cardiopulmonary resuscitation manikin based on the simulated electrocardiogram data, and use the defibrillation energy, defibrillation timing, and amplitude spectral area of ​​the cardiopulmonary resuscitation manikin to determine the defibrillation data corresponding to the simulated electrocardiogram data.

[0071] Defibrillation differs from chest compressions. When a trainee performs defibrillation, defibrillation electrodes are used on a CPR manikin. During this process, an ECG monitoring sensor collects simulated ECG data in real time. This data is then used to determine the defibrillation energy, timing, and amplitude spectrum area of ​​the CPR manikin. A dynamic correlation curve is generated using this data (e.g., when the defibrillation energy is sufficient, the slope of the amplitude spectrum area increases over time). The defibrillation data corresponding to the simulated ECG data is then obtained using this dynamic correlation curve.

[0072] Optionally, data processing step S103 is as follows: Figure 7 As shown, it also includes: Step S701: Determine the fourth display parameter corresponding to the defibrillation current path and amplitude spectrum area change in the mid-layer display area based on the defibrillation data, and generate defibrillation image data corresponding to the simulated physiological data based on the fourth display parameter; Step S702: Obtain the fit misalignment data and energy warning data contained in the defibrillation data, and generate defibrillation warning image data corresponding to the top display area based on the fit misalignment data and energy warning data; Step S703: Determine the three-dimensional image data corresponding to the holographic projector based on the defibrillation image data and defibrillation warning image data, and control the holographic projector to display the three-dimensional image data in the middle display area according to the preset same refresh rate.

[0073] During the defibrillation holographic projection process, the holographic projector transforms the defibrillation process into a three-dimensional image, such as displaying the defibrillation current path with red pulse animation, and reflecting the amplitude area change in real time with the height of the three-dimensional spectrum column (blue when below the threshold, green when reaching the standard), and superimposed with the original operating indicators and physiological parameters.

[0074] During defibrillation feedback adjustment, if the defibrillation electrode pads are misaligned, the defibrillation point in the holographic image will flash a red warning, and the amplitude area will not change significantly; if the energy is insufficient, the spectral column will rise slowly and be accompanied by a yellow warning, prompting the trainee to adjust the operation.

[0075] Optionally, the CPR manikin is also connected to a projection screen; the data processing steps in this case also include: generating two-dimensional image data corresponding to the projection screen based on compression data and simulated physiological data, and controlling the display of the two-dimensional image data on the projection screen. In real-world scenarios, such as team training where multiple people need to observe simultaneously, a holographic projector is insufficient. Therefore, a projection screen is used to ensure that multiple people can simultaneously and clearly obtain feedback information.

[0076] The technical effects of the above-mentioned cardiopulmonary resuscitation training and control methods are as follows: 1. This technology enables real-time, intuitive feedback of high-quality quantitative indicators for cardiopulmonary resuscitation (CPR), including operational indicators and physiological parameters, through holographic 3D projection. Operational indicators such as compression depth, frequency, and rebound are collected using pressure and accelerometers, while physiological parameters are acquired using blood oxygen saturation and electrocardiogram (ECG) sensors. After data processing, all indicators are converted into three-dimensional images and projected in real-time by a holographic projector. Compared to the fragmented and delayed feedback of existing technologies, this technology achieves instant visual integration of "operation-indicator-feedback," directly improving training efficiency and accuracy, which is key to delivering the core beneficial effects.

[0077] 2. Linkage Detection and Feedback Mechanism between Operational Indicators and Physiological Parameters. This method establishes a correlation between operational indicators (such as compression depth and frequency) and physiological parameters (such as the cardiopulmonary resuscitation quality index, heart rate, and end-tidal carbon dioxide), enabling changes in physiological parameters in the holographic projection to reflect operational quality in real time. For example, when compressions are performed correctly, blood oxygen saturation increases and heart rate recovers systematically. This linkage makes training more closely resemble clinical practice, helping learners understand the impact of the operation on the "patient's" physiological state, and is a key technology for enhancing the realism of training.

[0078] 3. Multi-sensor collaborative acquisition and data integration processing. This method integrates multiple sensors, including pressure sensors, acceleration sensors, blood oxygen saturation sensors, and electrocardiogram monitoring sensors. By synchronously acquiring, analyzing, and integrating multi-source data, it ensures the accuracy and timeliness of various indicator data. This technology provides a data foundation for the precise feedback of holographic projection and is a supporting innovation for the effective presentation of all quantitative indicators. 4. Holographic projection and data transmission solution adaptable to multiple scenarios. This solution can use a wide-angle holographic projector and a suitable projection screen (or alternative display device), combined with efficient wireless transmission technology (such as Bluetooth or Wi-Fi), to meet the needs of multiple scenarios such as single-person training and team collaboration, ensuring that multiple people can simultaneously and clearly obtain feedback information, thus improving the practicality and scalability of the solution.

[0079] 5. Linked Feedback Between Defibrillation Module and ECG Amplitude Spectrum Area. Defibrillation operation parameters are collected using defibrillation electrodes and a high-voltage pulse simulator. Combined with ECG amplitude spectrum analysis, the intensity of myocardial electrical activity is calculated. After data integration, the dynamic correlation between "defibrillation and ECG changes" is presented via holographic projection. Compared to existing technologies that can only simulate defibrillation actions, this technology achieves quantitative visualization of defibrillation effects, filling the gap in "coordinated training of defibrillation and cardiopulmonary resuscitation," and is key to improving the clinical relevance of training.

[0080] 6. Multimodal Data Conversion and Rendering Algorithm for Holographic Projection. This method transforms discrete operational indicators and physiological parameters into spatially correlated 3D images through algorithms such as linear mapping, Fourier transform, and dynamic mesh deformation. It then achieves intuitive fusion of multiple indicators based on a layered rendering strategy according to anatomical location. Compared to the simple numerical or 2D graphical feedback in existing technologies, this algorithm system achieves a deep transformation from "quantitative data to visualized images to clinical significance," which is key to improving training immersion and accuracy.

[0081] Corresponding to the above embodiments of the cardiopulmonary resuscitation training control method, this embodiment of the invention also provides a cardiopulmonary resuscitation training control system, such as... Figure 8 As shown, the system includes: Startup processing control module 810: used to control the cardiopulmonary resuscitation manikin and holographic projector to be in working state; wherein, the cardiopulmonary resuscitation manikin is connected to the holographic projector; the cardiopulmonary resuscitation manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor and an end-tidal carbon dioxide sensor; Training Operation Control Module 820: Used to control the compression of the cardiopulmonary resuscitation manikin, using pressure and acceleration sensors to acquire compression data in real time, and using bidirectional flow sensors, blood oxygen saturation sensors, electrocardiogram monitoring sensors and end-tidal carbon dioxide sensors to acquire simulated physiological data in real time; Data processing control module 830: used to generate three-dimensional image data corresponding to the holographic projector based on the pressure data and simulated physiological data, and to control the display of the three-dimensional image data in the holographic projector.

[0082] As can be seen from the above cardiopulmonary resuscitation training and control system, the system adds a holographic 3D projection feedback function during the cardiopulmonary resuscitation training process. By converting the operation indicators such as compression depth, frequency, and rebound of the cardiopulmonary resuscitation simulator, as well as related physiological parameters, into holographic 3D images in real time, the operation data is presented intuitively and synchronously, which significantly improves the training effect and teaching efficiency.

[0083] The cardiopulmonary resuscitation (CPR) training and control system provided in this embodiment of the invention has the same implementation principle and technical effects as the aforementioned CPR training and control method embodiment. For the sake of brevity, any parts not mentioned in the system embodiment can be referred to the corresponding content in the aforementioned CPR training and control method embodiment.

[0084] This embodiment also provides a cardiopulmonary resuscitation (CPR) simulation device, the structural schematic diagram of which is shown below. Figure 9 As shown, the cardiopulmonary resuscitation (CPR) simulation device includes: a CPR mannequin 1, a holographic projector 5, and a data processing module 4; wherein the data processing module 4 is connected to both the CPR mannequin 1 and the holographic projector 5. In addition, it includes a pressure sensor 2, an acceleration sensor 3, a blood oxygen saturation sensor 8, an electrocardiogram monitoring sensor 9, and an end-tidal carbon dioxide sensor 10; it also includes defibrillation electrodes 11, a high-voltage pulse simulator 12, a projection screen 6, and a power supply module 7.

[0085] Specifically, the cardiopulmonary resuscitation manikin 1 is the manikin body (including simulated structures such as the torso, chest, and airway); the pressure sensor 2 is built into the manikin's chest to detect compression depth; the accelerometer 3 is installed on the surface of the chest to capture compression frequency and rebound speed; the data processing module 4 is located inside the manikin's torso and is connected to the sensor via wires; the holographic projector 5 is placed next to the manikin and is connected to the data processing module via wireless signals; the projection screen 6 is foldable and is set opposite to the projector to display holographic images; and the power module 7 supplies power to the sensors, data processing module, and holographic projector, and is connected to each component via wires. The blood oxygen saturation sensor 8 is worn on the finger of the mannequin to monitor simulated blood oxygen saturation, pulse oxygen waveform, CQI, etc.; the electrocardiogram monitoring sensor 9 is attached to the chest of the mannequin to monitor simulated heart rate, electrocardiogram waveform, etc.; the end-tidal carbon dioxide sensor 10 is connected to the endotracheal tube after the advanced airway is established to monitor simulated end-tidal carbon dioxide waveform, etc.; the defibrillation electrode pads 11 are attached to the defibrillation points on the chest of the mannequin to simulate electrode contact during defibrillation; the high-voltage pulse simulator 12 is built into the torso of the mannequin and connected to the defibrillation electrode pads to simulate defibrillation pulse output; the electrocardiogram amplitude spectrum analysis submodule is integrated into the data processing module 4 to calculate the electrocardiogram amplitude spectrum area in real time, reflecting the intensity of myocardial electrical activity.

[0086] Pressure sensor 2 and accelerometer 3 are connected to the signal input terminal of data processing module 4 via embedded wires to transmit raw data of pressing depth, frequency, and rebound in real time. The signal output terminal of data processing module 4 is connected to holographic projector 5 via a wireless transmission module (such as Bluetooth) to convert the processed quantitative indicators into projection signals. Holographic projector 5 and projection screen 6 are placed opposite each other, with the projection direction facing the trainee's operating area to ensure that the image is clearly visible within the trainee's field of vision. Power module 7 is connected to pressure sensor 2, accelerometer 3, data processing module 4, and holographic projector 5 via branch wires to provide stable power supply.

[0087] The blood oxygen saturation sensor 8 is connected to the signal input terminal of the data processing module 4 via a wire, transmitting the detected simulated pulse blood oxygen related data to the data processing module 4 in real time; the electrocardiogram monitoring sensor 9 is also connected to the signal input terminal of the data processing module 4 via a wire, transmitting simulated heart rate, electrocardiogram waveform and other data to the data processing module 4; the end-tidal carbon dioxide sensor 10 is also connected to the signal input terminal of the data processing module 4 via a wire, transmitting simulated end-tidal carbon dioxide waveform and other data to the data processing module 4.

[0088] The defibrillation electrode pads 11 are connected to the high-voltage pulse simulator 12 via wires. The control terminal of the high-voltage pulse simulator 12 is connected to the data processing module 4 to receive defibrillation trigger signals (such as trigger commands when the trainee performs defibrillation actions). The raw ECG waveform data collected by the ECG monitoring sensor 9 is synchronously transmitted to the ECG amplitude spectrum analysis submodule. After calculating the amplitude spectrum area (unit: mV·s), the analysis submodule feeds back the result to the data processing module 4. The data processing module 4 integrates the defibrillation pulse parameters (such as energy and timing) with the ECG amplitude spectrum area data to generate a linkage feedback signal, which is transmitted to the holographic projector 5.

[0089] like Figure 10 As shown, the data processing module includes a processor 101 and a memory 102; wherein, the memory 102 is used to store one or more computer instructions, which are executed by the processor to implement the steps of the cardiopulmonary resuscitation training control method described above.

[0090] Figure 10 The cardiopulmonary resuscitation simulation device shown also includes a bus 103 and a communication interface 104. The processor 101, the communication interface 104 and the memory 102 are connected through the bus 103.

[0091] The memory 102 may include high-speed random access memory (RAM) and may also include non-volatile memory, such as at least one disk storage device. The bus 103 may be an ISA bus, PCI bus, or EISA bus, etc. The bus can be divided into address bus, data bus, control bus, etc. For ease of representation, Figure 10 The symbol is represented by a single double-headed arrow, but this does not mean that there is only one bus or one type of bus.

[0092] The communication interface 104 is used to connect to at least one user terminal and other network units through a network interface, and to send encapsulated IPv4 packets or IPv4 packets to the user terminal through the network interface.

[0093] Processor 101 may be an integrated circuit chip with signal processing capabilities. In implementation, each step of the above method can be completed by the integrated logic circuitry in the hardware of processor 101 or by instructions in software form. The processor 101 can be a general-purpose processor, including a Central Processing Unit (CPU), a Network Processor (NP), etc.; it can also be a Digital Signal Processor (DSP), an Application Specific Integrated Circuit (ASIC), a Field-Programmable Gate Array (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. It can implement or execute the methods, steps, and logic block diagrams disclosed in the embodiments of this disclosure. The general-purpose processor can be a microprocessor or any conventional processor. The steps of the methods disclosed in the embodiments of this disclosure can be directly manifested as execution by a hardware decoding processor, or execution by a combination of hardware and software modules in the decoding processor. The software module can reside in a mature storage medium in the art, such as random access memory, flash memory, read-only memory, programmable read-only memory, electrically erasable programmable memory, or registers. This storage medium is located in memory 102. The processor 101 reads the information in memory 102 and, in conjunction with its hardware, completes the steps of the method described in the foregoing embodiments.

[0094] This invention also provides a storage medium storing a computer program, which, when run by a processor, executes the steps of the cardiopulmonary resuscitation training control method described in the foregoing embodiments.

[0095] In the several embodiments provided in this application, it should be understood that the disclosed systems, apparatuses, devices, and methods can be implemented in other ways. The system embodiments described above are merely illustrative. For example, the division of units is only a logical functional division, and in actual implementation, there may be other division methods. Furthermore, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Additionally, the coupling or direct coupling or communication connection shown or discussed may be through some communication interfaces; the indirect coupling or communication connection between devices or units may be electrical, mechanical, or other forms.

[0096] The units described as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0097] In addition, the functional units in the various embodiments of the present invention can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit.

[0098] If the aforementioned functions are implemented as software functional units and sold or used as independent products, they can be stored in a processor-executable, non-volatile, computer-readable storage medium. Based on this understanding, the technical solution of this invention, or the part that contributes to the prior art, or a portion of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of this invention. The aforementioned storage medium includes various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0099] Finally, it should be noted that the above-described embodiments are merely specific implementations of the present invention, used to illustrate the technical solutions of the present invention, and not to limit it. The scope of protection of the present invention is not limited thereto. Although the present invention has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that any person skilled in the art can still modify or easily conceive of changes to the technical solutions described in the foregoing embodiments within the technical scope disclosed in the present invention, or make equivalent substitutions for some of the technical features; and these modifications, changes, or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of the present invention, and should all be covered within the scope of protection of the present invention. Therefore, the scope of protection of the present invention should be determined by the scope of the claims.

Claims

1. A method for controlling cardiopulmonary resuscitation training, characterized in that, The method includes: Initiation process: Control the cardiopulmonary resuscitation (CPR) manikin and holographic projector to be in working state; wherein, the CPR manikin is connected to the holographic projector; the CPR manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram (ECG) monitoring sensor, and an end-tidal carbon dioxide sensor; Training operation steps: Press the cardiopulmonary resuscitation manikin, use the pressure sensor and the acceleration sensor to acquire compression data in real time, and use the bidirectional flow sensor, the blood oxygen saturation sensor, the electrocardiogram monitoring sensor and the end-tidal carbon dioxide sensor to acquire simulated physiological data in real time; Data processing steps: Generate three-dimensional image data corresponding to the holographic projector based on the pressure data and the simulated physiological data, and control the display of the three-dimensional image data in the holographic projector.

2. The cardiopulmonary resuscitation training control method according to claim 1, characterized in that, Real-time acquisition of compression data using the pressure sensor and the acceleration sensor includes: The compression depth corresponding to the cardiopulmonary resuscitation manikin is acquired in real time using the pressure sensor. The height value and color value of the bar chart corresponding to the compression depth are calculated according to the preset linear mapping relationship. The compression depth data corresponding to the cardiopulmonary resuscitation manikin is determined based on the compression depth, the height value of the bar chart, and the color value of the bar chart. The compression interval time corresponding to the cardiopulmonary resuscitation (CPR) manifold is acquired in real time using the accelerometer. The compression frequency of the CPR manifold is determined based on the Fourier transform curve corresponding to the compression interval time. The compression frequency data corresponding to the CPR manifold is determined based on the compression interval time, the Fourier transform curve, and the compression frequency. The accelerometer is used to acquire the rebound velocity and rebound height of the cardiopulmonary resuscitation manikin in real time. The arrow length and arrow color value corresponding to the rebound velocity and rebound height are calculated according to the preset velocity threshold relationship. The rebound data corresponding to the cardiopulmonary resuscitation manikin is determined based on the rebound velocity, the rebound height, the arrow length and the arrow color value. The pressing data is determined based on the pressing depth data, the pressing frequency data, and the rebound data.

3. The cardiopulmonary resuscitation training control method according to claim 1, characterized in that, The system utilizes the bidirectional flow sensor, the blood oxygen saturation sensor, the electrocardiogram monitoring sensor, and the end-tidal carbon dioxide sensor to acquire simulated physiological data in real time, including: The bidirectional flow sensor is used to acquire the instantaneous flow data of the cardiopulmonary resuscitation manipulator during chest compressions in real time, and the ventilation rate data corresponding to the cardiopulmonary resuscitation manipulator is determined based on the instantaneous flow data. The pulse oximetry waveform corresponding to the cardiopulmonary resuscitation manikin is acquired in real time using the blood oxygen saturation sensor. The peripheral tissue region and filling color are determined based on the peripheral perfusion simulation calculation results corresponding to the pulse oximetry waveform. The cardiopulmonary resuscitation quality index data corresponding to the cardiopulmonary resuscitation manikin is determined based on the pulse oximetry waveform, the peripheral tissue region and the filling color. The electrocardiogram (ECG) monitoring sensor is used to acquire the ECG activity heart rate value corresponding to the cardiopulmonary resuscitation (CPR) manikin in real time. Based on the ECG activity heart rate value, the ECG activity frequency of the heart model of the CPR manikin and its corresponding heart color value and heart model beating frequency are determined. Based on the ECG activity heart rate value, the ECG activity frequency of the heart model, the heart color value and the heart model beating frequency, the heart model linkage data corresponding to the CPR manikin is determined. The ECG monitoring sensor is used to acquire ECG data corresponding to the cardiopulmonary resuscitation manikin in real time. The spectral area of ​​the ECG data and its corresponding display strategy parameters are determined based on the fast Fourier transform result of the ECG data. The ECG spectral data corresponding to the cardiopulmonary resuscitation manikin is determined based on the ECG data, the spectral area of ​​the ECG data and the display strategy parameters. The end-tidal carbon dioxide sensor is used to acquire the end-tidal carbon dioxide partial pressure value corresponding to the cardiopulmonary resuscitation manikin in real time. The display area corresponding to the lung model is determined based on the surface data of the lung model of the cardiopulmonary resuscitation manikin. The display effect and display color corresponding to the end-tidal carbon dioxide partial pressure value in the display area are determined by a preset partial pressure threshold relationship. The end-tidal carbon dioxide partial pressure data is determined based on the end-tidal carbon dioxide partial pressure value, the display area, the display effect, and the display color. The simulated physiological data are determined based on the ventilation rate data, the cardiopulmonary resuscitation quality index data, the cardiac model linkage data, the electrocardiogram spectrum data, and the end-tidal carbon dioxide partial pressure data.

4. The cardiopulmonary resuscitation training control method according to claim 3, characterized in that, The blood oxygen saturation sensor is used to obtain the cardiopulmonary resuscitation quality index corresponding to the cardiopulmonary resuscitation manikin in real time, including: The pulse oxygen saturation sensor is used to acquire the pulse oxygen saturation, pulse oxygen waveform, and area under the curve of the cardiopulmonary resuscitation manipulator in real time. The cardiopulmonary resuscitation quality index is determined by the pulse oxygen saturation, the pulse oxygen waveform, and the area under the curve.

5. The cardiopulmonary resuscitation training control method according to claim 3, characterized in that, The data processing steps include: The bottom display area, lower middle display area, middle display area, and top display area corresponding to the display area are determined based on the height value of the display area in the holographic projector. Based on the press data, determine the first display parameters corresponding to the bar chart, fluctuation curve and rebound arrow in the underlying display area, and generate the underlying image data corresponding to the press data based on the first display parameters; Based on the end-tidal carbon dioxide partial pressure data, determine the second display parameters corresponding to the end-tidal carbon dioxide waveform data and the lung model associated image in the middle and lower layer display area, and generate the middle and lower layer image data corresponding to the end-tidal carbon dioxide waveform data based on the second display parameters; Based on the cardiac model linkage data, the third display parameters corresponding to the blood oxygen tissue image and the cardiac model in the middle layer display area are determined, and the middle layer image data corresponding to the cardiac model linkage data is generated based on the third display parameters. The system acquires the warning information contained in the compression data, the cardiac model linkage data, and the end-tidal carbon dioxide partial pressure data, and generates warning image data corresponding to the top-level display area based on the warning information. The three-dimensional image data corresponding to the holographic projector is determined based on the bottom layer image data, the middle and lower layer image data, the middle layer image data, and the early warning image data; The holographic projector displays the three-dimensional image data in the display area according to the preset refresh rate.

6. The cardiopulmonary resuscitation training control method according to claim 5, characterized in that, The cardiopulmonary resuscitation manikin also includes defibrillation electrodes; The training operation steps also include: The defibrillation electrode pads are used to defibrillate the cardiopulmonary resuscitation manikin, and the electrocardiogram monitoring sensor is used to collect simulated electrocardiogram data in real time. The defibrillation energy, defibrillation timing, and amplitude spectral area of ​​the cardiopulmonary resuscitation manipulator are determined based on the simulated electrocardiogram data, and the defibrillation data corresponding to the simulated electrocardiogram data are determined using the defibrillation energy, the defibrillation timing, and the amplitude spectral area of ​​the cardiopulmonary resuscitation manipulator.

7. The cardiopulmonary resuscitation training control method according to claim 6, characterized in that, The data processing steps also include: Based on the defibrillation data, the fourth display parameter corresponding to the defibrillation current path and amplitude spectrum area change in the middle layer display area is determined, and defibrillation image data corresponding to the simulated physiological data is generated based on the fourth display parameter. Acquire the fit misalignment data and energy warning data contained in the defibrillation data, and generate defibrillation warning image data corresponding to the top display area based on the fit misalignment data and the energy warning data; Based on the defibrillation image data and the defibrillation warning image data, the three-dimensional image data corresponding to the holographic projector is determined, and the holographic projector is controlled to display the three-dimensional image data in the middle layer display area according to the same preset refresh rate.

8. The cardiopulmonary resuscitation training control method according to claim 1, characterized in that, The cardiopulmonary resuscitation manikin is also connected to a projection screen; The data processing steps also include: Based on the pressure data and the simulated physiological data, two-dimensional image data corresponding to the projection screen is generated, and the two-dimensional image data is controlled to be displayed on the projection screen.

9. A cardiopulmonary resuscitation training and control system, characterized in that, The system includes: Startup processing control module: used to control the cardiopulmonary resuscitation manikin and holographic projector to be in working state; wherein, the cardiopulmonary resuscitation manikin is connected to the holographic projector; the cardiopulmonary resuscitation manikin is equipped with at least a pressure sensor, an acceleration sensor, a bidirectional flow sensor, a blood oxygen saturation sensor, an electrocardiogram monitoring sensor and an end-tidal carbon dioxide sensor; Training operation control module: used to control the compression of the cardiopulmonary resuscitation manikin, to acquire compression data in real time using the pressure sensor and the acceleration sensor, and to acquire simulated physiological data in real time using the bidirectional flow sensor, the blood oxygen saturation sensor, the electrocardiogram monitoring sensor and the end-tidal carbon dioxide sensor; Data processing and control module: used to generate three-dimensional image data corresponding to the holographic projector based on the pressing data and the simulated physiological data, and to control the display of the three-dimensional image data in the holographic projector.

10. A cardiopulmonary resuscitation (CPR) simulation device, characterized in that, The cardiopulmonary resuscitation (CPR) simulation device includes: a CPR manikin, a holographic projector, and a data processing module; wherein the data processing module is connected to both the CPR manikin and the holographic projector. The data processing module includes a processor and a memory. The memory stores computer-executable instructions that can be executed by the processor. The processor executes the computer-executable instructions to implement the steps of the cardiopulmonary resuscitation training control method according to any one of claims 1 to 8.

Images