Intelligent scene type CPR visual training system based on MR technology

Abstract

The invention discloses an intelligent scene type CPR visual training system based on an MR technology, which belongs to the technical field of non-special measurement for specific variables and comprises a training request sensing module, an intelligent scene automatic generation module, a sensing data acquisition module, a visual display and voice prompt module and a network performance evaluation management and control module. According to the method, the performance parameters of the sensing source nodes built in the simulation human body model are acquired and analyzed in real time, so that the data feedback precision in the training process is improved, and the data feedback precision in the training process is further improved; the problem of poor CPR visual training experience caused by lack of real-time performance monitoring and feedback mechanisms in the prior art is effectively solved.

Description

Technical Field

[0001] This invention relates to the field of measurement technology that is not specific to a particular variable, and in particular to an intelligent scenario-based CPR visualization training system based on MR technology. Background Technology

[0002] As people's demand for life safety and health protection increases, they have begun to use MR technology to assist in CPR visualization training. MR technology refers to Mixed Reality (MR) technology, which is used to build realistic virtual first aid scenarios. CPR refers to cardiopulmonary resuscitation.

[0003] Existing CPR training systems use portable trainers, but trainers cannot intuitively understand whether their CPR operations are standardized and effective, nor can they correct their mistakes in a timely manner. This not only reduces the training effect but also affects the trainers' experience.

[0004] For example, CN111768671A discloses a portable CPR trainer with depth and rate detection functions and a compression displacement detection method. This includes an upper component and a lower component, with an elastic element between them. Either the upper or lower component has a detection device for displacement detection, and the other has a scale adapted to the detection device. The detection device contains at least two optical couplers, which are coaxial vertically or offset vertically on either side of the scale. The scale has spaced black and white markings, and the vertical distance between the two optical couplers is less than the width of the black (transparent) markings on the scale. This invention has a simple structure and small size, and can display the two most important indicators in CPR training in real time: rate and depth. The most basic requirement for CPR training for the general public is that trainees should be able to perform effective compressions at an appropriate rate and depth during CPR.

[0005] For example, the portable CPR trainer with depth and rate detection function disclosed in CN212365234U includes: an upper part and a lower part, with an elastic element between the upper and lower parts. Either the upper or lower part is equipped with a detection device for detecting displacement, and the other part is equipped with a scale adapted to the detection device. The detection device contains at least two optical couplers, which are coaxially arranged vertically or axially staggered. The scale has spaced black and white markings, and the vertical distance between the two optical couplers is less than the width of the black markings on the scale. This utility model has a simple structure and small size, and can display the two most important indicators in CPR training in real time: rate and depth. The most basic requirement for CPR training for the general public is that trainees should be able to "perform effective compressions at an appropriate rate and depth during CPR."

[0006] However, in the process of implementing the inventive technical solution in the embodiments of this application, it was found that the above-mentioned technology has at least the following technical problems: In existing technologies, trainees cannot intuitively understand whether their CPR operations are standardized and effective, nor can they correct their mistakes in a timely manner, which reduces the training effect. There is a problem of poor CPR visualization training experience due to the lack of real-time performance monitoring and feedback mechanisms. Summary of the Invention

[0007] This application provides an intelligent scenario-based CPR visualization training system based on MR technology, which solves the problem of poor CPR visualization training experience caused by the lack of real-time performance monitoring and feedback mechanisms in the prior art, and realizes real-time monitoring of the operation of simulated human models and improves data accuracy.

[0008] This application provides an intelligent scenario-based CPR visualization training system based on MR technology, including: a training request perception module, an intelligent scene automatic generation module, a sensor data acquisition module, and a visualization display and voice prompt module. The training request perception module receives training request signals transmitted by personnel, marks the personnel transmitting the training request signals as trainees, and obtains the scene type selected by the trainee and the parameters set for the simulated human body model. The intelligent scene automatic generation module automatically generates a virtual scene based on the scene type selected by the trainee, and processes the parameters set for the simulated human body model selected by the trainee to obtain CPR operation comparison parameters. The sensor data acquisition module performs real-time sensor acquisition of the trainee's training process, obtains real-time training sensor data, and performs fusion verification processing with the CPR operation comparison parameters to obtain the trainee's real-time CPR operation performance evaluation value. The visualization display and voice prompt module visualizes the trainee's training process and provides real-time voice prompts based on the trainee's real-time CPR operation performance evaluation value.

[0009] One or more technical solutions provided in the embodiments of this application have at least the following technical effects or advantages: 1. The present invention provides an intelligent scenario-based CPR visualization training system based on MR technology, which improves the accuracy of data feedback during training by acquiring and analyzing the performance parameters of the sensor source nodes built into the simulated human body model in real time, thereby effectively solving the problem of poor CPR visualization training experience caused by the lack of real-time performance monitoring and feedback mechanisms in the prior art; 2. This invention obtains network synchronization evaluation values ​​by comparing network state parameters with a preset network state parameter reference set in a database, thereby optimizing the utilization of network resources and achieving the technical effect of maintaining network stability and reliability in complex operations. It effectively solves the problem of network latency and packet loss affecting training results in the prior art. 3. By evaluating the real-time CPR operational effectiveness of trainees, a comprehensive assessment of operational effectiveness during CPR training can be achieved, thereby solving the problem of insufficient assessment of trainees' actual operational capabilities in existing technologies. Attached Figure Description

[0010] Figure 1 A schematic diagram of the structure of an intelligent scenario-based CPR visualization training system based on MR technology provided in this application embodiment; Figure 2 This application provides a visualization training result of an intelligent scenario-based CPR visualization training system based on MR technology, as shown in the embodiments of this application. Figure 3 This application provides a virtual story background for an intelligent scenario-based CPR visualization training system based on MR technology. Figure 4 This application provides a virtual scenario-based intelligent scenario-based CPR visualization training system based on MR technology. Detailed Implementation

[0011] This application provides an intelligent scenario-based CPR visualization training system based on MR technology, which solves the problem of poor CPR visualization training experience caused by the lack of real-time performance monitoring and feedback mechanisms in existing technologies. The system receives training request signals transmitted by personnel, identifies the person transmitting the training request signal as the trainer, and obtains the scene type selected by the trainer and the parameters set for the simulated human body model. Based on the selected scene type, a virtual scene is automatically generated, and CPR operation comparison parameters are obtained based on the selected simulated human body model parameters. The training process of the trainer is monitored in real time to obtain real-time sensor data, which is then fused and verified with the CPR operation comparison parameters to obtain the trainer's real-time CPR operation performance evaluation value. The training process is visualized and displayed, and real-time voice prompts are provided simultaneously based on the trainer's real-time CPR operation performance evaluation value, achieving real-time monitoring of the simulated human body model operation and improving data accuracy.

[0012] The technical solution in this application aims to address the problem of poor CPR visualization training experience caused by the lack of real-time performance monitoring and feedback mechanisms. The overall approach is as follows: A training request perception module receives training request signals transmitted by personnel, identifies the transmitter as a trainer, and obtains the scene type selected by the trainer and the parameters set for the simulated human model. An intelligent scene automation generation module automatically generates a virtual scene based on the selected scene type and processes the parameters set for the simulated human model to obtain CPR operation comparison parameters. A sensor data acquisition module performs real-time sensor data acquisition of the trainer's training process, obtains real-time training sensor data, and fuses and verifies it with the CPR operation comparison parameters to obtain the trainer's real-time CPR operation performance evaluation value. A visualization display and voice prompt module visualizes the trainer's training process and provides real-time voice prompts based on the trainer's real-time CPR operation performance evaluation value, achieving real-time monitoring of the simulated human model operation and improving data accuracy.

[0013] To better understand the above technical solutions, the following will provide a detailed explanation of the technical solutions in conjunction with the accompanying drawings and specific implementation methods.

[0014] like Figure 1 The diagram shown is a structural schematic of an intelligent scenario-based CPR visualization training system based on MR technology provided in this application embodiment. This system includes: a training request perception module, used to receive training request signals transmitted by personnel, mark the personnel transmitting the training request signals as trainees, and obtain the scene type selected by the trainee and the setting parameters of the simulated human body model; an intelligent scene automatic generation module, used to automatically generate a virtual scene under the scene type selected by the trainee, and process the CPR operation comparison parameters based on the setting parameters of the simulated human body model selected by the trainee; a sensor data acquisition module, used to perform real-time sensor acquisition of the trainee's training process, obtain real-time training sensor data, and perform fusion verification processing with the CPR operation comparison parameters to obtain the trainee's real-time CPR operation performance evaluation value; and a visualization display and voice prompt module, used to visualize the trainee's training process and simultaneously provide real-time voice prompts based on the trainee's real-time CPR operation performance evaluation value, achieving real-time monitoring of the simulated human body model operation and improving data accuracy.

[0015] In this embodiment, by performing operations such as training request processing, scene generation, real-time data acquisition and feedback, a highly automated experience is provided to trainers, thereby significantly improving the efficiency and accuracy of CPR training. The introduction of a network synchronization module ensures the stable operation of the system and avoids training interruptions or errors caused by network problems.

[0016] Furthermore, the parameters for setting the simulated human body model include: setting age, setting height, setting weight, and setting the anteroposterior diameter of the chest cavity.

[0017] In this embodiment, age affects the flexibility of the human body, the elasticity of the chest cavity, and bone density. Older individuals experience decreased chest cavity flexibility, a stiffer sternum, and increased difficulty in chest compressions. Age also influences weight, anteroposterior diameter of the chest cavity, and height; height affects the longitudinal length of the chest cavity and the required compression depth. Taller individuals have a larger chest cavity area and a wider compression zone, requiring more precise compression positions and force. Taller individuals are generally heavier, which also affects the force required for compressions; heavier individuals require more force to achieve the appropriate compression depth. Individuals who are too light or too heavy have different chest cavity stress tolerances, affecting the depth and frequency of compressions. The size of the anteroposterior diameter of the chest cavity directly determines the required compression depth; a deeper chest cavity requires greater force to achieve an effective depth. Age, height, weight, and anteroposterior diameter of the chest cavity interact and collectively affect the difficulty of training. For example, when parameters such as greater height, weight, and a deeper anteroposterior diameter of the chest cavity are present, trainers require greater force and precision to complete compressions, increasing the complexity of the training.

[0018] Furthermore, the CPR operation comparison parameters are obtained through the following steps: First, a preset set of simulated human body model references is obtained from the database. This set includes reference age, reference height, reference weight, and reference chest anteroposterior diameter. Second, the parameters of the simulated human body model are compared with the preset set of simulated model references in the database to obtain the virtual rescue indicator values ​​of the simulated human body model. These virtual rescue indicator values ​​are used to characterize the training complexity of the simulated human body model. Third, the CPR operation parameters corresponding to each preset interval of virtual rescue indicator values ​​in the database are obtained and matched with the virtual rescue indicator values ​​of the simulated human body model. If the virtual rescue indicator values ​​of the simulated human body model belong to a certain preset interval, the CPR operation parameters corresponding to that interval are obtained and recorded as the CPR operation comparison parameters.

[0019] In this embodiment, the virtual rescue indicator value is obtained by means of the following method: Subtracting the reference age from the set age yields the age difference. Dividing this age difference by the reference age yields the age comparison result. Dividing the set height, set weight, and set anteroposterior diameter of the chest cavity by the reference age, reference height, and reference weight respectively yields the virtual rescue processing result. Multiplying the age comparison result and the virtual rescue processing result by their respective virtual rescue influence weights and then summing them yields the virtual rescue indicator value. The virtual rescue influence weights include the influence weights of set age, set height, set weight, and set anteroposterior diameter of the chest cavity.

[0020] It should be noted that the simulated human body model reference set can be obtained through MR technology backend data. Generally, the complexity and difficulty of rescue increases with children and the elderly. Therefore, the closer the set age is to the ideal rescue age, the better the rescue outcome. Heavier patients often require greater force during CPR, increasing the difficulty of the procedure. Taller patients typically have larger chest cavities, requiring rescuers to have a wider range of movements and greater strength for effective CPR, increasing the difficulty and physical exertion.

[0021] It should be noted that if the virtual rescue indicator values ​​of the simulated human body model fall within a certain preset virtual rescue indicator value range, then the CPR operation parameters corresponding to that virtual rescue indicator value range are obtained and recorded as CPR operation comparison parameters. For example, in this embodiment, in two simulation training sessions, the parameters of the simulated human body model were set as follows: age 20 years old, reference chest anteroposterior diameter 13cm, weight 75kg, and height 1.85 meters for the first simulation training session, and age 20 years old, reference chest anteroposterior diameter 13cm, weight 70kg, and height 1.80 meters for the second simulation training session. With the age and chest anteroposterior diameter remaining consistent with the reference age, the weight and height set in the first simulated human model were at a higher level compared to the weight and height set in the second simulated human model. This indicates that the training difficulty for the first time was higher, requiring greater compression depth, stronger force, faster compression frequency, and more ventilation for CPR. Therefore, the CPR operation comparison parameters for the first CPR operation were: compression depth 6cm, compression frequency of 115 compressions per minute, ventilation frequency of two ventilations after every 30 compressions, and average ventilation volume of 550ml.

[0022] It should also be noted that the height influence weight represents the numerical value of the impact of a set height on the virtual rescue indicator value. When using it, the influence weight corresponding to the set height can be directly retrieved from the database. The correspondence can be a pre-defined mapping relationship; for example, a mapping set is formed between the set height and the set height influence weight. Inputting the real-time set height into the mapping set yields the influence weight corresponding to the set height. This mapping relationship can be one-to-one or many-to-one. Similarly, the age influence weight represents the numerical value of the impact of a set age on the virtual rescue indicator value. When using it, the influence weight corresponding to the set age can be directly retrieved from the database. The correspondence can also be a pre-defined mapping relationship; for example, a mapping set is formed between the set age and the set age influence weight. Inputting the real-time set age into the mapping set yields the influence weight corresponding to the set age. This mapping relationship can be one-to-one or many-to-one. The weight influence weight represents the numerical value indicating the degree of influence of a set weight on the virtual rescue indicator value. When using it, the influence weight corresponding to the set weight can be directly retrieved from the database. The correspondence can be a pre-defined mapping relationship; for example, a mapping set is formed between the set weight and the set weight influence weight. Inputting the real-time set weight into the mapping set yields the influence weight corresponding to the set weight. This mapping relationship can be one-to-one or many-to-one. Similarly, the anteroposterior diameter influence weight represents the numerical value indicating the degree of influence of the set anteroposterior diameter on the virtual rescue indicator value. When using it, the influence weight corresponding to the set anteroposterior diameter can be directly retrieved from the database. The correspondence can be a pre-defined mapping relationship; for example, a mapping set is formed between the set anteroposterior diameter and the set anteroposterior diameter influence weight. Inputting the real-time set anteroposterior diameter into the mapping set yields the influence weight corresponding to the set anteroposterior diameter. This mapping relationship can be one-to-one or many-to-one.

[0023] Furthermore, the training process of trainees is monitored in real time to obtain real-time training sensor data. The specific process is as follows: within a preset time, the average compression depth, compression frequency, average rebound height, ventilation frequency, and average ventilation volume of trainees performing CPR operations on the simulated human body model are collected through the sensor source nodes built into the simulated human body model, and these data are combined as real-time training sensor data.

[0024] In this embodiment, compression depth and compression frequency directly affect the degree of chest cavity compression and recovery rhythm. Compression depth that is too shallow reduces the efficiency of the heart's pumping action, while a compression frequency that is too fast may prevent the chest cavity from fully recoiling, affecting blood return. Average recoil height measures the chest cavity's recovery after compression; insufficient recoil will prevent the chest cavity from achieving its maximum effect during the next compression. Ventilation frequency and average ventilation volume affect the effectiveness of breathing; too low a ventilation volume may lead to insufficient oxygen in the blood, while too high a frequency will reduce the effectiveness of compression, because compression and ventilation need to be coordinated.

[0025] Furthermore, the real-time CPR performance evaluation values ​​of the trainees are obtained through the following steps: Historical application impact data of the simulated human body model was obtained, including historical average compression pressure, historical oxidation duration, historical average compression depth, and historical cumulative compression count. Preset reference application impact parameters from the database were obtained and compared with the historical application impact data of the simulated human body model to obtain an operational efficiency interference factor. The preset reference application impact parameters included reference compression pressure, reference oxidation duration, reference average compression depth, and reference cumulative compression count. The operational efficiency interference factor was used to assess the impact of the simulated human body model's wear and tear on trainees' CPR training. Based on the analysis of real-time training sensor data and CPR operation comparison parameters, a real-time training sensor evaluation value was obtained. Based on the real-time training sensor evaluation value and combined with the operational efficiency interference factor analysis, a real-time CPR operational efficiency evaluation value for the trainees was obtained. CPR operation comparison parameters included: compression depth comparison value, compression frequency comparison value, rebound height comparison value, ventilation frequency comparison value, and ventilation volume comparison value. The real-time CPR operational efficiency evaluation value for the trainees was used to characterize the effectiveness of the trainees' CPR operations.

[0026] In this embodiment, the real-time CPR operational effectiveness evaluation value of the trainee is obtained based on the training real-time sensor evaluation value and combined with the operational effectiveness interference factor analysis. The specific method is as follows: the operational effectiveness interference factor is compared with a preset operational effectiveness interference threshold to obtain the real-time CPR operational effectiveness evaluation value of the trainee. If the operational effectiveness interference factor is below the operational effectiveness interference threshold, the training real-time sensor evaluation value is used as the real-time CPR operational effectiveness evaluation value of the trainee. If the operational effectiveness interference factor is greater than the operational effectiveness interference threshold, the operational effectiveness interference factor and the operational effectiveness interference threshold are superimposed to obtain the superposition result. The operational effectiveness interference factor is divided by the superposition result and then added to the training real-time sensor evaluation value to obtain the real-time CPR operational effectiveness evaluation value of the trainee.

[0027] The operational efficiency interference factor is introduced to assess the impact of the wear and tear on CPR training, preventing situations where trainees perform procedures correctly but the wear and tear on the mannequin negatively affects training effectiveness and experience. Historical average compression pressure influences the chest cavity stress on the mannequin; excessive pressure may accelerate wear, with higher pressure resulting in more severe wear. Historical oxidation time measures the duration of exposure of mannequin components to oxygen during training; prolonged exposure can lead to material aging, affecting the mannequin's durability. Historical average compression depth is closely related to the mannequin's elastic recovery ability; excessive compression may increase the burden on internal materials, reducing its recovery capacity. Historical cumulative compression count is a key parameter for calculating the overall wear and tear on the mannequin; more compressions result in a more significant cumulative wear effect. These parameters work together to influence the degree of mannequin wear and tear, thus impacting the trainee's CPR operational efficiency. By evaluating the operational efficiency interference factor, we can understand the extent to which mannequin wear and tear interferes with training effectiveness.

[0028] Furthermore, the real-time sensor evaluation value for training is obtained through the following method: The average compression depth, average ventilation volume, ventilation frequency, and compression frequency are compared with their corresponding compression depth, compression frequency, ventilation frequency, and ventilation volume comparison values ​​using absolute difference processing to obtain the difference comparison results. The average rebound height is compared with the rebound height comparison value to obtain the rebound height processing result. Based on the difference comparison results and the rebound height processing results, corresponding effectiveness evaluation influence weights are introduced, multiplied, and then added to obtain the real-time sensor evaluation value for training. The effectiveness evaluation influence weights include... Influence weight Average rebound height affects weight Average ventilation influence weight The frequency of ventilation affects the weight, and the frequency of chest compressions also affects the weight.

[0029] The numerical value representing the influence of compression depth on operational performance interference factors can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, the average compression depth and its influence weight form a mapping set. Inputting the real-time average compression depth into this mapping set yields the corresponding influence weight. This mapping relationship can be one-to-one or many-to-one. Similarly, the influence weight representing the average rebound height indicates the numerical value of the influence of average rebound height on operational performance interference factors. This can also be directly obtained from the database. Again, the correspondence can be a pre-defined mapping relationship; for example, the average rebound height and its influence weight form a mapping set. Inputting the real-time average rebound height into this mapping set yields the corresponding influence weight. This mapping relationship can be one-to-one or many-to-one. The average ventilation volume influence weight represents the numerical value of the impact of average ventilation volume on operational performance interference factors. When using it, the influence weight corresponding to the average ventilation volume can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, average ventilation volume and its influence weight form a mapping set. Inputting the real-time average ventilation volume into the mapping set yields the influence weight corresponding to the average ventilation volume. This mapping relationship can be one-to-one or many-to-one. The ventilation frequency influence weight represents the numerical value of the impact of ventilation frequency on operational performance interference factors. When using it, the influence weight corresponding to the ventilation frequency can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, ventilation frequency and its influence weight form a mapping set. Inputting the real-time ventilation frequency into the mapping set yields the influence weight corresponding to the ventilation frequency. This mapping relationship can be one-to-one or many-to-one. The impact weight of pressing frequency represents the numerical value of the degree of influence of pressing frequency on the interference factor of operation efficiency. When using it, the impact weight corresponding to the pressing frequency can be directly obtained from the database. The correspondence can be a pre-set mapping relationship. For example, the pressing frequency and the impact weight of pressing frequency form a mapping set. The real-time pressing frequency is input into the mapping set to obtain the impact weight corresponding to the pressing frequency. The mapping relationship can be one-to-one or many-to-one.

[0030] It should be noted that the operational efficacy interference threshold can be obtained from a database. The operational efficacy interference threshold represents the degree of influence of the simulated human body model on the trainee's CPR training. If the value of the operational efficacy interference factor is below the operational efficacy interference threshold, it means that the performance of the simulated human body model has a small and negligible impact on the trainee's CPR training. If the value of the operational efficacy interference factor is greater than the operational efficacy interference threshold, it needs to be taken seriously.

[0031] The operational efficiency interference factor is obtained as follows: the historical average pressing pressure is divided by the reference pressing pressure to obtain the pressing pressure comparison value; the historical cumulative pressing number is divided by the reference cumulative pressing number to obtain the cumulative pressing number comparison value; the pressing pressure comparison value and the cumulative pressing number comparison value are multiplied to obtain the comprehensive pressing treatment value; the historical average pressing depth and historical oxidation time are divided by the corresponding reference average pressing depth and reference oxidation time to obtain the pressing depth comparison treatment value and oxidation time comparison treatment value; the comprehensive pressing treatment value, pressing depth comparison treatment value, and oxidation time comparison treatment value are introduced into the corresponding operational efficiency interference influence weights, multiplied, and then added to obtain the operational efficiency interference factor. The operational efficiency interference influence weights include the pressing pressure influence weight, the historical average pressing depth influence weight, and the historical oxidation time influence weight.

[0032] It should be noted that historical application impact data of the simulated human body model, such as historical average compression pressure, historical oxidation duration, historical average compression depth, and historical cumulative compression count, can be obtained from a database. The compression pressure impact weight represents the numerical value of the influence of historical average compression pressure and historical cumulative compression count on the operational efficiency interference factor. When using this data, the impact weights corresponding to historical average compression pressure and historical cumulative compression count can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship. For example, historical average compression pressure and historical cumulative compression count can form a mapping set with the compression pressure impact weight. Inputting the real-time historical average compression pressure and historical cumulative compression count into the mapping set yields the impact weight corresponding to the compression pressure. The mapping relationship can be one-to-one or many-to-one. The historical average compression depth influence weight represents the numerical value of the impact of historical average compression depth on operational performance interference factors. When using it, the influence weight corresponding to the historical average compression depth can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, historical average compression depth and its influence weight form a mapping set. Inputting the real-time historical average compression depth into this mapping set yields the influence weight corresponding to the historical average compression depth. This mapping relationship can be one-to-one or many-to-one. Similarly, the historical oxidation duration influence weight represents the numerical value of the impact of historical oxidation duration on operational performance interference factors. When using it, the influence weight corresponding to historical oxidation duration can be directly obtained from the database. The correspondence can also be a pre-defined mapping relationship; for example, historical oxidation duration and its influence weight form a mapping set. Inputting the real-time historical oxidation duration into this mapping set yields the influence weight corresponding to the historical oxidation duration. This mapping relationship can be one-to-one or many-to-one.

[0033] Furthermore, real-time voice prompts are simultaneously generated based on the trainee's real-time CPR performance evaluation value. The steps include: acquiring and analyzing the performance parameters of the sensor source nodes built into the simulated human body model in real time, and processing them to obtain the sensor source node performance evaluation value of the simulated human body model; performing a comprehensive analysis based on the trainee's real-time CPR performance evaluation value and the simulated human body model's sensor source node performance evaluation value to obtain the trainee's real-time CPR comprehensive performance score; comparing the trainee's real-time CPR comprehensive performance score with a preset comprehensive performance score threshold in the database; if the trainee's real-time CPR comprehensive performance score is above the preset comprehensive performance score threshold, the trainee's initial action judgment result is considered correct, and no real-time voice prompt is executed; if the trainee's real-time CPR comprehensive performance score is below the preset comprehensive performance score threshold, the trainee's initial action judgment result is considered incorrect, and a real-time voice prompt is executed.

[0034] In this embodiment, the steps of acquiring and analyzing the performance parameters of the sensor source nodes built into the simulated human body model in real time, and processing them to obtain the performance evaluation value of the sensor source nodes of the simulated human body model are as follows: acquiring and analyzing the performance parameters of the sensor source nodes built into the simulated human body model in real time, obtaining the baseline value of the sensor source node performance parameters, comparing the performance parameters of the sensor source nodes built into the simulated human body model within a preset time period with the baseline value of the sensor source node performance parameters, and processing them to obtain the performance evaluation value of the sensor source nodes of the simulated human body model.

[0035] The performance parameters of the sensor source nodes built into the simulated human body model include: the signal strength, signal response time, and data acquisition rate of the sensor source nodes built into the simulated human body model; the benchmark values ​​of the sensor source node performance parameters include: the benchmark value of signal strength, the benchmark value of signal response time, and the data acquisition rate.

[0036] It should be noted that the performance evaluation values ​​of the sensor source nodes of the simulated human body model obtained by evaluating the performance parameters of the built-in sensor source nodes take into account the mutual influence between these parameters. For example, signal strength directly affects the signal transmission quality of the sensor source node; the higher the strength, the better the signal transmission stability. Frequency deviation reflects the accuracy of the signal; a large deviation may reduce the availability of the signal and affect the signal strength and response stability. Signal response time determines the reaction speed of the sensor source node to external commands; a slow response will reduce the real-time performance of the system. Pressure sensitivity reflects the detection accuracy of the sensor source node to physical pressure; high sensitivity helps improve the detection accuracy of the system. Higher noise may cause more interference to the signal accuracy and response, thus affecting the overall performance evaluation.

[0037] The performance evaluation value of the sensor source node of the simulated human body model is obtained by multiplying the standardized signal strength by the data acquisition rate and then dividing by the standardized signal response time. Specifically, the standardized signal strength is obtained by dividing the signal strength of the sensor source node built into the simulated human body model by a baseline signal strength value; the data acquisition rate is obtained by dividing the data acquisition rate of the sensor source node built into the simulated human body model by a baseline data acquisition rate value; and the standardized signal response time is obtained by dividing the signal response time of the sensor source node built into the simulated human body model by a baseline signal response time value.

[0038] Furthermore, the performance parameters of the built-in sensor source nodes in the simulated human body model include: sensor source node signal response time, sensor source node signal strength, and data acquisition rate.

[0039] In this embodiment, the performance parameters of the sensor source nodes built into the simulated human body model can be obtained by retrieving them from the training backend.

[0040] Furthermore, it also includes a network performance evaluation and control module, used to evaluate the network used by trainees during training. Specific steps include: obtaining network status parameters for each press time point within a preset time period, including bandwidth, latency, packet loss rate, and network utilization; obtaining a preset network status parameter reference set from the database, including reference bandwidth, reference latency, reference packet loss rate, and reference network utilization; comparing the network status parameters with the preset network status parameter reference set in the database to obtain a network synchronization evaluation value; and implementing targeted control based on the network synchronization evaluation value.

[0041] In this embodiment, it should be noted that network bandwidth directly determines the data transmission capacity; the higher the bandwidth, the faster the transmission rate. Network latency reflects the transmission time of data in the network; the higher the latency, the lower the efficiency of data synchronization. Excessive latency will seriously affect the synchronization quality. Network packet loss rate indicates the proportion of data packets lost during transmission. A high packet loss rate will lead to data loss or the need for retransmission, further increasing network latency and placing an additional burden on bandwidth requirements. Network utilization is used to measure the actual use of network resources. High utilization indicates that the network is close to saturation, which can easily lead to increased latency and packet loss rate, affecting the overall synchronization capability of the network.

[0042] The network synchronization evaluation value is obtained by averaging the network bandwidth, network latency, network packet loss rate, and network utilization at each pressing time point. Then, these average values ​​are divided by their corresponding reference network bandwidth, reference network latency, reference network utilization, and reference network utilization rate to obtain the network synchronization evaluation result. This result is then multiplied by the corresponding network synchronization evaluation influence weights and summed to obtain the network synchronization evaluation value. The network synchronization evaluation influence weights include the influence weights of network bandwidth, network latency, network packet loss rate, and network utilization rate.

[0043] It should also be noted that network status parameters can be obtained through network measurement tools (such as a network cable tester). Network bandwidth impact weight represents the numerical value of the influence of network bandwidth on the network synchronization evaluation value. When using it, the impact weight corresponding to network bandwidth can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, network bandwidth and network bandwidth impact weight form a mapping set. Inputting the real-time network bandwidth into the mapping set yields the impact weight corresponding to the network bandwidth. The mapping relationship can be one-to-one or many-to-one. Network latency impact weight represents the numerical value of the influence of network latency on the network synchronization evaluation value. When using it, the impact weight corresponding to network latency can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, network latency and network latency impact weight form a mapping set. Inputting the real-time network latency into the mapping set yields the impact weight corresponding to the network latency. The mapping relationship can be one-to-one or many-to-one. The network packet loss rate impact weight represents the numerical value indicating the degree of influence of network packet loss rate on the network synchronization evaluation value. When using it, the impact weight corresponding to network packet loss rate can be directly obtained from the database. The correspondence can be a pre-defined mapping relationship; for example, a mapping set can be formed between network packet loss rate and its impact weight. Inputting the real-time network packet loss rate into this mapping set yields the corresponding impact weight. This mapping relationship can be one-to-one or many-to-one. Similarly, the network utilization rate impact weight represents the numerical value indicating the degree of influence of network utilization on the network synchronization evaluation value. When using it, the impact weight corresponding to network utilization rate can be directly obtained from the database. The correspondence can also be a pre-defined mapping relationship; for example, a mapping set can be formed between network utilization rate and its impact weight. Inputting the real-time network utilization rate into this mapping set yields the corresponding impact weight. This mapping relationship can be one-to-one or many-to-one.

[0044] Furthermore, targeted control is implemented based on the network synchronization evaluation value. Specifically, the network synchronization anomaly threshold is obtained and compared with the network synchronization evaluation value. If the network synchronization evaluation value is less than the network synchronization anomaly threshold, no action is taken. If the network synchronization evaluation value is greater than the network synchronization anomaly threshold, network switching is performed.

[0045] In this embodiment, as Figure 2 , Figure 3 and Figure 4 The image shown depicts the training results for the trainees.

[0046] It's important to note that by setting a network synchronization anomaly threshold, network synchronization problems can be automatically identified and addressed, avoiding frequent network switching due to network fluctuations or minor anomalies. This improves network stability and reliability. When the network synchronization assessment value is within the normal range, no action is taken, ensuring the continuity and stability of the network connection used by trainees. This reduces service interruptions or delays caused by unnecessary network switching, improving the trainee experience. Network switching only occurs when the network synchronization assessment value exceeds the anomaly threshold. This avoids unnecessary network switching operations and reduces resource consumption, such as CPU, memory, and network bandwidth.

[0047] In summary, this embodiment obtains the performance evaluation value of the sensor source nodes of the simulated human body model by acquiring and analyzing the performance parameters of the sensor source nodes built into the simulated human body model in real time. This enables real-time monitoring of the operation of the simulated human body model and improves the accuracy of the data, effectively solving the problem of poor CPR visualization training experience caused by the lack of real-time performance monitoring and feedback mechanisms in the prior art.

[0048] Those skilled in the art will understand that embodiments of the present invention can be provided as methods, systems, or computer program products. Therefore, the present invention can take the form of a completely hardware embodiment, a completely software embodiment, or an embodiment combining software and hardware aspects. Furthermore, the present invention can take the form of a computer program product embodied on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROM, optical storage, etc.) containing computer-usable program code.

[0049] This invention is described with reference to flowchart illustrations and / or block diagrams of systems, apparatus (systems), and computer program products according to embodiments of the invention. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, special-purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, generate instructions for implementing the flowchart illustrations and / or block diagrams. Figure 1 One or more processes and / or boxes Figure 1 A device that provides the functions specified in one or more boxes.

[0050] These computer program instructions may also be stored in a computer-readable storage medium that can direct a computer or other programmable data processing device to function in a particular manner, such that the instructions stored in the computer-readable storage medium produce an article of manufacture including instruction means, which are implemented in a process Figure 1 One or more processes and / or boxes Figure 1 The function specified in one or more boxes.

[0051] These computer program instructions may also be loaded onto a computer or other programmable data processing equipment to cause a series of operational steps to be performed on the computer or other programmable equipment to produce a computer-implemented process, thereby providing instructions that execute on the computer or other programmable equipment for implementing the process. Figure 1 One or more processes and / or boxes Figure 1 The steps of the function specified in one or more boxes.

[0052] Although preferred embodiments of the invention have been described, those skilled in the art, upon learning the basic inventive concept, can make other changes and modifications to these embodiments. Therefore, the appended claims are intended to be interpreted as including the preferred embodiments as well as all changes and modifications falling within the scope of the invention.

[0053] Obviously, those skilled in the art can make various modifications and variations to this invention without departing from its spirit and scope. Therefore, if these modifications and variations fall within the scope of the claims of this invention and their equivalents, this invention also intends to include these modifications and variations.

Claims

1. A smart scenario-based CPR visualization training system based on MR technology, characterized in that, include: The training request perception module, the intelligent scene automatic generation module, the sensor data acquisition module, and the visualization display and voice prompt module; The training request perception module is used to receive training request signals transmitted by personnel, mark the personnel transmitting the training request signals as training personnel, and obtain the scene type selected by the training personnel and the setting parameters of the simulated human body model. The intelligent scene automatic generation module is used to automatically generate a virtual scene of the scene type selected by the trainee, and to set parameters based on the simulated human body model selected by the trainee to obtain CPR operation comparison parameters. The sensor data acquisition module is used to collect real-time sensor data of the training process of the trainees, obtain real-time training sensor data, and perform fusion and verification processing with CPR operation comparison parameters to obtain the real-time CPR operation effectiveness evaluation value of the trainees. The visualization and voice prompt module is used to visualize the training process of the trainer and provide real-time voice prompts based on the trainer's real-time CPR performance evaluation value.

2. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 1, characterized in that: The parameters for setting the simulated human body model specifically include: setting age, setting height, setting weight, and setting anteroposterior diameter of the chest cavity.

3. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 2, characterized in that: The specific steps for obtaining the CPR operation comparison parameters include: Obtain a preset set of simulated human body model references from the database. The simulated human body model reference set includes: reference age, reference height, reference weight, and reference chest anteroposterior diameter. The virtual rescue index values ​​of the simulated human body model are obtained by comparing the set parameters of the simulated human body model with the preset simulation model reference set in the database. The virtual rescue indicator value of the simulated human body model is used to characterize the training complexity of the simulated human body model. Obtain the CPR operation parameters corresponding to each preset virtual rescue indicator value range in the database, and match them with the virtual rescue indicator values ​​of the simulated human body model. If the virtual rescue indicator values ​​of the simulated human body model belong to a certain preset virtual rescue indicator value range, obtain the CPR operation parameters corresponding to that virtual rescue indicator value range and record them as CPR operation comparison parameters.

4. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 1, characterized in that, The process of real-time sensing and data acquisition during the training of trainees to obtain real-time training sensing data is as follows: Within a preset time period, the average compression depth, compression frequency, average rebound height, ventilation frequency, and average ventilation volume of trainees performing CPR on the simulated human body model are collected through the built-in sensor source nodes of the simulated human body model, and combined as real-time training sensor data.

5. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 4, characterized in that: The specific steps for obtaining the real-time CPR performance evaluation value of the trainees are as follows: The historical application impact data of the simulated human body model is obtained, including: historical average compression pressure, historical oxidation duration, historical average compression depth, and historical cumulative number of compressions. Obtain the preset reference application impact parameters from the database and compare them with the historical application impact data of the simulated human body model to obtain the operational efficiency interference factor; The preset reference application influence parameters include: reference pressing pressure, reference oxidation time, reference average pressing depth, and reference cumulative pressing count; The operational performance interference factor is used to assess the impact of the wear and tear on the simulated human body model on CPR training. Based on the analysis of training real-time sensor data and CPR operation comparison parameters, the training real-time sensor evaluation value is obtained. Based on the training real-time sensor evaluation value and combined with the operation effectiveness interference factor analysis, the real-time CPR operation effectiveness evaluation value of the trainee is obtained. The CPR operation comparison parameters include: compression depth comparison value, compression frequency comparison value, rebound height comparison value, ventilation frequency comparison value, and ventilation volume comparison value. The real-time CPR performance evaluation value of the trainers is used to characterize the effectiveness of the trainers in performing CPR.

6. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 4, characterized in that: The specific method for obtaining the real-time sensor evaluation value during training is as follows: The average compression depth, average ventilation volume, ventilation frequency, and compression frequency are compared with their corresponding compression depth, compression frequency, ventilation frequency, and ventilation volume comparison values ​​to obtain the difference comparison results. The average rebound height is compared with the rebound height comparison value to obtain the rebound height comparison result. Based on the difference comparison results and the rebound height comparison results, the corresponding effectiveness evaluation influence weights are introduced, multiplied, and then added to obtain the training real-time sensor evaluation value. The weighting of the effectiveness assessment includes the weighting of average compression depth, average rebound height, average ventilation volume, ventilation frequency, and compression frequency.

7. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 1, characterized in that: The synchronization is based on the trainee's real-time CPR performance evaluation value, providing real-time voice prompts. The steps include: Real-time acquisition and analysis of the performance parameters of the built-in sensor source nodes of the simulated human body model, and processing to obtain the performance evaluation value of the sensor source nodes of the simulated human body model. A comprehensive analysis is conducted based on the trainee's real-time CPR performance evaluation value and the sensor source node performance evaluation value of the simulated human body model to obtain the trainee's real-time CPR comprehensive operation score. The trainee's real-time CPR comprehensive operation score is then compared with a preset comprehensive operation score threshold in the database. If the trainee's real-time CPR comprehensive operation score is above the preset comprehensive operation score threshold, the trainee's initial action judgment result is that the action is correct, and no real-time voice prompt is given. If the trainee's real-time CPR comprehensive operation score is below the preset comprehensive operation score threshold, the trainee's initial action judgment result is that the action is incorrect, and a real-time voice prompt is given.

8. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 7, characterized in that: The performance parameters of the built-in sensor source nodes in the simulated human body model include: sensor source node signal response time, sensor source node signal strength, and data acquisition rate.

9. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 1, characterized in that: It also includes a network performance evaluation and control module, used to evaluate the network implemented by trainers during the training process. Specific steps include: The network status parameters of each pressing time node of the trainee within a preset time period are obtained, and the network status parameters include: bandwidth, latency, packet loss rate and network utilization. Obtain a preset network status parameter reference set from the database. The network status parameter reference set includes: reference bandwidth, reference latency, reference packet loss rate, and reference network utilization. The network state parameters are compared with a preset network state parameter reference set in the database to obtain the network synchronization evaluation value; Targeted control measures will be implemented based on network synchronization assessment values.

10. The intelligent scenario-based CPR visualization training system based on MR technology as described in claim 9, characterized in that: The specific method for targeted control based on network synchronization evaluation values ​​is as follows: Obtain the network synchronization anomaly threshold and compare it with the network synchronization evaluation value. If the network synchronization evaluation value is less than the network synchronization anomaly threshold, no action is taken. If the network synchronization evaluation value is greater than the network synchronization anomaly threshold, network handover is performed.

Images