Self-adaptive pressing control system of cardio-pulmonary resuscitation machine and medium

Abstract

The invention relates to a self-adaptive pressing control system of a cardio-pulmonary resuscitation machine and a medium, and solves the problem that the improvement of the resuscitation effect is possibly limited due to the fact that an existing cardio-pulmonary resuscitation machine cannot perform self-adaptive adjustment according to real-time physiological indexes and individual differences of patients. The self-adaptive pressing control method for the cardiopulmonary resuscitation machine is realized when the at least one processor is configured to execute a computer program, and comprises the following specific steps of: inputting recognized and acquired real-time physiological index related data and age groups as input objects into a cardiopulmonary resuscitation machine adjustment information analysis model which completes training in advance; the adjustment information of the cardio-pulmonary resuscitation machine is output; and controlling the cardiopulmonary resuscitation machine to adjust according to the output cardiopulmonary resuscitation machine adjustment information. The method has the advantages that the pressing parameters of the cardio-pulmonary resuscitation machine are adjusted more accurately, and therefore the resuscitation effect is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of medical emergency equipment, and in particular to an adaptive pressing control system and medium of a cardiopulmonary resuscitation machine. Background Art

[0002] In the field of medical emergency, cardiopulmonary resuscitation is a key measure to rescue patients with cardiac arrest.

[0003] Currently, cardiopulmonary resuscitation machines are widely used in the field of emergency treatment. They can help restore the patient's heart function through mechanical compression. However, most existing cardiopulmonary resuscitation machines use fixed compression modes and parameters, which fail to fully consider the individual differences and real-time physiological status of patients, which may affect the resuscitation effect. Summary of the invention

[0004] In order to more accurately adjust the compression parameters of a cardiopulmonary resuscitation machine, thereby improving the resuscitation effect, the present application provides an adaptive compression control system and medium for a cardiopulmonary resuscitation machine.

[0005] In a first aspect, the present application provides an adaptive compression control system for a cardiopulmonary resuscitation machine, which adopts the following technical solution: An adaptive compression control system for a cardiopulmonary resuscitation machine, comprising: CPR machine; at least one processor; At least one memory storing a computer program, and at least one processor configured to implement an adaptive compression control method of a cardiopulmonary resuscitation machine when executing the computer program, the specific steps are as follows: Analyze whether the person who is undergoing cardiopulmonary resuscitation is wearing a physiological indicator monitoring device; If not, the age group of the person to be resuscitated is obtained, and the resuscitation mode of the cardiopulmonary resuscitation machine is analyzed and determined according to the corresponding relationship between the age group of the person to be resuscitated and the resuscitation mode of the cardiopulmonary resuscitation machine; Controlling the cardiopulmonary resuscitation machine to execute the resuscitation mode determined by the analysis; If yes, then identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated, and at the same time obtain the age group of the person to be resuscitated; The identified and acquired real-time physiological index related data and age group are used as input objects, input into a pre-trained cardiopulmonary resuscitation machine adjustment information analysis model, and the cardiopulmonary resuscitation machine adjustment information is output; Control the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information.

[0006] By adopting the above technical solutions, the adaptive compression control system of the cardiopulmonary resuscitation machine cleverly integrates the physiological indicators of personnel and age group information to achieve personalized resuscitation operations. When the monitoring device is not worn, it can intelligently select the appropriate resuscitation mode according to the age group; when the device is worn, it can analyze physiological data in real time and dynamically adjust the resuscitation strategy. This method not only improves the pertinence and efficiency of cardiopulmonary resuscitation, but also greatly reduces the difficulty of operation, so that non-professionals can also perform effective first aid measures.

[0007] Optionally, analyzing whether the person to be resuscitated is wearing a physiological indicator monitoring device includes: Analyze whether there is a physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine within a preset distance range centered on the cardiopulmonary resuscitation machine, wherein the connection relationship includes direct connection and waiting to be connected; If no, confirm that the person to be resuscitated is not wearing any physiological indicator monitoring equipment; If yes, then analyze the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only a direct connection, a preset direct connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and whether the person to be resuscitated is wearing the physiological indicator monitoring device according to the analysis result; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only to be connected, a preset matching analysis method for users to be connected is used to analyze whether the user of the physiological indicator monitoring device to be connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and whether the person to be resuscitated is wearing the physiological indicator monitoring device according to the analysis result; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine includes direct connection and pending connection, the preset comprehensive connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is the person waiting for cardiopulmonary resuscitation, and based on the analysis results, it is confirmed whether the person waiting for cardiopulmonary resuscitation is wearing the physiological indicator monitoring device.

[0008] By adopting the above technical solution, it is possible to accurately determine whether the person to be resuscitated is wearing such equipment by intelligently identifying whether there are physiological indicator monitoring devices connected to the cardiopulmonary resuscitation machine around it. It not only takes into account the direct connection between devices, but also covers the pending connection state, ensuring the accuracy and comprehensiveness of the judgment. This method greatly improves the pertinence and personalization of cardiopulmonary resuscitation operations, allowing rescuers to make more scientific and effective resuscitation decisions based on the real-time physiological indicators of the person to be resuscitated.

[0009] Optional, pre-set distance range acquisition centered on the CPR machine includes: Obtain information related to emergency scene factors, including the size of the environment space and the density of personnel distribution; According to the correspondence between the spatial size range within which the environmental space size falls, the personnel distribution density interval range within which the personnel distribution density falls, and the preset distance range centered on the cardiopulmonary resuscitation machine, the preset distance range centered on the cardiopulmonary resuscitation machine is analyzed and determined.

[0010] By adopting the above technical solution, the size of the environmental space and the density of personnel distribution in the emergency scene are comprehensively considered, so as to intelligently determine the preset distance range centered on the cardiopulmonary resuscitation machine. This method not only makes the use of the cardiopulmonary resuscitation machine more flexible and can adapt to emergency environments of different sizes and personnel densities, but also improves the efficiency of emergency treatment and ensures that the cardiopulmonary resuscitation machine can play a role within the most effective range. In short, this innovative method defines a reasonable operating radius for the use of cardiopulmonary resuscitation machines by scientifically analyzing scene factors, which helps to improve the pertinence and effectiveness of emergency rescue.

[0011] Optional, pre-set distance range acquisition centered on the CPR machine includes: Obtain the types of events where the cardiopulmonary resuscitation machine is used, including disaster scenes, traffic accident scenes, and other scenes; According to the correspondence between the event type of using the cardiopulmonary resuscitation machine and the preset distance range centered on the cardiopulmonary resuscitation machine, the preset distance range centered on the cardiopulmonary resuscitation machine is analyzed and determined.

[0012] By adopting the above technical solution, the preset distance range centered on the cardiopulmonary resuscitation machine is intelligently set by considering the type of event where the cardiopulmonary resuscitation machine is used, such as disaster scenes, traffic accident scenes, etc. This method makes the application of the cardiopulmonary resuscitation machine more scene-adaptive and can play an effective role in different types of emergency events. Adjusting the preset distance range according to the type of event can ensure that the cardiopulmonary resuscitation machine performs rescue within the most suitable range, thereby improving rescue efficiency and success rate. In short, this innovative method enables the cardiopulmonary resuscitation machine to better adapt to changing event scenarios by flexibly adjusting the preset distance range, providing strong support for emergency rescue.

[0013] Optionally, identifying and obtaining real-time physiological index related data transmitted by a physiological index monitoring device worn by a person to be resuscitated includes: Obtain the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine; If the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine is a direct connection, then identifying and obtaining real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated; If the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine is to be connected, actively match the connection and identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is that there is a direct connection or a pending connection at the same time, then obtain the real-time physiological indicator related data transmitted by the physiological indicator monitoring device that is directly connected or to be connected, and analyze whether the same physiological indicator comes from different physiological indicator monitoring devices and the corresponding physiological indicator data are different; If yes, then according to the preset confidences of different physiological indicator monitoring devices for different physiological indicator monitoring devices, analyze and determine the confidences of the same physiological indicator from different physiological indicator monitoring devices, and select the same physiological indicator data with the highest confidence as the corresponding physiological indicator data for this application; If not, keep the original setting.

[0014] By adopting the above technical solution, the accuracy and efficiency of cardiopulmonary resuscitation are significantly improved by intelligently identifying and acquiring real-time data transmitted by the physiological indicator monitoring equipment worn by the cardiopulmonary resuscitation personnel. It can flexibly handle the different connection states of the monitoring equipment and the cardiopulmonary resuscitation machine to ensure continuous acquisition of data. When multiple devices monitor the same indicator, the solution can intelligently analyze and select the data with the highest confidence, thereby ensuring the accuracy of physiological indicators during the rescue process. This intelligent data processing method not only improves the quality of rescue, but also provides more reliable decision-making support for medical staff, helping to save more lives.

[0015] Optionally, the confidence level acquisition of different physiological indicators by different preset physiological indicator monitoring devices includes: Obtain the current environment category information and environment parameter information. The environment category includes home environment and sports environment. The environment parameter information includes environment temperature, environment humidity and altitude information of the area. According to the corresponding relationship between the current environment category information, environmental parameter information, the category of physiological index monitoring equipment and the confidence of different physiological indexes, the confidence of different physiological index monitoring equipment about different physiological indexes is analyzed and determined.

[0016] By adopting the above technical solution, the confidence of different devices regarding different physiological indicators is intelligently analyzed and determined by comprehensively considering the current environment category, environmental parameters and the characteristics of the physiological indicator monitoring equipment. This method significantly improves the accuracy and reliability of physiological indicator data, and provides more powerful data support for health monitoring and medical diagnosis. By finely adjusting the confidence level, the solution can ensure that the most reliable physiological indicator data can still be obtained under complex and changing environmental conditions. This not only improves the performance of health monitoring equipment, but also brings users a more accurate and personalized health service experience.

[0017] Optionally, the confidence level acquisition of different physiological indicators by different preset physiological indicator monitoring devices includes: Obtain the current environment category information and environment parameter information. The environment category includes home environment and sports environment. The environment parameter information includes environment temperature, environment humidity and altitude information of the area. According to the corresponding relationship between the current environment category information, environmental parameter information, the category of physiological index monitoring equipment and the confidence of different physiological indexes, the confidence of different physiological index monitoring equipment about different physiological indexes is analyzed and determined.

[0018] By adopting the above technical solutions, environmental perception and data analysis are cleverly integrated to achieve intelligent evaluation of the confidence of different physiological indicator monitoring equipment. By obtaining the current environmental category and parameter information, such as home or sports environment, as well as specific data such as temperature, humidity and altitude, the solution can more accurately adjust the equipment's monitoring confidence for different physiological indicators. This dynamic adjustment mechanism ensures that the monitoring data of physiological indicators in various environments are highly accurate and reliable, providing users with more personalized and refined health management services.

[0019] Optionally, the method further includes the following steps after controlling the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information: Obtain the patient's subsequent physiological index related data; Extracting the patient's key physiological index-related data after a preset time interval based on the patient's subsequent physiological index-related data; According to the correspondence between the key physiological indicator data range and the resuscitation effect evaluation value within which the key physiological indicator related data of the patient falls after the preset time interval, the resuscitation effect evaluation value matched by different key physiological indicator related data is analyzed and determined, and the overall resuscitation evaluation value is calculated; If the overall resuscitation assessment value exceeds the preset resuscitation assessment threshold, the existing setting is maintained; If the overall resuscitation assessment value is less than or equal to the preset resuscitation assessment threshold, the patient's key physiological indicator data after the preset time interval is input into the trained model of the problem prediction confidence value, and the confidence value of the problem is output. The confidence value of the problem is converted through a preset probability estimation method to obtain the probability estimate of each possible problem, and the probability estimate of the possible problem is sent to the terminal held by the person in charge.

[0020] By adopting the above technical solutions, through refined data processing and intelligent evaluation, the efficiency and effect of cardiopulmonary resuscitation have been significantly improved. After controlling the adjustment of the cardiopulmonary resuscitation machine, the patient's physiological indicators are continuously monitored, key data are extracted in real time, and the resuscitation effect is evaluated, ensuring the scientificity and pertinence of the treatment process. When the resuscitation effect is not good, the system can quickly identify and predict potential problems through the model, and promptly notify the person in charge of possible problems and probabilities, providing valuable information support for adjusting the treatment strategy. This intelligent processing method not only improves the accuracy of treatment, but also buys valuable treatment time for medical staff, which helps to improve the survival rate of patients.

[0021] In a second aspect, the present application provides a computer storage medium, which adopts the following technical solution: A computer storage medium includes a program that can be loaded and executed by a processor to implement an adaptive compression control method in an adaptive compression control system of a cardiopulmonary resuscitation machine as described in the first aspect. BRIEF DESCRIPTION OF THE DRAWINGS

[0022] Figure 1 It is a flow chart of an adaptive compression control method in an adaptive compression control system of a cardiopulmonary resuscitation machine according to an embodiment of the present application.

[0023] Figure 2 It is a flowchart of another embodiment of the present application for analyzing whether a person who is to be resuscitated by cardiopulmonary resuscitation is wearing a physiological indicator monitoring device.

[0024] Figure 3 It is a schematic diagram of the process of obtaining a preset distance range centered on a cardiopulmonary resuscitation machine according to another embodiment of the present application.

[0025] Figure 4 It is a schematic diagram of the process of obtaining a preset distance range centered on a cardiopulmonary resuscitation machine according to another embodiment of the present application. DETAILED DESCRIPTION

[0026] The present application is further described in detail below in conjunction with the accompanying drawings.

[0027] Reference Figure 1, is an adaptive compression control system of a cardiopulmonary resuscitation machine disclosed in the present application, comprising a cardiopulmonary resuscitation machine, at least one processor and at least one memory storing a computer program, wherein the at least one processor is configured to implement an adaptive compression control method of the cardiopulmonary resuscitation machine when executing the computer program, and the specific steps are as follows: Step S100, analyzing whether the person to be resuscitated by cardiopulmonary resuscitation is wearing a physiological index monitoring device. If not, executing step S200; if yes, executing step S400.

[0028] First, the system will automatically scan and identify whether there are physiological indicator monitoring devices on the person who is undergoing cardiopulmonary resuscitation through wireless sensors or similar device detection mechanisms. These devices may include electrocardiogram monitors, blood oxygen saturation monitors, etc., which can provide key physiological indicators such as heart rate, respiratory rate, blood pressure, etc. of the patient in real time.

[0029] If the system detects that the person to be resuscitated is not wearing any physiological indicator monitoring equipment, it will immediately execute step S200, that is, obtaining the age group information of the person to be resuscitated through other means (such as asking family members, checking medical records, etc.), and analyzing and determining the appropriate resuscitation mode of the cardiopulmonary resuscitation machine based on this.

[0030] If the system detects that the person to be resuscitated is wearing a physiological indicator monitoring device, step S200 will be skipped and step S400 will be executed directly. In this step, the system will establish a data connection with the physiological indicator monitoring device, and receive and identify the physiological indicator related data transmitted by the device in real time. At the same time, the system will also obtain the age group information of the person to be resuscitated, so as to combine the real-time physiological indicator data in the subsequent steps to make more accurate and personalized adjustments to the compression control of the cardiopulmonary resuscitation machine.

[0031] Step S200, obtaining the age group of the person to be resuscitated, and analyzing and determining the resuscitation mode of the cardiopulmonary resuscitation machine according to the corresponding relationship between the age group of the person to be resuscitated and the resuscitation mode of the cardiopulmonary resuscitation machine.

[0032] Specifically, the age of the person to be resuscitated is obtained as follows: 1. Use the camera on site or the camera of the smart device carried by the emergency personnel to collect facial images of the person to be resuscitated. Through artificial intelligence image recognition technology, facial features such as wrinkles, skin elasticity, hair color, etc. are analyzed to roughly determine the age of the patient. For example, the artificial intelligence algorithm can divide patients into different age groups such as young, middle-aged, and elderly according to the number and depth of facial wrinkles, the grayness of hair, and other features. 2. Obtain the patient's age information through voice dialogue with on-site personnel (such as the patient's companions, witnesses, etc.). For example, the device sends a voice question: "How old is the patient?" After the on-site personnel answer, the voice recognition system converts the answer into text information and analyzes and processes it.

[0033] The analysis and determination of the resuscitation mode of the cardiopulmonary resuscitation machine is as follows: the age group information obtained by intelligent means is matched with the pre-stored database of the correspondence between age groups and the resuscitation mode of the cardiopulmonary resuscitation machine. This database is established based on a large amount of medical research and clinical experience, and contains the physiological characteristics of patients of different age groups and suitable resuscitation mode parameters.

[0034] Suppose in an emergency scenario: After the emergency personnel arrive at the scene, they start the intelligent system of the cardiopulmonary resuscitation machine. First, the camera captures the patient's facial image, and the artificial intelligence image recognition system analyzes and determines that the patient may be in middle age. At the same time, the voice interaction system asks questions to the on-site personnel to confirm that the patient is around 45 years old. Based on this age group information, the system searches the database for the corresponding resuscitation mode parameters. For middle-aged people around 45 years old, it may be considered that their bodies have a certain tolerance, but there may also be potential risks such as cardiovascular disease. The resuscitation mode of the cardiopulmonary resuscitation machine can be set to a compression depth of 5-6 cm and a compression frequency of 100-120 times per minute.

[0035] Step S300, controlling the cardiopulmonary resuscitation machine to execute the resuscitation mode determined by the analysis.

[0036] Specifically, when controlling the cardiopulmonary resuscitation machine to execute a certain resuscitation mode, it is necessary to ensure the accurate setting and stable operation of various parameters. This includes precise control of key indicators such as compression depth, compression frequency, and ventilation volume. For example, through advanced motor control systems and sensor feedback, ensure that the compression depth is always maintained within the preset range and the error is controlled within a very small range. At the same time, use a high-precision timer and speed control system to ensure the accuracy and stability of the compression frequency. For the ventilation function, the gas delivery volume and gas delivery time must be accurately controlled according to the requirements of the resuscitation mode to ensure that the patient receives appropriate oxygen supply. For example, the ventilation status is monitored in real time through flow sensors and pressure sensors, and the gas delivery parameters are adjusted in time to meet the needs of the patient.

[0037] Step S400, identifying and acquiring real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated, and simultaneously acquiring the age group of the person to be resuscitated.

[0038] Specifically, the physiological indicator monitoring equipment worn by the person to be resuscitated can be identified and data can be obtained in a variety of ways. Wireless communication technologies, such as Bluetooth and Wi-Fi, can be used to establish a connection with the monitoring equipment and receive real-time physiological indicator data. At the same time, for some devices with specific interfaces, data can also be transmitted through wired connections.

[0039] Once the connection is established with the physiological indicator monitoring device, it immediately starts to receive and process real-time physiological indicator related data. This includes key indicators such as heart rate, blood pressure, and blood oxygen saturation. Through high-speed data processing algorithms, these data are analyzed and filtered in real time to remove noise and interference, ensuring the accuracy and reliability of the data.

[0040] At the same time, real-time data is combined with timestamps to record the acquisition time of each data point for subsequent analysis and evaluation of changing trends of physiological indicators during the resuscitation process.

[0041] For example, first responders found that the person who was to perform CPR was wearing a smart bracelet that monitored heart rate, blood pressure, and blood oxygen saturation.

[0042] The first responders used the wireless connection function of the CPR machine to establish a connection with the smart bracelet via Bluetooth. The CPR machine immediately began to receive the real-time physiological index data transmitted by the bracelet and quickly processed it. For example, it removed the noise caused by the patient's body movement or the surrounding environment to ensure the accuracy of the heart rate data. At the same time, the first responders learned from the eyewitnesses at the scene that the patient was about 50 years old. In this way, the CPR machine simultaneously obtained the patient's real-time physiological index data and age group information, preparing for subsequent analysis and adjustments.

[0043] Step S500, the real-time physiological index related data and age group identified and obtained are input into a pre-trained cardiopulmonary resuscitation machine adjustment information analysis model, and the cardiopulmonary resuscitation machine adjustment information is output.

[0044] The model structure of the cardiopulmonary resuscitation machine adjustment information analysis model is as follows: Input layer: Receives real-time physiological index related data and age information of the person to be resuscitated. Real-time physiological indexes may include data of multiple dimensions such as heart rate, blood pressure, and blood oxygen saturation, and each dimension of data is used as an input node. Age information can be used as a single input node, or converted into multiple input nodes by encoding. For example, the input layer may have a heart rate node, a blood pressure node, a blood oxygen saturation node, and an age encoding node. Middle layer: A multi-layer neural network structure may be used, such as a deep neural network or a convolutional neural network. The function of the middle layer is to extract and abstract the input data features and learn the complex relationship between different physiological indicators and age groups and the adjustment information of the cardiopulmonary resuscitation machine. For example, the middle layer may be composed of multiple hidden layers, each of which contains a certain number of neurons. The output of the neuron is nonlinearly transformed by the activation function to enhance the expression ability of the model. Output layer: Outputs the adjustment information of the cardiopulmonary resuscitation machine. The adjustment information may include a compression depth adjustment value, a compression frequency adjustment value, a ventilation adjustment value, etc. The number of nodes in the output layer is determined according to the specific adjustment information dimension. For example, the output layer may have a compression depth adjustment node, a compression frequency adjustment node, a ventilation volume adjustment node, and the like.

[0045] The training of the cardiopulmonary resuscitation machine adjustment information analysis model is as follows: 1. Data collection: Collect a large amount of cardiopulmonary resuscitation case data, including physiological index data of patients of different age groups, the initial settings and actual adjustments of the cardiopulmonary resuscitation machine, and the final resuscitation effect. These data can come from clinical records of hospitals, simulation experiments or real emergency scenarios. Clean and preprocess the data to remove outliers and noise to ensure the quality and reliability of the data. 2. Labeling and target setting: For each case data, according to the experience and best practices of professional medical staff, label the corresponding cardiopulmonary resuscitation machine adjustment information as the target output. For example, according to the physiological indicators and age group of the patient, determine the appropriate compression depth, compression frequency and ventilation adjustment value. Set a suitable loss function to measure the difference between the model output and the target output. Common loss functions include mean square error, cross entropy, etc. 3. Training process: Use training data to train the model. Use optimization algorithms (such as stochastic gradient descent) to continuously adjust the parameters of the model to minimize the loss function. During the training process, the data can be divided into training set, validation set and test set to evaluate the performance of the model and prevent overfitting. Regularly evaluate the performance of the model on the validation set. When the model performance no longer improves, stop training and select the model parameters with the best performance as the final model.

[0046] For example, the output adjustment information may be specific adjustment suggestions such as increasing the compression depth by 1 cm, increasing the compression frequency by 5 times / minute, and increasing the ventilation volume by 100 ml.

[0047] Assume that in an emergency scenario, the person to be resuscitated is a 50-year-old male. The real-time physiological indicator data obtained by the physiological indicator monitoring device are heart rate 40 times / minute, blood pressure 80 / 50mmHg, and blood oxygen saturation 85%. These real-time physiological indicator data and the patient's age (50 years old) are input into the cardiopulmonary resuscitation machine adjustment information analysis model. After analysis, the model may output adjustment information such as increasing the compression depth from the current 5 cm to 6 cm, increasing the compression frequency from 100 times per minute to 110 times per minute, and increasing ventilation to improve blood oxygen saturation.

[0048] In another scenario, the patient is a 30-year-old woman with physiological indicators of heart rate 35 beats / minute, blood pressure 70 / 40 mmHg, and blood oxygen saturation 80%. After inputting these data and age group (30 years old) into the model, the model may output different adjustment information, such as keeping the compression depth unchanged, but increasing the compression frequency to 120 times per minute, and appropriately adjusting the ventilation volume to suit the patient's condition.

[0049] Step S600, controlling the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information.

[0050] The cardiopulmonary resuscitation machine has a precise parameter adjustment function and can accurately change the corresponding operating parameters according to the received adjustment information. The adjustment of the compression depth can be achieved by adjusting the motor control system or the mechanical structure. For example, the compression depth can be changed by adjusting the stroke of the motor or the length of the mechanical connecting rod. The compression frequency can be adjusted by controlling the speed of the motor or the setting of the timer. For example, the compression frequency can be increased by increasing the speed of the motor or shortening the time interval of the timer. The ventilation volume can be adjusted by adjusting the gas flow control valve or changing the working parameters of the ventilation equipment. For example, the opening of the gas flow control valve is increased to increase the ventilation volume.

[0051] Reference Figure 2 , analyze whether the person who is undergoing cardiopulmonary resuscitation is wearing physiological indicator monitoring equipment including: Step S110, analyzing whether there is a physiological index monitoring device connected to the cardiopulmonary resuscitation machine within a preset distance range centered on the cardiopulmonary resuscitation machine. If not, executing step S120; if yes, executing step S130.

[0052] The connection relationship includes direct connection and pending connection.

[0053] The cardiopulmonary resuscitation machine searches and detects physiological indicator monitoring devices within a preset distance range through a built-in wireless communication module (such as Bluetooth, Wi-Fi, etc.) or a wired connection interface.

[0054] For direct connection, the CPR machine can actively scan the list of connected devices or receive connection requests from other devices to determine whether there is a physiological indicator monitoring device directly connected to itself. For example, if the CPR machine and a smart bracelet have been successfully paired via Bluetooth and a stable data transmission channel has been established, then they are considered to have a direct connection relationship.

[0055] For pending connections, the CPR machine can send a broadcast signal to ask if there are any physiological indicator monitoring devices that can be connected nearby. If a device responds and indicates that it is in a connectable state, but has not yet established an actual connection with the CPR machine, then they are considered to be in a pending connection relationship. For example, the CPR machine sends a Bluetooth broadcast signal, and an unpaired blood pressure monitor nearby responds to the signal. At this time, it is considered that the blood pressure monitor and the CPR machine are in a pending connection relationship.

[0056] Step S120, confirming that the person to be resuscitated is not wearing any physiological indicator monitoring equipment.

[0057] Step S130, analyzing the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine.

[0058] First, the specific meanings of direct connection and pending connection are clarified. Direct connection means that the physiological index monitoring device has established a stable data transmission channel with the cardiopulmonary resuscitation machine and can transmit physiological index data in real time. Pending connection means that the device is in a state that can be connected, but has not yet established an actual connection with the cardiopulmonary resuscitation machine.

[0059] The detected physiological indicator monitoring devices with connection relationships are classified to determine which are directly connected devices and which are waiting to be connected. This can be judged by indicators such as the communication status flag and signal strength of the device.

[0060] Step S140, if the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only a direct connection, a preset direct connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and based on the analysis results, it is confirmed whether the person to be resuscitated is wearing the physiological indicator monitoring device.

[0061] Direct connection user matching analysis method: an analysis method used to determine whether the user of a physiological indicator monitoring device directly connected to a cardiopulmonary resuscitation machine is a person to be resuscitated.

[0062] Directly connected device: A device that establishes a stable data transmission channel with the cardiopulmonary resuscitation machine and can transmit physiological indicator data in real time. For example, a smart bracelet that is connected via Bluetooth and has a stable signal strength within a certain range.

[0063] The specific execution steps of the preset direct connection user matching analysis method are as follows: The steps for device identification matching are as follows: 1. The cardiopulmonary resuscitation machine reads the unique identification information of the directly connected device, such as the device serial number, MAC address, etc. Record the reading time to ensure the timeliness of the information. 2. Compare the identification information with the patient information database. This database can pre-set a probability threshold for successful matching, such as a similarity of more than 80% to consider the match successful. For example, if the device serial number has more than 8 digits in common with the record in the database, or the first half of the MAC address is exactly the same, it can be considered that the probability of matching is high. 3. If the matching probability exceeds the set threshold, it is preliminarily determined that the device may be associated with a specific patient and proceed to the next step of analysis; if the threshold is not reached, continue to collect other information or determine that the device is not related to the person to be resuscitated.

[0064] The steps of physiological data feature matching are as follows: 1. Receive real-time physiological index data from the directly connected device, including heart rate, blood pressure, blood oxygen saturation, electrocardiogram, etc. Set the normal range and abnormal range of each physiological index and assign different weights. For example, the normal range of heart rate is 60-100 beats / minute, the weight is 0.2 for deviation within 10% of the normal range, 0.4 for deviation from 10%-20%, and 0.6 for deviation above 20%. The same is true for blood pressure, blood oxygen saturation and other indicators. 2. Analyze the characteristics of these physiological index data, calculate the degree of deviation from the normal range and the corresponding weight value. If it is known that the person to be resuscitated has a history of a specific disease, adjust the weight according to the impact of the disease on the physiological index. For example, for patients with a history of heart disease, the weight of abnormal heart rate can be appropriately increased. 3. Combine the weight values ​​of all physiological indicators to obtain a total score for physiological data feature matching. Set a total score threshold, such as reaching 0.5 points or more to consider that there is a high probability that the user of the device is a person to be resuscitated.

[0065] The comprehensive judgment steps are as follows: Comprehensive judgment is performed based on the results of device identification matching and physiological data feature matching. If the device identification matching probability is high and the total score of physiological data feature matching exceeds the set threshold, then it can be relatively certain that the user of the device is a person who needs cardiopulmonary resuscitation. For example, if the device identification matching probability is 85% and the total score of physiological data feature matching is 0.6, it can be determined that the user is a person who needs cardiopulmonary resuscitation.

[0066] Step S150, if the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only to be connected, a preset matching analysis method for the user to be connected is used to analyze whether the user of the physiological indicator monitoring device to be connected to the cardiopulmonary resuscitation machine is the person to be resuscitated, and whether the person to be resuscitated is wearing the physiological indicator monitoring device based on the analysis result.

[0067] Matching analysis method for users to be connected: an analysis method used to determine whether the user acted upon by a physiological indicator monitoring device that is in a pending connection relationship with a cardiopulmonary resuscitation machine is a person to be resuscitated.

[0068] Devices to be connected: devices that are in a connectable state but have not yet established a connection with the CPR machine. For example, a smart bracelet or blood pressure monitor that is near the CPR machine and has responded to the CPR machine's broadcast signal but has not yet completed the connection.

[0069] The specific execution steps of the preset matching analysis method for users to be connected are as follows: The specific steps for initial device identification are as follows: 1. The CPR machine sends a broadcast signal. After the connected device responds, the CPR machine obtains its basic information. Record the response time. The shorter the time, the higher the initial response value can be assigned. For example, if the response time is within 1 second, the initial response value is 0.8, 1-2 seconds is assigned 0.6, 2-3 seconds is assigned 0.4, etc. 2. Determine the distance between the device and the CPR machine based on the strength of the response signal. Set the correspondence between the distance range and the distance value. For example, if the distance is within 1 meter, the distance value is assigned 0.9, 1-2 meters is assigned 0.7, 2-3 meters is assigned 0.5, etc.

[0070] The steps for device location inference are as follows: 1. Combined with on-site environmental factors, such as obstacle distribution, determine the influence coefficient on signal propagation. If there are no obvious obstacles around, the coefficient can be set to 0.9; if there are a few obstacles, it is set to 0.7; if there are more obstacles, it is set to 0.5. 2. According to the signal strength and influence coefficient, further refine the approximate position of the device. If the signal strength is high and the influence coefficient is large, it means that the device is more likely to be close to the person who needs cardiopulmonary resuscitation, and the position inference value is assigned to 0.8; if the signal strength is medium and the influence coefficient is medium, the position inference value is assigned to 0.6; if the signal strength is low and the influence coefficient is small, the position inference value is assigned to 0.4.

[0071] The steps for device feature matching are as follows: 1. Analyze the appearance features of the device to be connected, such as color, shape, size, etc. Set the matching weights of different features, for example, the color matching weight is 0.2, the shape matching weight is 0.3, and the size matching weight is 0.2. If the color of the device matches the color of the device that the person who may be undergoing cardiopulmonary resuscitation may use, assign the color matching value to the weight value, such as 0.2; the same applies to shape and size. 2. Determine the brand and model of the device. If it matches the brand and model of the device that the person who may be undergoing cardiopulmonary resuscitation may use, assign the brand and model matching value to 0.3.

[0072] The comprehensive judgment steps are as follows: The results of the three steps of preliminary device identification, position inference and feature matching are combined to calculate the total score. Total score = initial response value × 0.2 + distance value × 0.2 + position inference value × 0.3 + color matching value × 0.2 + shape matching value × 0.3 + size matching value × 0.2 + brand model matching value × 0.3.

[0073] A total score threshold is set. For example, if the total score reaches 0.6 or above, it is considered that the user of the device may be a person who needs cardiopulmonary resuscitation. If the total score is lower than the threshold, it is judged that the device is not very relevant to the person who needs cardiopulmonary resuscitation, and further information collection or other methods are needed to judge.

[0074] Step S160, if the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine includes direct connection and pending connection, a preset comprehensive connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and based on the analysis results, it is confirmed whether the person to be resuscitated is wearing the physiological indicator monitoring device.

[0075] Comprehensive connection user matching analysis method: a quantitative analysis method used to determine whether the user of a physiological indicator monitoring device that is directly connected and waiting to be connected to a cardiopulmonary resuscitation machine is a person waiting for cardiopulmonary resuscitation.

[0076] The specific execution steps of the comprehensive connection user matching analysis method are as follows: Direct connection device analysis steps: 1. Device identification matching quantification: Read the unique identification information of the directly connected device, such as the device serial number, MAC address, etc. Compare with the patient information database and set the matching degree calculation formula, such as (number of identical characters / total number of characters) × 100%. If the matching degree reaches more than 80%, the identification matching value is assigned to 0.4. 2. Physiological data feature matching quantification: Obtain real-time physiological indicator data from the directly connected device, including heart rate, blood pressure, blood oxygen saturation, etc. Set the normal range and deviation weight of each indicator, for example, the normal range of heart rate is 60-100 beats / minute, the weight of deviation within 10% of the normal range is 0.2, the weight of deviation 10%-20% is 0.4, and the weight of deviation above 20% is 0.6. 3. The physiological data feature matching value is obtained by combining the weights of each indicator. If the total score is above 0.5 points, the value is assigned to 0.4.

[0077] Analysis steps for devices to be connected: 1. Quantification of preliminary identification of devices: The cardiopulmonary resuscitation machine sends a broadcast signal. After the device to be connected responds, the response time and signal strength are recorded. The initial response value is assigned to a response time of 0.3 within 1 second, 0.2 for 1-2 seconds, and 0.1 for 2-3 seconds. The distance between the device and the cardiopulmonary resuscitation machine is determined according to the signal strength. The distance is assigned a distance value of 0.3 if the distance is within 1 meter, 0.2 for 1-2 meters, and 0.1 for 2-3 meters. 2. Quantification of device location inference: Determine the influence coefficient on signal propagation in combination with on-site environmental factors. The influence coefficient is 0.3 if there are no obvious obstacles, 0.2 if there are a few obstacles, and 0.1 if there are many obstacles. Determine the location inference value based on the signal strength and the influence coefficient. The location inference value is assigned to a high signal strength and a large influence coefficient of 0.3, the location inference value is assigned to a medium signal strength and a medium influence coefficient of 0.2, and the location inference value is assigned to a low signal strength and a small influence coefficient of 0.1. 3. Quantification of device feature matching: Analyze the appearance features, brand model, etc. of the device to be connected, and set the matching weights of different features. The color matching weight is 0.1, the shape matching weight is 0.15, the size matching weight is 0.1, and the brand model matching weight is 0.15. If each feature matches successfully, the corresponding weight value is assigned.

[0078] Comprehensive judgment steps: 1. Calculate the total score based on the analysis results of the directly connected device and the device to be connected. Total score = directly connected device identification matching value + directly connected device physiological data feature matching value + to-be-connected device initial response value + to-be-connected device distance value + to-be-connected device position inference value + to-be-connected device color matching value + to-be-connected device shape matching value + to-be-connected device size matching value + to-be-connected device brand and model matching value. 2. Set the total score threshold. For example, if the score reaches 0.8 or above, it is considered that the user of the device is a person who is waiting for cardiopulmonary resuscitation; 0.6-0.8 points means that the user may be a person who is waiting for cardiopulmonary resuscitation and needs further confirmation; if the score is lower than 0.6, it is judged that the device has little to do with the person who is waiting for cardiopulmonary resuscitation.

[0079] Reference Figure 3 , the acquisition of the preset distance range centered on the cardiopulmonary resuscitation machine includes: Step S111, obtaining information related to first aid scene factors, where the information related to first aid scene factors includes the size of the environment space and the density of personnel distribution.

[0080] Information related to first aid scenario factors can be obtained through the user inputting his own judgment of the environmental space size and personnel distribution density, or it can be obtained through detection devices pre-equipped in the cardiopulmonary resuscitation machine.

[0081] Regarding the acquisition of the size of the environment space, the cardiopulmonary resuscitation machine can be equipped with a distance sensor, such as a laser distance sensor or an ultrasonic sensor, which transmits signals in different directions and measures the distance to surrounding objects based on the time it takes for the signals to return. By measuring in multiple directions, the size of the surrounding space can be roughly estimated.

[0082] For example, a cardiopulmonary resuscitation machine can emit laser beams at certain angles in the horizontal direction to measure the distance to surrounding walls or obstacles. Based on these distance data, a two-dimensional spatial profile can be constructed to estimate the area of ​​the environment. If combined with the measurement in the vertical direction, the volume information of the space can be obtained.

[0083] Regarding the density of personnel distribution, the CPR machine can be equipped with infrared sensors or thermal imaging sensors to detect the distribution of people around it. These sensors can detect the heat emitted by the human body to determine the location and number of people.

[0084] For example, infrared sensors can scan the surrounding environment and detect infrared radiation signals from the human body. By analyzing the intensity and distribution of these signals, the approximate location and density of people can be determined. Thermal imaging sensors can generate thermal imaging images to intuitively show the distribution of people around.

[0085] For example, infrared sensors can scan the surrounding environment and detect infrared radiation signals from the human body. By analyzing the intensity and distribution of these signals, the approximate location and density of people can be determined. Thermal imaging sensors can generate thermal imaging images to intuitively show the distribution of people around.

[0086] Step S112, analyzing and determining the preset distance range centered on the cardiopulmonary resuscitation machine based on the correspondence between the space size range within which the environmental space size falls, the personnel distribution density interval range within which the personnel distribution density falls, and the preset distance range centered on the cardiopulmonary resuscitation machine.

[0087] Specifically, based on the actual data provided by the detection device, the corresponding relationship between the size range of the environmental space, the range of the personnel distribution density interval and the preset distance range can be refined and adjusted. For example, through multiple practical applications in different scenarios, the data of the detection device and the actual first aid effect feedback are collected, and the corresponding relationship rules are continuously optimized to make it more accurately adapt to different first aid scenarios.

[0088] In addition, different weights can be set for the two factors of environmental space size and personnel distribution density. In some cases, environmental space size may have a greater impact on the preset distance range, while in other cases, personnel distribution density may be a more critical factor. Through the data feedback of the detection device, these weights can be dynamically adjusted to achieve a more reasonable preset distance range determination.

[0089] For example, when performing first aid in a hospital ward, the distance sensor on the CPR machine detects that the ward is relatively small, about 20 square meters. The infrared sensor detects that there are a small number of medical staff and family members in the ward, and the density of people is low. According to the pre-set correspondence, in this environment with a small space and low density of people, the CPR machine determines that the preset distance range centered on it is 3 meters.

[0090] During the emergency treatment, some more medical staff entered the ward, and the density of people increased. At this time, the infrared sensor detected this change and fed back the information to the cardiopulmonary resuscitation machine. The control system readjusted the preset distance range to 4 meters based on the new density of people and the corresponding relationship to ensure that more possible physiological indicator monitoring devices can be detected.

[0091] Reference Figure 4 , the acquisition of the preset distance range centered on the cardiopulmonary resuscitation machine includes: Step S11a, obtaining the event type of using the cardiopulmonary resuscitation machine, the event type includes disaster scene, traffic accident scene and other scenes.

[0092] The event type of using the cardiopulmonary resuscitation machine can be confirmed by the user inputting the corresponding event, or by collecting environmental information through a variety of sensors pre-equipped on the cardiopulmonary resuscitation machine, which can help infer the event type of using the cardiopulmonary resuscitation machine.

[0093] Sound sensors can capture the surrounding sound characteristics. At a disaster site, there may be a lot of specific sound patterns such as noise and alarms. By analyzing the intensity, frequency, and duration of the sound, it can help determine the type of event. For example, if a sound sensor detects continuous high-decibel noise and a chaotic sound environment, it may point to a disaster site.

[0094] Image sensors (such as cameras) can capture images of the surrounding environment. Image recognition technology can be used to analyze scene features in images, such as collapsed buildings and damaged vehicles, to determine the type of event. For example, if there are a lot of rubble and injured people in the image, it is likely to be a disaster scene; if there are obvious signs of vehicle collision and damaged vehicles, it may be a traffic accident scene.

[0095] For example, a CPR machine was delivered to a site, and the accelerometer detected a strong vibration followed by a continuous smaller vibration. The sound sensor captured high-decibel noise and alarms. The image sensor captured some collapsed buildings and injured people around.

[0096] The control system of the cardiopulmonary resuscitation machine combines the data of these detection devices and determines that this is likely to be a disaster site. According to the pre-set correspondence, the preset distance range centered on the cardiopulmonary resuscitation machine is determined to be a larger value in order to search for possible physiological indicator monitoring equipment in the vast disaster area.

[0097] Step S11b: analyzing and determining the preset distance range centered on the cardiopulmonary resuscitation machine according to the correspondence between the event type of using the cardiopulmonary resuscitation machine and the preset distance range centered on the cardiopulmonary resuscitation machine.

[0098] Take the disaster scene as an example: the CPR machine is activated at the disaster site after an earthquake. The distance sensor detects that the surrounding space is vast, there are a lot of ruins and collapsed buildings, and it is difficult to determine the specific location of people. The image sensor recognizes that there are many injured people scattered in different areas around.

[0099] Based on these detection data and the correspondence between the disaster site and the preset distance range, the CPR machine determines that the preset distance range centered on it is 20 meters. As the rescue work progresses, personnel are gradually concentrated at several temporary rescue points. After the distance sensor and image sensor detect this change, the CPR machine adjusts the preset distance range to 15 meters to search for physiological indicator monitoring equipment more efficiently.

[0100] Take the traffic accident scene as an example: a traffic accident involving multiple vehicles occurred on the highway. The image sensor identified that the accident involved three large trucks and several small cars, and the road was relatively wide. The distance sensor measured that there was a certain amount of open space around. Based on this information and the correspondence between the traffic accident scene and the preset distance range, the CPR machine determined that the preset distance range centered on it was 10 meters. Over time, some passing drivers stopped to participate in the rescue, bringing more information and possible resources. After the detection device sensed these new people and vehicles, the CPR machine expanded the preset distance range to 12 meters to search for more clues related to the injured.

[0101] Furthermore, it is also possible to consider the types of events in which a cardiopulmonary resuscitation machine is used. Some events may require more than one cardiopulmonary resuscitation machine. In the case of a small number of cardiopulmonary resuscitation machines on site, the following settings may be made, as follows: An adaptive compression control system for a cardiopulmonary resuscitation machine further includes steps after obtaining the event type of using the cardiopulmonary resuscitation machine, specifically as follows: By identifying and obtaining the real-time physiological index related data transmitted by the physiological index monitoring equipment worn by the person waiting for cardiopulmonary resuscitation, it is analyzed whether there are multiple people waiting for cardiopulmonary resuscitation.

[0102] If not, keep the original setting.

[0103] If yes, the change of the event is further analyzed according to the event type, and the urgency of each person who needs cardiopulmonary resuscitation is determined by combining the real-time physiological indicator related data obtained and other information at the event scene.

[0104] Patients with a higher degree of urgency and who are more in need of CPR are given priority. If the number of CPR machines on site is insufficient, the drone transportation system is activated to quickly transport additional CPR machines to the incident site for rescue. The specific steps are as follows: First, the physiological indicators of all personnel to be resuscitated are continuously monitored, including heart rate, blood pressure, blood oxygen saturation, etc. According to the preset urgency assessment model, combined with the physiological indicator data and the event type, the urgency score of each person to be resuscitated is calculated. For example, at the disaster site, patients with a low heart rate and a severe decrease in blood oxygen saturation will have a higher urgency score. Then, all personnel to be resuscitated are sorted according to the urgency score. Patients with a high degree of urgency are given priority to be assigned CPR machines for rescue. If the number of CPR machines on site cannot meet the demand, a drone transportation request is immediately triggered. After receiving the request, the drone transportation system quickly loads the CPR machine and plans the best flight path to the incident site. During the transportation process, the transportation progress and location information are fed back to the command center in real time. When the drone arrives at the scene with the CPR machine, it is immediately put into use to provide timely CPR support for patients in urgent need of rescue. At the same time, the status information of all people waiting for cardiopulmonary resuscitation is continuously updated so that the rescue strategy can be adjusted at any time.

[0105] Specifically, the changes in events can be further analyzed according to the event type, and the following classification analysis can be conducted, as follows: Disaster site: For disaster sites caused by natural disasters such as earthquakes and floods, continuously monitor changes in environmental factors, such as aftershock intensity and water level changes. If aftershocks are frequent and strong, it means that the situation at the site may further deteriorate and the difficulty of rescue will increase. At the same time, observe the progress of the rescue team and the supply of materials to judge the changes in the overall rescue situation. For example, if the rescue channel is blocked or there is a shortage of rescue materials, it may affect the continued implementation of cardiopulmonary resuscitation. At disaster sites such as fires, pay attention to the direction and intensity of the fire. If the fire spreads rapidly, more people may be injured and require cardiopulmonary resuscitation, which will also affect the safety and efficiency of the rescue. In addition, analyze the smoke concentration and the spread of toxic gases, which may aggravate the patient's condition and affect the effect of cardiopulmonary resuscitation. Traffic accident site: Continuously observe the traffic conditions around the accident site. If the traffic congestion is serious, it may affect the arrival time of rescue vehicles and equipment and prolong the waiting time of patients. At the same time, pay attention to whether there are new vehicles involved in the accident or the occurrence of secondary accidents, and adjust the rescue strategy in time. Analyze the damage and leakage risks of the accident vehicles. For example, if a vehicle is leaking fuel or there is a risk of explosion, the patient needs to be moved to a safe area as quickly as possible for CPR to avoid further injury.

[0106] Physiological indicators are analyzed as follows: Heart rate: A heart rate that is too low or too high may indicate that the patient's condition is serious. For example, a heart rate below 40 beats / minute or above 150 beats / minute may mean that heart function is severely impaired and the level of urgency is high. Blood pressure: Low blood pressure (systolic blood pressure below 90 mmHg) or high blood pressure (systolic blood pressure above 180 mmHg) may indicate that the patient has serious problems such as shock and cardiovascular disease, and the level of urgency is high. Blood oxygen saturation: Blood oxygen saturation below 90% usually indicates that the patient is severely hypoxic and may require immediate cardiopulmonary resuscitation. Especially in harsh environments such as disaster sites or traffic accident sites, low blood oxygen saturation may quickly cause the patient's condition to deteriorate. Respiratory rate: Rapid breathing (respiratory rate above 25 times / minute) or slow breathing (respiratory rate below 10 times / minute) may indicate that the patient has respiratory dysfunction and the level of urgency is high.

[0107] Analysis of other information at the scene of the incident: Extent of injury: Observe the patient's trauma, such as extensive burns, severe fractures, bleeding, etc. Patients with severe trauma usually have a higher level of urgency and require priority for cardiopulmonary resuscitation and treatment. State of consciousness: Patients who are in a coma, confused or unconscious have a higher level of urgency. The state of consciousness can be judged by calling the patient and observing his or her reaction. Age and underlying diseases: The elderly and patients with underlying diseases (such as heart disease, diabetes, respiratory diseases, etc.) may be more likely to have their condition worsen in an emergency, and the level of urgency is relatively high. On-site environmental factors: Consider whether the patient's environment has an impact on his or her condition. For example, in a high temperature environment, the patient may be prone to heatstroke or dehydration, and the level of urgency is higher; in a cold environment, the patient may suffer from hypothermia, which also requires timely treatment.

[0108] The urgency assessment model is as follows: Establish an urgency assessment model that comprehensively considers physiological indicators, other information at the incident site, and the type of incident. Methods such as weighted average method or machine learning algorithm can be used to assign different weights to each factor, and the patient's urgency score is calculated based on the weight. For example, physiological indicators such as heart rate, blood pressure, blood oxygen saturation, and respiratory rate can be assigned certain weights, and the physiological indicator score is calculated based on the patient's actual physiological indicator values. At the same time, the degree of injury, state of consciousness, age and underlying diseases, on-site environmental factors, etc. are also assigned corresponding weights to calculate other information scores. Finally, the physiological indicator score and other information scores are combined with the weight of the event type to calculate the patient's urgency score.

[0109] Identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated, including: Step S410, obtaining the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine.

[0110] Step S420, if the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is a direct connection, then identify and obtain real-time physiological indicator related data transmitted by the physiological indicator monitoring device worn by the person to be resuscitated.

[0111] Specifically, once the directly connected device is confirmed, the CPR machine begins to identify the real-time physiological indicator-related data transmitted by the device. Different physiological indicator monitoring devices may transmit different types of physiological indicator data, such as heart rate, blood pressure, blood oxygen saturation, etc. The CPR machine parses the received data according to the communication protocol and data format of the device and extracts the required physiological indicator information. For example, if a smart bracelet is connected, heart rate and motion data may be transmitted. The CPR machine converts this data into useful information that can be used to analyze and adjust the operation of the CPR machine through specific algorithms and data processing processes.

[0112] Step S430, if the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is to be connected, actively match the connection and identify and obtain the real-time physiological indicator related data transmitted by the physiological indicator monitoring device worn by the person to be resuscitated.

[0113] Specifically, the CPR machine continuously scans the surrounding environment to find physiological indicator monitoring devices that are in a waiting state. This can be achieved by sending a specific broadcast signal or querying a list of connectable devices. For example, the CPR machine can use the device discovery function of Bluetooth to send a query request to detect nearby connectable Bluetooth devices.

[0114] When a device to be connected is detected, the CPR machine obtains basic information about the device, such as device type, brand, model, etc., in order to determine whether it is likely to be the device worn by the person to be resuscitated.

[0115] Based on the detected information of the devices to be connected, the CPR machine attempts to actively pair and connect with these devices. This may require entering a password, confirming a pairing request, or following a specific connection protocol. For example, if the device to be connected is a smart bracelet, you may need to confirm the connection request with the CPR machine on the bracelet, or enter a preset pairing password.

[0116] Step S440: If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is that they are directly connected or to be connected at the same time, then obtain the real-time physiological indicator related data transmitted by the physiological indicator monitoring device that is directly connected or to be connected, and analyze whether the same physiological indicator comes from different physiological indicator monitoring devices and the corresponding physiological indicator data are different. If yes, execute step S450; if no, execute step S460.

[0117] Specifically, when the physiological indicator monitoring device and the cardiopulmonary resuscitation machine are in a direct connection and / or a mixed connection relationship to be connected, the cardiopulmonary resuscitation machine first obtains the real-time physiological indicator related data transmitted by all devices in a direct connection state. At the same time, for the device to be connected, the cardiopulmonary resuscitation machine actively matches and connects, and obtains its data after the connection is successful. The acquired data is classified and sorted, and classified according to the type of physiological indicators, so as to analyze whether the same physiological indicator comes from different devices and the data is different.

[0118] Each physiological indicator is checked one by one to determine whether there are differences in the data representing the same physiological indicator from different devices. For example, when checking the heart rate indicator, if two devices transmit different heart rate values, it is determined that there are different data for the same physiological indicator.

[0119] For complex physiological indicators, such as electrocardiograms, more in-depth analysis algorithms may be needed to determine whether there are substantial differences in the data collected by different devices. At the same time, consider the timestamp of the data to ensure that the data compared are within the same time period.

[0120] According to the analysis results, if the same physiological indicator comes from different devices and the data is different, step S450 is triggered to perform confidence analysis and data selection; if this situation does not exist, step S460 is executed to maintain the original settings and continue to use the acquired data for subsequent processing and analysis.

[0121] Step S450, according to the preset confidences of different physiological indicator monitoring devices about different physiological indicators, analyze and determine the confidences of the same physiological indicator from different physiological indicator monitoring devices, and select the same physiological indicator data with the highest confidence as the corresponding physiological indicator data for this application.

[0122] First, it is necessary to pre-set the confidence of different physiological indicator monitoring devices for different physiological indicators. This can be determined based on factors such as the accuracy, reliability, and professionalism of the equipment. For example, professional medical-grade monitoring equipment may have a higher confidence when measuring certain key physiological indicators (such as blood pressure and blood oxygen saturation), while ordinary consumer-grade smart wearable devices may have relatively low confidence in certain indicators.

[0123] The initial confidence values ​​of different devices for different physiological indicators can be determined through a large amount of experimental data, clinical verification, and industry standards. At the same time, this confidence value can be dynamically adjusted according to actual usage and new research results.

[0124] For example, a professional medical electrocardiogram monitoring device may be assigned a higher confidence level, such as 0.9, when measuring heart rate and electrocardiogram-related indicators; while an ordinary smart bracelet may have a confidence level of 0.7 when measuring heart rate.

[0125] When it is determined that the same physiological indicator comes from different physiological indicator monitoring devices and the data are different, the confidence analysis of the same physiological indicator provided by each device is performed according to the preset confidence level. This can be comprehensively judged by comparing factors such as the type, brand, measurement principle and historical performance of different devices.

[0126] For example, if a professional medical sphygmomanometer and a smartwatch both provide different blood pressure data, a higher confidence level may be given to the medical sphygmomanometer, given that the medical sphygmomanometer is usually strictly calibrated and quality tested and is more professional in measuring blood pressure.

[0127] At the same time, further adjustments can be made based on other factors, such as the environment in which the device is used, recent accuracy performance, etc. If a smartwatch has shown high accuracy in recent multiple uses, while a medical blood pressure monitor may have data deviations due to improper use or malfunction, then the confidence levels of both can be adjusted appropriately.

[0128] After performing confidence analysis on the same physiological index provided by different devices, the same physiological index data with the highest confidence is selected as the corresponding physiological index data for this application. This data will be used in the subsequent cardiopulmonary resuscitation machine adjustment information analysis and decision-making process.

[0129] For example, if after analysis, the confidence level of the blood pressure data provided by a professional medical sphygmomanometer is 0.8, and the confidence level of the blood pressure data provided by a smartwatch is 0.6, then the data of the medical sphygmomanometer is selected as the blood pressure physiological indicator data for this application.

[0130] Suppose in an emergency scenario: the cardiopulmonary resuscitation machine is connected to a directly connected smart bracelet and a professional medical oximeter to be connected at the same time. Both the smart bracelet and the medical oximeter provide blood oxygen saturation data, but the values ​​are different. The smart bracelet shows that the blood oxygen saturation is 93%, and the medical oximeter shows 95%. According to the preset confidence level, the professional medical oximeter is usually more accurate and reliable in measuring blood oxygen saturation, so it is assigned a higher confidence level, such as 0.9; while the smart bracelet may have a confidence level of 0.7 in measuring blood oxygen saturation.

[0131] After analysis, the blood oxygen saturation data provided by the medical oximeter has a higher confidence level. Therefore, the 95% of the medical oximeter was selected as the blood oxygen saturation physiological indicator data for this application, which will be used for the subsequent adjustment and analysis of the cardiopulmonary resuscitation machine.

[0132] After the confidence of the same physiological indicator from different physiological indicator monitoring devices is determined by analysis in step S450, it is also necessary to consider whether to select the same physiological indicator data with the highest confidence as the corresponding physiological indicator data for this application. The specific steps are as follows: Calculate the confidence difference: Assume that the device and equipment The confidence levels of measuring the same physiological index are and First, calculate the average confidence of all devices ,in is the number of devices. Then the confidence difference index is calculated , which is the maximum value of the difference between the confidence levels of any two devices.

[0133] Define data stability indicators: As in the previous method, calculate the standard deviation of the same physiological indicator measured by each device over a period of time (for example, the last 5 minutes) as follows: ,in is the number of measurements, Yes Equipment No. The measured value, Yes Equipment The average value during this period.

[0134] Set the stability threshold to ,in is the average standard deviation of all devices measuring the physiological index. Standard Deviation , the data measured by the device is considered stable.

[0135] Filter condition: If the confidence difference index And the data of all devices are stable (that is, the standard deviation of each device is less than or equal to the stability threshold ), the same physiological indicator data with the highest confidence level is selected.

[0136] Otherwise, the weighted average method is used to determine the same physiological indicator data. The weight of the weighted average can be determined based on the confidence level and data stability. Weight ,in Yes Equipment The confidence level, Yes Equipment The standard deviation of is the stability threshold. The final data of the same physiological index is ,in Yes Equipment The same physiological index value is measured.

[0137] Step S460, maintaining the original settings.

[0138] The confidence level of different physiological indicators obtained by the preset different physiological indicator monitoring devices includes: Step S451, obtaining the current environment category information and environment parameter information.

[0139] Environmental categories include home environment and sports environment. The current environment category can be determined in a variety of ways. For example, the device's location information can be combined with a geographic information system (GIS) to determine that if the device is located in a residential area and the time is not working hours, it may be determined as a home environment; if the device is located in a park, gym, stadium, etc., it may be determined as a sports environment.

[0140] The environment category can also be determined by the interaction information with other devices. For example, if it is connected to a smart home system and detects the activities of common household electrical appliances, it can be judged as a home environment; if it is connected to smart devices in a sports venue (such as a sports equipment management system in a gym), it may be judged as a sports environment.

[0141] Environmental parameter information includes ambient temperature, ambient humidity, and altitude information of the area. The ambient temperature can be obtained through the temperature sensor equipped by the cardiopulmonary resuscitation machine itself or the connected environmental monitoring device. The temperature sensor can measure the temperature of the surrounding environment in real time and transmit the data to the control system of the cardiopulmonary resuscitation machine.

[0142] Ambient humidity can also be obtained through appropriate humidity sensors. These sensors can accurately measure the moisture content in the air and provide important information for determining environmental parameters.

[0143] The altitude information of the area can be determined by the Global Positioning System (GPS) or the air pressure sensor. GPS can provide the altitude data of the device's location; the air pressure sensor can calculate the altitude of the area by measuring the atmospheric pressure and combining the known relationship between air pressure and altitude.

[0144] Step S452, analyzing and determining the confidences of different physiological indicator monitoring devices regarding different physiological indicators based on the corresponding relationship between the current environment category information, environmental parameter information, and the category of physiological indicator monitoring devices and the confidences of different physiological indicators.

[0145] First, it is necessary to establish a database that contains the corresponding relationship between the current environment category information, environmental parameter information, physiological indicator monitoring equipment category and the confidence level of different physiological indicators. This database can be constructed through a large amount of experimental data, clinical research and actual use experience.

[0146] For different environmental categories, such as home environment and sports environment, the impact of their characteristics on physiological indicator monitoring equipment is considered separately. For example, in the home environment, it may be relatively stable, and some home physiological indicator monitoring equipment may show higher accuracy in this environment; while in the sports environment, due to factors such as intense physical activity and large environmental changes, some professional sports monitoring equipment may be more reliable.

[0147] Environmental parameter information such as ambient temperature, ambient humidity and altitude information of the area will also have an impact on different physiological indicator monitoring devices. For example, a high temperature and high humidity environment may affect the sensor performance of some devices, while high altitude areas may affect devices that measure indicators such as blood oxygen saturation.

[0148] After obtaining the current environment category information and environmental parameter information, combined with the category of the physiological indicator monitoring equipment, query and analyze in the corresponding relationship database. According to different situations, different analysis methods are used to determine the confidence.

[0149] For example, if you are currently in a home environment with moderate ambient temperature and normal humidity, and you are using a home blood pressure monitor, you can query the database to find that in a home environment, for the physiological indicator of blood pressure, the confidence of this type of home blood pressure monitor is a certain value (such as 0.8). If the environmental parameters change significantly at this time, such as the temperature is too high or too low, the humidity is beyond the normal range, etc., the confidence can be appropriately adjusted according to the preset adjustment rules.

[0150] Assume that you are currently in a home environment with an ambient temperature of 25°C, a humidity of 40%, and a low altitude. You are using a home smart bracelet to monitor physiological indicators such as heart rate and blood pressure.

[0151] The corresponding relationship database shows that in a home environment, the confidence level of the smart bracelet for the heart rate indicator is 0.7. For the blood pressure indicator, the confidence level is 0.6 because the accuracy of home smart bracelets in measuring blood pressure is relatively low.

[0152] Assume that someone needs CPR during an outdoor running activity in a sports environment. The temperature is 30°C, the humidity is 50%, and the altitude is moderate. A professional sports watch is used to monitor physiological indicators such as heart rate and blood oxygen saturation.

[0153] According to the corresponding database, in a sports environment, the confidence level of the professional sports watch for the heart rate indicator is 0.8. For the blood oxygen saturation indicator, considering that there may be some interference factors in a sports environment, but the sports watch is specially designed to adapt to sports scenes, the confidence level is 0.75.

[0154] An adaptive compression control system for a cardiopulmonary resuscitation machine further includes steps after controlling the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information, specifically as follows: Step SA00, obtaining the patient's subsequent physiological index related data.

[0155] Specifically, the patient's physiological indicator-related data can be continuously obtained through physiological indicator monitoring devices connected to the cardiopulmonary resuscitation machine. These devices may include heart rate monitors, blood pressure monitors, blood oxygen saturation monitors, etc. The cardiopulmonary resuscitation machine and these devices can transmit data through wired connections or wireless connections (such as Bluetooth, Wi-Fi, etc.). Some physiological indicator data can also be obtained using the sensors equipped on the cardiopulmonary resuscitation machine itself. For example, some advanced cardiopulmonary resuscitation machines may be equipped with pressure sensors that can indirectly reflect the patient's circulatory system status; or equipped with respiratory sensors to monitor the patient's breathing condition.

[0156] The acquired data related to the patient's physiological indicators need to be stored and managed for subsequent analysis and processing. The data can be stored in the local memory of the cardiopulmonary resuscitation machine, or transmitted to a remote server through a network connection for storage and analysis. The data is marked and classified for quick retrieval and analysis. For example, the data can be classified and stored according to time sequence, physiological indicator type, etc., while recording information such as the time point of data collection and the source of the device.

[0157] Step SB00, extracting the patient's key physiological indicator related data after a preset time interval based on the patient's subsequent physiological indicator related data.

[0158] The setting of the preset time interval needs to comprehensively consider factors such as the progress of cardiopulmonary resuscitation, the severity of the patient's condition, and the speed of change of physiological indicators. Generally speaking, an appropriate time range can be determined based on clinical experience and research results, such as every 5 minutes, 10 minutes or 15 minutes.

[0159] The selection of key physiological indicators should be based on the importance and clinical significance of the effect of cardiopulmonary resuscitation. Common key physiological indicators include heart rate, blood pressure, blood oxygen saturation, respiratory rate, etc. These indicators can directly reflect the patient's vital signs and cardiopulmonary function status.

[0160] Key physiological index related data can be extracted through data screening and analysis methods. For example, for continuously collected physiological index data, statistics such as average value, maximum value, minimum value, etc. within a preset time interval can be calculated as key physiological index data. Or according to a specific threshold or range, data points that meet the conditions can be screened out as key physiological index data.

[0161] Step SC00, according to the correspondence between the key physiological indicator data range and the resuscitation effect evaluation value within which the key physiological indicator related data of the patient falls after a preset time interval, analyze and determine the resuscitation effect evaluation value matched by different key physiological indicator related data, and calculate the overall resuscitation evaluation value.

[0162] First, a large amount of clinical research and practical experience is needed to determine the correspondence between the data ranges of different key physiological indicators and the resuscitation effect evaluation values. This can include collecting physiological indicator data of different patients during cardiopulmonary resuscitation and the final resuscitation effect, analyzing the correlation between these data, and thus establishing a reliable correspondence model.

[0163] For example, for the key physiological index of heart rate, different heart rate ranges can be divided, such as 60-80 beats per minute, 80-100 beats per minute, 100-120 beats per minute, etc., and each range corresponds to a different resuscitation effect evaluation value. Similarly, for other key physiological indicators such as blood pressure and blood oxygen saturation, similar range divisions and evaluation value determinations are also performed.

[0164] Consider the mutual influence between different physiological indicators and comprehensively determine the overall corresponding relationship. For example, within a certain heart rate range, if blood pressure is also within a reasonable range, then the resuscitation effect evaluation value may be higher; conversely, if a physiological indicator exceeds the normal range, the overall resuscitation effect evaluation value may be reduced.

[0165] After obtaining the relevant data of the patient's key physiological indicators after a preset time interval, the data of each key physiological indicator is compared with the corresponding range to determine the range to which it belongs, and based on the pre-established correspondence, the resuscitation effect evaluation value matched by the key physiological indicator is analyzed and determined.

[0166] For example, if the patient's heart rate is 85 beats per minute, according to the corresponding relationship, this heart rate value falls within the range of 80-100 beats per minute, and the corresponding resuscitation effect evaluation value is medium. The same analysis is performed on other key physiological indicators such as blood pressure and blood oxygen saturation to determine their respective resuscitation effect evaluation values.

[0167] The calculation of the overall resuscitation assessment value can be calculated by weighted average and other methods. Different weights are assigned to each key physiological indicator according to the importance of different key physiological indicators. Then, the resuscitation effect assessment value of each key physiological indicator is multiplied by the corresponding weight, and finally all the results are added to obtain the overall resuscitation assessment value. For example, assume that the weights of the three key physiological indicators of heart rate, blood pressure, and blood oxygen saturation are 0.4, 0.3, and 0.3, respectively. If the resuscitation effect assessment value of the heart rate is at a medium level (assuming the corresponding value is 50), the assessment value of the blood pressure is at a high level (assuming the corresponding value is 70), and the assessment value of the blood oxygen saturation is at a medium level (assuming the corresponding value is 50), then the overall resuscitation assessment value = 50×0.4+70×0.3+50×0.3=56.

[0168] Assume that in an emergency scenario: after a period of cardiopulmonary resuscitation, the patient's key physiological index data are extracted after a preset time interval, including a heart rate of 82 beats per minute, a blood pressure of 115 / 75 mmHg, and a blood oxygen saturation of 94%. According to the pre-established correspondence, the resuscitation effect evaluation value corresponding to a heart rate of 80-100 beats per minute is a medium level, assuming 50; the evaluation value corresponding to a blood pressure of 110-120 / 70-80 mmHg is a high level, assuming 70; the evaluation value corresponding to a blood oxygen saturation of 90%-95% is a medium level, assuming 50. Assume that the weights of the three key physiological indicators are 0.4 for heart rate, 0.3 for blood pressure, and 0.3 for blood oxygen saturation. Then the overall resuscitation evaluation value = 50×0.4+70×0.3+50×0.3=56.

[0169] Step SD00: if the overall resuscitation assessment value exceeds the preset resuscitation assessment threshold, the existing setting is maintained.

[0170] Step SE00, if the overall resuscitation assessment value is less than or equal to the preset resuscitation assessment threshold, the patient's key physiological indicator related data after the preset time interval is input into the model of the trained problem prediction confidence value, and the confidence value of the problem is output, and the confidence value of the problem is converted through a preset probability estimation method to obtain the probability estimate of each possible problem, and the probability estimate of the possible problem is sent to the terminal held by the person in charge.

[0171] The model for predicting confidence values ​​of completed training questions is obtained as follows: 1. Collect a large amount of cardiopulmonary resuscitation case data, including various physiological index data of patients during cardiopulmonary resuscitation. 2. Clean the collected physiological index data to remove outliers and noise. Outliers can be detected by statistical methods such as box plots, and appropriate processing can be performed, such as replacing them with medians or means. Standardize the data so that different feature variables have similar scales. Commonly used methods include Z-score standardization, that is, subtracting the mean of each feature variable and dividing it by the standard deviation. Among them, the data is randomly divided into training sets and test sets, and the ratio can be 7:3 or 8:2. The training set is used to train the model, and the test set is used to evaluate the performance of the model. The random forest model is trained using the training set data. During the training process, each decision tree is constructed by randomly sampling the training data (with replacement sampling) and randomly selecting features. 3. Use the trained random forest model to predict the test set data to obtain the predicted category of the question. Calculate the evaluation indicators of the model, such as accuracy, precision, recall, F1 value, etc. Accuracy refers to the ratio of correctly predicted samples to the total number of samples; precision refers to the ratio of samples predicted to be positive that are actually positive; recall refers to the ratio of samples predicted to be positive that are actually positive; F1 value is the harmonic mean of precision and recall. Analyze the performance of the model based on the evaluation results. If the performance is not ideal, adjust the model parameters and retrain and evaluate.

[0172] The confidence value of the problem is converted by a preset probability estimation method as follows: After obtaining the confidence value of the problem, it is converted by a preset probability estimation method. Common methods include normalizing the confidence value to convert it into a range of probability values ​​(between 0 and 1). For example, normalization can be performed using methods such as the softmax function. In this way, the probability estimates of each possible problem can be obtained. These probability estimates represent the likelihood of various possible problems occurring under the current physiological indicator data.

[0173] The estimated probability of each possible problem is sent to the terminal held by the responsible person, such as the doctor's mobile phone, tablet computer or medical monitoring equipment. Data transmission can be carried out through wireless communication technology such as Bluetooth, Wi-Fi or mobile network.

[0174] Suppose in an emergency scenario: after calculation, the overall resuscitation assessment value is 45, which is less than the preset resuscitation assessment threshold of 50. At this time, the patient's key physiological indicators, such as heart rate of 70 beats per minute, blood pressure of 100 / 60mmHg, blood oxygen saturation of 90%, etc., are input into the model of the problem prediction confidence value. After analysis, the model outputs the confidence value of the problem, for example, the confidence of possible breathing problems is 0.7, the confidence of possible heart problems is 0.4, and the confidence of possible brain problems is 0.2. After conversion by the probability estimation method, the probability of breathing problems is estimated to be 0.58, the probability of heart problems is estimated to be 0.32, and the probability of brain problems is estimated to be 0.1. These probability estimates are then sent to the tablet held by the doctor.

[0175] After seeing these probability estimates, the doctor decided to further examine the patient's breathing condition and adjust the treatment plan, such as adjusting the parameters of the ventilator, considering the high probability of respiratory problems.

[0176] Based on the same inventive concept, an embodiment of the present invention provides a computer storage medium, including a computer program product that can be loaded and executed by a processor to implement the following Figures 1 to 4 Procedures for each step involved in the process.

[0177] The embodiments of this specific implementation method are all preferred embodiments of the present application, and are not intended to limit the protection scope of the present application. Therefore, all equivalent changes made based on the structure, shape, and principle of the present application should be included in the protection scope of the present application.

Claims

1. An adaptive compression control system for a cardiopulmonary resuscitation machine, characterized in that: include: CPR machine; at least one processor; At least one memory storing a computer program, and at least one processor configured to implement an adaptive compression control method of a cardiopulmonary resuscitation machine when executing the computer program, the specific steps are as follows: Analyze whether the person who is undergoing cardiopulmonary resuscitation is wearing a physiological indicator monitoring device; If not, the age group of the person to be resuscitated is obtained, and the resuscitation mode of the cardiopulmonary resuscitation machine is analyzed and determined according to the corresponding relationship between the age group of the person to be resuscitated and the resuscitation mode of the cardiopulmonary resuscitation machine; Controlling the cardiopulmonary resuscitation machine to execute the resuscitation mode determined by the analysis; If yes, then identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated, and at the same time obtain the age group of the person to be resuscitated; The identified and acquired real-time physiological index related data and age group are used as input objects, input into a pre-trained cardiopulmonary resuscitation machine adjustment information analysis model, and the cardiopulmonary resuscitation machine adjustment information is output; Control the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information.

2. The adaptive compression control system of a cardiopulmonary resuscitation machine according to claim 1, characterized in that: Analyze whether the person who is undergoing cardiopulmonary resuscitation is wearing a physiological indicator monitoring device, including: Analyze whether there is a physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine within a preset distance range centered on the cardiopulmonary resuscitation machine, wherein the connection relationship includes direct connection and waiting to be connected; If no, confirm that the person to be resuscitated is not wearing any physiological indicator monitoring equipment; If yes, then analyze the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only a direct connection, a preset direct connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and whether the person to be resuscitated is wearing the physiological indicator monitoring device according to the analysis result; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is only to be connected, a preset matching analysis method for users to be connected is used to analyze whether the user of the physiological indicator monitoring device to be connected to the cardiopulmonary resuscitation machine is a person to be resuscitated, and whether the person to be resuscitated is wearing the physiological indicator monitoring device according to the analysis result; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine includes direct connection and pending connection, the preset comprehensive connection user matching analysis method is used to analyze whether the user of the physiological indicator monitoring device connected to the cardiopulmonary resuscitation machine is the person waiting for cardiopulmonary resuscitation, and based on the analysis results, it is confirmed whether the person waiting for cardiopulmonary resuscitation is wearing the physiological indicator monitoring device.

3. The adaptive compression control system of a cardiopulmonary resuscitation machine according to claim 2, characterized in that: Acquisition of preset distance ranges centered on the CPR machine includes: Obtain information related to emergency scene factors, including the size of the environment space and the density of personnel distribution; According to the correspondence between the spatial size range within which the environmental space size falls, the personnel distribution density interval range within which the personnel distribution density falls, and the preset distance range centered on the cardiopulmonary resuscitation machine, the preset distance range centered on the cardiopulmonary resuscitation machine is analyzed and determined.

4. The adaptive compression control system of a cardiopulmonary resuscitation machine according to claim 2, characterized in that: Acquisition of preset distance ranges centered on the CPR machine includes: Obtain the types of events where the cardiopulmonary resuscitation machine is used, including disaster scenes, traffic accident scenes, and other scenes; According to the correspondence between the event type of using the cardiopulmonary resuscitation machine and the preset distance range centered on the cardiopulmonary resuscitation machine, the preset distance range centered on the cardiopulmonary resuscitation machine is analyzed and determined.

5. The adaptive compression control system of a cardiopulmonary resuscitation machine according to claim 1, characterized in that: Identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated, including: Obtain the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine; If the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine is a direct connection, then identifying and obtaining real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated; If the connection relationship between the physiological index monitoring device and the cardiopulmonary resuscitation machine is to be connected, actively match the connection and identify and obtain the real-time physiological index related data transmitted by the physiological index monitoring device worn by the person to be resuscitated; If the connection relationship between the physiological indicator monitoring device and the cardiopulmonary resuscitation machine is that there is a direct connection or a pending connection at the same time, then obtain the real-time physiological indicator related data transmitted by the physiological indicator monitoring device that is directly connected or to be connected, and analyze whether the same physiological indicator comes from different physiological indicator monitoring devices and the corresponding physiological indicator data are different; If yes, then according to the preset confidences of different physiological indicator monitoring devices for different physiological indicator monitoring devices, analyze and determine the confidences of the same physiological indicator from different physiological indicator monitoring devices, and select the same physiological indicator data with the highest confidence as the corresponding physiological indicator data for this application; If not, keep the original setting.

6. The adaptive compression control system of a cardiopulmonary resuscitation machine according to claim 5, characterized in that: The confidence level of different physiological indicators obtained by the preset different physiological indicator monitoring devices includes: Obtain the current environment category information and environment parameter information. The environment category includes home environment and sports environment. The environment parameter information includes environment temperature, environment humidity and altitude information of the area. According to the corresponding relationship between the current environment category information, environmental parameter information, the category of physiological index monitoring equipment and the confidence of different physiological indexes, the confidence of different physiological index monitoring equipment about different physiological indexes is analyzed and determined.

7. An adaptive compression control system for a cardiopulmonary resuscitation machine according to any one of claims 1 to 6, characterized in that: The method also includes the following steps after controlling the cardiopulmonary resuscitation machine to make adjustments according to the output cardiopulmonary resuscitation machine adjustment information: Obtain the patient's subsequent physiological index related data; Extracting the patient's key physiological index-related data after a preset time interval based on the patient's subsequent physiological index-related data; According to the correspondence between the key physiological indicator data range and the resuscitation effect evaluation value within which the key physiological indicator related data of the patient falls after the preset time interval, the resuscitation effect evaluation value matched by different key physiological indicator related data is analyzed and determined, and the overall resuscitation evaluation value is calculated; If the overall resuscitation assessment value exceeds the preset resuscitation assessment threshold, the existing setting is maintained; If the overall resuscitation assessment value is less than or equal to the preset resuscitation assessment threshold, the patient's key physiological indicator data after the preset time interval is input into the trained model of the problem prediction confidence value, and the confidence value of the problem is output. The confidence value of the problem is converted through a preset probability estimation method to obtain the probability estimate of each possible problem, and the probability estimate of the possible problem is sent to the terminal held by the person in charge.

8. A computer storage medium, characterized in that: The invention comprises a program which, when loaded and executed by a processor, implements an adaptive compression control method in an adaptive compression control system of a cardiopulmonary resuscitation machine as claimed in any one of claims 1 to 7.

Images