Emergency rescue system and method for cardiovascular diseases

Abstract

The invention discloses an emergency rescue system and method for cardiovascular diseases, and relates to the technical field of emergency rescue for cardiovascular diseases, and the system comprises a collection and fusion module which is used for collecting physiological data of a patient in real time for fusion; the prediction module is used for constructing a convolutional neural network CNN model to predict the state of the patient in real time; the unmanned aerial vehicle rescue module is used for the unmanned aerial vehicle to carry out preliminary rescue according to the early warning, and first-aid personnel carry out rescue through AR glasses and VR guidance; and the storage module is used for storing the collected and analyzed physiological data. Patient physiological data are collected in real time and fused, a convolutional neural network CNN model is constructed to predict the state of the patient and early warn in real time, the unmanned aerial vehicle carries out preliminary rescue according to early warning, first-aid personnel carry out rescue through AR glasses and VR guidance, and real-time monitoring and early warning of the state of the patient with the cardiovascular disease are achieved. The response speed and the processing efficiency of cardiovascular emergencies are remarkably improved, and the timeliness and the effectiveness of rescue are improved.

Description

Technical Field

[0001] The present invention relates to the technical field of emergency rescue for cardiovascular diseases, and in particular to an emergency rescue system and method for cardiovascular diseases. Background Art

[0002] Cardiovascular disease is one of the leading causes of death and disability worldwide. With the aging of the global population and changes in lifestyle, the incidence of cardiovascular disease continues to rise. Existing technologies mainly rely on traditional hospital treatment and regular examinations to prevent and treat cardiovascular disease, but these methods are often unable to monitor the patient's status in real time, especially for immediate intervention when an acute event occurs in the patient. Traditional cardiovascular disease management strategies often ignore the possibility of remote and real-time monitoring, limiting the efficiency of early warning and treatment. Therefore, there is an urgent need to develop a cardiovascular disease emergency rescue system that can monitor in real time and respond quickly.

[0003] There are several deficiencies in the existing technology in the field of emergency treatment of cardiovascular diseases. The existing rescue systems mostly rely on the response of patients or bystanders after making an emergency call, which may result in the loss of precious treatment windows in terms of time. The existing systems are not mature enough in data fusion processing and fail to effectively utilize the complementary advantages of multi-source data, resulting in the need to improve the accuracy and stability of the early warning system. The rescue response methods are still relatively simple, and most of them still rely on traditional ground medical emergency resources, resulting in low rescue efficiency in remote or transportation-inconvenient areas. Summary of the invention

[0004] In view of the problems existing in the above-mentioned existing emergency rescue systems and methods for cardiovascular diseases, the present invention is proposed.

[0005] Therefore, the problem to be solved by the present invention is that the existing rescue systems mostly rely on the response of patients or bystanders after making an emergency call, which may result in the loss of precious treatment windows in terms of time. The existing systems are not mature enough in data fusion processing and fail to effectively utilize the complementary advantages of multi-source data, resulting in the accuracy and stability of the early warning system to be improved. The rescue response methods are still relatively simple and most of them still rely on traditional ground medical emergency resources, resulting in low rescue efficiency in remote or traffic-inconvenient areas.

[0006] To solve the above technical problems, the present invention provides the following technical solutions: an enterprise intelligent matching method based on big data, which includes: a collection and fusion module, which is used to collect patient physiological data in real time and fuse the collected physiological data; a prediction module, which is used to construct a convolutional neural network (CNN) model to predict patient status and early warning in real time; a drone rescue module, which is used for drones to perform initial rescue according to early warnings, and emergency personnel to perform rescue through AR glasses and VR guidance; a storage module, which is used to store and back up the collected and analyzed physiological data in the cloud.

[0007] As a preferred solution of the enterprise intelligent matching method based on big data described in the present invention, the real-time collection of patient physiological data refers to the patient wearing a smart wearable device, which integrates an electrocardiogram sensor, a heart rate sensor, a blood pressure sensor, a blood oxygen sensor, a GPS sensor and an RFID chip, and collects the patient's physiological data and location data in real time.

[0008] As a preferred solution of the enterprise intelligent matching method based on big data of the present invention, the fusion of the collected physiological data includes:

[0009] The collected physiological data were subjected to noise removal using a Kalman filter;

[0010] The denoised physiological data were smoothed using the moving average method;

[0011] Standardize the smoothed physiological data;

[0012] Calculate the time autocorrelation function ACF of the normalized physiological data, and take the maximum value of the autocorrelation function as the time correlation coefficient ρ i ;

[0013] Calculate the Pearson correlation coefficient for each pair of sensor position data, and take the maximum value of the Pearson correlation coefficient as the spatial correlation coefficient r i ;

[0014] According to the time correlation coefficient ρ i and spatial correlation coefficient r i , dynamically adjust the weight of sensor data;

[0015] The information entropy of temporal correlation and spatial correlation is calculated using the entropy weight method;

[0016] Based on the results calculated by the entropy weight method, the adjustment coefficients α and β are determined;

[0017] The physiological data are weightedly fused using dynamically adjusted weights to generate comprehensive physiological data.

[0018] The construction of the convolutional neural network (CNN) model to predict the patient's status in real time refers to collecting historical physiological data, preprocessing and fusing them to form historical comprehensive physiological data I′, and generating a training set;

[0019] Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer;

[0020] Define the input layer as comprehensive physiological data;

[0021] Use the training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0022] The comprehensive physiological data are input into the trained convolutional neural network (CNN) model to obtain the probability of cardiovascular disease events;

[0023] Based on historical cardiovascular disease events, the threshold is set at 40%. When the convolutional neural network CNN model detects that the probability of a cardiovascular disease event in real-time data is greater than or equal to the set threshold, the early warning mechanism is automatically triggered and medical staff and patients are notified.

[0024] The drone performs preliminary rescue according to the early warning, which means that according to the information sent by the early warning system, the doctor selects the emergency medicine according to the patient's physiological data and loads it on the drone with integrated high-definition camera, RFID reader and environmental sensor.

[0025] Sensor drones;

[0026] Set the patient position data as the attraction point and create the attraction potential U att , guide the drone to fly towards the patient; use high-definition cameras and environmental sensors to identify obstacles, set obstacles as repulsion points, and generate repulsion potential U rep ;

[0027] where k rey is the repulsion constant, D is the impact distance, and j is the distance from the drone to the nearest obstacle;

[0028] Use the potential field method to obtain the total potential field U of the UAV;

[0029] The initial flight path is derived from the total potential field using the gradient descent method;

[0030] Select the starting point, turning point and end point in the preliminary flight path as control points, and divide the path into segments between the two control points;

[0031] Generate a smooth curve B(c) for each segmented path using the Bezier curve formula;

[0032] The formula for the number of combinations is:

[0033] Connect the smooth curves of each segmented path to form a complete path as the final flight path of the drone;

[0034] When the drone reaches above the patient, it receives the RFID signal from the patient's wearable device through the RFID reader and high-definition camera to obtain the patient's precise location data to find the patient. If the drone cannot get close to the patient, it will immediately activate the emergency communication protocol to contact the emergency personnel, request assistance from nearby personnel through the speaker, and transmit the patient's precise location data and surrounding environment data to the emergency personnel;

[0035] If the drone approaches a patient, it will determine the patient's condition by asking the patient questions;

[0036] If the patient is awake, use a high-definition camera to determine whether the patient can move;

[0037] If the patient is awake and able to move, the first aid medicine will be accurately delivered to the patient through the delivery device, the patient's medication process will be monitored through the camera, and the 5G network technology will be used to transmit the patient's surrounding environment data after taking the medicine to the first aid personnel through the drone in real time;

[0038] If the patient is conscious but unable to move, use a loudspeaker to notify people around to help the patient take the medicine, and continue to notify until the patient takes the medicine;

[0039] If the patient is in a coma, the drone will sound an alarm, contact the patient's family by phone, transmit the patient's surrounding environment data, patient status and location information to emergency personnel, and maintain on-site monitoring until emergency personnel arrive.

[0040] As a preferred solution of the enterprise intelligent matching method based on big data described in the present invention, wherein: the first aid personnel use AR glasses and VR guidance to perform rescue operations, and construct an integrated AR and VR technology platform, using 5G network technology for real-time transmission;

[0041] Based on the patient's current physiological data and the environmental data transmitted by the drone, the doctor wears a VR helmet to perform virtual treatment and generate treatment steps and guidance information;

[0042] The doctor's treatment steps and guidance information are received in real time through the AR interface, and emergency personnel perform corresponding first aid operations according to the guidance information displayed in the AR glasses.

[0043] As a preferred solution of the enterprise intelligent matching method based on big data described in the present invention, wherein: the cloud storage and backup of the collected and analyzed data refers to storing the physiological data and patient treatment steps collected and analyzed in the cloud, marking the stored data, backing up the stored data regularly, and regularly performing security and integrity checks on the stored data and backup data and generating test reports.

[0044] Another object of the present invention is to provide an enterprise intelligent matching system based on big data, which comprises:

[0045] Collect patients' physiological data in real time and integrate the collected physiological data;

[0046] Construct a convolutional neural network (CNN) model to predict patient status and early warning in real time;

[0047] Drones conduct initial rescue based on early warnings, and emergency personnel conduct rescue operations through AR glasses and VR guidance;

[0048] The collected and analyzed physiological data are stored and backed up in the cloud.

[0049] A computer device comprises: a memory and a processor; the memory stores a computer program, and the processor implements the steps of the above-mentioned enterprise intelligent matching method based on big data when executing the computer program.

[0050] A computer-readable storage medium stores a computer program, which, when executed by a processor, implements the steps of the above-mentioned enterprise intelligent matching method based on big data.

[0051] The beneficial effects of the present invention are as follows: the present invention collects and integrates the patient's physiological data in real time, constructs a convolutional neural network (CNN) model to predict the patient's status and early warning in real time, the drone performs initial rescue according to the early warning, and emergency personnel perform rescue through AR glasses and VR guidance, thereby achieving real-time monitoring and early warning of the status of patients with cardiovascular disease, significantly improving the response speed and processing efficiency of cardiovascular emergencies, and improving the timeliness and effectiveness of rescue. BRIEF DESCRIPTION OF THE DRAWINGS

[0052] In order to more clearly illustrate the technical solutions of the embodiments of the present invention, the accompanying drawings required for use in the description of the embodiments will be briefly introduced below. Obviously, the accompanying drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other accompanying drawings can be obtained based on these accompanying drawings without paying creative work.

[0053] Figure 1 A schematic diagram of the structure of an emergency rescue system for cardiovascular diseases;

[0054] Figure 2 A schematic diagram of the structure of an emergency rescue system for cardiovascular diseases;

[0055] Figure 3 Schematic diagram of the flow chart of the emergency rescue system for cardiovascular diseases. DETAILED DESCRIPTION

[0056] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below in conjunction with the accompanying drawings.

[0057] In the following description, many specific details are set forth to facilitate a full understanding of the present invention, but the present invention may also be implemented in other ways different from those described herein, and those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0058] Secondly, the term "one embodiment" or "embodiment" as used herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The term "in one embodiment" that appears in different places in this specification does not necessarily refer to the same embodiment, nor is it a separate or selective embodiment that is mutually exclusive with other embodiments.

[0059] Example 1

[0060] Reference Figure 1 and Figure 3 , which is the first embodiment of the present invention, and which provides an emergency rescue system for cardiovascular diseases, the emergency rescue system for cardiovascular diseases comprising:

[0061] S1, a collection and fusion module, used to collect the patient's physiological data in real time and fuse the collected physiological data;

[0062] Specifically, real-time collection of patient physiological data refers to having the patient wear a smart wearable device, which integrates an electrocardiogram sensor, a heart rate sensor, a blood pressure sensor, a blood oxygen sensor, a GPS sensor and an RFID chip, and collects the patient's physiological data and location data in real time.

[0063] By real-time monitoring of physiological parameters such as heart rate, blood pressure and blood oxygen levels, the medical team can immediately detect any abnormal changes in the patient's health status, so that they can respond quickly and implement necessary treatment measures. Smart wearable devices can provide personalized health advice and warnings based on each patient's specific physiological data, making medical services more in line with the actual needs of individuals. The integration of GPS sensors allows patients even in remote areas to receive timely and effective medical responses, greatly enhancing the coverage of medical services, especially in public health emergencies. Continuous health monitoring enables doctors to track patients' long-term health status, detect possible health problems early, and intervene, which is particularly effective for chronic disease management.

[0064] Furthermore, the collected physiological data are integrated including:

[0065] The collected physiological data were subjected to noise removal using a Kalman filter;

[0066] The denoised physiological data were smoothed using the moving average method;

[0067] Standardize the smoothed physiological data;

[0068] Calculate the time autocorrelation function ACF of the normalized physiological data using the formula:

[0069]

[0070] where ρ(τ) is the autocorrelation coefficient of time lag τ, x t is the data at time t, is the average value of the data, and N is the total amount of data;

[0071] The maximum value in the autocorrelation function is taken as the time correlation coefficient ρ i ;

[0072] Calculate the Pearson correlation coefficient for each pair of sensor position data using the formula:

[0073]

[0074] Where r is the Pearson correlation coefficient, x i and i is the data of the sensor location, and is the average value of the data, and n is the number of data points;

[0075] The maximum value of the Pearson correlation coefficient is taken as the spatial correlation coefficient r i ;

[0076] According to the time correlation coefficient ρ i and spatial correlation coefficient r i , dynamically adjust the weight of sensor data, the formula is:

[0077] ω i (t) = α·ρ i (t)+β·r i ;

[0078] where ω i (t) is the weight of sensor i at time t, ρ i (t) is the time correlation coefficient, α and β are adjustment coefficients;

[0079] The information entropy of time correlation and space correlation is calculated using the entropy weight method. The formula is:

[0080]

[0081]

[0082] Among them, H j is the data entropy of temporal correlation and spatial correlation, o mjis the data value of the jth sensor at the mth time point, k is a constant, p mj is the data value of the jth sensor at the ith time point, and M is the total number of time periods;

[0083] Based on the results calculated by the entropy weight method, the adjustment coefficients α and β are determined as follows:

[0084]

[0085]

[0086] Among them, H time is the information entropy of time correlation, H space is the information entropy of spatial correlation;

[0087] Use the dynamically adjusted weights to perform weighted fusion on physiological data to generate comprehensive physiological data. The formula is:

[0088]

[0089] Where I(t) is the comprehensive physiological data at time t, p is the total number of sensors, and z i (t) is the data of sensor i at time t.

[0090] Using Kalman filter to remove noise in physiological data can significantly improve data quality and ensure the accuracy of subsequent analysis, which is particularly important for quickly identifying cardiovascular emergencies. Data smoothed by moving average method reduces the interference of short-term fluctuations, making trend analysis clearer and helping medical staff understand the long-term health changes of patients. Standardization ensures that data from different sensors can be compared under the same standards, which is very important for integrating different physiological parameters. By analyzing the time autocorrelation function, the system can identify repetitive patterns or periodic changes in physiological data, which is crucial for predicting cardiovascular events and formulating preventive measures. The calculation of Pearson correlation coefficient helps identify the correlation between different sensors, thereby providing more physiological data interpretation and more accurate health status assessment. Using entropy weight method to dynamically adjust the weight of sensor data, the proportion of each sensor in the comprehensive data can be adjusted according to its information contribution, thereby improving the accuracy and relevance of data fusion. Dynamically adjusted data weights and weighted fusion provide an effective way to synthesize and analyze multi-source medical data, improving the system's response speed and accuracy to complex physiological signals.

[0091] S2, prediction module, used to build a convolutional neural network (CNN) model to predict patient status and early warning in real time;

[0092] Specifically, constructing a convolutional neural network (CNN) model to predict patient status in real time refers to collecting historical physiological data, preprocessing and fusing them to form historical comprehensive physiological data I′, and generating a training set;

[0093] Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer;

[0094] Define the input layer as comprehensive physiological data;

[0095] Use the training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters;

[0096] The comprehensive physiological data are input into the trained convolutional neural network (CNN) model to obtain the probability of cardiovascular disease events;

[0097] Based on historical cardiovascular disease events, the threshold is set at 40%. When the convolutional neural network CNN model detects that the probability of a cardiovascular disease event in real-time data is greater than or equal to the set threshold, the early warning mechanism is automatically triggered and medical staff and patients are notified.

[0098] Through deep learning analysis of physiological data, CNN can identify early warning signs of cardiovascular disease and provide early warning, thereby increasing the success rate of treatment. The constructed CNN model can process comprehensive physiological data in real time, promptly detect any possible cardiovascular abnormalities, and automatically trigger the warning mechanism to ensure that patients receive a rapid response. The efficiency and accuracy of the CNN model help reduce medical misdiagnosis, especially in complex cases of cardiovascular disease. The model can provide more accurate diagnostic support. By analyzing historical and real-time data, the CNN model can not only predict cardiovascular events, but also help medical personnel optimize treatment plans based on the predicted results. Setting a threshold for the probability of cardiovascular events allows the model to dynamically adjust the warning criteria based on historical data, so that the warning system can be customized according to the specific circumstances of different patients.

[0099] S3, UAV rescue module, used for UAV to carry out preliminary rescue according to early warning, and emergency personnel to carry out rescue through AR glasses and VR guidance;

[0100] Specifically, drones conduct preliminary rescue based on early warnings, which means that according to the information sent by the early warning system, doctors select emergency medicines based on the patient's physiological data and load them on drones that integrate high-definition cameras, RFID readers, and environmental sensors;

[0101] Set the patient position data as the attraction point and create the attraction potential U att , guide the drone to fly towards the patient, the formula is:

[0102]

[0103] where k att is the attraction constant, d is the Euclidean distance from the current position of the UAV to the target position;

[0104] Use high-definition cameras and environmental sensors to identify obstacles, set obstacles as repulsion points, and generate repulsion potential U rep , the formula is:

[0105]

[0106] where k rey is the repulsion constant, D is the impact distance, and j is the distance from the drone to the nearest obstacle;

[0107] Use the potential field method to obtain the total potential field U of the drone. The formula is:

[0108] U=U att +U rep ;

[0109] The initial flight path is derived from the total potential field using the gradient descent method;

[0110] Select the starting point, turning point and end point in the preliminary flight path as control points, and divide the path into segments between the two control points;

[0111]

[0112] Where P v is the vth control point, c is the parameter of the Bezier curve, V is the total number of control points minus one, is the number of combinations for selecting the vth element from V elements. When calculating the points on the curve, each control point P v All through their corresponding combination number Weighted, indicating the contribution of this point to the curve shape under a given parameter c, (1-c) (V-v) and c v is the weight factor;

[0113] The formula for the number of combinations is:

[0114]

[0115] Among them! is the factorial;

[0116] Connect the smooth curves of each segmented path to form a complete path as the final flight path of the drone;

[0117] When the drone reaches above the patient, it receives the RFID signal from the patient's wearable device through the RFID reader and high-definition camera to obtain the patient's precise location data to find the patient. If the drone cannot get close to the patient, it will immediately activate the emergency communication protocol to contact the emergency personnel, request assistance from nearby personnel through the speaker, and transmit the patient's precise location data and surrounding environment data to the emergency personnel;

[0118] If the drone approaches a patient, it will determine the patient's condition by asking the patient questions;

[0119] If the patient is awake, use a high-definition camera to determine whether the patient can move;

[0120] If the patient is awake and able to move, the first aid medicine will be accurately delivered to the patient through the delivery device, the patient's medication process will be monitored through the camera, and the 5G network technology will be used to transmit the patient's surrounding environment data after taking the medicine to the first aid personnel through the drone in real time;

[0121] If the patient is conscious but unable to move, use a loudspeaker to notify people around to help the patient take the medicine, and continue to notify until the patient takes the medicine;

[0122] If the patient is in a coma, the drone will sound an alarm, contact the patient's family by phone, transmit the patient's surrounding environment data, patient status and location information to emergency personnel, and maintain on-site monitoring until emergency personnel arrive.

[0123] Based on the patient's real-time physiological data, doctors can choose the most suitable emergency medicine, ensuring the personalization and targeting of the rescue operation and improving the success rate of treatment. By creating attractive and repulsive potentials, the drone can automatically calculate the path to avoid obstacles and reach the patient's location as quickly as possible. This navigation strategy not only improves the autonomy of the drone in complex environments, but also reduces the operator's workload and increases the safety and accuracy of the rescue operation. By using Bezier curves, the flight path of the drone is optimized to a smooth curve, reducing sharp turns and sudden stops during flight, thereby reducing mechanical wear and improving flight efficiency. The drone delivers the medicine accurately and uses 5G technology to transmit environmental and physiological data after taking the medicine in real time, enabling the telemedicine team to instantly evaluate the effect of the drug and the patient's reaction. Through notifications on the loudspeaker, the surrounding personnel are mobilized to assist and ensure that the patient can get the necessary drug support in time. The drone issues an alarm and notifies the patient's family, while transmitting key data to the emergency personnel to ensure that the rescue team has a full understanding of the patient's condition before arriving at the scene. Before the emergency personnel arrive, the drone maintains on-site monitoring to ensure continuous monitoring of the patient's condition, which is crucial to preventing the patient's condition from deteriorating and providing continuous rescue information.

[0124] Furthermore, first responders use AR glasses and VR guidance to conduct rescue operations. It means building an integrated AR and VR technology platform and using 5G network technology for real-time transmission;

[0125] Based on the patient's current physiological data and the environmental data transmitted by the drone, the doctor wears a VR helmet to perform virtual treatment and generate treatment steps and guidance information;

[0126] The doctor's treatment steps and guidance information are received in real time through the AR interface, and emergency personnel perform corresponding first aid operations according to the guidance information displayed in the AR glasses.

[0127] This platform allows doctors to provide precise treatment guidance remotely, while enabling emergency personnel to obtain real-time, intuitive operating instructions through AR glasses. This integrated approach improves the accuracy and real-time nature of medical guidance, especially in emergency situations, which can significantly improve processing speed and treatment effectiveness. Doctors can use VR helmets to analyze patient conditions more deeply and design more appropriate treatment steps. This immersive experience allows doctors to eliminate external interference and concentrate on developing the best treatment plan. It also provides doctors with a new way to deal with complex or rare medical situations. Through AR glasses, emergency personnel can instantly receive guidance information and operating steps from doctors, reducing the possibility of operational errors and improving the accuracy and efficiency of treatment. The application of AR technology can also reduce education and training costs, and novice emergency personnel can also quickly get started and provide effective treatment.

[0128] S4, storage module, used for cloud storage and backup of collected and analyzed physiological data;

[0129] Specifically, cloud storage and backing up of collected and analyzed data means storing the physiological data and patient treatment steps collected and analyzed in the cloud, marking the stored data, backing up the stored data regularly, and regularly testing the security and integrity of the stored data and backup data and generating test reports.

[0130] By storing data in the cloud, the medical team can access this data in real time from any location, whether for remote diagnosis or emergency medical response. This improves the flexibility and responsiveness of medical services. By backing up data at different locations, the present invention significantly reduces the risk of data loss. In the event of a data center failure, natural disaster or other form of data damage, data can be quickly restored to ensure the continuity of medical services. The security and integrity of data are regularly checked to ensure the confidentiality, availability and consistency of data. By generating security detection reports, medical institutions can promptly detect potential security threats and vulnerabilities and take timely measures to respond. Marking stored data not only facilitates data management, but also enhances data traceability, which is particularly important for complying with strict privacy and data protection regulations in the medical industry, such as GDPR or HIPAA.

[0131] Example 2

[0132] Reference Figure 2 , which is the second embodiment of the present invention, is different from the previous embodiment and provides an emergency rescue method for cardiovascular disease, comprising:

[0133] Collect patients' physiological data in real time and integrate the collected physiological data;

[0134] Construct a convolutional neural network (CNN) model to predict patient status and early warning in real time;

[0135] Drones conduct initial rescue based on early warnings, and emergency personnel conduct rescue operations through AR glasses and VR guidance;

[0136] The collected and analyzed physiological data are stored and backed up in the cloud.

[0137] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0138] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0139] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0140] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following technologies known in the art or a combination thereof can be used to implement: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

Claims

1. An emergency rescue system for cardiovascular disease, characterized in that: include: A collection and fusion module is used to collect the patient's physiological data in real time and fuse the collected physiological data; The prediction module is used to build a convolutional neural network (CNN) model to predict patient status and early warning in real time; The drone rescue module is used for drones to conduct preliminary rescue according to early warnings, and emergency personnel conduct rescue through AR glasses and VR guidance; The storage module is used to store and back up the collected and analyzed physiological data in the cloud.

2. The emergency rescue system for cardiovascular disease according to claim 1, characterized in that: The real-time collection of patient physiological data refers to the patient wearing a smart wearable device, which integrates an electrocardiogram sensor, a heart rate sensor, a blood pressure sensor, a blood oxygen sensor, a GPS sensor and an RFID chip, and collects the patient's physiological data and location data in real time.

3. The emergency rescue system for cardiovascular disease according to claim 2, characterized in that: The fusing of the collected physiological data includes: The collected physiological data were subjected to noise removal using a Kalman filter; The denoised physiological data were smoothed using the moving average method; Standardize the smoothed physiological data; Calculate the time autocorrelation function ACF of the normalized physiological data, and take the maximum value of the autocorrelation function as the time correlation coefficient ρ i ; Calculate the Pearson correlation coefficient for each pair of sensor position data, and take the maximum value of the Pearson correlation coefficient as the spatial correlation coefficient r i ; According to the time correlation coefficient ρ i and spatial correlation coefficient r i , dynamically adjust the weight of sensor data; The information entropy of temporal correlation and spatial correlation is calculated using the entropy weight method; Based on the results calculated by the entropy weight method, the adjustment coefficients α and β are determined; The physiological data are weightedly fused using dynamically adjusted weights to generate comprehensive physiological data.

4. The emergency rescue system for cardiovascular disease according to claim 3, characterized in that: The construction of the convolutional neural network (CNN) model to predict the patient's status in real time refers to collecting historical physiological data, preprocessing and fusing them to form historical comprehensive physiological data I′, and generating a training set; Construct a convolutional neural network (CNN) model, including input layer, convolution layer, pooling layer, and fully connected output layer; Define the input layer as comprehensive physiological data; Use the training set to train the convolutional neural network (CNN) model, and use the loss function and Adam optimizer to iteratively optimize the model parameters; The comprehensive physiological data are input into the trained convolutional neural network (CNN) model to obtain the probability of cardiovascular disease events; Based on historical cardiovascular disease events, the threshold is set at 40%. When the convolutional neural network CNN model detects that the probability of a cardiovascular disease event in real-time data is greater than or equal to the set threshold, the early warning mechanism is automatically triggered and medical staff and patients are notified.

5. The emergency rescue system for cardiovascular disease according to claim 4, characterized in that: The drone performs preliminary rescue according to the early warning, which means that according to the information sent by the early warning system, the doctor selects emergency medicines according to the patient's physiological data and loads them on the drone with integrated high-definition camera, RFID reader and environmental sensor; Set the patient position data as the attraction point and create the attraction potential U att , guiding the drone to fly in the direction of the patient; Use high-definition cameras and environmental sensors to identify obstacles, set obstacles as repulsion points, and generate repulsion potential U rep ; where k rey is the repulsion constant, D is the impact distance, and j is the distance from the drone to the nearest obstacle; Use the potential field method to obtain the total potential field U of the UAV; The initial flight path is derived from the total potential field using the gradient descent method; Select the starting point, turning point and end point in the preliminary flight path as control points, and divide the path into segments between the two control points; Generate a smooth curve B(c) for each segmented path using the Bezier curve formula; The formula for the number of combinations is; Connect the smooth curves of each segmented path to form a complete path as the final flight path of the drone; When the drone reaches above the patient, it receives the RFID signal from the patient's wearable device through the RFID reader and high-definition camera to obtain the patient's precise location data to find the patient. If the drone cannot get close to the patient, it will immediately activate the emergency communication protocol to contact the emergency personnel, request assistance from nearby personnel through the speaker, and transmit the patient's precise location data and surrounding environment data to the emergency personnel; If the drone approaches a patient, it will determine the patient's condition by asking the patient questions: If the patient is awake, use a high-definition camera to determine whether the patient can move: If the patient is awake and able to move, the first aid medicine will be accurately delivered to the patient through the delivery device, the patient's medication process will be monitored through the camera, and the 5G network technology will be used to transmit the patient's surrounding environment data after taking the medicine to the first aid personnel through the drone in real time; If the patient is conscious but unable to move, use a loudspeaker to notify people around to help the patient take the medicine, and continue to notify until the patient takes the medicine; If the patient is in a coma, the drone will sound an alarm, contact the patient's family by phone, transmit the patient's surrounding environment data, patient status and location information to emergency personnel, and maintain on-site monitoring until emergency personnel arrive.

6. The emergency rescue system for cardiovascular disease according to claim 5, characterized in that: The rescue work of first responders through AR glasses and VR guidance refers to the construction of an integrated AR and VR technology platform, using 5G network technology for real-time transmission; Based on the patient's current physiological data and the environmental data transmitted by the drone, the doctor wears a VR helmet to perform virtual treatment and generate treatment steps and guidance information; The doctor's treatment steps and guidance information are received in real time through the AR interface, and emergency personnel perform corresponding first aid operations according to the guidance information displayed in the AR glasses.

7. The emergency rescue system for cardiovascular disease according to claim 6, characterized in that: The cloud storage and backing up of the collected and analyzed data refers to storing the physiological data and patient treatment steps collected and analyzed in the cloud, marking the stored data, regularly backing up the stored data, and regularly performing security and integrity checks on the stored data and backup data and generating test reports.

8. An emergency rescue method for cardiovascular disease based on the emergency rescue system for cardiovascular disease according to any one of claims 1 to 7, characterized in that: include: Collect patients' physiological data in real time and integrate the collected physiological data; Construct a convolutional neural network (CNN) model to predict patient status and early warning in real time; Drones conduct initial rescue based on early warnings, and emergency personnel conduct rescue operations through AR glasses and VR guidance; The collected and analyzed physiological data are stored and backed up in the cloud.

9. A computer device comprising: A memory and a processor; the memory stores a computer program, characterized in that: when the processor executes the computer program, the steps of the enterprise intelligent matching method based on big data described in any one of claims 1 to 7 are implemented.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the steps of the enterprise intelligent matching method based on big data described in any one of claims 1 to 7 are implemented.

Images