Intelligent method and system for quickly getting AED to emergency scene, device, and medium

Abstract

The present application discloses an intelligent method and system for quickly getting an AED to an emergency scene, a device, and a medium. The method comprises: acquiring distress call information of an emergency event and the geographical location of an emergency scene; performing first AED search range calculation, second AED search range calculation and third AED search range calculation; and AED delivery personnel getting an available AED from an available AED location corresponding to the fastest AED access plan and delivering the AED to the emergency scene. The system comprises an emergency mobile terminal, an intelligent AED device and an emergency cloud platform. The use of the plan in the present application can provide a good solution for passersby to participate in cardiac arrest first aid, accurately, scientifically and effectively allowing passersby to participate in cardiac arrest first aid; moreover, the possibility of passersby responding can gradually increase with the popularization and application of AEDs, providing another boost for patients to receive timely medical treatment, thereby further ensuring the life safety and health protection of patients.

Description

Intelligent and rapid method, system, device and medium for obtaining AED arrival at emergency scene

[0001] This application claims priority to the Chinese patent application filed with the China Patent Office on October 25, 2023, with application number 202311389063.6 and invention name “Intelligent and rapid acquisition of AED arrival at the emergency scene method and system, device, and medium”, the entire contents of which are incorporated by reference into this application. Technical Field

[0002] The present application relates to the field of cardiopulmonary resuscitation technology, and in particular to an intelligent method, system, device, and medium for quickly acquiring an AED to arrive at the emergency scene. Background Art

[0003] The statements in this section merely provide background technical information related to this application and do not necessarily constitute prior art.

[0004] In the early stages of cardiac arrest, 85% to 90% of patients experience ventricular fibrillation. The most effective treatment for ventricular fibrillation is early defibrillation with an AED (Automated External Defibrillator). Defibrillation is most effective within 3-5 minutes of onset. For every minute of delay, survival decreases by 7% to 10%. Approximately 540,000 people die from cardiac arrest in my country each year. Placing AEDs in public places is a crucial measure to reduce sudden death from cardiac arrest. External defibrillation with an AED is a crucial step in CPR (Cardio Pulmonary Resuscitation). The person using an AED is called the AED CPR performer (hereinafter referred to as the performer), and the person receiving external defibrillation with an AED is called the AED CPR recipient (hereinafter referred to as the patient).

[0005] Currently, AEDs are widely used outside of hospitals in high-traffic public spaces to provide timely assistance to patients suffering from sudden cardiac arrest. When an emergency occurs, an AED must be quickly obtained and delivered to the scene. The longer it takes for an AED to arrive, the lower the patient's survival rate. However, the speed with which an AED can be quickly retrieved and delivered to the emergency scene remains inefficient. Most current solutions focus on locating, properly deploying, and distributing AEDs, but none offer a solution for rapidly obtaining an AED. Furthermore, existing AED delivery solutions often rely on the cooperation of rescue volunteers equipped with rescue volunteer terminals. Rescuers or rescue volunteers must first travel to the target AED location to retrieve the AED and then return to the emergency scene. When the rescuer or rescue volunteer is too far from the target AED, the time required for both travel and return exceeds the optimal rescue time, slowing down the rescue process and hindering patient survival.

[0006] In view of this, how to obtain a plan for AED to arrive at the scene as quickly as possible after an emergency incident occurs, achieve the most efficient response time, and thus improve the patient's treatment speed and survival rate, has become the topic to be studied and solved in this application.

[0007] Summary of the Invention

[0008] The purpose of this application is to provide an intelligent and rapid method, system, device, and medium for obtaining an AED to arrive at the emergency scene, so that after an emergency event occurs, the AED can be obtained at the scene as quickly as possible to achieve the most efficient response time, thereby improving the patient's treatment speed and survival rate.

[0009] To achieve the above objectives, the first aspect of the present application proposes an intelligent method for quickly obtaining an AED to arrive at the emergency scene, the method comprising:

[0010] Obtain emergency call information and the geographic location of the emergency scene, and search for available AEDs near the emergency scene;

[0011] AED search first range calculation, search for the available AED closest to the emergency incident and lock the available AED, calculate the best path and time for the rescuer to pick up and deliver the AED, and output the AED delivery time A;

[0012] AED search second range calculation, searching for the available AED closest to the emergency incident and locking it, calculating the optimal path and time required for volunteers or AED managers nearby to obtain the AED and deliver it to the emergency scene, and outputting the AED delivery time B;

[0013] AED search third range calculation: Search for available AEDs near the emergency incident with pedestrian traffic. Calculate the final response probability of pedestrians based on the pedestrian traffic data obtained in the previous time period near the available AED and the average pedestrian response probability. Calculate the optimal path and time required for pedestrians near the available AED to finally respond and deliver the AED to the emergency scene after acquiring the AED, and output the AED delivery time C.

[0014] If the final response probability is greater than the response setting index, the arrival plan with the shortest duration among AED delivery time A, AED delivery time B, and AED delivery time C is output as the fastest AED arrival plan; if the final response probability is less than the response setting index, the arrival plan with the shortest duration among AED delivery time A and AED delivery time B is output as the fastest AED arrival plan;

[0015] The rescuer, callable volunteer, AED manager or responding passerby corresponding to the fastest AED arrival plan is defined as the AED delivery executor, and the optimal path and time consumption information corresponding to the fastest AED arrival plan is displayed to the AED delivery executor. The AED delivery executor obtains the available AED from the available AED corresponding to the fastest AED arrival plan and delivers the AED to the emergency scene.

[0016] The second aspect of the present application proposes an intelligent system for quickly obtaining an AED at the emergency scene, which is used in the method described in the first aspect. The system includes an emergency mobile terminal, an intelligent AED device, and an emergency cloud platform.

[0017] The first aid mobile terminal is a device for sending emergency call information and the geographical location of the first aid scene, and receiving the optimal path and time information corresponding to the fastest AED arrival plan; the first aid mobile terminal communicates with the first aid cloud platform via long-distance wireless communication;

[0018] The intelligent AED device is a device for performing external defibrillation. The intelligent AED device includes an alarm module, a video display module, and a video acquisition module. The alarm module is configured to at least generate an alarm upon receiving a message that uses the AED delivery time C as the fastest AED arrival plan, so that passers-by near the available AED can respond to the emergency call in a timely manner; the video display module is configured to display the optimal path and time information corresponding to the fastest AED arrival plan; and the video acquisition module is configured to capture video images near the intelligent AED.

[0019] The first aid cloud platform communicates with the first aid mobile terminal and the intelligent AED device through a long-distance wireless method. The first aid cloud platform is used to receive the distress call information of the first aid event sent by the first aid mobile terminal, perform AED search first range calculation, AED search second range calculation, AED search third range calculation, output the fastest AED arrival plan, and display the optimal path and time consumption information corresponding to the fastest AED arrival plan to the AED delivery executor via the first aid mobile terminal or the intelligent AED device.

[0020] A third aspect of the present application provides an intelligent AED device for use in the method described in the first aspect, wherein the intelligent AED device includes a main control module, a video acquisition module, a power supply module, a communication module, a storage module, a video display module, and an alarm module;

[0021] The main control module is used for information collection, storage, analysis and decision-making;

[0022] The video acquisition module is used to collect video images near the intelligent AED;

[0023] The power supply module is used to supply power to other modules;

[0024] The storage module is used to store AED operation information, video image information, and detection information;

[0025] The communication module is responsible for communicating with the emergency cloud platform;

[0026] The video display module is used to display the optimal path and time-consuming information corresponding to the fastest AED arrival plan;

[0027] The alarm module is used to issue an alarm when receiving a plan that adopts the AED delivery time C as the fastest AED arrival plan.

[0028] The fourth aspect of the present application proposes a readable storage medium having a control program stored thereon. When the control program is executed by a processor, the processor executes the steps of the method for intelligently and quickly acquiring an AED to arrive at the emergency scene as described in the first aspect.

[0029] The relevant contents of this application are explained as follows:

[0030] 1. Through the implementation of the above technical solutions of the present application, after obtaining the distress call information of the emergency incident, the AED search first range calculation, the AED search second range calculation, and the AED search third range calculation are performed, and the plan for delivering the AED in the fastest time is output to the corresponding rescuer, callable volunteer, AED manager or responding passerby. Compared with the existing AED distribution plan that can only rely on volunteers and AED managers to distribute AEDs, the present application specifically uses passersby near the available AED as AED delivery executors to obtain the AED to the emergency scene. This is because the cardiac arrest patient occurs suddenly and the geographical location of the emergency scene is irregular. The time it takes for the rescuer, callable volunteer or AED manager who is closer to the available AED to deliver the available AED may be relatively long. At this time, the AED search third range calculation is performed, and the final response probability of the passerby is calculated based on the pedestrian flow data of the previous time period near the available AED and the average response probability of the passerby. The final response probability of the passerby near the available AED is measured after the AED is obtained. D is the best path and time for delivering the AED to the emergency scene, and when the final response probability is greater than the response setting index, the arrival plan with the shortest time output in the AED search first range, AED search second range, and AED search third range is output as the fastest AED arrival plan. Since the best path and time for delivering the AED to the emergency scene after the passerby finally responds and obtains the AED in the AED search third range are usually shorter than those in the AED search first range and AED search second range, it can provide the most efficient way to quickly obtain the AED to arrive at the scene in the emergency scenario, achieve the most efficient response time, and provide an intelligent computing solution for cardiac arrest patients to be defibrillated as soon as possible after ventricular fibrillation occurs, thereby improving the patient's treatment speed and survival rate; and with the popularization of AED and first aid knowledge, there will be more and more passers-by who have received AED knowledge, and the final response probability of passers-by will also be higher and higher. After adopting the solution of this application, it will be able to provide a good solution for passers-by to participate in cardiac arrest first aid, accurately, scientifically and effectively allow passers-by to participate in cardiac arrest first aid, and provide another help for patients to receive timely treatment.

[0031] 2. In the first aspect of the above technical solution, the rescuer initiates a one-click rescue on the emergency mobile terminal. After the emergency cloud platform obtains the distress call information and the geographical location of the incident, the emergency cloud platform calculates the available AED closest to the emergency scene and the available AED with a high level of traffic near the emergency incident. An available AED is defined as an AED in normal condition.

[0032] The emergency cloud platform performs the first, second, and third range calculations for AED searches. The emergency cloud platform outputs the fastest AED arrival plan to the AED delivery executor, and also transmits the optimal path and time information corresponding to the fastest AED arrival plan, and the AED delivery executor information to the emergency mobile terminal.

[0033] The rescuer can send a distress call on the mobile emergency terminal and obtain the fastest AED arrival plan, which allows the rescuer to know the distance and time for the AED to arrive at the emergency scene in real time. This will enable the rescuer to better understand the relevant situation when performing CPR on the scene, thereby providing assistance for taking better CPR and improving the patient's survival rate.

[0034] 3. In the first aspect of the above technical solution, for the calculation of the optimal path and the time consumption in the steps of calculating the AED search first range, calculating the AED search second range, and calculating the AED search third range, a graph search path algorithm is used to obtain the optimal path;

[0035] In the step of calculating the AED search first range, AED delivery time A = (outbound optimal path + return optimal path) / average speed;

[0036] In the step of calculating the AED search second range, AED arrival time B = (optimal path from the available volunteer or AED manager to the AED + optimal path from the AED to the emergency scene) / average speed;

[0037] In the step of calculating the AED search third range, the AED arrival time C = the optimal path from the AED to the emergency scene / the average speed.

[0038] In this way, after obtaining the distress call information of an emergency incident, the fastest plan to get the AED can be calculated as quickly as possible, allowing patients to receive AED defibrillation treatment faster and more promptly.

[0039] 4. In the first aspect of the above technical solution, the following steps are adopted to obtain the optimal path:

[0040] Convert the grid path into a weighted graph;

[0041] Create a distance matrix between the node and the starting point based on the weighted graph, set the value of the starting point to 0, and set the remaining elements to infinity;

[0042] Create the parent node matrix of the node and initialize it to 0, indicating that there is no parent node;

[0043] Find the node with the lowest total evaluation cost among the untraversed nodes in the distance matrix and set it as the current node; set the distance of the current node to infinity and mark it as completed traversal; determine the untraversed nodes among all adjacent nodes of the current node to determine whether the adjacent node's authorized distance is greater than the edge weight of the current node to the next node. If so, update it to the current node;

[0044] Repeat the above steps until the current node is the target point;

[0045] The parent node backtracking is completed according to the parent node matrix to obtain the best path.

[0046] This optimal path acquisition method has the advantages of wide applicability, high efficiency, and the ability to quickly find the optimal solution, which can further improve the path planning and resource allocation capabilities in emergency incidents.

[0047] 5. In the first aspect of the above technical solution, after the arrival plan in the AED search third range is output as the fastest AED arrival plan, the fastest AED arrival plan is sent to the available AED and the available AED issues an alarm, and passers-by near the available AED quickly respond to pick up the AED and send it to the emergency scene according to the navigation information of the optimal path on the AED screen; if the passers-by near the available AED that issues the alarm do not respond to obtain the AED within time N, the arrival plan with the shortest time between AED delivery time A and AED delivery time B is re-output as the fastest AED arrival plan, where the sum of time N plus AED delivery time C is greater than AED delivery time A and AED delivery time B.

[0048] Through the implementation of the above method, it is ensured that when no passers-by respond after the AED searches the third range as the fastest AED arrival plan, the arrival plan with the shortest time between AED delivery time A and AED delivery time B can be promptly converted to output as the fastest AED arrival plan, thereby providing further guarantee for the delivery of the AED, allowing the patient to receive AED defibrillation treatment and avoiding the occurrence of accidents.

[0049] 6. In the first aspect of the above technical solution, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal. The emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographic location of the emergency incident and locks the available AED. It also calculates the optimal path and time for the rescuer to retrieve and deliver the AED. When the AED delivery time A within the first search range is calculated to be the shortest, the emergency cloud platform sends the AED's geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the rescuer's mobile terminal. The rescuer then goes to retrieve the AED and arrives at the emergency scene. This solution, which uses the AED search first range, is the fastest AED arrival solution, allowing the rescuer to quickly know the location and route of available AEDs and obtain the available AEDs as quickly as possible, so that the patient receives AED defibrillation treatment in the most effective time.

[0050] 7. In the first aspect of the above technical solution, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal, and the emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographical location of the emergency incident, searches for callable volunteers and AED managers near the available AED, and when it is calculated that the AED delivery time B in the second search range is the shortest, sends an event request to the mobile terminal of the callable volunteer or AED manager and locks the available AED at the same time. The callable volunteer or AED manager receives the emergency incident on the mobile terminal and processes it, calculates the best path and time for the person to obtain the AED and deliver the AED to the emergency scene, and when the callable volunteer or AED manager goes to pick up the AED and arrives at the emergency scene, the emergency cloud platform sends the AED geographical location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal. This is a solution that uses the second range of AED search to provide the fastest AED arrival solution. It allows callable volunteers or AED managers to quickly learn of the occurrence of an emergency incident, the location and route of an available AED, and to obtain the available AED as quickly as possible, so that the patient can receive AED defibrillation treatment in the most effective time.

[0051] 8. In the first aspect of the above technical solution, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal, and the emergency cloud platform obtains the on-site location and specific conditions, and searches for an available AED with the most traffic near the emergency incident. When the AED delivery time C in the third search range is calculated to be the shortest, the available AED emits a sound or light alarm, and sends the emergency incident location navigation and specific event description information to the available AED. The available AED screen presents the event request. After a passerby near the available AED notices the alarm of the available AED, he opens the AED outer box to obtain the AED and processes the emergency incident request. After the AED autonomously alarms, the best path and time for the passerby to obtain the AED and be sent to the scene are calculated. The passerby navigates to the emergency scene according to the device information prompts. At the same time, the emergency cloud platform sends the AED's geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal. This solution, which uses the third range of AED search, is the fastest solution for AED arrival. It allows passers-by to quickly know the occurrence of an emergency incident, the location and route of an available AED, and obtain the available AED as quickly as possible, so that the patient can receive AED defibrillation treatment in the most effective time.

[0052] 9. In the first aspect of the above technical solution, in the step of calculating the AED search third range, the following steps are used to obtain the data of the flow of people:

[0053] Collecting images and videos of the vicinity of an available AED in the period preceding the moment the emergency information is obtained;

[0054] Perform motion extraction on spatial object information collected from images and videos to estimate the flow of people near available AEDs;

[0055] The crowd flow density is characterized and the obtained crowd flow probability density distribution is used as the crowd flow data.

[0056] By acquiring the above-mentioned data on the flow of people, it is possible to obtain effective data on the flow of people near the available AED in the previous period before the moment of obtaining the emergency information, thereby enabling faster calculation and output of the fastest plan for AED arrival.

[0057] 10. In the first aspect of the above technical solution, in the step of calculating the third range for searching for an AED, the time period of the previous period is set to be within 10 to 20 minutes before the moment of receiving the emergency information near the available AED;

[0058] The response setting index was set at 95%;

[0059] The image video is captured by a camera on an available AED;

[0060] Final response probability = pedestrian flow data Y * average passerby response probability Z;

[0061] When Y*Z>95% and the AED delivery time C is less than the AED delivery time A and the AED delivery time B, the arrival plan calculated by the AED search third range is output as the fastest AED arrival plan.

[0062] By adopting the above steps and related parameter settings, it can be ensured that the information collected in the AED search third range calculation step is sufficient to calculate the final response probability, and that the final response probability is obtained reasonably and effectively. Therefore, when the arrival plan calculated by the AED search third range is output as the fastest AED arrival plan, it can be ensured that passers-by respond in time, obtain the AED in time, and deliver the AED to the first aid site in time.

[0063] 11. In the first aspect of the above technical solution, in the step of calculating the third AED search range, the process of calculating the final pedestrian response probability based on pedestrian flow data obtained in the previous time period near the available AED and the average pedestrian response probability is as follows:

[0064] Collecting images and videos of the vicinity of an available AED in the period preceding the moment the emergency information is obtained;

[0065] Establish a staggered local grid near the available AED; pre-construct a crowd density distribution matrix to represent the distribution information of crowd flow in the uniform local grid;

[0066] Use image filtering methods to extract motion from spatial object information collected from images and videos, and extract spatial crowd flow information;

[0067] The extracted spatial crowd flow information is projected onto a local grid in plane coordinates using the image space projection method. The plane projection representation is used to represent the probability density distribution of crowd flow on each grid in the local grid, which is used as the crowd flow data.

[0068] The final response probability of the AED is calculated by the Poisson distribution of the flow probability on the local grid under the plane coordinates.

[0069] 12. In the first aspect of the above technical solution, the following steps are used to extract motion from spatial object information collected from images and videos using an image filtering method:

[0070] For the acquired images and videos near the available AED, a background image without human traffic is reconstructed based on the pixel points with slow pixel value changes on the time axis of the image and video, and the background model is updated in real time: in the detection of human traffic, the original background pixel value is retained for the pixel points judged to belong to human traffic and is not updated; for the points judged to belong to the background, the background model is updated according to the following rules: B n+1 (i,j)=αB n (i,j)+(1-α)G(i,j);

[0071] Where α∈(0,1) is the update rate, B n (i, j) represents the pixel value of the background image pixel, G(i, j) represents the pixel value of the pixel in the current frame;

[0072] For continuous video images, continuous Gaussian distribution difference extraction is performed on the nth image to filter the background noise and obtain the background image B;

[0073] The HIS space of the color image is used as the basic space for image difference, and the image video is differentiated. The image obtained after the difference is binarized to detect the crowd flow, thereby extracting the spatial crowd flow information.

[0074] By implementing the above-mentioned process of using image filtering methods to extract motion from spatial object information collected by image videos, for video images shot by cameras in the same direction, since the pixel values ​​of background pixels change relatively slowly, while the pixel values ​​of pixels corresponding to moving targets change relatively quickly, a video image sequence collected over a period of time can be used to reconstruct a background image without crowds based on the pixel values ​​of pixels that change slowly on the time axis. At the same time, the background model can be adaptive to changes in external light, and can also combat background noise caused by the slow rotation of the camera in the same direction, thereby obtaining more accurate data on the flow of people.

[0075] 13. In the first aspect of the above technical solution, for pre-constructing the crowd density distribution matrix to represent the distribution information of the crowd in the uniform local grid, the crowd density distribution matrix X is pre-constructed.

[0076] Each element X in the matrix X ij A numerical representation of the density distribution of people flow recorded in the local grid;

[0077] Use the directional projection transformation matrix H to project each calculated image pixel to obtain the crowd flow density for plane projection. The directional projection transformation matrix H is:

[0078] Where θ is the rotation angle of the matrix image pixel, h2 and h5 are the translation amounts of the entire image;

[0079] Projection transformation is used to uniformly transform the image data into a plane representation at the same angle to represent the crowd density distribution, X = H*(GB);

[0080] Assume that the probability of each passerby responding to the AED is the same and equal to Z. The final response probability of the passerby is calculated using the Poisson distribution: Where k represents the number of times the event occurs, and λ represents the probability response coefficient under the crowd flow distribution;

[0081] For the probability response coefficient λ under the crowd distribution, since the expectation of the pine and cypress distribution is directly related to the crowd density distribution matrix X, that is, Po(λ)=E(X)*Z, the value is obtained by looking up the table.

[0082] Through the above calculation of the final response probability of passers-by, the calculation process is scientific and reasonable, and the obtained information is effectively used for rapid measurement, thereby providing assistance for the reliability and accuracy of passers-by responding to the AED in the calculation of the AED search third range, and trying to avoid the situation where passers-by do not respond after the AED delivery time C in the AED search third range is used as the fastest AED arrival plan.

[0083] 14. In the technical solution of the present application, the duration requirements for AED delivery time A, AED delivery time B, and AED delivery time C are to be less than 3 minutes. If they are all greater than 3 minutes, that is, the AED cannot arrive at the emergency scene within 3 minutes, the system can inform the rescuer that the AED cannot be obtained, please call 120 immediately (or the emergency cloud platform directly contacts 120 at the same time as the emergency information is sent, and the relevant information is sent to 120) and perform CPR at the same time.

[0084] Due to the application of the above scheme, this application has the following advantages and effects compared with the prior art:

[0085] 1. Through the implementation of the technical solution of the present application, by performing AED search first range calculation, AED search second range calculation, and AED search third range calculation after obtaining the distress call information of the emergency event, the AED delivery plan will be output to the corresponding rescuer, callable volunteer, AED manager or responding passerby in the fastest time, so that the AED can be delivered to the emergency scene as quickly as possible.

[0086] 2. Through the implementation of the technical solution of the present application, compared with the existing AED distribution solution which can only rely on volunteers and AED managers to distribute AEDs, the present application specifically includes passers-by near the available AED as AED delivery executors for obtaining the AED to arrive at the first aid site. This is because the cardiac arrest patient occurs suddenly and the geographical location of the first aid site is irregular. It may take a long time for the rescuer, callable volunteers or AED managers who are closer to the available AED to deliver the available AED. At this time, the AED searches the third range for calculation, calculates the final response probability of passers-by based on the pedestrian flow data of the previous time period near the available AED and the average response probability of passers-by, and measures the final response probability of passers-by near the available AED. The optimal path and time for delivering the AED to the emergency scene after the passerby finally responds and obtains the AED in the AED search third range, and when the final response probability is greater than the response setting index, the arrival plan with the shortest time output in the AED search first range, AED search second range, and AED search third range is output as the AED fastest arrival plan. Since the optimal path and time for delivering the AED to the emergency scene after the passerby finally responds and obtains the AED in the AED search third range are usually shorter than those in the AED search first range and AED search second range, it can provide the most efficient way to quickly obtain the AED to arrive at the scene in the emergency scenario, achieve the most efficient response time, and provide an intelligent computing solution for cardiac arrest patients to be defibrillated as early as possible in the most effective time after ventricular fibrillation occurs, thereby improving the patient's treatment speed and survival rate.

[0087] 3. In summary, the adoption of the solution of this application will be able to provide a good solution for passers-by to participate in cardiac arrest first aid, accurately, scientifically and effectively allowing passers-by to participate in cardiac arrest first aid, and with the promotion and application of AED, the possibility of passers-by responding will gradually increase, providing another boost for patients to receive timely treatment, thereby further ensuring the patient's life safety and health protection. BRIEF DESCRIPTION OF THE DRAWINGS

[0088] FIG1 is a flow chart of a method for intelligently and quickly obtaining an AED at an emergency scene according to an embodiment of the present application;

[0089] FIG2 is a schematic diagram of a flow chart of calculation for performing AED search within a first range in the method according to an embodiment of the present application;

[0090] FIG3 is a schematic diagram of a scenario in which the AED search first range calculation is performed in the method according to an embodiment of the present application;

[0091] FIG4 is a schematic diagram of a flow chart of calculation for performing AED search in a second range in the method according to an embodiment of the present application;

[0092] FIG5 is a schematic diagram of a scenario in which the second range calculation for AED search is performed in the method according to an embodiment of the present application;

[0093] FIG6 is a schematic diagram of a flow chart of calculation for performing AED search within a third range in the method according to an embodiment of the present application;

[0094] FIG7 is a schematic diagram of a scenario in which the third range calculation for AED search is performed in the method according to an embodiment of the present application;

[0095] FIG8 is a schematic diagram of a flow chart of AED search range merging calculation in the method according to an embodiment of the present application;

[0096] FIG9 is a schematic diagram of converting a grid path into a weighted graph in a method according to an embodiment of the present application;

[0097] FIG10 is a schematic diagram of plane projection transformation in the method according to an embodiment of the present application;

[0098] FIG11 is a system block diagram of a system for intelligently and rapidly acquiring an AED at an emergency scene according to an embodiment of the present application;

[0099] FIG12 is a system block diagram of the intelligent AED device according to an embodiment of the present application. DETAILED DESCRIPTION

[0100] To make the above-mentioned objects, features, and advantages of the present application more clearly understood, the specific embodiments of the present application are described in detail below with reference to the accompanying drawings. The following description sets forth many specific details to facilitate a full understanding of the present application. However, the present application can be implemented in many other ways than those described herein, and those skilled in the art can make similar improvements without violating the scope of the present application. Therefore, the present application is not limited to the specific embodiments disclosed below.

[0101] The terms used herein are for describing specific embodiments only and are not intended to be limiting of the present invention. Singular forms such as "a," "the," "this," "this," and "the" as used herein also include plural forms.

[0102] The terms “first”, “second”, etc. used in this document do not specifically refer to an order or sequence, nor are they used to limit this case. They are only used to distinguish components or operations described with the same technical terms.

[0103] As used herein, “connected” or “positioned” may refer to two or more components or devices being in direct or indirect physical contact with each other, or may refer to two or more components or devices operating or moving with each other.

[0104] The terms “include”, “including”, “have”, etc. used in this document are open-ended terms, meaning including but not limited to.

[0105] Unless otherwise noted, the terms used herein generally have their ordinary meanings in the art, in the context of the present invention, and in the specific context. Certain terms used to describe the present invention are discussed below or elsewhere in this specification to provide additional guidance to those skilled in the art regarding the description of the present invention.

[0106] The present application aims to provide an intelligent and rapid method, system, device, and medium for obtaining an AED to arrive at the emergency scene, so as to obtain an AED to arrive at the scene as quickly as possible after an emergency incident occurs, achieve the most efficient response time, thereby improving the patient's treatment speed and survival rate. In particular, it can provide a good solution for passers-by to participate in cardiac arrest emergency treatment, accurately, scientifically, and effectively allowing passers-by to participate in cardiac arrest emergency treatment, and with the promotion and application of AEDs, the possibility of passers-by responding will gradually increase, providing another boost for patients to receive timely treatment, thereby further ensuring the patient's life safety and health protection.

[0107] Example 1, as shown in FIG1 , Example 1 of the present application proposes an intelligent method for quickly obtaining an AED at the emergency scene, the method comprising:

[0108] Obtain emergency call information and the geographic location of the emergency scene, and search for available AEDs near the emergency scene;

[0109] AED search first range calculation, search for the available AED closest to the emergency incident and lock the available AED, calculate the best path and time for the rescuer to pick up and deliver the AED, and output the AED delivery time A;

[0110] AED search second range calculation, searching for the available AED closest to the emergency incident and locking it, calculating the optimal path and time required for volunteers or AED managers nearby to obtain the AED and deliver it to the emergency scene, and outputting the AED delivery time B;

[0111] AED search third range calculation: Search for available AEDs near the emergency incident with pedestrian traffic. Calculate the final response probability of pedestrians based on the pedestrian traffic data obtained in the previous time period near the available AED and the average pedestrian response probability. Calculate the optimal path and time required for pedestrians near the available AED to finally respond and deliver the AED to the emergency scene after acquiring the AED, and output the AED delivery time C.

[0112] If the final response probability is greater than the response setting index, the arrival plan with the shortest duration among AED delivery time A, AED delivery time B, and AED delivery time C is output as the fastest AED arrival plan; if the final response probability is less than the response setting index, the arrival plan with the shortest duration among AED delivery time A and AED delivery time B is output as the fastest AED arrival plan;

[0113] The rescuer, callable volunteer, AED manager or responding passerby corresponding to the fastest AED arrival plan is defined as the AED delivery executor, and the optimal path and time consumption information corresponding to the fastest AED arrival plan is displayed to the AED delivery executor. The AED delivery executor obtains the available AED from the available AED corresponding to the fastest AED arrival plan and delivers the AED to the emergency scene.

[0114] In the first embodiment of the present application, a rescuer initiates a one-click rescue on the emergency mobile terminal. After the emergency cloud platform obtains the distress call information and the geographical location of the incident, the emergency cloud platform calculates the available AED closest to the geographical location of the emergency scene and the available AED with a flow of people near the emergency incident. The definition of an available AED is that the AED device status is normal; the emergency cloud platform performs AED search first range calculation, AED search second range calculation, and AED search third range calculation. The emergency cloud platform outputs the fastest AED arrival plan to the AED delivery executor and also transmits the optimal path and time-consuming information corresponding to the fastest AED arrival plan and the AED delivery executor information to the emergency mobile terminal. The rescuer sends the distress call information and obtains the fastest AED arrival plan on the emergency mobile terminal, which allows the rescuer to understand the distance and time of the AED to the emergency scene in real time, so that the rescuer can better understand the relevant situation when performing CPR on the scene, thereby providing assistance for taking better CPR, thereby improving the patient's survival rate.

[0115] In the first embodiment of the present application, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal, and the emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographical location of the emergency incident and locks the available AED, calculates the optimal path and time for the rescuer to pick up and deliver the AED, and when it is calculated that the AED delivery time A in the first range of the AED search is the shortest, the emergency cloud platform sends the AED geographical location, device status, delivery method, route map, real-time location, and delivery countdown information to the rescuer's mobile terminal, and the rescuer goes to pick up the AED and arrives at the emergency scene. This is a solution that uses the AED search first range as the fastest AED arrival solution, which allows the rescuer to quickly know the location and route of the available AED and obtain the available AED as quickly as possible, so that the patient can receive AED defibrillation treatment in the most effective time.

[0116] In Example 1 of the present application, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal, the emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographical location of the emergency incident, searches for callable volunteers and AED managers near the available AED, and when it is calculated that the AED delivery time B in the second range of the AED search is the shortest, sends an event request to the mobile terminal of the callable volunteer or AED manager and locks the available AED at the same time. The callable volunteer or AED manager receives the emergency incident on the mobile terminal and processes it, calculates the best path and time for the person to obtain the AED and deliver the AED to the emergency scene, and when the callable volunteer or AED manager goes to pick up the AED and arrives at the emergency scene, the emergency cloud platform sends the AED geographical location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal. This is a solution that uses the second range of AED search to provide the fastest AED arrival time. It allows callable volunteers or AED managers to quickly learn of the occurrence of an emergency incident, the location and route of an available AED, and to obtain the available AED as quickly as possible, so that the patient can receive AED defibrillation treatment in the most effective time.

[0117] In Example 1 of the present application, when an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal, the emergency cloud platform obtains the on-site location and specific situation, and searches for the available AED with the most traffic near the emergency incident. When it is calculated that the AED delivery time C in the third range of the AED search is the shortest, the available AED emits a sound or light alarm, and sends the emergency incident location navigation and specific event description information to the available AED. The available AED screen presents the event request. After passers-by near the available AED notice the alarm of the available AED, they open the AED outer box to obtain the AED and process the emergency incident request. After the AED autonomously alarms, the best path and time for the passers-by to obtain the AED and be sent to the scene are calculated. The passers-by navigate to the emergency scene according to the device information prompts. At the same time, the emergency cloud platform sends the AED's geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal. This solution, which uses the third range of AED search, is the fastest solution for AED arrival. It allows passers-by to quickly know the occurrence of an emergency incident, the location and route of an available AED, and obtain the available AED as quickly as possible, so that the patient can receive AED defibrillation treatment in the most effective time.

[0118] In the first embodiment of the present application, during the calculation step of the third range for searching for an AED, the following steps are used to obtain the data on the flow of people: collecting images and videos of the area near the available AED in the period prior to the moment the emergency information is obtained; performing motion extraction on the spatial object information collected by the images and videos to estimate the flow of people near the available AED; and performing crowd density characterization to obtain the probability density distribution of the flow of people as the data on the flow of people. By obtaining the above data on the flow of people, valid data on the flow of people near the available AED in the period prior to the moment the emergency information is obtained can be obtained, thereby enabling faster calculation and output of the fastest AED arrival plan.

[0119] In the first embodiment of the present application, in the step of calculating the third range of the AED search, the time period of the previous period is set to 10 to 20 minutes before the moment of receiving the emergency information near the available AED, preferably 15 minutes; the response setting index is set to 95%; the image video is captured by the camera on the available AED; the final response probability = the flow of people data Y * the average passerby response probability Z; when Y * Z > 95% and the AED delivery time C is less than the AED delivery time A and the AED delivery time B, the arrival plan calculated by the AED search third range is output as the fastest AED arrival plan. The above steps and related parameter settings can ensure that the information collected in the step of calculating the third range of the AED search is sufficient for calculating the final response probability, ensure that the final response probability is obtained reasonably and effectively, and thus, when the arrival plan calculated by the AED search third range is output as the fastest AED arrival plan, it can ensure that passersby respond in a timely manner, obtain the AED in a timely manner, and deliver the AED to the emergency scene in a timely manner.

[0120] Next, the first embodiment of the present application will be further described with reference to one of the embodiments in more detail.

[0121] The following details of the intelligent and rapid method for obtaining an AED at the emergency scene in this embodiment can be referred to as shown in Figures 2 to 5.

[0122] The embodiment of the present application is mainly to provide an intelligent computing solution for quickly getting an AED to the scene. The intelligent AED device itself can receive emergency information sent by the cloud platform and issue an alarm. Passersby near the intelligent AED device quickly respond to pick up the AED and send it to the emergency scene according to the navigation on the AED screen. The time consumption of the scheme is calculated by combining the AED camera to obtain the density of nearby pedestrians and the average probability of passersby responding to the AED in the past 15 minutes. Only when the probability of passersby responding to this scheme meets the conditions and the total time consumption is less than the time for the rescuer or volunteer to go back and forth to pick up and send the AED, the scheme can be established and pushed for execution by the system. If the scheme is executed, it is the most efficient way to obtain an AED in an emergency scenario.

[0123] When an emergency occurs, the rescuer reports the incident on their mobile device and initiates a request to locate an AED. Upon receiving the request, the emergency cloud platform begins real-time calculation of the optimal AED solution, specifically the fastest AED arrival solution. The fastest AED arrival solution is defined as the fastest way for an AED to reach the emergency scene. The backend then sends this fastest solution back to the rescuer's mobile device, notifying the user in real time of the distance and time it will take for the AED to arrive at the scene.

[0124] The specific solutions of the embodiments of this application are as follows.

[0125] The flowchart of the AED search first range calculation can be found in Figure 2, and the scenario diagram can be found in Figure 3. The AED search first range calculation is as follows:

[0126] (1) The rescuer reports the emergency incident on the emergency mobile terminal and sends the on-site location and specific information to the emergency cloud platform;

[0127] (2) After receiving the emergency incident, the emergency cloud platform processes the incident and searches for the nearest available AED;

[0128] (3) The emergency cloud platform calculates the available AED closest to the geographic location of the emergency incident and locks the AED (an available AED is defined as one with a device status of "normal");

[0129] (4) The emergency cloud platform calculates the optimal route and time for the rescuer to pick up and deliver the AED (e.g., based on the average speed of 2 m / s for a normal adult);

[0130] (5) Calculation formula A:

[0131] (Outbound optimal route + Return optimal route) / Average speed = AED delivery time A;

[0132] The best path is defined as: shortest time;

[0133] Average speed is defined as the average speed of a reasonable mode of transportation such as walking or running that suits the current scenario;

[0134] (6) The emergency cloud platform sends the AED’s geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the rescuer’s mobile terminal;

[0135] (7) The rescuer goes to get the AED and arrives at the emergency scene.

[0136] The flowchart of the AED search second range calculation can be found in Figure 4, and the scenario diagram can be found in Figure 5. The AED search second range calculation is as follows:

[0137] (1) The rescuer reports the emergency incident on the emergency mobile terminal and sends the on-site location and specific information to the emergency cloud platform;

[0138] (2) After receiving an emergency incident, the emergency cloud platform processes the incident, searches for the nearest available AED, and searches for callable volunteers and AED managers near the available AED (“callable” volunteers and managers are defined as those who are in working condition and whose geographical location is within an X-kilometer radius);

[0139] (3) The emergency cloud platform sends an event request to the mobile terminal of the callable volunteer or AED manager and locks the AED at the same time;

[0140] (4) The callable volunteer or AED manager receives and handles the emergency incident on the mobile terminal;

[0141] (5) The emergency cloud platform calculates the optimal path and time required for the person to obtain the AED and deliver it to the emergency scene;

[0142] (6) Calculation formula B:

[0143] (Optimal distance between the callable volunteer or AED manager and the AED + optimal distance between the AED and the scene) / average speed = AED arrival time B;

[0144] (7) The emergency cloud platform sends the AED geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal;

[0145] (8) A volunteer or AED manager is called to retrieve the AED and arrive at the emergency scene.

[0146] The flowchart of the AED search third range calculation can be found in Figure 6 , and the scenario diagram can be found in Figure 7 . The AED search third range calculation is as follows:

[0147] (1) The rescuer reports the emergency incident on the emergency mobile terminal and sends the on-site location and specific information to the emergency cloud platform;

[0148] (2) After receiving the emergency incident, the emergency cloud platform processes the incident, searches for an available AED near the emergency scene, and locks the AED (searching for an AED within the third range requires two conditions to be met: 1. The AED with the most traffic near the emergency scene in the past 15 minutes is not necessarily the closest AED; 2. The device status is "available").

[0149] (3) The intelligent AED device emits a sound prompt "emergency incident" and a red light alarm

[0150] (4) The emergency cloud platform sends the emergency event location navigation and specific event description information to the AED, and the AED screen displays the event request;

[0151] (5) The emergency cloud platform calculates the optimal route and time required for passersby to obtain the AED and transport it to the scene after the AED automatically alarms

[0152] (6) Calculation formula C:

[0153] Calculation of the final pedestrian response probability: The pedestrian flow data Y captured by the AED camera at the AED's location over the past 15 minutes multiplied by the average pedestrian response probability Z;

[0154] The time it takes for a passerby to obtain the AED to arrive at the scene is calculated as follows: optimal path distance from the AED to the scene / average speed = AED arrival time C; (Since step (2) results in the device not necessarily being the same AED within the first and second ranges, AED arrival time C is not necessarily less than AED arrival time A or AED arrival time B).

[0155] When Y*Z>95% and AED arrival time C is less than AED arrival time A and AED arrival time B, the system feedback to the rescuer's emergency mobile terminal that the fastest AED arrival solution is the AED search third range calculation solution;

[0156] (7) A passerby near the AED responds after noticing the AED alarm, opens the AED case to obtain the AED, and handles the emergency request;

[0157] (8) The emergency cloud platform sends the AED geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal;

[0158] (9) Passersby navigate to the emergency scene according to the device information prompts.

[0159] As shown in Figures 3, 5, and 7, the AED search calculation scheme for the third range is as follows: if the targeted AED is the same as the one in the first and second ranges, the total distance required for a passerby to retrieve the AED and deliver it to the scene is the shortest. Therefore, theoretically, time C is the shortest under normal circumstances. However, if the AED targeted in the third range is different from the one in the first and second ranges, and the passerby's response speed is related to the pedestrian density near the AED and the average probability of retrieval over the past 15 minutes as captured by the AED camera, then this scheme is only valid and pushed for execution by the system if its total time is less than that in the first and second ranges. If the third scheme is recommended to the user as a feasible option, but the AED is still not retrieved by a passerby within N seconds, the system recommends the second-ranked option as the final feasible option. The above calculation process is continuously processed in real time by the emergency cloud platform to ensure that the AED arrives at the scene within 3 minutes using the fastest possible solution.

[0160] In this way, the emergency cloud platform algorithm model calculates in real time, sorts the time of the three measurement methods for obtaining the AED delivery scene, and finally outputs the fastest solution result and sends it to the rescuer's mobile terminal. The process diagram of the combined calculation of the AED search range can be found in Figure 8. The rescuer can see the AED delivery method, route map and real-time location, and delivery countdown on the mobile terminal. If the AED can arrive at the scene within 3 minutes, the mobile terminal displays the fastest acquisition plan. If it cannot arrive at the scene within 3 minutes, the system informs the rescuer that the AED cannot be obtained, please call 120 immediately and perform CPR at the same time (or the emergency cloud platform directly contacts 120 while sending the emergency information, and sends the relevant information to 120).

[0161] For obtaining the optimal path in the above method, please refer to the following.

[0162] (1) First, the grid path is transformed into a weighted graph, as shown in Figure 9;

[0163] (2) Create a distance matrix between the node and the starting point, set the value of the starting point to 0, and set the remaining elements to infinity (inf);

[0164] (3) Create the parent node matrix of the node and initialize it to 0, indicating that there is no parent node;

[0165] (4) Each time iterative update is performed, the node with the lowest total evaluation cost (the minimum sum of the edge weights of the node) among the untraversed nodes in the distance matrix is ​​found and set as the current node; in order to prevent re-traversal, the distance of the current node is set to infinity and marked as completed traversal; the untraversed nodes among all adjacent nodes of the current node are judged to determine whether the adjacent node has a weighted distance greater than the edge weight of the current node to the next node. If so, the node is updated to the current node;

[0166] (5) Repeat step (4) until the current node is the target point;

[0167] (6) The optimal path is completed by backtracking the parent nodes according to the parent node matrix.

[0168] For the calculation of the final response probability in the third range of AED search, please refer to the following.

[0169] The video image information collected by the video acquisition module (camera) on the intelligent AED device is used to reflect the crowd density estimation environment, and a local grid is established to record the crowd density distribution. Finally, the probability of the crowd responding to the AED alarm is estimated using the Poisson distribution. The main process is as follows:

[0170] (1) First, establish a staggered local grid near the available AEDs. Pre-construct a crowd density distribution matrix to represent the distribution information of crowd flow in the uniform local grid.

[0171] (2) Then, the image filtering method is used to extract the motion of the spatial object information collected by the image video, which is used to estimate the surrounding crowd flow.

[0172] (3) Then, the image space projection method is used to project the extracted spatial crowd flow information into the plane coordinate grid unit.

[0173] (4) Finally, the final response probability of the AED is calculated by the Poisson distribution of the probability of human flow on the local grid of the plane.

[0174] The crowd density distribution matrix X is used to represent the distribution of crowd flow in a unit grid;

[0175] Each element X in the matrix X ij A numerical representation of the crowd density distribution recorded in a unit grid.

[0176] For video images shot by cameras in the same direction, the pixel values ​​of background pixels change slowly, while the pixel values ​​of pixels corresponding to moving targets change relatively quickly. Therefore, by collecting a video image sequence over a period of time, a background image without human traffic can be reconstructed based on the pixel values ​​of pixels that change slowly on the time axis. At the same time, in order to make the background model adaptive to changes in external light, the background model must be updated in real time. The following update method can be used: In the detection of human traffic, for pixels that are judged to belong to human traffic, the original background pixel values ​​are still maintained and not updated. For points judged to be background, the background model is updated according to the following rules: B t+1 (i,j)=αB t(i,j)+(1-α)G(i,j) (2)

[0177] Where α∈(0,1) is the update rate, B t (i, j) represents the pixel value of the background image pixel at time t, and G(i, j) represents the pixel value of the pixel in the current frame.

[0178] Based on human visual characteristics, background subtraction utilizes the HIS space of color images as the basis for image differentiation. In high-saturation (high S) regions, the chromaticity information represented by H is more prominent, and differentiation can be performed using the H value. In low-saturation (low S) regions, the luminance information represented by I is more prominent, and differentiation can be performed using the I value. Binarizing the resulting image after differentiation allows for the detection of human traffic.

[0179] At the same time, in order to combat the background noise caused by the slow rotation of the camera in the same direction, we further filter the background noise. For continuous video images, we perform continuous Gaussian distribution difference extraction on the nth image at time t; g n,t =(1-α)g n,t-1 +αG n,t (3)

[0180] where g n,t is the Gaussian distribution of the nth image at time t, specifically:

[0181] Among them, μ t represents the mean value of n image pixels at time t, represents the variance of n image pixels at time t, ρ represents the Gaussian distribution probability density estimated using binary distribution, and η represents the binary distribution function.

[0182] By Gaussian optimization of noise, the background image B is:

[0183] Where W is the minimum weight of the background noise, which is generally 1≤W≤n. In actual situations, this weight is related to the slow rotation rate of the camera.

[0184] In order to project the spatial crowd density information represented in the video to the plane coordinate representation of the geographical location, the spatial representation information of the video image captured by the camera needs to be subjected to a plane projection transformation as shown in FIG10 .

[0185] Use the directional projection transformation matrix H to project each calculated image pixel point to obtain the crowd flow density for plane projection. The projection matrix is:

[0186] Where θ is the rotation angle of the matrix image pixel; h2 and h5 are the translation amounts of the entire image.

[0187] Through the above transformation, the image data is uniformly transformed into a plane representation at the same angle using projection transformation to represent the crowd density distribution. According to formula (1), each element of the matrix X is the crowd distribution of the unit grid. Specifically, the pixel G of the image is subtracted from the background pixel B corrected by formulas (2)-(5), and then the calculation is performed by projection through affine transformation (6), as shown in the following formula: X = H*(GB) (7)

[0188] The plane projection representation can represent the probability density distribution of the flow of people on each grid. Assuming that the probability of each person responding to the AED is the same and equal to Z, we use the Poisson distribution to calculate the response probability of the flow of people as follows:

[0189] In the above formula, k represents the number of times the event occurs. The plan requires at least one AED response to the crowd flow. Therefore, for the case of , k = 1; λ represents the probability response coefficient under the crowd flow distribution. Assuming that the probability of each person responding to the AED is a fixed value, the expected probability is related to the density of the crowd flow. Therefore, the np expectation of the Poisson distribution can be directly related to the mean of the crowd flow density distribution matrix, as follows: Po(λ) = E(X) (9)

[0190] The value of λ can be obtained by looking up the table.

[0191] Example 2, as shown in FIG11 , Example 2 of the present application proposes an intelligent system for quickly obtaining an AED to arrive at the emergency scene, the system including an emergency mobile terminal, an intelligent AED device, and an emergency cloud platform; wherein,

[0192] The first aid mobile terminal is a device for sending emergency call information and the geographical location of the first aid scene, and receiving the optimal path and time information corresponding to the fastest AED arrival plan; the first aid mobile terminal communicates with the first aid cloud platform via long-distance wireless communication;

[0193] The intelligent AED device is a device for performing external defibrillation. The intelligent AED device includes an alarm module, a video display module, and a video acquisition module. The alarm module is configured to at least generate an alarm upon receiving a message that uses the AED delivery time C as the fastest AED arrival plan, so that passers-by near the available AED can respond to the emergency call in a timely manner; the video display module is configured to display the optimal path and time information corresponding to the fastest AED arrival plan; and the video acquisition module is configured to capture video images near the intelligent AED.

[0194] The first aid cloud platform communicates with the first aid mobile terminal and the intelligent AED device through a long-distance wireless method. The first aid cloud platform is used to receive the distress call information of the first aid event sent by the first aid mobile terminal, perform AED search first range calculation, AED search second range calculation, AED search third range calculation, output the fastest AED arrival plan, and display the optimal path and time consumption information corresponding to the fastest AED arrival plan to the AED delivery executor via the first aid mobile terminal or the intelligent AED device.

[0195] In the second embodiment of the present application, the first aid mobile terminal can be a mobile terminal, such as a smart phone, a tablet computer, etc., which has a real-time network communication function, and the user can initiate a first aid request. The first aid cloud platform is the first aid cloud platform dispatch center, which obtains the first aid request and pushes the optimal AED quick acquisition solution to the mobile terminal. The intelligent AED communicates with the first aid cloud platform server via a long-distance wireless method (including but not limited to a cellular network, Wi-Fi). The first aid mobile terminal communicates with the first aid cloud platform server via a long-distance wireless method (including but not limited to a cellular network, Wi-Fi).

[0196] Specifically:

[0197] 1. The AED is connected to the emergency cloud platform server via the Internet. The platform obtains the AED's geographical location and equipment operation status. Based on the location of the emergency request event, it matches the event with the distance to the available intelligent AED device.

[0198] 2. The emergency cloud platform server receives the emergency event request from the emergency mobile terminal, calculates and outputs the fastest AED delivery response plan, outputs the result and sends it to the rescuer's mobile terminal;

[0199] 3. The emergency cloud platform connects with volunteers and the mobile terminals of intelligent AED device administrators through the Internet, and locks the currently available personnel based on their work status, service area, and geographic location.

[0200] Embodiment 3, as shown in FIG12 , embodiment 3 of the present application proposes an intelligent AED device for use in the method described in embodiment 1 of the present application, wherein the intelligent AED device includes a main control module, a video acquisition module, a power supply module, a communication module, a storage module, a video display module, and an alarm module;

[0201] The main control module is used for information collection, storage, analysis and decision-making;

[0202] The video acquisition module is used to collect video images near the intelligent AED;

[0203] The power supply module is used to supply power to other modules;

[0204] The storage module is used to store AED operation information, video image information, and detection information;

[0205] The communication module is responsible for communicating with the emergency cloud platform;

[0206] The video display module is used to display the optimal path and time-consuming information corresponding to the fastest AED arrival plan;

[0207] The alarm module is used to issue an alarm when receiving a plan that adopts the AED delivery time C as the fastest AED arrival plan.

[0208] Example 4. Example 4 of the present application also proposes a readable storage medium, on which a control program is stored. When the control program is executed by the processor, the processor executes the steps of the method for intelligently and quickly obtaining an AED to arrive at the emergency scene as described in Example 1 of the present application.

[0209] By implementing the above embodiments, the purpose of the present application has been achieved. After obtaining the distress call information of the emergency event, the AED search first range calculation, the AED search second range calculation, and the AED search third range calculation are performed, and the plan for delivering the AED in the fastest time is output to the corresponding rescuer, callable volunteer, AED manager or responding passerby. Compared with the existing AED distribution plan that can only rely on volunteers and AED managers to distribute AEDs, the present application specifically uses passersby near the available AED as AED delivery executors to obtain the AED to the emergency scene. This is because the cardiac arrest patient occurs suddenly and the geographical location of the emergency scene is irregular. The time it takes for the rescuer, callable volunteer or AED manager who is closer to the available AED to deliver the available AED may be relatively long. At this time, the AED search third range calculation is performed, and the final response probability of the passerby is calculated based on the pedestrian flow data of the previous time period near the available AED and the average response probability of the passerby. The final response probability of the passerby near the available AED is measured after obtaining the AED. The optimal path and time for the AED to arrive at the emergency scene, and when the final response probability is greater than the response setting index, the arrival plan with the shortest time output in the AED search first range, AED search second range, and AED search third range is output as the AED fastest arrival plan. Since the optimal path and time for the AED to be delivered to the emergency scene after the passerby finally responds and obtains the AED in the AED search third range are usually shorter than those in the AED search first range and AED search second range, it can provide the most efficient way to quickly obtain the AED to arrive at the scene in the emergency scenario, achieve the most efficient response time, and provide an intelligent computing solution for cardiac arrest patients to be defibrillated as soon as possible after ventricular fibrillation occurs, thereby improving the patient's treatment speed and survival rate; and with the popularization of AED and first aid knowledge, more and more passers-by will have received AED knowledge, and the final response probability of passers-by will also be higher and higher. After adopting the solution of this application, it will be able to provide a good solution for passers-by to participate in cardiac arrest first aid, accurately, scientifically and effectively allow passers-by to participate in cardiac arrest first aid, and provide another help for patients to receive timely treatment.

[0210] The above embodiments are intended only to illustrate the technical concepts and features of this application. Their purpose is to enable those familiar with the art to understand the content of this application and implement it accordingly. They are not intended to limit the scope of protection of this application. Any equivalent changes or modifications made in accordance with the spirit of this application shall be included in the scope of protection of this application.

Claims

1. An intelligent and rapid method for obtaining an AED to arrive at the emergency scene, wherein: The method comprises: Obtain emergency call information and the geographic location of the emergency scene, and search for available AEDs near the emergency event; AED search first range calculation, search for the available AED closest to the emergency incident and lock the available AED, calculate the best path and time for the rescuer to pick up and deliver the AED, and output the AED delivery time A; AED search second range calculation, search for the available AED closest to the emergency incident, calculate the best path and time for the AED to be delivered to the emergency scene after the AED can be called by volunteers or AED managers near the available AED, and output the AED delivery time B; AED search third range calculation, search for available AEDs with pedestrian traffic near the emergency event, calculate the final response probability of pedestrians based on the pedestrian traffic data of the previous period near the available AED and the average pedestrian response probability, measure the optimal path and time for the pedestrians near the available AED to finally respond to the AED, and deliver the AED to the emergency scene after obtaining the AED, and output the AED delivery time C; If the final response probability is greater than the response setting index, the AED delivery time A, AED delivery time B, and AED delivery time C with the shortest arrival time will be output as the AED fastest arrival plan; if the final response probability is less than the response setting index, the AED delivery time A, AED delivery time B with the shortest arrival time will be output as the AED fastest arrival plan; The rescuer, callable volunteer, AED manager or responsive passerby corresponding to the AED fastest arrival plan are defined as the AED delivery executor, the optimal path and time consumption information corresponding to the AED fastest arrival plan are displayed to the AED delivery executor, and the AED delivery executor obtains the available AED from the available AED corresponding to the AED fastest arrival plan and delivers the AED to the first aid site.

2. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: The rescuer initiates a one-click rescue on the emergency mobile terminal. After the emergency cloud platform obtains the call for help and the geographical location of the incident, it calculates the available AED closest to the emergency scene and the available AED with pedestrian traffic near the emergency incident. The definition of an available AED is that the AED device status is normal; The emergency cloud platform performs AED search first range calculation, AED search second range calculation, and AED search third range calculation. The emergency cloud platform outputs the fastest AED arrival plan to the AED delivery executor, and also transmits the optimal path and time consumption information corresponding to the fastest AED arrival plan and the AED delivery executor information to the emergency mobile terminal.

3. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: For the calculation of the best path and time consumption in the steps of the AED searching the first range calculation, the AED searching the second range calculation and the AED searching the third range calculation, a graph search path algorithm is used to obtain the best path; In the step of calculating the AED search first range, AED delivery time A = (outbound best path + return best path) / average speed; In the step of calculating the AED search second range, AED delivery time B = (the best path from the AED to the volunteer or AED manager + the best path from the AED to the emergency scene) / average speed; In the step of calculating the AED search third range, the AED delivery time C = the optimal distance between the AED and the emergency scene. Path / average speed.

4. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 3, wherein: The following steps are used to obtain the best path: Convert the grid path into a weighted graph; Create a distance matrix between the node and the starting point based on the weighted graph, set the value of the starting point to 0, and set the remaining elements to infinity; Create a parent node matrix for the node, initialized to 0, indicating no parent node; Find the node with the lowest total evaluation cost among the untraversed nodes in the distance matrix and set it as the current node; set the distance of the current node to infinity and mark it as completed traversal; determine the untraversed nodes among all adjacent nodes of the current node to determine whether the adjacent node has a weighted distance greater than the edge weight of the current node to the next node. If so, update it to the current node; Repeat the above steps until the current node is the target point; The parent node backtracking is done according to the parent node matrix to obtain the best path.

5. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: After the arrival plan in the third range of the AED search is output as the fastest AED arrival plan, the fastest AED arrival plan is sent to the available AED and the available AED issues an alarm, and passers-by near the available AED respond quickly to pick up the AED and send it to the emergency scene according to the navigation information of the best path on the AED screen; if the passers-by near the available AED that issues the alarm do not respond to obtain the AED within time N, then the arrival plan with the shortest duration between AED delivery time A and AED delivery time B is re-output as the fastest AED arrival plan, where the sum of time N plus AED delivery time C is greater than AED delivery time A and AED delivery time B.

6. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: When an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal. The emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographical location of the emergency incident and locks the available AED, calculates the best path and time for the rescuer to pick up and deliver the AED, and when it is calculated that the AED delivery time A in the first search range is the shortest, the emergency cloud platform sends the AED geographical location, equipment status, delivery method, route map, real-time location, and delivery countdown information to the rescuer's mobile terminal, and the rescuer goes to pick up the AED and arrives at the emergency scene.

7. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: When an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal. The emergency cloud platform obtains the on-site location and specific conditions, calculates the available AED closest to the geographical location of the emergency incident, searches for callable volunteers and AED managers near the available AED, and when it is calculated that the AED delivery time B in the second range of the AED search is the shortest, sends an event request to the mobile terminal of the callable volunteer or AED manager and locks the available AED at the same time. The callable volunteer or AED manager receives and processes the emergency incident on the mobile terminal, calculates the best path and time for the person to obtain the AED and deliver the AED to the emergency site, and when the callable volunteer or AED manager goes to pick up the AED and arrives at the emergency site, the emergency cloud platform sends the AED's geographical location, equipment status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal.

8. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: When an emergency incident occurs, the rescuer initiates a one-click call for help on the emergency mobile terminal. The emergency cloud platform obtains the on-site location and specific conditions, and searches for the available AED with the most traffic near the emergency incident. When it is calculated that the AED delivery time C in the third range of the AED search is the shortest, the available AED emits a sound or light alarm, and sends the emergency incident location navigation and specific event description information to the available AED. The available AED screen presents the event request. Passersby near the available AED notice the alarm of the available AED and open the AED outer box to obtain the AED and process the emergency incident request. After the AED autonomously alarms, the best path and time for passers-by to obtain the AED and send it to the scene are calculated. Passers-by navigate to the emergency scene according to the device information prompts. At the same time, the emergency cloud platform sends the AED's geographic location, device status, delivery method, route map, real-time location, and delivery countdown information to the emergency mobile terminal.

9. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: In the step of AED searching for the third range calculation, the following steps are adopted to obtain the data of the flow of people: Collecting video images of the vicinity of the available AED in the period prior to the moment of obtaining the emergency information; Perform motion extraction on spatial object information collected by image and video to estimate the flow of people near available AEDs; The crowd density is characterized and the crowd probability density distribution is obtained as the crowd flow data.

10. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 9, wherein: In the step of calculating the third range of the AED search, the time period of the previous period is set to the time period of the vicinity of the available AED within 10 to 20 minutes before the moment of receiving the emergency information; The response setting indicator was set at 95%; The image video is captured by a camera on an available AED; Final response probability = pedestrian flow data Y*average passerby response probability Z; When Y*Z>95% and the AED delivery time C is less than the AED delivery time A and the AED delivery time B, the arrival plan calculated by the AED searching the third range is output as the fastest AED arrival plan.

11. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 1, wherein: In the step of calculating the third range of the AED search, the process of calculating the final response probability of the passerby based on the pedestrian flow data of the previous time period near the available AED and the average response probability of the passerby is as follows: Collecting video images of the vicinity of the available AED in the period prior to the moment of obtaining the emergency information; Establish a staggered local grid near the available AED; pre-construct a crowd density distribution matrix to represent the distribution information of crowd flow in a uniform local grid; Use image filtering methods to extract motion from spatial object information collected by image videos to obtain spatial human flow information; The extracted spatial crowd flow information is projected onto the local grid under the plane coordinates using the image space projection method, and the probability density distribution of the crowd flow on each grid of the local grid is represented by the plane projection representation, which is used as the crowd flow data; The final response probability of the AED being responded to is calculated by the Poisson distribution of the probability of human flow on the local grid under plane coordinates.

12. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 11, wherein: The following steps are used to extract motion from spatial object information collected by image video using an image filtering method: For the acquired images and videos near the available AED, the pixel values ​​on the time axis of the images and videos change slowly. The background image without human traffic is reconstructed from the pixels of the image, and the background model is updated in real time: in the detection of human traffic, for the pixels judged to belong to human traffic, the original background pixel values ​​are still maintained and not updated; for the pixels judged to be background, the background model is updated according to the following rules: n+1 (i,j)=αB n (i,j)+(1-α)G(i,j); Among them, α∈(0,1) is the update rate, B n (i, j) represents the pixel value of the background image pixel, G(i, j) represents the pixel value of the pixel in the current frame; For continuous video images, continuous Gaussian distribution difference extraction is performed on the nth image to filter the background noise and obtain the background image B; The HIS space of color images is used as the basic space for image difference, and the image video is differentiated. The image obtained after the difference is binarized to detect the flow of people, thereby extracting the spatial flow of people information.

13. The intelligent method for quickly obtaining an AED to arrive at the emergency scene according to claim 12, wherein: For pre-constructing the crowd density distribution matrix to represent the distribution information of crowd in a uniform local grid, the crowd density distribution matrix X is pre-constructed. In which, each element X in the matrix X ij A numerical representation of the density distribution of people flow recorded in the local grid; Use the directional projection transformation matrix H to project each calculated image pixel point to obtain the crowd density for plane projection. The directional projection transformation matrix H is: Among them, θ is the rotation angle of the matrix image pixel, h2 and h5 are the translation amounts of the entire image; Projection transformation is used to uniformly transform image data into a plane representation at the same angle to characterize the density distribution of human traffic, X = H*(GB); Assume that the probability of each passerby responding to the AED is the same and equal to Z, and the final response probability of the passerby is calculated using the Poisson distribution: Where k represents the number of times the event occurs, and λ represents the probability response coefficient under the crowd flow distribution; For the probability response coefficient λ under the crowd distribution, since the expectation of the pine and cypress distribution is directly related to the crowd density distribution matrix X, that is, Po(λ)=E(X)*Z, the value of λ is obtained by table lookup method.

14. An intelligent system for quickly obtaining AED arrival at the emergency scene, used in the method according to any one of claims 1 to 10, wherein: The system includes a mobile emergency terminal, an intelligent AED device, and an emergency cloud platform; The first aid mobile terminal is a device for sending out emergency call information and the geographical location of the first aid scene, and receiving the best path and time information corresponding to the fastest AED arrival plan; the first aid mobile terminal communicates with the first aid cloud platform via long-distance wireless mode; The intelligent AED device is a device for external defibrillation. The intelligent AED device includes an alarm module, a video display module, and a video acquisition module. The alarm module is arranged to at least alarm when receiving a signal that the AED delivery time C is used as the fastest AED arrival plan, so that passers-by near the available AED can respond to the emergency call information of the emergency event in time; the video display module is used to display the fastest AED arrival plan corresponding to the fastest AED arrival plan. The optimal path and time-consuming information; the video acquisition module is used to collect video images near the intelligent AED; The first aid cloud platform communicates with the first aid mobile terminal and the intelligent AED device through long-distance wireless means. The first aid cloud platform is used to receive the distress call information of the first aid incident sent by the first aid mobile terminal, perform AED search first range calculation, AED search second range calculation, AED search third range calculation, output the fastest AED arrival plan and display the optimal path and time consumption information corresponding to the fastest AED arrival plan to the AED delivery executor via the first aid mobile terminal or the intelligent AED device.

15. An intelligent AED device, used in the method according to any one of claims 1 to 10, wherein: The intelligent AED device includes a main control module, a video acquisition module, a power module, a communication module, a storage module, a video display module, and an alarm module; The main control module is used for information concentration, storage, analysis and decision-making; The video acquisition module is used to collect video images near the intelligent AED; The power module is used to supply power to other modules; The storage module is used to store AED operation information, video image information, and detection information; The communication module is responsible for communicating with the emergency cloud platform; The video display module is used to display the optimal path and time-consuming information corresponding to the fastest AED arrival solution; The alarm module is used to issue an alarm when receiving a signal that the AED delivery time C is used as the fastest AED arrival solution.

16. A readable storage medium, wherein: The readable storage medium stores a control program, and when the control program is executed by a processor, the processor executes the steps of the method according to any one of claims 1 to 10.

Images