Aed drone emergency rescue communication method, device and program product

Abstract

The application discloses an AED unmanned plane emergency rescue communication method, device and program product, and belongs to the technical field of unmanned plane emergency rescue and communication. The method comprises the following steps: acquiring rescue related data sent by multiple AED unmanned planes; wherein the rescue related data comprises multiple data streams; performing optimization processing on the rescue related data of each AED unmanned plane to obtain an optimal communication scheme; wherein the optimal communication scheme comprises optimal communication links of each data stream in each AED unmanned plane; and sending the rescue related data of each AED unmanned plane to a remote command end according to the optimal communication scheme, so that the remote command end performs rendering display processing on the rescue related data of each AED unmanned plane. According to the application, the link resources can be dynamically adjusted according to the real-time communication demand and real-time communication condition of the emergency rescue task, so that the communication efficiency of the unmanned plane emergency rescue is effectively improved.

Description

Technical Field

[0001] This application relates to the field of drone emergency rescue and communication technology, and in particular to an AED drone emergency rescue communication method, device and program product. Background Technology

[0002] Currently, unmanned aerial vehicle (UAV)-assisted emergency rescue response systems typically consist of a UAV flight platform, an automated external defibrillator (AED) mounting and deployment module, a multimodal data acquisition unit, and a remote command terminal. The system achieves on-site situational awareness and emergency rescue guidance through an integrated air-ground data link.

[0003] In related technologies, all data streams collected by the drone, including video streams, audio streams, device status, and control commands, are transmitted through a single communication link to enable information exchange between the drone and the remote command center. However, this method is prone to causing interference between different drones competing for the same communication link, leading to congestion and severely limiting the communication efficiency of drone-based emergency rescue. Summary of the Invention

[0004] The main objective of this application is to propose an AED drone emergency rescue communication method, device, and program product, which aims to effectively improve the communication efficiency of drone emergency rescue.

[0005] To achieve the above objectives, one aspect of this application proposes an AED (Automated External Defibrillator) drone emergency rescue communication method, the method comprising: Acquire rescue-related data transmitted by multiple AED drones; wherein, the rescue-related data includes multiple data streams; The rescue-related data of each AED drone are optimized to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each AED drone; According to the optimal communication scheme, the rescue-related data of each AED drone is sent to the remote command terminal, so that the remote command terminal can render and display the rescue-related data of each AED drone.

[0006] In some embodiments, the optimization processing of the rescue-related data of each of the AED drones to obtain the optimal communication scheme includes: Each of the AED drones, each of the data streams, and each of the communication links are encoded and initialized to obtain an initial population as the parent population; wherein, the population includes multiple individuals, each individual includes multiple gene bits, each gene bit corresponds one-to-one with each of the data streams, and each gene bit represents the communication link allocated to the data stream; The parent population is selected based on the fitness values ​​of each individual in the parent population to obtain the selected population. The selected population is subjected to mutation and crossover processes to obtain the offspring population; If the current iteration count has not reached the maximum iteration count, the offspring population is determined as the new parent population, the current iteration count is incremented by one, and the process returns to the step of selecting the parent population based on the fitness values ​​of each individual in the parent population. Otherwise, the individual with the highest fitness value in the offspring population is decoded to obtain the optimal communication scheme.

[0007] In some embodiments, the process of encoding and initializing each of the AED drones, each of the data streams, and each of the communication links to obtain an initial population as the parent population includes: A flattened integer encoding method is used to encode and initialize each of the AED drones, each of the data streams, and each of the communication links to obtain the initial population as the parent population.

[0008] In some embodiments, the selection process of the parent population based on the fitness values ​​of each individual in the parent population to obtain a selected population includes: Based on the fitness values ​​of each individual in the parent population, and using a roulette wheel selection method, the parent population is selected to obtain the selected population.

[0009] In some embodiments, the mutation and crossover process performed on the selected population to obtain a progeny population includes: Perform a two-point crossover process on the selected population to obtain a crossover population; The crossover population is subjected to site mutation processing to obtain a variant population, which is then used as the offspring population.

[0010] In some embodiments, the steps for calculating the fitness value of the individual include: The global average latency, global average packet loss rate, and link load balancing variance of all communication links are calculated for the target individual to obtain the communication overhead value of the target individual. The bandwidth overload penalty value and the link number overload penalty value are calculated for the target individual to obtain the communication penalty value of the target individual; The fitness value of the target individual is obtained based on its communication overhead and communication penalty values. Wherein, the target individual refers to any one of the individuals.

[0011] In some embodiments, sending rescue-related data from each of the AED drones to a remote command terminal according to the optimal communication scheme includes: Each of the data streams is backed up to obtain backup data for each of the data streams; Each data stream and its backup data are encrypted separately to obtain the original encrypted data and the backup encrypted data of each data stream. According to the optimal communication scheme, the original encrypted data of each data stream is sent to the remote command terminal, and the backup encrypted data of each data stream is sent to the remote command terminal through a preset communication link.

[0012] In some embodiments, the rescue-related data includes: Video data streams, including video data from the rescue site; Voice data stream, including audio data from the rescue site; Vital signs data stream, including physiological data of the target object at the rescue site; AED data stream, including defibrillation operation data from the AED device.

[0013] To achieve the above objectives, another aspect of this application proposes an AED drone emergency rescue communication device, the device comprising: The acquisition module is used to acquire rescue-related data sent by multiple AED drones; wherein the rescue-related data includes multiple data streams; The first processing module is used to perform optimization processing on the rescue-related data of each of the AED drones to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each of the AED drones; The second processing module is used to send the rescue-related data of each of the AED drones to the remote command terminal according to the optimal communication scheme, so that the remote command terminal can render and display the rescue-related data of each of the AED drones.

[0014] To achieve the above objectives, another aspect of this application provides a computer program product, including a computer program that, when executed by a processor, implements the aforementioned AED drone emergency rescue communication method.

[0015] According to an embodiment of this application, an AED drone emergency rescue communication method, device, and program product are provided. The method acquires rescue-related data transmitted by multiple AED drones. The rescue-related data includes multiple data streams. The method optimizes the rescue-related data of each AED drone to obtain an optimal communication scheme. The optimal communication scheme includes the optimal communication link for each data stream in each AED drone. The rescue-related data of each AED drone is transmitted to a remote command terminal according to the optimal communication scheme, enabling the remote command terminal to render and display the rescue-related data of each AED drone. The technical solution of this application embodiment can dynamically adjust link resources according to the real-time communication needs and real-time communication status of the emergency rescue mission, thereby effectively improving the communication efficiency of drone emergency rescue.

[0016] Other features and advantages of this application will be set forth in the following description and will be apparent in part from the description or may be learned by practicing the application. The objectives and other advantages of this application may be realized and obtained by means of the structures particularly pointed out in the description and the accompanying drawings. Attached Figure Description

[0017] Figure 1 This is a flowchart of an AED drone emergency rescue communication method provided in this application; Figure 2 This is a flowchart of the optimization process provided in this application; Figure 3 This is a diagram illustrating the implementation process of an AED drone emergency rescue communication method provided in this application; Figure 4 This is a structural diagram of an AED drone emergency rescue communication device provided in this application. Detailed Implementation

[0018] To make the objectives, technical solutions, and advantages of this application clearer, the following detailed description is provided in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of this application and are not intended to limit it. In the following description, when referring to the accompanying drawings, unless otherwise indicated, the same numbers in different drawings represent the same or similar elements. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with those of this application; they are merely examples of apparatuses and methods consistent with some aspects of the embodiments of this application as detailed in the appended claims.

[0019] It is understood that the terms “first,” “second,” etc., used in this application may be used herein to describe various concepts, but unless otherwise stated, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiments of this application, first information may also be referred to as second information, and similarly, second information may also be referred to as first information. Depending on the context, the words “if,” “when,” or “in response to a determination” as used herein may be interpreted as “when…” or “when…” or “in response to a determination.”

[0020] As used in this application, the terms "at least one", "multiple", "each", "any", etc., "at least one" includes one, two or more, "multiple" includes two or more, "each" refers to each of the corresponding multiples, and "any" refers to any one of the multiples.

[0021] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the art to which this application belongs. The terminology used herein is for the purpose of describing embodiments of this application only and is not intended to limit this application.

[0022] Cardiac arrest (CA) is a major public health problem threatening human life. Timely cardiopulmonary resuscitation (CPR) and automated external defibrillator (AED) defibrillation are key interventions to save patients' lives. A typical drone-assisted emergency rescue response system usually consists of a drone flight platform, an AED mounting and release module, a multimodal data acquisition unit, and a remote command terminal. The system achieves on-site situational awareness and emergency rescue guidance through an integrated air-to-ground data link. With the continuous breakthroughs in drone endurance, payload miniaturization, and 5G communication technology, drone-assisted emergency rescue has gradually moved from the early proof-of-concept stage to the regional pilot application stage. Such systems can not only overcome the physical limitations of ground traffic congestion to quickly deliver AEDs to the scene, but also support high-quality CPR implementation at the rescue site through audio and video interaction, thus buying valuable time for the arrival of professional medical forces.

[0023] In related technologies, data backhaul typically relies on a single-link communication architecture. This means that all data streams collected by the UAV, including video streams, audio streams, device status, and control commands, are transmitted through a single communication link, enabling information exchange between the UAV and the remote command center. However, this approach fails to rationally allocate and optimize link resources based on the differentiated communication needs of each UAV. This leads to mutual interference and congestion when different UAVs compete for the same communication link, severely limiting the communication efficiency of UAV-assisted emergency rescue and hindering the clinical effectiveness and reliability of UAV-assisted emergency rescue systems in actual pre-hospital care.

[0024] In view of this, this application provides an AED drone emergency rescue communication method, device, and program product. This solution uses communication indicators such as transmission latency, packet loss rate, and link load of each drone data stream as multi-dimensional constraints. Through the global optimization capability of a genetic algorithm, appropriate link resources are dynamically allocated to each drone data stream, thereby realizing efficient communication interaction between the drone end and the remote command end. In this way, link resources can be dynamically adjusted according to the real-time communication needs and real-time communication status of the emergency rescue mission, thereby effectively improving the communication efficiency of drone emergency rescue and ensuring the clinical efficacy and reliability of the drone-assisted emergency rescue system in actual pre-hospital rescue.

[0025] First, the implementation steps of an AED drone emergency rescue communication method provided in this application embodiment will be described in detail below with reference to the accompanying drawings.

[0026] This application provides an AED drone emergency rescue communication method, which can be applied to a terminal, a server, or software running on either a terminal or a server. The terminal can be a tablet, laptop, desktop computer, etc., but is not limited to these. The server can be an independent physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing basic cloud computing services such as cloud services, cloud databases, cloud computing, cloud functions, cloud storage, network services, cloud communication, middleware services, domain name services, security services, content delivery networks (CDN), and big data and artificial intelligence platforms. Additionally, the server can be a node server in a blockchain network, but is not limited to these. Blockchain is a new application model of computer technologies such as distributed data storage, peer-to-peer transmission, consensus mechanisms, and encryption algorithms.

[0027] Reference Figure 1 , Figure 1 This is a flowchart of an AED drone emergency rescue communication method provided in this application, which may include the following steps S101-S103.

[0028] S101, acquire rescue-related data sent by multiple AED drones; the rescue-related data includes multiple data streams.

[0029] It should be noted that "AED drone" refers to a drone equipped with an AED. The AED drone communicates with the entity executing this method, which in turn communicates with a remote monitoring device. Furthermore, "rescue-related data" refers to data collected by the AED drone and associated with the rescue scene. This data can include multiple data streams, such as patient physiological data streams, rescue scene status data streams, and AED device data streams.

[0030] In this step, each AED drone collects rescue-related data and sends it to the entity executing this method. The entity executing this method receives the rescue-related data sent by multiple AED drones, so that appropriate link resources can be allocated to each AED drone based on the differentiated communication needs of this data in subsequent processing.

[0031] S102, optimize the rescue-related data of each AED drone to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each AED drone.

[0032] In this step, the execution entity of this method uses communication indicators such as transmission delay, packet loss rate and link load of each UAV data stream as multi-dimensional constraints. It uses the global optimization capability of the genetic algorithm combined with the rescue-related data of each AED UAV to perform optimization processing, dynamically allocate appropriate link resources for each AED UAV data stream, thereby obtaining the optimal communication scheme. This scheme may include, but is not limited to, the optimal communication link of each data stream in each AED UAV.

[0033] S103, according to the optimal communication scheme, sends the rescue-related data of each AED drone to the remote command terminal, so that the remote command terminal can render and display the rescue-related data of each AED drone.

[0034] In this step, the executing entity of this method sends the rescue-related data of each AED drone to the remote command terminal according to the optimal communication scheme. During this process, each data stream is transmitted to the remote command terminal through the corresponding optimal communication link. The remote command terminal receives the rescue-related data of each AED drone and renders and displays it, so that the rescue-related data of each AED drone is displayed on the remote command terminal's screen. In this case, the emergency dispatcher can issue rescue command instructions, such as "Please attach the electrode pads to the patient's right subclavian and left chest side." This instruction is transmitted from the remote command terminal to the executing entity of this method through any communication link, and then forwarded by the executing entity to the designated AED drone. The AED drone's speaker plays the instruction, thereby guiding the rescue personnel at the scene to perform rescue operations, such as CPR. The input method of the rescue command instructions can be flexibly set according to the actual situation. For example, the rescue command instructions can be input by voice or by other methods such as text, but are not limited to these. Furthermore, the communication link for sending rescue command instructions can be flexibly configured according to the actual situation. For example, considering the low latency communication requirement of rescue command instructions, they can be transmitted to the drone via a mobile private network link with the lowest latency, but this is not a limitation. Moreover, the remote command terminal can be an Emergency Medical Service System (EMSS) center, or an ambulance, a nearby hospital, etc., but this is not a limitation.

[0035] Therefore, this application embodiment uses communication indicators such as transmission latency, packet loss rate, and link load of each UAV data stream as multi-dimensional constraints. Through the global optimization capability of the genetic algorithm, appropriate link resources are dynamically allocated to each UAV data stream, thereby realizing efficient communication interaction between the UAV end and the remote command end. In this way, the link resources can be dynamically adjusted according to the real-time communication needs and real-time communication status of the emergency rescue mission, thereby effectively improving the communication efficiency of UAV emergency rescue and ensuring the clinical efficacy and reliability of the UAV-assisted emergency rescue system in actual pre-hospital rescue.

[0036] The steps described above will be explained in further detail below.

[0037] In some implementations, refer to Figure 2 The above-mentioned optimization processing of rescue-related data from each AED drone to obtain the optimal communication scheme may include: Each AED drone, each data stream, and each communication link is encoded and initialized to obtain an initial population as the parent population. The population consists of multiple individuals, each individual consists of multiple gene bits, each gene bit corresponds one-to-one with each data stream, and each gene bit represents the communication link allocated to the data stream. The parent population is selected based on the fitness values ​​of each individual in the parent population to obtain the selected population. The selected population is subjected to mutation and crossover processes to obtain the offspring population; If the current iteration count has not reached the maximum iteration count, the offspring population is determined as the new parent population, the current iteration count is incremented by one, and the process returns to the step of selecting the parent population based on the fitness values ​​of each individual in the parent population. Otherwise, the individual with the highest fitness value in the offspring population is decoded to obtain the optimal communication scheme.

[0038] It should be noted that individuals in the parent population are defined as parent individuals, individuals in the selection population are defined as selection individuals, and individuals in the offspring population are defined as offspring individuals.

[0039] In this embodiment, each AED drone, each data stream, and each communication link is encoded and initialized to obtain an initial population as the parent population. The population may include, but is not limited to, multiple individuals, each representing a chromosome. Each individual may include, but is not limited to, multiple gene loci, each gene locus corresponding one-to-one with each data stream, and each gene locus representing the communication link assigned to the data stream. Simply put, one individual represents one communication scheme, and each communication scheme may include, but is not limited to, the communication links of each data stream within each drone. After determining the parent population, the fitness value of each parent individual is calculated, and a selection operation is performed accordingly. This aims to select parent individuals probabilistically for subsequent crossover and mutation operations, resulting in a selected population. Subsequently, the selected individuals in this population undergo mutation and crossover to obtain the offspring population. Finally, it is determined whether the current iteration count has reached the maximum. If so, the iteration is complete, and the offspring individual with the highest fitness value in the offspring population is decoded; this decoded offspring individual represents the optimal communication solution. Otherwise, the iteration is not yet complete, and the offspring population is designated as the new parent population. The current iteration count is incremented, and the selection operation is returned to perform iterative optimization. The maximum number of iterations can be flexibly set according to the actual situation; for example, it could be 150 iterations, but it is not limited to this. Furthermore, in some examples, an elite retention strategy can be introduced. After each generation of evolution, the individuals with the highest fitness in the current population are saved as elite individuals, and the individuals with the lowest fitness in the next generation are replaced with elite individuals, thus ensuring that the optimal solution in each generation is not destroyed by crossover and mutation.

[0040] In some implementations, the above-described encoding and population initialization processing of each AED drone, each data stream, and each communication link to obtain an initial population as the parent population may include: A flattened integer encoding method is used to encode and initialize each AED drone, each data stream, and each communication link to obtain an initial population as the parent population.

[0041] In this embodiment, the AED drone ensemble is defined as , Indicates the number of AED drones, the first The maximum number of parallel links for a single AED drone is [value]. , No. The number of data streams from each AED drone is The sum of the data streams from all AED drones is , No. The first AED drone A data stream is represented as Data Stream The bandwidth requirement is Meanwhile, the communication link set is defined as... , Indicates the number of communication links, the first The available bandwidth of the communication links is , No. The transmission delay of the communication link is , No. The packet loss rate of the communication link Based on this, a flattened integer encoding method is adopted, that is, each individual is encoded as an array, represented as... The array indices are mapped to globally unique data stream numbers and ordered sequentially, which means that the indices... This represents the number of the communication link assigned to the data stream. Multiple chromosomes are randomly generated using a greedy algorithm; each chromosome represents an individual. Each gene locus in the chromosome is randomly and uniformly selected from all available links, thus forming an initial population as the parent population, thereby realizing individual encoding and population initialization.

[0042] In some implementations, the selection process of the parent population based on the fitness values ​​of each individual in the parent population to obtain the selected population may include: Based on the fitness values ​​of each individual in the parent population, and using a roulette wheel selection method, the parent population is selected to obtain the selected population.

[0043] In this embodiment, a fitness function is pre-constructed, which uses communication metrics such as transmission latency, packet loss rate, and link load of each UAV data stream as multi-dimensional constraints. During the selection operation, the fitness value of each parent individual in the parent population is first calculated based on the pre-constructed fitness function. Then, a roulette wheel operation is performed based on the calculated fitness values ​​to calculate the probability of each parent individual being selected and to select suitable parent individuals for subsequent crossover and mutation operations, thereby obtaining the selected population and thus realizing the selection operation.

[0044] In some implementations, the above-described mutation and crossover processes on the selected population to obtain the offspring population may include: Perform a two-point crossover process on the selected population to obtain the crossover population; The crossover population is subjected to site mutation processing to obtain a variant population, which is then used as the offspring population.

[0045] It should be noted that individuals in the crossover population are defined as crossover individuals, while individuals in the variant population are defined as variant individuals, and variant individuals are offspring individuals.

[0046] In this embodiment, during the crossover and mutation operation, firstly, two-point crossover is performed on the selected individuals in the selected population. That is, based on a preset crossover probability, two selected individuals are randomly selected from the selected population, and two crossover points are randomly generated. The gene segments of the two selected individuals between the two crossover points are exchanged, generating two crossover individuals. Multiple crossover operations can be performed to obtain multiple crossover individuals, thus forming a crossover population. Next, site mutation processing is performed on the crossover individuals in the crossover population. That is, based on a preset mutation probability, each gene position of each crossover individual in the crossover population is traversed, and the gene position that triggers mutation is determined as the gene position to be mutated. For each gene position to be mutated, the gene position to be mutated is replaced with any gene position other than the gene position to be mutated, thereby generating a mutated individual. Multiple mutation operations can be performed to obtain multiple mutated individuals, thus forming a mutated population, i.e., a progeny population, thereby realizing the crossover and mutation operations. The crossover probability and mutation probability can be flexibly set according to the actual situation. For example, the crossover probability can be 0.8 and the mutation probability can be 0.1, but it is not limited to these.

[0047] In some implementations, the steps for calculating the fitness value of the aforementioned individual may include: The global average latency, global average packet loss rate, and link load balancing variance of all communication links are calculated for the target individual to obtain the communication overhead value of the target individual. Calculate the bandwidth overload penalty value and the link number overload penalty value for the target individual to obtain the communication penalty value of the target individual; The fitness value of the target individual is obtained based on its communication overhead and communication penalty values. Here, the target individual refers to any single individual.

[0048] In this embodiment, any individual is defined as the target individual. The fitness value of the target individual consists of the communication overhead value and the communication penalty value, as detailed below: The global average latency, global average packet loss rate, and link load balancing variance of all communication links for the target individual are calculated to obtain the communication overhead value of the target individual, as shown in the following formula (1):

[0049] , (1); In equation (1), Indicates the communication overhead value; This represents the sum of the number of data streams from all AED drones. Indicates the number of AED drones. Indicates the first Number of data streams from each AED drone; Indicates an indicator function, when Data stream The communication link is the first When there is a communication link The value is one, otherwise It is zero; Indicates the first Transmission delay of the communication link; Indicates the first Packet loss rate of each communication link; Indicates the first The total bandwidth load of the communication links; Indicates the number of communication links; Indicates the first The available bandwidth of each communication link; , and These are all preset weight values, which can be flexibly set according to the actual situation; Represents data stream The bandwidth requirements.

[0050] It is worth noting that in equation (1), the first term represents the global average delay value, that is, the transmission delay of all communication links; the second term represents the global average packet loss rate, that is, the packet loss of all communication links; the third term represents the link load balancing variance value, that is, the load balancing degree between different communication links; the three together constitute the communication overhead value, with the goal of minimizing the global average delay, the global average packet loss rate and the load imbalance between links.

[0051] Simultaneously, the bandwidth overload penalty value and the link number overload penalty value are calculated for the target individual to obtain the communication penalty value of the target individual, as shown in the following formula (2): , (2); In equation (2), Indicates the communication penalty value; It represents a very large positive number, used to suppress illegal individuals; Indicates the first Available bandwidth of each communication link; Indicates the first Is the AED drone connected to the first...? A communication link, when For one time, it means the first At least one data stream from each AED drone is in use. A communication link, when When it is zero, it means the first All data streams from the AED drone did not use the first... One communication link; Indicates the first The maximum number of communication links that an AED drone can simultaneously connect to, i.e., the number of... The communication module of each AED drone can connect to a maximum of [number] devices simultaneously. One communication link.

[0052] It is worth noting that in equation (2), the first term represents the processing bandwidth overload penalty value, that is, the load of any communication link cannot exceed its available bandwidth; the second term represents the link number overload penalty value, that is, the number of communication links connected to a single UAV cannot exceed its hardware limit; the two together constitute the communication penalty value, which is intended to impose a huge penalty on individuals that violate physical restrictions, thereby reducing their fitness value.

[0053] The fitness value can then be obtained as shown in formula (3): (3); In equation (3), This represents the fitness value. The formula aims to transform the minimization objective into maximizing fitness, with the fitness value ranging from [0, 1]. The fitness value for all individuals can be calculated using this formula.

[0054] In some implementations, the above-mentioned transmission of rescue-related data from each AED drone to a remote command terminal according to an optimal communication scheme may include: Each data stream is backed up to obtain backup data for each data stream; Each data stream and its backup data are encrypted separately to obtain the original encrypted data and the backup encrypted data for each data stream. The original encrypted data of each data stream is sent to the remote command terminal according to the optimal communication scheme, and the backup encrypted data of each data stream is sent to the remote command terminal through the preset communication link.

[0055] In this embodiment, after determining the optimal communication scheme, the execution entity of this method first performs copy backup processing on each data stream to obtain backup data for each data stream. Then, each data stream and its backup data are packetized in the sending buffer to obtain the original data packets and backup data packets for each data stream. An Advanced Encryption Standard (AES) 256 encryption header is added when the data packets are encapsulated to obtain the original encrypted data and backup encrypted data for each data stream. Finally, using Virtual Private Network (VPN) technology and the operator's Access Point Name (APN) private network, combined with the optimal communication scheme, the original encrypted data of each data stream is sent to the remote command terminal. At the same time, the backup encrypted data of each data stream is sent to the remote command terminal through a preset communication link.

[0056] The remote command terminal receives backup encrypted data from each data stream and determines whether the original encrypted data of each data stream has been received. If so, the backup encrypted data of each data stream is discarded, and the original encrypted data of each data stream is determined as the target encrypted data of each data stream. Otherwise, the backup encrypted data of each data stream is retained as the target encrypted data of each data stream. Subsequently, the target encrypted data of each data stream is decrypted using the corresponding decryption algorithm to obtain the decrypted data packets of each data stream. Based on the sequence number, timestamp, and other information in the decrypted data packets, algorithms such as delay algorithms and sorting algorithms are used to reassemble and shape the out-of-order decrypted data packets to obtain the complete data packets of each data stream, thereby restoring the complete and timely data stream and displaying it on the display screen.

[0057] Here, on the one hand, a secure transmission strategy employing packet segmentation and link segmentation, AES encryption, and VPN / APN private networks ensures that the data stream is segmented and encrypted during transmission. Even if a single link is intercepted, the complete data stream cannot be recovered, thus effectively enhancing data transmission security and preventing medical privacy leaks. On the other hand, a redundant backup strategy effectively combats sudden interruptions and high packet loss rates in communication links, ensuring uninterrupted data transmission. Furthermore, communication is based on an optimal communication scheme, ensuring that the allocation of link resources meets the real-time communication needs and status of emergency rescue missions, thereby improving the communication efficiency of UAV emergency rescue. In this way, an optimal engineering balance can be achieved between reliability improvement and bandwidth consumption, comprehensively guaranteeing the security, real-time performance, and stability of data transmission in emergency rescue scenarios.

[0058] In some implementations, the aforementioned rescue-related data may include: Video data streams, including video data from the rescue site; Voice data stream, including audio data from the rescue site; Vital signs data stream, including physiological data of the target object at the rescue site; AED data stream, including defibrillation operation data from the AED device.

[0059] It should be noted that the target object refers to the user object of data collection, and the rescue site refers to the location of emergency rescue.

[0060] In this embodiment, the AED drone is equipped with components such as an AED device, a vital signs monitor, and a high-definition camera and audio acquisition unit. During real-time data acquisition, the AED drone collects AED data streams through the AED device, such as defibrillation operation data; it collects vital signs data streams of the target object, such as heart rate, respiration, and blood oxygen saturation, through the vital signs monitor; and it collects video and audio data streams from the rescue scene through the high-definition camera and audio acquisition unit. This is how data acquisition is achieved.

[0061] To facilitate understanding of the AED drone emergency rescue communication method described in this application, an example of its actual application scenario is provided below.

[0062] This application scenario involves a multi-vehicle collision rescue scene. The execution of this method is cloud-based, with each AED drone equipped with an AED device, vital signs monitor, high-definition camera and audio acquisition unit, embedded processor, and communication module. The AED device is used to defibrillate patients experiencing cardiac arrest; the vital signs monitor collects real-time physiological data such as heart rate, respiration, and blood oxygen saturation; the high-definition camera and audio acquisition unit collects video and audio data from the rescue scene; the embedded processor converts the collected analog signal data stream into a digital signal data stream; and the communication module integrates a multi-link communication module, supporting 4G / 5G, broadband, VPN / APN private networks, etc., and is used to transmit the collected data stream to the cloud. During communication, each AED drone connects to the cloud via the lowest latency mobile private network link, and the cloud connects to the remote command center via multiple available communication links. The remote command center is the EMSS center.

[0063] Reference Figure 3 The process of implementing emergency rescue communication using this method is shown in steps S201-S205 below.

[0064] S201. Each AED drone arrives at the rescue site, collects data, and sends the relevant data to the cloud. This rescue-related data includes video streams, audio streams, vital signs streams, and AED data streams. The video streams include video data from the rescue site; the audio streams include audio data from the rescue site; the vital signs streams include physiological data of the target at the rescue site; and the AED data streams include defibrillation operation data from the AED devices.

[0065] In S202, the cloud first receives rescue-related data from each AED drone and parses the data streams to identify their application types, such as video streams, audio streams, AED data streams, and vital signs data streams. Then, it classifies and labels the data streams based on their characteristics (e.g., video streams require high bandwidth, AED data streams require low latency, and vital signs data streams require low packet loss rate). A genetic algorithm is then invoked to comprehensively evaluate parameters such as latency, bandwidth, and packet loss rate of multiple available communication links and optimize them accordingly. This dynamically allocates suitable link resources to each AED drone data stream, resulting in the optimal communication scheme. This scheme may include, but is not limited to, the optimal communication link for each data stream within each AED drone. Next, each data stream is backed up to obtain backup data. The data streams and their backup data are then packetized in the sending buffer to obtain the original data packets and backup data packets for each data stream. AES is added during data packet encapsulation. The 256-bit encrypted header is used to obtain the original encrypted data and backup encrypted data of each data stream. Finally, using VPN technology and APN private network, combined with the optimal communication scheme, the original encrypted data of each data stream is sent to the remote command terminal, and the backup encrypted data of each data stream is sent to the remote command terminal through the preset communication link.

[0066] S203, the remote command terminal first receives the backup encrypted data of each data stream and determines whether the original encrypted data of each data stream has been received. If so, the backup encrypted data of each data stream is discarded, and the original encrypted data of each data stream is determined as the target encrypted data of each data stream. Otherwise, the backup encrypted data of each data stream is retained as the target encrypted data of each data stream. Then, the target encrypted data of each data stream is decrypted using the corresponding decryption algorithm to obtain the decrypted data packets of each data stream. Based on the sequence number, timestamp, and other information in the decrypted data packets, algorithms such as delay algorithms and sorting algorithms are used to reassemble and shape the out-of-order decrypted data packets to obtain the complete data packets of each data stream, thereby restoring the complete and timely data stream and displaying it on the display screen.

[0067] S204: The remote command terminal generates rescue command instructions, which are then packetized, encrypted, and transmitted to the cloud via the lowest latency mobile private network link. The cloud then forwards these instructions to the designated drone terminal.

[0068] The S205 drone uses a loudspeaker to broadcast rescue command instructions, thereby guiding personnel at the rescue site to carry out rescue operations.

[0069] Through the above process, stable, low-latency, and highly secure emergency rescue communication can be achieved.

[0070] In addition, refer to Figure 4This application also provides an AED drone emergency rescue communication device that can implement the above-mentioned method. The device includes: The acquisition module 301 is used to acquire rescue-related data sent by multiple AED drones; the rescue-related data includes multiple data streams. The first processing module 302 is used to perform optimization processing on the rescue-related data of each AED drone to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each AED drone; The second processing module 303 is used to send the rescue-related data of each AED drone to the remote command terminal according to the optimal communication scheme, so that the remote command terminal can render and display the rescue-related data of each AED drone.

[0071] The content of the above method embodiments is applicable to the device embodiments. The specific functions implemented by the device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0072] Finally, this application also provides a computer program product, including a computer program that, when executed by a processor, implements the above-described AED drone emergency rescue communication method.

[0073] The content of the above method embodiments is applicable to the embodiments of this program product. The specific functions implemented by the embodiments of this program product are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0074] In summary, on the one hand, the embodiments of this application use communication indicators such as transmission latency, packet loss rate, and link load of each UAV data stream as multi-dimensional constraints. Through the global optimization capability of the genetic algorithm, appropriate link resources are dynamically allocated to each UAV data stream, thereby achieving efficient communication interaction between the UAV end and the remote command end. In this way, link resources can be dynamically adjusted according to the real-time communication needs and real-time communication status of emergency rescue missions, maximizing the utilization of link resources of multiple communication links and meeting the needs of concurrent transmission of multiple data streams. This effectively improves the communication efficiency of UAV emergency rescue and ensures the clinical efficacy and reliability of the UAV-assisted emergency rescue system in actual pre-hospital rescue. On the other hand, the secure transmission strategy of packet segmentation and link segmentation, AES encryption, and VPN / APN private network is adopted during transmission. This ensures that the data stream is segmented and encrypted during transmission. Even if a single link is monitored, the complete data stream cannot be restored, thereby effectively enhancing the security of data transmission and preventing the leakage of medical privacy. Furthermore, the redundant backup strategy adopted during transmission can effectively combat sudden interruptions and high packet loss rates of communication links, ensuring uninterrupted transmission of data streams. In summary, the embodiments of this application achieve the best engineering balance between reliability improvement and bandwidth overhead, comprehensively ensuring the security, real-time performance and stability of data transmission in emergency rescue scenarios.

[0075] The embodiments described in this application are for the purpose of more clearly illustrating the technical solutions of the embodiments of this application, and do not constitute a limitation on the technical solutions provided by the embodiments of this application. As those skilled in the art will know, with the evolution of technology and the emergence of new application scenarios, the technical solutions provided by the embodiments of this application are also applicable to similar technical problems.

[0076] Those skilled in the art will understand that the technical solutions shown in the figures do not constitute a limitation on the embodiments of this application, and may include more or fewer steps than shown, or combine certain steps, or different steps.

[0077] The device embodiments described above are merely illustrative. The units described as separate components may or may not be physically separate; that is, they may be located in one place or distributed across multiple network units. Some or all of the modules can be selected to achieve the purpose of this embodiment according to actual needs.

[0078] Those skilled in the art will understand that all or some of the steps in the methods disclosed above, as well as the functional modules / units in the systems and devices, can be implemented as software, firmware, hardware, or suitable combinations thereof.

[0079] The terms “first,” “second,” “third,” “fourth,” etc. (if present) in the specification and accompanying drawings of this application are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence. It should be understood that such data can be interchanged where appropriate so that the embodiments of this application described herein can be implemented in orders other than those illustrated or described herein. Furthermore, the terms “comprising” and “having,” and any variations thereof, are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or apparatus that comprises a series of steps or units is not necessarily limited to those steps or units explicitly listed, but may include other steps or units not explicitly listed or inherent to such processes, methods, products, or apparatus.

[0080] It should be understood that in this application, "at least one (item)" means one or more, and "more than" means two or more. "And / or" is used to describe the relationship between related objects, indicating that three relationships can exist. For example, "A and / or B" can represent three cases: only A exists, only B exists, and both A and B exist simultaneously, where A and B can be singular or plural. The character " / " generally indicates that the preceding and following related objects are in an "or" relationship. "At least one (item) of the following" or similar expressions refer to any combination of these items, including any combination of single or plural items. For example, at least one (item) of a, b, or c can represent: a, b, c, "a and b", "a and c", "b and c", or "a and b and c", where a, b, and c can be single or multiple.

[0081] In the several embodiments provided in this application, it should be understood that the disclosed apparatus and methods can be implemented in other ways. For example, the apparatus embodiments described above are merely illustrative; for instance, the division of the units described above is only a logical functional division, and in actual implementation, there may be other division methods. For example, multiple units or components may be combined or integrated into another system, or some features may be ignored or not executed. Furthermore, the coupling or direct coupling or communication connection shown or discussed may be through some interfaces; the indirect coupling or communication connection between apparatuses or units may be electrical, mechanical, or other forms.

[0082] The units described above as separate components may or may not be physically separate. The components shown as units may or may not be physical units; that is, they may be located in one place or distributed across multiple network units. Some or all of the units can be selected to achieve the purpose of this embodiment according to actual needs.

[0083] Furthermore, the functional units in the various embodiments of this application can be integrated into one processing unit, or each unit can exist physically separately, or two or more units can be integrated into one unit. The integrated unit can be implemented in hardware or as a software functional unit.

[0084] If the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of this application, in essence, or the part that contributes to the prior art, or all or part of the technical solution, can be embodied in the form of a software product. This computer software product is stored in a storage medium and includes multiple instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute all or part of the steps of the methods of the various embodiments of this application. The aforementioned storage medium includes various media capable of storing programs, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0085] The preferred embodiments of the present application have been described above with reference to the accompanying drawings, but this does not limit the scope of the claims of the present application. Any modifications, equivalent substitutions, and improvements made by those skilled in the art without departing from the scope and substance of the embodiments of the present application shall be within the scope of the claims of the present application.

Claims

1. An emergency rescue communication method for AED drones, characterized in that, The method includes: Acquire rescue-related data transmitted by multiple AED drones; wherein, the rescue-related data includes multiple data streams; The rescue-related data of each AED drone are optimized to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each AED drone; According to the optimal communication scheme, the rescue-related data of each AED drone is sent to the remote command terminal, so that the remote command terminal can render and display the rescue-related data of each AED drone.

2. The method according to claim 1, characterized in that, The optimization process for obtaining the optimal communication scheme by optimizing the rescue-related data of each AED drone includes: Each of the AED drones, each of the data streams, and each of the communication links are encoded and initialized to obtain an initial population as the parent population; wherein, the population includes multiple individuals, each individual includes multiple gene bits, each gene bit corresponds one-to-one with each of the data streams, and each gene bit represents the communication link allocated to the data stream; The parent population is selected based on the fitness values ​​of each individual in the parent population to obtain the selected population. The selected population is subjected to mutation and crossover processes to obtain the offspring population; If the current iteration count has not reached the maximum iteration count, the offspring population is determined as the new parent population, the current iteration count is incremented by one, and the process returns to the step of selecting the parent population based on the fitness values ​​of each individual in the parent population. Otherwise, the individual with the highest fitness value in the offspring population is decoded to obtain the optimal communication scheme.

3. The method according to claim 2, characterized in that, The process of encoding and initializing each of the AED drones, each of the data streams, and each of the communication links to obtain an initial population as the parent population includes: A flattened integer encoding method is used to encode and initialize each of the AED drones, each of the data streams, and each of the communication links to obtain the initial population as the parent population.

4. The method according to claim 2, characterized in that, The selection process based on the fitness values ​​of each individual in the parent population to obtain the selected population includes: Based on the fitness values ​​of each individual in the parent population, and using a roulette wheel selection method, the parent population is selected to obtain the selected population.

5. The method according to claim 2, characterized in that, The process of performing mutation and crossover on the selected population to obtain the offspring population includes: Perform a two-point crossover process on the selected population to obtain a crossover population; The crossover population is subjected to site mutation processing to obtain a variant population, which is then used as the offspring population.

6. The method according to claim 2, characterized in that, The steps for calculating the fitness value of the individual include: The global average latency, global average packet loss rate, and link load balancing variance of all communication links are calculated for the target individual to obtain the communication overhead value of the target individual. The bandwidth overload penalty value and the link number overload penalty value are calculated for the target individual to obtain the communication penalty value of the target individual; The fitness value of the target individual is obtained based on its communication overhead and communication penalty values. Wherein, the target individual refers to any one of the individuals.

7. The method according to claim 1, characterized in that, The step of sending rescue-related data from each of the AED drones to the remote command terminal according to the optimal communication scheme includes: Each of the data streams is backed up to obtain backup data for each of the data streams; Each data stream and its backup data are encrypted separately to obtain the original encrypted data and the backup encrypted data of each data stream. According to the optimal communication scheme, the original encrypted data of each data stream is sent to the remote command terminal, and the backup encrypted data of each data stream is sent to the remote command terminal through a preset communication link.

8. The method according to any one of claims 1-7, characterized in that, The rescue-related data includes: Video data streams, including video data from the rescue site; Voice data stream, including audio data from the rescue site; Vital signs data stream, including physiological data of the target object at the rescue site; AED data stream, including defibrillation operation data from the AED device.

9. An AED drone emergency rescue communication device, characterized in that, The device includes: The acquisition module is used to acquire rescue-related data sent by multiple AED drones; wherein the rescue-related data includes multiple data streams; The first processing module is used to perform optimization processing on the rescue-related data of each of the AED drones to obtain the optimal communication scheme; wherein, the optimal communication scheme includes the optimal communication link of each data stream in each of the AED drones; The second processing module is used to send the rescue-related data of each of the AED drones to the remote command terminal according to the optimal communication scheme, so that the remote command terminal can render and display the rescue-related data of each of the AED drones.

10. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by the processor, it implements the AED drone emergency rescue communication method as described in any one of claims 1 to 8.

Images