A medical material distribution method and system based on a marine medical rescue unmanned aerial vehicle

Abstract

The application provides a medical material distribution method and system based on a marine medical rescue unmanned aerial vehicle. A marine environment model is generated; according to the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priority and urgency of the marine receiving point, and an optimized task sequence and material loading scheme are obtained; a cooperative communication mechanism between the formations of marine medical rescue unmanned aerial vehicles is established through an AI-driven distributed consensus algorithm, and an AI path planning technology is used in combination with real-time situation awareness and obstacle detection analysis to dynamically adjust the flight path and generate a distribution path; after arriving at the designated receiving point, the landing coordinates are automatically calibrated and processed, and the material state, handover information and environmental data are synchronized to the medical team and the central dispatching system through a low-delay wireless transmission mode according to the distribution path. The technical scheme provided by the application greatly improves the efficiency and reliability of marine material distribution.

Description

Technical Field

[0001] This application relates to the field of material distribution technology, and in particular to a method and system for medical material distribution based on a maritime medical rescue drone. Background Technology

[0002] Maritime medical rescue missions typically take place in remote, high-altitude environments, often characterized by severe weather and unstable sea conditions. In such environments, the rapid and accurate delivery of supplies to designated locations is crucial. Maritime rescue operations require highly precise environmental awareness, efficient resource allocation mechanisms, and safe and reliable delivery route planning to ensure timely and effective delivery of supplies.

[0003] Currently, maritime medical rescue mainly relies on traditional helicopters or ships for transporting supplies. While these methods are reliable, they suffer from slow response times and are highly dependent on weather and sea conditions. In recent years, with the development of drone technology, some initial attempts have been made to use drones for supply delivery. However, these solutions often lack a comprehensive understanding of the complex marine environment, have insufficiently precise resource allocation, and struggle to achieve efficient collaborative communication between fleets.

[0004] Existing solutions lack sufficient environmental awareness and real-time adaptability when facing dynamically changing marine environments, resulting in inflexible mission planning. Furthermore, in situations with multiple receiving points, they fail to fully consider the specific needs, priorities, and urgency of each point, leading to unreasonable resource allocation and impacting overall rescue efficiency. In addition, the lack of an effective inter-formation collaborative communication mechanism results in insufficient information sharing among drones, increasing flight risks and reducing the safety and orderliness of delivery. Summary of the Invention

[0005] This application provides a method and system for medical supply delivery based on a maritime medical rescue drone, in order to solve the problems of unreasonable resource allocation and low flight safety in the prior art.

[0006] In a first aspect, embodiments of this application provide a method for delivering medical supplies based on a maritime medical rescue drone, including:

[0007] By utilizing a comprehensive perception system integrated into a maritime medical rescue drone and combining it with an AI environmental prediction model, multi-source environmental information is acquired and fused in real time to generate a marine environment model.

[0008] Based on the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the receiving points at sea. At the same time, based on the knapsack problem analysis technique in operations research, the resource allocation is finely planned to obtain an optimized task sequence and material loading scheme.

[0009] Based on the optimized task sequence and material loading plan, a collaborative communication mechanism among the maritime medical rescue drone formations is established through an AI-driven distributed consensus algorithm to ensure real-time information sharing. Furthermore, AI path planning technology is used in conjunction with real-time situational awareness and obstacle detection analysis to dynamically adjust the flight path and generate delivery routes.

[0010] Upon arrival at the designated receiving point, the landing coordinates are automatically calibrated, and based on the delivery route, the status of the supplies, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information.

[0011] Optionally, based on the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the maritime receiving points. Simultaneously, based on the knapsack problem analysis technique in operations research, resource allocation is finely planned to obtain an optimized task sequence and material loading scheme, including:

[0012] Using the marine environment model, the location, sea conditions, weather forecast, and time window of each marine receiving point are comprehensively evaluated to obtain a score of mission importance and urgency.

[0013] Based on the task importance and urgency scores, and combined with the AI ​​scheduling algorithm to simulate the behavior pattern of a multi-agent system, the needs of each receiving point are dynamically evaluated and processed to generate a task requirement matrix, which reflects the task priority.

[0014] Based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drone and the types and quantities of materials. The resource allocation strategy is optimized to generate a preliminary material loading plan.

[0015] Using the preliminary material loading plan, and combining it with AI scheduling algorithms, the mission sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized mission sequence and material loading plan.

[0016] Optionally, based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drone and the types and quantities of supplies, and the resource allocation strategy is optimized to generate a preliminary supply loading plan, including:

[0017] Using the aforementioned task requirement matrix, the urgency of tasks and the amount of materials required at each maritime receiving point are quantitatively analyzed and processed to obtain a requirement feature vector reflecting the demand characteristics of each receiving point.

[0018] Based on the aforementioned demand feature vector, and combined with the maximum payload capacity and effective payload volume of the maritime medical rescue drone, the knapsack problem model is applied to optimize the combination of different types and quantities of materials, generating multiple candidate loading schemes that meet the load constraints.

[0019] Based on the candidate loading schemes, considering the importance and urgency of each material, a priority weighting factor is introduced to evaluate the comprehensive benefits of each candidate scheme, resulting in an optimized loading benefit score.

[0020] By utilizing the optimized loading efficiency score, we can ensure that delivery efficiency and task completion are maximized under limited load conditions, and generate a preliminary material loading plan.

[0021] Optionally, by utilizing the initial material loading plan and combining it with an AI scheduling algorithm, the task sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized task sequence and material loading plan, including:

[0022] Using the aforementioned preliminary material loading plan, a comprehensive analysis and processing of the payload configuration and expected flight path of each maritime medical rescue drone is conducted to generate an initial task allocation table;

[0023] Based on the initial task allocation table, and combined with the AI ​​scheduling algorithm to simulate the behavior pattern of a multi-agent system, the task execution order of each maritime medical rescue drone is dynamically evaluated. Considering the dependencies between tasks and time window constraints, a task execution sequence reflecting task priority is obtained.

[0024] Based on the task execution sequence, a complexity analysis method is introduced to evaluate the time synchronization requirements and collaborative operation needs between different tasks, optimize the connection between tasks, ensure that high-priority tasks can be completed in a timely manner, and generate an optimized task sequence.

[0025] Using the optimized mission sequence, combined with the maximum endurance of the maritime medical rescue drone and real-time sea state data, the material loading plan is fine-tuned to ensure that the delivery efficiency of a single flight is maximized while meeting all mission requirements, resulting in an optimized mission sequence and material loading plan.

[0026] Optionally, based on the optimized task sequence and material loading plan, a collaborative communication mechanism is established among the maritime medical rescue drone formations through an AI-driven distributed consensus algorithm to ensure real-time information sharing. Furthermore, AI path planning technology, combined with real-time situational awareness and obstacle detection analysis, is used to dynamically adjust the flight path and generate a delivery route, including:

[0027] Using the optimized task sequence and material loading scheme, the task allocation and flight plan of each maritime medical rescue UAV are analyzed in detail to obtain precise task execution instructions.

[0028] According to the task execution instructions, an AI-driven distributed consensus algorithm is used to establish a collaborative communication mechanism among the maritime medical rescue drone formations, ensuring that each maritime medical rescue drone can share its location and status in real time and generate an instant communication network.

[0029] Based on the aforementioned instant communication network, data from the real-time situational awareness system and obstacle detection sensors are integrated to monitor and process potential risks in the flight environment, thereby obtaining an environmental risk assessment report.

[0030] Using the aforementioned environmental risk assessment report and combined with AI path planning technology, the current flight path is dynamically adjusted to ensure that obstacles are avoided and the optimal path is selected, ultimately generating a delivery path.

[0031] Optionally, the step of using the environmental risk assessment report, combined with AI path planning technology, to dynamically adjust the current flight path to ensure obstacle avoidance and select the optimal path, ultimately generating a delivery path, includes:

[0032] Using the aforementioned environmental risk assessment report, potential obstacles and risk areas in the flight environment are identified and processed to obtain an obstacle distribution map;

[0033] Based on the obstacle distribution map and combined with real-time sea conditions and meteorological data, the existing flight path is recalculated using an AI path planning algorithm to obtain multiple candidate obstacle avoidance paths.

[0034] Based on the multiple candidate obstacle avoidance paths, the shortest path algorithm and weighted scoring mechanism in graph theory are introduced. Taking into account path length, flight time and risk coefficient, each candidate path is comprehensively evaluated to obtain the optimized path score.

[0035] Using the optimized path score, the path with the highest score is selected as the final flight path. The path is then fine-tuned based on the maximum endurance and payload of the maritime medical rescue drone to ensure its safety and efficiency, thus generating a delivery path.

[0036] Optionally, upon arrival at the designated receiving point, the landing coordinates are automatically calibrated, and based on the delivery route, the status of the supplies, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information, including:

[0037] By utilizing high-precision visual recognition technology and GPS positioning system, the predetermined landing coordinates of the maritime medical rescue drone are monitored in real time and automatically calibrated to obtain the accurate landing position.

[0038] Based on the precise landing location and the delivery route, low-latency wireless transmission technology is applied to synchronously transmit the status information, flight trajectory, and current environmental data of the maritime medical rescue drone to the medical team and central dispatch system at the receiving point, generating a preliminary material handover report.

[0039] Based on the preliminary material handover report, the material status and handover details during the actual delivery process are recorded in detail to ensure that all materials are delivered to the target location accurately and without error, and to obtain a detailed delivery list.

[0040] Using the detailed delivery list and the confirmation feedback from the medical team, a delivery record is obtained, and this delivery record is transmitted back to the central dispatch system as feedback information to generate accurate delivery records and feedback information.

[0041] Secondly, embodiments of this application provide a medical supply delivery system based on a maritime medical rescue drone, comprising:

[0042] The acquisition module is used to acquire and fuse multi-source environmental information in real time by utilizing the integrated perception system of the maritime medical rescue drone and combining it with the AI ​​environmental prediction model to generate a marine environment model.

[0043] The analysis module is used to analyze the specific needs, priorities and urgency of the receiving points at sea based on the marine environment model and AI scheduling algorithms. It also uses the knapsack problem analysis technique in operations research to finely plan resource allocation and obtain optimized task sequences and material loading schemes.

[0044] The adjustment module is used to establish a collaborative communication mechanism among the maritime medical rescue drone formations based on the optimized task sequence and material loading plan through an AI-driven distributed consensus algorithm, to ensure real-time information sharing, and to dynamically adjust the flight path and generate a delivery path by using AI path planning technology combined with real-time situational awareness and obstacle detection analysis.

[0045] The calibration module is used to automatically calibrate the landing coordinates after arriving at the designated receiving point, and synchronize the status of materials, handover information and environmental data to the medical team and the central dispatch system through low-latency wireless transmission according to the delivery route, so as to generate accurate delivery records and feedback information.

[0046] Thirdly, embodiments of this application provide a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a medical supply delivery method based on a maritime medical rescue drone as described in the first aspect.

[0047] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a computer, implements a method for delivering medical supplies based on a maritime medical rescue drone as described in the first aspect.

[0048] In this embodiment, a comprehensive perception system integrated into a maritime medical rescue drone is used, combined with an AI environmental prediction model, to acquire and fuse multi-source environmental information in real time, generating a marine environment model. Based on the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the maritime receiving point. Simultaneously, based on the knapsack problem analysis technique in operations research, resource allocation is finely planned to obtain an optimized task sequence and material loading scheme. Based on the optimized task sequence and material loading scheme, a collaborative communication mechanism among the maritime medical rescue drone formations is established through an AI-driven distributed consensus algorithm to ensure real-time information sharing. AI path planning technology, combined with real-time situational awareness and obstacle detection analysis, is used to dynamically adjust the flight path and generate a delivery path. Upon arrival at the designated receiving point, the landing coordinates are automatically calibrated, and based on the delivery path, the material status, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information.

[0049] The technical solution of this application has the following beneficial effects:

[0050] By integrating a comprehensive sensing system and an AI environmental prediction model, the system can acquire and process multi-source environmental information in real time, rapidly generating marine environmental models. This enables the system to respond quickly to maritime emergencies and optimize delivery routes, significantly shortening the time from task allocation to material delivery. By applying AI scheduling algorithms combined with knapsack problem analysis techniques from operations research, the system can accurately assess the needs, priorities, and urgency of each receiving point based on the marine environmental model, thereby achieving refined resource allocation planning, ensuring optimal material loading schemes, and improving the scientific rigor and accuracy of decision-making. Furthermore, by utilizing an AI-driven distributed consensus algorithm to establish a collaborative communication mechanism, the system ensures real-time information sharing among UAVs within the formation. Meanwhile, by combining real-time situational awareness and obstacle detection analysis technologies, the flight path is dynamically adjusted to avoid potential risks and ensure the safety and orderliness of the delivery process. Automatic calibration of landing coordinates and the application of low-latency wireless transmission technology ensure that supplies are delivered accurately to the target location, and the status of supplies, handover information, and environmental data are synchronized with relevant parties. This not only improves mission completion but also increases the system's flexibility to adapt to different on-site conditions. Through optimization of mission sequences and supply loading plans, the system can maximize the delivery efficiency of a single flight under limited load conditions, reducing unnecessary resource waste and improving resource utilization efficiency throughout the rescue operation. The generation of accurate delivery records and feedback information helps in post-event analysis and summarizing lessons learned, providing a reference for future missions and continuously optimizing rescue processes and technical methods.

[0051] Furthermore, by utilizing a marine environment model and combining AI scheduling algorithms with knapsack problem analysis techniques from operations research, this method can comprehensively evaluate the location, sea conditions, weather forecasts, and time windows of each maritime receiving point, accurately calculating the importance and urgency scores of the tasks. Based on this score, the system simulates the behavioral patterns of a multi-agent system, dynamically assesses the needs of each receiving point, generates a task requirement matrix reflecting task priority, and optimizes resource allocation strategies accordingly, generating a preliminary material loading plan. Further, by adjusting the UAV's task sequence to maximize the delivery efficiency of a single flight, the optimized task sequence and material loading plan are finally obtained. This method not only significantly improves the scientific rigor and accuracy of task planning but also ensures efficient and precise resource allocation in the complex and ever-changing marine environment. It effectively solves the problems of low delivery efficiency and resource waste caused by a lack of detailed planning in existing solutions, thereby greatly improving the overall response speed and service quality of maritime medical rescue.

[0052] Furthermore, by utilizing optimized task sequences and material loading schemes, this method provides a detailed analysis of the task allocation and flight plans for each maritime medical rescue drone, generating precise task execution instructions. Based on these instructions, an AI-driven distributed consensus algorithm is applied to establish an efficient collaborative communication mechanism among the drone formations, ensuring that each drone can share its location and status information in real time, forming an instant communication network. This network combines data from a real-time situational awareness system and obstacle detection sensors to continuously monitor potential risks in the flight environment and generate an environmental risk assessment report. Based on this report, AI path planning technology is used to dynamically adjust the flight path, ensuring that the drones can avoid obstacles and select the optimal path, ultimately generating a delivery route. This method significantly improves the accuracy and coordination of task execution, enhances flight safety and reliability, and effectively solves the problems of insufficient information sharing and weak risk response capabilities in existing solutions, thereby greatly improving the success rate and efficiency of maritime medical rescue operations.

[0053] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0054] To more clearly illustrate the technical solutions in the embodiments of this application or the prior art, the drawings used in the description of the embodiments or the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of this application. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort.

[0055] Figure 1 A flowchart illustrating a medical supply delivery method based on a maritime medical rescue drone, provided as an embodiment of this application;

[0056] Figure 2 A schematic diagram of a medical supply delivery system based on a maritime medical rescue drone is provided as an embodiment of this application;

[0057] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0058] To enable those skilled in the art to better understand the present application, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings.

[0059] In some of the processes described in the specification, claims, and accompanying drawings of this application, multiple operations are included in a specific order. However, it should be clearly understood that these operations may be performed out of order or in parallel. Furthermore, these processes may include more or fewer operations, and these operations may be performed sequentially or in parallel. It should be noted that the terms "first," "second," etc., used herein are used to distinguish different messages, devices, modules, etc., and do not represent a sequential order, nor do they limit "first" and "second" to different types.

[0060] The technical solutions of the embodiments of this application will be clearly and completely described below with reference to the accompanying drawings. Obviously, the described embodiments are only some embodiments of this application, and not all embodiments. Based on the embodiments of this application, all other embodiments obtained by those skilled in the art without creative effort are within the scope of protection of this application.

[0061] Figure 1 This application provides a flowchart of a medical supply delivery method based on a maritime medical rescue drone, as shown in the embodiments of this application. Figure 1 As shown, the method includes:

[0062] By utilizing a comprehensive perception system integrated into a maritime medical rescue drone and combining it with an AI environmental prediction model, multi-source environmental information is acquired and fused in real time to generate a marine environment model.

[0063] In this step, the integrated perception system of the maritime medical rescue drone includes multiple sensors and data acquisition devices to acquire real-time data such as meteorological data (wind speed, wind direction, temperature, etc.), sea state information (wave height, current direction, current velocity, etc.), and geospatial data (location coordinates, topography, etc.). Combined with an AI environmental prediction model, this multi-source environmental information is fused and processed to generate a dynamic model that comprehensively reflects the current marine environmental conditions. This model not only provides an accurate description of the existing environmental conditions but also predicts future trends, providing a solid foundation for subsequent mission planning.

[0064] In this embodiment, data collected by a comprehensive perception system deployed on an unmanned aerial vehicle (UAV) is preprocessed and then input into an AI environmental prediction model for analysis. The model uses machine learning algorithms to identify patterns and predict future environmental changes, ultimately outputting a marine environmental model that integrates all relevant information. This model serves as the basis for all subsequent decisions, ensuring the accuracy and adaptability of mission planning.

[0065] Suppose that during a maritime medical rescue operation, a drone activates its integrated perception system before takeoff to collect real-time weather and sea condition data of the surrounding waters and sends this data to an AI environmental prediction model. After analysis, the model generates a detailed marine environment model, showing that strong winds and high waves are likely to occur in a specific area within the next 24 hours. Based on this model, the rescue team adjusts its mission plan, selecting a safer flight route and time window.

[0066] Based on the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the receiving points at sea. At the same time, based on the knapsack problem analysis technique in operations research, the resource allocation is finely planned to obtain an optimized task sequence and material loading scheme.

[0067] In this step, AI scheduling algorithms are applied to analyze the specific needs, priorities, and urgency of the maritime receiving points. Simultaneously, the knapsack problem analysis technique from operations research is introduced to consider the drone's payload limitations and the types and quantities of supplies, enabling refined planning of resource allocation. Specific needs include the quantity and type of supplies, as well as the geographical location of the receiving points, estimated arrival time, and urgency score. Through this comprehensive evaluation, the system can generate optimized task sequences and supply loading plans, ensuring that each flight maximizes efficiency and effectiveness.

[0068] In this embodiment, based on the generated marine environment model, the AI ​​scheduling algorithm first calculates the task importance and urgency score for each receiving point, then simulates the interaction behavior pattern of a multi-agent system to generate a task requirement matrix reflecting the priority of each receiving point's needs. Next, the system employs a knapsack problem analysis method to formulate a preliminary material loading plan based on the UAV's payload capacity and material characteristics. Finally, the UAV's task sequence is further adjusted to ensure that the delivery efficiency of a single flight reaches its optimal state.

[0069] In a rescue mission involving multiple receiving points, the system calculates the mission importance and urgency scores for each point based on a marine environment model and the needs of each receiving point. Subsequently, the system simulates the collaborative working modes between different drones, generates a mission requirement matrix, and optimizes resource allocation based on this matrix, developing a detailed material loading plan. In this way, the system ensures that the mission sequence of each drone is carefully arranged to maximize delivery efficiency.

[0070] Based on the optimized task sequence and material loading plan, a collaborative communication mechanism among the maritime medical rescue drone formations is established through an AI-driven distributed consensus algorithm to ensure real-time information sharing. Furthermore, AI path planning technology is used in conjunction with real-time situational awareness and obstacle detection analysis to dynamically adjust the flight path and generate delivery routes.

[0071] In this step, based on the optimized task sequence and material loading plan, an efficient collaborative communication mechanism is established among the drone formations through an AI-driven distributed consensus algorithm, ensuring that all drones can share their location, status, and other critical information in real time. Furthermore, combined with real-time situational awareness and obstacle detection analysis, AI path planning technology dynamically adjusts flight paths to ensure avoidance of potential risks and selection of the safest and most efficient delivery route. This step is crucial for ensuring flight safety and improving mission completion rates.

[0072] In this embodiment, once the task sequence and material loading plan are determined, the system immediately activates a distributed consensus algorithm to build an instant communication network covering the entire formation. Based on this, data from a real-time situational awareness system and obstacle detection sensors are integrated, and AI path planning technology continuously monitors changes in the flight environment and adjusts the flight path of each drone accordingly. In this way, the system not only improves flight safety but also ensures optimal selection of delivery routes.

[0073] Imagine a complex maritime environment where multiple drones are preparing to perform a series of supply delivery missions. The system first establishes a collaborative communication mechanism based on an optimized mission sequence, enabling each drone to share its location and status information in real time. As the mission unfolds, the real-time situational awareness system continuously monitors the surrounding environment. When an unknown obstacle is detected ahead, AI path planning technology responds rapidly, dynamically adjusting the drone's flight path to successfully avoid the obstacle and ensure the safe completion of the mission.

[0074] Upon arrival at the designated receiving point, the landing coordinates are automatically calibrated, and based on the delivery route, the status of the supplies, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information.

[0075] In this step, as the drone approaches the designated receiving point, the system automatically calibrates its landing coordinates to ensure a precise landing. Simultaneously, via low-latency wireless transmission, the drone synchronizes the status of supplies, handover information, and environmental data to the medical team and the central dispatch system, generating detailed delivery records and feedback information. This information is crucial for confirming that supplies have been accurately delivered to the target location, assessing mission completion, and providing a reference for subsequent missions.

[0076] In this embodiment, when the drone approaches the designated receiving point, the system activates high-precision visual recognition technology and a GPS positioning system to automatically calibrate the landing coordinates, ensuring the drone lands accurately at the designated location. Simultaneously, the drone uses low-latency wireless transmission technology to synchronize its status information, flight trajectory, and current environmental data in real time to the medical team and central dispatch system at the receiving point. This not only guarantees accurate delivery of supplies but also provides timely information support for subsequent mission adjustments.

[0077] Imagine a drone approaching a medical station on a remote island. As it nears its destination, the system uses high-precision visual recognition technology and GPS positioning to automatically calibrate its landing coordinates, ensuring a safe and accurate landing at the designated location. Simultaneously, the drone transmits information about the supplies, handover details, and the latest environmental data to the island's medical team and the central dispatch system via low-latency wireless transmission. This allows the medical team to immediately confirm successful delivery and prepare for the next steps in the rescue effort, while the central dispatch system adjusts subsequent task assignments based on the feedback.

[0078] In summary, this invention covers the entire process from environmental perception, mission planning, collaborative communication to precise delivery, aiming to provide an efficient, safe, and reliable maritime medical rescue supply delivery solution that meets the needs of rapid response and precise execution in complex and ever-changing marine environments. Through this series of steps, the system not only improves the scientific rigor and accuracy of mission planning but also enhances flight safety and reliability, effectively addressing the problems of insufficient information sharing and weak risk response capabilities in existing solutions, and significantly improving the overall efficiency and service quality of maritime medical rescue.

[0079] To address the issues of irrational resource allocation and insufficiently refined task planning, some embodiments involve analyzing the specific needs, priorities, and urgency of maritime receiving points using AI scheduling algorithms based on the marine environment model. Simultaneously, resource allocation is refined using knapsack problem techniques from operations research, resulting in optimized task sequences and material loading schemes, including:

[0080] Using the aforementioned marine environment model, the location, sea conditions, weather forecast, and time window of each maritime receiving point are comprehensively evaluated to obtain a task importance and urgency score. Based on the task importance and urgency score, and combined with an AI scheduling algorithm to simulate the behavior pattern of a multi-agent system, the needs of each receiving point are dynamically evaluated to generate a task requirement matrix, which reflects task priority. Based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drones and the types and quantities of supplies, optimizing the resource allocation strategy and generating a preliminary supply loading plan. Using the preliminary supply loading plan, and combined with the AI ​​scheduling algorithm, the task sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized task sequence and supply loading scheme.

[0081] In this embodiment, the marine environment model is used to comprehensively evaluate the location, sea conditions, weather forecast, and time window of each maritime receiving point, resulting in task importance and urgency scores. These scores quantify the demand level of each receiving point. Based on the task importance and urgency scores, and combined with an AI scheduling algorithm to simulate the behavior pattern of a multi-agent system, the needs of each receiving point are dynamically evaluated, generating a task demand matrix. This matrix reflects task priorities and helps determine the execution order of each task. Based on the task demand matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drones and the types and quantities of supplies, optimizing the resource allocation strategy and generating a preliminary supply loading plan. This plan ensures maximum delivery efficiency under limited payload conditions. Using the preliminary supply loading plan, and combined with the AI ​​scheduling algorithm, the task sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized task sequence and supply loading scheme. The final scheme ensures optimal resource utilization and efficient task completion.

[0082] In this embodiment, firstly, a comprehensive assessment of key information (such as location, sea state, weather forecast, and time window) of each receiving point is conducted using a marine environment model to calculate the task importance and urgency score for each receiving point. Secondly, based on these scores, an AI scheduling algorithm is used to simulate the interactive behavior of a multi-agent system, dynamically assessing the needs of each receiving point and generating a task requirement matrix reflecting task priority. Thirdly, based on the task requirement matrix and considering the payload limitations of the UAV and the quantity and type of different materials, a knapsack problem analysis technique is used to optimize the resource allocation strategy, forming a preliminary material loading plan. Finally, combined with the preliminary plan, the UAV's task sequence is further adjusted using an AI scheduling algorithm to ensure that a single flight can maximize delivery efficiency, thereby obtaining the final optimized task sequence and material loading plan.

[0083] Here is a specific example:

[0084] In a complex maritime rescue scenario involving multiple islands requiring emergency supplies, the system first uses a marine environment model to assess the location of each island, current sea conditions, 24-hour weather forecasts, and estimated arrival time windows. Based on this, it calculates the mission importance and urgency score for each island. Second, using these scores, the system simulates the interaction between the drone formation and the receiving points, generating a detailed mission requirement matrix that clearly identifies the highest priority tasks. Third, based on the mission requirement matrix, the system considers the maximum payload of the drones and the quantity of different types of supplies to be carried, using knapsack problem analysis techniques to develop a preliminary supply loading plan. Finally, based on the preliminary plan, the system adjusts the drone mission sequence to ensure that each flight covers as many receiving points as possible, ultimately forming an optimized mission sequence and supply loading plan. Through these steps, the system not only achieves optimal resource allocation but also ensures that each flight completes its mission efficiently and accurately, significantly improving overall rescue efficiency and service quality.

[0085] To address the issues of irrational resource allocation and insufficiently refined task planning, some embodiments incorporate knapsack problem analysis techniques from operations research, based on the task requirement matrix, to consider the payload limitations of maritime medical rescue drones and the types and quantities of supplies. This optimizes the resource allocation strategy and generates a preliminary supply loading plan, including:

[0086] Using the aforementioned task requirement matrix, the urgency of the task and the amount of materials required at each maritime receiving point are quantitatively analyzed to obtain a requirement feature vector reflecting the characteristics of each receiving point's needs. Based on this requirement feature vector, and combined with the maximum payload capacity and effective payload volume of the maritime medical rescue UAV, a knapsack problem model is applied to optimize the combination of different types and quantities of materials, generating multiple candidate loading schemes that meet the load constraints. Based on these candidate loading schemes, considering the importance and urgency of each material, a priority weighting factor is introduced to evaluate the comprehensive benefits of each candidate scheme, resulting in an optimized loading benefit score. Using this optimized loading benefit score, delivery efficiency and task completion are maximized under limited load conditions, generating a preliminary material loading plan.

[0087] In this embodiment, the task requirement matrix is ​​used to quantitatively analyze the urgency and material demand of each maritime receiving point, resulting in a demand feature vector reflecting the characteristics of each receiving point's needs. These vectors are used to accurately describe the demand situation of each receiving point. Based on the demand feature vector, combined with the maximum payload capacity and effective payload volume of the maritime medical rescue UAV, a knapsack problem model is applied to optimize the combination of different types and quantities of materials, generating multiple candidate loading schemes that meet the load constraints. This process ensures that all possible loading combinations are considered. Based on the candidate loading schemes, considering the importance and urgency of each material, a priority weighting factor is introduced to evaluate the comprehensive benefits of each candidate scheme, resulting in an optimized loading benefit score. In this way, the system can select the most effective loading scheme. Using the optimized loading benefit score, the system ensures that delivery efficiency and task completion are maximized under limited load conditions, generating a preliminary material loading plan. The final plan ensures that each flight can efficiently complete the mission.

[0088] In this embodiment, firstly, the system uses a task requirement matrix to quantify the urgency of the task and the quantity of materials required at each receiving point, forming a requirement feature vector. Secondly, based on these feature vectors, combined with the maximum payload capacity and effective payload volume of the UAV, a knapsack problem model is applied to calculate multiple candidate loading schemes. Thirdly, for each candidate scheme, the importance and urgency of the materials are considered, and a priority weight factor is introduced to evaluate its comprehensive benefits, resulting in an optimized loading benefit score. Finally, based on these scores, the optimal scheme is selected to ensure maximum delivery efficiency and task completion under limited load conditions, generating a preliminary material loading plan.

[0089] Here is a specific example:

[0090] In a multi-island rescue scenario, the system first quantifies the urgency of the mission and the required quantity of supplies for each island based on a task requirement matrix, forming a detailed requirement feature vector. Second, combining the maximum payload capacity and effective payload volume of the drone, the system applies a knapsack problem model to calculate multiple possible loading schemes. Third, considering the importance and urgency of each type of supply, the system introduces a priority weighting factor to evaluate the comprehensive effectiveness of each candidate scheme, deriving an optimized loading efficiency score. Finally, the system selects the scheme with the highest score, ensuring maximum delivery efficiency and mission completion under limited load conditions, generating a preliminary supply loading plan. Through these steps, the system can not only accurately match the needs of each receiving point but also maximize the rescue effect under limited resource conditions.

[0091] To address the issue that the initial material loading plan failed to adequately consider the task sequence, in one or more of the above embodiments, the task sequence of each maritime medical rescue drone is further adjusted using the initial material loading plan in conjunction with an AI scheduling algorithm to maximize the delivery efficiency of a single flight, resulting in an optimized task sequence and material loading scheme, including:

[0092] Using the preliminary material loading plan, the payload configuration and expected flight paths of each maritime medical rescue drone are comprehensively analyzed to generate an initial task allocation table. Based on this initial task allocation table, and combined with an AI scheduling algorithm to simulate the behavior patterns of a multi-agent system, the task execution order of each maritime medical rescue drone is dynamically evaluated. Considering the dependencies between tasks and time window constraints, a task execution sequence reflecting task priority is obtained. Based on this task execution sequence, a complexity analysis method is introduced to evaluate the time synchronization requirements and collaborative operation needs between different tasks, and the connection between tasks is optimized to ensure that high-priority tasks can be completed in a timely manner, generating an optimized task sequence. Using the optimized task sequence, combined with the maximum endurance of the maritime medical rescue drones and real-time sea state data, the material loading plan is fine-tuned to ensure that the delivery efficiency of a single flight is maximized while meeting all task requirements, resulting in an optimized task sequence and material loading plan.

[0093] In this embodiment, the initial material loading plan is used to comprehensively analyze and process the payload configuration and expected flight path of each maritime medical rescue UAV, generating an initial task allocation table. This table guides the task arrangement of the UAVs. Based on the initial task allocation table, and combined with an AI scheduling algorithm to simulate the behavior pattern of a multi-agent system, the task execution order of each maritime medical rescue UAV is dynamically evaluated. Considering the dependencies between tasks and time window constraints, a task execution sequence reflecting task priority is obtained; this sequence clarifies the task execution order. Based on the task execution sequence, a complexity analysis method is introduced to evaluate the time synchronization requirements and collaborative operation needs between different tasks, optimizing the connection between tasks to ensure that high-priority tasks can be completed in a timely manner; this step ensures the continuity and efficiency of the tasks. Using the optimized task sequence, combined with the maximum endurance of the maritime medical rescue UAVs and real-time sea state data, the material loading plan is fine-tuned to ensure that the delivery efficiency of a single flight is maximized while meeting all task requirements, resulting in an optimized task sequence and material loading plan; the final plan ensures the successful completion of the task and the best utilization of resources.

[0094] In this embodiment, firstly, based on a preliminary material loading plan, the system analyzes the payload configuration and expected flight path of each UAV and generates an initial task allocation table. Secondly, based on this table, and combined with an AI scheduling algorithm to simulate the behavior pattern of a multi-agent system, the system dynamically evaluates and adjusts the task execution order of the UAVs, considering the dependencies between tasks and time window constraints, and generates a task execution sequence reflecting task priorities. Thirdly, the system introduces a complexity analysis method to evaluate the time synchronization requirements and collaborative operation needs between different tasks, optimizes the connection between tasks, and ensures that high-priority tasks can be completed in a timely manner. Finally, the system combines the maximum endurance of the UAVs and real-time sea state data to fine-tune the material loading plan, ensuring that the delivery efficiency of a single flight is maximized while meeting all task requirements, thereby obtaining an optimized task sequence and material loading plan.

[0095] Here is a specific example:

[0096] In a complex maritime rescue operation, the system first analyzes the payload configuration and expected flight paths of each UAV based on a preliminary material loading plan, generating an initial task allocation table. Second, using this table and an AI scheduling algorithm, the system simulates the behavior patterns of a multi-agent system, dynamically evaluating and adjusting the UAV task execution order, considering task dependencies and time window constraints, and generating a task execution sequence reflecting task priorities. Third, the system introduces complexity analysis methods to assess the time synchronization requirements and collaborative operation needs between different tasks, optimizing task connections to ensure high-priority tasks are completed promptly. Finally, the system fine-tunes the material loading plan based on the UAVs' maximum endurance and real-time sea state data, maximizing the delivery efficiency of a single flight while meeting all task requirements, ultimately resulting in an optimized task sequence and material loading plan. Through these steps, the system not only improves the continuity and efficiency of the mission but also ensures optimal resource utilization and successful mission completion.

[0097] This application addresses the problems of unreasonable resource allocation and inaccurate task priority assessment in existing technologies, which hinder efforts to improve the planning accuracy and response speed of maritime medical rescue missions. Traditional methods struggle to comprehensively consider the specific needs of each receiving point, environmental urgency, and UAV payload capacity, resulting in low delivery efficiency and an inability to promptly meet emergency rescue needs. Therefore, this invention proposes an alternative solution to solve these problems. By introducing an AI scheduling algorithm to simulate the behavior patterns of a multi-agent system, the needs of each receiving point are dynamically assessed, generating a task requirement matrix reflecting task priority. This optimizes resource allocation and improves rescue efficiency and service quality.

[0098] Optionally, based on the task importance and urgency scores, and combined with an AI scheduling algorithm to simulate the behavior patterns of a multi-agent system, the needs of each receiving point are dynamically evaluated to generate a task requirement matrix. This task requirement matrix reflects task priorities and includes:

[0099] In calculating the task urgency score US i Previously, time sensitivity analysis, comprehensive assessment of the positional relationships of neighboring nodes, and evaluation of the degree of environmental urgency were required; these analyses provided comprehensive and accurate basic data for subsequent calculations.

[0100]

[0101] US i D represents the task urgency score of the i-th receiving point; i Indicates the estimated time required for supplies at the receiving point; T iRepresents the current time; α is the time sensitivity coefficient; Neighbors(i) is the set of neighboring nodes of the receiving point; W j It is the task weight of the neighboring nodes; S j It is the service capacity coefficient of the neighboring nodes; d ij is the distance from receiver i to its neighbor j; b is the distance influence index, used to adjust the degree of influence of neighbor nodes; β is the neighbor influence coefficient; E i It is the environmental urgency score of the receiving point; E j λ is the environmental urgency score of neighboring nodes; λ is the urgency difference sensitivity coefficient.

[0102] After calculating the mission urgency score, and taking into account the specific material needs of each receiving point, the payload capacity of the maritime medical rescue drone, and material priorities, as well as the impact of environmental urgency, a mission requirement matrix element TDME is generated that reflects the needs of each receiving point for different types of materials. ik ;

[0103]

[0104] TDME ik γ represents the requirement score of the receiving point for material type k in the task requirement matrix; γ represents the task importance adjustment coefficient; Q k C represents the demand for material type k; k δ represents the upper limit of the quantity of type k of supplies that a maritime medical rescue drone can carry in a single trip; η represents the demand ratio sensitivity coefficient; P represents the urgency level impact coefficient; i The environmental urgency score at the receiving point is represented by μ; the periodic fluctuation coefficient is represented by R. i Indicates the relative location of the receiving point with respect to the distribution center; R max Indicates the furthest delivery distance;

[0105] After calculating the elements of the mission requirement matrix, it is normalized, and the material allocation scheme is optimized based on the maximum endurance and actual flight path of the maritime medical rescue drone. A redundancy mechanism is introduced to deal with emergencies, and a mission requirement matrix that comprehensively considers multiple factors is generated.

[0106] This formula is designed to calculate the task urgency score (US). i and Task Requirements Matrix Elements TDME ikPreviously, a comprehensive time sensitivity analysis, a comprehensive assessment of the location relationships of neighboring nodes, and an evaluation of the urgency of the environment were required to ensure that subsequent calculations were based on comprehensive and accurate foundational data. This not only helps to accurately assess the demand priority of each receiving point, but also enables the optimization of resource allocation schemes by combining the maximum endurance of the UAV and the actual flight path, introducing redundancy mechanisms to cope with emergencies, and ultimately generating a task requirement matrix that comprehensively considers multiple factors, thereby improving the scientific nature and accuracy of task planning.

[0107] The following is a brief introduction to the design rationale behind each term of the formula:

[0108]

[0109] Time sensitivity section This indicates the urgency of the task;

[0110] Neighbor node impact part This indicates the impact of neighboring nodes on the task;

[0111] The following is a brief introduction to how the parameters of this formula are obtained:

[0112] D i and T i Obtained from the task schedule and system clock respectively; α is set based on historical data analysis; Neighbors(i) are determined through a Geographic Information System (GIS); W j and S j Provided by the task database; d ij Measurements were taken using a GPS positioning system; b was adjusted based on experiments; β was set through simulation testing; E i and E j Sourced from the environmental monitoring system; λ is set based on the pattern of urgency changes.

[0113] The following is a brief introduction to the design rationale behind each term of the formula:

[0114]

[0115] Task importance adjustment section γ·US i This section indicates the importance and urgency of the task; it is used to emphasize the importance and urgency of the task.

[0116] Demand ratio sensitivity section This section represents the ratio of material requirements to the drone's payload capacity, and is used to assess the reasonableness of the material requirements relative to the drone's payload.

[0117] The degree of urgency affects the part 1+η·log(1+P) i): This indicates the impact of environmental urgency at the receiving point. This part is used to quantify the impact of environmental urgency on the task.

[0118] Periodic fluctuations This section represents the impact of periodic fluctuations in the relative position of the receiving point; it is used to account for the periodic effects of the receiving point's position.

[0119] The following is a brief introduction to how the parameters of this formula are obtained:

[0120] γ is set through expert experience; US i Calculated from the aforementioned formula; Q k and C k Provided by the material requirements list and drone specifications; δ is set based on historical data analysis of demand ratios; η is set through simulation testing; P i From the environmental monitoring system; μ is set according to geographical location characteristics; R i and R max Determined using a GIS system.

[0121] Assume a rescue scenario in a complex sea area with three receiving points A, B, and C. The estimated time required for supplies is 2 hours, 3 hours, and 4 hours respectively, and the current time is 0 hours. Neighbor node impact assessment shows that receiving points A and B are adjacent, 5 kilometers apart, and both have a service capacity coefficient of 0.8; receiving point C has no neighboring nodes. The environmental urgency scores are A: 7, B: 6, and C: 5. The maximum payload of the drone is 100 kg, and the required quantities of supply type k are A: 30 kg, B: 40 kg, and C: 30 kg respectively. The task importance adjustment coefficient γ = 1.2, time sensitivity coefficient α = 1, neighbor influence coefficient β = 0.5, distance influence index b = 2, urgency difference sensitivity coefficient λ = 0.5, demand ratio sensitivity coefficient δ = 0.8, urgency level influence coefficient η = 0.3, periodic fluctuation coefficient μ = 0.2, and the maximum delivery distance R... max = 100 kilometers.

[0122] First, calculate the task urgency score (US). i :

[0123]

[0124] Next, calculate the Task Requirements Matrix (TDME) elements. ik :

[0125]

[0126] Through the above steps, the system not only improves the accuracy and response speed of mission planning, but also ensures optimal resource allocation and efficient utilization, significantly enhancing the overall efficiency and service quality of maritime medical rescue. Since the result exceeds the set threshold, it indicates that the system can effectively identify and prioritize the most urgent tasks, ensuring timely delivery of supplies and increasing the success rate and reliability of rescue operations.

[0127] To address the issue of insufficient consideration of collaborative communication and environmental risks in task allocation and flight path planning, some embodiments involve establishing a collaborative communication mechanism among maritime medical rescue drone formations based on the optimized task sequence and material loading plan using an AI-driven distributed consensus algorithm. This ensures real-time information sharing, and utilizes AI path planning technology combined with real-time situational awareness and obstacle detection analysis to dynamically adjust flight paths and generate delivery routes. This includes:

[0128] Using the optimized task sequence and material loading scheme, the task allocation and flight plan of each maritime medical rescue drone are analyzed in detail to obtain precise task execution instructions. Based on the task execution instructions, an AI-driven distributed consensus algorithm is applied to establish a collaborative communication mechanism among the maritime medical rescue drone formations, ensuring that each drone can share its location and status in real time, generating an instant communication network. Based on the instant communication network, data from the real-time situational awareness system and obstacle detection sensors are integrated to monitor and process potential risks in the flight environment, resulting in an environmental risk assessment report. Using the environmental risk assessment report, combined with AI path planning technology, the current flight path is dynamically adjusted to ensure obstacle avoidance and selection of the optimal path, ultimately generating a delivery route.

[0129] In this embodiment, the optimized task sequence and material loading scheme are used to analyze and process the task allocation and flight plan of each maritime medical rescue drone in detail, resulting in precise task execution instructions. These instructions guide the specific actions of each drone. Based on the task execution instructions, an AI-driven distributed consensus algorithm is applied to establish a collaborative communication mechanism among the maritime medical rescue drone formation, ensuring that each drone can share its location and status in real time, generating an instant communication network. This network guarantees the instant sharing of information within the formation. Based on the instant communication network, data from the real-time situational awareness system and obstacle detection sensors are integrated to monitor and process potential risks in the flight environment, resulting in environmental risk assessment reports. These reports provide detailed environmental risk information. Using the environmental risk assessment reports, combined with AI path planning technology, the current flight path is dynamically adjusted to ensure obstacle avoidance and selection of the optimal path, ultimately generating a delivery path. This path ensures the safety and efficiency of each flight.

[0130] In this embodiment, firstly, the system analyzes the task allocation and flight plan of each UAV in detail based on the optimized task sequence and material loading scheme, generating precise task execution instructions; secondly, based on these instructions, the system applies an AI-driven distributed consensus algorithm to establish an efficient collaborative communication mechanism among the UAV formations, ensuring that each UAV can share its position and status in real time, forming an instant communication network; thirdly, based on this communication network, the system integrates data from a real-time situational awareness system and obstacle detection sensors to continuously monitor potential risks in the flight environment and generate an environmental risk assessment report; finally, the system uses these risk assessment reports, combined with AI path planning technology, to dynamically adjust the current flight path, ensuring that obstacles are avoided and the optimal path is selected, ultimately generating a delivery route.

[0131] Here is a specific example:

[0132] In a complex maritime rescue scenario, the system first analyzes the task allocation and flight plan for each drone based on an optimized task sequence and cargo loading scheme, generating precise mission execution instructions. Second, based on these instructions, the system applies an AI-driven distributed consensus algorithm to establish an efficient collaborative communication mechanism among the drone formations, ensuring that each drone can share its location and status in real time, forming an instant communication network. Third, based on this communication network, the system integrates data from a real-time situational awareness system and obstacle detection sensors to continuously monitor potential risks in the flight environment, generating a detailed environmental risk assessment report. Finally, using these risk assessment reports and AI path planning technology, the system dynamically adjusts the current flight path to ensure obstacle avoidance and selection of the optimal route, ultimately generating a delivery route. Through these steps, the system not only achieves efficient information sharing and collaborative work but also ensures that each flight avoids potential risks and selects the safest and most effective path, significantly improving the success rate and reliability of rescue missions.

[0133] To address the issue of insufficient consideration of environmental risks in flight path planning, some embodiments utilize the environmental risk assessment report, combined with AI path planning technology, to dynamically adjust the current flight path, ensuring obstacle avoidance and selecting the optimal route, ultimately generating a delivery route. This includes:

[0134] Using the aforementioned environmental risk assessment report, potential obstacles and risk areas in the flight environment are identified to obtain an obstacle distribution map. Based on the obstacle distribution map and combined with real-time sea conditions and meteorological data, an AI path planning algorithm is applied to recalculate the existing flight path, resulting in multiple candidate obstacle avoidance paths. Based on these multiple candidate obstacle avoidance paths, the shortest path algorithm and weighted scoring mechanism from graph theory are introduced, considering path length, flight time, and risk coefficients, to comprehensively evaluate each candidate path and obtain an optimized path score. Using the optimized path score, the path with the highest score is selected as the final flight path. Furthermore, considering the maximum endurance and payload of the maritime medical rescue drone, the path is fine-tuned to ensure its safety and efficiency, generating a delivery path.

[0135] In this embodiment, the environmental risk assessment report is used to identify potential obstacles and risk areas in the flight environment, resulting in an obstacle distribution map. This data is used to accurately describe the physical obstacles and risk areas that may be encountered in the flight environment. Based on the obstacle distribution map, combined with real-time sea state and meteorological data, an AI path planning algorithm is applied to recalculate the existing flight path, resulting in multiple candidate obstacle avoidance paths. This process ensures that every possible obstacle avoidance scheme is considered. Based on these multiple candidate obstacle avoidance paths, the shortest path algorithm and weighted scoring mechanism from graph theory are introduced. Considering path length, flight time, and risk coefficients, each candidate path is comprehensively evaluated to obtain an optimized path score. In this way, the system can select the most effective flight path. Using the optimized path score, the path with the highest score is selected as the final flight path. The path is then fine-tuned based on the maximum endurance and payload of the maritime medical rescue drone to ensure the safety and efficiency of the path, generating a delivery path. The final path ensures that each flight can complete the mission efficiently and safely.

[0136] In this embodiment, firstly, the system uses an environmental risk assessment report to identify potential obstacles and risk areas in the flight environment, forming a detailed obstacle distribution map. Secondly, based on these distribution maps and combined with real-time sea conditions and meteorological data, an AI path planning algorithm is applied to calculate multiple possible obstacle avoidance paths. Thirdly, based on these candidate paths, the system uses the shortest path algorithm and weighted scoring mechanism in graph theory, considering path length, flight time, and risk coefficient, to comprehensively evaluate each candidate path and obtain an optimized path score. Finally, the system selects the path with the highest score as the final flight path and makes fine adjustments based on the maximum endurance and payload of the UAV to ensure the safety and efficiency of the path, generating a delivery path.

[0137] Here is a specific example:

[0138] In a complex maritime rescue scenario, the system first uses an environmental risk assessment report to identify potential obstacles and risk areas in the flight environment, creating a detailed obstacle distribution map. Second, based on these maps and real-time sea conditions and weather data, an AI path planning algorithm is applied to calculate multiple possible obstacle avoidance paths. Third, based on these candidate paths, the system uses a shortest path algorithm and weighted scoring mechanism from graph theory, considering path length, flight time, and risk coefficients, to comprehensively evaluate each candidate path and obtain an optimized path score. Finally, the system selects the path with the highest score as the final flight path and fine-tunes it based on the drone's maximum endurance and payload capacity to ensure the path's safety and efficiency, generating a delivery route. Through these steps, the system can not only avoid obstacles but also select the optimal path, ensuring that each flight completes the mission efficiently and safely, improving the overall success rate and reliability of rescue operations.

[0139] This application addresses the shortcomings of existing technologies in improving collaborative communication efficiency among UAV formations during maritime medical rescue missions, including insufficient information sharing, communication bottlenecks, and inadequate real-time performance. Traditional methods struggle to comprehensively consider the relative positions, motion states, mission requirements, urgency levels, and environmental factors of each UAV, resulting in poor communication quality and an inability to respond promptly to complex changes in the marine environment. Therefore, this invention proposes an alternative solution to address these issues. By introducing an AI-driven distributed consensus algorithm, an efficient collaborative communication mechanism is established among UAV formations, ensuring that each UAV can share its position, status, and other critical information in real time, generating an instant communication network. This optimizes information sharing strategies and improves information interaction efficiency and service quality.

[0140] Optionally, according to the task execution instructions, an AI-driven distributed consensus algorithm is applied to establish a collaborative communication mechanism among the maritime medical rescue drone formations to ensure that each maritime medical rescue drone can share its location, status and other key information in real time, generating an instant communication network;

[0141] In calculating the Collaborative Communication Quality Evaluation (CCQE) score for maritime medical rescue drones. j Previously, it was necessary to analyze the communication environment of the maritime medical rescue drone formation, and assess the impact of relative position, motion status, mission requirements, urgency, and environmental factors to provide basic data for subsequent scoring.

[0142]

[0143] Here is CCQE j ζ represents the collaborative communication quality score of the i-th maritime medical rescue drone; ζ is the communication efficiency sensitivity coefficient; N is the total number of drones participating in the mission; W iW is the weight of the i-th task, and W i ≥0; D ij It is the data transmission delay from the drone to the mission, and D ij ≥0; T j It is the data processing threshold of drone j, and T j ≥0; It is the urgency level influence coefficient; E j It is the environmental urgency score of the drone, and E j ≥0; ω is the relative velocity influence coefficient; V j It is the speed of drone j, and V j ≥0; It is the average speed of the formation; V max It is the maximum permissible speed, and V max >0;

[0144] Complete the collaborative communication quality assessment (CCQE) for maritime medical rescue drones. j After calculation, the information sharing strategy is optimized based on the score, the communication bandwidth allocation is adjusted, and future information sharing patterns are predicted to reduce communication bottlenecks and improve the RSI (Resource Sharing Index) for maritime medical rescue drones. j Prepare for computation and improve the efficiency of information exchange;

[0145]

[0146] Among them, RSI j This represents the information sharing index of the j-th maritime medical rescue drone; M is the number of information types; C k The importance of information type k, and C k ≥0; S jk Let S be the success rate of drone j sharing information type k, and 0 ≤ S. jk ≤1; B jk (t) = B0 + αt is the change of communication bandwidth of information type k over time, where B0 is the initial bandwidth and α is the rate of change of bandwidth over time; Neighbors(j) is the set of UAVs adjacent to the i-th UAV; d jl It is the distance between drones j and l, and d jl ≥0; J is the distance decay exponent; η is the environmental change impact coefficient; F l (t)=βe -γt It represents the change of environmental change factors over time, where β and γ are parameters that adjust the rate of environmental change; ψ is the periodic fluctuation coefficient; R j It refers to the relative position of the drone with respect to the distribution center; R max It is the furthest delivery distance, and R max >0; χ is the influence coefficient of environmental urgency; ΔE j=E j (t)-E j (0) represents the change in the environmental urgency of the drone; E max It is the maximum environmental urgency score, and E max >0.

[0147] After calculating the Information Sharing Index (RSI) for maritime medical rescue drones j Subsequently, an instant communication network is constructed based on the information sharing index, the optimal path and timing for data transmission are selected, a distributed consensus algorithm is applied to ensure real-time information sharing, a redundancy mechanism is introduced to deal with emergencies, and the network health status is checked regularly to maintain stable operation.

[0148] In calculating the Collaborative Communication Quality Evaluation (CCQE) score for maritime medical rescue drones. j Information Sharing Index (RSI) j Previously, it was necessary to analyze the communication environment of the drone formation, assessing relative positions, motion states, mission requirements, urgency, and the impact of environmental factors to provide basic data for subsequent scoring. This not only helps to accurately evaluate the communication quality and information sharing capabilities of each drone, but also enables the optimization of communication bandwidth allocation based on actual conditions, prediction of future information sharing patterns, reduction of communication bottlenecks, and ultimately the construction of an efficient and stable real-time communication network to ensure the successful completion of missions.

[0149] The following is a brief introduction to the design rationale behind each term of the formula:

[0150]

[0151] Communication efficiency section Represents communication efficiency; ζ is the communication efficiency sensitivity coefficient; N is the total number of UAVs participating in the mission; W i D is the weight of the i-th task; ij This refers to the data transmission latency from the drone to the mission; T j This is the data processing threshold for drone j; this part is used to measure communication efficiency.

[0152] The degree of urgency affects the part 1+φ·log(1+E) j ): Indicates the impact of urgency on communication quality; φ is the urgency impact coefficient; E j This is the environmental urgency score for drones; this part is used to quantify the impact of urgency on communication quality.

[0153] Relative speed influence part This represents the impact of relative speed on communication quality; ω is the relative speed influence coefficient; V j It is the speed of drone j; It is the average speed of the formation; V maxThis is the maximum permissible speed; this section is used to assess the impact of relative speed on communication quality.

[0154] The following is a brief introduction to how the parameters of this formula are obtained:

[0155] ζ is set based on historical communication efficiency data analysis; N is determined by the task schedule; W i and D ij From communication log; T j Preset by the system; φ is set through simulation testing; E j Source: Environmental monitoring system; ω adjusted according to experiment; V j Measured using a GPS positioning system; V avg V is calculated from the speed of all drones; max Provided by drone specifications.

[0156] The following is a brief introduction to the design rationale behind each term of the formula:

[0157]

[0158] Importance of Information Types This represents the importance of different types of information; M is the number of information types; C k The importance of information type k; S jk B is the success rate of drone j in sharing information type k; jk (t) = B0 + αt is the communication bandwidth of information type k as it changes over time; this part is used to assess the importance of different types of information.

[0159] Neighbor node impact part This represents the impact of neighboring nodes on information sharing; Neighbors(j) is the set of drones adjacent to drone j; d jl The distance between drones j and l is J; the distance decay index is η; the environmental change impact coefficient is F. l (t)=βe -γt This refers to the change of environmental factors over time; this part is used to assess the impact of neighboring nodes on information sharing.

[0160] Periodic fluctuations This represents the impact of periodic fluctuations on information sharing; ψ is the periodic fluctuation coefficient; R j It refers to the relative position of the drone with respect to the distribution center; R max This is the furthest delivery distance; this section is used to account for the impact of periodic fluctuations.

[0161] Changes in environmental urgency affect some aspects This represents the impact of changes in environmental urgency on information sharing; χ is the influence coefficient of changes in environmental urgency; ΔE j =E j (t)-E j (0) represents the change in the environmental urgency of the drone; E max This is the maximum environmental urgency score; this section is used to assess the impact of changes in environmental urgency on information sharing.

[0162] The following is a brief introduction to how the parameters of this formula are obtained:

[0163] M is determined by task requirements; C k and S jk From information sharing records; B jk (t) is provided by the communication bandwidth management module; Neighbors(j) are determined through a Geographic Information System (GIS); d jl Measurements were taken using a GPS positioning system; J was adjusted based on experiments; η was set through simulation testing; β and γ were set according to environmental change patterns; ψ was set based on geographical location characteristics; R j and R max Determined using a GIS system; χ is set through expert experience; ΔE j and E max Source: Environmental monitoring system.

[0164] Suppose a rescue scenario in a complex maritime area involves five drones, numbered A, B, C, D, and E. Drone A has a task weight W. A =0.8, data transmission delay D Aj = 2 seconds, data processing threshold T A =3 seconds, environmental urgency score E A =7, velocity V A =10 m / s, average formation speed V avg =12 m / s, maximum permissible speed V max =20 meters per second. Number of information types M = 3, information type importance C1 = 0.6, C2 = 0.4, C3 = 0.5 respectively, and sharing success rates S respectively. A1 =0.9, S A2 =0.8, S A3 =0.7, initial bandwidth B0 = 5MHz, bandwidth changes with time at a rate of α = 0.1MHz / s. Neighbor set Neighbors(A) = {B, C}, distances d and d respectively. AB =5 meters, d AC =7 meters, distance attenuation index J=2, environmental change impact coefficient η=0.3, environmental change factor parameters β=0.8 and γ=0.1 over time, periodic fluctuation coefficient ψ=0.2, maximum delivery distance Rmax =100 meters, the influence coefficient of environmental urgency change χ = 0.4, the change in environmental urgency ΔE A =2, Maximum environmental urgency score E max =10.

[0165] First, calculate the Collaborative Communication Quality (CCQE) score. A :

[0166]

[0167] After substituting the values, we get CCQE. A ≈0.92

[0168] Next, calculate the Information Sharing Index (RSI). A :

[0169]

[0170] After substituting the values, we get the RSI. A ≈0.88

[0171] Through the above steps, the system not only improved the quality of collaborative communication and the efficiency of information sharing, but also ensured the optimal allocation and efficient utilization of resources, significantly enhancing the overall efficiency and service quality of maritime medical rescue. Since the results exceeded the set threshold, it indicates that the system can effectively identify and prioritize drones with high communication quality and strong information sharing capabilities, ensuring timely and accurate information transmission and enhancing the success rate and reliability of rescue operations.

[0172] To address the issues of insufficient accuracy and untimely information feedback during material handover, some embodiments involve automatically calibrating the landing coordinates upon arrival at the designated receiving point. Based on the delivery route, the material status, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information, including:

[0173] Utilizing high-precision visual recognition technology and a GPS positioning system, the predetermined landing coordinates of the maritime medical rescue drone are monitored in real time and automatically calibrated to obtain an accurate landing position. Based on the accurate landing position and the delivery route, low-latency wireless transmission technology is applied to synchronously transmit the drone's status information, flight trajectory, and current environmental data to the receiving medical team and the central dispatch system, generating a preliminary material handover report. Based on this preliminary material handover report, the material status and handover details during the actual delivery process are recorded in detail to ensure that all materials are delivered accurately to the target location, resulting in a detailed delivery list. Using this detailed delivery list, combined with confirmation feedback from the medical team, a delivery record is obtained and transmitted back to the central dispatch system as feedback information, generating an accurate delivery record and feedback information.

[0174] In this embodiment, high-precision visual recognition technology and a GPS positioning system are used to monitor and automatically calibrate the predetermined landing coordinates of the maritime medical rescue drone in real time, obtaining a precise landing location. These technologies ensure that the drone can accurately land at the predetermined location. Based on the precise landing location and the delivery route, low-latency wireless transmission technology is applied to synchronously transmit the status information, flight trajectory, and current environmental data of the maritime medical rescue drone to the medical team at the receiving point and the central dispatch system, generating a preliminary material handover report. This report provides an initial overview of the handover situation. Based on the preliminary material handover report, the status of materials and the handover situation during the actual delivery process are recorded in detail to ensure that all materials are delivered accurately to the target location, resulting in a detailed delivery list. This list ensures the transparency and accuracy of the material handover. Using the detailed delivery list, combined with the confirmation feedback from the medical team, a delivery record is obtained and transmitted back to the central dispatch system as feedback information, generating an accurate delivery record and feedback information. This information ensures the traceability of the entire delivery process.

[0175] In this embodiment, firstly, the system uses high-precision visual recognition technology and a GPS positioning system to monitor and automatically calibrate the drone's predetermined landing coordinates in real time, ensuring that the drone can land accurately at the designated location. Secondly, based on the precise landing location and the previously planned safe and orderly delivery route, the system applies low-latency wireless transmission technology to synchronously transmit the drone's status information, flight trajectory, and current environmental data to the medical team at the receiving point and the central dispatch system, generating a preliminary material handover report. Thirdly, based on this preliminary report, the system records the material status and handover details during the actual delivery process in detail, ensuring that all materials are delivered accurately to the target location, forming a detailed delivery list. Finally, the system combines the confirmation feedback from the medical team to generate a final delivery record, and transmits this record back to the central dispatch system as feedback information, ensuring the transparency and traceability of the entire delivery process.

[0176] Here is a specific example:

[0177] In an emergency medical rescue scenario on a remote island, the system first uses high-precision visual recognition technology and GPS positioning to monitor and automatically calibrate the drone's predetermined landing coordinates in real time, ensuring the drone lands precisely at the designated location. Second, based on the precise landing location and the previously planned safe and orderly delivery route, the system uses low-latency wireless transmission technology to synchronously transmit the drone's status information, flight trajectory, and current environmental data to the island's medical team and the central dispatch system, generating a preliminary supplies handover report. Third, based on this preliminary report, the system meticulously records the status of supplies and the handover process during actual delivery, ensuring all supplies are accurately delivered to the target location, creating a detailed delivery list. Finally, the system, combined with confirmation feedback from the medical team, generates a final delivery record, which is transmitted back to the central dispatch system as feedback information, ensuring the transparency and traceability of the entire delivery process. Through these steps, the system not only ensures the accuracy and efficiency of supplies handover but also provides a complete delivery record, enhancing the transparency and reliability of mission execution.

[0178] Figure 2 This application provides a schematic diagram of a medical supply delivery system based on a maritime medical rescue drone, as shown in the embodiment of the present application. Figure 2 As shown, the device includes:

[0179] The acquisition module 21 is used to acquire and fuse multi-source environmental information in real time by utilizing the integrated perception system integrated into the marine medical rescue drone and combining it with the AI ​​environment prediction model to generate a marine environment model.

[0180] Analysis module 22 is used to analyze the specific needs, priorities and urgency of the receiving points at sea based on the marine environment model and AI scheduling algorithm, and to finely plan resource allocation based on the knapsack problem analysis technology in operations research, so as to obtain an optimized task sequence and material loading plan.

[0181] The adjustment module 23 is used to establish a collaborative communication mechanism among the maritime medical rescue drone formations based on the optimized task sequence and material loading plan through an AI-driven distributed consensus algorithm, to ensure real-time information sharing, and to dynamically adjust the flight path and generate a delivery path by using AI path planning technology combined with real-time situational awareness and obstacle detection analysis.

[0182] The calibration module 24 is used to automatically calibrate the landing coordinates after arriving at the designated receiving point, and synchronize the material status, handover information and environmental data to the medical team and the central dispatch system through low-latency wireless transmission according to the delivery route, so as to generate accurate delivery records and feedback information.

[0183] Figure 2 The aforementioned medical supply delivery system based on a maritime medical rescue drone can perform... Figure 1 The implementation principle and technical effects of the medical supply delivery method based on a maritime medical rescue drone, as described in the illustrated embodiment, will not be repeated here. The specific methods by which each module and unit of the medical supply delivery system based on a maritime medical rescue drone in the above embodiments are performed have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0184] In one possible design, Figure 2 The medical supply delivery system based on a maritime medical rescue drone, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0185] The storage component 31 stores one or more computer instructions, wherein the one or more computer instructions are invoked and executed by the processing component 32.

[0186] The processing component 32 is used to: utilize the integrated perception system of the maritime medical rescue drone, combined with an AI environment prediction model, to acquire and fuse multi-source environmental information in real time, generating a marine environment model; based on the marine environment model, apply an AI scheduling algorithm to analyze the specific needs, priorities, and urgency of the maritime receiving point, and simultaneously perform fine-grained resource allocation based on the knapsack problem analysis technique in operations research, obtaining an optimized task sequence and material loading scheme; based on the optimized task sequence and material loading scheme, establish a collaborative communication mechanism among the maritime medical rescue drone formations through an AI-driven distributed consensus algorithm to ensure real-time information sharing, and dynamically adjust the flight path using AI path planning technology combined with real-time situational awareness and obstacle detection analysis to generate a delivery path; upon arrival at the designated receiving point, automatically calibrate the landing coordinates, and based on the delivery path, synchronize the material status, handover information, and environmental data to the medical team and the central dispatch system through low-latency wireless transmission, generating accurate delivery records and feedback information.

[0187] The processing component 32 may include one or more processors to execute computer instructions to complete all or part of the steps in the above-described method. Alternatively, the processing component may be implemented as one or more application-specific integrated circuits (ASICs), digital signal processors (DSPs), digital signal processing devices (DSPDs), programmable logic devices (PLDs), field-programmable gate arrays (FPGAs), controllers, microcontrollers, microprocessors, or other electronic components to perform the above-described method.

[0188] Storage component 31 is configured to store various types of data to support operations at the terminal. The storage component can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as static random access memory (SRAM), electrically erasable programmable read-only memory (EEPROM), erasable programmable read-only memory (EPROM), programmable read-only memory (PROM), read-only memory (ROM), magnetic storage, flash memory, magnetic disk, or optical disk.

[0189] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0190] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0191] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0192] The computing device can be a physical device or an elastic computing host provided by a cloud computing platform. In this case, the computing device can refer to a cloud server, and the aforementioned processing components, storage components, etc., can be basic server resources rented or purchased from the cloud computing platform.

[0193] This application also provides a computer storage medium storing a computer program, which, when executed by a computer, can perform the above-described functions. Figure 1 The illustrated embodiment is a method for delivering medical supplies based on a maritime medical rescue drone.

[0194] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working processes of the systems, devices, and units described above can be referred to the corresponding processes in the foregoing method embodiments, and will not be repeated here.

[0195] The device embodiments described above are merely illustrative. The units described 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 modules can be selected to achieve the purpose of this embodiment according to actual needs. Those skilled in the art can understand and implement this without any creative effort.

[0196] Through the above description of the embodiments, those skilled in the art can clearly understand that each embodiment can be implemented by means of software plus necessary general-purpose hardware platforms, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solutions, in essence or the part that contributes to the prior art, can be embodied in the form of a software product. This computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, magnetic disk, optical disk, etc., and includes several instructions to cause a computer device (which may be a personal computer, server, or network device, etc.) to execute the methods described in the various embodiments or some parts of the embodiments.

[0197] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of this application, and are not intended to limit them. Although this application has been described in detail with reference to the foregoing embodiments, those skilled in the art should understand that modifications can still be made to the technical solutions described in the foregoing embodiments, or equivalent substitutions can be made to some of the technical features. Such modifications or substitutions do not cause the essence of the corresponding technical solutions to deviate from the spirit and scope of the technical solutions of the embodiments of this application.

Claims

1. A method for delivering medical supplies based on a maritime medical rescue drone, characterized in that, include: By utilizing a comprehensive perception system integrated into a maritime medical rescue drone and combining it with an AI environmental prediction model, multi-source environmental information is acquired and fused in real time to generate a marine environment model. Based on the marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the receiving points at sea. At the same time, based on the knapsack problem analysis technique in operations research, the resource allocation is finely planned to obtain an optimized task sequence and material loading scheme. Based on the optimized task sequence and material loading plan, a collaborative communication mechanism among the maritime medical rescue drone formations is established through an AI-driven distributed consensus algorithm to ensure real-time information sharing. Furthermore, AI path planning technology is used in conjunction with real-time situational awareness and obstacle detection analysis to dynamically adjust the flight path and generate delivery routes. Upon arrival at the designated receiving point, the landing coordinates are automatically calibrated, and based on the delivery route, the status of the supplies, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information. Based on the aforementioned marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the maritime receiving points. Simultaneously, based on the knapsack problem analysis technique in operations research, resource allocation is finely planned to obtain an optimized task sequence and material loading scheme, including: Using the marine environment model, the location, sea conditions, weather forecast, and time window of each marine receiving point are comprehensively evaluated to obtain a score of mission importance and urgency. Based on the task importance and urgency scores, and combined with the AI ​​scheduling algorithm to simulate the behavior pattern of a multi-agent system, the needs of each receiving point are dynamically evaluated and processed to generate a task requirement matrix, which reflects the task priority. Based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drone and the types and quantities of materials. The resource allocation strategy is optimized to generate a preliminary material loading plan. Using the preliminary material loading plan, and combining it with AI scheduling algorithms, the mission sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized mission sequence and material loading plan.

2. The method according to claim 1, characterized in that, Based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drone and the types and quantities of supplies. The resource allocation strategy is optimized to generate a preliminary supply loading plan, including: Using the aforementioned task requirement matrix, the urgency of tasks and the amount of materials required at each maritime receiving point are quantitatively analyzed and processed to obtain a requirement feature vector reflecting the demand characteristics of each receiving point. Based on the aforementioned demand feature vector, and combined with the maximum payload capacity and effective payload volume of the maritime medical rescue drone, the knapsack problem model is applied to optimize the combination of different types and quantities of materials, generating multiple candidate loading schemes that meet the load constraints. Based on the candidate loading schemes, considering the importance and urgency of each material, a priority weighting factor is introduced to evaluate the comprehensive benefits of each candidate scheme, resulting in an optimized loading benefit score. By utilizing the optimized loading efficiency score, we can ensure that delivery efficiency and task completion are maximized under limited load conditions, and generate a preliminary material loading plan.

3. The method according to claim 1, characterized in that, The preliminary material loading plan is used, combined with AI scheduling algorithms, to further adjust the mission sequence of each maritime medical rescue drone, maximizing the delivery efficiency of a single flight, resulting in an optimized mission sequence and material loading plan, including: Using the aforementioned preliminary material loading plan, a comprehensive analysis and processing of the payload configuration and expected flight path of each maritime medical rescue drone is conducted to generate an initial task allocation table; Based on the initial task allocation table, and combined with the AI ​​scheduling algorithm to simulate the behavior pattern of a multi-agent system, the task execution order of each maritime medical rescue drone is dynamically evaluated. Considering the dependencies between tasks and time window constraints, a task execution sequence reflecting task priority is obtained. Based on the task execution sequence, a complexity analysis method is introduced to evaluate the time synchronization requirements and collaborative operation needs between different tasks, optimize the connection between tasks, ensure that high-priority tasks can be completed in a timely manner, and generate an optimized task sequence. Using the optimized mission sequence, combined with the maximum endurance of the maritime medical rescue drone and real-time sea state data, the material loading plan is fine-tuned to ensure that the delivery efficiency of a single flight is maximized while meeting all mission requirements, resulting in an optimized mission sequence and material loading plan.

4. The method according to claim 1, characterized in that, Based on the optimized task sequence and material loading plan, a collaborative communication mechanism is established among the maritime medical rescue drone formations through an AI-driven distributed consensus algorithm to ensure real-time information sharing. Furthermore, AI path planning technology, combined with real-time situational awareness and obstacle detection analysis, is used to dynamically adjust flight paths and generate delivery routes, including: Using the optimized task sequence and material loading scheme, the task allocation and flight plan of each maritime medical rescue UAV are analyzed in detail to obtain precise task execution instructions. According to the task execution instructions, an AI-driven distributed consensus algorithm is used to establish a collaborative communication mechanism among the maritime medical rescue drone formations, ensuring that each maritime medical rescue drone can share its location and status in real time and generate an instant communication network. Based on the aforementioned instant communication network, data from the real-time situational awareness system and obstacle detection sensors are integrated to monitor and process potential risks in the flight environment, thereby obtaining an environmental risk assessment report. Using the aforementioned environmental risk assessment report and combined with AI path planning technology, the current flight path is dynamically adjusted to ensure that obstacles are avoided and the optimal path is selected, ultimately generating a delivery path.

5. The method according to claim 4, characterized in that, The process of using the environmental risk assessment report, combined with AI path planning technology, to dynamically adjust the current flight path, ensure obstacle avoidance and select the optimal path, ultimately generating a delivery route, includes: Using the aforementioned environmental risk assessment report, potential obstacles and risk areas in the flight environment are identified and processed to obtain an obstacle distribution map; Based on the obstacle distribution map and combined with real-time sea conditions and meteorological data, the existing flight path is recalculated using an AI path planning algorithm to obtain multiple candidate obstacle avoidance paths. Based on the multiple candidate obstacle avoidance paths, the shortest path algorithm and weighted scoring mechanism in graph theory are introduced. Taking into account path length, flight time and risk coefficient, each candidate path is comprehensively evaluated to obtain the optimized path score. Using the optimized path score, the path with the highest score is selected as the final flight path. The path is then fine-tuned based on the maximum endurance and payload of the maritime medical rescue drone to ensure its safety and efficiency, thus generating a delivery path.

6. The method according to claim 1, characterized in that, Upon arrival at the designated receiving point, the landing coordinates are automatically calibrated. Based on the delivery route, the status of the supplies, handover information, and environmental data are synchronized to the medical team and the central dispatch system via low-latency wireless transmission, generating accurate delivery records and feedback information, including: By utilizing high-precision visual recognition technology and GPS positioning system, the predetermined landing coordinates of the maritime medical rescue drone are monitored in real time and automatically calibrated to obtain the accurate landing position. Based on the precise landing location and the delivery route, low-latency wireless transmission technology is applied to synchronously transmit the status information, flight trajectory, and current environmental data of the maritime medical rescue drone to the medical team and central dispatch system at the receiving point, generating a preliminary material handover report. Based on the preliminary material handover report, the material status and handover details during the actual delivery process are recorded in detail to ensure that all materials are delivered to the target location accurately and without error, and to obtain a detailed delivery list. Using the detailed delivery list and the confirmation feedback from the medical team, a delivery record is obtained, and this delivery record is transmitted back to the central dispatch system as feedback information to generate accurate delivery records and feedback information.

7. A medical supply delivery system based on a maritime medical rescue drone, characterized in that, include: The acquisition module is used to acquire and fuse multi-source environmental information in real time by utilizing the integrated perception system of the maritime medical rescue drone and combining it with the AI ​​environmental prediction model to generate a marine environment model. The analysis module is used to analyze the specific needs, priorities and urgency of the receiving points at sea based on the marine environment model and AI scheduling algorithms. It also uses the knapsack problem analysis technique in operations research to finely plan resource allocation and obtain optimized task sequences and material loading schemes. Based on the aforementioned marine environment model, an AI scheduling algorithm is applied to analyze the specific needs, priorities, and urgency of the maritime receiving points. Simultaneously, based on the knapsack problem analysis technique in operations research, resource allocation is finely planned to obtain an optimized task sequence and material loading scheme, including: Using the marine environment model, the location, sea conditions, weather forecast, and time window of each marine receiving point are comprehensively evaluated to obtain a score of mission importance and urgency. Based on the task importance and urgency scores, and combined with the AI ​​scheduling algorithm to simulate the behavior pattern of a multi-agent system, the needs of each receiving point are dynamically evaluated and processed to generate a task requirement matrix, which reflects the task priority. Based on the task requirement matrix, the knapsack problem analysis technique from operations research is introduced to consider the payload limitations of the maritime medical rescue drone and the types and quantities of materials. The resource allocation strategy is optimized to generate a preliminary material loading plan. Using the preliminary material loading plan, and combining it with AI scheduling algorithms, the mission sequence of each maritime medical rescue drone is further adjusted to maximize the delivery efficiency of a single flight, resulting in an optimized mission sequence and material loading plan. The adjustment module is used to establish a collaborative communication mechanism among the maritime medical rescue drone formations based on the optimized task sequence and material loading plan through an AI-driven distributed consensus algorithm, to ensure real-time information sharing, and to dynamically adjust the flight path and generate a delivery path by using AI path planning technology combined with real-time situational awareness and obstacle detection analysis. The calibration module is used to automatically calibrate the landing coordinates after arriving at the designated receiving point, and synchronize the status of materials, handover information and environmental data to the medical team and the central dispatch system through low-latency wireless transmission according to the delivery route, so as to generate accurate delivery records and feedback information.

8. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement a medical supply delivery method based on a maritime medical rescue drone as described in any one of claims 1 to 6.

9. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements a method for delivering medical supplies based on a maritime medical rescue drone as described in any one of claims 1 to 6.

Images