Satellite communication-based offshore first-aid information transmission method and system

Abstract

The application provides a satellite communication-based offshore first-aid information transmission method and system. A temporary dedicated satellite communication link is constructed, and the temporary dedicated satellite communication link is parameter-optimized to obtain an optimized communication link. A field environment is three-dimensionally reconstructed, a disease severity description is analyzed, a disease development is predicted, and a disease prediction result is generated. The distribution strategy of special medical supplies is optimized by considering factors such as weather changes and sea current directions, and an optimal distribution path plan is obtained. Pattern recognition and trend prediction are performed, a potential risk warning is generated, and updated medical needs are formed. The optimal distribution path plan is re-evaluated and optimized, and an updated optimal distribution path plan is generated. The technical scheme provided by the application improves the efficiency and accuracy of offshore first-aid response, and ensures that medical supplies can be timely and accurately delivered to the first-aid site.

Description

Technical Field

[0001] This application relates to the field of maritime emergency rescue information transmission technology, and in particular to a method and system for maritime emergency rescue information transmission based on satellite communication. Background Technology

[0002] In maritime emergency rescue scenarios, timely and accurate medical response is crucial. Due to the complex and ever-changing marine environment, traditional land-based emergency rescue methods are difficult to apply directly to maritime rescues. Specifically, maritime emergency rescue requires ensuring stable, low-latency, high-definition audio and video communication and data sharing between medical experts and on-site rescue personnel. Precise tools for reconstructing the scene and analyzing patient conditions must be provided to assist medical experts in making accurate diagnoses and treatment recommendations. Given the influence of weather changes and ocean currents, the delivery routes for specialized medical supplies need continuous optimization to ensure timely and accurate delivery to the emergency scene.

[0003] Currently, maritime emergency rescue information transmission mainly relies on conventional satellite communication systems and limited remote diagnostic tools. These solutions typically include basic voice and low-bandwidth data transmission, but lack optimization for emergency rescue scenarios. For example, video conferencing software can provide basic audio and video communication, but it is insufficient in terms of image quality and real-time performance. Material delivery plans based on preset conditions cannot be dynamically adjusted to adapt to real-time changing environmental factors.

[0004] However, existing solutions exhibit significant limitations when dealing with complex maritime emergency rescue missions. Standard satellite communication links, lacking parameter optimization, are susceptible to interference from external factors such as weather, leading to communication delays or interruptions and impacting the efficiency and accuracy of remote diagnosis. Existing remote guidance tools lack support from augmented reality technology and computer vision algorithms, failing to provide comprehensive and intuitive 3D reconstructions of the scene, thus limiting medical experts' understanding and decision-making capabilities. Static delivery planning fails to adequately consider factors such as weather changes and ocean currents, resulting in inflexible material delivery routes that may cause delays or prevent timely arrival of supplies at the emergency site, thereby affecting treatment outcomes.

[0005] In summary, existing maritime emergency rescue information transmission solutions have significant shortcomings in communication quality, remote diagnostic accuracy, and resource delivery flexibility, necessitating a more efficient, accurate, and flexible method to meet the practical needs of maritime emergency rescue. This invention aims to comprehensively improve the information transmission and response capabilities of maritime emergency rescue by constructing a temporary dedicated satellite communication link, combining augmented reality technology and computer vision algorithms for 3D reconstruction, applying machine learning models to predict disease progression, and optimizing resource delivery routes through reinforcement learning algorithms. Summary of the Invention

[0006] This application provides a method and system for transmitting maritime emergency rescue information based on satellite communication, in order to solve the problems of low efficiency and accuracy of maritime emergency rescue response in the prior art.

[0007] In a first aspect, embodiments of this application provide a method for transmitting maritime emergency rescue information based on satellite communication, including:

[0008] Based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal, a temporary dedicated satellite communication link is constructed, and the parameters of the temporary dedicated satellite communication link are optimized to obtain an optimized communication link;

[0009] Using the optimized communication link, combined with augmented reality technology and computer vision algorithms, the on-site environment is reconstructed in three dimensions, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Furthermore, machine learning models are applied to analyze the severity of the illness, predict its progression, and generate disease prediction results.

[0010] Based on the disease prediction results, the distribution strategy for special medical supplies is optimized by taking into account factors such as weather changes and ocean current direction through reinforcement learning algorithms, resulting in the optimal distribution route plan.

[0011] Based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and form updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0012] Based on the aforementioned potential risk warnings and updated medical needs, the optimal delivery route plan is reassessed and optimized to generate an updated optimal delivery route plan, ensuring that supplies can be delivered to the emergency site in a timely and accurate manner.

[0013] Optionally, the optimized communication link, combined with augmented reality technology and computer vision algorithms, is used to perform three-dimensional reconstruction of the on-site environment, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Furthermore, machine learning models are applied to analyze the severity of the illness, predict its progression, and generate a disease prediction result, including:

[0014] The optimized communication link establishes a high-quality communication connection between the emergency scene and medical experts, ensuring stable, low-latency high-definition audio and video calls. The optimized communication link supports high-bandwidth data transmission, ensuring the quality and efficiency of real-time data sharing, and achieving a high-quality communication connection.

[0015] Based on the high-quality communication connection, combined with augmented reality technology, images and video streams from the emergency scene are processed to overlay virtual information onto the actual scene on the medical expert's end, assisting in remote diagnosis and obtaining an augmented reality-assisted remote diagnosis environment.

[0016] Using computer vision algorithms, multi-angle images and videos transmitted from the scene and processed by augmented reality technology are processed to construct an accurate three-dimensional model of the emergency scene. Based on the data obtained in the augmented reality-assisted remote diagnostic environment, an accurate three-dimensional reconstruction of the scene is obtained.

[0017] Based on the optimized communication link and the accurate on-site 3D reconstruction, vital sign data and specific key environmental indicators transmitted from various on-site monitoring devices are shared in real time and displayed in the form of charts or values ​​on the expert interface. This facilitates immediate assessment of the patient's condition, promotes collaborative work, and obtains real-time shared vital sign data. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0018] Prepare the input data required for the machine learning model, organize and preprocess the preliminary medical condition description and vital sign data shared in real time through the communication link, and form a structured dataset suitable for machine learning model analysis based on the real-time shared vital sign data.

[0019] By applying a machine learning model, a quantitative assessment and trend prediction are performed on the structured dataset suitable for analysis by the machine learning model. The machine learning model, after learning from a large number of cases, is able to quantitatively assess the severity of the disease and predict its development trend, thus obtaining detailed disease analysis results.

[0020] Based on the detailed disease analysis results and the accurate on-site 3D reconstruction, a disease prediction report is generated.

[0021] Optionally, the process of using computer vision algorithms to process multi-angle images and videos transmitted from the scene and processed by augmented reality technology to construct an accurate three-dimensional model of the emergency scene, and obtaining an accurate three-dimensional reconstruction of the scene based on data acquired in the augmented reality-assisted remote diagnostic environment, includes:

[0022] Using computer vision algorithms, the received multi-angle images and videos are preprocessed to remove noise, correct distortion, and perform color calibration to obtain high-quality input data.

[0023] Based on the high-quality input data, a feature detection algorithm is used to identify and extract stable feature points to obtain key feature points for subsequent matching.

[0024] Based on the key feature points used for subsequent matching, a feature matching algorithm is used to match the key feature points from different perspectives, and the matching results are optimized by bundle adjustment to improve the accuracy of 3D reconstruction and generate optimized feature point matching results.

[0025] The position of feature points in three-dimensional space in the optimized feature point matching result is calculated using the principle of triangulation, and the spatial structure of the emergency scene is initially formed, resulting in a sparse three-dimensional point cloud.

[0026] A multi-view stereo vision algorithm is applied to fill the gaps between the sparse 3D point clouds to generate a dense 3D point cloud.

[0027] A continuous 3D surface is constructed from the dense 3D point cloud using the Poisson surface reconstruction algorithm, and the texture information of the original image is mapped onto the surface to obtain an accurate 3D model.

[0028] By combining the precise 3D model with real-time scene information obtained through augmented reality technology, medical experts are provided with a comprehensive and intuitive view of the emergency scene, ensuring the accuracy and effectiveness of remote diagnosis and obtaining a precise 3D reconstruction of the scene.

[0029] Optionally, based on the disease prediction results, the optimization of the distribution strategy for special medical supplies using a reinforcement learning algorithm, taking into account factors such as weather changes and ocean current direction, to obtain the optimal distribution route plan includes:

[0030] Based on the disease prediction results, the key environmental parameters of weather changes and ocean current direction are acquired and analyzed in real time using the comprehensive environmental factor assessment module to obtain an environmental condition report affecting delivery route planning.

[0031] Based on the environmental condition report, a multi-objective optimization problem model including transportation cost, time efficiency, and safety factor is created by applying reinforcement learning algorithm to obtain the initial delivery strategy.

[0032] A dynamic adjustment mechanism is introduced into the initial delivery strategy, which allows the delivery strategy to be updated in real time with the latest weather changes and ocean current directions, ensuring that the effectiveness and accuracy of delivery can be maintained even in complex and ever-changing environments, and generating continuously optimized delivery route plans.

[0033] By utilizing the interactive learning process between the reinforcement learning model and actual delivery conditions, the delivery route planning is automatically adjusted, and the optimal delivery route planning is obtained based on the latest environmental changes and delivery feedback.

[0034] Optionally, based on the environmental condition report, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model that includes transportation cost, time efficiency, and safety factor to obtain an initial delivery strategy, including:

[0035] Using the aforementioned environmental condition report, in-depth analysis of key environmental parameters such as weather changes and ocean current direction is performed to obtain the analysis results of factors affecting delivery route selection and material delivery time;

[0036] Based on the results of the factor analysis, multiple optimization objectives are defined, including minimizing transportation costs, maximizing time efficiency, and ensuring the highest safety factor, thus generating a multi-objective optimization framework.

[0037] By applying reinforcement learning algorithms and based on the multi-objective optimization framework, a multi-objective optimization problem model capable of handling the trade-offs between different optimization objectives is constructed, and the objective definition and weight allocation in the multi-objective optimization framework are used as the basis for model construction.

[0038] A simulation environment is constructed to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model, and the multi-objective optimization model is used in the simulation environment.

[0039] Through numerous simulation experiments, the reinforcement learning model is allowed to continuously try delivery route selection in the simulation environment, and the trade-offs between various objectives are adjusted based on feedback, gradually converging to the optimal strategy combination to obtain a preliminary optimized delivery solution.

[0040] Based on the preliminary optimized delivery plan, and taking into account the latest environmental conditions and actual delivery needs, a final adjustment is made to generate the initial delivery strategy.

[0041] Optionally, based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed, including:

[0042] Using the optimized communication link, vital sign monitoring data and specific key environmental indicators at the emergency scene are collected and processed to obtain coded monitoring data. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0043] Based on the encoded monitoring data, the encoded monitoring data is processed in real time through the optimized communication link to obtain a data stream that is transmitted to the medical command center in real time.

[0044] Based on the data stream transmitted to the medical command center in real time, the deep learning algorithm deployed in the medical command center is used to analyze and process the vital signs monitoring data and specific key environmental indicators to obtain pattern recognition results. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall and ocean current speed.

[0045] Based on the pattern recognition results, a deep learning model is used to predict the development trend of the patient's condition and generate a trend prediction report.

[0046] Based on the trend prediction report, the system automatically generates potential risk warnings for each patient, providing warning information that includes current risk factors and potential future risks.

[0047] Based on the aforementioned early warning information, the medical command center reassessed and adjusted the emergency response plan, resulting in updated medical needs.

[0048] Optionally, the step of reassessing and optimizing the optimal delivery route plan based on the potential risk warning and updated medical needs, and generating an updated optimal delivery route plan to ensure that supplies can be delivered to the emergency scene in a timely and accurate manner, includes:

[0049] Using the aforementioned potential risk warning, risk factors at the emergency scene are analyzed and processed to obtain a detailed risk assessment report;

[0050] Based on the risk assessment report and the updated medical needs, the current medical supply needs are reassessed, and an updated list of medical supply needs is generated.

[0051] Based on the latest list of medical supplies needs, examine whether the existing optimal delivery route plan needs to be adjusted to adapt to the new demand changes, and preliminarily identify the aspects that need to be optimized;

[0052] Based on the preliminary optimization aspects identified above, and considering the latest environmental conditions, the optimal delivery route is replanned to ensure that the material delivery strategy meets the latest medical needs and risk warnings.

[0053] Through continuous updates and adjustments, the optimal delivery route plan is ultimately generated to ensure that special medical supplies can be delivered to the emergency site in a timely and accurate manner.

[0054] Secondly, embodiments of this application provide a satellite-based maritime emergency rescue information transmission system, comprising:

[0055] An optimization module is constructed to construct a temporary dedicated satellite communication link based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal, and to optimize the parameters of the temporary dedicated satellite communication link to obtain an optimized communication link.

[0056] The reconstruction analysis module is used to perform three-dimensional reconstruction of the on-site environment by utilizing the optimized communication link and combining augmented reality technology and computer vision algorithms. This enables high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. It also applies machine learning models to analyze the severity of the illness, predict the progression of the illness, and generate illness prediction results.

[0057] The optimization processing module is used to optimize the distribution strategy of special medical supplies based on the disease prediction results, by using reinforcement learning algorithms and taking into account factors such as weather changes and ocean current direction, to obtain the optimal distribution route plan.

[0058] The data collection and formation module is used to collect vital sign monitoring data and specific key environmental indicators according to the optimized communication link, transmit them back to the medical command center in real time, and apply deep learning algorithms to perform pattern recognition and trend prediction, generate potential risk warnings, and form updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0059] The evaluation and optimization module is used to re-evaluate and optimize the optimal delivery route plan based on the potential risk warning and updated medical needs, and generate an updated optimal delivery route plan to ensure that supplies can be delivered to the emergency site in a timely and accurate manner.

[0060] 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 to be invoked and executed by the processing component to implement a method for transmitting maritime emergency rescue information based on satellite communication as described in any of the first aspects.

[0061] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a computer, implements a method for transmitting maritime emergency rescue information based on satellite communication as described in any of the first aspects.

[0062] In this embodiment, a temporary dedicated satellite communication link is constructed based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal. The parameters of the temporary dedicated satellite communication link are then optimized to obtain an optimized communication link. Using this optimized communication link, combined with augmented reality technology and computer vision algorithms, a 3D reconstruction of the on-site environment is performed, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. A machine learning model is applied to analyze the severity description of the illness, predict its progression, and generate a disease prediction result. Based on the disease prediction result, a reinforcement learning algorithm is used to consider weather changes and ocean currents. The optimal delivery route plan is obtained by optimizing the distribution strategy for special medical supplies based on directional factors. According to the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed. Based on the potential risk warnings and updated medical needs, the optimal delivery route plan is re-evaluated and optimized to generate an updated optimal delivery route plan, ensuring that supplies can be delivered to the emergency site in a timely and accurate manner.

[0063] The technical solution of this application has the following beneficial effects:

[0064] This application constructs a temporary dedicated satellite communication link and optimizes its parameters to ensure stable, low-latency high-definition audio and video calls and real-time data sharing, thereby accelerating information exchange between medical experts and on-site rescue personnel and shortening decision-making time. Augmented reality technology and computer vision algorithms are used to reconstruct the 3D environment of the scene, and machine learning models are combined to analyze the severity of the illness, predict its progression, and generate a disease prediction result. This method not only improves the accuracy of remote diagnosis but also provides a scientific basis for subsequent treatment. Based on the disease prediction result, reinforcement learning algorithms are used to optimize the delivery strategy of special medical supplies, considering factors such as weather changes and ocean current direction, resulting in the optimal delivery route plan. This ensures that supplies can reach the emergency site in the shortest time with the lowest risk, improving the reliability and timeliness of supply delivery. Vital sign monitoring data and specific key environmental indicators are collected, and deep learning algorithms are applied for pattern recognition and trend prediction to generate potential risk warnings. This enables the system to better cope with the complex and ever-changing marine environment, anticipate potential risks, adjust delivery strategies, and ensure the safety and effectiveness of the emergency rescue process. Based on potential risk warnings and updated medical needs, the optimal delivery route plan is reassessed and optimized, generating an updated optimal delivery route plan. This dynamic adjustment mechanism ensures that the delivery route is always the optimal choice, enabling a rapid response even in emergencies and ensuring timely and accurate delivery of supplies.

[0065] Furthermore, this embodiment of the application utilizes an optimized communication link combined with augmented reality technology and computer vision algorithms to perform 3D reconstruction of the emergency scene, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Machine learning models are also applied to analyze and predict the severity of the patient's condition. By using reinforcement learning algorithms to consider factors such as weather changes and ocean currents, multi-objective optimization of the delivery strategy for special medical supplies is performed to ensure timely and accurate delivery to the emergency scene. This process not only encompasses the establishment of high-quality communication connections, accurate 3D reconstruction, real-time vital sign data sharing, and the preparation of structured datasets, but also includes generating a condition prediction report based on detailed condition analysis results, and continuously optimizing delivery route planning through a dynamic adjustment mechanism.

[0066] The aforementioned methods not only established stable, low-latency high-definition audio and video communication connections and accurate on-site 3D reconstruction, but also enhanced the accuracy of remote diagnosis, providing medical experts with an intuitive and comprehensive view of the emergency scene. Simultaneously, machine learning models were applied to quantitatively assess the patient's condition and predict its development trend, generating detailed case analysis results to support more scientific decision-making. Furthermore, by introducing reinforcement learning algorithms to create a multi-objective optimization problem model incorporating transportation costs, time efficiency, and safety factors, optimal planning of delivery routes for special medical supplies was achieved, maintaining the effectiveness and accuracy of delivery even in complex and variable marine environments. These improvements collectively enhanced the overall performance of the system, maximizing patient safety and significantly increasing the success rate of maritime emergency rescue missions.

[0067] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0068] 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.

[0069] Figure 1 A flowchart illustrating a method for transmitting maritime emergency rescue information based on satellite communication, provided as an embodiment of this application;

[0070] Figure 2 A schematic diagram of a satellite-based maritime emergency rescue information transmission system provided in this application embodiment;

[0071] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0072] 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.

[0073] 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.

[0074] 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.

[0075] Figure 1 A flowchart illustrating a method for transmitting maritime emergency rescue information based on satellite communication is provided in this application embodiment. Figure 1 As shown, the method includes:

[0076] Based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal, a temporary dedicated satellite communication link is constructed, and the parameters of the temporary dedicated satellite communication link are optimized to obtain an optimized communication link;

[0077] Based on the emergency medical distress signal containing the location information and preliminary medical condition description, a temporary dedicated satellite communication link is constructed and its parameters are optimized to obtain the optimized communication link. The emergency location information typically includes latitude and longitude coordinates, depth (if applicable), and other data to accurately pinpoint the location of the emergency scene. The preliminary medical condition description includes the patient's basic symptoms and vital signs, which are crucial for quickly assessing the severity of the condition. The temporary dedicated satellite communication link is a communication connection specifically established for the current emergency medical mission, ensuring stable, low-latency data transmission. Parameter optimization involves adjusting various parameters of the communication link (such as frequency, bandwidth, and power) to adapt to the specific marine environment and emergency medical needs.

[0078] Upon receiving an emergency medical distress signal, the system first parses the included location information and preliminary description of the medical condition. Based on this information, the system selects the optimal satellite resources to establish a temporary dedicated satellite communication link. Then, the system dynamically adjusts the link parameters according to real-time environmental conditions (such as weather and ocean currents) to ensure the stability and efficiency of the communication link. Ultimately, this optimized communication link provides a solid foundation for subsequent high-definition audio and video calls and real-time data sharing.

[0079] In a real-world maritime emergency rescue scenario, a cruise ship issued an emergency medical distress signal, reporting that a passenger had suffered a heart attack. Upon receiving the signal, the system quickly determined the cruise ship's precise location (e.g., 40.7128°N, 74.0060°W) and a preliminary description of the patient's medical condition (e.g., abnormal heart rate, difficulty breathing). The system then automatically selected the most suitable satellite resources to establish a temporary dedicated satellite communication link from the cruise ship to the shore-based medical command center. Next, the system adjusted the communication link parameters based on the prevailing weather forecast and ocean current data, ensuring the link's stability and efficiency even in adverse weather conditions, thus providing reliable communication support for subsequent remote diagnosis and supplies delivery.

[0080] Using the optimized communication link, combined with augmented reality technology and computer vision algorithms, the on-site environment is reconstructed in three dimensions, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Furthermore, machine learning models are applied to analyze the severity of the illness, predict its progression, and generate disease prediction results.

[0081] This involves utilizing optimized communication links, combined with augmented reality technology and computer vision algorithms, to perform 3D reconstruction of emergency scene data. This enables high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Machine learning models are applied to analyze descriptions of patient severity, predict disease progression, and generate disease prediction results. Augmented reality technology allows virtual information to be overlaid onto the real-world scene, aiding remote diagnosis; computer vision algorithms process multi-angle images and videos to construct accurate 3D models; and machine learning models are used to quantitatively assess patient conditions and predict their development.

[0082] Through optimized communication links, medical experts can conduct stable, high-definition audio and video calls with on-site rescue personnel and share images and videos of the emergency scene in real time. Simultaneously, computer vision algorithms process these images and videos to construct accurate 3D models, helping medical experts gain a more intuitive understanding of the situation. Furthermore, machine learning models analyze the collected preliminary medical condition descriptions and real-time monitoring data to generate detailed disease predictions, supporting more informed decision-making.

[0083] Continuing with the cruise ship case, after establishing a stable communication link, medical experts guided on-site rescue personnel through high-definition audio and video calls. Simultaneously, computer vision algorithms processed multi-angle images and videos transmitted from the cruise ship, constructing a precise 3D model of the ship's interior and the patient's surroundings. Medical experts used augmented reality technology to see the actual scene overlaid with virtual information, gaining a better understanding of the situation. Machine learning models, based on the patient's vital signs and other key indicators, predicted the possible progression of the illness, generating a detailed prognostic report that provided a scientific basis for further treatment.

[0084] Based on the disease prediction results, the distribution strategy for special medical supplies is optimized by taking into account factors such as weather changes and ocean current direction through reinforcement learning algorithms, resulting in the optimal distribution route plan.

[0085] Based on the disease prediction results, a reinforcement learning algorithm is used to optimize the delivery strategy for special medical supplies, taking into account factors such as weather changes and ocean current direction, to obtain the optimal delivery route plan. The disease prediction results provide detailed information about the patient's condition development, while the reinforcement learning algorithm simulates different delivery routes to find the most effective delivery plan, ensuring that supplies can reach the emergency scene in the shortest time with the lowest risk.

[0086] Based on the generated disease prediction results, the system uses a comprehensive environmental factor assessment module to obtain real-time weather changes and key environmental parameters such as ocean current direction, generating an environmental condition report. Then, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model, considering factors such as transportation cost, time efficiency, and safety, to generate an initial delivery strategy. As the latest weather changes and ocean current direction data are continuously updated, the delivery strategy is adjusted accordingly to ensure the effectiveness and accuracy of delivery even in complex and changing environments, ultimately generating the optimal delivery route plan.

[0087] In the case of a cruise ship patient with a heart attack, based on the condition prediction report, the system determined that a defibrillator and medication needed to be immediately transported to the cruise ship. The system uses a comprehensive environmental factor assessment module to obtain real-time weather changes and ocean current direction data, generating an environmental condition report. Next, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model that includes transportation cost, time efficiency, and safety factors, generating an initial delivery strategy. As weather and ocean current data are continuously updated, the delivery route is optimized and adjusted multiple times to ensure that the defibrillator and medication can be safely delivered to the cruise ship in the shortest possible time, buying precious time for the patient's treatment.

[0088] Based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and form updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0089] Based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. Vital sign monitoring data includes heart rate, blood pressure, and blood oxygen saturation, reflecting the patient's health status. Specific key environmental indicators cover ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed, which affect the safety of material delivery and rescue operations.

[0090] Through optimized communication links, the system collects vital sign data and specific key environmental indicators from various monitoring devices at the emergency scene in real time. This data is transmitted back to the medical command center in real time, where deep learning algorithms are used for pattern recognition and trend prediction to generate potential risk warnings. Based on these warnings, the system reassesses and updates medical needs to ensure that all necessary medical supplies and services are delivered in a timely manner.

[0091] In the case of the cruise ship patient with a heart attack, the system continuously collected vital signs data such as heart rate, blood pressure, and blood oxygen saturation, as well as key environmental indicators such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed, through an optimized communication link. This data was transmitted back to the medical command center in real time and analyzed using deep learning algorithms, which identified a potential risk of acute myocardial infarction in the patient. Based on this potential risk warning, the system immediately updated medical needs, increased the demand for emergency medications, and notified relevant units to prepare further rescue measures to ensure the patient received the most timely and appropriate treatment.

[0092] Based on the aforementioned potential risk warnings and updated medical needs, the optimal delivery route plan is reassessed and optimized to generate an updated optimal delivery route plan, ensuring that supplies can be delivered to the emergency site in a timely and accurate manner.

[0093] Based on potential risk warnings and updated medical needs, the optimal delivery route planning is reassessed and optimized to ensure that supplies reach the emergency scene in a timely and accurate manner. Potential risk warnings provide information on possible future hazardous situations, while updated medical needs clarify new requirements for supplies and services. By reassessing and optimizing delivery routes, the system ensures the flexibility and reliability of supply delivery, improving the overall efficiency of emergency response.

[0094] Based on the generated potential risk warnings and updated medical needs, the system reassesses the existing optimal delivery route plan. Taking into account new risk factors and medical needs, the system again applies reinforcement learning algorithms to optimize the delivery route, ensuring that supplies can safely reach the emergency scene in the shortest possible time. Through continuous dynamic adjustments, the system ensures that the delivery route is always the optimal choice, enabling a rapid response even in emergency situations.

[0095] In the case of the cruise ship patient with a heart attack, the system detected a potential risk of acute myocardial infarction based on a warning of emerging risks and updated the medical needs, adding a requirement for emergency medications. Based on this new information, the system re-evaluated the original optimal delivery route plan, taking into account the latest weather changes and ocean currents, and again applied reinforcement learning algorithms to optimize the delivery route. Ultimately, the defibrillator and the newly added emergency medications were safely delivered to the cruise ship by drone in the shortest possible time, buying the patient valuable time for treatment and successfully saving their life.

[0096] This invention significantly improves the speed and accuracy of maritime emergency response, ensuring that medical supplies are delivered to the emergency site in a timely and accurate manner. Specifically, it constructs and optimizes a temporary dedicated satellite communication link, enhancing communication stability and efficiency; combines augmented reality technology and computer vision algorithms for 3D reconstruction, improving the accuracy of remote diagnosis; applies machine learning models to predict disease progression, supporting more scientific decision-making; optimizes the distribution strategy for special medical supplies through reinforcement learning algorithms, ensuring the effectiveness and safety of supply delivery; and finally, by collecting and analyzing vital sign monitoring data and specific key environmental indicators in real time, it achieves comprehensive monitoring and dynamic adjustment of the emergency response process. These improvements collectively enhance the overall performance of the system, maximizing patient safety and significantly increasing the success rate of maritime emergency response missions.

[0097] The following describes the process of transmitting maritime emergency medical information based on satellite communication, from receiving the emergency medical distress signal to optimizing the final delivery of supplies:

[0098] First, in the event of an emergency at sea, a distress signal is sent via a globally covered satellite network using satellite communication terminals (such as those from Inmarsat, Iridium, etc.) pre-deployed on ships or facilities. The distress signal is then relayed via satellite to the nearest Earth Station, which in turn transmits the information to the Rescue Coordination Center (RCC) or medical service providers.

[0099] Secondly, based on the distress location and required bandwidth, resources are dynamically allocated from the satellite operator to establish a temporary dedicated satellite communication link. Considering the characteristics of the maritime environment (such as high humidity and strong electromagnetic interference), the satellite link's modulation and demodulation schemes and coding strategies are optimized to ensure link stability and data transmission rate.

[0100] Furthermore, through the optimized satellite link, low-latency coding technology enables high-definition audio and video calls, maintaining good call quality even under weak signal conditions. Leveraging the two-way communication capability of the satellite link, real-time data sharing is achieved, including patient vital signs data, on-site images, and 3D environmental models.

[0101] Next, ensure that all data involving patient privacy is transmitted through an encrypted tunnel and directly to the telemedicine expert's terminal device via satellite link. The disease prediction model may run on a cloud server, uploading and downloading necessary computing resources and results via satellite link, reducing the local computing burden.

[0102] Next, by combining precise location services provided by satellite navigation systems (such as GPS and GLONASS) with weather forecast information from meteorological satellites, the optimal route for material delivery is selected. In the event of sudden weather changes or other influencing factors, delivery instructions can be updated in real time via satellite links to ensure timely delivery of materials.

[0103] Next, utilizing the persistent connection provided by the satellite link, vital sign monitoring data and key environmental indicators are continuously collected to ensure the continuity of information flow. This data is transmitted back to the medical command center via the satellite link, where deep learning algorithms rapidly process the massive amounts of data to generate early warning information.

[0104] Finally, the satellite-based intelligent scheduling platform can receive information from multiple sources in real time, including the latest risk warnings and changes in medical needs, thereby making the most appropriate route planning decisions. After each event, lessons learned through the satellite link will be used to improve algorithms and technical means, enhancing response speed and service quality in similar future events.

[0105] In this way, the key role of satellite communication in the entire process of maritime emergency rescue information transmission can be more clearly demonstrated, as well as how satellite communication specifically supports the effective implementation of each step.

[0106] To address the quality issues of high-definition audio and video calls and real-time data sharing, some embodiments utilize optimized communication links, combined with augmented reality technology and computer vision algorithms to perform 3D reconstruction of the on-site environment. This enables high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel. Furthermore, machine learning models are applied to analyze the severity of the illness, predict its progression, and generate disease prediction results, including:

[0107] Utilizing the optimized communication link, a high-quality communication connection is established between the emergency scene and medical experts, ensuring stable, low-latency high-definition audio and video calls. The optimized communication link supports high-bandwidth data transmission, guaranteeing the quality and efficiency of real-time data sharing, resulting in a high-quality communication connection. Based on this high-quality communication connection, combined with augmented reality technology, images and video streams from the emergency scene are processed, enabling the overlay of virtual information onto the actual scene at the medical expert's end, assisting remote diagnosis and obtaining an augmented reality-assisted remote diagnostic environment. Using computer vision algorithms, multi-angle images and videos transmitted from the scene and processed by augmented reality technology are processed to construct a precise 3D model of the emergency scene. Based on the data obtained in the augmented reality-assisted remote diagnostic environment, a precise 3D reconstruction of the scene is obtained. According to the optimized communication link and the precise 3D reconstruction of the scene, vital sign data transmitted from various monitoring devices at the scene and Specific key environmental indicators are shared in real time and displayed on the expert interface in the form of charts or values ​​to facilitate immediate assessment of the patient's condition, promote collaborative work, and obtain real-time shared vital sign data. These key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed. Input data required for the machine learning model is prepared by organizing and preprocessing the preliminary medical condition description and the vital sign data shared in real time via the communication link. Based on the real-time shared vital sign data, a structured dataset suitable for machine learning model analysis is formed. The machine learning model is then applied to quantitatively evaluate and predict trends in this structured dataset. Having learned from numerous cases, the machine learning model can quantitatively assess the severity of the condition and predict its development trend, resulting in detailed condition analysis results. Based on the detailed condition analysis results and the accurate on-site 3D reconstruction, a condition prediction report is generated.

[0108] In this embodiment, the high-quality communication connection includes establishing stable, low-latency, high-definition audio and video calls between the emergency scene and medical experts through an optimized satellite communication link. This communication link supports high-bandwidth data transmission, ensuring the quality and efficiency of real-time data sharing, thus achieving a high-quality communication connection. This connection not only provides clear audio and video streams but also supports the rapid transmission of high-resolution images and large amounts of monitoring data. The augmented reality-assisted remote diagnostic environment, based on the high-quality communication connection and combined with augmented reality technology, processes emergency scene images and video streams, enabling medical experts to overlay virtual information onto the actual scene at their end, assisting in remote diagnosis. Augmented reality technology can display key vital signs and disease predictions of patients as virtual labels on the video screen, helping medical experts to understand the situation more intuitively. Accurate 3D reconstruction of the scene utilizes computer vision algorithms to process multi-angle images and videos transmitted from the scene and processed by augmented reality technology to construct an accurate 3D model of the emergency scene. This data comes from multiple cameras and sensors, and after algorithmic processing, forms a complete 3D spatial structure, providing medical experts with a comprehensive and realistic view of the emergency scene. Real-time shared vital sign data is collected from various monitoring devices on-site, based on optimized communication links and accurate on-site 3D reconstruction, along with specific key environmental indicators. This data is displayed in charts or numerical values ​​on the expert interface. This data includes vital signs such as heart rate, blood pressure, and blood oxygen saturation, as well as environmental parameters such as temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed, facilitating immediate patient assessment and promoting collaborative work. A structured dataset suitable for machine learning model analysis serves as the input data for the machine learning model. This involves organizing and preprocessing the initial medical condition description and the vital sign data shared in real-time via the communication link to form a structured dataset suitable for machine learning model analysis. This data undergoes cleaning and normalization preprocessing steps to ensure consistent formatting and ease of analysis. Detailed disease analysis results are obtained by applying machine learning models to quantitatively assess and predict trends in the structured dataset suitable for machine learning model analysis. Through learning from numerous cases, the model can quantitatively assess the severity of the disease and predict possible development trends, ultimately generating detailed disease analysis results. These results provide a scientific basis for subsequent treatment decisions. The disease prediction report is generated based on detailed disease analysis and accurate on-site 3D reconstruction. This report not only includes the likelihood of disease deterioration but also details on symptom changes requiring special attention, providing comprehensive reference information for medical experts.

[0109] In this embodiment, firstly, an optimized communication link ensures high-definition audio and video call quality between the emergency scene and medical experts, supporting high-bandwidth data transmission and guaranteeing the quality and efficiency of real-time data sharing. Secondly, augmented reality technology is used to process emergency scene images and video streams, overlaying virtual information onto the actual scene at the medical expert's end to assist in remote diagnosis. Next, computer vision algorithms are used to process multi-angle images and videos transmitted from the scene, constructing an accurate 3D model of the emergency scene and providing a comprehensive and realistic view. Further, based on the optimized communication link and 3D reconstruction, vital sign data and specific key environmental indicators are collected and shared in real time, displayed in chart or numerical form for immediate assessment of the patient's condition. Further still, preliminary medical condition descriptions and real-time shared vital sign data are organized and preprocessed to form a structured dataset suitable for machine learning model analysis. Finally, the structured dataset is quantitatively evaluated and trend predicted to generate detailed disease analysis results. Based on the detailed disease analysis results and 3D reconstruction, a disease prediction report is generated to provide decision support for medical experts.

[0110] Here is a specific example:

[0111] Imagine a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting a passenger suffering a heart attack. Upon receiving the signal, the system quickly establishes a high-quality satellite communication link, ensuring high-definition audio and video communication between the emergency site and the onshore medical command center. Medical experts use augmented reality technology to see virtual information overlaid on the patient's surroundings; key vital signs such as the patient's heart rate and respiratory rate are displayed as virtual labels on the video feed, helping them better understand the situation.

[0112] Meanwhile, computer vision algorithms processed multi-angle images and videos transmitted from the cruise ship to construct a precise 3D model of the ship's interior and the patient's surroundings. This allowed medical experts to gain a more intuitive understanding of the site layout and patient location through the 3D view, improving the accuracy of remote diagnosis. The system collects and shares the patient's vital signs data (such as electrocardiogram and blood oxygen saturation) and specific key environmental indicators (such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed) in real time, displaying them in charts or numerical form on the expert's interface, facilitating immediate assessment of the patient's condition by medical experts.

[0113] Next, the system prepared a structured dataset suitable for machine learning model analysis, and organized and preprocessed the preliminary medical condition descriptions and real-time shared vital sign data. Then, the machine learning model was applied to quantitatively evaluate and predict trends in this data, generating detailed disease analysis results, including the likelihood of disease deterioration and symptom changes requiring special attention. Based on these analysis results, the system generated a disease prediction report, providing comprehensive reference information for medical experts and supporting more scientific treatment decisions.

[0114] Through these measures, the system not only improves the accuracy and real-time nature of remote diagnosis, but also provides medical experts with a comprehensive view of the emergency scene and detailed analysis of the patient's condition, significantly enhancing the success rate of maritime emergency rescue missions.

[0115] To address the issues of accuracy and real-time performance in 3D reconstruction of emergency scenes, some embodiments utilize computer vision algorithms to process multi-angle images and videos transmitted from the scene and processed using augmented reality technology to construct an accurate 3D model of the emergency scene. Based on data acquired in the augmented reality-assisted remote diagnostic environment, an accurate 3D reconstruction of the scene is obtained, including:

[0116] Using computer vision algorithms, the received multi-angle images and videos are preprocessed to remove noise, correct distortion, and perform color calibration, resulting in high-quality input data. Based on this high-quality input data, a feature detection algorithm is used to identify and extract stable feature points, obtaining key feature points for subsequent matching. Based on these key feature points, a feature matching algorithm is used to match key feature points from different viewpoints, and the matching results are optimized using bundle adjustment to improve the accuracy of 3D reconstruction, generating optimized feature point matching results. The optimized feature point matching results are then calculated using the principle of triangulation. The location of feature points in three-dimensional space initially forms the spatial structure of the emergency scene, resulting in a sparse three-dimensional point cloud. A multi-view stereo vision algorithm is applied to fill the gaps between the sparse three-dimensional point clouds, generating a dense three-dimensional point cloud. A Poisson surface reconstruction algorithm is used to construct a continuous three-dimensional surface from the dense three-dimensional point cloud, and the texture information of the original image is mapped onto the surface to obtain an accurate three-dimensional model. This accurate three-dimensional model is then combined with real-time scene information obtained through augmented reality technology to provide medical experts with a comprehensive and intuitive view of the emergency scene, ensuring the accuracy and effectiveness of remote diagnosis and obtaining a precise three-dimensional reconstruction of the scene.

[0117] In this embodiment, high-quality input data includes preprocessing the received multi-angle images and videos to remove noise, correct distortion, and perform color calibration. These preprocessing steps ensure the quality of the input data and improve the accuracy of subsequent feature point detection and matching. Key feature points are stable feature points in the image identified and extracted using feature detection algorithms. These feature points are unique local regions in the image, used for subsequent feature matching and 3D reconstruction. The optimized feature point matching result is achieved by matching key feature points from different viewpoints using a feature matching algorithm, and optimizing the matching result using bundle adjustment to improve the accuracy of 3D reconstruction. The optimized matching result provides more accurate spatial location information. The sparse 3D point cloud is generated by calculating the positions of the successfully matched feature points in 3D space using the principle of triangulation, initially forming the spatial structure of the emergency scene. The point cloud generated at this stage is relatively sparse, but it can already provide a basic spatial framework. The dense 3D point cloud is generated by filling the gaps between the sparse 3D point clouds using a multi-view stereo vision algorithm, generating a more detailed dense 3D point cloud. This step makes the model more complete and realistic, enhancing the effect of 3D reconstruction. The accurate 3D model is constructed by using the Poisson surface reconstruction algorithm to create a continuous 3D surface from a dense 3D point cloud, mapping the texture information of the original image onto the surface. The resulting accurate 3D model not only possesses geometric accuracy but also preserves the color and texture details of the original scene. Augmented reality-assisted remote diagnostic environments combine the accurate 3D model with real-time scene information acquired through augmented reality technology, providing medical experts with a comprehensive and intuitive view of the emergency scene, ensuring the accuracy and effectiveness of remote diagnosis.

[0118] In this embodiment, firstly, the received multi-angle images and videos are preprocessed to remove noise, correct distortion, and perform color calibration to ensure high-quality input data. Secondly, based on the high-quality input data, a feature detection algorithm is used to identify and extract stable feature points, preparing key feature points for subsequent matching. Next, a feature matching algorithm is used to match key feature points from different perspectives, and the matching results are optimized using bundle adjustment to improve the accuracy of 3D reconstruction. Then, the position of feature points in the optimized feature point matching results in 3D space is calculated using the principle of triangulation, initially forming the spatial structure of the emergency scene and obtaining a sparse 3D point cloud. Further, a multi-view stereo vision algorithm is applied to fill the gaps between the sparse 3D point clouds, generating a more detailed dense 3D point cloud, making the model more complete and realistic. Further still, a Poisson surface reconstruction algorithm is used to construct a continuous 3D surface from the dense 3D point cloud, and the texture information of the original image is mapped onto the surface to obtain an accurate 3D model. Finally, the accurate 3D model is combined with real-time scene information obtained through augmented reality technology to provide medical experts with a comprehensive and intuitive view of the emergency scene, ensuring the accuracy and effectiveness of remote diagnosis.

[0119] Here is a specific example:

[0120] As another example, consider a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly establishes a high-quality satellite communication link and begins collecting multi-angle images and video streams from the emergency scene. To construct an accurate 3D model, the system first preprocesses the received images and videos, removing noise, correcting lens distortion, and performing color calibration to ensure the quality of the input data.

[0121] Next, the system used the SIFT feature detection algorithm to identify and extract stable feature points in the image. These feature points are unique local regions in the image, used for subsequent feature matching. Through the feature matching algorithm, the system matched feature points from different viewpoints and optimized the matching results using bundle adjustment, improving the accuracy of 3D reconstruction. Subsequently, the system used the principle of triangulation to calculate the positions of the successfully matched feature points in 3D space, initially forming the spatial structure of the emergency scene and obtaining a sparse 3D point cloud.

[0122] To make the model more complete and realistic, the system applied a multi-view stereo vision algorithm to fill the gaps between sparse 3D point clouds, generating a dense 3D point cloud. Finally, a Poisson surface reconstruction algorithm was used to construct a continuous 3D surface from the dense 3D point cloud, and the texture information of the original image was mapped onto the surface, resulting in an accurate 3D model. This model not only possesses geometric accuracy but also preserves the color and texture details of the original scene.

[0123] The system combines precise 3D models with real-time scene information acquired through augmented reality technology, providing medical experts with a comprehensive and intuitive view of the emergency scene. Medical experts can see virtual information overlaid on the patient's surroundings through augmented reality devices; for example, key vital signs such as the patient's heart rate and respiratory rate are displayed as virtual labels on the video screen, helping them better understand the situation and significantly improving the accuracy and effectiveness of remote diagnosis.

[0124] Through these measures, the system not only improves the accuracy and real-time performance of 3D reconstruction of emergency scenes, but also provides medical experts with a comprehensive view of the emergency scene and detailed analysis of the patient's condition, significantly enhancing the success rate of maritime emergency rescue missions.

[0125] To address the effectiveness and accuracy issues of special medical supply delivery route planning in complex and ever-changing environments, some embodiments involve optimizing the delivery strategy for special medical supplies based on the disease prediction results, using reinforcement learning algorithms to consider factors such as weather changes and ocean current direction, to obtain the optimal delivery route plan. This includes:

[0126] Based on the disease prediction results, the comprehensive environmental factor assessment module is used to acquire and analyze key environmental parameters such as weather changes and ocean current direction in real time, resulting in an environmental condition report affecting delivery route planning. Based on the environmental condition report, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model that includes transportation cost, time efficiency, and safety factor, resulting in an initial delivery strategy. A dynamic adjustment mechanism is introduced into the initial delivery strategy, allowing for real-time updates to the delivery strategy based on the latest weather changes and ocean current direction, ensuring the effectiveness and accuracy of delivery even in complex and changeable environments, and generating continuously optimized delivery route plans. Utilizing the interactive learning process between the reinforcement learning model and actual delivery conditions, the delivery route planning is automatically adjusted, and the optimal delivery route plan is obtained based on the latest environmental changes and delivery feedback.

[0127] In this embodiment, the environmental condition report includes real-time acquisition and analysis of key environmental parameters (such as wind speed, temperature, humidity, air pressure, rainfall, and ocean current velocity) related to weather changes and ocean current direction using a comprehensive environmental factor assessment module. This data is used to generate an environmental condition report influencing delivery route planning, ensuring that the delivery route planning can adapt to changes in the actual environment. The multi-objective optimization problem model is based on the environmental condition report and uses reinforcement learning algorithms to create a multi-objective optimization problem model that includes transportation costs, time efficiency, and safety factors. This model considers not only the cost-effectiveness of delivery but also time and safety, ensuring that the optimal delivery strategy is found under various constraints. The initial delivery strategy is a preliminary delivery plan generated by the multi-objective optimization problem model, serving as the basis for subsequent dynamic adjustments. This strategy considers current environmental conditions and medical needs, providing an initial delivery route plan. The dynamic adjustment mechanism introduces a dynamic adjustment mechanism that allows the delivery strategy to be updated in real-time with the latest weather changes and ocean current direction. This mechanism ensures that the effectiveness and accuracy of delivery are maintained even in complex and changing environments, generating continuously optimized delivery route plans. The interactive learning process utilizes the interaction between the reinforcement learning model and actual delivery conditions to automatically adjust the delivery route planning. The system continuously optimizes delivery routes based on the latest environmental changes and delivery feedback, ultimately arriving at the optimal delivery route plan. This interactive learning process enables the system to continuously improve and adapt to new situations during actual operation.

[0128] In this embodiment, firstly, based on the disease prediction results, a comprehensive environmental factor assessment module is used to acquire and analyze key environmental parameters related to weather changes and ocean current direction in real time, generating an environmental condition report affecting delivery route planning. Secondly, based on the environmental condition report, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model that includes transportation cost, time efficiency, and safety factor, resulting in an initial delivery strategy. Then, a dynamic adjustment mechanism is introduced to the initial delivery strategy, allowing for real-time updates to the strategy based on the latest weather changes and ocean current direction, ensuring the effectiveness and accuracy of delivery even in complex and changing environments. Finally, through the interactive learning process between the reinforcement learning model and actual delivery conditions, the delivery route planning is automatically adjusted, and the optimal delivery route plan is obtained based on the latest environmental changes and delivery feedback.

[0129] Here is a specific example:

[0130] As another example, consider a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly generates a detailed prognosis report and initiates the delivery process for specialized medical supplies (such as a defibrillator and medications).

[0131] First, the system utilizes a comprehensive environmental factor assessment module to acquire and analyze key environmental parameters related to weather changes and ocean current direction (such as wind speed, temperature, humidity, air pressure, rainfall, and ocean current velocity) in real time, generating an environmental condition report affecting delivery route planning. This report details the current and future weather conditions and ocean current dynamics, providing crucial reference information for delivery route planning.

[0132] Next, based on the environmental condition report, the system applied a reinforcement learning algorithm to create a multi-objective optimization problem model that included transportation cost, time efficiency, and safety factors. This model not only considered the cost-effectiveness of delivery but also took into account time and safety, ensuring that the optimal delivery strategy was found under various constraints. By simulating different delivery scenarios, the system generated a preliminary delivery plan, i.e., an initial delivery strategy, determining the optimal route from the nearest medical supply depot to the cruise ship.

[0133] To cope with the complex marine environment, the system incorporates a dynamic adjustment mechanism that allows delivery strategies to be updated in real time based on the latest weather changes and ocean current directions. For example, if the forecast indicates strong winds or large waves, the system will automatically adjust the delivery route, choosing a safer but potentially slower route to ensure the safe delivery of supplies. This dynamic adjustment mechanism ensures the effectiveness and accuracy of delivery even in complex and changing environments, generating continuously optimized delivery route plans.

[0134] Finally, the system utilizes the interactive learning process between the reinforcement learning model and actual delivery conditions to automatically adjust the delivery route planning. When drones or rapid response vessels are performing delivery missions, the system continuously optimizes the delivery route based on the latest environmental changes (such as real-time wind speed and ocean current strength) and delivery feedback (such as actual speed and fuel consumption). Through continuous interactive learning, the system ultimately obtains the optimal delivery route plan, ensuring that defibrillators and medications can be safely delivered to the cruise ship in the shortest possible time, saving valuable treatment time for the patient.

[0135] Through these measures, the system has not only improved the effectiveness and accuracy of route planning for the delivery of special medical supplies, but also maintained the flexibility and reliability of delivery in the complex and ever-changing marine environment, significantly enhancing the success rate of maritime emergency rescue missions.

[0136] To address the challenge of balancing transportation costs, time efficiency, and safety in complex environments, some embodiments involve using reinforcement learning algorithms to create a multi-objective optimization model that incorporates transportation costs, time efficiency, and safety factors based on the environmental condition report, thereby obtaining an initial delivery strategy, including:

[0137] Using the environmental condition report, key environmental parameters such as weather changes and ocean current direction are analyzed in depth to obtain the factors affecting delivery route selection and material delivery time. Based on the factor analysis results, multiple optimization objectives are defined, including minimizing transportation costs, maximizing time efficiency, and ensuring the highest safety factor, generating a multi-objective optimization framework. A reinforcement learning algorithm is applied to construct a multi-objective optimization problem model that can handle the trade-offs between different optimization objectives, using the objective definitions and weight allocations in the multi-objective optimization framework as the basis for model construction. A simulation environment is built to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model, which is then used in the simulation environment. Through numerous simulation experiments, the reinforcement learning model continuously attempts delivery route selection in the simulation environment, adjusting the trade-offs between objectives based on feedback, gradually converging to the optimal strategy combination to obtain a preliminary optimized delivery plan. Based on the preliminary optimized delivery plan, combined with the latest environmental conditions and actual delivery needs, a final adjustment is made to generate an initial delivery strategy.

[0138] In this embodiment, the factor analysis results utilize the environmental condition report to perform in-depth analysis of key environmental parameters (such as wind speed, temperature, humidity, air pressure, rainfall, and ocean current speed) related to weather changes and ocean current direction, obtaining factor analysis results that influence delivery route selection and material delivery time. These factor analysis results provide important information about the optimal delivery route under different environmental conditions.

[0139] The multi-objective optimization framework, based on the aforementioned factor analysis results, defines multiple optimization objectives, including minimizing transportation costs, maximizing time efficiency, and ensuring the highest safety factor, thus generating the multi-objective optimization framework. Each optimization objective has a clear definition and weight allocation, used to guide subsequent model construction and optimization processes. The multi-objective optimization problem model applies reinforcement learning algorithms and, based on the aforementioned multi-objective optimization framework, constructs a multi-objective optimization problem model capable of handling the trade-offs between different optimization objectives. This model not only considers the optimal solution for a single objective but also finds the global optimum by adjusting the weights between objectives. The simulation environment constructs a simulation environment to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model. The simulation environment can simulate various possible delivery situations, including different weather conditions, ocean current directions, traffic congestion, and other factors, helping the model better adapt to the real-world environment. The optimal strategy combination is determined through extensive simulation experiments, allowing the reinforcement learning model to continuously try delivery route selections in the simulation environment and adjust the trade-offs between objectives based on feedback, gradually converging to the optimal strategy combination. This process enables the model to find the most suitable delivery route in complex environments. The initial delivery strategy is generated by making final adjustments based on the previously optimized delivery plan, combined with the latest environmental conditions and actual delivery needs. This strategy not only considers changes in the current environment but also fine-tunes itself according to actual delivery requirements to ensure its applicability and effectiveness.

[0140] In this embodiment, firstly, the environmental condition report is used to perform in-depth analysis of key environmental parameters such as weather changes and ocean current direction, obtaining the analysis results of factors affecting delivery route selection and material delivery time. Secondly, based on the factor analysis results, multiple optimization objectives are defined, including minimizing transportation costs, maximizing time efficiency, and ensuring the highest safety factor, generating a multi-objective optimization framework, and clarifying the definition and weight allocation of each objective. Next, a reinforcement learning algorithm is applied, and a multi-objective optimization problem model capable of handling the trade-offs between different optimization objectives is constructed according to the multi-objective optimization framework. Further, a simulation environment is constructed to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model, and the multi-objective optimization model is used in the simulation environment. Further still, through numerous simulation experiments, the reinforcement learning model continuously attempts delivery route selection in the simulation environment, adjusting the trade-offs between objectives based on feedback, gradually converging to the optimal strategy combination, obtaining a preliminary optimized delivery plan. Finally, based on the preliminary optimized delivery plan, combined with the latest environmental conditions and actual delivery needs, a final adjustment is made to generate an initial delivery strategy.

[0141] Here is a specific example:

[0142] As another example, consider a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly generates a detailed prognosis report and initiates the delivery process for specialized medical supplies (such as a defibrillator and medications).

[0143] First, the system utilizes a comprehensive environmental factor assessment module to acquire and analyze key environmental parameters related to weather changes and ocean current direction (such as wind speed, temperature, humidity, air pressure, rainfall, and ocean current velocity) in real time, generating an environmental condition report affecting delivery route planning. This report details the current and future weather conditions and ocean current dynamics, providing crucial reference information for delivery route planning.

[0144] Next, the system performed in-depth analysis of these key environmental parameters, obtaining the results of factor analysis affecting delivery route selection and material delivery time. For example, strong winds may cause drone flight instability, large waves may increase the risk of ship navigation, and low temperatures may affect equipment performance. These factor analysis results provide a foundation for subsequent optimization.

[0145] Based on the analysis of these factors, the system defined multiple optimization objectives, including minimizing transportation costs, maximizing time efficiency, and ensuring the highest safety factor, generating a multi-objective optimization framework. Each optimization objective was assigned a corresponding weight to reflect its importance. For example, the safety factor might be given a higher weight because the patient's life safety is of paramount importance.

[0146] Then, the system applies reinforcement learning algorithms and, based on the aforementioned multi-objective optimization framework, constructs a multi-objective optimization problem model capable of handling trade-offs between different optimization objectives. This model not only considers the optimal solution for a single objective but also finds the global optimum by adjusting the weights between the objectives. To train this model, the system constructs a simulation environment that simulates various delivery scenarios, including sunny days, heavy rain, strong winds, and large waves. The simulation environment provides the model with rich training data, enabling it to better adapt to real-world environments.

[0147] In the simulation environment, the reinforcement learning model continuously attempts to select delivery routes and adjusts the trade-offs between various objectives based on feedback. For example, if a certain route is the fastest but too risky, the model will automatically adjust to select a safer but slightly slower route. After numerous simulation experiments, the model gradually converges to the optimal combination of strategies, yielding a preliminary optimized delivery solution.

[0148] Finally, based on the initially optimized delivery plan, and considering the latest environmental conditions (such as real-time wind speed and ocean current intensity) and actual delivery needs (such as the type and quantity of supplies), the system made final adjustments and generated an initial delivery strategy. For example, if the latest forecast indicates strong winds are imminent, the system will reassess and select a safer route to ensure the supplies arrive at the cruise ship safely. Through continuous interactive learning, the system ultimately determined the optimal delivery route, ensuring that the defibrillator and medications could be safely delivered to the cruise ship in the shortest possible time, buying valuable time for the patient's treatment.

[0149] Through these measures, the system not only improves the adaptability and accuracy of multi-objective optimization problem models in complex environments, but also maximizes delivery efficiency while ensuring safety, significantly enhancing the success rate of maritime emergency rescue missions.

[0150] To address the issues of real-time performance and accuracy in emergency scene data collection and analysis, some embodiments involve collecting vital sign monitoring data and specific key environmental indicators via the optimized communication link, transmitting this data back to the medical command center in real time, and applying deep learning algorithms for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. This includes:

[0151] Using the optimized communication link, vital sign monitoring data and specific key environmental indicators at the emergency scene are collected and processed to obtain coded monitoring data. These key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed. Based on this coded monitoring data, the data is transmitted in real-time through the optimized communication link to obtain a data stream transmitted to the medical command center. According to this data stream, a deep learning algorithm deployed at the medical command center analyzes the vital sign monitoring data and key environmental indicators to obtain pattern recognition results. These key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed. Based on these pattern recognition results, a deep learning model is used to predict the development trend of the patient's condition, generating a trend prediction report. Based on this trend prediction report, the system automatically generates potential risk warnings for each patient, providing warning information that includes current risk factors and future risk indications. Based on this warning information, the medical command center reassesses and adjusts the emergency response plan, forming updated medical needs.

[0152] In this embodiment, the encoded monitoring data is obtained by collecting and processing vital sign monitoring data (such as heart rate, blood pressure, and blood oxygen saturation) and specific key environmental indicators (such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed) at the emergency site using the optimized communication link. This encoded data facilitates efficient transmission and subsequent processing. The real-time data stream transmitted to the medical command center is based on the encoded monitoring data and is processed in real-time through the optimized communication link. This process ensures the timeliness and reliability of the data, enabling the medical command center to quickly obtain the latest information. Pattern recognition results are obtained by applying deep learning algorithms deployed at the medical command center to analyze the vital sign monitoring data and specific key environmental indicators based on the real-time data stream transmitted to the medical command center. These results not only reflect the current health status but also reveal potential abnormal patterns. The trend prediction report is generated based on the pattern recognition results, using a deep learning model to predict the development trend of the patient's condition. This report details the potential future trends of the patient's condition, providing a scientific basis for medical decision-making. Based on the trend prediction report, the system automatically generates potential risk warnings for each patient, including current risk factors and potential future risks. These warnings help medical experts anticipate and address potential risks in advance. Updated medical needs are based on the warning information; the medical command center reassesses and adjusts the emergency response plan to form updated medical needs. These new medical needs take into account the latest changes in the patient's condition and environmental conditions, ensuring the effectiveness and relevance of treatment measures.

[0153] First, using the optimized communication link, vital sign monitoring data and specific key environmental indicators at the emergency scene are collected and processed to obtain coded monitoring data. Second, based on the coded monitoring data, the data is transmitted in real-time through the optimized communication link, resulting in a data stream transmitted to the medical command center. Next, based on the data stream transmitted to the medical command center, a deep learning algorithm deployed at the medical command center is applied to analyze the vital sign monitoring data and specific key environmental indicators, obtaining pattern recognition results. Further, based on the pattern recognition results, a deep learning model is used to predict the development trend of the patient's condition, generating a trend prediction report. Even further, based on the trend prediction report, the system automatically generates potential risk warnings for each patient, obtaining warning information that includes current risk factors and future risk indications. Finally, based on the warning information, the medical command center reassesses and adjusts the emergency response plan, forming updated medical needs.

[0154] Here is a specific example:

[0155] As another example, consider a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly establishes an optimized satellite communication link and begins collecting vital sign monitoring data and specific key environmental indicators from the emergency scene in real time.

[0156] First, the system utilizes an optimized communication link to collect and process vital sign monitoring data (such as heart rate, blood pressure, and blood oxygen saturation) and specific key environmental indicators (such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed) at the emergency scene, resulting in coded monitoring data. This encoded data facilitates efficient transmission and subsequent processing.

[0157] Next, the system uses an optimized communication link to transmit and process the coded monitoring data in real time, ensuring that the medical command center can quickly obtain the latest information. The real-time data stream includes changes in the patient's vital signs and environmental conditions, providing rich data support for subsequent analysis.

[0158] At the medical command center, deployed deep learning algorithms performed detailed analysis of the real-time data streams, yielding pattern recognition results. For example, the algorithm detected abnormal fluctuations in a patient's heart rate and identified a risk that low ambient temperatures might cause a drop in the patient's body temperature. These pattern recognition results not only reflected the current health status but also revealed potential abnormal patterns.

[0159] Based on these pattern recognition results, the system used a deep learning model to predict the progression of the patient's condition and generated a trend prediction report. The report indicated that if the current low temperatures persisted, the patient might be at risk of hypothermia and recommended immediate measures to keep warm. Furthermore, the model also predicted the likelihood of the patient's cardiac function deteriorating in the coming hours, alerting medical experts to be prepared.

[0160] Based on the trend prediction report, the system automatically generated potential risk warnings for this patient, providing information including current risk factors (such as abnormal heart rate fluctuations and cold environments) and potential future risks (such as hypothermia and deterioration of cardiac function). This information helps medical experts anticipate and address potential risks in advance.

[0161] Finally, based on the aforementioned early warning information, the medical command center reassessed and adjusted the emergency response plan, resulting in updated medical needs. For example, the need for warming equipment was increased, and additional medical supplies (such as heating blankets and thermal clothing) were arranged to ensure patients received appropriate treatment in the shortest possible time. Simultaneously, the system adjusted the drone delivery routes, selecting safer but slightly slower routes to ensure the safe delivery of supplies.

[0162] Through these measures, the system not only improves the real-time performance and accuracy of emergency scene data collection and analysis, but also maintains the effectiveness and relevance of treatment measures in complex and ever-changing environments, significantly enhancing the success rate of maritime emergency rescue missions.

[0163] To address the effectiveness and adaptability of emergency medical supply delivery strategies in the face of potential risks and evolving needs, some embodiments involve reassessing and optimizing the optimal delivery route plan based on the potential risk warning and updated medical needs, generating an updated optimal delivery route plan to ensure timely and accurate delivery of supplies to the emergency medical scene. This includes:

[0164] Using the aforementioned potential risk warnings, risk factors at the emergency scene are analyzed and processed to obtain a detailed risk assessment report. Based on the risk assessment report and the updated medical needs, the current medical supply needs are reassessed, generating a new medical supply demand list. According to the new medical supply demand list, the existing optimal delivery route plan is checked to see if it needs adjustment to adapt to the new demand changes, and aspects that need optimization are initially identified. Based on the initially identified optimization aspects, considering the latest environmental conditions, the optimal delivery route is replanned to ensure that the supply delivery strategy meets the latest medical needs and risk warnings. Through continuous updating and adjustment, an updated optimal delivery route plan is finally generated to ensure that special medical supplies can be delivered to the emergency scene in a timely and accurate manner.

[0165] In this embodiment, the detailed risk assessment report is generated by analyzing and processing risk factors at the emergency scene using the potential risk warning. This report not only includes existing risk factors (such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed) but also predicts potential future risks and provides corresponding response suggestions. The latest medical supply demand list is generated based on the risk assessment report and the updated medical needs, reassessing the current medical supply requirements. This list clarifies the types, quantities, and urgency of the required supplies, providing clear guidance for subsequent distribution planning. Preliminary optimization aspects are determined based on the latest medical supply demand list, examining whether the existing optimal distribution route plan needs adjustment to adapt to new demand changes, and preliminarily identifying aspects requiring optimization. For example, it may be necessary to increase or decrease the transport volume of certain supplies, or choose a safer but slightly slower distribution route. The optimal distribution route is then replanned based on the preliminarily determined optimization aspects, considering the latest environmental conditions (such as weather forecasts, ocean current direction, etc.), to ensure that the supply distribution strategy conforms to the latest medical needs and risk warnings. This process ensures the safety and timeliness of the delivery route. The updated optimal delivery route plan is generated through continuous updates and adjustments, ensuring that special medical supplies can be delivered to the emergency site in a timely and accurate manner. This plan not only considers the latest changes in demand but also incorporates real-time environmental data, improving the reliability and flexibility of delivery.

[0166] In this embodiment, firstly, the potential risk warning is used to analyze and process the risk factors at the emergency scene, resulting in a detailed risk assessment report. Secondly, based on the risk assessment report and the updated medical needs, the current medical supply needs are reassessed, generating a new medical supply demand list. Then, according to the latest medical supply demand list, the existing optimal delivery route plan is checked to see if it needs adjustment to adapt to the new demand changes, and aspects requiring optimization are preliminarily identified. Further, based on the preliminarily identified optimization aspects, and considering the latest environmental conditions, the optimal delivery route is replanned to ensure that the supply delivery strategy conforms to the latest medical needs and risk warning situation. Finally, through continuous updating and adjustment, an updated optimal delivery route plan is generated to ensure that special medical supplies can be delivered to the emergency scene in a timely and accurate manner.

[0167] Here is a specific example:

[0168] As another example, consider a maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly generates a detailed prognosis report and initiates the delivery process for specialized medical supplies (such as a defibrillator and medications). As the condition progresses and environmental conditions change, the system needs to continuously optimize the delivery route to ensure timely and accurate delivery of the supplies.

[0169] First, the system utilized potential risk warnings to analyze and process risk factors at the emergency scene, resulting in a detailed risk assessment report. The report indicated that low nighttime temperatures could lead to a drop in patient body temperature, and that future strong winds and high waves could affect the delivery safety of drones and boats. This information helped the system gain a comprehensive understanding of the complex environment at the emergency scene.

[0170] Next, based on the risk assessment report and the updated medical needs, the system reassessed the current medical supply requirements and generated an updated list of medical supply needs. The list added the need for warming equipment (such as heating blankets and thermal clothing) and adjusted the quantity and type of medications to better address the progression of the patient's condition and changes in the environment.

[0171] Based on the latest list of medical supply needs, the system reviewed existing optimal delivery route plans and preliminarily identified areas requiring optimization. For example, considering the strong winds and high waves expected in the coming days, the system decided to choose a safer but slightly slower delivery route to ensure the safe delivery of supplies.

[0172] Then, based on the initially determined optimization aspects, the system replanned the optimal delivery route, taking into account the latest environmental conditions (such as weather forecasts and ocean current directions). The system simulated delivery time, cost, and safety under different routes and ultimately selected the best route. For example, choosing a route that bypasses the storm area, although slightly longer, avoids the risks posed by severe weather.

[0173] Finally, through continuous updates and adjustments, the system generates an updated optimal delivery route plan, ensuring that special medical supplies can be delivered to the emergency site in a timely and accurate manner. The system continuously monitors environmental changes and delivery progress, dynamically adjusting routes to ensure the successful completion of delivery tasks. For example, when the weather in a certain area improves, the system automatically switches back to a faster route to shorten delivery time.

[0174] Through these measures, the system not only improves the effectiveness and adaptability of emergency medical supplies delivery strategies, but also maintains the safety and reliability of delivery in complex and ever-changing environments, significantly enhancing the success rate of maritime emergency medical missions.

[0175] This application considers that in maritime emergency rescue scenarios, the planning of delivery routes for specialized medical supplies faces numerous challenges, such as complex weather changes and ocean currents. Traditional single-objective optimization methods struggle to simultaneously consider the three key indicators of transportation cost, time efficiency, and safety. Therefore, a multi-objective optimization method is needed to balance these conflicting objectives and ensure the optimal delivery strategy in complex and ever-changing environments. Thus, a new alternative solution is proposed, which includes:

[0176] Based on the environmental condition report, a reinforcement learning algorithm is applied to create a multi-objective optimization problem model that includes transportation cost, time efficiency, and safety factor, resulting in an initial delivery strategy, including:

[0177] Using the aforementioned environmental condition report, in-depth analysis of key environmental parameters related to weather changes and ocean current direction is performed to obtain the analysis results of factors affecting delivery route selection and material delivery time. Key environmental parameters include wind speed, temperature, rainfall, and ocean current speed.

[0178] Based on the factor analysis results, multiple optimization objectives are defined, generating a multi-objective optimization framework. The resulting optimization objective definitions and weight allocations will serve as data inputs for the next step. The optimization objectives include minimizing transportation cost C. t Maximize time efficiency E t And ensure the highest safety factor F t The weights for each objective are w. C w E and w F And satisfying ∑w i =1;

[0179] The weight w is expressed by the following formula. C w E and w F :

[0180]

[0181] Among them, α, β, and γ are adjustment factors used to adjust the importance of different objectives; C t It is to minimize transportation costs; E t It is to maximize time efficiency; F t It ensures the highest safety factor; e is the natural base.

[0182] By applying reinforcement learning algorithms and based on the aforementioned multi-objective optimization framework, a multi-objective optimization problem model capable of handling trade-offs between different optimization objectives is constructed; the multi-objective optimization problem model uses the objectives and their weights in the aforementioned multi-objective optimization framework as the basis for its construction.

[0183] The multi-objective optimization problem can be expressed by the following formula:

[0184]

[0185] Among them, C d It's the transportation cost, E d It's about time efficiency, F d δ is the safety factor; δ, ∈ and ζ are the exponential factors of transportation cost, time efficiency and safety factor, respectively, used to adjust the degree of influence of each objective;

[0186] A simulation environment is constructed to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model. Information obtained from the multi-objective optimization problem model is used to guide the design of the simulation environment, ensuring that the multi-objective optimization problem model can be trained under near-realistic conditions.

[0187] Through numerous simulation experiments, the reinforcement learning model is allowed to continuously try delivery route selection in the simulation environment, and the trade-offs between various objectives are adjusted based on feedback, gradually converging to the optimal strategy combination to obtain a preliminary optimized delivery solution.

[0188] The updated policy π for each iteration t is calculated using the following formula. t+1 :

[0189]

[0190] Among them, C d (π), E d (π), F d (π) represents the transportation cost, time efficiency, and safety factor when using strategy π.

[0191] The following is a detailed explanation of each parameter:

[0192] Key environmental parameters:

[0193] Wind speed: Affects the speed and stability of drones or ships. Data is obtained in real time via weather stations or satellites.

[0194] Temperature: May affect equipment performance (e.g., battery life). Obtained through on-site sensors or weather forecast data.

[0195] Rainfall: May reduce visibility or increase the risk of skidding. Obtained through weather radar or weather forecast data.

[0196] Ocean current speed: affects the course and speed of ships at sea. This information is obtained through ocean monitoring systems or historical data analysis.

[0197] C tThis involves minimizing transportation costs, reducing fuel consumption, and labor costs. This is achieved through historical data analysis from the logistics management system.

[0198] E t The goal is to maximize time efficiency and minimize delivery time. This is calculated using historical delivery time and traffic data.

[0199] F t This ensures the highest safety level and guarantees zero accidents during delivery. It is determined through risk assessment models and historical accident data.

[0200] w C The weight of transportation costs indicates the importance of minimizing transportation costs. It is set based on historical data and specific application scenarios.

[0201] w E The weight of time efficiency indicates the importance of maximizing time efficiency. It is set according to the urgency of the task.

[0202] w F The weight of the safety factor indicates the importance of ensuring the highest possible safety level. It is set based on the mission risk assessment.

[0203] C d This refers to transportation costs, representing the actual transportation costs when employing a specific delivery strategy, including fuel consumption, labor costs, etc. It is obtained through historical data statistics from the logistics management system.

[0204] E d Time efficiency refers to the delivery time when a certain delivery strategy is adopted, that is, the total time required from the starting point to the destination. It is calculated using a GPS positioning system or a route planning algorithm in a simulated environment.

[0205] F d This is the safety factor, representing the safety of a particular delivery strategy. It is typically a value between 0 and 1, with 1 indicating complete safety. It is determined through risk assessment models and historical incident data.

[0206] α: The importance of adjusting transportation costs. This is determined based on the specific application scenario; for example, in situations with limited resources, the α value can be increased to place greater emphasis on cost control.

[0207] β: The importance of adjusting time efficiency. In emergency situations, this value can be increased to prioritize rapid response.

[0208] γ: The importance of adjusting the safety factor. For high-risk tasks, the γ value should be increased to ensure safety is prioritized.

[0209] δ: Adjusts the degree of impact on transportation costs. It is usually set to a positive value to emphasize cost savings.

[0210] ∈: Adjusts the degree of impact on time efficiency. Usually set to a positive value to emphasize rapid response.

[0211] ζ: Adjusts the degree of influence of the safety factor. It is usually set to a negative value to emphasize safety.

[0212] π represents a delivery route selection scheme, including the starting point, waypoints, destination, and information such as speed and route for each segment. It is obtained through iterative optimization using a reinforcement learning algorithm. After each iteration, it is updated to the optimal strategy π. t+1 .

[0213] C d (π): This represents the transportation cost, indicating the actual transportation cost when using a specific delivery strategy π, including fuel consumption, labor costs, etc. It is obtained through historical data statistics from the logistics management system and adjusted for current environmental conditions (such as wind speed and ocean current speed).

[0214] E d (π): This represents the time efficiency, indicating the delivery time when a certain delivery strategy T is adopted, i.e., the total time required from the starting point to the destination. It is calculated using a GPS positioning system or a route planning algorithm in a simulated environment, taking into account real-time traffic conditions and weather effects.

[0215] F d (π): This is the safety factor, representing the safety of a given delivery strategy π. It is typically a value between 0 and 1, with 1 indicating complete safety. It is determined through risk assessment models and historical accident data, and dynamically adjusted in conjunction with current environmental conditions (such as wind speed and rainfall).

[0216] The following explains the rationale behind each sub-item design:

[0217] This component represents the contribution of transportation costs to the multi-objective optimization problem. By introducing an exponential factor δ, the impact of transportation costs on the overall objective can be flexibly adjusted. When δ is large, the impact of transportation costs is amplified; conversely, it is reduced. This approach allows the system to flexibly adjust the importance of cost control under different scenarios.

[0218] This item represents the contribution of time efficiency to multi-objective optimization problems. The reciprocal of time efficiency is used. This is because the shorter the time, the larger its reciprocal, thus highlighting the importance of time efficiency in the optimization process. By introducing an exponential factor ∈, the impact of time efficiency on the overall goal can be flexibly adjusted. When ∈ is large, the impact of time efficiency is amplified; conversely, it is reduced.

[0219] This component represents the contribution of the safety factor to the multi-objective optimization problem. (Using...) Because of the safety factor F d The closer the value is to 1 (i.e., the safer), the smaller it becomes, thus emphasizing the priority of safety during the optimization process. By introducing an exponential factor, the impact of the safety factor on the overall objective can be flexibly adjusted. When ζ is large, the impact of safety is amplified; conversely, it is reduced.

[0220] Adding the three components allows for linear combinations of different objectives, making it easier to understand and implement. The weight and exponential factor of each component ensure that the importance of its respective objective is reflected in the final optimization result. Transportation cost, time efficiency, and safety are often conflicting objectives. By adding them together, the importance of each objective can be flexibly adjusted in different application scenarios to find an optimal compromise.

[0221] The purpose of the entire formula is to construct a multi-objective optimization framework that can balance the three conflicting objectives of transportation cost, time efficiency, and safety in complex and ever-changing environments. By introducing weights and exponential factors, the model can flexibly adjust the importance of each objective according to specific application scenarios. Simultaneously, using reinforcement learning algorithms, different delivery route selections are continuously tried in a simulation environment, and the trade-offs between objectives are adjusted based on feedback, gradually converging to the optimal strategy combination.

[0222] w C ·C d (π) δ This component represents the contribution of transportation costs to the multi-objective optimization problem. By introducing an exponential factor δ, the impact of transportation costs on the overall objective can be flexibly adjusted. When δ is large, the impact of transportation costs is amplified; conversely, it is reduced. This approach allows the system to flexibly adjust the importance of cost control in different scenarios.

[0223] This item represents the contribution of time efficiency to multi-objective optimization problems. The reciprocal of time efficiency is used. This is because the shorter the time, the larger its reciprocal, thus highlighting the importance of time efficiency in the optimization process. By introducing an exponential factor ∈, the impact of time efficiency on the overall goal can be flexibly adjusted. When ∈ is large, the impact of time efficiency is amplified; conversely, it is reduced.

[0224] w F ·(1-F d (π)ζ): This term represents the contribution of the safety factor to the multi-objective optimization problem. Use Because of the safety factor F dThe closer the value is to 1 (i.e., the safer it is), the smaller its value, thus emphasizing the priority of safety during the optimization process. By introducing an exponential factor ζ, the impact of the safety factor on the overall objective can be flexibly adjusted. When ζ is large, the impact of safety is amplified; conversely, it is reduced.

[0225] Adding the three components allows for linear combinations of different objectives, making it easier to understand and implement. The weight and exponential factor of each component ensure that the importance of its respective objective is reflected in the final optimization result. Transportation cost, time efficiency, and safety are often conflicting objectives. By adding them together, the importance of each objective can be flexibly adjusted in different application scenarios to find an optimal compromise.

[0226] The purpose of the entire formula is to construct a multi-objective optimization framework that can balance the three conflicting objectives of transportation cost, time efficiency, and safety in complex and ever-changing environments. By introducing weights and exponential factors, the model can flexibly adjust the importance of each objective according to specific application scenarios. Simultaneously, using reinforcement learning algorithms, different delivery route selections are continuously tried in a simulation environment, and the trade-offs between objectives are adjusted based on feedback, gradually converging to the optimal strategy combination.

[0227] Here is a specific example:

[0228] Suppose a cruise ship sends out an emergency medical distress signal, reporting that a passenger has suffered a heart attack. Upon receiving the signal, the system quickly generates a detailed prognosis report and initiates the delivery process for specialized medical supplies (such as a defibrillator and medication). To ensure the supplies are safely delivered to the cruise ship in the shortest possible time, the system applies the aforementioned multi-objective optimization problem model for path planning.

[0229] The following are the parameter settings:

[0230] Regulation factors: α = 0.1, β = 0.2, γ = 0.3; Exponential factors: δ = 1, ∈ = 1, ( = 1;

[0231] Initial weights: W C =0.4, W E =0.3, W F =0.3;

[0232] Assume the current environmental conditions are as follows:

[0233] Wind speed: 15 m / s; Temperature: 15℃; Rainfall: 5 mm / h; Ocean current speed: 2 knots;

[0234] Calculate the weights:

[0235] Assume transportation cost C t= 500 yuan, time efficiency E t =6 hours, safety factor F t =0.9 (out of 1):

[0236]

[0237] After calculation, the updated weight values ​​are obtained:

[0238] W C ≈0.0001;

[0239] W E ≈0.748;

[0240] W F ≈0.252;

[0241] Constructing a multi-objective optimization problem model:

[0242] Suppose that in a certain iteration, the transportation cost C under strategy π is... d (π) = 450 yuan, time efficiency E d (π) = 5 hours, safety factor F d (π)=0.95

[0243] The objective function is then min(0.0001·450). 1 +0.748·(1 / 5) 1 +0.252·(1-0.95 1 ))

[0244] The calculation result is:

[0245] min(0.045+0.1496+0.126)≈0.321

[0246] Update strategy:

[0247] Update policy π using the following formula. t+1 :

[0248]

[0249] Suppose that after multiple iterations, the system finds a new path that reduces transportation costs to 400 yuan, increases time efficiency to 4 hours, and keeps the safety factor unchanged at 0.95.

[0250] The new optimization objective function is then min(0.0001·400). 1 +0.748·(1 / 4) 1 +0.252·(1-0.95 1 ))

[0251] The calculation result is:

[0252] min(0.04+0.187+0.126)≈0.353

[0253] Since the optimization target value of the new route is slightly higher than the previous result, it indicates that although transportation costs and time efficiency have improved, it is not significantly better than the previous route overall. Therefore, the system may choose to maintain the original route or make further fine-tuning to find a better solution.

[0254] The calculations above lead to the following conclusions: the initial weights were set to 0.4 for transportation cost, 0.3 for time efficiency, and 0.3 for safety factor. Calculating the updated weights revealed that the importance of time efficiency was significantly amplified, while the impact of transportation cost became very small. This indicates that, in the current environment, time efficiency is the most important optimization objective, followed by safety factor, and lastly transportation cost. Although the new path reduced transportation cost and improved time efficiency, the overall optimization objective value did not decrease significantly due to the high weight of time efficiency. This suggests that in practical applications, it may be necessary to re-evaluate the weights of each objective or explore other potential paths to find the true optimal solution. Through continuous iteration and feedback adjustments, the system can gradually approach the optimal path. In this process, the simulation environment provides an important training platform, helping the system better adapt to the complex and ever-changing marine environment.

[0255] In summary, this multi-objective optimization model not only effectively solves the problem of special medical supply delivery route planning in maritime emergency rescue scenarios, but also maintains the safety and reliability of delivery in complex and ever-changing environments, significantly enhancing the success rate of maritime emergency rescue missions.

[0256] This application recognizes that in emergency medical rescue scenarios, particularly maritime emergency rescue missions, the real-time collection and analysis of vital sign monitoring data and specific key environmental indicators are crucial for the effective treatment of patients. Traditional data analysis methods often struggle to handle large, complex, and dynamically changing data streams, failing to provide accurate disease prediction and risk warnings. Therefore, an efficient and intelligent data processing method is needed to support telemedicine decision-making. This application proposes a new alternative solution, which includes:

[0257] The optimized communication link is used to collect vital sign monitoring data and specific key environmental indicators, which are transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0258] Using the optimized communication link, vital sign monitoring data and specific key environmental indicators at the emergency scene are collected and processed to obtain coded monitoring data. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed.

[0259] Based on the encoded monitoring data, the encoded monitoring data is processed in real time through the optimized communication link to obtain a data stream that is transmitted to the medical command center in real time, ensuring the security and reliability of data transmission. Encryption technology and redundancy mechanisms are used to prevent data loss or leakage.

[0260] Based on the data stream D transmitted in real time to the medical command center, a deep learning algorithm deployed at the medical command center is used to analyze and process the vital signs monitoring data and specific key environmental indicators to obtain the pattern recognition result R.

[0261] The pattern recognition result R is calculated using the following formula:

[0262]

[0263] Where f(·) is the feature extraction function in the deep learning model; θ represents the model parameters; w i It is each data point D i The weights; α1 is an exponential factor that adjusts the degree of influence of each data point; R is the result obtained by the deep learning model after analyzing and processing vital sign monitoring data and specific key environmental indicators;

[0264] Based on the pattern recognition result R, a deep learning model is used to predict the development trend of the patient's condition, generating a trend prediction report T. pred ;

[0265] The trend forecast report T is calculated using the following formula. pred :

[0266]

[0267] Where g(·) is the prediction function in the deep learning model; φ represents the model parameters; H t Represents historical data; β1 is the time decay factor, used to adjust the influence weights at different time points; R t f represents the pattern recognition result at time point t; pred It is a trend forecast report;

[0268] According to the trend forecast report Tp red The system automatically generates a potential risk warning W for each patient, providing warning information that includes current risk factors and potential future risks.

[0269] The potential risk warning W is calculated using the following formula:

[0270]

[0271] Where h(·) is the risk assessment function; ψ represents the model parameters; C curr This represents the current conditions; γ1 and δ1 are the influencing factors of trend prediction and current conditions, respectively; W is the potential risk warning.

[0272] Based on the aforementioned early warning information W, the medical command center reassesses and adjusts the emergency response plan, resulting in an updated medical demand M. new ;

[0273] The updated healthcare demand M is calculated using the following formula. new :

[0274]

[0275] Where k(·) is the demand evaluation function; ω represents the model parameters; D curr Indicates the latest data stream; η j and ζ k These are the weights of the early warning information and the latest data stream, respectively; ∈1 and λ1 are the exponential factors that adjust the degree of their respective influence; M new It is an updated medical need; W j This represents the j-th risk factor in the early warning information; max(0, ·) ensures that the calculation result is non-negative, even if the weighted sum is negative, the final M new The value will also be set to 0.

[0276] Here is a specific example:

[0277] Imagine a specific maritime emergency rescue scenario where a cruise ship sends out an emergency medical distress signal, reporting a passenger suffering a sudden heart attack. Upon receiving the signal, the system quickly establishes an optimized satellite communication link and begins real-time collection of vital sign monitoring data (such as heart rate, blood pressure, and blood oxygen saturation) and specific key environmental indicators (such as ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed) from the emergency scene. To ensure supplies are safely delivered to the cruise ship in the shortest possible time, the system applies the aforementioned multi-objective optimization problem model for path planning. It also uses deep learning algorithms to predict the progression of the patient's condition, generating potential risk warnings and updating medical needs.

[0278] The following are the parameter settings:

[0279] Exponential factors: α1 = 0.5, ∈1 = 0.6, λ1 = 0.7;

[0280] Weight: w i =[0.2, 0.3, 0.1, 0.1, 0.1, 0.2] corresponds to each data point D. i ;

[0281] Time decay factor: β1 = 0.3;

[0282] Impact factors: γ1 = 0.4, δ1 = 0.2;

[0283] Warning information weight: η j = [0.6, 0.4];

[0284] Latest data stream weights: ζ k = [0.5, 0.5];

[0285] Assume the current environmental conditions are as follows:

[0286] Vital signs monitoring data: Heart rate = 90 beats / minute, Blood pressure = 120 / 80 mmHg, Blood oxygen saturation = 95%

[0287] Specific key environmental indicators: ambient temperature = 15℃, humidity = 80%, air pressure = 1013 hPa, wind speed = 15 m / s, rainfall = 5 mm / h, ocean current speed = 2 knots

[0288] Using the optimized communication link, vital sign monitoring data and specific key environmental indicators at the emergency scene are collected and processed to obtain coded monitoring data. This data, after encryption and redundancy processing, is transmitted in real time to the medical command center via the optimized communication link, ensuring the security and reliability of data transmission.

[0289] Calculate the pattern recognition result R:

[0290] Suppose that the vital signs monitoring data and specific key environmental indicators received at a certain moment are D respectively. i =[90, 120, 95, 15, 80, 1013, 15, 5, 2]

[0291] Then R = 0.2·90 0.5 +0.3·120 0.5 +0.1·95 0.5 +0.1·15 0.5 +0.1·80 0.5 +0.2·1013 0.5

[0292] The calculated pattern recognition result is R≈22.4.

[0293] Assume the pattern recognition results at several past time points are Rt =[20, 22, 24, 22.4]

[0294] but

[0295] After calculation, the trend forecast report T is obtained. pred ≈23.2

[0296] Assume the current condition C curr =0.8 (out of 1);

[0297] but

[0298] Calculations show that the potential risk warning value is approximately W≈0.97.

[0299] Forming an updated medical demand model M new :

[0300] Assume the early warning information contains two risk factors W. j = [0.97, 0.8], the latest data stream D curr，k =[90, 120]

[0301] Then M new =max(0, 0.6·0.97) 0.6 +0.4·0.8 0.6 +0.5·90 0.7 +0.5·120 0.7 )≈117.3

[0302] After calculation, the updated medical demand M was obtained. new ≈117.3;

[0303] Based on the above calculations, the following conclusion can be drawn: the initial pattern recognition result R≈22.4 reflects the overall condition of the patient's vital signs and environmental conditions. This result provides a basis for subsequent trend prediction. Trend Prediction Report T pred The value ≈23.2 indicates that the patient's condition may continue to deteriorate in the coming hours. This suggests that medical experts need to prepare for a higher level of treatment. The potential risk warning value W≈0.97 indicates a high level of risk factors, especially considering the current conditions and the greater likelihood of the patient's condition worsening. This warning information helps medical experts take timely preventative measures. Updated medical needs M new The value ≈117.3 suggests a need for increased medical resources and support to address potential risks. For example, this includes increasing the demand for warming equipment, adjusting the quantity and types of medications, and ensuring patients receive appropriate treatment in the shortest possible time.

[0304] In summary, this system not only improves the real-time performance and accuracy of data collection and analysis at emergency sites, but also maintains the effectiveness and relevance of treatment measures in complex and ever-changing environments, significantly enhancing the success rate of maritime emergency rescue missions. Through continuous monitoring and dynamic adjustments, the system can continuously optimize delivery strategies to ensure that special medical supplies are delivered to emergency sites in a timely and accurate manner.

[0305] Figure 2 This application provides a schematic diagram of the structure of a satellite-based maritime emergency rescue information transmission system, as shown in the embodiment of the present application. Figure 2 As shown, the system includes:

[0306] The optimization module 21 is used to construct a temporary dedicated satellite communication link based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal, and to optimize the parameters of the temporary dedicated satellite communication link to obtain an optimized communication link.

[0307] The reconstruction analysis module 22 is used to use the optimized communication link, combined with augmented reality technology and computer vision algorithms, to perform three-dimensional reconstruction of the on-site environment, realize high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel, and apply machine learning models to analyze the description of the severity of the illness, predict the development of the illness, and generate illness prediction results.

[0308] The optimization processing module 23 is used to optimize the distribution strategy of special medical supplies based on the disease prediction results, by using a reinforcement learning algorithm and taking into account factors such as weather changes and ocean current direction, to obtain the optimal distribution route plan.

[0309] The data collection and formation module 24 is used to collect vital sign monitoring data and specific key environmental indicators according to the optimized communication link, transmit them back to the medical command center in real time, and apply deep learning algorithms to perform pattern recognition and trend prediction, generate potential risk warnings, and form updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall and ocean current speed.

[0310] The evaluation and optimization module 25 is used to re-evaluate and optimize the optimal delivery route plan based on the potential risk warning and the updated medical needs, and generate an updated optimal delivery route plan to ensure that supplies can be delivered to the emergency site in a timely and accurate manner.

[0311] Figure 2 The aforementioned satellite communication-based maritime emergency rescue information transmission system can perform... Figure 1The implementation principle and technical effects of the satellite communication-based maritime emergency rescue information transmission method described in the illustrated embodiment will not be repeated here. The specific operation methods of each module and unit in the satellite communication-based maritime emergency rescue information transmission system in the above embodiments have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0312] In one possible design, Figure 2 The satellite-based maritime emergency rescue information transmission system illustrated in this 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;

[0313] 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.

[0314] The processing component 32 is used to: construct a temporary dedicated satellite communication link based on the emergency location information and preliminary medical condition description in the received emergency medical distress signal, and optimize the parameters of the temporary dedicated satellite communication link to obtain an optimized communication link; using the optimized communication link, combined with augmented reality technology and computer vision algorithms, to perform three-dimensional reconstruction of the on-site environment, enabling high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel, and applying a machine learning model to analyze the severity description of the illness, predict the development of the illness, and generate an illness prediction result; based on the illness prediction result, using a reinforcement learning algorithm to consider weather changes, sea conditions, etc. The distribution strategy for special medical supplies is optimized based on flow direction factors to obtain the optimal distribution route plan. Based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted back to the medical command center in real time. Deep learning algorithms are then applied for pattern recognition and trend prediction to generate potential risk warnings and formulate updated medical needs. The specific key environmental indicators include ambient temperature, humidity, air pressure, wind speed, rainfall, and ocean current speed. Based on the potential risk warnings and updated medical needs, the optimal distribution route plan is re-evaluated and optimized to generate an updated optimal distribution route plan, ensuring that supplies can be delivered to the emergency site in a timely and accurate manner.

[0315] 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.

[0316] 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.

[0317] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0318] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0319] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0320] 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.

[0321] 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 transmitting maritime emergency rescue information based on satellite communication.

[0322] 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.

[0323] 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.

[0324] 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.

[0325] 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 transmitting maritime emergency information based on satellite communication, characterized in that, The method comprises the following steps: According to the emergency location information and the preliminary medical condition description in the received emergency medical help signal, a temporary dedicated satellite communication link is constructed, and the temporary dedicated satellite communication link is parameter optimized to obtain an optimized communication link; Using the optimized communication link, combining augmented reality technology and computer vision algorithm, a three-dimensional reconstruction of the on-site environment is performed to realize high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel, and a machine learning model is applied to analyze the severity of the illness and predict the development of the illness to generate an illness prediction result; Based on the illness prediction result, the distribution strategy of special medical supplies is optimized by considering factors such as weather changes and sea current directions through a reinforcement learning algorithm to obtain an optimal distribution path planning; According to the optimized communication link, life sign monitoring data and specific key environmental indicators are collected and transmitted in real time to a medical command center, and a deep learning algorithm is applied for pattern recognition and trend prediction to generate a potential risk warning and update the medical demand, the specific key environmental indicators include environmental temperature, humidity, air pressure, wind speed, rainfall and sea current speed; Based on the potential risk warning and the updated medical demand, the optimal distribution path planning is re-evaluated and optimized to generate an updated optimal distribution path planning to ensure that the supplies can be delivered to the emergency site in a timely and accurate manner.

2. The method of claim 1, wherein, The use of the optimized communication link, combined with augmented reality technology and computer vision algorithm, to perform three-dimensional reconstruction of the on-site environment to realize high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel, and to apply a machine learning model to analyze the severity of the illness and predict the development of the illness to generate an illness prediction result, comprises: Using the optimized communication link, a high-quality communication connection is established between the emergency site and the medical experts to ensure stable, low-latency high-definition audio and video calls, the optimized communication link supports large-bandwidth data transmission, ensuring the quality and efficiency of real-time data sharing, and obtaining a high-quality communication connection; Based on the high-quality communication connection, combined with augmented reality technology, the images and video streams of the emergency site are processed to superimpose virtual information onto the actual scene at the medical expert end to assist remote diagnosis, obtaining an augmented reality-assisted remote diagnosis environment; Using computer vision algorithms, multi-angle images and videos transmitted from the scene and processed through augmented reality technology are processed to construct an accurate three-dimensional model of the emergency site based on the data obtained in the augmented reality-assisted remote diagnosis environment to obtain an accurate on-site three-dimensional reconstruction; According to the optimized communication link and the accurate on-site three-dimensional reconstruction, the life sign data and specific key environmental indicators transmitted from the on-site monitoring devices are shared in real time and displayed in the form of charts or numerical values on the expert end interface to facilitate immediate assessment of the patient's condition and promote collaborative work, and the life sign data is shared in real time, the specific key environmental indicators include environmental temperature, humidity, air pressure, wind speed, rainfall and sea current speed; Input data required for preparing a machine learning model, preliminary medical condition descriptions, and vital sign data shared in real time through a communication link are collated and preprocessed to form a structured data set suitable for machine learning model analysis based on the real-time shared vital sign data; A machine learning model is applied to quantitatively evaluate and predict trends for the structured data set suitable for machine learning model analysis, the machine learning model having learned from a large number of cases to quantitatively evaluate the severity of the condition and predict the development trend, resulting in a detailed condition analysis result; Based on the detailed condition analysis result and the accurate on-site three-dimensional reconstruction, a condition prediction report is generated.

3. The method of claim 2, wherein, The use of computer vision algorithms to process multi-angle images and videos returned from the scene and processed through augmented reality technology to construct an accurate three-dimensional model of the emergency scene, based on the data obtained in the augmented reality-assisted remote diagnosis environment, results in an accurate on-site three-dimensional reconstruction, including: Using computer vision algorithms, the received multi-angle images and videos are preprocessed to remove noise, correct distortion, and perform color calibration to obtain high-quality input data; Based on the high-quality input data, feature detection algorithms are used to identify and extract stable feature points to obtain key feature points for subsequent matching; Based on the key feature points for subsequent matching, feature matching algorithms are used to match the key feature points under different perspectives, and the matching results are optimized through bundle adjustment to improve the accuracy of three-dimensional reconstruction, generating optimized feature point matching results; The positions of the feature points in the optimized feature point matching results in the three-dimensional space are calculated using the principle of triangulation to preliminarily form the spatial structure of the emergency scene, resulting in a sparse three-dimensional point cloud; Multi-view stereo vision algorithms are applied to fill the gaps between the sparse three-dimensional point clouds to generate a dense three-dimensional point cloud; Poisson surface reconstruction algorithms are used to construct a continuous three-dimensional surface from the dense three-dimensional point cloud, and the texture information of the original image is mapped onto the surface to obtain an accurate three-dimensional model; The accurate three-dimensional model is combined with real-time scene information obtained through augmented reality technology to provide medical experts with a comprehensive and intuitive view of the emergency scene, ensuring the accuracy and effectiveness of remote diagnosis, resulting in an accurate on-site three-dimensional reconstruction.

4. The method of claim 1, wherein, Based on the condition prediction result, the delivery strategy for special medical supplies is optimized through a reinforcement learning algorithm considering factors such as weather changes and sea current directions to obtain an optimal delivery path planning, including: According to the condition prediction result, the key environmental parameters of weather changes and sea current directions are obtained and analyzed in real time using a comprehensive environmental factor evaluation module to obtain an environmental condition report that affects the delivery path planning; Based on the environmental condition report, a multi-objective optimization problem model is created using a reinforcement learning algorithm, including transportation cost, time efficiency, and safety factor, to obtain an initial delivery strategy; A dynamic adjustment mechanism is introduced to the initial delivery strategy, allowing real-time updates to the delivery strategy as the latest weather changes and current directions change, ensuring that the effectiveness and accuracy of the delivery are maintained even in complex and changing environments, generating continuously optimized delivery path solutions; An interactive learning process between the reinforcement learning model and the actual delivery situation is used to automatically adjust the delivery path planning, based on the latest environmental changes and delivery feedback, to obtain the optimal delivery path planning.

5. The method of claim 4, wherein, Based on the environmental condition report, a multi-objective optimization problem model is created using a reinforcement learning algorithm, including transportation cost, time efficiency, and safety factor, to obtain an initial delivery strategy, including: Using the environmental condition report, the key environmental parameters of weather changes and current directions are deeply analyzed to obtain the factor analysis results that affect the selection of delivery paths and the delivery time of materials; Based on the factor analysis results, multiple optimization objectives are defined, including minimizing transportation cost, maximizing time efficiency, and ensuring the highest safety factor, to generate a multi-objective optimization framework; A multi-objective optimization problem model is constructed using a reinforcement learning algorithm based on the multi-objective optimization framework, which can handle the trade-off between different optimization objectives, and the target definition and weight allocation in the multi-objective optimization framework are used as the basis for model construction; A simulation environment is constructed to simulate different delivery scenarios, providing a training platform for the multi-objective optimization problem model, and the multi-objective optimization model is used in the simulation environment; Through a large number of simulation experiments, the reinforcement learning model continuously tries to select delivery paths in the simulation environment, and adjusts the trade-off between objectives based on feedback, gradually converging to the best strategy combination to obtain a preliminary optimized delivery solution; Based on the preliminary optimized delivery solution, the latest environmental conditions and actual delivery requirements are combined to make the final adjustments, generating an initial delivery strategy.

6. The method of claim 1, wherein, Based on the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and transmitted in real time to the medical command center, and a deep learning algorithm is applied for pattern recognition and trend prediction to generate potential risk warnings, forming updated medical needs, including environmental temperature, humidity, air pressure, wind speed, rainfall, and current speed. Using the optimized communication link, vital sign monitoring data and specific key environmental indicators are collected and processed at the first aid site, including environmental temperature, humidity, air pressure, wind speed, rainfall, and current speed. Based on the encoded monitoring data, real-time transmission processing of the encoded monitoring data is performed through the optimized communication link to obtain a data stream transmitted in real time to the medical command center. Based on the real-time data stream transmitted to the medical command center, a deep learning algorithm deployed in the medical command center is applied to analyze and process the vital sign monitoring data and specific key environmental indicators, including environmental temperature, humidity, air pressure, wind speed, rainfall, and current speed, to obtain pattern recognition results. Based on the pattern recognition result, a deep learning model is used to predict the development trend of the patient's condition, and a trend prediction report is generated; According to the trend prediction report, the system automatically generates a potential risk warning for each patient, obtaining a warning information containing the current risk factors and the future risk prompts; Based on the warning information, the medical command center re-evaluates and adjusts the emergency plan to form an updated medical demand.

7. The method of claim 1, wherein, Based on the potential risk warning and the updated medical demand, the optimal distribution path planning is re-evaluated and optimized to generate an updated optimal distribution path planning, ensuring that the materials can be delivered to the emergency site in a timely and accurate manner, including: Using the potential risk warning, the risk factors at the emergency site are analyzed and processed to obtain a detailed risk assessment report; Based on the risk assessment report and the updated medical demand, the current medical material demand is re-evaluated to generate the latest medical material demand list; According to the latest medical material demand list, check whether the existing optimal distribution path planning needs to be adjusted to adapt to the new demand changes, and preliminarily determine the aspects that need to be optimized; Based on the preliminary optimization aspect, consider the latest environmental conditions to re-plan the optimal distribution path, ensuring that the material distribution strategy meets the latest medical demand and risk warning situation; Through continuous updating and adjustment, an updated optimal distribution path planning is finally generated to ensure that special medical materials can be delivered to the emergency site in a timely and accurate manner.

8. A satellite communication based offshore emergency information transmission system characterized in that, It includes: An optimization module is constructed to construct a temporary dedicated satellite communication link according to the emergency location information and the preliminary medical condition description in the received emergency medical help signal, and to optimize the parameters of the temporary dedicated satellite communication link to obtain an optimized communication link; A reconstruction analysis module is used to use the optimized communication link to combine augmented reality technology and computer vision algorithms to perform three-dimensional reconstruction of the on-site environment, realize high-definition audio and video calls and real-time data sharing between medical experts and on-site rescue personnel, and apply a machine learning model to analyze the severity of the condition description, predict the development of the condition, and generate a condition prediction result; An optimization processing module is used to optimize the distribution strategy of special medical materials based on the condition prediction result through reinforcement learning algorithm and considering the factors of weather change and sea current direction to obtain an optimal distribution path planning; A collection forming module is used to collect vital sign monitoring data and specific key environmental indicators according to the optimized communication link, and real-time feedback to the medical command center, and apply a deep learning algorithm for pattern recognition and trend prediction to generate a potential risk warning and form an updated medical demand, the specific key environmental indicators include environmental temperature, humidity, air pressure, wind speed, rainfall and sea current speed; An evaluation and optimization module is used to re-evaluate and optimize the optimal distribution path planning based on the potential risk warning and the updated medical demand to generate an updated optimal distribution path planning, ensuring that the materials can be delivered to the emergency site in a timely and accurate manner.

9. A computing device, comprising: The method comprises a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are used to be called and executed by the processing component to realize the method for transmitting maritime first aid information based on satellite communication according to any one of claims 1-7.

10. A computer storage medium, characterized in that, The computer program is stored and is executed by a computer to realize the method for transmitting maritime first aid information based on satellite communication according to any one of claims 1-7.

Images