An optimization method and system based on first aid personnel psychological self-adaptation

Abstract

The application provides an optimization method and system based on psychological self-adaptation of first-aid personnel. Wherein, dynamic information of a first-aid scene and a sea area along a route corresponding to a first-aid task is collected to obtain a risk assessment result; psychological state monitoring data of the first-aid personnel is acquired, a machine learning algorithm is used to analyze a psychological stress level of the first-aid personnel to obtain a psychological state analysis result; according to the risk assessment result, an intelligent path planning algorithm based on a particle swarm optimization algorithm is applied to generate a specific execution path; based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to perform real-time re-evaluation processing on the path when unexpected emergency conditions are encountered to generate an alternative route; and a maritime communication system and an intelligent navigation auxiliary device are integrated to obtain an optimized sea first-aid path. The technical scheme provided by the application realizes intelligentization and real-time optimization of path planning.

Description

Technical Field

[0001] This application relates to the field of maritime emergency rescue route planning technology, and in particular to an optimization method and system based on the psychological adaptation of emergency responders. Background Technology

[0002] In maritime emergency rescue scenarios, the efficiency and safety of rescue operations are paramount. The maritime environment is complex and ever-changing, including weather, ocean currents, and other unpredictable factors, all of which significantly impact emergency rescue missions. To ensure efficient and safe rescues, a technological solution is needed that can collect real-time dynamic information about the emergency scene and the surrounding sea area, and conduct risk assessments by combining historical rescue cases and marine meteorological forecast data. Furthermore, the psychological state of emergency responders must be considered to provide personalized psychological support plans, thereby improving their performance under high-pressure conditions.

[0003] Currently, many maritime emergency medical services systems rely primarily on traditional route planning methods, which select the optimal route based on static maps and pre-defined conditions. Some systems have begun to introduce basic risk assessment models, but these models are often limited to physical environmental factors and fail to comprehensively cover all variables that may affect emergency response operations, particularly neglecting the psychological state of emergency responders.

[0004] The existing solutions have several significant shortcomings: First, they lack the ability to effectively respond to dynamic changes at the emergency scene and cannot adjust route planning in a timely manner; second, few systems take into account the psychological stress level of emergency responders and its impact on mission execution; and finally, the integration between existing communication and navigation aids is not high, resulting in untimely information synchronization between the emergency response team and the command center, which affects the speed and accuracy of decision-making. Summary of the Invention

[0005] This application provides an optimization method and system based on the psychological adaptation of emergency responders, in order to solve the problem that path planning in the prior art ignores psychological factors and dynamic environmental changes.

[0006] In a first aspect, embodiments of this application provide an optimization method based on the psychological adaptation of emergency responders, comprising:

[0007] Dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission is collected. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation.

[0008] Acquire psychological state monitoring data of emergency responders, analyze their psychological stress levels using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results.

[0009] Based on the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of different rescue action plans under various possible changing scenarios. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel, a specific execution path is generated.

[0010] Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in real time when encountering unforeseen emergencies. Contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment and generate alternative routes.

[0011] By integrating maritime communication systems and intelligent navigation aids, the system enables two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the system dynamically modifies the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

[0012] Optionally, based on the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of different rescue action plans under various possible changing scenarios. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency responders, a specific execution path is generated, including:

[0013] Using the risk assessment results, the response effects of different rescue action plans under various possible changing scenarios are modeled to obtain the response model of the rescue action plan;

[0014] Based on the response model, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of each rescue action plan. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel, preliminary path planning suggestions are generated.

[0015] Based on the preliminary route planning suggestions, and combined with historical data and real-time information, the safety and feasibility of the route are evaluated to obtain the route evaluation results.

[0016] Using the path evaluation results, the path selection strategy is continuously improved through iterative learning to ensure that the path selection can adapt to the complex marine environment and generate specific execution paths.

[0017] Optionally, based on the preliminary route planning suggestions, and in conjunction with historical data and real-time information, the safety and feasibility of the route are evaluated to obtain a route evaluation result, including:

[0018] Using the aforementioned preliminary route planning suggestions, combined with historical rescue data, a statistical analysis of the historical success rate and failure cases of each route is conducted to obtain a route historical evaluation report;

[0019] Based on the historical assessment report of the route and combined with real-time marine environmental monitoring information, the current safety and feasibility of the route are dynamically assessed, and real-time assessment indicators of the route are generated.

[0020] Based on the real-time evaluation indicators of the path, a risk prediction model is applied to estimate the risks that may be encountered in the future, and the path risk prediction results are obtained.

[0021] Using the path risk prediction results, and taking into account the urgency of the rescue mission and resource availability, a comprehensive evaluation of each path is conducted to generate path assessment results.

[0022] Optionally, the step of using the path evaluation results to continuously improve the path selection strategy through iterative learning, ensuring that the path selection can adapt to complex maritime environments, and generating specific execution paths includes:

[0023] Using the path evaluation results, different path schemes are scored to obtain a path scoring table;

[0024] Based on the path scoring table, a machine learning model is applied to optimize the path selection strategy. Iterative learning is performed based on historical and real-time data to generate an optimized path selection model.

[0025] Based on the optimized path selection model, and combined with the current rescue mission requirements and environmental change predictions, the path selection strategy is adjusted to obtain the adjusted path planning draft.

[0026] Using the revised path planning draft, verification testing is conducted in a simulation environment to collect feedback data and perform performance evaluation, thereby generating a specific execution path.

[0027] Optionally, based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in real time when encountering unforeseen emergencies. Contextual awareness technology is used to continuously monitor and provide early warnings of changes in the surrounding environment, generating alternative routes, including:

[0028] Using the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to monitor and process the path in real time, thereby obtaining path monitoring data.

[0029] Based on the path monitoring data and information on unforeseen emergencies, a Bayesian optimization algorithm is applied to re-evaluate the current path in real time, generating a re-evaluation result.

[0030] Based on the reassessment results, situational awareness technology is used to continuously monitor and provide early warning of changes in the surrounding environment, thereby obtaining early warning information on environmental changes.

[0031] Using the environmental change early warning information, combined with historical path data and current task requirements, the path is dynamically adjusted to generate alternative routes.

[0032] Optionally, based on the reassessment results, the use of contextual awareness technology to continuously monitor and provide early warning of changes in the surrounding environment, thereby obtaining environmental change early warning information, includes:

[0033] Using the reassessment results and real-time marine environmental data, potential risk areas around the current path are identified and processed to generate a potential risk area map;

[0034] Based on the potential risk area map, multi-source sensing fusion technology is applied to integrate data from multiple types of sensors to perform comprehensive sensing processing on the surrounding environment, resulting in comprehensive sensing data.

[0035] Based on the comprehensive perception data, the context awareness technology is used to predict the changing trends of the surrounding environment and generate an environmental change prediction model.

[0036] By utilizing the aforementioned environmental change prediction model, combined with historical data and real-time monitoring information, early warning processing can be carried out for possible emergencies, generating environmental change early warning information.

[0037] Optionally, the integrated maritime communication system and intelligent navigation aids enable two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the specific execution path and alternative routes are dynamically revised to obtain an optimized maritime emergency rescue route, including:

[0038] By utilizing the maritime communication system, a two-way information transmission channel is established between the emergency rescue team and the command center to synchronously update and process real-time information and generate a synchronously updated information flow.

[0039] Based on the synchronously updated information stream and combined with data from the intelligent navigation assistance device, the progress of the current rescue mission is tracked and processed in real time to obtain a mission progress report.

[0040] Based on the task progress report, a dynamic correction algorithm is applied to adjust the specific execution path and the alternative routes according to the latest on-site feedback, thereby generating a dynamic correction scheme.

[0041] Using the aforementioned dynamic correction scheme, combined with environmental change early warning information and the latest mission requirements, the route is finally optimized to obtain the optimized maritime emergency rescue route.

[0042] Secondly, embodiments of this application provide an optimization system based on the psychological adaptation of emergency responders, comprising:

[0043] The data collection module is used to collect dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation.

[0044] The acquisition module is used to acquire psychological state monitoring data of emergency responders, analyze the psychological stress level of emergency responders using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results.

[0045] The simulation module is used to simulate the response effects of different rescue action plans under various possible changing scenarios based on the risk assessment results and an intelligent path planning algorithm based on particle swarm optimization. It comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel to generate a specific execution path.

[0046] The evaluation module is used to introduce an adaptive adjustment mechanism based on Bayesian optimization based on the specific execution path, to re-evaluate the path in real time when encountering unforeseen emergencies, and to continuously monitor and warn of changes in the surrounding environment using context awareness technology, and to generate alternative routes.

[0047] The correction module integrates the maritime communication system and intelligent navigation aids to realize the two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, it dynamically corrects the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

[0048] Thirdly, embodiments of this application provide a computing device, including a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an optimization method based on the psychological adaptation of emergency responders as described in the first aspect.

[0049] Fourthly, embodiments of this application provide a computer storage medium storing a computer program, which, when executed by a computer, implements an optimization method based on the psychological adaptation of emergency responders as described in the first aspect.

[0050] In this embodiment, dynamic information of the emergency rescue site and the surrounding sea area corresponding to the emergency rescue mission is collected. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. These results comprehensively cover all variables that may affect the emergency rescue operation. Psychological state monitoring data of emergency personnel is acquired, and their psychological stress levels are analyzed using machine learning algorithms to obtain psychological state analysis results. Based on these results, personalized psychological support plans are generated for each emergency rescue mission. According to the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to different rescue action plans under various possible changing scenarios. The response effect is simulated, and a specific execution path is generated by comprehensively considering the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency responders. Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in case of unforeseen emergencies. Contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment and generate alternative routes. The maritime communication system and intelligent navigation assistance equipment are integrated to realize the two-way information synchronization between the emergency response team and the command center. Based on the latest on-site feedback, the specific execution path and the alternative routes are dynamically corrected to obtain an optimized maritime emergency rescue path.

[0051] The technical solution of this application has the following beneficial effects:

[0052] By collecting dynamic information from the emergency rescue site and the surrounding sea areas, and combining it with historical rescue cases and marine meteorological forecast data, the risk assessment built using machine learning models can more comprehensively cover all variables affecting emergency rescue operations, improving the scientific nature and accuracy of decision-making. Considering the psychological state monitoring data of emergency personnel and providing personalized psychological support plans based on this can effectively reduce their psychological stress, improve their work efficiency and safety, and ensure they maintain a good operational state even under high-pressure environments. Applying particle swarm optimization algorithms to simulate the response effects of different rescue plans under various changing scenarios, and comprehensively considering vessel performance parameters, safety indices, and the psychological state of emergency personnel, generates specific execution paths. This process not only optimizes route selection but also accelerates response to emergencies, making rescue operations more efficient. The introduction of a Bayesian-based adaptive adjustment mechanism allows for immediate reassessment of routes in the event of unforeseen emergencies, and the continuous monitoring and early warning of changes in the surrounding environment using situational awareness technology significantly increases the flexibility and adaptability of route planning, ensuring timely adjustments to the optimal route even in complex and ever-changing maritime environments. The integration of maritime communication systems and intelligent navigation aids enables two-way information synchronization between the emergency response team and the command center, dynamically revising route planning based on the latest on-site feedback. This efficient communication and coordination mechanism ensures real-time information sharing, enhances teamwork, and improves the overall emergency response level.

[0053] Furthermore, by utilizing risk assessment results and intelligent path planning based on particle swarm optimization algorithms, the response effects of different rescue operation plans under various possible changing scenarios are modeled and simulated. Taking into account the performance parameters of rescue vessels, the safety index of emergency responders, and the analysis results of their psychological state, this method can generate specific execution paths. The beneficial effects of this method are: it not only improves the accuracy and reliability of maritime emergency rescue path planning, but also continuously improves the path selection strategy through a continuous iterative learning mechanism, ensuring that path selection flexibly responds to complex maritime environments and emergencies; at the same time, it rigorously evaluates the safety and feasibility of paths by combining historical data and real-time information, making the final generated specific execution path both safe and efficient, maximizing the protection of emergency responders' lives, improving the success rate of rescue missions, and providing strong technical support for maritime emergency rescue.

[0054] Furthermore, by introducing a Bayesian optimization-based adaptive adjustment mechanism, the specific execution path is monitored and feedback is processed in real time. Combined with information on unforeseen emergencies, the path is reassessed immediately. This method can quickly respond to environmental changes and generate alternative routes. Its beneficial effects are: it significantly enhances the flexibility and adaptability of maritime emergency rescue route planning, ensuring rapid and accurate path adjustments in the event of emergencies, thus guaranteeing the safety and efficiency of rescue operations; simultaneously, the use of situational awareness technology to continuously monitor and warn of changes in the surrounding environment not only improves the ability to predict potential risks but also makes route planning more intelligent and forward-looking, minimizing the impact of uncertainty on rescue missions, thereby improving the overall success rate of rescue and emergency response capabilities.

[0055] These or other aspects of this application will become more apparent in the following description of the embodiments. Attached Figure Description

[0056] 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.

[0057] Figure 1 A flowchart illustrating an optimization method based on the psychological adaptation of emergency responders, provided for an embodiment of this application;

[0058] Figure 2 A schematic diagram of the structure of an optimization system based on the psychological adaptation of emergency responders provided in this application embodiment;

[0059] Figure 3 This is a schematic diagram of the structure of a computing device provided in an embodiment of this application. Detailed Implementation

[0060] 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.

[0061] 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.

[0062] 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.

[0063] Figure 1 A flowchart of an optimization method based on the psychological adaptation of emergency responders is provided as an embodiment of this application, such as... Figure 1 As shown, the method includes:

[0064] Dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission is collected. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation.

[0065] This step involves collecting dynamic information on the emergency response site and the surrounding sea areas, including real-time weather, sea conditions, and traffic data. This information, combined with historical rescue cases and marine meteorological forecasts, is used to construct a multi-dimensional risk assessment model that comprehensively covers all variables that could potentially affect emergency response operations. These data sources ensure that the model not only considers the current environment but also draws on past experience and future predictions to provide more accurate risk assessment results.

[0066] In this embodiment, dynamic information about the emergency rescue scene and its surrounding sea area is first collected using various sensors and monitoring devices, and this information is combined with historical rescue cases and marine weather forecasts. Then, a machine learning model is used to analyze the data and generate a multi-dimensional risk assessment model, thereby providing detailed risk assessment results for each potential emergency rescue scenario and ensuring that all possible influencing factors are taken into account.

[0067] Suppose a rescue ship is en route to an island for emergency medical assistance. The system collects real-time information on the area, including weather forecasts, ocean current speeds, and the density of passing ships. It then combines this information with historical records of similar rescue operations and weather forecasts for the next few days, using machine learning algorithms to build a comprehensive risk assessment model to guide the selection of the optimal route.

[0068] Acquire psychological state monitoring data of emergency responders, analyze their psychological stress levels using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results.

[0069] In this step, psychological state monitoring data of emergency responders are acquired, including physiological indicators such as heart rate and skin conductance, as well as subjective evaluations such as self-reported psychological state questionnaires, to analyze their psychological stress levels. Based on this analysis, personalized psychological support plans are developed for each emergency response mission to reduce their psychological burden and improve work efficiency.

[0070] In this embodiment, first responders wear wearable devices to continuously monitor their physiological parameters and submit regular psychological status reports via a mobile application. Machine learning algorithms analyze this data to identify individuals with high stress levels and generate personalized psychological support plans tailored to different task requirements, ensuring that each first responder receives appropriate help and support.

[0071] Suppose that during a large-scale maritime search and rescue operation, the system detects an abnormally high heart rate in some emergency responders, indicating that they are under high psychological stress. In this case, based on a pre-set psychological support plan, the system automatically sends relaxation exercise guidelines or arranges short rest periods for these emergency responders, while adjusting their workload to ensure they can continue performing their mission in optimal condition.

[0072] Based on the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of different rescue action plans under various possible changing scenarios. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel, a specific execution path is generated.

[0073] In this step, based on the aforementioned risk assessment results, a particle swarm optimization algorithm is used to simulate the response effects of different rescue operation plans under various possible changing scenarios. Taking into account the performance parameters of rescue vessels (such as speed and load capacity), the safety index of emergency responders, and the psychological state analysis results, the optimal specific execution path is ultimately determined.

[0074] In this embodiment, based on the risk assessment results provided by the multidimensional risk assessment model, the particle swarm optimization algorithm is used to simulate and evaluate the response effects of multiple rescue operation plans. Through iterative optimization, the algorithm selects paths that both meet safety standards and efficiently complete the task, ensuring the most rational use of resources.

[0075] Suppose we need to plan a rescue route from the port to the accident site. Based on previous risk assessments, the system uses a particle swarm optimization algorithm to simulate multiple possible paths, taking into account ship speed limitations and the safety and psychological state of emergency responders. After a series of calculations, the optimal route is selected that ensures both rapid arrival and the safety of personnel.

[0076] Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in real time when encountering unforeseen emergencies. Contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment and generate alternative routes.

[0077] In this step, based on the generated execution path, a Bayesian optimization adaptive adjustment mechanism is introduced to reassess the path in real time when unforeseen emergencies occur. Contextual awareness technology is used to continuously monitor changes in the surrounding environment and provide early warnings of potential risks in order to quickly generate alternative routes.

[0078] In this embodiment, once the specific execution path is determined, the system initiates a Bayesian optimization algorithm for real-time monitoring. If any unforeseen emergencies are detected, such as sudden severe weather or obstacles, the system will immediately reassess the safety of the current path and use situational awareness technology to predict environmental change trends, adjusting the path in a timely manner to ensure that the rescue operation is not hindered.

[0079] Suppose a sudden storm occurs during a rescue operation. The system immediately triggers a Bayesian optimization algorithm, combining the latest weather data and the ship's current position to quickly reassess the existing route. Simultaneously, using situational awareness technology to monitor the surrounding environment, it identifies a nearby safe harbor for temporary anchorage. The system then adjusts the route in real time, guiding the ship to the harbor to avoid danger until conditions permit before continuing to its destination.

[0080] By integrating maritime communication systems and intelligent navigation aids, the system enables two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the system dynamically modifies the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

[0081] This step integrates maritime communication systems with intelligent navigation aids to enable two-way information synchronization between the emergency response team and the command center. Based on the latest on-site feedback, the specific execution path and alternative routes are dynamically adjusted to ensure optimal path status even in complex and changing environments.

[0082] In this embodiment, by integrating advanced maritime communication systems and intelligent navigation tools, seamless information exchange between the emergency rescue team and the command center is achieved. Whether during execution or in response to emergencies, the system can quickly adjust its route planning based on the latest on-site feedback data, ensuring the efficiency and flexibility of the entire rescue operation.

[0083] Imagine a complex maritime rescue operation where the rescue team encounters a new obstacle as they approach their target. Using an efficient maritime communication system, the team immediately reports this to the command center. Upon receiving the information, the command center, combining data from intelligent navigation aids, quickly adjusts its route planning to bypass the obstacle, ensuring the rescue vessel reaches its destination safely and efficiently.

[0084] In summary, this invention covers the entire process from information collection, psychological state monitoring, route planning, real-time adjustment to information synchronization, aiming to provide an intelligent, personalized and flexible maritime emergency rescue route planning solution to meet the complex and ever-changing needs of maritime rescue, and significantly improve rescue efficiency and safety.

[0085] To address the issue of insufficient flexibility in path planning within complex and ever-changing maritime environments, some embodiments involve applying an intelligent path planning algorithm based on particle swarm optimization (PSO) to simulate the response effects of different rescue operation plans under various possible changing scenarios, based on the risk assessment results. This process comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency responders to generate a specific execution path, including:

[0086] Using the risk assessment results, the response effects of different rescue operation plans under various possible changing scenarios are modeled to obtain response models for the rescue operation plans. Based on the response models, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of each rescue operation plan. Taking into account the performance parameters of the rescue vessels and the safety index and psychological state analysis results of the emergency responders, preliminary path planning suggestions are generated. Based on the preliminary path planning suggestions, combined with historical data and real-time information, the safety and feasibility of the path are evaluated to obtain path evaluation results. Using the path evaluation results, the path selection strategy is continuously improved through iterative learning to ensure that the path selection can adapt to the complex maritime environment and generate specific execution paths.

[0087] In this embodiment, the risk assessment results are used to model the response effects of different rescue action plans under various possible changing scenarios, resulting in a response model for the rescue action plan. The response model includes, but is not limited to, data such as weather conditions, ocean current speed, and obstacle location, which are used to predict the effects of different action plans.

[0088] In this embodiment, firstly, the system establishes response models for multiple possible rescue operation plans based on risk assessment results; secondly, based on these models, a particle swarm optimization algorithm is applied to simulate the response effects of each plan under different environmental changes, and combined with the analysis results of vessel performance and personnel safety psychological state, preliminary route planning suggestions are proposed; thirdly, based on historical data and real-time information, the safety and feasibility of the preliminary suggested routes are assessed, and route evaluation results are obtained; finally, the route selection strategy is continuously optimized through iterative learning to ensure that the final route is both adaptable to the complex maritime environment and ensures personnel safety, thereby generating a specific execution route;

[0089] Here is a specific example:

[0090] Suppose that during a maritime search and rescue mission, the command center immediately activates the intelligent path planning system upon receiving a distress signal. First, based on the latest marine weather forecasts and risk assessments from similar past cases, the system establishes response models for several possible rescue action plans. Second, the system uses a particle swarm optimization algorithm to simulate the response effect of each plan under various possible changing scenarios (such as sudden storms or unknown obstacles), while also considering the speed limitations of rescue vessels and the psychological endurance of emergency responders, proposing several preliminary path planning suggestions. Third, based on successful rescue records under similar historical conditions and real-time monitoring information of the current sea area, the system comprehensively evaluates these suggestions and selects the safest and most feasible path. Finally, through a continuous learning process, the system adjusts its path selection strategy to ensure that it can provide the optimal solution even in complex maritime environments, generating the final specific execution path.

[0091] Through the above steps, the system not only improves the accuracy and adaptability of route planning, but also effectively ensures the safety and efficiency of rescue operations.

[0092] Optionally, based on the preliminary route planning suggestions, and in conjunction with historical data and real-time information, the safety and feasibility of the route are evaluated to obtain a route evaluation result, including:

[0093] Using the preliminary route planning suggestions and historical rescue data, a statistical analysis of the historical success rate and failure cases of each route is performed to obtain a route historical assessment report. Based on the route historical assessment report and real-time marine environmental monitoring information, the current safety and feasibility of the route are dynamically assessed to generate real-time route assessment indicators. Based on the real-time route assessment indicators, a risk prediction model is applied to predict potential future risks, resulting in route risk prediction results. Using the route risk prediction results, and comprehensively considering the urgency of the rescue mission and resource availability, each route is comprehensively evaluated to generate a route assessment result.

[0094] In this embodiment, the preliminary route planning suggestions are used in conjunction with historical rescue data to statistically analyze the historical success rate and failure cases of each route, resulting in a route historical assessment report. This report includes, but is not limited to, data on past successes and failures, used to assess the success probability of different routes. Based on the historical assessment report and real-time marine environmental monitoring information, the current safety and feasibility of the routes are dynamically assessed, generating real-time route assessment indicators. These indicators comprehensively consider real-time conditions such as weather and ocean currents in the current sea area, reflecting the actual safety of the routes. Based on these indicators, a risk prediction model is applied to forecast potential future risks, resulting in route risk prediction results. These results predict potential future risks, such as severe weather or obstacles, allowing for advance preparation. Using these risk prediction results, the urgency of the rescue mission and resource availability are comprehensively considered to evaluate each route, generating route assessment results. These results comprehensively consider all factors, ensuring that the final selected route is both safe and efficient.

[0095] In this embodiment, firstly, the system analyzes the success rate and failure cases of each route based on preliminary route planning suggestions and historical rescue data, and compiles a route historical assessment report; secondly, based on this report and the latest marine environmental monitoring data, the system dynamically assesses the safety and feasibility of each route, forming real-time route assessment indicators; thirdly, based on these real-time assessment indicators, the system applies a risk prediction model to predict potential future risks and obtain route risk prediction results; finally, the system comprehensively considers the urgency of the mission and the existing resource situation, conducts a comprehensive evaluation of all routes, and ultimately generates route assessment results to ensure the selection of the most suitable route.

[0096] Here is a specific example:

[0097] In a maritime search and rescue mission, the system proposes several preliminary route planning suggestions. First, the system consults historical rescue databases, comparing the proposed routes with successful and unsuccessful routes in similar past situations, and compiles a detailed historical route assessment report. Second, the system combines this report with the latest marine weather forecasts to evaluate the safety and feasibility of each route under the current environment, forming precise real-time route assessment indicators. Third, the system uses advanced risk prediction models, considering factors such as possible storms or ocean current changes in the coming days, to estimate the potential risks of each route, generating route risk prediction results. Finally, the system comprehensively considers the urgency of the rescue mission (such as the vital signs of the people in distress) and available resources (such as the number of vessels and fuel reserves), conducts a comprehensive evaluation of all routes, and ultimately determines the optimal route that is both safe and allows for rapid arrival at the destination.

[0098] Through the above steps, the system not only improves the safety and reliability of route selection, but also ensures that rescue operations can be carried out quickly and effectively, maximizing the safety of people in distress.

[0099] To address the issue of insufficient adaptability of path selection strategies in complex and ever-changing maritime environments, some embodiments involve using the path evaluation results to iteratively improve the path selection strategy, ensuring that the path selection can adapt to complex maritime environments and generate specific execution paths. This includes:

[0100] Using the path evaluation results, different path schemes are scored to obtain a path score table. Based on the path score table, a machine learning model is applied to optimize the path selection strategy, and iterative learning is performed based on historical and real-time data to generate an optimized path selection model. Based on the optimized path selection model, combined with the current rescue mission requirements and environmental change predictions, the path selection strategy is adjusted to obtain an adjusted path planning draft. Using the adjusted path planning draft, verification testing is conducted in a simulation environment, feedback data is collected, performance is evaluated, and a specific execution path is generated.

[0101] In this embodiment, the path evaluation results are used to score different path schemes, resulting in a path scoring table. The path scoring table includes scores for indicators such as safety, feasibility, and efficiency for each path, used to quantitatively compare the merits of different path selections. Based on the path scoring table, a machine learning model is applied to optimize the path selection strategy, iteratively learning from historical and real-time data to generate an optimized path selection model. The optimized path selection model incorporates past successful experiences and current environmental changes to improve the accuracy and adaptability of path planning. Based on the optimized path selection model, and considering current rescue mission requirements and predicted environmental changes, the path selection strategy is adjusted to obtain an adjusted path planning draft. The adjusted path planning draft fully considers the latest mission requirements and predicted environmental changes to ensure optimal path adaptability. Using the adjusted path planning draft, verification testing is conducted in a simulated environment, feedback data is collected, and performance is evaluated to generate a specific execution path. The specific execution path is the optimal choice after simulation verification, aiming to ensure the safety and efficiency of the rescue operation.

[0102] In this embodiment, firstly, the system scores all possible route options based on the route evaluation results, forming a route score table to intuitively compare the advantages and disadvantages of each route. Secondly, based on these scores, the system uses a machine learning model to analyze historical data and real-time information, continuously optimizing the route selection strategy through iterative learning to build a more intelligent route selection model. Thirdly, based on this optimized model, the system adjusts the route selection strategy by combining the current specific rescue mission requirements and predictions of future environmental changes, formulating a preliminary route planning draft. Finally, the system places this draft in a simulation environment for multiple tests, collects feedback data from each test, evaluates its performance, and ultimately determines a safe and efficient execution route.

[0103] Here is a specific example:

[0104] Assuming a deep-sea search and rescue mission, the system has completed preliminary path assessment and generated a detailed path scoring table. First, the system quantifies the score for each path based on factors such as safety, time, and resource consumption. Second, based on these scores, the system uses machine learning algorithms to analyze past successful rescue cases and real-time data from the current sea area, generating a more intelligent path selection model through continuous iterative learning. Third, based on the new model and the specific requirements of the mission (such as the rescue time window and the location of the distressed personnel) as well as the weather forecast for the next few days, the system adjusts the path selection strategy and formulates a preliminary path planning draft. Finally, the system places this draft in a highly realistic simulation environment for multiple rounds of testing, collecting feedback data on path stability and time efficiency, and conducts performance evaluation accordingly, ultimately confirming an optimal execution path.

[0105] Through the above steps, the system not only improves the scientific nature and accuracy of route selection, but also enhances its adaptability to complex maritime environments, thereby ensuring that rescue operations can be completed safely and effectively in the shortest possible time.

[0106] This application addresses the shortcomings of existing path planning methods, such as a lack of comprehensive consideration of rescue vessel performance parameters, emergency responders' safety index, and psychological state, as well as insufficient response to complex maritime environmental changes. Therefore, this invention proposes this alternative solution. By introducing a particle swarm optimization algorithm and a multi-dimensional risk assessment model, this solution aims to solve the problems of poor adaptability, insufficient safety, and low efficiency of existing path planning methods in the face of complex and changing maritime environments, thereby improving the success rate and safety of maritime emergency rescue missions.

[0107] Optionally, based on the response model, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of each rescue action plan. Taking into account the performance parameters of the rescue vessels and the safety index and psychological state analysis results of the emergency responders, preliminary path planning suggestions are generated, including:

[0108] Before calculating the particle fitness function F(p), a comprehensive response effectiveness assessment of the rescue operation plan is required. Through multi-dimensional data analysis, combined with historical cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed to lay the foundation for subsequent fitness scoring.

[0109] F(p)=α·R(p)+β·S(p)-γ·C(p)+η·D(p)-ζ·I(p)

[0110] Wherein, α, β, γ, η, ζ represent weighting coefficients, indicating the importance of response effect, safety, cost, distance, and interference, respectively; R(p) represents the path response effect score calculated based on the response model; S(p) represents the safety score that comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency responders; C(p) represents the cost assessment of the path; D(p) represents the total path length, used to measure the distance factor of the path; I(p) represents the interference impact score, which assesses the potential interference risk on the path based on a multi-dimensional dynamic interference map;

[0111] After calculating F(p), the fitness score is converted into the path selection probability P. select (p) Normalization ensures the comparability of scores, and real-time monitoring and historical data are combined to dynamically adjust the selection probability to reflect current environmental changes and uncertainties, ensuring that path selection can flexibly respond to emergencies.

[0112]

[0113] Where N represents the total number of particles; δ represents the mutation intensity coefficient, reflecting the impact of environmental changes; V(p) represents the mutation value of particle p, calculated based on real-time monitoring data and historical data, representing the uncertainty and risk of the path under the current environment; θ represents the time sensitivity coefficient, reflecting the impact of the urgency of the task; T(p) represents the expected completion time of particle p, estimated based on current conditions and historical data, used to evaluate the time efficiency of the path; λ represents the uncertainty coefficient, reflecting the impact of unknown factors in the path; and U(p) represents the uncertainty score, which assesses the unknown risks and the probability of change in the path based on situational awareness technology.

[0114] After calculating P select (p) After that, candidate routes are selected by random sampling, and their feasibility and safety are verified by situational awareness technology. Finally, the candidate routes are optimized based on the latest on-site feedback and mission requirements to generate the final preliminary route planning suggestions, ensuring the safe and efficient implementation of the rescue operation.

[0115] This formula aims to ensure that route selection can adapt to complex changes in the marine environment while guaranteeing the safety and efficient completion of missions by emergency responders. This solution proposes an intelligent route planning algorithm based on particle swarm optimization. The algorithm first conducts a comprehensive response effectiveness evaluation of the rescue operation plan, constructing a multi-dimensional risk assessment model by combining historical cases and marine meteorological forecast data; then, it utilizes the particle fitness function F(p) and the route selection probability P... select(p) Quantitatively score each rescue operation plan and ensure the comparability of the scores through normalization; finally, apply situational awareness technology to verify the feasibility and safety of candidate routes, and generate the final preliminary route planning suggestions based on the latest on-site feedback and mission requirements.

[0116] The following is a brief introduction to the design rationale behind each term of the formula:

[0117] F(p)=α·R(p)+β·S(p)-γ·C(p)+η·D(p)-ζ·I(p)

[0118] Response effect α·R(p): reflects the path's responsiveness to different situations; Safety β·S(p): comprehensively considers the performance parameters of rescue vessels and the safety index and psychological state of emergency responders; Cost -γ·C(p): measures the cost factors of the path; Distance η·D(p): measures the total length of the path; Interference impact -ζ·I(p): assesses the potential interference risks on the path based on a multi-dimensional dynamic interference map;

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

[0120] α, β, γ, η, and ζ are weighting coefficients, representing the importance of response effect, safety, cost, distance, and interference, respectively, and are determined through expert experience and experimental data; R(p) is obtained by simulating the response effect under different scenarios; S(p) is calculated by combining ship performance parameters and monitoring data on the psychological state of emergency responders; C(p) is estimated based on factors such as fuel consumption and time; D(p) is directly measured by the GPS positioning system; and I(p) is obtained through real-time monitoring and historical data statistics.

[0121] The following is a brief introduction to the design rationale behind each term of the formula:

[0122]

[0123] Path selection probability Ensure the sum of probabilities of all paths is 1; Impact of environmental changes: δ.V(p): reflects the uncertainty and risk of the path in the current environment; Time sensitivity θ·T(p): reflects the impact of the urgency of the task; Impact of unknown factors -λ.U(p): reflects the unknown risks and probability of change in the path;

[0124] The following is a brief introduction to how the parameters of this formula are obtained:

[0125] N represents the total number of particles, i.e., the number of all possible paths; δ is the variation intensity coefficient, obtained through historical data analysis; V(p) is the variation value calculated based on real-time monitoring data and historical data; θ is the time sensitivity coefficient, set according to the urgency of the task; T(p) is estimated through current conditions and historical data; λ is the uncertainty coefficient, set through expert experience; U(p) is based on situational awareness technology to assess the unknown risks and changes in the path.

[0126] Assuming a maritime search and rescue mission, the system has completed a preliminary risk assessment and established response models for multiple possible rescue action plans. First, the system calculates the particle fitness function F(p) for each plan based on these models: F(p) = 0.3·85 + 0.4·90 - 0.1·70 + 0.15·60 - 0.05·20, where α = 0.3, β = 0.4, γ = 0.1, η = 0.15, and ζ = 0.05, resulting in F(p) = 80.5. Second, the system converts the fitness score into path selection probabilities. Where N = 5, δ = 0.05, V(p) = 0.8, θ = 0.1, T(p) = 3.5, λ = 0.02, U(p) = 0.3, and finally P is calculated. select (p) = 0.25; then, the system randomly sampled and selected a candidate path, and applied situational awareness technology to verify its feasibility and safety; finally, based on the latest on-site feedback and task requirements, the candidate path was optimized and the optimal path was selected, ensuring the safe and efficient implementation of the rescue operation.

[0127] Through the above steps, the system not only improves the scientific rigor and accuracy of route selection but also enhances its adaptability to complex maritime environments, ensuring that rescue operations can be completed safely and effectively in the shortest possible time. Assuming a threshold of 0.2 is set, the result exceeding this threshold indicates that the route has a high probability of selection, effectively guaranteeing the safety and efficiency of the rescue operation.

[0128] To address the issue of insufficient response to unforeseen circumstances in path planning within complex and dynamic maritime environments, some embodiments incorporate a Bayesian optimization-based adaptive adjustment mechanism based on the specific execution path. This mechanism performs real-time reassessment of the path in the event of unforeseen emergencies and utilizes contextual awareness technology to continuously monitor and provide early warnings of changes in the surrounding environment, generating alternative routes, including:

[0129] Using the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to monitor and process the path in real time, obtaining path monitoring data. Based on the path monitoring data and information on unforeseen emergencies, a Bayesian optimization algorithm is applied to re-evaluate the current path in real time, generating a re-evaluation result. Based on the re-evaluation result, contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment, obtaining environmental change warning information. Using the environmental change warning information, combined with historical path data and current task requirements, the path is dynamically adjusted to generate alternative routes.

[0130] In this embodiment, a Bayesian optimization-based adaptive adjustment mechanism is introduced using the specific execution path to monitor and process the path in real time, obtaining path monitoring data. This data includes information such as vessel position, speed, and surrounding environment, used to monitor the path status in real time. Based on this monitoring data and information on unforeseen emergencies, a Bayesian optimization algorithm is applied to re-evaluate the current path, generating a re-evaluation result. This re-evaluation result reflects the feasibility and safety of the current path under emergencies. Based on the re-evaluation result, contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment, obtaining environmental change warning information. This warning information provides a safety prediction of potential future impacts on the path, helping to address risks in advance. Using this environmental change warning information, combined with historical path data and current task requirements, the path is dynamically adjusted to generate alternative routes. These alternative routes are safe and efficient alternative paths that have been considered from all perspectives.

[0131] In this embodiment, firstly, the system introduces a Bayesian optimization adaptive adjustment mechanism to collect and analyze data on the specific execution path in real time, ensuring comprehensive control over the path status. Secondly, when any unforeseen emergencies are detected, the system immediately applies the Bayesian optimization algorithm to quickly generate new path evaluation results based on the latest path monitoring data and emergencies information. Thirdly, the system uses contextual awareness technology to continuously monitor changes in the surrounding environment and issue early warning information to predict potential risks. Finally, the system combines these early warning information, historical path data, and the specific requirements of the current task to dynamically adjust the path and generate one or more alternative routes to ensure that the rescue operation is not affected by emergencies.

[0132] Here is a specific example:

[0133] Suppose a rescue ship is en route to an accident site when it suddenly encounters a severe storm warning. First, the system activates a Bayesian-optimized adaptive adjustment mechanism, collecting real-time data on the ship's position, speed, and surrounding sea conditions to generate detailed path monitoring data. Second, upon detecting the sudden storm, the system immediately applies a Bayesian optimization algorithm, combining the latest path monitoring data and storm information to quickly reassess the safety and feasibility of the current path, arriving at a new assessment result. Third, the system utilizes contextual awareness technology to continuously monitor changes in the surrounding environment, such as wind speed and wave height, and issues corresponding warnings to alert users to potential risks. Finally, the system integrates these warnings, data from past successful paths, and the specific requirements of the mission (such as time urgency and the location of those in distress) to dynamically adjust the path, generating an alternative route that avoids the storm zone and reaches the destination as quickly as possible.

[0134] Through the above steps, the system can not only respond quickly to emergencies, but also ensure the safety and efficiency of rescue operations, maximizing the success rate of rescue missions.

[0135] To address the issue of insufficient monitoring of changes in the surrounding environment during path planning, some embodiments involve using context-aware technology based on the reassessment results to continuously monitor and provide early warnings of changes in the surrounding environment, thereby obtaining environmental change early warning information, including:

[0136] Using the reassessment results and real-time marine environmental data, potential risk areas around the current path are identified and processed to generate a potential risk area map. Based on the potential risk area map, multi-source sensing fusion technology is applied to integrate data from multiple types of sensors to comprehensively sense and process the surrounding environment, obtaining comprehensive sensing data. Based on the comprehensive sensing data, contextual awareness technology is used to predict the changing trends of the surrounding environment, generating an environmental change prediction model. Using the environmental change prediction model, combined with historical data and real-time monitoring information, early warning processing is performed for possible emergencies, generating environmental change early warning information.

[0137] In this embodiment, the reassessment results, combined with real-time marine environmental data, are used to identify potential risk areas around the current path, generating a potential risk area map. This map identifies areas that may pose safety hazards to rescue operations, such as strong storms and ocean currents, and is used to guide path adjustments. Based on this potential risk area map, multi-source sensing fusion technology is applied to integrate data from multiple types of sensors, performing comprehensive sensing processing on the surrounding environment to obtain comprehensive sensing data. This comprehensive sensing data comes from various sensors (such as weather stations, radar, and satellite images), providing comprehensive environmental information. Based on this comprehensive sensing data, scenario-aware technology is used to predict the changing trends of the surrounding environment, generating an environmental change prediction model. This model can predict environmental changes over a future period, helping to prepare countermeasures in advance. Using this environmental change prediction model, combined with historical data and real-time monitoring information, early warning processing is performed for possible emergencies, generating environmental change early warning information. This early warning information provides timely risk alerts, ensuring the safety and efficiency of rescue operations.

[0138] In this embodiment, firstly, based on the reassessment results and the latest marine environmental data, the system identifies potential risk areas around the current path and draws a detailed map of these potential risk areas. Secondly, the system integrates data from different types of sensors using multi-source perception fusion technology to form a comprehensive perception of the surrounding environment and obtain accurate comprehensive perception data. Thirdly, the system uses this comprehensive perception data, combined with situational awareness technology, to analyze and predict the changing trends of the surrounding environment and construct an environmental change prediction model. Finally, the system combines this prediction model with historical data and real-time monitoring information to provide early warning processing for possible emergencies, ultimately generating environmental change early warning information to ensure that rescue operations can respond to environmental changes in a timely manner.

[0139] Here is a specific example:

[0140] Suppose a rescue vessel is on an emergency mission and suddenly receives a reassessment indicating an unforeseen high-risk area ahead. First, the system, combining the latest marine weather forecasts and the vessel's current position, identifies potential risk areas near its current path, such as areas of severe storms or abnormal currents, and generates a detailed map of these potential risk areas. Second, the system uses various sensors installed on the vessel (such as weather stations, radar, and underwater sonar) to collect data on the surrounding environment. After multi-source sensing fusion processing, it forms comprehensive sensing data, providing detailed information on wind speed, wave height, and current velocity. Third, based on this comprehensive sensing data, the system uses situational awareness technology to analyze trends in environmental changes, predicting possible events in the next few hours and constructing an environmental change prediction model. Finally, the system combines this prediction model with historical data from similar past situations and current real-time monitoring information to provide early warnings of potential risks, generating environmental change warning information to alert the rescue team to impending severe weather and recommending evacuation measures or alternative routes.

[0141] Through the above steps, the system not only improves its ability to monitor and warn of changes in the surrounding environment, but also enhances the safety and flexibility of rescue operations, ensuring the smooth progress of the mission.

[0142] This application addresses the shortcomings of existing path planning methods, such as untimely response to emergencies, lack of comprehensive consideration of environmental changes and unknown risks, and insufficient adaptability in complex and ever-changing maritime environments. Therefore, this invention proposes this alternative solution. By introducing a Bayesian optimization algorithm, this solution aims to solve the technical problems of existing path planning methods in terms of inflexible path adjustment, difficulty in guaranteeing safety and efficiency when facing unforeseen emergencies, thereby improving the success rate and safety of maritime emergency rescue missions.

[0143] Optionally, the step of applying a Bayesian optimization algorithm to re-evaluate the current path in real time based on the path monitoring data and information on unforeseen emergencies, and generating a re-evaluation result, includes:

[0144] Before calculating the Bayesian score B(p) of path p, it is necessary to comprehensively analyze and process information including environmental monitoring, risk assessment, historical data and multi-source sensing fusion information to build a response model and prepare for subsequent score calculation.

[0145]

[0146] Wherein, B(p) represents the Bayesian score of path p; W, X, Y, Z represent weighting coefficients, corresponding to the degree of influence of response effect, safety, cost, and distance, respectively; Γ, Δ, Ω are power coefficients used to adjust the influence intensity of each factor on the score; R(p) is the path response effect score calculated based on the response model; S(p) represents the safety score that comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel; C(p) represents the cost assessment of the path; D(p) represents the total length of the path; H is the interference influence weighting coefficient; I(p) represents the interference influence score, which assesses the potential interference risk on the path based on a multi-dimensional dynamic interference map; J is the uncertainty influence coefficient; Λ is the environmental change influence intensity coefficient; V(p) represents the variation value of particle p, calculated based on real-time monitoring data and historical data, representing the uncertainty and risk of the path in the current environment; Φ is the unknown factor influence coefficient; U(p) represents the uncertainty score, which assesses the unknown risks and changes in the path based on situational awareness technology.

[0147] After calculating B(p), the Bayesian score is converted into the path selection probability P for re-evaluation by means of normalization and the introduction of a time-sensitivity coefficient. reassess (p), and dynamically adjust the selection probability according to the real-time situation to reflect the current environmental changes;

[0148]

[0149] Where N represents the total number of particles; B(i) represents the Bayesian score of path i; Θ is a probability enhancement factor used to emphasize the influence of the Bayesian score on the path selection probability; K is the environmental change influence coefficient; V(p) represents the variation value of particle p; M is the uncertainty coefficient; U(p) represents the uncertainty score; L is an enhancement factor used to emphasize the influence of environmental changes and uncertainty on the path selection probability; Ψ is the time sensitivity coefficient, reflecting the influence of task urgency; T(p) represents the expected completion time of particle p; T0 is the expected time reference point used to evaluate the time efficiency of the path.

[0150] Complete P reassess (p) After calculation, the system randomly samples candidate paths based on the latest probability distribution, performs situational awareness verification and further optimization, generates instant re-evaluation results, and guides the selection of the optimal path.

[0151] This formula aims to ensure that route selection can be rapidly and optimally adjusted in the event of unforeseen emergencies, and to comprehensively consider the impact of environmental changes and unknown risks. This scheme proposes an immediate re-evaluation mechanism based on a Bayesian optimization algorithm. This mechanism first constructs a response model by comprehensively analyzing and processing route monitoring data and emergency situation information; then, it uses a Bayesian score B(p) to comprehensively quantify and evaluate the current route; finally, through normalization methods and the introduction of a time-sensitivity coefficient, the Bayesian score is converted into a probability P for re-evaluating the route selection. reassess (p) and dynamically adjust the selection probability according to the real-time situation to reflect the current environmental changes and ensure that the path selection can flexibly respond to emergencies.

[0152] The following is a brief introduction to the design rationale behind each term of the formula:

[0153]

[0154] Response effectiveness W·R(p): Reflects the path's responsiveness to different situations; Safety X·S(p): A comprehensive analysis of the rescue vessel's performance parameters and the safety index and psychological state of the emergency responders; Cost Y·C(p): Measures the cost factors of the path; Distance Z·D(p): Measures the total length of the path; Interference impact H·I(p): Assess the potential interference risks on the path based on a multi-dimensional dynamic interference map; Uncertainty impact J·(Λ·V(p)+Φ·U(p)): Reflects the uncertainty and unknown risks of the path in the current environment;

[0155] The following is a brief introduction to how the parameters of this formula are obtained:

[0156] W, X, Y, and Z are weighting coefficients, corresponding to the degree of influence of response effect, safety, cost, and distance, respectively, determined through expert experience and experimental data; Γ, Δ, and Ω are power coefficients used to adjust the influence intensity of each factor on the score, calibrated through experimental data; R(p) is obtained by simulating the response effect under different scenarios; S(p) is calculated by combining ship performance parameters and monitoring data of the psychological state of emergency responders; C(p) is estimated based on factors such as fuel consumption and time; D(p) is directly measured by the GPS positioning system; H is the interference influence weighting coefficient, obtained through historical data analysis; I(p) is obtained through real-time monitoring and historical data statistics; J is the uncertainty influence coefficient, set through expert experience; Λ is the environmental change influence intensity coefficient, obtained through historical data analysis; V(p) is the variation value calculated based on real-time monitoring data and historical data; Φ is the unknown factor influence coefficient, set through expert experience; U(p) is based on situational awareness technology to assess the unknown risks and changes in the path.

[0157] The following is a brief introduction to the design rationale behind each term of the formula:

[0158]

[0159] Bayesian rating conversion Ensure the sum of probabilities for all paths equals 1; Environmental change impact: KB(p): reflects the uncertainty and risk of the path under the current environment; Uncertainty impact - M·U(p): reflects the unknown risks and probabilities of change in the path; Time sensitivity. The impact reflects the urgency of the task;

[0160] The following is a brief introduction to how the parameters of this formula are obtained:

[0161] N represents the total number of particles, i.e., the number of all possible paths; B(i) represents the Bayesian score of path i, calculated using the formula B(p); Θ is a probability enhancement factor, used to emphasize the influence of the Bayesian score on the path selection probability, calibrated using experimental data; K is the environmental change influence strength coefficient, obtained through historical data analysis; V(p) is the variation value calculated based on real-time monitoring data and historical data; M is the uncertainty coefficient, set through expert experience; U(p) assesses the unknown risks and changes in the path based on situational awareness technology; L is an enhancement factor used to emphasize the influence of environmental changes and uncertainties on the path selection probability, calibrated using experimental data; ψ is the time sensitivity coefficient, reflecting the influence of task urgency, set through expert experience; T(p) is estimated through current conditions and historical data; T0 is the expected time baseline, used to evaluate the time efficiency of the path, set according to task requirements.

[0162] Assuming that in a maritime search and rescue mission, the system has completed preliminary path planning and established detailed path monitoring data; firstly, the system comprehensively analyzes and processes information including environmental monitoring, risk assessment, historical data, and multi-source sensing fusion information to construct a response model, preparing for subsequent score calculation; then, the system calculates the Bayesian score B(p) of path p = ((0.4·85+0.6·90)). 2 ) / ((0.3·70+0.2U60) (1.5+0.5) ·20 3 )×e -0.1·(0.8·0.8+0.2·0.3) Where W = 0.4, X = 0.6, Y = 0.3, Z = 0.2, Γ = 2, Δ = 1.5, H = 0.5, Ω = 3, J = 0.1, Λ = 0.8, Φ = 0.2, and finally B(p) = 0.78 is calculated; secondly, the system converts the Bayesian score into the probability of re-evaluating the path selection by means of normalization methods and the introduction of time sensitivity coefficients. Where N = 5, Θ = 1.2, K = 0.05, M = 0.02, L = 1.5, ψ = 0.1, T(p) = 3.5, T0 = 3, and finally P is calculated. reassess (p) = 0.28; then, the system randomly samples a candidate path based on the latest probability distribution, and performs situational awareness verification and further optimization; finally, the system generates an instant re-evaluation result, which guides the selection of the optimal path and ensures the safe and efficient implementation of the rescue operation.

[0163] Through the above steps, the system not only improves the scientific rigor and accuracy of route selection but also enhances its adaptability to complex maritime environmental changes, ensuring that rescue operations can be completed safely and effectively in the shortest possible time. Assuming a threshold of 0.2 is set, the result exceeding this threshold indicates that the route has a high probability of selection, effectively guaranteeing the safety and efficiency of the rescue operation.

[0164] To address the issues of insufficient information synchronization and dynamic adjustment in maritime emergency rescue route planning, some embodiments integrate maritime communication systems and intelligent navigation aids to achieve two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the specific execution route and the alternative routes are dynamically revised to obtain an optimized maritime emergency rescue route, including:

[0165] By utilizing a maritime communication system, a two-way information transmission channel is established between the emergency rescue team and the command center to synchronously update real-time information and generate a synchronously updated information stream. Based on the synchronously updated information stream and data from intelligent navigation assistance equipment, the progress of the current rescue mission is tracked in real time to obtain a mission progress report. Based on the mission progress report, a dynamic correction algorithm is applied to adjust the specific execution path and the alternative routes according to the latest on-site feedback, generating a dynamic correction scheme.

[0166] Using the aforementioned dynamic correction scheme, combined with environmental change early warning information and the latest mission requirements, the route is finally optimized to obtain the optimized maritime emergency rescue route.

[0167] In this embodiment, a two-way information transmission channel is established between the emergency rescue team and the command center using a maritime communication system. Real-time information is updated synchronously to generate a synchronously updated information stream. This stream includes data such as vessel position, speed, and environmental conditions to ensure real-time information sharing between the emergency rescue team and the command center. Based on this synchronously updated information stream and data from intelligent navigation aids, the progress of the current rescue mission is tracked in real time, resulting in a mission progress report. This report details each step of the rescue operation and any problems encountered, providing a basis for subsequent adjustments. Based on the mission progress report, a dynamic correction algorithm is applied to adjust the specific execution path and alternative routes based on the latest on-site feedback, generating a dynamic correction scheme. This scheme considers changes in the latest situation to ensure the safety and efficiency of path selection. Using this dynamic correction scheme, combined with environmental change warning information and the latest mission requirements, the path is finally optimized to obtain an optimized maritime emergency rescue path. This optimized path comprehensively considers all factors to ensure the efficient and safe completion of the rescue operation.

[0168] In this embodiment, firstly, the system integrates a maritime communication system to establish a two-way information transmission channel between the emergency rescue team and the command center, ensuring that both parties can exchange the latest information and data in real time, forming a continuous information flow. Secondly, the system combines data provided by intelligent navigation assistance equipment, such as GPS coordinates, speed, and heading, to track the progress of the current rescue mission in real time and generate a detailed mission progress report. Thirdly, based on this report, the system applies a dynamic correction algorithm to make necessary adjustments to the specific execution path and alternative routes according to the latest on-site feedback (such as weather changes and the status of the distressed personnel), formulating a dynamic correction plan. Finally, the system combines this correction plan with environmental change early warning information (such as storm forecasts) and the latest mission requirements to perform final path optimization processing, ensuring that the selected path is both safe and efficient, meeting the current rescue needs.

[0169] Here is a specific example:

[0170] Imagine a complex maritime search and rescue mission where a rescue vessel is en route to the accident site. First, the system integrates maritime communication systems to establish a stable two-way information transmission channel between the emergency response team and the command center. This ensures that both sides can instantly share crucial information such as the vessel's position, speed, and surrounding sea conditions, creating a continuously updated information flow. Second, the system combines data from intelligent navigation aids, such as GPS positioning and radar monitoring results, to track every detail of the rescue mission in real time, generating a detailed mission progress report that records the rescue vessel's route, estimated arrival time, and potential problems. Third, based on this report, the system applies a dynamic correction algorithm, taking into account the latest on-site feedback (such as the discovery of new obstacles or more accurate locations of those in distress), adjusting the originally planned execution path and alternative routes to develop a dynamic correction plan. Finally, the system combines this correction plan with environmental change warnings (such as an impending strong wind warning) and the latest mission requirements (such as the need for additional rescue supplies) to perform final route optimization, ensuring the rescue vessel avoids dangerous areas and reaches its destination as quickly as possible.

[0171] Through the above steps, the system not only achieves efficient information synchronization between the emergency medical team and the command center, but also ensures that rescue operations can be carried out smoothly in complex and ever-changing environments by dynamically correcting and optimizing the routes, thereby improving the success rate and safety of rescue operations.

[0172] Figure 2 This application provides a schematic diagram of the structure of an optimization system based on the psychological adaptation of emergency responders, as shown in the embodiment of the present application. Figure 2 As shown, the device includes:

[0173] The collection module 21 is used to collect dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation.

[0174] The acquisition module 22 is used to acquire psychological state monitoring data of emergency responders, analyze the psychological stress level of emergency responders using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results.

[0175] Simulation module 23 is used to simulate the response effects of different rescue action plans under various possible changing scenarios by applying an intelligent path planning algorithm based on particle swarm optimization algorithm according to the risk assessment results. It comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel to generate a specific execution path.

[0176] The evaluation module 24 is used to introduce an adaptive adjustment mechanism based on Bayesian optimization based on the specific execution path, to re-evaluate the path in real time when encountering unforeseen emergencies, and to continuously monitor and warn of changes in the surrounding environment using situational awareness technology, and to generate alternative routes.

[0177] The correction module 25 is used to integrate the maritime communication system and intelligent navigation auxiliary equipment to realize the two-way information synchronization update between the emergency rescue team and the command center. Based on the latest on-site feedback, it dynamically corrects the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

[0178] Figure 2 The aforementioned optimization system based on the psychological adaptation of emergency responders can execute... Figure 1 The implementation principle and technical effects of the optimization method based on the psychological adaptation of emergency responders described in the illustrated embodiment will not be repeated here. The specific methods by which each module and unit performs its operations in the above embodiment of the optimization system based on the psychological adaptation of emergency responders have been described in detail in the embodiments related to this method, and will not be elaborated upon here.

[0179] In one possible design, Figure 2 An optimization system based on the psychological adaptation of emergency responders, as shown in the embodiment, can be implemented as a computing device, such as... Figure 3 As shown, the computing device may include a storage component 31 and a processing component 32;

[0180] 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.

[0181] The processing component 32 is used to: collect dynamic information on the emergency rescue site and the surrounding sea area corresponding to the emergency rescue mission; combine historical rescue cases and marine meteorological forecast data; construct a multi-dimensional risk assessment model using a machine learning model to obtain risk assessment results, which comprehensively cover all variables that may affect the emergency rescue operation; acquire psychological state monitoring data of emergency personnel; analyze the psychological stress level of emergency personnel using machine learning algorithms to obtain psychological state analysis results; and generate personalized psychological support plans for each emergency rescue mission based on the psychological state analysis results; and, according to the risk assessment results, apply an intelligent path planning algorithm based on particle swarm optimization to perform different rescue operation plans in various possible changing scenarios. The response effect is simulated, and a specific execution path is generated by comprehensively considering the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel. Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in case of unforeseen emergencies. Contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment and generate alternative routes. The maritime communication system and intelligent navigation assistance equipment are integrated to realize the two-way information synchronization between the emergency team and the command center. The specific execution path and the alternative routes are dynamically corrected based on the latest on-site feedback to obtain an optimized maritime emergency rescue path.

[0182] 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.

[0183] 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.

[0184] Of course, computing devices may also include other components, such as input / output interfaces, display components, communication components, etc.

[0185] Input / output interfaces provide interfaces between processing components and peripheral interface modules, which can be output devices, input devices, etc.

[0186] The communication components are configured to facilitate wired or wireless communication between computing devices and other devices.

[0187] 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.

[0188] 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 An optimization method based on the psychological adaptation of emergency responders is shown in the embodiment.

[0189] 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.

[0190] 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.

[0191] 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.

[0192] 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. An optimization method based on the psychological adaptation of emergency responders, characterized in that, include: Dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission is collected. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation. Acquire psychological state monitoring data of emergency responders, analyze their psychological stress levels using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results. Based on the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of different rescue action plans under various possible changing scenarios. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel, a specific execution path is generated. Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in real time when encountering unforeseen emergencies. Contextual awareness technology is used to continuously monitor and warn of changes in the surrounding environment and generate alternative routes. By integrating maritime communication systems and intelligent navigation aids, the system enables two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the system dynamically modifies the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

2. The method according to claim 1, characterized in that, Based on the risk assessment results, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of different rescue operation plans under various possible changing scenarios. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency responders, a specific execution path is generated, including: Using the risk assessment results, the response effects of different rescue action plans under various possible changing scenarios are modeled to obtain the response model of the rescue action plan; Based on the response model, an intelligent path planning algorithm based on particle swarm optimization is applied to simulate the response effects of each rescue action plan. Taking into account the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel, preliminary path planning suggestions are generated. Based on the preliminary route planning suggestions, and combined with historical data and real-time information, the safety and feasibility of the route are evaluated to obtain the route evaluation results. Using the path evaluation results, the path selection strategy is continuously improved through iterative learning to ensure that the path selection can adapt to the complex marine environment and generate specific execution paths.

3. The method according to claim 2, characterized in that, Based on the preliminary route planning suggestions, and combining historical data and real-time information, the safety and feasibility of the route are evaluated to obtain the route evaluation results, including: Using the aforementioned preliminary route planning suggestions and combining them with historical rescue data, a statistical analysis of the historical success rate and failure cases of each route is conducted to obtain a route historical evaluation report. Based on the historical assessment report of the route and combined with real-time marine environmental monitoring information, the current safety and feasibility of the route are dynamically assessed, and real-time assessment indicators of the route are generated. Based on the real-time evaluation indicators of the path, a risk prediction model is applied to estimate the risks that may be encountered in the future, and the path risk prediction results are obtained. Using the path risk prediction results, and taking into account the urgency of the rescue mission and resource availability, a comprehensive evaluation of each path is conducted to generate path assessment results.

4. The method according to claim 2, characterized in that, The process of using the path evaluation results to continuously improve the path selection strategy through iterative learning, ensuring that the path selection can adapt to complex maritime environments, and generating specific execution paths includes: Using the path evaluation results, different path schemes are scored to obtain a path scoring table; Based on the path scoring table, a machine learning model is applied to optimize the path selection strategy. Iterative learning is performed based on historical and real-time data to generate an optimized path selection model. Based on the optimized path selection model, and combined with the current rescue mission requirements and environmental change predictions, the path selection strategy is adjusted to obtain the adjusted path planning draft. Using the revised path planning draft, verification testing is conducted in a simulation environment to collect feedback data and perform performance evaluation, thereby generating a specific execution path.

5. The method according to claim 1, characterized in that, Based on the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to re-evaluate the path in real time when encountering unforeseen emergencies. Contextual awareness technology is used to continuously monitor and provide early warnings of changes in the surrounding environment, generating alternative routes, including: Using the specific execution path, an adaptive adjustment mechanism based on Bayesian optimization is introduced to monitor and process the path in real time, thereby obtaining path monitoring data. Based on the path monitoring data and combined with information on unforeseen emergencies, the Bayesian optimization algorithm is applied to re-evaluate the current path in real time, generating a re-evaluation result. Based on the reassessment results, situational awareness technology is used to continuously monitor and provide early warning of changes in the surrounding environment, thereby obtaining early warning information on environmental changes. Using the environmental change early warning information, combined with historical path data and current task requirements, the path is dynamically adjusted to generate alternative routes.

6. The method according to claim 5, characterized in that, Based on the reassessment results, situational awareness technology is used to continuously monitor and provide early warnings of changes in the surrounding environment, resulting in environmental change early warning information, including: Using the reassessment results and real-time marine environmental data, potential risk areas around the current path are identified and processed to generate a potential risk area map; Based on the potential risk area map, multi-source sensing fusion technology is applied to integrate data from multiple types of sensors to perform comprehensive sensing processing on the surrounding environment, resulting in comprehensive sensing data. Based on the comprehensive perception data, the changing trends of the surrounding environment are predicted using contextual awareness technology, and an environmental change prediction model is generated. By utilizing the aforementioned environmental change prediction model, combined with historical data and real-time monitoring information, early warning processing can be carried out for possible emergencies, generating environmental change early warning information.

7. The method according to claim 1, characterized in that, The integrated maritime communication system and intelligent navigation aids enable two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, the specific execution path and alternative routes are dynamically revised to obtain an optimized maritime emergency rescue path, including: By utilizing the maritime communication system, a two-way information transmission channel is established between the emergency rescue team and the command center to synchronously update and process real-time information and generate a synchronously updated information flow. Based on the synchronously updated information stream and combined with data from the intelligent navigation assistance device, the progress of the current rescue mission is tracked and processed in real time to obtain a mission progress report. Based on the task progress report, a dynamic correction algorithm is applied to adjust the specific execution path and the alternative routes according to the latest on-site feedback, thereby generating a dynamic correction scheme. Using the aforementioned dynamic correction scheme, combined with environmental change early warning information and the latest mission requirements, the route is finally optimized to obtain the optimized maritime emergency rescue route.

8. An optimization system based on the psychological adaptation of emergency responders, characterized in that, include: The data collection module is used to collect dynamic information on the emergency rescue site and the sea area along the route corresponding to the emergency rescue mission. Combined with historical rescue cases and marine meteorological forecast data, a multi-dimensional risk assessment model is constructed using a machine learning model to obtain risk assessment results. The risk assessment results comprehensively cover all variables that may affect the emergency rescue operation. The acquisition module is used to acquire psychological state monitoring data of emergency responders, analyze the psychological stress level of emergency responders using machine learning algorithms, obtain psychological state analysis results, and generate personalized psychological support plans for each emergency response task based on the psychological state analysis results. The simulation module is used to simulate the response effects of different rescue action plans under various possible changing scenarios based on the risk assessment results and an intelligent path planning algorithm based on particle swarm optimization. It comprehensively considers the performance parameters of the rescue vessel and the safety index and psychological state analysis results of the emergency personnel to generate a specific execution path. The evaluation module is used to introduce an adaptive adjustment mechanism based on Bayesian optimization based on the specific execution path, to re-evaluate the path in real time when encountering unforeseen emergencies, and to continuously monitor and warn of changes in the surrounding environment using context awareness technology, and to generate alternative routes. The correction module integrates the maritime communication system and intelligent navigation aids to realize the two-way information synchronization between the emergency rescue team and the command center. Based on the latest on-site feedback, it dynamically corrects the specific execution path and the alternative routes to obtain an optimized maritime emergency rescue path.

9. A computing device, characterized in that, It includes a processing component and a storage component; the storage component stores one or more computer instructions; the one or more computer instructions are invoked and executed by the processing component to implement an optimization method based on the psychological adaptation of emergency responders as described in any one of claims 1 to 7.

10. A computer storage medium, characterized in that, The device contains a computer program that, when executed by a computer, implements an optimization method based on the psychological adaptation of emergency responders as described in any one of claims 1 to 7.

Images