Ship accident emergency closed-loop management methods, devices, equipment and media

Abstract

This application relates to a closed-loop management method, apparatus, equipment, and medium for ship accident emergency response, applied in the field of ship accident management technology. The method includes: acquiring ship monitoring data and rescue force distribution information; analyzing the ship monitoring data to determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue; if the ship anomaly information includes the anomaly requiring rescue, determining a rescue strategy based on the ship anomaly information and the rescue force distribution information, the rescue strategy including a rescue route determined based on rescue priority; analyzing the ship anomaly information and the rescue force distribution information to determine a maintenance and improvement strategy; and determining an accident management strategy based on the rescue strategy and the maintenance and improvement strategy. This application has the effect of reducing losses caused by ship accidents.

Description

Technical Field

[0001] This application relates to the technical field of ship accident management, and in particular to a method, apparatus, equipment and medium for closed-loop emergency management of ship accidents. Background Technology

[0002] Ship accidents occur frequently during operation due to various factors such as severe weather, mechanical failure, and human error. If an accident is not handled promptly and effectively, it can result in serious casualties, property damage, and environmental pollution.

[0003] Currently, there are many problems in handling ship accidents. On the one hand, when an accident occurs, the abnormal situation is often judged and a rescue plan is formulated based on human experience. However, due to limitations in human experience and manpower, the efficiency and accuracy of the rescue cannot be guaranteed, resulting in the inability to reduce losses in a timely manner. On the other hand, existing accident handling often lacks an effective closed-loop management mechanism. After the accident rescue is completed, there is no analysis and summary of the abnormality and the rescue process, and the lessons learned cannot be fed back into subsequent ship safety management work, which may lead to similar accidents recurring and causing more losses. Summary of the Invention

[0004] In order to reduce the losses caused by ship accidents, this application provides a method, device, equipment and medium for closed-loop emergency management of ship accidents.

[0005] Firstly, this application provides a closed-loop emergency management method for ship accidents, employing the following technical solution:

[0006] A closed-loop emergency management method for ship accidents includes:

[0007] Obtain ship monitoring data and information on the distribution of rescue forces;

[0008] The ship monitoring data is analyzed to determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue.

[0009] If the ship anomaly information includes the anomaly to be rescued, then a rescue strategy is determined based on the ship anomaly information and the rescue force distribution information. The rescue strategy includes a rescue route, which is determined based on the rescue priority.

[0010] The abnormal ship information and the distribution information of the rescue forces are analyzed to determine maintenance and improvement strategies;

[0011] An accident management strategy is determined based on the rescue strategy and the maintenance improvement strategy.

[0012] By adopting the above technical solutions and analyzing ship monitoring data, abnormal situations can be detected in a timely manner. Automatic and rapid generation of rescue strategies improves rescue efficiency, thereby reducing losses caused by delayed rescues during ship accidents. Rescue routes are determined according to rescue priorities, ensuring that higher-priority incidents receive more timely assistance. Post-incident analysis of ship anomaly information and rescue force distribution information allows for the determination of maintenance and improvement strategies, enabling timely learning of lessons, reducing the probability of subsequent anomalies, and further improving rescue efficiency, thus further reducing losses caused by ship accidents.

[0013] Optionally, acquiring ship monitoring data includes:

[0014] Obtain vessel and crew information;

[0015] A first monitoring strategy is determined based on the ship information and the crew information;

[0016] The vessel information and crew information are analyzed to determine whether the vessel is a key monitoring vessel and whether there are key monitoring crew members.

[0017] A second monitoring strategy is determined based on the key monitored vessels and the key monitored crew members;

[0018] The data acquisition frequency is determined based on the first monitoring strategy and the second monitoring strategy;

[0019] The ship monitoring data is obtained based on the data acquisition frequency.

[0020] By adopting the above technical solution, anomaly monitoring can be carried out for different ships and crew members according to different data acquisition frequencies, saving computing resources without affecting the monitoring effect.

[0021] Optionally, the analysis of the ship monitoring data to determine ship anomaly information includes:

[0022] The ship monitoring data is integrated and analyzed to obtain corrected monitoring data;

[0023] The corrected monitoring data is analyzed to determine the abnormal information of the ship;

[0024] The process of integrating and analyzing the ship monitoring data to obtain corrected monitoring data includes:

[0025] The ship monitoring data is classified to obtain multiple monitoring data combinations, and each monitoring data combination corresponds to a data type.

[0026] If there are multiple ship monitoring data in the monitoring data combination, then calculate the error value between every two ship monitoring data in the monitoring data combination;

[0027] If all the error values ​​are less than the first error value, then the weight value is determined based on the accuracy of each of the ship monitoring data.

[0028] The corrected monitoring data is determined based on the weight values ​​and the ship monitoring data;

[0029] If there is an error value greater than or equal to the first error value, and all of the error values ​​are less than the second error value, then the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data.

[0030] If there is an error value that is greater than or equal to the second error value, then the error value that is greater than or equal to the second error value is determined to be a serious error value;

[0031] Count the first number of the severe error values;

[0032] Count the second number of all error values ​​in the aforementioned monitoring data combination;

[0033] The deviation ratio is determined based on the first quantity and the second quantity;

[0034] If the deviation ratio is greater than the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information and the historical monitoring data.

[0035] If the deviation ratio is less than or equal to the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data.

[0036] By adopting the above technical solution, the accuracy of ship monitoring data is improved through mutual verification between ship monitoring data of the same data type. When the error values ​​between ship monitoring data of the same data type are in different ranges, different methods are used for correction, which further improves the accuracy of ship monitoring data.

[0037] Optionally, the corrected monitoring data includes vessel position data and video data, and the analysis of the corrected monitoring data to determine vessel anomaly information includes:

[0038] The corrected monitoring data is compared with the standard data threshold to determine the first abnormal information;

[0039] The ship's position data is analyzed to determine the second anomaly.

[0040] The video data is identified to determine the third abnormal information;

[0041] The ship's abnormal information is determined based on the first abnormal information, the second abnormal information, and the third abnormal information;

[0042] The analysis of the ship position data to determine the second anomaly includes:

[0043] The ship's speed is determined based on the ship's position data;

[0044] The abnormal speed and abnormal type are determined based on the ship's sailing speed and the anomaly judgment rules.

[0045] If the duration of consecutive abnormal speeds corresponding to the same type of abnormality exceeds a preset duration, then speed abnormality information is generated based on the type of abnormality and the duration of consecutive abnormality.

[0046] Obtain the ship's navigation trajectory for the current voyage;

[0047] Meteorological data is obtained based on the ship's position data and its navigation trajectory.

[0048] Based on the ship's position data, the ship's navigation trajectory, and the meteorological data, navigation anomaly information is generated;

[0049] The second abnormal information is determined based on the speed abnormality information and the navigation abnormality information.

[0050] Optionally, determining the ship anomaly information based on the first anomaly information, the second anomaly information, and the third anomaly information includes:

[0051] Determine whether there is a related abnormal type among the first abnormal information, the second abnormal information, and the third abnormal information;

[0052] If the associated anomaly types exist, then determine whether there are any conflicts in the anomaly information corresponding to each of the associated anomaly types;

[0053] The conflicting abnormal information is identified as the abnormal information to be verified;

[0054] The corrected monitoring data corresponding to the anomaly information to be verified is determined as the monitoring data to be referenced.

[0055] Obtain historical anomaly information corresponding to the monitoring data to be referenced, the historical anomaly information including historical monitoring data to be referenced and anomaly situations;

[0056] The machine learning algorithm is trained based on the historical anomaly information to obtain an anomaly detection model;

[0057] The anomaly information to be verified is corrected based on the anomaly detection model and the reference monitoring data;

[0058] The ship's abnormal information is determined based on the corrected abnormal information to be verified, the first abnormal information, the second abnormal information, and the third abnormal information.

[0059] By adopting the above technical solution, three types of abnormal information are first identified through single ship monitoring data, and then the abnormal information is corrected by the correlation between the abnormal types and the abnormal detection model, thereby improving the reliability of ship abnormal information.

[0060] Optionally, determining the rescue strategy based on the ship anomaly information and the rescue force distribution information includes:

[0061] Based on the ship's abnormal information, the required rescue resources are determined, including rescue equipment and rescue personnel.

[0062] Based on the information on the distribution of rescue forces, candidate resource locations are determined, wherein the candidate resource locations include all the locations of the required rescue resources.

[0063] Obtain the rescue information for each of the candidate resource locations, including the location to be rescued, the rescue priority, and the estimated rescue duration;

[0064] Based on the aforementioned abnormal ship information, the estimated rescue duration and rescue priority of the current ship are determined;

[0065] Based on the rescue priority, a rescue route is determined for each of the candidate resource locations;

[0066] Obtain meteorological information;

[0067] Determine the navigation speed based on the meteorological information;

[0068] The estimated rescue time for the current vessel is determined based on the rescue route, the estimated rescue duration, the route location, and the sailing speed. The route location includes the candidate resource location, the location to be rescued, and the current vessel's position.

[0069] The candidate resource location that is earliest at the expected rescue time is determined as the target rescue location;

[0070] The rescue route corresponding to the target rescue location is determined as the target rescue route;

[0071] The rescue strategy is determined based on the target rescue location and the target rescue route.

[0072] By adopting the above technical solutions and determining the rescue route based on rescue priority, accidents with higher rescue priority can be rescued first. By determining the target rescue location based on the earliest expected rescue time, accidents can be resolved more quickly, reducing the losses caused by ship accidents.

[0073] Optionally, the analysis of the ship anomaly information and the rescue force distribution information to determine maintenance improvement strategies includes:

[0074] Obtain historical information on ship anomalies and historical maintenance cycles;

[0075] Obtain the service life of various ship components;

[0076] The frequency of anomalies in each component is determined based on the historical ship anomaly information and the ship anomaly information.

[0077] The periodic correction coefficient is determined based on the abnormal frequency and the usage duration.

[0078] The current maintenance cycle is determined based on the cycle correction coefficient and the historical maintenance cycle.

[0079] Obtain the duration of this rescue response and the historical rescue response duration for the current marine area where the vessel is located;

[0080] The average response time is determined based on the historical rescue response time and the current rescue response time;

[0081] A rescue force maintenance strategy is determined based on the average response time and the rescue force distribution information.

[0082] Based on the current maintenance cycle and the rescue force maintenance strategy, a maintenance improvement strategy is determined.

[0083] By adopting the above technical solutions, the historical maintenance cycle can be corrected by analyzing the abnormal frequency and usage duration of each component, thus reducing the probability of accidents when maintenance is carried out according to the current maintenance cycle. By adjusting the distribution of rescue forces through the rescue response time, rescue can be made more timely, reducing the losses caused by ship accidents.

[0084] Secondly, this application provides a closed-loop emergency management device for ship accidents, which adopts the following technical solution:

[0085] A closed-loop emergency management device for ship accidents, comprising:

[0086] The data acquisition module is used to acquire ship monitoring data and information on the distribution of rescue forces;

[0087] An anomaly determination module is used to analyze the ship monitoring data and determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue.

[0088] The rescue determination module is used to determine a rescue strategy based on the ship anomaly information and the rescue force distribution information if the ship anomaly information includes the anomaly to be rescued. The rescue strategy includes a rescue route, and the rescue route is determined based on the rescue priority.

[0089] The maintenance and improvement module is used to analyze the abnormal information of the vessel and the distribution information of the rescue forces to determine maintenance and improvement strategies.

[0090] The strategy determination module is used to determine an accident management strategy based on the rescue strategy and the maintenance improvement strategy.

[0091] By adopting the above technical solutions and analyzing ship monitoring data, abnormal situations can be detected in a timely manner. Automatic and rapid generation of rescue strategies improves rescue efficiency, thereby reducing losses caused by delayed rescues during ship accidents. Rescue routes are determined according to rescue priorities, ensuring that higher-priority incidents receive more timely assistance. Post-incident analysis of ship anomaly information and rescue force distribution information allows for the determination of maintenance and improvement strategies, enabling timely learning of lessons, reducing the probability of subsequent anomalies, and further improving rescue efficiency, thus further reducing losses caused by ship accidents.

[0092] Thirdly, this application provides an electronic device that adopts the following technical solution:

[0093] An electronic device includes a processor coupled to a memory;

[0094] The memory stores a computer program that can be loaded by a processor and executed as described in any of the first aspects of the ship accident emergency closed-loop management method.

[0095] In a fourth aspect, the present application provides a computer-readable storage medium, which adopts the following technical solution:

[0096] A computer-readable storage medium storing a computer program capable of being loaded by a processor and executing the ship accident emergency closed-loop management method as described in any of the first aspects. Attached Figure Description

[0097] Figure 1 This is a flowchart illustrating a closed-loop emergency management method for ship accidents provided in an embodiment of this application.

[0098] Figure 2This is a structural block diagram of a ship accident emergency closed-loop management device provided in an embodiment of this application.

[0099] Figure 3 This is a structural block diagram of the electronic device provided in the embodiments of this application. Detailed Implementation

[0100] The present application is further described in detail below with reference to the accompanying drawings.

[0101] This application provides a closed-loop emergency management method for ship accidents. This method can be executed by an electronic device, which can be a server or a terminal device. The server can be a standalone physical server, a server cluster or distributed system composed of multiple physical servers, or a cloud server providing cloud computing services. The terminal device can be a smartphone, tablet, desktop computer, etc., but is not limited to these.

[0102] To make the objectives, technical solutions, and advantages of the embodiments of this application clearer, 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, 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.

[0103] Furthermore, the term "and / or" in this article is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can represent: A existing alone, A and B existing simultaneously, or B existing alone. Additionally, the character " / " in this article, unless otherwise specified, generally indicates that the preceding and following related objects have an "or" relationship.

[0104] like Figure 1 As shown, a closed-loop emergency management method for ship accidents is described in the following steps (S101-S105):

[0105] Step S101: Obtain ship monitoring data and information on the distribution of rescue forces.

[0106] Ship monitoring data refers to the data that needs to be monitored during a ship's voyage, including but not limited to navigation data (e.g., ship position, course, speed, draft, etc.), crew status data (e.g., crew body temperature, heart rate, pressure level, etc.), and equipment monitoring data (e.g., engine speed, generator current, voltage, fuel pressure, etc.). Various ship monitoring data are obtained from various sensors installed on the ship and from the crew, and information on the distribution of rescue forces is obtained from rescue management departments.

[0107] Specifically, acquiring ship monitoring data includes: acquiring ship information and crew information; determining a first monitoring strategy based on the ship information and crew information; analyzing the ship information and crew information to determine whether the ship is a key monitoring ship and whether there are key monitoring crew members; determining a second monitoring strategy based on the key monitoring ship and key monitoring crew members; determining the data acquisition frequency based on the first monitoring strategy and the second monitoring strategy; and acquiring ship monitoring data based on the data acquisition frequency.

[0108] In this embodiment, ship and crew information is obtained from a database or from staff. Ship information includes basic ship information (e.g., ship name, ship model, ship width, etc.) and static navigation information (e.g., navigation area, ship trajectory, etc.). Crew information includes basic crew information (name, gender, etc.) and crew resume information (position, rank, etc.). The first monitoring strategy is to monitor the ship and crew according to a conventional monitoring strategy (pre-set, not specifically limited here). The preset rules are rules for determining whether a ship is a key monitored ship and whether a crew member is a key monitored crew member. For example, if a crew member's performance evaluation score is lower than a preset score (pre-set, not specifically limited here), then the crew member is a key monitored crew member, according to the preset rules. The system analyzes vessel and crew information to determine whether a vessel is a key monitoring vessel and whether there are key monitoring crew members. The second monitoring strategy is to monitor key monitoring vessels and crew members according to a high-frequency monitoring strategy (pre-set, not specifically limited here) if such vessels or crew members exist. Other crew members or vessels (if the vessel is not a key monitoring vessel) are monitored according to a regular monitoring strategy (pre-set, not specifically limited here). Both the regular monitoring strategy and the high-frequency monitoring strategy include data acquisition frequency, and the corresponding data acquisition frequencies are different. Based on the first and second monitoring strategies, vessel monitoring data is acquired for vessels and different crew members according to the corresponding data acquisition frequencies.

[0109] Step S102: Analyze the ship monitoring data to determine abnormal ship information.

[0110] The abnormal information of the vessel includes self-adjusting abnormalities and rescue-required abnormalities. Self-adjusting abnormalities are those that the crew can resolve on their own and do not require rescue; rescue-required abnormalities are those that the crew cannot resolve on their own and require rescue.

[0111] Specifically, analyzing ship monitoring data to identify ship anomalies includes: integrating and analyzing ship monitoring data to obtain corrected monitoring data; analyzing the corrected monitoring data to identify ship anomalies; integrating and analyzing ship monitoring data to obtain corrected monitoring data includes: classifying ship monitoring data to obtain multiple monitoring data combinations, each monitoring data combination corresponding to a data type; if there are multiple ship monitoring data in a monitoring data combination, calculating the error value between every two ship monitoring data in the monitoring data combination; if all error values ​​are less than the first error value, determining a weight value based on the accuracy of each ship monitoring data; determining corrected monitoring data based on the weight value and the ship monitoring data; if there are error values ​​greater than or equal to... If the error value is equal to the first error value and all error values ​​are less than the second error value, then corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and ship monitoring data. If there is an error value greater than or equal to the second error value, then the error value greater than or equal to the second error value is determined as a serious error value. The first number of serious error values ​​is counted. The second number of all error values ​​in the monitoring data combination is counted. The deviation ratio is determined based on the first number and the second number. If the deviation ratio is greater than the preset deviation ratio, then corrected monitoring data is determined based on the ship's static navigation information and historical monitoring data. If the deviation ratio is less than or equal to the preset deviation ratio, then corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and ship monitoring data.

[0112] In this embodiment, before determining abnormal ship information through ship monitoring data, it is necessary to improve the reliability of ship monitoring data. That is, by integrating and analyzing the ship monitoring data, corrected monitoring data is obtained. Specifically, this includes classifying the ship monitoring data according to data type to obtain multiple monitoring data combinations. Each monitoring data combination corresponds to a data type, such as ship position. The ship position obtained through GPS and the ship position obtained through the AIS system are grouped into one monitoring data combination.

[0113] If a monitoring data set contains multiple ship monitoring data, the error value between every two ship monitoring data in the set is calculated. If all error values ​​in the set are less than the first error value, the accuracy rate of each type of ship monitoring data is obtained from the database or from staff. The weight value of a ship monitoring data is calculated as the accuracy rate of that data / (the sum of the accuracy rates of all ship monitoring data of the same data type corresponding to that data). The corrected monitoring data for a data type is the sum of all (ship monitoring data × weight value) corresponding to that data type.

[0114] If a monitoring data set contains an error value greater than or equal to the first error value, and all error values ​​are less than the second error value, then historical monitoring data is retrieved from the database. The historical monitoring data consists of all ship monitoring data prior to the current time of the current voyage, and the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and ship monitoring data.

[0115] The specific steps for determining corrected monitoring data based on ship static navigation information, historical monitoring data, and ship monitoring data are as follows: A machine learning algorithm is trained using ship static navigation information and historical monitoring data to obtain a monitoring data prediction model. This model is then used to predict the ship monitoring data for the current moment. The deviation values ​​between each ship monitoring data point in the monitoring data set and the predicted ship monitoring data are calculated. Ship monitoring data with deviation values ​​less than a preset deviation value (pre-set, not specifically limited here) are identified as usable monitoring data. The weight values ​​of the usable monitoring data are calculated based on their accuracy. The method for determining the weight values ​​is the same as above and will not be repeated here. Corrected monitoring data for a data type is the sum of all (usable monitoring data × weight values) corresponding to that data type. The machine learning algorithm can be a convolutional neural network, a random forest algorithm, or a support vector machine; no specific limitation is made here.

[0116] If a monitoring data set contains an error value greater than or equal to the second error value, then that error value is identified as a severe error value. The first number of severe error values ​​in the monitoring data set is counted, and the second number of all error values ​​(including severe error values) in the monitoring data set is counted. The deviation ratio is calculated as the first number divided by the second number. If the deviation ratio is greater than a preset deviation ratio (preset, not specifically defined here), it indicates that most monitoring data has significant errors and poor usability. The predicted ship monitoring data for the current moment is then predicted based on the monitoring data prediction model, and this predicted ship monitoring data is identified as corrected monitoring data. If the deviation ratio is less than or equal to the preset deviation ratio, corrected monitoring data is determined based on ship static navigation information, historical monitoring data, and ship monitoring data. The specific steps for "determining corrected monitoring data based on ship static navigation information, historical monitoring data, and ship monitoring data" are the same as above and will not be repeated here.

[0117] It is worth noting that the first error value is smaller than the second error value, and both are preset, so no specific limitation is made here.

[0118] If a monitoring data set contains only one ship monitoring data point, then that ship monitoring data point is identified as the corrected monitoring data point.

[0119] After obtaining the corrected monitoring data, the corrected monitoring data is analyzed to determine the abnormal information of the vessel. The data types of the corrected monitoring data and the vessel monitoring data are consistent, including but not limited to vessel position data and video data.

[0120] Specifically, the process involves analyzing corrected monitoring data to determine abnormal ship information, including: comparing corrected monitoring data with standard data thresholds to determine first abnormal information; analyzing ship position data to determine second abnormal information; identifying video data to determine third abnormal information; determining ship abnormal information based on the first, second, and third abnormal information; analyzing ship position data to determine second abnormal information, including: determining ship speed based on ship position data; determining abnormal speed and abnormal type based on ship speed and abnormal judgment rules; generating speed abnormal information based on the abnormal speed corresponding to the same abnormal type and the continuous abnormal duration if the duration exceeds a preset duration; acquiring the ship's trajectory for the current voyage; acquiring meteorological data based on ship position data and ship trajectory; generating navigation abnormal information based on ship position data, ship trajectory, and meteorological data; and determining second abnormal information based on speed abnormal information and navigation abnormal information.

[0121] In this embodiment, standard data thresholds (which can be a data range) corresponding to each data type are obtained from a database or from staff. The corrected monitoring data is compared with the corresponding standard data thresholds. Corrected monitoring data that does not meet the standard data thresholds are identified as abnormal data. If abnormal data exists, the abnormal data and the corresponding abnormal type are jointly identified as the first abnormal information. The ship position data is analyzed to determine the second abnormal information. The video data is identified using a pre-trained image recognition model to determine the third abnormal information. The ship abnormal information is determined based on the first, second, and third abnormal information. The image recognition model is, for example, a convolutional neural network model.

[0122] The specific process of analyzing ship position data to determine the second anomaly information includes: calculating the ship's speed based on the ship's position data at every two adjacent moments and the interval duration; retrieving anomaly judgment rules from the database, which are rules for judging whether there are anomalies in the speed; judging whether there are abnormal speeds and the corresponding anomaly types based on the anomaly judgment rules, such as slow speed, drifting, and speeding; calculating the continuous anomaly duration corresponding to each anomaly type; if the continuous anomaly duration corresponding to the same anomaly type exceeds a preset duration, then the anomaly type and the continuous anomaly duration are used together to generate speed anomaly information; searching for the ship's current voyage trajectory from the ship's static navigation information; obtaining meteorological data on the trajectory following the current ship's position data from the meteorological department; if the current ship's position data deviates from the ship's trajectory, or if the meteorological data on the trajectory following the current ship's position data contains preset weather (pre-set, such as strong winds), then navigation anomaly information is generated, which includes navigation trajectory anomaly information and / or meteorological anomaly information; and combining the speed anomaly information and the navigation anomaly information as the second anomaly information.

[0123] Further, determining ship anomaly information based on the first, second, and third anomaly information includes: determining whether there are related anomaly types among the first, second, and third anomaly information; if related anomaly types exist, determining whether there are conflicts in the anomaly information corresponding to each related anomaly type; identifying conflicting anomaly information as anomaly information to be verified; identifying the corrected monitoring data corresponding to the anomaly information to be verified as reference monitoring data; obtaining historical anomaly information corresponding to the reference monitoring data, including historical reference monitoring data and anomaly conditions; training a machine learning algorithm based on the historical anomaly information to obtain an anomaly detection model; correcting the anomaly information to be verified based on the anomaly detection model and the reference monitoring data; and determining ship anomaly information based on the corrected anomaly information to be verified, the first, second, and third anomaly information.

[0124] In this embodiment, since the first, second, and third anomalies are primarily determined through single ship monitoring data, their reliability is low. Therefore, it is necessary to combine multiple ship monitoring data to correct the aforementioned anomalies. Various related anomaly types and their relationships are retrieved from the database. A related anomaly type is one or more anomaly types that are related; for example, engine anomalies and speed anomalies are related anomalies. The system determines whether related anomaly types exist among the first, second, and third anomalies. If related anomaly types exist, it determines whether there are conflicts in the anomaly information corresponding to each related anomaly type based on the relationships between them. For example, if one anomaly... If one message indicates an engine speed that is too low and another message indicates a speed that is too high, then a conflict is identified. The conflicting anomalies are identified as anomalies to be verified, and the corrected monitoring data corresponding to the anomalies to be verified is identified as reference monitoring data. Historical anomalies corresponding to the reference monitoring data are retrieved from the database, and a machine learning algorithm is trained using the historical anomalies to obtain an anomaly detection model. The reference monitoring data is then input into the anomaly detection model to predict anomalies and obtain predicted anomalies. The predicted anomalies are identified as corrected anomalies to be verified. The corrected anomalies to be verified, along with the first, second, and third anomalies that do not conflict with each other, are collectively identified as ship anomalies.

[0125] Step S103: If the ship anomaly information includes anomalies requiring rescue, then determine the rescue strategy based on the ship anomaly information and the distribution information of rescue forces.

[0126] The rescue strategy includes rescue routes, which may include multiple anomalies to be rescued. The rescue routes are determined based on the rescue priority.

[0127] Based on preset rescue rules (pre-set and retrieved from the database), determine whether the anomaly type in the ship's anomaly information includes anomalies awaiting rescue. If it does not include anomalies awaiting rescue, i.e., all are self-adjusting anomalies, then send the ship's anomaly information to the corresponding crew member so that the crew member can handle the anomaly. If it includes anomalies awaiting rescue, then determine the rescue strategy based on the ship's anomaly information and the distribution information of rescue forces, and at the same time send the ship's anomaly information to the corresponding crew member.

[0128] Specifically, determining a rescue strategy based on ship anomaly information and rescue force distribution information includes: determining the required rescue resources based on ship anomaly information, including rescue equipment and rescue personnel; determining candidate resource locations based on rescue force distribution information, including locations of all required rescue resources; obtaining the rescue information for each candidate resource location, including the location to be rescued, rescue priority, and estimated rescue duration; determining the estimated rescue duration and rescue priority of the current ship based on ship anomaly information; determining the rescue route for each candidate resource location based on the rescue priority; obtaining meteorological information; determining the sailing speed based on the meteorological information; determining the estimated rescue time of the current ship based on the rescue route, estimated rescue duration, route locations, and sailing speed, including candidate resource locations, locations to be rescued, and the current ship's location; determining the candidate resource location with the earliest estimated rescue time as the target rescue location; determining the rescue route corresponding to the target rescue location as the target rescue route; and determining the rescue strategy based on the target rescue location and the target rescue route.

[0129] In this embodiment, different types of anomalies require different rescue resources. The database stores the correspondence between anomaly types and required rescue resources. Based on the anomaly type in the ship anomaly information, the required rescue resources are retrieved from the database. The locations in the rescue force distribution information where the required rescue resources can be met are determined as candidate resource locations. The waiting-to-rescue information for each candidate resource location is obtained from the rescue center or staff. The waiting-to-rescue information is the location information of other ships besides the current ship that are waiting for rescue forces at the candidate resource location to provide rescue. The database stores the correspondence between anomaly types and estimated rescue durations, as well as between anomaly types and rescue priorities. Based on the anomaly type in the ship anomaly information, the estimated rescue duration and rescue priority of the current ship are retrieved from the database.

[0130] All candidate resource locations (including the current vessel's location data) are sorted from highest to lowest rescue priority to obtain the rescue route for each candidate resource location. Meteorological information for the ocean area where the candidate resource location is located is obtained, and the sailing speed corresponding to the meteorological information is obtained from the database or from staff. The estimated rescue time for the current vessel is calculated as: current time + sailing time + estimated total rescue time. The sailing time is the time spent by the rescue force from the candidate rescue location along the rescue route until it reaches the current vessel's location data. This time can be calculated using the total sailing distance and sailing speed. The estimated total rescue time is the sum of the estimated rescue times for each candidate resource location before reaching the current vessel's location data along the sailing route. The candidate resource location with the earliest estimated rescue time is determined as the target rescue location, and the rescue route corresponding to the target rescue location is determined as the target rescue route. The rescue strategy is to select the rescue force at the target rescue location for rescue work, and the rescue force will carry out rescue work sequentially according to the target rescue route.

[0131] Step S104: Analyze the abnormal information of the vessel and the distribution information of rescue forces to determine maintenance and improvement strategies.

[0132] After an accident and the subsequent rescue efforts, it is necessary to analyze the accident and the rescue situation in order to learn lessons and summarize experiences.

[0133] Specifically, the analysis of vessel anomaly information and rescue force distribution information determines maintenance improvement strategies, including: obtaining historical vessel anomaly information and historical maintenance cycles; obtaining the usage time of various vessel components; determining the anomaly frequency of each component based on historical vessel anomaly information; determining the cycle correction coefficient based on the anomaly frequency and usage time; determining the current maintenance cycle based on the cycle correction coefficient and historical maintenance cycles; obtaining the duration of the current rescue response and the historical rescue response duration of the current marine area where the vessel is located; determining the average response time based on the historical rescue response duration and the current rescue response duration; determining the rescue force maintenance strategy based on the average response time and rescue force distribution information; and determining maintenance improvement strategies based on the current maintenance cycle and the rescue force maintenance strategy.

[0134] In this embodiment, historical ship anomaly information and historical maintenance cycles are obtained from the database; the usage time of various ship components is obtained from the database or from staff; the historical ship anomaly information and ship anomaly information are analyzed using data analysis tools (e.g., EXCEL) to obtain the anomaly frequency of each component; the database stores the correspondence between anomaly frequency, usage time and cycle correction coefficient; the cycle correction coefficient is retrieved from the database based on the anomaly frequency and usage time; the current maintenance cycle = cycle correction coefficient × historical maintenance cycle.

[0135] Obtain the response time of this rescue from the staff, as well as the historical response times of the current vessel in the ocean area within a preset time period (e.g., within one month). Calculate the average response time of all historical response times and the current rescue response time. If the average response time exceeds the preset response time (preset, not specifically limited here), the rescue force maintenance strategy is to increase the distribution of rescue forces in the ocean area where the vessel is currently located. If the average response time does not exceed the preset response time, the rescue force maintenance strategy is not to increase the distribution of rescue forces in the ocean area where the vessel is currently located, but to maintain the current distribution. The maintenance improvement strategy includes maintaining each component according to the current maintenance cycle and adjusting the distribution of rescue forces according to the rescue force maintenance strategy.

[0136] Step S105: Determine the incident management strategy based on the rescue strategy and maintenance improvement strategy.

[0137] The rescue strategy and the maintenance and improvement strategy are jointly defined as the accident management strategy.

[0138] Figure 2 This is a structural block diagram of a ship accident emergency closed-loop management device 200 provided in an embodiment of this application.

[0139] like Figure 2 As shown, the ship accident emergency closed-loop management device 200 mainly includes:

[0140] Data acquisition module 201 is used to acquire ship monitoring data and rescue force distribution information;

[0141] The anomaly determination module 202 is used to analyze ship monitoring data and determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue.

[0142] The rescue determination module 203 is used to determine a rescue strategy based on the ship anomaly information and the distribution information of rescue forces if the ship anomaly information includes anomalies to be rescued. The rescue strategy includes a rescue route, which is determined based on the rescue priority.

[0143] The maintenance and improvement module 204 is used to analyze ship anomaly information and rescue force distribution information to determine maintenance and improvement strategies;

[0144] The strategy determination module 205 is used to determine the incident management strategy based on the rescue strategy and the maintenance improvement strategy.

[0145] As an optional implementation of this embodiment, the data acquisition module 201 is further specifically used to acquire ship monitoring data, including: acquiring ship information and crew information; determining a first monitoring strategy based on the ship information and crew information; analyzing the ship information and crew information to determine whether the ship is a key monitoring ship and whether there are key monitoring crew members; determining a second monitoring strategy based on the key monitoring ship and key monitoring crew members; determining a data acquisition frequency based on the first monitoring strategy and the second monitoring strategy; and acquiring ship monitoring data based on the data acquisition frequency.

[0146] As an optional implementation of this embodiment, the anomaly determination module 202 is further specifically used to analyze ship monitoring data and determine ship anomaly information, including: integrating and analyzing ship monitoring data to obtain corrected monitoring data; analyzing the corrected monitoring data to determine ship anomaly information; integrating and analyzing ship monitoring data to obtain corrected monitoring data includes: classifying ship monitoring data to obtain multiple monitoring data combinations, each monitoring data combination corresponding to a data type; if there are multiple ship monitoring data in the monitoring data combination, calculating the error value between every two ship monitoring data in the monitoring data combination; if all error values ​​are less than a first error value, determining a weight value based on the accuracy of each ship monitoring data; determining the corrected monitoring data based on the weight value and the ship monitoring data. The monitoring data is analyzed as follows: If there is an error value greater than or equal to the first error value, and all error values ​​are less than the second error value, then corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and ship monitoring data; if there is an error value greater than or equal to the second error value, then the error value greater than or equal to the second error value is determined as a serious error value; the first number of serious error values ​​is counted; the second number of all error values ​​in the monitoring data combination is counted; the deviation ratio is determined based on the first number and the second number; if the deviation ratio is greater than the preset deviation ratio, then corrected monitoring data is determined based on the ship's static navigation information and historical monitoring data; if the deviation ratio is less than or equal to the preset deviation ratio, then corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and ship monitoring data.

[0147] As an optional implementation of this embodiment, the corrected monitoring data includes ship position data and video data. The anomaly determination module 202 is further specifically used to analyze the corrected monitoring data to determine ship anomaly information, including: comparing the corrected monitoring data with a standard data threshold to determine first anomaly information; analyzing the ship position data to determine second anomaly information; identifying the video data to determine third anomaly information; determining ship anomaly information based on the first, second, and third anomaly information; analyzing the ship position data to determine second anomaly information, including: determining the ship's speed based on the ship position data; determining the abnormal speed and anomaly type based on the ship's speed and anomaly judgment rules; if the continuous anomaly duration corresponding to the same anomaly type exceeds a preset duration, generating speed anomaly information based on the anomaly type and continuous anomaly duration; acquiring the ship's trajectory for the current voyage; acquiring meteorological data based on the ship position data and ship trajectory; generating navigation anomaly information based on the ship position data, ship trajectory, and meteorological data; and determining second anomaly information based on speed anomaly information and navigation anomaly information.

[0148] As an optional implementation of this embodiment, the anomaly determination module 202 is further specifically used to determine ship anomaly information based on the first anomaly information, the second anomaly information, and the third anomaly information, including: determining whether there are related anomaly types among the first anomaly information, the second anomaly information, and the third anomaly information; if there are related anomaly types, determining whether there are conflicts in the anomaly information corresponding to each related anomaly type; determining the conflicting anomaly information as anomaly information to be verified; determining the corrected monitoring data corresponding to the anomaly information to be verified as reference monitoring data; obtaining historical anomaly information corresponding to the reference monitoring data, the historical anomaly information including historical reference monitoring data and anomaly conditions; training a machine learning algorithm based on the historical anomaly information to obtain an anomaly detection model; correcting the anomaly information to be verified based on the anomaly detection model and the reference monitoring data; and determining the ship anomaly information based on the corrected anomaly information to be verified, the first anomaly information, the second anomaly information, and the third anomaly information.

[0149] As an optional implementation of this embodiment, the rescue determination module 203 is further specifically used to determine a rescue strategy based on ship anomaly information and rescue force distribution information, including: determining the required rescue resources based on ship anomaly information, the required rescue resources including rescue equipment and rescue personnel; determining candidate resource locations based on rescue force distribution information, the candidate resource locations including locations of all required rescue resources; acquiring the rescue information for each candidate resource location, the rescue information including the rescue location, rescue priority, and estimated rescue duration; determining the estimated rescue duration and rescue priority of the current ship based on ship anomaly information; determining the rescue route of the rescue resources at each candidate resource location based on the rescue priority; acquiring meteorological information; determining the sailing speed based on the meteorological information; determining the estimated rescue time of the current ship based on the rescue route, estimated rescue duration, route location, and sailing speed, the route location including candidate resource locations, the location to be rescued, and the current ship's location; determining the candidate resource location with the earliest estimated rescue time as the target rescue location; determining the rescue route corresponding to the target rescue location as the target rescue route; and determining a rescue strategy based on the target rescue location and the target rescue route.

[0150] As an optional implementation of this embodiment, the maintenance improvement module 204 is further specifically used to analyze ship anomaly information and rescue force distribution information to determine maintenance improvement strategies, including: acquiring historical ship anomaly information and historical maintenance cycles; acquiring the usage time of various ship components; determining the anomaly frequency of each component based on historical ship anomaly information and ship anomaly information; determining a cycle correction coefficient based on the anomaly frequency and usage time; determining the current maintenance cycle based on the cycle correction coefficient and historical maintenance cycles; acquiring the duration of the current rescue response and the historical rescue response duration of the current marine area where the ship is located; determining the average response duration based on the historical rescue response duration and the current rescue response duration; determining a rescue force maintenance strategy based on the average response duration and rescue force distribution information; and determining a maintenance improvement strategy based on the current maintenance cycle and the rescue force maintenance strategy.

[0151] In one example, the module in any of the above devices may be one or more integrated circuits configured to implement the above methods, such as one or more application-specific integrated circuits (ASICs), or one or more digital signal processors (DSPs), or one or more field-programmable gate arrays (FPGAs), or a combination of at least two of these integrated circuit forms.

[0152] For example, when modules in a device can be implemented via a processing element scheduler, the processing element can be a general-purpose processor, such as a central processing unit (CPU) or other processor capable of calling programs. Alternatively, these modules can be integrated together as a system-on-a-chip (SOC).

[0153] Those skilled in the art will clearly understand that, for the sake of convenience and brevity, the specific working process of the above-described device and module can be referred to the corresponding process in the foregoing method embodiments, and will not be repeated here.

[0154] Figure 3 This is a structural block diagram of an electronic device 300 provided in an embodiment of this application.

[0155] like Figure 3 As shown, the electronic device 300 includes a processor 301 and a memory 302, and may further include one or more of an information input / output (I / O) interface 303, a communication component 304, and a communication bus 305.

[0156] The processor 301 controls the overall operation of the electronic device 300 to complete all or part of the steps of the aforementioned ship accident emergency closed-loop management method. The memory 302 stores various types of data to support the operation of the electronic device 300. This data may include, for example, instructions for any application or method operating on the electronic device 300, as well as application-related data. The memory 302 can be implemented by any type of volatile or non-volatile storage device or a combination thereof, such as one or more of 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.

[0157] I / O interface 303 provides an interface between processor 301 and other interface modules, such as keyboards, mice, and buttons. These buttons can be virtual or physical. Communication component 304 is used for wired or wireless communication between electronic device 300 and other devices. Wireless communication includes Wi-Fi, Bluetooth, Near Field Communication (NFC), 2G, 3G, or 4G, or a combination thereof. Therefore, the corresponding communication component 304 may include a Wi-Fi component, a Bluetooth component, and an NFC component.

[0158] The electronic device 300 may be implemented by 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 execute the ship accident emergency closed-loop management method given in the above embodiments.

[0159] The communication bus 305 may include a path for transmitting information between the aforementioned components. The communication bus 305 may be a PCI (Peripheral Component Interconnect) bus or an EISA (Extended Industry Standard Architecture) bus, etc. The communication bus 305 may be divided into an address bus, a data bus, a control bus, etc.

[0160] Electronic device 300 may include, but is not limited to, mobile terminals such as mobile phones, laptops, digital radio receivers, PDAs (personal digital assistants), PADs (tablet computers), PMPs (portable multimedia players), and in-vehicle terminals (such as in-vehicle navigation terminals), as well as fixed terminals such as digital TVs and desktop computers, and may also be servers.

[0161] This application also provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the steps of the above-described closed-loop management method for emergency response to ship accidents.

[0162] The computer-readable storage medium may include various media capable of storing program code, such as USB flash drives, portable hard drives, read-only memory (ROM), random access memory (RAM), magnetic disks, or optical disks.

[0163] The terms “comprising,” “including,” or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, method, article, or apparatus.

[0164] The above description is merely a preferred embodiment of this application and an explanation of the technical principles employed. Those skilled in the art should understand that the scope of this application is not limited to technical solutions formed by specific combinations of the above-described technical features, but should also cover other technical solutions formed by arbitrary combinations of the above-described technical features or their equivalents without departing from the foregoing application concept. For example, technical solutions formed by substituting the above features with (but not limited to) technical features with similar functions claimed in this application.

Claims

1. A closed-loop emergency management method for ship accidents, characterized in that, include: Obtain ship monitoring data and information on the distribution of rescue forces; The ship monitoring data is analyzed to determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue. The analysis of the ship monitoring data to determine abnormal ship information includes: The ship monitoring data is integrated and analyzed to obtain corrected monitoring data; The corrected monitoring data is analyzed to determine the abnormal information of the ship; The process of integrating and analyzing the ship monitoring data to obtain corrected monitoring data includes: The ship monitoring data is classified to obtain multiple monitoring data combinations, and each monitoring data combination corresponds to a data type. If there are multiple ship monitoring data in the monitoring data combination, then calculate the error value between every two ship monitoring data in the monitoring data combination; If all the error values ​​are less than the first error value, then the weight value is determined based on the accuracy of each of the ship monitoring data. The corrected monitoring data is determined based on the weight values ​​and the ship monitoring data; If there is an error value greater than or equal to the first error value, and all of the error values ​​are less than the second error value, then the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data. If there is an error value that is greater than or equal to the second error value, then the error value that is greater than or equal to the second error value is determined to be a serious error value; Count the first number of the severe error values; Count the second number of all error values ​​in the aforementioned monitoring data combination; The deviation ratio is determined based on the first quantity and the second quantity; If the deviation ratio is greater than the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information and the historical monitoring data. If the deviation ratio is less than or equal to the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data. The determination of corrected monitoring data based on ship static navigation information, historical monitoring data, and ship monitoring data includes: A monitoring data prediction model is obtained by training a machine learning algorithm using static navigation information of ships and historical monitoring data. Predict the ship monitoring data for the current moment based on the monitoring data prediction model; Calculate the deviation between all ship monitoring data and the corresponding predicted ship monitoring data in the monitoring data combination; Ship monitoring data with deviation values ​​less than the preset deviation value are identified as usable monitoring data; Calculate the weight value of the available monitoring data based on the accuracy of the available monitoring data; The corrected monitoring data is determined based on available monitoring data and weight values; If the ship anomaly information includes the anomaly to be rescued, then a rescue strategy is determined based on the ship anomaly information and the rescue force distribution information. The rescue strategy includes a rescue route, which is determined based on the rescue priority. The abnormal ship information and the distribution information of the rescue forces are analyzed to determine maintenance and improvement strategies; An accident management strategy is determined based on the rescue strategy and the maintenance improvement strategy.

2. The method according to claim 1, characterized in that, The acquisition of ship monitoring data includes: Obtain vessel and crew information; A first monitoring strategy is determined based on the ship information and the crew information; The vessel information and crew information are analyzed to determine whether the vessel is a key monitoring vessel and whether there are key monitoring crew members. A second monitoring strategy is determined based on the key monitored vessels and the key monitored crew members; The data acquisition frequency is determined based on the first monitoring strategy and the second monitoring strategy; The ship monitoring data is obtained based on the data acquisition frequency.

3. The method according to claim 1, characterized in that, The corrected monitoring data includes vessel position data and video data. The analysis of the corrected monitoring data to determine abnormal vessel information includes: The corrected monitoring data is compared with the standard data threshold to determine the first abnormal information; The ship's position data is analyzed to determine the second anomaly. The video data is identified to determine the third abnormal information; The ship's abnormal information is determined based on the first abnormal information, the second abnormal information, and the third abnormal information; The analysis of the ship position data to determine the second anomaly includes: The ship's speed is determined based on the ship's position data; The abnormal speed and abnormal type are determined based on the ship's sailing speed and the anomaly judgment rules. If the duration of consecutive abnormal speeds corresponding to the same type of abnormality exceeds a preset duration, then speed abnormality information is generated based on the type of abnormality and the duration of consecutive abnormality. Obtain the ship's navigation trajectory for the current voyage; Meteorological data is obtained based on the ship's position data and its navigation trajectory. Based on the ship's position data, the ship's navigation trajectory, and the meteorological data, navigation anomaly information is generated; The second abnormal information is determined based on the speed abnormality information and the navigation abnormality information.

4. The method according to claim 3, characterized in that, The process of determining ship anomaly information based on the first anomaly information, the second anomaly information, and the third anomaly information includes: Determine whether there is a related abnormal type among the first abnormal information, the second abnormal information, and the third abnormal information; If the associated anomaly types exist, then determine whether there are any conflicts in the anomaly information corresponding to each of the associated anomaly types; The conflicting abnormal information is identified as the abnormal information to be verified; The corrected monitoring data corresponding to the anomaly information to be verified is determined as the monitoring data to be referenced. Obtain historical anomaly information corresponding to the monitoring data to be referenced, the historical anomaly information including historical monitoring data to be referenced and anomaly situations; The machine learning algorithm is trained based on the historical anomaly information to obtain an anomaly detection model; The anomaly information to be verified is corrected based on the anomaly detection model and the reference monitoring data; The ship's abnormal information is determined based on the corrected abnormal information to be verified, the first abnormal information, the second abnormal information, and the third abnormal information.

5. The method according to claim 1, characterized in that, The process of determining a rescue strategy based on the ship anomaly information and the rescue force distribution information includes: Based on the ship's abnormal information, the required rescue resources are determined, including rescue equipment and rescue personnel. Based on the information on the distribution of rescue forces, candidate resource locations are determined, wherein the candidate resource locations include all the locations of the required rescue resources. Obtain the rescue information for each of the candidate resource locations, including the location to be rescued, the rescue priority, and the estimated rescue duration; Based on the aforementioned abnormal ship information, the estimated rescue duration and rescue priority of the current ship are determined; Based on the rescue priority, a rescue route is determined for each of the candidate resource locations; Obtain meteorological information; Determine the navigation speed based on the meteorological information; The estimated rescue time for the current vessel is determined based on the rescue route, the estimated rescue duration, the route location, and the sailing speed. The route location includes the candidate resource location, the location to be rescued, and the current vessel's position. The candidate resource location that is earliest at the expected rescue time is determined as the target rescue location; The rescue route corresponding to the target rescue location is determined as the target rescue route; The rescue strategy is determined based on the target rescue location and the target rescue route.

6. The method according to claim 1, characterized in that, The analysis of the ship anomaly information and the distribution information of the rescue forces to determine maintenance and improvement strategies includes: Obtain historical information on ship anomalies and historical maintenance cycles; Obtain the service life of various ship components; The frequency of anomalies in each component is determined based on the historical ship anomaly information and the ship anomaly information. The periodic correction coefficient is determined based on the abnormal frequency and the usage duration. The current maintenance cycle is determined based on the cycle correction coefficient and the historical maintenance cycle. Obtain the duration of this rescue response and the historical rescue response duration for the current marine area where the vessel is located; The average response time is determined based on the historical rescue response time and the current rescue response time; A rescue force maintenance strategy is determined based on the average response time and the rescue force distribution information. The maintenance improvement strategy is determined based on the current maintenance cycle and the rescue force maintenance strategy.

7. A closed-loop emergency management device for ship accidents, characterized in that, include: The data acquisition module is used to acquire ship monitoring data and information on the distribution of rescue forces; An anomaly determination module is used to analyze the ship monitoring data and determine ship anomaly information, including self-adjustment anomalies and anomalies requiring rescue. The analysis of the ship monitoring data to determine abnormal ship information includes: The ship monitoring data is integrated and analyzed to obtain corrected monitoring data; The corrected monitoring data is analyzed to determine the abnormal information of the ship; The process of integrating and analyzing the ship monitoring data to obtain corrected monitoring data includes: The ship monitoring data is classified to obtain multiple monitoring data combinations, and each monitoring data combination corresponds to a data type. If there are multiple ship monitoring data in the monitoring data combination, then calculate the error value between every two ship monitoring data in the monitoring data combination; If all the error values ​​are less than the first error value, then the weight value is determined based on the accuracy of each of the ship monitoring data. The corrected monitoring data is determined based on the weight values ​​and the ship monitoring data; If there is an error value greater than or equal to the first error value, and all of the error values ​​are less than the second error value, then the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data. If there is an error value that is greater than or equal to the second error value, then the error value that is greater than or equal to the second error value is determined to be a serious error value; Count the first number of the severe error values; Count the second number of all error values ​​in the aforementioned monitoring data combination; The deviation ratio is determined based on the first quantity and the second quantity; If the deviation ratio is greater than the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information and the historical monitoring data. If the deviation ratio is less than or equal to the preset deviation ratio, the corrected monitoring data is determined based on the ship's static navigation information, historical monitoring data, and the ship's monitoring data. The determination of corrected monitoring data based on ship static navigation information, historical monitoring data, and ship monitoring data includes: A monitoring data prediction model is obtained by training a machine learning algorithm using static navigation information of ships and historical monitoring data. Predict the ship monitoring data for the current moment based on the monitoring data prediction model; Calculate the deviation between all ship monitoring data and the corresponding predicted ship monitoring data in the monitoring data combination; Ship monitoring data with deviation values ​​less than the preset deviation value are identified as usable monitoring data; Calculate the weight value of the available monitoring data based on the accuracy of the available monitoring data; The corrected monitoring data is determined based on available monitoring data and weight values; The rescue determination module is used to determine a rescue strategy based on the ship anomaly information and the rescue force distribution information if the ship anomaly information includes the anomaly to be rescued. The rescue strategy includes a rescue route, and the rescue route is determined based on the rescue priority. The maintenance and improvement module is used to analyze the abnormal information of the vessel and the distribution information of the rescue forces to determine maintenance and improvement strategies. The strategy determination module is used to determine an accident management strategy based on the rescue strategy and the maintenance improvement strategy.

8. An electronic device, characterized in that, Includes a processor, which is coupled to a memory; The processor is configured to execute a computer program stored in the memory, causing the electronic device to perform the method as described in any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, It includes a computer program or instructions that, when run on a computer, cause the computer to perform the method as described in any one of claims 1 to 6.

Images