A data fusion and integration method and system based on multi-source nautical data

Abstract

The present invention relates to the field of navigation risk prediction, and particularly to a data fusion and integration method and system based on multi-source navigation data, which constructs a correlation analysis model; obtains source data of different scenario types in real time; inputs the source data of different types into the correlation analysis model, and extracts the risk characteristics of the source data through the correlation analysis model; sets up a hierarchical clustering model, inputs each risk characteristic into the hierarchical clustering model respectively, and analyzes the correlation coefficient between each risk characteristic and historical navigation data through the hierarchical clustering model; determines the weight coefficient of the risk characteristic according to the correlation coefficient, which is used to reflect the importance level of the risk characteristic in navigation risk prediction; constructs a data framework for navigation risk data, and integrates the risk characteristics and their weight coefficients into the data framework. Formulate corresponding risk management strategies. Ship operators can more effectively process multi-source navigation data, improve the accuracy of navigation risk prediction, thereby ensuring navigation safety and optimizing navigation plans.

Description

Technical Field

[0001] This application relates to the technical field of navigation risk prediction, and particularly to a data fusion and integration method and system based on multi-source marine data. Background Art

[0002] Multi-source marine data refers to data collected from multiple different sources and types during navigation. These data can include meteorological data, ocean current data, ship performance data, navigation logs, satellite data, historical accident data, traffic data, etc. These data sources include manual records, automatic sensors, communication systems, satellite remote sensing, etc. The fusion and integration of multi-source marine data are the key to improving navigation safety and efficiency, as they provide comprehensive information about the navigation environment, ship status, and historical navigation behavior. By analyzing these data, useful risk features can be extracted for navigation risk prediction and management.

[0003] When predicting navigation risks in the prior art, usually a variety of data sources are collected by the system, including meteorological data, navigation logs, ship performance data, etc. These data are directly input into a risk identification system, and the system attempts to identify features directly related to navigation risks. This may only focus on features directly related to navigation risks, such as wind speed, wave height, etc., and may lack effective feature extraction methods, making it difficult to accurately predict navigation risks, resulting in insufficient or over-reactive preventive measures, and easily ignoring those features that are strongly related to navigation risks but not the direct cause. In navigation, there is not only risk prediction and risk avoidance. In cases where some risks cannot be avoided, various situations that require facing risks directly also need to be dealt with.

[0004] Therefore, there are defects in the prior art and improvements are needed. Summary of the Invention

[0005] In order to solve one or several problems in the prior art, the main object of this application is to provide a data fusion and integration method and system based on multi-source marine data.

[0006] To achieve the above-mentioned invention object, this application proposes a data fusion and integration method based on multi-source marine data, and the method includes:

[0007] Construct an association analysis model for extracting risk features of the data;

[0008] Obtain source data of different scenario types in real time;

[0009] Input source data of different types into the association analysis model, and extract risk features of the source data through the association analysis model;

[0010] Set up a hierarchical clustering model, input each risk feature into the hierarchical clustering model respectively, and analyze the correlation coefficient between each risk feature and historical navigation data through the hierarchical clustering model;

[0011] Determine the weight coefficient of the risk feature according to the correlation coefficient, which is used to reflect the importance level of the risk feature in navigation risk prediction;

[0012] Construct a data framework for navigation risk data, and integrate the risk features and their weight coefficients into the data framework.

[0013] The embodiment of the present application also provides a data fusion and integration system based on multi-source navigation data, including:

[0014] A construction module, used to construct an association analysis model for extracting risk features of data;

[0015] An acquisition module, used to acquire source data of different scenario types in real time;

[0016] An input module, used to input source data of different types into the association analysis model, and extract risk features of the source data through the association analysis model;

[0017] An analysis module, used to set up a hierarchical clustering model, input each risk feature into the hierarchical clustering model respectively, and analyze the correlation coefficient between each risk feature and historical navigation data through the hierarchical clustering model;

[0018] A determination module, used to determine the weight coefficient of the risk feature according to the correlation coefficient, which is used to reflect the importance level of the risk feature in navigation risk prediction;

[0019] An integration module, used to construct a data framework for navigation risk data, and integrate the risk features and their weight coefficients into the data framework.

[0020] The present application also provides a computer device, including a memory and a processor, where the memory stores a computer program, and when the processor executes the computer program, the steps of the method described in any one of the above are implemented.

[0021] The present application also provides a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the steps of the method described in any one of the above are implemented.

[0022] The data fusion and integration method and system based on multi-source marine data according to the embodiments of the present application can extract risk features from multiple data sources, including those with strong relevance to navigation risks, by constructing an association analysis model and a hierarchical clustering model. Determine the weight coefficient of each risk feature according to the correlation coefficient, which reflects its importance level in navigation risk prediction. The determination of the weight coefficient helps to improve the prediction performance and stability of the model, enabling decision-makers to formulate corresponding risk management strategies based on the importance of risk features. Establish a data framework for navigation risk data, integrating risk features and their weight coefficients. The data framework can be used as a decision support tool to help ship operators and maritime management agencies better understand navigation risks and formulate corresponding risk management strategies. Ship operators can process multi-source marine data more effectively, improve the accuracy of navigation risk prediction, and thus ensure navigation safety and optimize navigation plans. BRIEF DESCRIPTION OF THE DRAWINGS

[0023] Figure 1 is a schematic flowchart of a data fusion and integration method based on multi-source marine data according to an embodiment of the present application;

[0024] Figure 2 is a schematic flowchart of a data fusion and integration method based on multi-source marine data according to an embodiment of the present application;

[0025] Figure 3 is a schematic block diagram of the structure of a data fusion and integration system based on multi-source marine data according to an embodiment of the present application;

[0026] Figure 4 is a schematic block diagram of the structure of a computer device according to an embodiment of the present application.

[0027] The implementation, functional features, and advantages of the objectives of the present application will be further described with reference to the embodiments and the accompanying drawings. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0028] In order to make the objectives, technical solutions, and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0029] Refer to Figure 1 , in the embodiments of the present application, a data fusion and integration method based on multi-source marine data is provided, and the method includes:

[0030] S1. Construct an association analysis model for extracting risk features of data;

[0031] S2. Real-time obtain source data of different scenario types;

[0032] S3. Input source data of different types into the association analysis model, and extract the risk characteristics of the source data through the association analysis model;

[0033] S4. Set up a hierarchical clustering model, input each risk characteristic into the hierarchical clustering model respectively, and analyze the correlation coefficient between each risk characteristic and historical voyage data through the hierarchical clustering model;

[0034] S5. Determine the weight coefficient of the risk characteristic according to the correlation coefficient, which is used to reflect the importance level of the risk characteristic in voyage risk prediction;

[0035] S6. Construct a data framework for voyage risk data, and integrate the risk characteristics and their weight coefficients into the data framework.

[0036] As described in the above steps S1 - S2, the association analysis model finds the correlation between data by analyzing different types of source data, so as to extract risk characteristics. It can include statistical analysis, machine learning algorithms or other data mining techniques. Through association analysis, potential relationships between different data sources can be discovered, helping to identify key factors that may affect voyage risk. Obtaining source data of different scenario types in real time means that the system can continuously update the data to reflect real-time environmental changes. Real-time data can provide more accurate risk characteristics, helping to predict voyage risks in real time and take corresponding preventive measures.

[0037] As described in the above steps S3 - S6, the hierarchical clustering model inputs each risk characteristic into the model respectively, and determines the importance of the risk characteristic by analyzing the correlation coefficient between the risk characteristic and historical voyage data. The hierarchical clustering model can help determine which risk characteristics are the most important for voyage risk prediction, thus improving the accuracy and reliability of the prediction. According to the analysis results of the hierarchical clustering model, determine the weight coefficient of each risk characteristic, reflecting its importance level in voyage risk prediction. The weight coefficient can help decision-makers understand which risk characteristics require more attention and resources, so as to manage voyage risks more effectively. Construct a data framework for voyage risk data, and integrate the risk characteristics and their weight coefficients into a structured data model. The data framework can be used as a decision support tool to help ship operators and maritime management agencies better understand voyage risks and formulate corresponding risk management strategies.

[0038] As described above, by constructing an association analysis model and a hierarchical clustering model, risk features can be extracted from multiple data sources, including those with a strong correlation with navigation risks. The weight coefficient of each risk feature is determined according to the correlation coefficient, reflecting its importance level in navigation risk prediction. The determination of the weight coefficient helps to improve the prediction performance and stability of the model, enabling decision-makers to formulate corresponding risk management strategies based on the importance of risk features. A data framework for navigation risk data is established, integrating risk features and their weight coefficients. The data framework can serve as a decision support tool to help ship operators and maritime management agencies better understand navigation risks and formulate corresponding risk management strategies. Ship operators can process multi-source navigation data more effectively, improve the accuracy of navigation risk prediction, and thus ensure navigation safety and optimize navigation plans.

[0039] Referring to Figure 2 , in one embodiment, when each risk feature is respectively input into the hierarchical clustering model, and the correlation coefficient between each risk feature and historical navigation data is analyzed through the hierarchical clustering model, the method includes:

[0040] S41. Obtain the scenario classification corresponding to the risk feature, input the risk features of each scenario classification into the hierarchical clustering model, map the risk features in the historical navigation data through the hierarchical clustering model, and determine the target feature and auxiliary feature corresponding to the risk feature in the navigation risk data;

[0041] S42. Based on the target feature, calculate the association ratio between the target feature of each scenario classification and the historical navigation data, where the scenario classification includes meteorological features, ocean current features, and geographical features;

[0042] S43. Quantify the association ratio through the hierarchical clustering model to obtain the correlation coefficient between the risk feature and the historical navigation data.

[0043] As described in the above steps, according to the attributes of risk characteristics, they are classified into different scenarios, such as meteorological characteristics, ocean current characteristics, and geographical characteristics. Classification helps to group similar risk characteristics together, facilitating further analysis of their relationships with historical navigation data. Input the risk characteristics classified for each scenario into the hierarchical clustering model, and the model analyzes the correlation coefficients between each risk characteristic and the historical navigation data. The hierarchical clustering model can identify which risk characteristics have strong associations with the target characteristics and auxiliary characteristics in the navigation risk data, thereby helping to determine which risk characteristics are important. Based on the analysis results of the hierarchical clustering model, determine the target characteristics and auxiliary characteristics corresponding to the risk characteristics in the navigation risk data. Identifying the target characteristics and auxiliary characteristics helps to more accurately understand the relationship between risk characteristics and navigation risks, thereby improving the accuracy of prediction. Based on the target characteristics, calculate the association ratio between the target characteristics classified for each scenario and the historical navigation data. Calculating the association ratio helps to quantify the degree of association between risk characteristics and navigation risk data, providing a quantitative basis for decision-making. Quantify the association ratio through the hierarchical clustering model to obtain the correlation coefficient between risk characteristics and historical navigation data. Quantifying the correlation coefficient helps to more accurately reflect the relationship between risk characteristics and navigation risk data, providing a quantitative basis for decision-making.

[0044] In one embodiment, for determining the target characteristics and auxiliary characteristics corresponding to the risk characteristics in the navigation risk data, the method includes:

[0045] When the scenario is classified as meteorological characteristics, obtain the navigation performance parameters and navigation delay parameters of the navigation risk data, where the meteorological characteristics include wind speed, wind direction, and air pressure parameters;

[0046] Based on the navigation performance parameters, analyze the speed change parameters of the ship under meteorological characteristic conditions;

[0047] Based on the navigation delay parameters, analyze the number of navigation delays and the time of the ship under meteorological characteristic conditions;

[0048] Input the speed change parameters and the parameters of the meteorological characteristics into the hierarchical clustering model, and analyze the directly and indirectly influencing meteorological parameters through the hierarchical clustering model, and output the analysis results;

[0049] Input the number of navigation delays and the time, as well as the parameters of the meteorological characteristics, into the hierarchical clustering model, and analyze the directly and indirectly influencing meteorological parameters through the hierarchical clustering model;

[0050] Take the directly influencing meteorological parameters as the target characteristics, and take the indirectly influencing meteorological parameters as the auxiliary parameters.

[0051] As described above, navigation performance parameters and navigation delay parameters related to meteorological characteristics are obtained from navigation risk data. Meteorological characteristics are key factors affecting navigation safety. Obtaining these data helps to more accurately evaluate the impact of meteorological conditions on navigation risk. Based on the navigation performance parameters, the speed changes of the ship under specific meteorological characteristic conditions are analyzed. The speed change is an important indicator directly reflecting the impact of meteorological conditions on ship navigation. Analyzing the speed change helps to determine the direct correlation between meteorological characteristics and navigation risk. Based on the navigation delay parameters, the number of navigation delays and the time of the ship under specific meteorological characteristic conditions are analyzed. Navigation delay reflects the impact of meteorological conditions on navigation plans and ship operations. Analyzing the delay helps to determine the indirect correlation between meteorological characteristics and navigation risk. The speed change parameters and meteorological characteristic parameters are input into a hierarchical clustering model to analyze the meteorological parameters with direct and indirect impacts. The hierarchical clustering model can help identify which meteorological parameters have a direct impact on navigation risk and which have an indirect impact, thus more accurately evaluating the impact of meteorological conditions on navigation risk. The meteorological parameters with direct impacts are used as target features, and the meteorological parameters with indirect impacts are used as auxiliary features. Distinguishing target features and auxiliary features helps to more accurately evaluate the impact of meteorological conditions on navigation risk and provides more targeted information for risk prediction and management.

[0052] In a feasible embodiment, assume that a ship operator uses a method to determine the target features and auxiliary features corresponding to meteorological characteristics in navigation risk data. They have multiple data sources, including meteorological data, navigation logs, ship performance data, etc. These data are input into a risk prediction system in real time.

[0053] Assume the meteorological characteristics are: wind speed (m / s), wind direction (°), air pressure (hPa)

[0054] Navigation performance parameters: speed (m / s), course (°), engine status (normal / abnormal)

[0055] Navigation delay parameters: number of delays, delay time (in minutes). By collecting real-time meteorological data, including wind speed, wind direction, and air pressure. Collecting navigation logs, including ship speed, course, and engine status. Collecting ship performance data, including the number of navigation delays and delay time. Preprocessing the data, including cleaning, standardization, normalization, etc. Obtaining navigation performance parameters and navigation delay parameters related to meteorological characteristics from the navigation risk data. Based on the navigation performance parameters, analyzing the ship speed changes under specific meteorological characteristic conditions. It is found that when the wind speed exceeds a certain threshold, the ship speed drops significantly. Based on the navigation delay parameters, analyzing the number of navigation delays and the delay time of the ship under specific meteorological characteristic conditions. It is found that when the wind direction changes, the number of delays increases and the delay time extends. Inputting the ship speed change parameters and meteorological characteristic parameters into the hierarchical clustering model to analyze the meteorological parameters with direct and indirect impacts. Inputting the number of navigation delays and the delay time as well as the meteorological characteristic parameters into the hierarchical clustering model to analyze the meteorological parameters with direct and indirect impacts. The model analysis results show that the wind speed is the key factor directly affecting the ship speed change, while the wind direction change leads to navigation delays. Taking the meteorological parameters with direct impacts (such as wind speed) as the target features and the meteorological parameters with indirect impacts (such as wind direction) as the auxiliary features. According to the target features and auxiliary features, predicting the navigation risk and formulating corresponding risk management strategies. For example, when the wind speed exceeds the safety threshold, the ship should reduce speed and consider adjusting the course to avoid strong wind areas.

[0056] In one embodiment, for determining the target features and auxiliary features corresponding to the risk characteristics in the navigation risk data, the method further includes:

[0057] When the scenario is classified as a sea current feature, obtaining the navigation performance parameters and navigation delay parameters of the navigation risk data, where the sea current feature includes sea current speed, sea current direction, sea current density, and sea current change rate parameters;

[0058] Based on the navigation performance parameters, analyzing the ship speed change parameters of the ship under the sea current feature conditions;

[0059] Based on the navigation delay parameters, analyzing the number of navigation delays and the delay time of the ship under the sea current feature conditions;

[0060] According to the dynamic changes of the sea current feature, inputting the ship speed change parameters and the parameters of the sea current feature into the hierarchical clustering model, and analyzing the sea current parameters with direct and indirect impacts through the hierarchical clustering model;

[0061] According to the real-time impact of the sea current feature on navigation performance and delay, inputting the number of navigation delays and the delay time as well as the parameters of the sea current feature into the hierarchical clustering model, analyzing the sea current parameters with direct and indirect impacts through the hierarchical clustering model, and outputting the analysis results;

[0062] Take the directly affected ocean current parameters as the target features and the indirectly affected ocean current parameters as the auxiliary parameters.

[0063] As described above, obtain the navigation performance parameters and navigation delay parameters related to ocean current characteristics from the navigation risk data. Ocean current characteristics are important factors affecting navigation safety. Obtaining these data helps to more accurately evaluate the impact of ocean current conditions on navigation risk. Based on the navigation performance parameters, analyze the speed change of the ship under specific ocean current characteristic conditions. The speed change is an important indicator directly reflecting the impact of ocean current conditions on ship navigation. Analyzing the speed change helps to determine the direct correlation between ocean current characteristics and navigation risk. Based on the navigation delay parameters, analyze the number of navigation delays and the time of the ship under specific ocean current characteristic conditions. Navigation delay reflects the impact of ocean current conditions on the navigation plan and ship operation. Analyzing the delay helps to determine the indirect correlation between ocean current characteristics and navigation risk. Input the speed change parameters and ocean current characteristic parameters into the hierarchical clustering model to analyze the directly affected and indirectly affected ocean current parameters. The hierarchical clustering model can help identify which ocean current parameters have a direct impact on navigation risk and which have an indirect impact, thus more accurately evaluating the impact of ocean current conditions on navigation risk. Take the directly affected ocean current parameters as the target features and the indirectly affected ocean current parameters as the auxiliary features. Distinguishing the target features and auxiliary features helps to more accurately evaluate the impact of ocean current conditions on navigation risk and provides more targeted information for risk prediction and management.

[0064] In one embodiment, for determining the target features and auxiliary features corresponding to the risk features in the navigation risk data, the method further includes:

[0065] When the scenario is classified as a geographical feature, obtain the navigation performance parameters and navigation delay parameters of the navigation risk data, where the geographical features include geographical location, port distance, ocean depth, and seabed terrain parameters;

[0066] Based on the navigation performance parameters, analyze the speed change parameters of the ship under geographical feature conditions;

[0067] Based on the navigation delay parameters, analyze the number of navigation delays and the time of the ship under geographical feature conditions;

[0068] Input the speed change parameters and the parameters of the geographical features into the hierarchical clustering model, and analyze the directly affected and indirectly affected geographical parameters through the hierarchical clustering model;

[0069] Input the number of navigation delays and the time, as well as the parameters of the geographical features, into the hierarchical clustering model, analyze the directly affected and indirectly affected geographical parameters through the hierarchical clustering model, and output the analysis results;

[0070] Take the directly affected geographical parameters as the target features and the indirectly affected geographical parameters as the auxiliary parameters.

[0071] As described above, obtain the navigation performance parameters and navigation delay parameters related to geographical features from the navigation risk data. Geographical features are important factors affecting navigation safety. Obtaining these data helps to more accurately evaluate the impact of geographical conditions on navigation risk. Based on the navigation performance parameters, analyze the speed changes of the ship under specific geographical feature conditions. The speed change is an important indicator directly reflecting the impact of geographical conditions on ship navigation. Analyzing the speed change helps to determine the direct correlation between geographical features and navigation risk. Based on the navigation delay parameters, analyze the number of navigation delays and the time of the ship under specific geographical feature conditions. Navigation delay reflects the impact of geographical conditions on the navigation plan and ship operation. Analyzing the delay helps to determine the indirect correlation between geographical features and navigation risk. Input the speed change parameters and geographical feature parameters into the hierarchical clustering model to analyze the directly and indirectly affected geographical parameters. The hierarchical clustering model can help identify which geographical parameters have a direct impact on navigation risk and which have an indirect impact, so as to more accurately evaluate the impact of geographical conditions on navigation risk. Take the directly affected geographical parameters as the target features and the indirectly affected geographical parameters as the auxiliary features. Distinguishing the target features and auxiliary features helps to more accurately evaluate the impact of geographical conditions on navigation risk and provide more targeted information for risk prediction and management.

[0072] In one embodiment, the method further includes:

[0073] Obtain the historical target features and auxiliary features of the same scenario, and analyze whether there is a time sequence attribute between the historical target features and auxiliary features of the same scenario;

[0074] When there is a time sequence attribute between the historical target features and auxiliary features of the same scenario, extract the historical target features and auxiliary features;

[0075] Construct a probability analysis model, input the historical target features and auxiliary features into the prediction model, analyze the probability that the auxiliary features trigger the target features through the prediction model, and output the probability analysis result;

[0076] When the probability analysis result shows that the probability that the auxiliary features trigger the target features is greater than the preset probability threshold, then mark the auxiliary features as warning features.

[0077] As described above, data on historical target features and auxiliary features of the same scenario are collected. By analyzing the historical data, patterns and trends related to navigation risks can be identified. Analyze whether there is a temporal precedence relationship between the historical target features and the auxiliary features. Determining the temporal precedence relationship helps to understand the causal relationship between risk features and provides a basis for prediction. When it is found that the historical target features and the auxiliary features have a temporal precedence attribute, these features are extracted. Extracting these features helps to further analyze their relationship with navigation risks. A probability analysis model is constructed, and the historical target features and the auxiliary features are input into the model. The probability analysis model can quantify the probability of the auxiliary features triggering the target features and provide a quantitative risk assessment. When the probability analysis result indicates that the probability of the auxiliary features triggering the target features reaches a preset probability threshold, the auxiliary feature is marked as a warning feature. Marking the warning feature helps to timely detect potential risks, provide warning information for decision-making, and facilitate the adoption of preventive measures.

[0078] In one embodiment, the navigation risk prediction includes navigation accident prediction, ship damage prediction, navigation delay prediction, and personnel risk prediction. Analyze historical navigation accident data, identify accident patterns and risk factors, and establish a prediction model. Predicting navigation accidents helps to take preventive measures in advance and reduce the risk of accidents. Analyze ship maintenance records and performance data, identify potential factors that may cause damage, and establish a prediction model. Predicting ship damage helps to timely detect potential problems, take repair measures, and avoid major damage. Analyze weather forecasts, navigation logs, and traffic data, predict possible navigation delays, and establish a prediction model. Predicting navigation delays helps to adjust the navigation plan, reduce unnecessary delays and costs. Analyze crew work records, health conditions, and mental states, identify factors that may cause personnel risks, and establish a prediction model. Predicting personnel risks helps to formulate corresponding safety management measures to ensure the safety and health of the crew.

[0079] In one embodiment, after the step of determining the weight coefficient of the risk feature according to the correlation coefficient to reflect the importance level of the risk feature in the navigation risk prediction, the method further includes:

[0080] Based on the importance level of the risk feature in the navigation risk prediction, analyze the risk type of the risk feature, where the risk type includes avoidable risks and unavoidable risks;

[0081] When the risk type is an unavoidable risk, obtain the current ship performance data and the historical coping strategies of the risk feature;

[0082] Based on the current ship performance data and the historical coping strategies for the risk characteristics, perform a simulation test on the current ship performance data using the historical coping strategies, and adjust the historical coping strategies according to the test results to serve as the current coping strategies, where the coping strategies include adjusting the ship speed, adjusting the load, and adjusting the route;

[0083] When the risk type is an avoidable risk, determine the target characteristics and auxiliary characteristics of the risk characteristics, and formulate an avoidance strategy based on the target characteristics and auxiliary characteristics;

[0084] Input the avoidance strategy and / or coping strategy of the risk characteristics into the data framework.

[0085] As described above, existing risk prediction systems can usually only identify and predict some common avoidable risks, such as meteorological conditions, sea current speed, etc. When a ship encounters sudden bad weather, such as a storm, the existing risk prediction system may not be able to accurately predict the arrival of the storm, resulting in the ship being unable to take evasive measures in time. In this case, it is necessary to face the risk directly and reduce the danger. This application determines the weight coefficient of the risk characteristics using the correlation coefficient, reflecting its importance level in the navigation risk prediction. It helps to identify the characteristics that are most important for the navigation risk prediction and provides a basis for subsequent analysis. Based on the weight coefficient of the risk characteristics, analyze the risk types of the risk characteristics, including avoidable risks and unavoidable risks. It provides a basis for formulating targeted coping strategies. Obtain the current ship performance data and the historical coping strategies for the risk characteristics, perform a simulation test on the current ship performance data using the historical coping strategies, and adjust the historical coping strategies according to the test results to serve as the current coping strategies. Improve the coping ability for unavoidable risks and reduce losses. Determine the target characteristics and auxiliary characteristics of the risk characteristics, and formulate an avoidance strategy based on the target characteristics and auxiliary characteristics. Through the avoidance strategy, reduce the occurrence probability of the risk and improve the navigation safety. Input the avoidance strategy and / or coping strategy of the risk characteristics into the data framework. Integrate the risk characteristics and their coping strategies into a structured data model for easy management and application.

[0086] In a feasible embodiment, when a ship encounters a storm, it may not be able to avoid the impact of the storm, but the risk can be reduced by adjusting the ship speed, adjusting the load, and adjusting the route. Combine the current ship performance data and the adjusted coping strategies to analyze the risk index of the crew. Determine the factors affecting the crew's risk index, such as workload, psychological pressure, fatigue level, etc. Establish a crew risk index evaluation model considering the crew's working conditions, physiological state, and psychological state. Evaluate the crew's risk index under the current coping strategies. If the crew's risk index is greater than the preset index threshold, it is determined that the coping strategy does not meet the output conditions. Readjust the coping strategy according to the risk index to reduce the crew's risk index.

[0087] In a specific embodiment, after the step of adjusting the coping strategy according to the test results, the method further includes:

[0088] Obtain the current physiological parameters of the crew members, and evaluate the acceptable risk index range of the crew members by combining the physiological parameters and the current ship performance data;

[0089] Input the acceptable risk index range of the crew members, the current ship performance data, and the coping strategy into a preset evaluation model respectively, and analyze whether the coping strategy is within the acceptable risk index range of the crew members through the evaluation model;

[0090] If the coping strategy is within the acceptable risk index range of the crew members, then determine that the coping strategy meets the output conditions;

[0091] Based on meeting the output conditions, use the adjusted coping strategy as the coping strategy for the currently un-avoidable risks.

[0092] As described above, sensors or other monitoring devices can be used to obtain the physiological parameters of crew members in real time, such as heart rate, blood pressure, body temperature, etc. Providing instant health status information of crew members helps to quickly identify potential health problems. For example, when encountering bad weather, real-time monitoring of the crew's heart rate and blood pressure can timely understand the crew's physiological reactions under stress, so as to take measures to prevent overwork or health crises. Combine the physiological parameters of crew members with the performance data of the ship (such as stability, speed, etc.), and calculate the risk index through algorithms. Determine the risk level that crew members can bear under specific operating conditions. If the ship is sailing in a storm, combining the physiological data of the crew and the stability data of the ship can help decide whether to adjust the route or take other measures to reduce risks. Analyze the input data using a preset evaluation model to determine the effectiveness of the response strategy. Ensure that the response strategy matches the current risk situation and is safe for the crew. If the response strategy includes asking the crew to carry out emergency repairs, the evaluation model will analyze whether such repairs are feasible and safe under the current ship performance and crew physiological conditions. The evaluation model will compare the risks that the response strategy may bring with the range of risk indices acceptable to the crew. Prevent taking response measures that may damage the health or safety of the crew. If the response strategy requires the crew to work under high-risk conditions, the evaluation model can identify this situation and recommend a safer alternative. After confirming that the risk level of the response strategy is within the acceptable range, consider it a feasible plan. Ensure that the output response strategy is both effective and safe. After determining that the physiological parameters of all crew members are within the normal range and the ship performance is stable, the response strategy taken is more likely to succeed and ensure the safety of the crew. Adjust and implement the response strategy according to the evaluation results. Provide a verified response plan for the current risk. After adjusting the response strategy, such as reducing the working hours of the crew or providing additional safety equipment, it can ensure that the safety and health of the crew are maximally protected when facing unavoidable risks.

[0093] In another embodiment, assume that we have a cargo ship crossing a sea area that has multiple risk characteristics in past navigation records, such as encountering a large number of fragmented icebergs and reefs during navigation, which cannot be bypassed.

[0094] The specific method is: through data analysis, determine the weight coefficients of the following risk characteristics:

[0095] Fragmented icebergs: weight coefficient 0.8

[0096] Reefs: weight coefficient 0.9

[0097] Analysis shows that both fragmented icebergs and reefs are risks that cannot be avoided. Current ship performance data: the ice-breaking ability, structural strength, speed, etc. of the ship.

[0098] Historical response strategies: In similar situations, ships usually slow down and choose the safest path to directly pass through the obstacles. Use the current ship performance data and historical response strategies for simulation tests. The test results show that when the speed does not exceed 5 knots, it is feasible to choose to directly impact the smaller and relatively safer ice blocks.

[0099] According to the test results, adjust the response strategy: Decide to reduce the speed to 5 knots and choose a relatively safe path to directly pass through the fragmented ice blocks. The current physiological parameters of the crew: The average heart rate is 80 beats per minute, and the average blood pressure is 110 / 70 mmHg. Combining the physiological parameters and ship performance data, the acceptable risk index range for the crew is evaluated to be 0.4 - 0.8. Input the acceptable risk index range for the crew (0.4 - 0.8), the current ship performance data (5 knots speed, icebreaker structural strength), and the response strategy (directly impact the smaller ice blocks) into the evaluation model. The analysis result of the evaluation model shows that the risk index of the response strategy of directly impacting the smaller ice blocks is 0.6, which is within the acceptable risk index range of the crew. Since the response strategy meets the output conditions, the adjusted response strategy (slow down to 5 knots, choose to directly impact the smaller ice blocks) is used as the response strategy for the current inescapable risks. Input the response strategy of direct impact into the data framework of the navigation risk data and prepare for implementation. From the above analysis, the ship must directly face the inescapable risks and reduce the damage caused by the impact by slowing down and choosing a relatively safe path. This method demonstrates how to ensure the safety of the crew and the ship in the face of extreme situations.

[0100] The data fusion and integration method based on multi-source navigation data of the present application can extract risk features from multiple data sources, including those with strong correlations with navigation risks, by constructing an association analysis model and a hierarchical clustering model. Determine the weight coefficient of each risk feature according to the correlation coefficient, reflecting its importance level in navigation risk prediction. The determination of the weight coefficient helps to improve the prediction performance and stability of the model, enabling decision-makers to formulate corresponding risk management strategies based on the importance of risk features. Establish a data framework for navigation risk data, integrating risk features and their weight coefficients. The data framework can be used as a decision support tool to help ship operators and maritime management agencies better understand navigation risks and formulate corresponding risk management strategies. Ship operators can process multi-source navigation data more effectively, improve the accuracy of navigation risk prediction, and thus ensure navigation safety and optimize the navigation plan.

[0101] Refer to Figure 3 , an embodiment of the present application also provides a data fusion and integration system based on multi-source navigation data, including:

[0102] The first acquisition module 1 is used to acquire navigation environment data in real time and identify the sea ice density parameter in the navigation environment data;

[0103] A second acquisition module 2, configured to acquire current preset lane position data, and mark target sea ice data within a preset range of the lane position data according to the lane position data and sea ice concentration parameters;

[0104] A judgment module 3, configured to judge whether the target sea ice data meets the condition for replacing the lane position data;

[0105] A determination module 4, configured to determine that the target sea ice data meets the condition for replacing the lane position data when the sea ice concentration parameters constitute an obstacle to passing on the lane position data;

[0106] A route avoidance module 5, configured to determine route avoidance data according to the target sea ice data based on the determination result;

[0107] A modification module 6, configured to modify the lane position data based on the route avoidance data.

[0108] As described above, it can be understood that each component of the data fusion and integration system based on marine multi-source data proposed in this application can implement the functions of any one of the data fusion and integration methods based on marine multi-source data as described above, and the specific structure will not be elaborated.

[0109] Referring to Figure 4 , this application embodiment also provides a computer device, which may be a server, and its internal structure may be as Figure 4 shown. The computer device includes a processor, a memory, a network interface, and a database connected through a system bus. Among them, the processor of the computer design is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system, a computer program, and a database. The memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The database of the computer device is used to store data such as monitoring data. The network interface of the computer device is used to communicate with an external terminal through a network connection. When the computer program is executed by the processor, it implements a data fusion and integration method based on marine multi-source data.

[0110] The above-mentioned processor executes the above-mentioned data fusion and integration method based on marine multi-source data, including: constructing an association analysis model for extracting risk characteristics of data; obtaining source data of different scenario types in real time; inputting source data of different types into the association analysis model, and extracting risk characteristics of the source data through the association analysis model; setting up a hierarchical clustering model, inputting each risk characteristic into the hierarchical clustering model respectively, and analyzing the correlation coefficient between each risk characteristic and historical navigation data through the hierarchical clustering model; determining the weight coefficient of the risk characteristic according to the correlation coefficient, which is used to reflect the importance level of the risk characteristic in navigation risk prediction; constructing a data framework for navigation risk data, and integrating the risk characteristic and its weight coefficient into the data framework.

[0111] The above-mentioned data fusion and integration method based on marine multi-source data can extract risk characteristics from multiple data sources, including those with strong relevance to navigation risks, by constructing an association analysis model and a hierarchical clustering model. Determine the weight coefficient of each risk characteristic according to the correlation coefficient, which reflects its importance level in navigation risk prediction. The determination of the weight coefficient helps to improve the prediction performance and stability of the model, enabling decision-makers to formulate corresponding risk management strategies based on the importance of risk characteristics. Construct a data framework for navigation risk data, and integrate risk characteristics and their weight coefficients. The data framework can be used as a decision support tool to help ship operators and maritime management agencies better understand navigation risks and formulate corresponding risk management strategies. Ship operators can process marine multi-source data more effectively, improve the accuracy of navigation risk prediction, and thus ensure navigation safety and optimize navigation plans.

[0112] An embodiment of the present application further provides a computer-readable storage medium, on which a computer program is stored. When the computer program is executed by a processor, it implements a data fusion and integration method based on marine multi-source data, including the steps of: constructing an association analysis model for extracting risk characteristics of data; obtaining source data of different scenario types in real time; inputting source data of different types into the association analysis model, and extracting risk characteristics of the source data through the association analysis model; setting up a hierarchical clustering model, inputting each risk characteristic into the hierarchical clustering model respectively, and analyzing the correlation coefficient between each risk characteristic and historical navigation data through the hierarchical clustering model; determining the weight coefficient of the risk characteristic according to the correlation coefficient, which is used to reflect the importance level of the risk characteristic in navigation risk prediction; constructing a data framework for navigation risk data, and integrating the risk characteristic and its weight coefficient into the data framework.

[0113] Those of ordinary skill in the art can understand that all or part of the processes in the methods of the above embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the embodiments of the above methods. Among them, any reference to a memory, storage, database, or other medium provided in this application and used in the embodiments can include non-volatile and / or volatile memories. Non-volatile memory can include read-only memory (ROM), programmable ROM (PROM), electrically programmable ROM (EPROM), electrically erasable programmable ROM (EEPROM), or flash memory. Volatile memory can include random access memory (RAM) or external cache memory. By way of illustration and not limitation, RAM is available in many forms, such as static RAM (SRAM), dynamic RAM (DRAM), synchronous DRAM (SDRAM), double data rate SDRAM (SSRSDRAM), enhanced SDRAM (ESDRAM), synchronous link (Synchlink) DRAM (SLDRAM), Rambus direct RAM (RDRAM), direct memory bus dynamic RAM (DRDRAM), and Rambus dynamic RAM (RDRAM), etc.

[0114] It should be noted that, in this document, the term "comprising", "including" or any other variation thereof is intended to cover a non-exclusive inclusion, such that a process, apparatus, article or method comprising a series of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such process, apparatus, article or method. Without further limitation, an element defined by the phrase "comprising a..." does not exclude the presence of additional identical elements in the process, apparatus, article or method comprising that element.

[0115] The above are only the preferred embodiments of this application, and do not limit the patent scope of this application. Any equivalent structure or equivalent process transformation made by using the specification and drawings of this application, or directly or indirectly applied in other related technical fields, shall be similarly included in the patent protection scope of this application.

Claims

1. A data fusion and integration method based on multi-source nautical data for predicting navigation risks in navigation, characterized in that, The method includes: Constructing an association analysis model for extracting risk characteristics of data; Obtaining source data of different scenario types in real time; Inputting source data of different types into the association analysis model, and extracting risk characteristics of the source data through the association analysis model; Setting up a hierarchical clustering model, inputting each risk characteristic into the hierarchical clustering model respectively, and analyzing the correlation coefficient between each risk characteristic and historical navigation data through the hierarchical clustering model; Determining the weight coefficient of the risk characteristic according to the correlation coefficient, which is used to reflect the importance level of the risk characteristic in navigation risk prediction; Constructing a data framework for navigation risk data, and integrating the risk characteristics and their weight coefficients into the data framework; The method of inputting each risk characteristic into the hierarchical clustering model respectively, and analyzing the correlation coefficient between each risk characteristic and historical navigation data through the hierarchical clustering model includes: Obtaining the scenario classification corresponding to the risk characteristic, inputting the risk characteristics of each scenario classification into the hierarchical clustering model, mapping the risk characteristics in the historical navigation data through the hierarchical clustering model, and determining the target characteristics and auxiliary characteristics of the risk characteristic corresponding in the navigation risk data; Based on the target characteristics, calculating the association ratio between the target characteristics of each scenario classification and the historical navigation data, where the scenario classification includes meteorological characteristics, ocean current characteristics and geographical characteristics; Quantifying the association ratio through the hierarchical clustering model to obtain the correlation coefficient between the risk characteristic and the historical navigation data; The method of determining the target characteristics and auxiliary characteristics of the risk characteristic corresponding in the navigation risk data includes: When the scenario classification is meteorological characteristics, obtaining the navigation performance parameters and navigation delay parameters of the navigation risk data, where the meteorological characteristics include wind speed, wind direction and air pressure parameters; Analyzing the speed change parameters of the ship under meteorological characteristic conditions based on the navigation performance parameters; Analyzing the number of navigation delays and the time of the ship under meteorological characteristic conditions based on the navigation delay parameters; Inputting the speed change parameters and the parameters of the meteorological characteristics into the hierarchical clustering model, analyzing the meteorological parameters of direct influence and indirect influence through the hierarchical clustering model, and outputting the analysis result; Inputting the number of navigation delays and the time and the parameters of the meteorological characteristics into the hierarchical clustering model, and analyzing the meteorological parameters of direct influence and indirect influence through the hierarchical clustering model; Taking the meteorological parameters of direct influence as target characteristics and the meteorological parameters of indirect influence as auxiliary characteristics.

2. The data fusion and integration method based on marine multi-source data according to claim 1, characterized in that The method of determining the target characteristics and auxiliary characteristics of the risk characteristic corresponding in the navigation risk data further includes: When the scenario classification is ocean current characteristics, obtaining the navigation performance parameters and navigation delay parameters of the navigation risk data, where the ocean current characteristics include ocean current speed, ocean current direction, ocean current density and ocean current change rate parameters; Analyzing the speed change parameters of the ship under ocean current characteristic conditions based on the navigation performance parameters; Analyzing the number of navigation delays and the time of the ship under ocean current characteristic conditions based on the navigation delay parameters; According to the dynamic changes of ocean current characteristics, input the speed change parameters and the parameters of ocean current characteristics into the hierarchical clustering model, and analyze the ocean current parameters with direct and indirect influences through the hierarchical clustering model; According to the real-time influence of ocean current characteristics on navigation performance and delays, input the number and time of navigation delays and the parameters of ocean current characteristics into the hierarchical clustering model, analyze the ocean current parameters with direct and indirect influences through the hierarchical clustering model, and output the analysis results; Use the directly influential ocean current parameters as target features and the indirectly influential ocean current parameters as auxiliary features.

3. The data fusion and integration method based on multi-source nautical data according to claim 1, wherein The method further includes: Obtain the historical target features and auxiliary features of the same scenario, and analyze whether there is a time sequence attribute for the historical target features and auxiliary features of the same scenario; When there is a time sequence attribute for the historical target features and auxiliary features of the same scenario, extract the historical target features and auxiliary features; Construct a probability analysis model, input the historical target features and auxiliary features into the probability analysis model, analyze the probability of the auxiliary features triggering the target features through the probability analysis model, and output the probability analysis results; When the probability analysis result shows that the probability of the auxiliary features triggering the target features is greater than a preset probability threshold, mark the auxiliary features as warning features.

4. The data fusion and integration method based on multi-source nautical data according to claim 1, characterized in that After the step of determining the weight coefficient of the risk feature according to the correlation coefficient to reflect the importance level of the risk feature in navigation risk prediction, the method further includes: Based on the importance level of the risk feature in navigation risk prediction, analyze the risk type of the risk feature, where the risk type includes avoidable risks and unavoidable risks; When the risk type is an unavoidable risk, obtain the current ship performance data and the historical coping strategies of the risk feature; According to the current ship performance data and the historical coping strategies of the risk feature, conduct a simulation test on the current ship performance data using the historical coping strategies, and adjust the historical coping strategies according to the test results as the current coping strategies, where the coping strategies include adjusting the speed, adjusting the load, and adjusting the route; When the risk type is an avoidable risk, determine the target features and auxiliary features of the risk feature, and formulate an avoidance strategy according to the target features and auxiliary features; Input the avoidance strategy and / or coping strategy of the risk feature into the data framework.

5. The data fusion and integration method based on multi-source marine data according to claim 4, characterized in that, After the step of adjusting the coping strategy according to the test results, the method further includes: Obtain the current physiological parameters of the crew, and evaluate the acceptable risk index range of the crew by combining the physiological parameters and the current ship performance data; Input the acceptable risk index range of the crew, the current ship performance data, and the coping strategy into a preset evaluation model respectively, and analyze whether the coping strategy is within the acceptable risk index range of the crew through the evaluation model; If the coping strategy is within the acceptable risk index range of the crew, then determine that the coping strategy meets the output conditions; Based on meeting the output conditions, use the adjusted coping strategy as the current coping strategy for unavoidable risks.

6. A data fusion and integration system based on multi-source marine data, for use in the method according to any one of claims 1-5, characterized in that, It includes: A construction module for constructing an association analysis model to extract the risk features of the data; An acquisition module, configured to acquire source data of different scenario types in real time; An input module, configured to input source data of different types into the association analysis model, and extract risk features of the source data through the association analysis model; An analysis module, configured to set up a hierarchical clustering model, input each risk feature into the hierarchical clustering model respectively, and analyze the correlation coefficient between each risk feature and historical navigation data through the hierarchical clustering model; A determination module, configured to determine the weight coefficient of the risk feature according to the correlation coefficient, which is used to reflect the importance level of the risk feature in navigation risk prediction; An integration module, configured to construct a data framework of navigation risk data, and integrate the risk feature and its weight coefficient into the data framework.

7. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, the steps of the method according to any one of claims 1 to 5 are implemented.

8. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, the steps of the method according to any one of claims 1 to 5 are implemented.

Images