Chart data risk monitoring method and system based on multi-model linkage
Through multi-model linkage of chart data risk monitoring methods, screening and predicting chart data, combined with risk association rules, the problem of unused correlation between chart data and routes in the existing technology is solved, and the accuracy of risk prediction and navigation safety are improved. sex.
Patent Information
- Application Number
- CN202410896785.9
- Authority / Receiving Office
- CN · China
- Patent Type
- Patents(China)
- Current Assignee / Owner
- Filing Date
- 2024-07-05
- Publication Date
- 2024-11-12
- Estimated Expiration
- 2044-07-05
AI Technical Summary
The existing risk prediction algorithms only use a single model, failing to fully consider the association between chart data and routes and the association between multiple risks, resulting in insufficient navigation safety.
Using a multi-model linkage method, the chart data and route information are obtained, and the route chart data is filtered out, and the prediction algorithm model of different risk types is input, and the final risk is calculated using risk association correction rules. Predict results.
It improves the accuracy and efficiency of risk prediction, enhances navigation stability and safety, and reduces the occurrence of accidents.
Smart Images

Figure CN118428564B_ABST
Abstract
Description
Technical Field
[0001] The present invention relates to the field of data processing technology, and in particular to a chart data risk monitoring method and system based on multi-model linkage. Background Art
[0002] With the increase of intelligent equipment on ships and the improvement of intelligent control, many navigation technologies have begun to introduce risk prediction algorithms based on nautical chart data to predict the dangers that ships may encounter during navigation. However, existing risk prediction algorithms often only consider preset nautical chart data through a single prediction model, without considering the introduction of multi-model prediction results and combining the correlation between multiple different risks to further improve the efficiency and accuracy of risk prediction. Therefore, when applied to risk prediction in real-time navigation, the safety of navigation is insufficient. It can be seen that the existing technology has defects that need to be solved urgently. Summary of the invention
[0003] The technical problem to be solved by the present invention is to provide a method and system for risk monitoring of nautical chart data based on multi-model linkage, which can fully consider the relationship between nautical chart data and routes and utilize the relationship between multiple risk predictions to improve the accuracy and efficiency of risk prediction, improve navigation stability and safety, and reduce the occurrence of accidents.
[0004] In order to solve the above technical problems, the first aspect of the present invention discloses a method for risk monitoring of nautical chart data based on multi-model linkage, the method comprising:
[0005] When the target ship is sailing in the target sea area, obtaining the nautical chart data of the target sea area and the current route of the target ship;
[0006] Filtering the data in the nautical chart data according to the current route to obtain route nautical chart data;
[0007] Inputting the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data;
[0008] According to the multiple risk prediction results and preset risk association correction rules, a final risk prediction result corresponding to the current route is determined.
[0009] As an optional implementation, in the first aspect of the present invention, the filtering of the data in the nautical chart data according to the current route to obtain the route nautical chart data includes:
[0010] Determine a route passing area corresponding to the current route;
[0011] Determine a route time interval corresponding to the current route;
[0012] The data in the nautical chart data whose corresponding position is within the area where the route passes and whose data time information is within the time interval of the route are screened out to be determined as the route nautical chart data.
[0013] As an optional implementation, in the first aspect of the present invention, determining the route passing area corresponding to the current route includes:
[0014] Inputting the chart data into a trained deviation risk prediction neural network to obtain a deviation risk value corresponding to the current route; the deviation risk prediction neural network is trained by a training data set including a plurality of training chart data and corresponding navigation deviation annotations;
[0015] calculating a range weight proportional to the yaw risk value;
[0016] Calculating the product of the range weight and the preset range distance value to obtain a corrected range distance value;
[0017] The portion of the current route within the target sea area is used as a basic line segment, a circle is drawn at each point on the basic line segment with the correction range distance value as the diameter, and the union of all the circles is calculated to obtain the route passing area.
[0018] As an optional implementation, in the first aspect of the present invention, determining the route time interval corresponding to the current route includes:
[0019] Determine a plurality of other similar sea areas similar to the target sea area; the regional similarity between the other similar sea areas and the target sea area is greater than a preset similarity threshold; the regional similarity is the product of the regional obstacle similarity and the regional weather similarity; the regional obstacle similarity is the similarity between the obstacle area distributions in the nautical chart data of the two sea areas; the regional weather similarity is the similarity between the weather forecast data when the target ship passes by in the nautical chart data of the two sea areas;
[0020] Obtaining the navigation speed of the target ship when passing through each of the other similar sea areas during the historical time period;
[0021] Calculating the average value of all the sailing speeds to obtain the predicted speed of the target ship;
[0022] Determine the ratio of the route length of the current route in the target sea area to the predicted speed to obtain the predicted route time;
[0023] The route time interval is determined by taking the current time point as the starting point and the predicted route time as the length of the time interval.
[0024] As an optional implementation, in the first aspect of the present invention, the inputting the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data includes:
[0025] For each risk type, according to the correspondence between the preset risk type and the data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk types are the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing;
[0026] The risk-related data is input into a neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including multiple training risk-related data and corresponding risk annotations.
[0027] As an optional implementation, in the first aspect of the present invention, determining the final risk prediction result corresponding to the current route according to the multiple risk prediction results and the preset risk association correction rule includes:
[0028] For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all the risk types;
[0029] Calculating the strong association probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type;
[0030] According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to contradictory types are screened from all the risk types; wherein the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold;
[0031] Calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type;
[0032] Calculate a weighted average of the strong association probability and the contradictory association probability to obtain a corrected probability of the risk type; wherein the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types;
[0033] Sorting all the risk types from high to low according to the corrected probabilities to obtain a type sequence;
[0034] All risk types that are a preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
[0035] As an optional implementation, in the first aspect of the present invention, the calculating, according to the first risk type and the risk prediction probability of the risk type, the strong association probability corresponding to the risk type includes:
[0036] calculating a first weight proportional to the total number of all the first risk types;
[0037] Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold;
[0038] calculating a second weight proportional to an average value of the risk prediction probabilities of all the high probability risks;
[0039] The risk prediction probability of the risk type is calculated by multiplying the first weight and the second weight to obtain the strong association probability corresponding to the risk type.
[0040] As an optional implementation, in the first aspect of the present invention, the calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type includes:
[0041] calculating a third weight inversely proportional to the total number of all the second risk types;
[0042] Screening out all strongly contradictory risks in the second risk type whose probability difference is greater than a preset second probability threshold;
[0043] Calculating a fourth weight inversely proportional to an average value of the risk prediction probabilities of all the strong conflicting risks;
[0044] The risk prediction probability of the risk type and the product of the third weight and the fourth weight are calculated to obtain the conflict association probability corresponding to the risk type.
[0045] A second aspect of an embodiment of the present invention discloses a risk monitoring system for nautical chart data based on multi-model linkage, the system comprising:
[0046] An acquisition module, used for acquiring the nautical chart data of the target sea area and the current route of the target ship when the target ship is sailing in the target sea area;
[0047] A screening module, used for screening the data in the chart data according to the current route to obtain the route chart data;
[0048] A prediction module, used for inputting the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data;
[0049] The determination module is used to determine the final risk prediction result corresponding to the current route based on the multiple risk prediction results and the preset risk association correction rules.
[0050] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module screens the data in the nautical chart data according to the current route to obtain the route nautical chart data includes:
[0051] Determine a route passing area corresponding to the current route;
[0052] Determine a route time interval corresponding to the current route;
[0053] The data in the nautical chart data whose corresponding position is within the area where the route passes and whose data time information is within the time interval of the route are screened out to be determined as the route nautical chart data.
[0054] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module determines the route corresponding to the current route passes through the area includes:
[0055] Inputting the chart data into a trained deviation risk prediction neural network to obtain a deviation risk value corresponding to the current route; the deviation risk prediction neural network is trained by a training data set including a plurality of training chart data and corresponding navigation deviation annotations;
[0056] calculating a range weight proportional to the yaw risk value;
[0057] Calculating the product of the range weight and the preset range distance value to obtain a corrected range distance value;
[0058] The portion of the current route within the target sea area is used as a basic line segment, a circle is drawn at each point on the basic line segment with the correction range distance value as the diameter, and the union of all the circles is calculated to obtain the route passing area.
[0059] As an optional implementation, in the second aspect of the present invention, the specific manner in which the screening module determines the route time interval corresponding to the current route includes:
[0060] Determine a plurality of other similar sea areas similar to the target sea area; the regional similarity between the other similar sea areas and the target sea area is greater than a preset similarity threshold; the regional similarity is the product of the regional obstacle similarity and the regional weather similarity; the regional obstacle similarity is the similarity between the obstacle area distributions in the nautical chart data of the two sea areas; the regional weather similarity is the similarity between the weather forecast data when the target ship passes by in the nautical chart data of the two sea areas;
[0061] Obtaining the navigation speed of the target ship when passing through each of the other similar sea areas during the historical time period;
[0062] Calculating the average value of all the sailing speeds to obtain the predicted speed of the target ship;
[0063] Determine the ratio of the route length of the current route in the target sea area to the predicted speed to obtain the predicted route time;
[0064] The route time interval is determined by taking the current time point as the starting point and the predicted route time as the length of the time interval.
[0065] As an optional implementation, in the second aspect of the present invention, the prediction module inputs the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data, including:
[0066] For each risk type, according to the correspondence between the preset risk type and the data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk types are the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing;
[0067] The risk-related data is input into a neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including multiple training risk-related data and corresponding risk annotations.
[0068] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module determines the final risk prediction result corresponding to the current route according to the multiple risk prediction results and the preset risk association correction rule includes:
[0069] For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all the risk types;
[0070] Calculating the strong association probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type;
[0071] According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to contradictory types are screened from all the risk types; wherein the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold;
[0072] Calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type;
[0073] Calculate a weighted average of the strong association probability and the contradictory association probability to obtain a corrected probability of the risk type; wherein the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types;
[0074] Sorting all the risk types from high to low according to the corrected probabilities to obtain a type sequence;
[0075] All risk types that are a preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
[0076] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module calculates the strong association probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type includes:
[0077] calculating a first weight proportional to the total number of all the first risk types;
[0078] Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold;
[0079] calculating a second weight proportional to an average value of the risk prediction probabilities of all the high probability risks;
[0080] The risk prediction probability of the risk type is calculated by multiplying the first weight and the second weight to obtain the strong association probability corresponding to the risk type.
[0081] As an optional implementation, in the second aspect of the present invention, the specific manner in which the determination module calculates the probability of conflict association corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type includes:
[0082] calculating a third weight inversely proportional to the total number of all the second risk types;
[0083] Screening out all strongly contradictory risks in the second risk type whose probability difference is greater than a preset second probability threshold;
[0084] Calculating a fourth weight inversely proportional to an average value of the risk prediction probabilities of all the strong conflicting risks;
[0085] The risk prediction probability of the risk type and the product of the third weight and the fourth weight are calculated to obtain the conflict association probability corresponding to the risk type.
[0086] The third aspect of the present invention discloses another risk monitoring system for nautical chart data based on multi-model linkage, the system comprising:
[0087] A memory storing executable program code;
[0088] a processor coupled to the memory;
[0089] The processor calls the executable program code stored in the memory to execute part or all of the steps in the chart data risk monitoring method based on multi-model linkage disclosed in the first aspect of the present invention.
[0090] The fourth aspect of the present invention discloses a computer storage medium, which stores computer instructions. When the computer instructions are called, they are used to execute part or all of the steps in the nautical chart data risk monitoring method based on multi-model linkage disclosed in the first aspect of the present invention.
[0091] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:
[0092] The present invention can filter the data in the nautical chart data through the current route to obtain the nautical chart data on the route, and then predict multiple risk results based on multiple prediction algorithm models corresponding to different risk types and through risk association correction rules, finally predict accurate risk results, thereby fully considering the association between the nautical chart data and the route and utilizing the association of multiple risk predictions to improve the accuracy and efficiency of risk prediction, improve navigation stability and safety, and reduce the occurrence of accidents. BRIEF DESCRIPTION OF THE DRAWINGS
[0093] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the description of the embodiments. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without creative work.
[0094] Figure 1 It is a flow chart of a method for risk monitoring of nautical chart data based on multi-model linkage disclosed in an embodiment of the present invention.
[0095] Figure 2 It is a structural schematic diagram of a nautical chart data risk monitoring system based on multi-model linkage disclosed in an embodiment of the present invention.
[0096] Figure 3 It is a structural schematic diagram of another nautical chart data risk monitoring system based on multi-model linkage disclosed in an embodiment of the present invention. DETAILED DESCRIPTION
[0097] In order to enable those skilled in the art to better understand the scheme of the present invention, the technical scheme in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without creative work are within the scope of protection of the present invention.
[0098] The terms "first", "second", etc. in the specification and claims of the present invention and the above-mentioned drawings are used to distinguish different objects, rather than to describe a specific order. In addition, the terms "including" and "having" and any variations thereof are intended to cover non-exclusive inclusions. For example, a process, method, device, product or equipment that includes a series of steps or units is not limited to the listed steps or units, but may optionally include steps or units that are not listed, or may optionally include other steps or units that are inherent to these processes, methods, products or equipment.
[0099] Reference to "embodiments" herein means that a particular feature, structure, or characteristic described in conjunction with the embodiments may be included in at least one embodiment of the present invention. The appearance of the phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it an independent or alternative embodiment that is mutually exclusive with other embodiments. It is explicitly and implicitly understood by those skilled in the art that the embodiments described herein may be combined with other embodiments.
[0100] The present invention discloses a chart data risk monitoring method and system based on multi-model linkage, which can filter the data in the chart data through the current route to obtain the chart data on the route, and then predict multiple risk results based on multiple prediction algorithm models corresponding to different risk types and finally predict accurate risk results through risk association correction rules, so as to fully consider the association between the chart data and the route and use the association of multiple risk predictions to improve the accuracy and efficiency of risk prediction, improve navigation stability and safety, and reduce the occurrence of accidents. The following are detailed descriptions.
[0101] For example, see Figure 1 , Figure 1 : is a flow chart diagram of a method for risk monitoring of nautical chart data based on multi-model linkage disclosed in an embodiment of the present invention. Figure 1 The described method for risk monitoring of nautical chart data based on multi-model linkage can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 1 As shown, the risk monitoring method for nautical chart data based on multi-model linkage may include the following operations:
[0102] 101. When the target ship is sailing in the target sea area, obtain the nautical chart data of the target sea area and the current route of the target ship.
[0103] 102. Filter the data in the chart data according to the current route to obtain the route chart data.
[0104] 103. Input the route chart data into multiple prediction algorithm models corresponding to different risk types to obtain multiple risk prediction results corresponding to the route chart data.
[0105] 104. According to the multiple risk prediction results and the preset risk association correction rules, the final risk prediction result corresponding to the current route is determined.
[0106] It can be seen that the above-mentioned embodiment of the invention can filter the data in the nautical chart data through the current route to obtain the nautical chart data on the route, and then predict multiple risk results based on multiple prediction algorithm models corresponding to different risk types and through risk association correction rules, finally predict accurate risk results, thereby fully considering the association between the nautical chart data and the route and utilizing the association between multiple risk predictions to improve the accuracy and efficiency of risk prediction, improve navigation stability and safety, and reduce the occurrence of accidents.
[0107] As an optional embodiment, in the above step, filtering the data in the chart data according to the current route to obtain the route chart data includes:
[0108] Determine the route passing area corresponding to the current route;
[0109] Determine the route time interval corresponding to the current route;
[0110] The data whose corresponding position in the chart data is within the route passing area and whose data time information is within the route time interval are screened out and determined as the route chart data.
[0111] It can be seen that through the above optional embodiments, the nautical chart data can be screened by the route passing area and route time interval corresponding to the current route to obtain route chart data with higher predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0112] As an optional embodiment, in the above step, determining the route passing area corresponding to the current route includes:
[0113] Inputting the chart data into a trained deviation risk prediction neural network to obtain a deviation risk value corresponding to the current route; optionally, the deviation risk prediction neural network is trained by a training data set including a plurality of training chart data and corresponding navigation deviation annotations;
[0114] Calculate the range weight proportional to the yaw risk value;
[0115] Calculate the product of the range weight and the preset range distance value to obtain the corrected range distance value;
[0116] Taking the part of the current route in the target sea area as the basic line segment, draw a circle with the correction range distance value as the diameter at each point on the basic line segment, and calculate the union of all circles to obtain the route passing area.
[0117] It can be seen that through the above-mentioned optional embodiments, the deviation risk value can be predicted by the neural network algorithm, and the range distance value can be adjusted based on this to draw the route passing area, so as to facilitate the subsequent more accurate screening of the nautical chart data and obtain route nautical chart data with more predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0118] As an optional embodiment, in the above step, determining the route time interval corresponding to the current route includes:
[0119] Determine a plurality of other similar sea areas similar to the target sea area; optionally, the regional similarity between the other similar sea areas and the target sea area is greater than a preset similarity threshold; the regional similarity is the product of the regional obstacle similarity and the regional weather similarity; the regional obstacle similarity is the similarity between the obstacle area distributions in the nautical chart data of the two sea areas; the regional weather similarity is the similarity between the weather forecast data when the target ship passes by in the nautical chart data of the two sea areas;
[0120] Obtain the navigation speed of the target ship when it passes through each other similar sea area during the historical period;
[0121] Calculate the average of all sailing speeds to get the predicted speed of the target ship;
[0122] Determine the ratio of the current route length in the target sea area to the predicted speed, and obtain the predicted route time;
[0123] The route time interval is determined by taking the current time point as the starting point and the predicted route time as the length of the time interval.
[0124] It can be seen that through the above optional embodiments, multiple similar areas can be screened out through the similarity algorithm, and the predicted speed can be calculated based on the historical sailing speed of the similar areas to further calculate the route time interval, so as to facilitate the subsequent more accurate screening of the chart data and obtain route chart data with more predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0125] As an optional embodiment, in the above steps, the route chart data is input into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data, including:
[0126] For each risk type, according to the correspondence between the preset risk type and data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk type can be the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing;
[0127] The risk-related data is input into the neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including multiple training risk-related data and corresponding risk annotations.
[0128] It can be seen that through the above-mentioned optional embodiments, the correspondence between the preset risk types and data types can first be used to filter out the risk-related data in the route chart data to improve the data relevance. Secondly, the risk prediction probability of the route chart data corresponding to each risk type will be predicted according to the neural network prediction model corresponding to the risk type, so as to subsequently assist in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0129] As an optional embodiment, in the above steps, determining the final risk prediction result corresponding to the current route according to multiple risk prediction results and a preset risk association correction rule includes:
[0130] For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all risk types;
[0131] Calculate the strong correlation probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type;
[0132] According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to the contradictory type are screened from all risk types; optionally, the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold;
[0133] Calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type;
[0134] Calculate the weighted sum average of the strong association probability and the contradictory association probability to obtain the corrected probability of the risk type; optionally, the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types;
[0135] All risk types are sorted from high to low according to the corrected probability to obtain a type sequence;
[0136] All risk types whose first preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
[0137] It can be seen that through the above-mentioned optional embodiments, the strongly associated risks and contradictory risks of each risk can be screened out based on the preset risk strong association rules and risk contradiction rules, and the risk prediction probability can be reasonably and effectively corrected based on these correlations to obtain a more accurate risk probability, which can improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0138] As an optional embodiment, in the above step, calculating the strong association probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type includes:
[0139] calculating a first weight proportional to the total number of types of all first risk types;
[0140] Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold;
[0141] calculating a second weight proportional to the average of the risk prediction probabilities of all high probability risks;
[0142] The risk prediction probability of the risk type is calculated by multiplying the first weight and the second weight to obtain the strong association probability corresponding to the risk type.
[0143] It can be seen that through the above-mentioned optional embodiments, the correction weight can be determined based on the total number of types of the first risk type and the probability average of the high-probability risks therein, and the risk prediction probability can be reasonably and effectively corrected based on the correction weight to obtain a more accurate strong correlation probability, which can subsequently improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0144] As an optional embodiment, in the above step, calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type includes:
[0145] calculating a third weight inversely proportional to the total type quantity of all second risk types;
[0146] Screen out all strongly contradictory risks of the second risk type whose probability difference is greater than a preset second probability threshold;
[0147] Calculating a fourth weight that is inversely proportional to the average of the risk prediction probabilities of all strongly contradictory risks;
[0148] The risk prediction probability of the risk type is calculated by multiplying the third weight and the fourth weight to obtain the conflict association probability corresponding to the risk type.
[0149] It can be seen that through the above-mentioned optional embodiments, the correction weight can be determined based on the total number of risk types and the average probability of risks with a higher degree of conflict, and the risk prediction probability can be reasonably and effectively corrected based on the correction weight to obtain a more accurate probability of conflict association, which can subsequently improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0150] For example 2, please refer to Figure 2 , Figure 2 : is a schematic diagram of a structure of a risk monitoring system for nautical chart data based on multi-model linkage disclosed in an embodiment of the present invention. Figure 2 The described nautical chart data risk monitoring system based on multi-model linkage can be applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 2 As shown, the chart data risk monitoring system based on multi-model linkage may include:
[0151] The acquisition module 201 is used to acquire the nautical chart data of the target sea area and the current route of the target ship when the target ship is sailing in the target sea area.
[0152] The screening module 202 is used to screen the data in the nautical chart data according to the current route to obtain the route nautical chart data.
[0153] The prediction module 203 is used to input the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data.
[0154] The determination module 204 is used to determine the final risk prediction result corresponding to the current route according to the multiple risk prediction results and the preset risk association correction rules.
[0155] It can be seen that the above-mentioned embodiment of the invention can filter the data in the nautical chart data through the current route to obtain the nautical chart data on the route, and then predict multiple risk results based on multiple prediction algorithm models corresponding to different risk types and through risk association correction rules, finally predict accurate risk results, thereby fully considering the association between the nautical chart data and the route and utilizing the association between multiple risk predictions to improve the accuracy and efficiency of risk prediction, improve navigation stability and safety, and reduce the occurrence of accidents.
[0156] As an optional embodiment, the specific method in which the filtering module filters the data in the chart data according to the current route to obtain the route chart data includes:
[0157] Determine the route passing area corresponding to the current route;
[0158] Determine the route time interval corresponding to the current route;
[0159] The data whose corresponding position in the chart data is within the route passing area and whose data time information is within the route time interval are screened out and determined as the route chart data.
[0160] It can be seen that through the above optional embodiments, the nautical chart data can be screened by the route passing area and route time interval corresponding to the current route to obtain route chart data with higher predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0161] As an optional embodiment, the specific manner in which the screening module determines the route corresponding to the current route passes through the area includes:
[0162] Inputting the chart data into a trained deviation risk prediction neural network to obtain a deviation risk value corresponding to the current route; optionally, the deviation risk prediction neural network is trained by a training data set including a plurality of training chart data and corresponding navigation deviation annotations;
[0163] Calculate the range weight proportional to the yaw risk value;
[0164] Calculate the product of the range weight and the preset range distance value to obtain the corrected range distance value;
[0165] Taking the part of the current route in the target sea area as the basic line segment, draw a circle with the correction range distance value as the diameter at each point on the basic line segment, and calculate the union of all circles to obtain the route passing area.
[0166] It can be seen that through the above-mentioned optional embodiments, the deviation risk value can be predicted by the neural network algorithm, and the range distance value can be adjusted based on this to draw the route passing area, so as to facilitate the subsequent more accurate screening of the nautical chart data and obtain route nautical chart data with more predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0167] As an optional embodiment, the specific method by which the screening module determines the route time interval corresponding to the current route includes:
[0168] Determine a plurality of other similar sea areas similar to the target sea area; optionally, the regional similarity between the other similar sea areas and the target sea area is greater than a preset similarity threshold; the regional similarity is the product of the regional obstacle similarity and the regional weather similarity; the regional obstacle similarity is the similarity between the obstacle area distributions in the nautical chart data of the two sea areas; the regional weather similarity is the similarity between the weather forecast data when the target ship passes by in the nautical chart data of the two sea areas;
[0169] Obtain the navigation speed of the target ship when it passes through each other similar sea area during the historical period;
[0170] Calculate the average of all sailing speeds to get the predicted speed of the target ship;
[0171] Determine the ratio of the current route length in the target sea area to the predicted speed, and obtain the predicted route time;
[0172] The route time interval is determined by taking the current time point as the starting point and the predicted route time as the length of the time interval.
[0173] It can be seen that through the above optional embodiments, multiple similar areas can be screened out through the similarity algorithm, and the predicted speed can be calculated based on the historical sailing speed of the similar areas to further calculate the route time interval, so as to facilitate the subsequent more accurate screening of the chart data and obtain route chart data with more predictive reference value, thereby assisting in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0174] As an optional embodiment, the prediction module inputs the route chart data into multiple prediction algorithm models corresponding to different risk types to obtain a specific method of multiple risk prediction results corresponding to the route chart data, including:
[0175] For each risk type, according to the correspondence between the preset risk type and data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk type can be the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing;
[0176] The risk-related data is input into the neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including multiple training risk-related data and corresponding risk annotations.
[0177] It can be seen that through the above-mentioned optional embodiments, the correspondence between the preset risk types and data types can first be used to filter out the risk-related data in the route chart data to improve the data relevance. Secondly, the risk prediction probability of the route chart data corresponding to each risk type will be predicted according to the neural network prediction model corresponding to the risk type, so as to subsequently assist in improving the accuracy and efficiency of risk prediction, improving navigation stability and safety, and reducing the occurrence of accidents.
[0178] As an optional embodiment, the specific manner in which the determination module determines the final risk prediction result corresponding to the current route according to the multiple risk prediction results and the preset risk association correction rule includes:
[0179] For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all risk types;
[0180] Calculate the strong correlation probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type;
[0181] According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to the contradictory type are screened from all risk types; optionally, the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold;
[0182] Calculating the conflict association probability corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type;
[0183] Calculate the weighted sum average of the strong association probability and the contradictory association probability to obtain the corrected probability of the risk type; optionally, the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types;
[0184] All risk types are sorted from high to low according to the corrected probability to obtain a type sequence;
[0185] All risk types whose first preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
[0186] It can be seen that through the above-mentioned optional embodiments, the strongly associated risks and contradictory risks of each risk can be screened out based on the preset risk strong association rules and risk contradiction rules, and the risk prediction probability can be reasonably and effectively corrected based on these correlations to obtain a more accurate risk probability, which can improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0187] As an optional embodiment, the specific manner in which the determination module calculates the strong correlation probability corresponding to the risk type according to the first risk type and the risk prediction probability of the risk type includes:
[0188] calculating a first weight proportional to the total number of types of all first risk types;
[0189] Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold;
[0190] calculating a second weight proportional to the average of the risk prediction probabilities of all high probability risks;
[0191] The risk prediction probability of the risk type is calculated by multiplying the first weight and the second weight to obtain the strong association probability corresponding to the risk type.
[0192] It can be seen that through the above-mentioned optional embodiments, the correction weight can be determined based on the total number of types of the first risk type and the probability average of the high-probability risks therein, and the risk prediction probability can be reasonably and effectively corrected based on the correction weight to obtain a more accurate strong correlation probability, which can subsequently improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0193] As an optional embodiment, the specific manner in which the determination module calculates the probability of conflict association corresponding to the risk type according to the second risk type and the risk prediction probability of the risk type includes:
[0194] calculating a third weight inversely proportional to the total type quantity of all second risk types;
[0195] Screen out all strongly contradictory risks of the second risk type whose probability difference is greater than a preset second probability threshold;
[0196] Calculating a fourth weight that is inversely proportional to the average of the risk prediction probabilities of all strongly contradictory risks;
[0197] The risk prediction probability of the risk type is calculated by multiplying the third weight and the fourth weight to obtain the conflict association probability corresponding to the risk type.
[0198] It can be seen that through the above-mentioned optional embodiments, the correction weight can be determined based on the total number of risk types and the average probability of risks with a higher degree of conflict, and the risk prediction probability can be reasonably and effectively corrected based on the correction weight to obtain a more accurate probability of conflict association, which can subsequently improve the accuracy and efficiency of risk prediction for the current route, improve navigation stability and safety, and reduce the occurrence of accidents.
[0199] For example 3, please refer to Figure 3 , Figure 3 It is another nautical chart data risk monitoring system based on multi-model linkage disclosed in an embodiment of the present invention. Figure 3 The described nautical chart data risk monitoring system based on multi-model linkage is applied to a data processing system / data processing device / data processing server (wherein the server includes a local processing server or a cloud processing server). Figure 3 As shown, the chart data risk monitoring system based on multi-model linkage may include:
[0200] A memory 301 storing executable program codes;
[0201] a processor 302 coupled to the memory 301;
[0202] The processor 302 calls the executable program code stored in the memory 301 to execute the steps of the method for risk monitoring of nautical chart data based on multi-model linkage described in the first embodiment.
[0203] Embodiment 4, the embodiment of the present invention discloses a computer-readable storage medium, which stores a computer program for electronic data exchange, wherein the computer program enables a computer to execute the steps of the method for risk monitoring of nautical chart data based on multi-model linkage described in embodiment 1.
[0204] Embodiment 5, the embodiment of the present invention discloses a computer program product, which includes a non-transitory computer-readable storage medium storing a computer program, and the computer program is operable to enable a computer to execute the steps of the method for risk monitoring of nautical chart data based on multi-model linkage described in Embodiment 1.
[0205] The above describes specific embodiments of the present specification, and other embodiments are within the scope of the appended claims. In some cases, the actions or steps recorded in the claims can be performed in an order different from that in the embodiments and still achieve the desired results. In addition, the processes depicted in the accompanying drawings do not necessarily have to be performed in the specific order or sequential order shown to achieve the desired results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
[0206] The systems, devices, modules or units described in the above embodiments may be implemented by computer chips or entities, or by products with certain functions. A typical implementation device is a computer. Specifically, the computer may be, for example, a personal computer, a laptop computer, a cellular phone, a camera phone, a smart phone, a personal digital assistant, a media player, a navigation device, an email device, a game console, a tablet computer, a wearable device, or a combination of any of these devices.
[0207] For the convenience of description, the above device is described in various units according to their functions. Of course, when implementing this specification, the functions of each unit can be implemented in the same or multiple software and / or hardware.
[0208] Those skilled in the art will appreciate that the embodiments of this specification may be provided as methods, systems, or computer program products. Therefore, the embodiments of this specification may be in the form of complete hardware embodiments, complete software embodiments, or embodiments in combination with software and hardware. Moreover, the embodiments of this specification may be in the form of a computer program product implemented in one or more computer-usable storage media (including but not limited to disk storage, CD-ROM, optical storage, etc.) that contain computer-usable program code.
[0209] This specification is described with reference to the flowcharts and / or block diagrams of the methods, devices (systems), and computer program products according to the embodiments of this specification. It should be understood that each process and / or box in the flowchart and / or block diagram, as well as the combination of the processes and / or boxes in the flowchart and / or block diagram, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general-purpose computer, a special-purpose computer, an embedded processor, or other programmable data processing device to produce a machine, so that the instructions executed by the processor of the computer or other programmable data processing device generate instructions for implementing the processes in the flowchart and / or block diagram. Figure 1 A process or multiple processes and / or boxes Figure 1 A device that provides the functions specified in a block or multiple blocks.
[0210] These computer program instructions may also be stored in a computer-readable memory capable of directing a computer or other programmable data processing device to operate in a specific manner, so that the instructions stored in the computer-readable memory produce an article of manufacture comprising an instruction device, which implements the process Figure 1 A process or multiple processes and / or boxes Figure 1 A function specified in one or more boxes.
[0211] These computer program instructions can also be loaded onto a computer or other programmable data processing device so that a series of operating steps are executed on the computer or other programmable device to produce a computer-implemented process, thereby providing instructions for implementing the process. Figure 1 A process or multiple processes and / or boxes Figure 1 The steps for the functions specified in one or more boxes.
[0212] In a typical configuration, a computing device includes one or more processors (CPU), input / output interfaces, network interfaces, and memory.
[0213] The memory may include non-permanent storage in a computer-readable medium, random access memory (RAM) and / or non-volatile memory in the form of read-only memory (ROM) or flash RAM. The memory is an example of a computer-readable medium.
[0214] Computer readable media include permanent and non-permanent, removable and non-removable media that can be implemented by any method or technology to store information. Information can be computer readable instructions, data structures, program modules or other data. Examples of computer storage media include, but are not limited to, phase change memory (PRAM), static random access memory (SRAM), dynamic random access memory (DRAM), other types of random access memory (RAM), read-only memory (ROM), electrically erasable programmable read-only memory (EEPROM), flash memory or other memory technology, compact disk read-only memory (CD-ROM), digital versatile disk (DVD) or other optical storage, magnetic cassettes, magnetic disk storage or other magnetic storage devices or any other non-transmission media that can be used to store information that can be accessed by a computing device. As defined herein, computer readable media does not include temporary computer readable media (transitory media), such as modulated data signals and carrier waves.
[0215] It should also be noted that the terms "include", "comprises" or any other variations thereof are intended to cover non-exclusive inclusion, so that a process, method, commodity or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, commodity or device. In the absence of more restrictions, the elements defined by the sentence "comprises a ..." do not exclude the existence of other identical elements in the process, method, commodity or device including the elements.
[0216] This specification may be described in the general context of computer-executable instructions executed by a computer, such as program modules. Generally, program modules include routines, programs, objects, components, data structures, etc. that perform specific tasks or implement specific abstract data types. This specification may also be practiced in distributed computing environments where tasks are performed by remote processing devices connected through a communication network. In a distributed computing environment, program modules may be located in local and remote computer storage media, including storage devices.
[0217] Each embodiment in this specification is described in a progressive manner, and the same or similar parts between the embodiments can be referred to each other, and each embodiment focuses on the differences from other embodiments. In particular, for the system embodiment, since it is basically similar to the method embodiment, the description is relatively simple, and the relevant parts can be referred to the partial description of the method embodiment.
[0218] Finally, it should be noted that the method and system for risk monitoring of nautical chart data based on multi-model linkage disclosed in the embodiment of the present invention only discloses a preferred embodiment of the present invention, which is only used to illustrate the technical solution of the present invention, rather than to limit it. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that the technical solutions recorded in the aforementioned embodiments can still be modified, or some of the technical features therein can be replaced by equivalents. However, these modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention.
Claims
1. A chart data risk monitoring method based on multi-model linkage, characterized in that: The method comprises: When the target ship is sailing in the target sea area, obtaining the nautical chart data of the target sea area and the current route of the target ship; Filtering the data in the nautical chart data according to the current route to obtain route nautical chart data; Inputting the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data, including: For each risk type, according to the correspondence between the preset risk type and the data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk types are the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing; Inputting the risk-related data into a neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including a plurality of training risk-related data and corresponding risk annotations; According to the multiple risk prediction results and the preset risk association correction rules, a final risk prediction result corresponding to the current route is determined, including: For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all the risk types; calculating a first weight proportional to the total number of all the first risk types; Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold; calculating a second weight proportional to an average value of the risk prediction probabilities of all the high probability risks; Calculate the risk prediction probability of the risk type and the product of the first weight and the second weight to obtain a strong association probability corresponding to the risk type; According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to contradictory types are screened from all the risk types; wherein the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold; calculating a third weight inversely proportional to the total number of all the second risk types; Screening out all strongly contradictory risks in the second risk type whose probability difference is greater than a preset second probability threshold; Calculating a fourth weight inversely proportional to an average value of the risk prediction probabilities of all the strong conflicting risks; Calculate the risk prediction probability of the risk type and the product of the third weight and the fourth weight to obtain the conflict association probability corresponding to the risk type; Calculate a weighted average of the strong association probability and the contradictory association probability to obtain a corrected probability of the risk type; wherein the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types; Sorting all the risk types from high to low according to the corrected probabilities to obtain a type sequence; All risk types that are a preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
2. The method for risk monitoring of nautical chart data based on multi-model linkage according to claim 1 is characterized in that: The filtering of the data in the nautical chart data according to the current route to obtain the route nautical chart data includes: Determine a route passing area corresponding to the current route; Determine a route time interval corresponding to the current route; The data in the nautical chart data whose corresponding position is within the area where the route passes and whose data time information is within the time interval of the route are screened out to be determined as the route nautical chart data.
3. The method for risk monitoring of nautical chart data based on multi-model linkage according to claim 2 is characterized in that: The determining of the route passing area corresponding to the current route includes: Inputting the chart data into a trained deviation risk prediction neural network to obtain a deviation risk value corresponding to the current route; the deviation risk prediction neural network is trained by a training data set including a plurality of training chart data and corresponding navigation deviation annotations; calculating a range weight proportional to the yaw risk value; Calculating the product of the range weight and the preset range distance value to obtain a corrected range distance value; The portion of the current route within the target sea area is used as a basic line segment, a circle is drawn at each point on the basic line segment with the correction range distance value as the diameter, and the union of all the circles is calculated to obtain the route passing area.
4. The method for risk monitoring of nautical chart data based on multi-model linkage according to claim 2 is characterized in that: The determining the route time interval corresponding to the current route includes: Determine a plurality of other similar sea areas similar to the target sea area; the regional similarity between the other similar sea areas and the target sea area is greater than a preset similarity threshold; the regional similarity is the product of the regional obstacle similarity and the regional weather similarity; the regional obstacle similarity is the similarity between the obstacle area distributions in the nautical chart data of the two sea areas; the regional weather similarity is the similarity between the weather forecast data when the target ship passes by in the nautical chart data of the two sea areas; Obtaining the navigation speed of the target ship when passing through each of the other similar sea areas during the historical time period; Calculating the average value of all the sailing speeds to obtain the predicted speed of the target ship; Determine the ratio of the route length of the current route in the target sea area to the predicted speed to obtain the predicted route time; The route time interval is determined by taking the current time point as the starting point and the predicted route time as the length of the time interval.
5. A chart data risk monitoring system based on multi-model linkage, characterized in that: The system comprises: An acquisition module, used for acquiring the nautical chart data of the target sea area and the current route of the target ship when the target ship is sailing in the target sea area; A screening module, used for screening the data in the chart data according to the current route to obtain the route chart data; A prediction module is used to input the route chart data into a plurality of prediction algorithm models corresponding to different risk types to obtain a plurality of risk prediction results corresponding to the route chart data, including: For each risk type, according to the correspondence between the preset risk type and the data type, the risk-related data corresponding to the risk type in the route chart data are screened out; the risk types are the risk of running aground, the risk of hull damage, the risk of failure in hot weather, the risk of failure in heavy rain, the risk of capsizing in big waves, the risk of hitting an iceberg, or the risk of turning sharply in low visibility and capsizing; Inputting the risk-related data into a neural network prediction model corresponding to the risk type to obtain the risk prediction probability of the route chart data corresponding to the risk type; the neural network prediction model is trained by a training data set including a plurality of training risk-related data and corresponding risk annotations; A determination module, used to determine the final risk prediction result corresponding to the current route according to the multiple risk prediction results and a preset risk association correction rule, including: For each risk type, according to a preset risk strong association rule, a plurality of first risk types belonging to a strongly associated type corresponding to the risk type are determined from all the risk types; calculating a first weight proportional to the total number of all the first risk types; Screen out all high-probability risks of the first risk type whose predicted risk probability is greater than a preset first probability threshold; calculating a second weight proportional to an average value of the risk prediction probabilities of all the high probability risks; Calculate the risk prediction probability of the risk type and the product of the first weight and the second weight to obtain a strong association probability corresponding to the risk type; According to a preset risk contradiction rule, a plurality of second risk types corresponding to the risk type and belonging to contradictory types are screened from all the risk types; wherein the second risk type and the risk type are in a contradictory relationship in the risk contradiction rule and the probability difference between the risk prediction probabilities of the two is greater than a preset difference threshold; calculating a third weight inversely proportional to the total number of all the second risk types; Screening out all strongly contradictory risks in the second risk type whose probability difference is greater than a preset second probability threshold; Calculating a fourth weight inversely proportional to an average value of the risk prediction probabilities of all the strong conflicting risks; Calculate the risk prediction probability of the risk type and the product of the third weight and the fourth weight to obtain the conflict association probability corresponding to the risk type; Calculate a weighted average of the strong association probability and the contradictory association probability to obtain a corrected probability of the risk type; wherein the calculation weight corresponding to the strong association probability is proportional to the number of all first risk types, and the calculation weight corresponding to the contradictory association probability is proportional to the number of all second risk types; Sorting all the risk types from high to low according to the corrected probabilities to obtain a type sequence; All risk types that are a preset number in the type sequence and whose corrected probabilities are greater than a preset probability threshold are determined as predicted risks corresponding to the current route.
6. A risk monitoring system for nautical chart data based on multi-model linkage, characterized in that: The system comprises: A memory storing executable program code; a processor coupled to the memory; The processor calls the executable program code stored in the memory to execute the chart data risk monitoring method based on multi-model linkage as described in any one of claims 1-4.
