Generative north pole channel daily navigation risk prediction method and device and medium

Abstract

The invention discloses a generative arctic waterway daily navigation risk prediction method and device and a medium, and the method comprises the steps: constructing a historical daily navigation risk data set of an arctic waterway according to historical daily environment data and navigation ship parameters; according to the historical daily navigation risk data set, constructing a generative daily navigation risk monthly covariance forecasting model; constructing a monthly navigation risk forecasting model according to the historical daily navigation risk data set and the navigation ship parameters; according to the generative daily navigation risk monthly covariance forecasting model and the timestamp information, generating a daily navigation risk monthly covariance in a corresponding month; and generating a daily navigation risk value of the navigation risk in the prediction time window through the monthly navigation risk prediction model and the daily navigation risk monthly covariance. The method can achieve the prediction of the long-term North Navigation risk, reduces the cost of North Navigation risk prediction, and can be widely used in the technical field of ship navigation safety.

Description

Technical Field

[0001] The present invention relates to the field of ship navigation safety technology, and in particular to a generative method, device and medium for predicting daily navigation risks of an Arctic waterway. Background Art

[0002] The Arctic route is a short path connecting the Atlantic and Pacific Oceans. Affected by environmental factors such as sea ice density and thickness, ships often face higher risks when sailing in the Arctic route. Traditional time series models and deep learning models are usually used to predict navigation risks. However, in the long-term navigation risk prediction with a daily frequency, traditional time series models have limitations in dealing with long-term dependencies and cannot handle long-term forecasting tasks, while models based on deep learning face problems of model complexity and computational cost. Summary of the invention

[0003] In view of this, the main purpose of the embodiments of the present invention is to provide a generative method, device and medium for predicting daily navigation risks of Arctic waterways, in order to solve at least one problem of the prior art. The present invention can realize the prediction of long-term Arctic navigation risks and reduce the cost of predicting Arctic navigation risks.

[0004] To achieve the above-mentioned purpose, an embodiment of the present invention provides a generative method for predicting the daily navigation risk of the Arctic route, the method comprising the following steps:

[0005] Obtain historical daily environmental data of the Arctic route and the parameters of ships sailing on the Arctic route;

[0006] Constructing a historical daily navigation risk dataset for the Arctic route based on the historical daily environmental data and the navigable ship parameters;

[0007] Based on the historical daily navigation risk data set, a generative daily navigation risk monthly covariance forecasting model is constructed;

[0008] Constructing and training a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters;

[0009] Generate the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and timestamp information;

[0010] According to the monthly information of the risk forecast time window, the daily navigation risk value of the navigation risk in the prediction time window is generated through the monthly navigation risk forecast model and the monthly covariance of the daily navigation risk.

[0011] In some embodiments, constructing a historical daily navigation risk dataset for the Arctic route based on the historical daily environmental data and the navigable ship parameters comprises the following steps:

[0012] Constructing a daily navigation risk assessment model based on the historical daily environmental data and the navigable ship parameters;

[0013] According to the daily navigation risk assessment model, the historical daily navigation risk dataset of the Arctic route is constructed.

[0014] In some embodiments, constructing a daily navigation risk assessment model based on the historical daily environmental data and the navigation ship parameters comprises the following steps:

[0015] Discretizing the historical daily environmental data to obtain environmental risk factors at various risk levels;

[0016] Obtaining a ship risk index result according to the historical daily environmental data and the navigable ship parameters;

[0017] Discretizing the ship risk index result to obtain the ship navigation risk of each risk level;

[0018] The daily navigation risk assessment model is constructed based on the environmental risk factors and the ship navigation risk.

[0019] In some embodiments, constructing the historical daily navigation risk dataset of the Arctic route according to the daily navigation risk assessment model comprises the following steps:

[0020] Obtaining assessment indicators according to the daily navigation risk assessment model;

[0021] The evaluation indicators are integrated through subjective and objective weighting methods to generate a comprehensive navigation risk value;

[0022] The historical daily navigation risk data set is constructed according to the comprehensive navigation risk value.

[0023] In some embodiments, constructing a generative daily navigation risk monthly covariance prediction model based on the historical daily navigation risk dataset comprises the following steps:

[0024] Constructing a daily navigation risk covariance dataset for each month based on the historical daily navigation risk dataset;

[0025] The generative daily navigation risk monthly covariance prediction model is constructed based on the daily navigation risk covariance dataset.

[0026] In some embodiments, constructing and training a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters comprises the following steps:

[0027] Constructing a historical monthly navigation risk dataset for the Arctic route based on the historical daily navigation risk dataset;

[0028] The monthly navigation risk prediction model is constructed and trained based on the historical monthly navigation risk data set and the navigable ship parameters.

[0029] In some embodiments, the method of generating a daily navigation risk value for the navigation risk in the prediction time window according to the monthly information of the risk prediction time window through the monthly navigation risk prediction model and the monthly covariance of the daily navigation risk comprises the following steps:

[0030] According to the monthly information of the risk forecast time window, the monthly navigation risk forecast model is used to predict the navigation risk on the first day of each month, the navigation risk in the middle of each month, and the navigation risk at the end of each month within the time window;

[0031] According to the first-day navigation risk, the mid-month navigation risk and the monthly covariance of the daily navigation risk, the daily navigation risk value of the navigation risk within the prediction time window is generated through the Gaussian process regression method.

[0032] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides a generative device for predicting daily navigation risks of Arctic waterways, the device comprising:

[0033] The first module is used to obtain historical daily environmental data of the Arctic route and the parameters of ships sailing on the Arctic route;

[0034] The second module is used to construct a historical daily navigation risk data set for the Arctic route based on the historical daily environmental data and the navigable ship parameters;

[0035] The third module is used to construct a generative daily navigation risk monthly covariance forecast model based on the historical daily navigation risk data set;

[0036] The fourth module is used to construct and train a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters;

[0037] The fifth module is used to generate the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and the timestamp information;

[0038] The sixth module is used to generate a daily navigation risk value for the navigation risk within the prediction time window according to the monthly information of the risk prediction time window, through the monthly navigation risk prediction model and the monthly covariance of the daily navigation risk.

[0039] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides an electronic device, which includes a memory and a processor, wherein the memory stores a computer program, and when the processor executes the computer program, it implements the aforementioned generative method for predicting daily navigation risks of Arctic routes.

[0040] To achieve the above-mentioned purpose, another aspect of an embodiment of the present invention provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the aforementioned generative method for predicting daily navigation risks of Arctic routes is implemented.

[0041] To achieve the above object, another aspect of an embodiment of the present invention provides a computer program product or a computer program, the computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the aforementioned generative method for predicting daily navigation risks of Arctic routes.

[0042] The embodiments of the present invention include at least the following beneficial effects: the present invention provides a generative method, device and medium for predicting daily navigation risk of Arctic waterways, which constructs a historical daily navigation risk data set of Arctic waterways through historical data; constructs a generative daily navigation risk monthly covariance prediction model based on the historical daily navigation risk data set; constructs and trains a monthly navigation risk prediction model based on the historical daily navigation risk data set and navigable ship parameters; generates the monthly covariance of daily navigation risk in each month based on the generative daily navigation risk monthly covariance prediction model and timestamp information; generates the daily navigation risk value of navigation risk within the prediction time window through the monthly navigation risk prediction model and the daily navigation risk monthly covariance based on the risk prediction time window month information. The embodiments of the present invention can realize the prediction of long-term Arctic navigation risk and reduce the cost of Arctic navigation risk prediction. BRIEF DESCRIPTION OF THE DRAWINGS

[0043] 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.

[0044] Figure 1 It is a flow chart of a generative method for predicting daily navigation risks of Arctic waterways provided by an embodiment of the present invention;

[0045] Figure 2 It is a schematic structural diagram of a generative Arctic waterway daily navigation risk prediction device provided by an embodiment of the present invention;

[0046] Figure 3 It is a schematic diagram of the hardware structure of an electronic device provided by an embodiment of the present invention. DETAILED DESCRIPTION

[0047] In order to make the purpose, technical solution and advantages of the present invention more clearly understood, the present invention is further described in detail below in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present invention and are not intended to limit the present invention. The embodiments described in the following exemplary embodiments do not represent all embodiments consistent with the embodiments of the present invention, and they are only examples of devices and methods consistent with some aspects of the embodiments of the present invention as detailed in the attached claims.

[0048] It should be noted that, although the functional modules are divided in the system schematic diagram and the logical order is shown in the flow chart, in some cases, the steps shown or described may be performed in a different order than the module division in the system or the flow chart. The terms "first / S100" and "second / S200" in the specification and claims and the above-mentioned drawings may be used to describe various concepts in this article, but unless otherwise specified, these concepts are not limited by these terms. These terms are only used to distinguish one concept from another. For example, without departing from the scope of the embodiment of the present invention, the first information may also be referred to as the second information, and similarly, the second information may also be referred to as the first information. Depending on the context, the words "if" and "if" as used herein may be interpreted as "at the time of" or "when" or "in response to determination".

[0049] The terms "at least one", "multiple", "each", "any", etc. used in the present invention, at least one includes one, two or more, multiple includes two or more, each refers to each of the corresponding multiple, and any refers to any one of the multiple.

[0050] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as those commonly understood by those skilled in the art to which the present invention belongs. The terms used herein are only for the purpose of describing the embodiments of the present invention and are not intended to limit the present invention.

[0051] Before describing the embodiments of the present application in detail, some nouns and terms involved in the embodiments of the present application are first described. The nouns and terms involved in the embodiments of the present application are subject to the following explanations.

[0052] The Polar Operational Limit Assessment Risk Indexing System (POLARIS) is a method used to assess the operational risk of ships in polar ice areas and to determine the operational limits of ships in specific ice conditions. The system takes into account the ship's ice class, ice conditions, operating mode and environmental factors to ensure the safe navigation of ships in polar waters.

[0053] At present, the prediction of navigation risks usually adopts traditional time series models and deep learning models. However, in the long-term navigation risk prediction with a daily frequency, the traditional time series model has limitations in dealing with long-term dependencies and cannot handle long-term forecasting tasks, while the model based on deep learning faces the problems of model complexity and computational cost.

[0054] In view of this, if Figure 1 As shown, an embodiment of the present invention provides a generative method for predicting daily navigation risks of Arctic waterways, which may include but is not limited to steps S100 to S600:

[0055] Step S100, obtaining historical daily environmental data of the Arctic route and parameters of ships passing through the Arctic route;

[0056] Step S200, constructing a historical daily navigation risk dataset of the Arctic route based on the historical daily environmental data and the navigable ship parameters;

[0057] Step S300, constructing a generative daily navigation risk monthly covariance prediction model based on the historical daily navigation risk data set;

[0058] Step S400, constructing and training a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters;

[0059] Step S500, generating the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and timestamp information;

[0060] Step S600, based on the monthly information of the risk forecast time window, the monthly navigation risk forecast model and the monthly covariance of the daily navigation risk are used to generate a daily navigation risk value for the navigation risk within the forecast time window.

[0061] In step S100 of some embodiments, historical daily environmental data of the Arctic route and parameters of navigable ships on the Arctic route are obtained, wherein the historical daily environmental data of the Arctic route may include but are not limited to sea ice density, sea ice thickness, sea ice type, sea ice drift speed, sea surface temperature, sea surface wind speed, sea surface air pressure, etc.; the parameters of navigable ships on the Arctic route may include but are not limited to ship ice class, ship main dimensions, draft, etc.

[0062] In some embodiments, step S200 may include but is not limited to steps S210 to S220:

[0063] Step S210, constructing a daily navigation risk assessment model based on the historical daily environmental data and the navigation ship parameters;

[0064] Step S220: constructing the historical daily navigation risk dataset of the Arctic route according to the daily navigation risk assessment model.

[0065] In some embodiments, step S210 may include but is not limited to steps S211 to S214:

[0066] Step S211, discretizing the historical daily environmental data to obtain environmental risk factors of each risk level;

[0067] Step S212, obtaining a ship risk index result according to the historical daily environmental data and the navigable ship parameters;

[0068] Step S213, discretizing the ship risk index result to obtain the ship navigation risk of each risk level;

[0069] Step S214: constructing the daily navigation risk assessment model according to the environmental risk factors and the ship navigation risk.

[0070] In step S211 of some embodiments, the collected historical daily environmental data of the Arctic route is discretized to classify the historical daily environmental data into different risk levels, thereby obtaining environmental risk factors of different risk levels.

[0071] In steps S212 to S213 of some embodiments, the ship risk index is calculated based on POLARIS according to the ship ice class in the navigable ship parameters and the sea ice density and sea ice type in the historical daily environmental data to obtain the ship risk index result, and the ship risk index result is discretized to divide different risk levels to obtain the ship navigation risks of different risk levels. Exemplarily, the calculation formula of the ship risk index is as follows:

[0072] RIOV =∑C α ×RV V，α

[0073] In the formula, RIO V Represents the risk of navigation for ships of Class V ice class; C α Represents the density of type α sea ice; RV V，α Represents the risk index value (RV) for a V-class ice-class ship sailing in an area covered by α-class sea ice.

[0074] In step S214 of some embodiments, a risk matrix is ​​constructed by combining environmental risk factors and ship navigation risks of various risk levels, that is, a daily navigation risk assessment model is constructed. The rows of the risk matrix represent the ship navigation risk levels of different ship ice classes; the columns of the risk matrix represent different environmental risk factors; and each unit in the risk matrix represents a risk value under a specific environment and a specific ship navigation risk level.

[0075] In some embodiments, step S220 may include but is not limited to steps S221 to S223:

[0076] Step S221, obtaining an assessment index according to the daily navigation risk assessment model;

[0077] Step S222, integrating the evaluation indicators by subjective and objective weighting method to generate a comprehensive navigation risk value;

[0078] Step S223: constructing the historical daily navigation risk data set according to the comprehensive navigation risk value.

[0079] In step S220 of some embodiments, the discretized historical daily environmental data and the discretized ship risk index results in the daily navigation risk assessment model are obtained, and the discretized historical daily environmental data and the ship risk index results are integrated through the subjective and objective weighting method to generate a comprehensive navigation risk value. By combining the various comprehensive navigation risk values, a historical daily navigation risk data set can be obtained. Exemplarily, the expression of the comprehensive navigation risk value is:

[0080]

[0081] In the formula, Risk represents the navigation risk value of ships; w i Represents the indicator weight; d i represents the index value; i represents the index number, and N represents the total number of indicators. Optionally, the index value is obtained by dividing the discretized historical daily environmental data into 10 levels, thereby corresponding to the risk values ​​of the ship risk index results of levels 1-10.

[0082] In some embodiments, the subjective and objective weighting method is a weight determination method that combines subjective judgment and objective data, and can include subjective weighting method and objective weighting method. Among them, the subjective weighting method can determine the importance of indicators by scoring or grading, such as the analytic hierarchy process (AHP) by establishing a hierarchical model, constructing a pair comparison matrix, and calculating eigenvalues ​​and eigenvectors to determine the weights. In addition, the objective weighting method is based on the indicator data information, and the weights are determined by mathematical deduction, which is not affected by subjective judgment. For example, the entropy method uses the entropy information of the data, that is, the amount of information, to calculate the weights.

[0083] In some embodiments, step S300 may include but is not limited to steps S310 to S320:

[0084] Step S310, constructing a daily navigation risk covariance dataset for each month based on the historical daily navigation risk dataset;

[0085] Step S320: constructing the generative daily navigation risk monthly covariance prediction model based on the daily navigation risk covariance data set.

[0086] In step S310 of some embodiments, based on the historical daily navigation risk data set, a daily navigation risk covariance data set for each month can be calculated and constructed. Exemplarily, based on the historical daily navigation risk data set, the navigation risk covariance ∑ between the first day to the last day of each month is calculated in units of natural months, and the navigation risk covariance of each month in the historical year is collected by month to form a daily navigation risk covariance data set for each month. Among them, the expression of the navigation risk covariance between the first day to the last day of each month is:

[0087]

[0088] In the formula, Cov i，j =E((x i -E(x i ))(x j -E(x j )));

[0089] i=1,2,......,n;

[0090] j=1,2,……,n;

[0091] Among them, x i represents the navigation risk on the i-th day; x j represents the navigation risk on day j; Cov i，j represents the covariance of navigation risk between the i-th day and the j-th day; E(·) represents the expected value; and n represents the total number of days.

[0092] In step S320 of some embodiments, a generative daily navigation risk monthly covariance prediction model is constructed and trained based on the daily navigation risk covariance dataset of each month, with the daily date timestamp as input.

[0093] In some embodiments, a deep diffusion neural network model, i.e., a generative daily navigation risk monthly covariance prediction model, is determined by determining the step size of the noise addition and denoising process, noise parameters, and neural network structure; according to the daily date timestamp and the daily navigation risk covariance data set of each month, each data in the daily navigation risk covariance data set of each month is converted into a single-channel grayscale image with a size of 31×31, and then divided into a training set, a test set, and a validation set; the deep diffusion neural network model is trained using the training set, and when the deep diffusion neural network model meets the constraint target termination condition, the model training task is completed.

[0094] For example, the generative daily navigation risk monthly covariance forecast model can be divided into two layers, wherein the first layer performs the denoising and noise addition process, each of which is divided into T steps, and the second layer is a neural network between the t-th step and the t-1-th step in the first layer, such as a U-net network. In the denoising process, the noise in the t-th step is an expected value of The variance is Gaussian distribution in, is a hyperparameter, x0 is the sample value of the navigation risk covariance, x t is the covariance value after adding noise in the tth step, and I is the unit matrix. In the denoising process, the noise removed in the tth step is an expected The variance is Gaussian distribution, where α t , α t-1 , β t are the hyperparameters of each diffusion network, and θ is the parameter to be learned by the U-net network, that is, the variance of each denoising step. Next, the generative daily navigation risk monthly covariance forecast model is trained based on the training set data. During the denoising process, the parameters in each denoising step are learned through the U-net network. When the generative daily navigation risk monthly covariance forecast model meets the constraint target termination condition, the model training task is completed.

[0095] In some embodiments, step S400 may include but is not limited to steps S410 to S420:

[0096] Step S410, constructing a historical monthly navigation risk dataset for the Arctic route based on the historical daily navigation risk dataset;

[0097] Step S420, constructing and training the monthly navigation risk prediction model based on the historical monthly navigation risk data set and the navigable ship parameters.

[0098] In step S400 of some embodiments, based on the historical daily navigation risk dataset, the navigation risks on the first day and the middle of each month are selected according to the timestamp to construct a historical monthly navigation risk dataset for the Arctic route. Based on the historical monthly navigation risk dataset for the Arctic route, a monthly navigation risk forecasting model can be constructed and trained.

[0099] For example, the historical monthly navigation risk data of the Arctic route is represented in the form of a time series, for example, 2 data per month, and the cumulative sequence length for 30 years is 720 steps. Then, a seasonal autoregressive integrated moving average model, i.e., a monthly navigation risk forecast model, can be constructed. Then, based on the historical monthly navigation risk data set, the seasonal autoregressive integrated moving average model is trained, and the expected maximum method is used to determine the unknown coefficients. Among them, the expression of the seasonal autoregressive integrated moving average model is:

[0100]

[0101] In the formula, φ p (L) represents the trend-related polynomial fitting term; represents the seasonal correlation polynomial fitting term; Δ d represents the trend-related difference term; represents the seasonal difference term; y t represents the navigation risk corresponding to time t; A(t) represents the time-related fitting term; θ q (L) represents the trend-related error polynomial fitting term; represents the seasonally related error polynomial fitting term; ζ t Represents the navigation risk error corresponding to time t.

[0102] In step S500 of some embodiments, the monthly covariance of daily navigation risk in the corresponding month can be generated according to the trained generative daily navigation risk monthly covariance forecast model and timestamp information. Exemplarily, the timestamp information is obtained according to the forecast time window. For example, to forecast the navigation risk in the next five months, the timestamp should be from May 1 to May 31. The timestamp is input into the trained generative daily navigation risk monthly covariance forecast model, and the parameters of each step in the denoising process are inferred, starting from pure noise of 31×31 dimensions, and denoising sampling is performed to generate the monthly covariance of daily navigation risk in the corresponding month.

[0103] In some embodiments, step S600 may include but is not limited to steps S610 to S620:

[0104] Step S610, according to the monthly information of the risk forecast time window, the navigation risk of the first day of each month, the navigation risk of the middle of each month and the navigation risk of the end of each month within the time window are predicted by the monthly navigation risk forecast model;

[0105] Step S620, generating a daily navigation risk value of the navigation risk within the prediction time window through a Gaussian process regression method according to the first-day navigation risk, the mid-month navigation risk and the monthly covariance of the daily navigation risk.

[0106] In step S600 of some embodiments, the time window to be forecasted is obtained, for example, the monthly navigation risk in the next May-June is forecasted, that is, the navigation risk of May 1, May 15, May 31, June 1, June 15, and June 30 is forecasted, and a total of 6 steps are forecasted. Optionally, since May 31 and June 1 are two adjacent days, one can choose to forecast one of the two adjacent days, that is, forecast the navigation risk of May 1, May 15, May 31, June 15, and June 30, and a total of 5 steps are forecasted; or the navigation risk of May 1, May 15, June 1, June 15, and June 30 is forecasted, and a total of 5 steps are forecasted. According to the monthly navigation risk forecast model and the forecast time window, the sampling expectation maximum method is used to forecast the monthly navigation risk, and the navigation risk of the first day of each month, the navigation risk of the middle of each month, and the navigation risk of the end of each month can be obtained within the time window. According to the predicted navigation risk of the first day of each month, the navigation risk of the middle of each month, and the navigation risk of the end of each month, the generated daily navigation risk monthly covariance is used, and the Gaussian process regression method is used to generate the daily navigation risk value within the forecast time window except for the first day, the middle of each month, and the end of each month. Then, the navigation risk of the first day of each month, the navigation risk of the middle of each month, and the navigation risk of the end of each month in the time window are combined to obtain the daily navigation risk value of the navigation risk within the final forecast time window.

[0107] For example, in the first step, the navigation risk predicted on the first day and the middle of the forecast month window is recorded as a sample, recorded as X1, and the corresponding expectation is recorded as μ1; the navigation risk to be predicted on the remaining days of the corresponding month is recorded as X2, the corresponding expectation is recorded as μ2, and the covariance is recorded as Among them, μ2 is the mean of historical data corresponding to the timestamp date;

[0108] The second step is to modify μ2 and ∑2 according to the sample data, and then we have the following expression:

[0109]

[0110] In the formula, μ 2|1 Represents the expectation of the corrected navigation risk X2 to be predicted under the condition of a given prediction sample X1; ∑ 11represents the covariance between X1 and X1 itself; ∑ 12 ,∑ 21 represents the covariance between X1 and X2; ∑ 22 represents the covariance between X2 and X2 itself; ∑ 2|1 Represents the covariance of the corrected navigation risk X2 to be predicted under the condition of a given prediction sample X1.

[0111] The third step is to calculate the covariance ∑ 2|1 Perform singular value decomposition to obtain matrix U, matrix S, and matrix V;

[0112] The fourth step is to sample from the standard normal distribution to generate a number of random variables corresponding to the timestamp, denoted as y;

[0113] The fifth step is to sample the Gaussian process.

[0114] Step 6. Repeat steps 4 and 5 n times (n ≥ 100), take the average of the above n sampling times, and obtain the daily navigation risk value except for the first day and the middle of each month.

[0115] like Figure 2 As shown, the embodiment of the present invention further provides a generative Arctic waterway daily navigation risk prediction device 700, which can implement the above-mentioned generative Arctic waterway daily navigation risk prediction method, and the device includes:

[0116] The first module 701 is used to obtain historical daily environmental data of the Arctic route and parameters of ships passing through the Arctic route;

[0117] The second module 702 is used to construct a historical daily navigation risk data set for the Arctic route based on the historical daily environmental data and the navigable ship parameters;

[0118] The third module 703 is used to construct a generative daily navigation risk monthly covariance prediction model based on the historical daily navigation risk data set;

[0119] The fourth module 704 is used to construct and train a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters;

[0120] The fifth module 705 is used to generate the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and the timestamp information;

[0121] The sixth module 706 is used to generate a daily navigation risk value for the navigation risk within the prediction time window according to the monthly information of the risk prediction time window, through the monthly navigation risk prediction model and the monthly covariance of the daily navigation risk.

[0122] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0123] An embodiment of the present invention further provides an electronic device, the electronic device comprising a processor and a memory, the memory storing a computer program, and the processor implementing the above-mentioned generative method for predicting daily navigation risks of the Arctic route when executing the computer program. The electronic device may be any intelligent terminal including a tablet computer, a vehicle-mounted computer, etc.

[0124] It can be understood that the contents of the above method embodiments are all applicable to the present device embodiments, the functions specifically implemented by the present device embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0125] refer to Figure 3 , Figure 3 The hardware structure of an electronic device of another embodiment is illustrated, and the electronic device includes:

[0126] The processor 801 may be implemented by a general-purpose CPU (Central Processing Unit), a microprocessor, an application-specific integrated circuit (Application Specific Integrated Circuit, ASIC), or one or more integrated circuits, and is used to execute relevant programs to implement the technical solutions provided in the embodiments of the present invention;

[0127] The memory 802 can be implemented in the form of a read-only memory (ROM), a static storage device, a dynamic storage device, or a random access memory (RAM). The memory 802 can store an operating system and other application programs. When the technical solution provided in the embodiment of this specification is implemented by software or firmware, the relevant program code is stored in the memory 802, and the processor 801 calls and executes a generative Arctic route daily navigation risk prediction method according to an embodiment of the present invention;

[0128] Input / output interface 803, used to implement information input and output;

[0129] The communication interface 804 is used to realize the communication interaction between the device and other devices. The communication can be realized through a wired manner (such as USB, network cable, etc.) or a wireless manner (such as mobile network, WIFI, Bluetooth, etc.);

[0130] A bus 805 that transmits information between the various components of the device (e.g., the processor 801, the memory 802, the input / output interface 803, and the communication interface 804);

[0131] The processor 801 , the memory 802 , the input / output interface 803 and the communication interface 804 are connected to each other in communication within the device via a bus 805 .

[0132] An embodiment of the present invention further provides a computer-readable storage medium storing a computer program, which, when executed by a processor, implements the above-mentioned generative method for predicting daily navigation risks of Arctic waterways.

[0133] It can be understood that the contents of the above method embodiments are all applicable to the present storage medium embodiments, the functions specifically implemented by the present storage medium embodiments are the same as those of the above method embodiments, and the beneficial effects achieved are also the same as those achieved by the above method embodiments.

[0134] The embodiment of the present invention also provides a computer program product or a computer program, which includes computer instructions stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the aforementioned generative method for predicting daily navigation risks of Arctic routes.

[0135] In summary, the generative method, device and medium for predicting daily navigation risk of Arctic waterways according to the embodiments of the present invention have the following advantages:

[0136] 1. In view of the fact that the navigation environment such as sea ice in Arctic waterways changes rapidly and the navigation risk of ships is highly time-varying, the embodiment of the present invention evaluates historical navigation risks and forms daily and monthly navigation risk data sets based on historical environmental data and characteristics of navigable ships, thereby reflecting the daily and monthly evolution of the navigation risk of ships in the Arctic.

[0137] 2. The embodiment of the present invention conducts monthly navigation risk forecasting based on the monthly evolution law of historical navigation risk, thereby controlling the forecast step length within 7 steps, increasing the forecast confidence, and reducing the cost of Arctic navigation risk prediction. Then, taking the monthly navigation risk forecast value as the boundary, a covariance generation model is constructed based on the historical daily navigation risk covariance data set, and the covariance relationship between daily risks in the forecast month is inferred, and then the Gaussian process regression method is used to generate daily navigation risks in each forecast month.

[0138] 3. The embodiment of the present invention can realize the prediction of long-term Arctic navigation risks. On the basis of ensuring a high confidence level in the forecast risks for each month, it complies with the statistical laws of daily and monthly risk evolution, thereby realizing the assessment of daily waterway navigation risks, guiding the navigation of ships in the Arctic waterway, and improving the safety of ship navigation.

[0139] In some selectable embodiments, the function / operation mentioned in the block diagram may not occur in the order mentioned in the operation diagram. For example, depending on the function / operation involved, the two boxes shown in succession can actually be executed substantially simultaneously or the boxes can sometimes be executed in reverse order. In addition, the embodiment presented and described in the flow chart of the present invention is provided by way of example, for the purpose of providing a more comprehensive understanding of technology. The disclosed method is not limited to the operation and logic flow presented herein. Selectable embodiments are expected, wherein the order of various operations is changed and the sub-operation of a part for which is described as a larger operation is performed independently.

[0140] In addition, although the present invention is described in the context of functional modules, it should be understood that, unless otherwise specified, one or more of the functions and / or features described may be integrated into a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It is also understood that a detailed discussion of the actual implementation of each module is unnecessary for understanding the present invention. More specifically, in view of the properties, functions, and internal relationships of the various functional modules in the device disclosed herein, the actual implementation of the module will be understood within the conventional skills of the engineer. Therefore, those skilled in the art can implement the present invention set forth in the claims without excessive experimentation using ordinary techniques. It is also understood that the specific concepts disclosed are merely illustrative and are not intended to limit the scope of the present invention, which is determined by the full scope of the appended claims and their equivalents.

[0141] If the functions are implemented in the form of software functional units and sold or used as independent products, they can be stored in a computer-readable storage medium. Based on this understanding, the technical solution of the present invention, or the part that contributes to the prior art or the part of the technical solution, can be embodied in the form of a software product. The computer software product is stored in a storage medium, including several instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to perform all or part of the steps of the methods described in each embodiment of the present invention. The aforementioned storage medium includes: U disk, mobile hard disk, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory), disk or optical disk, etc., which can store program codes.

[0142] The logic and / or steps represented in the flowchart or otherwise described herein, for example, can be considered as an ordered list of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by an instruction execution system, device or apparatus (such as a computer-based system, a system including a processor, or other system that can fetch instructions from an instruction execution system, device or apparatus and execute instructions), or in conjunction with such instruction execution systems, devices or apparatuses. For the purposes of this specification, "computer-readable medium" can be any device that can contain, store, communicate, propagate or transmit a program for use by an instruction execution system, device or apparatus, or in conjunction with such instruction execution systems, devices or apparatuses.

[0143] More specific examples of computer-readable media (a non-exhaustive list) include the following: an electrical connection with one or more wires (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disk read-only memory (CDROM). In addition, the computer-readable medium may even be a paper or other suitable medium on which the program is printed, since the program may be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a computer memory.

[0144] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware or a combination thereof. In the above-mentioned embodiments, a plurality of steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0145] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" means that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representation of the above terms does not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described may be combined in any one or more embodiments or examples in a suitable manner.

[0146] Although the embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions and variations may be made to the embodiments without departing from the principles and spirit of the present invention, and that the scope of the present invention is defined by the claims and their equivalents.

[0147] The above is a specific description of the preferred implementation of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art may make various equivalent modifications or substitutions without violating the spirit of the present invention. These equivalent modifications or substitutions are all included in the scope defined by the claims of the present invention.

Claims

1. A generative method for predicting daily navigation risk of Arctic waterways, characterized in that: The following steps are involved: Obtain historical daily environmental data of the Arctic route and the parameters of ships sailing on the Arctic route; Constructing a historical daily navigation risk dataset for the Arctic route based on the historical daily environmental data and the navigable ship parameters; Based on the historical daily navigation risk data set, a generative daily navigation risk monthly covariance forecasting model is constructed; Constructing and training a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters; Generate the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and timestamp information; According to the monthly information of the risk forecast time window, the daily navigation risk value of the navigation risk in the prediction time window is generated through the monthly navigation risk forecast model and the monthly covariance of the daily navigation risk.

2. A generative method for predicting daily navigation risk of Arctic waterways according to claim 1, characterized in that: The step of constructing a historical daily navigation risk dataset for the Arctic route based on the historical daily environmental data and the navigable ship parameters comprises the following steps: Constructing a daily navigation risk assessment model based on the historical daily environmental data and the navigable ship parameters; According to the daily navigation risk assessment model, the historical daily navigation risk dataset of the Arctic route is constructed.

3. A generative method for predicting daily navigation risk of Arctic waterways according to claim 2, characterized in that: The method of constructing a daily navigation risk assessment model based on the historical daily environmental data and the navigation ship parameters includes the following steps: Discretizing the historical daily environmental data to obtain environmental risk factors at various risk levels; Obtaining a ship risk index result according to the historical daily environmental data and the navigable ship parameters; Discretizing the ship risk index result to obtain the ship navigation risk of each risk level; The daily navigation risk assessment model is constructed based on the environmental risk factors and the ship navigation risk.

4. A generative method for predicting daily navigation risk of Arctic waterways according to claim 2, characterized in that: The step of constructing the historical daily navigation risk dataset of the Arctic route according to the daily navigation risk assessment model comprises the following steps: Obtaining assessment indicators according to the daily navigation risk assessment model; The evaluation indicators are integrated through subjective and objective weighting methods to generate a comprehensive navigation risk value; The historical daily navigation risk data set is constructed according to the comprehensive navigation risk value.

5. A generative method for predicting daily navigation risk of Arctic waterways according to claim 1, characterized in that: The method of constructing a generative daily navigation risk monthly covariance forecasting model based on the historical daily navigation risk data set comprises the following steps: Constructing a daily navigation risk covariance dataset for each month based on the historical daily navigation risk dataset; The generative daily navigation risk monthly covariance prediction model is constructed based on the daily navigation risk covariance dataset.

6. A generative method for predicting daily navigation risk of Arctic waterways according to claim 1, characterized in that: The method of constructing and training a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters includes the following steps: Constructing a historical monthly navigation risk dataset for the Arctic route based on the historical daily navigation risk dataset; The monthly navigation risk prediction model is constructed and trained based on the historical monthly navigation risk data set and the navigable ship parameters.

7. A generative method for predicting daily navigation risk of Arctic waterways according to claim 1, characterized in that: The method of generating a daily navigation risk value of the navigation risk in the prediction time window according to the monthly information of the risk prediction time window through the monthly navigation risk prediction model and the monthly covariance of the daily navigation risk comprises the following steps: According to the monthly information of the risk forecast time window, the monthly navigation risk forecast model is used to predict the navigation risk on the first day of each month, the navigation risk in the middle of each month, and the navigation risk at the end of each month within the time window; According to the first-day navigation risk, the mid-month navigation risk and the monthly covariance of the daily navigation risk, the daily navigation risk value of the navigation risk within the prediction time window is generated through the Gaussian process regression method.

8. A generative Arctic route daily navigation risk prediction device, characterized in that: include: The first module is used to obtain historical daily environmental data of the Arctic route and the parameters of ships sailing on the Arctic route; The second module is used to construct a historical daily navigation risk data set for the Arctic route based on the historical daily environmental data and the navigable ship parameters; The third module is used to construct a generative daily navigation risk monthly covariance forecast model based on the historical daily navigation risk data set; The fourth module is used to construct and train a monthly navigation risk prediction model based on the historical daily navigation risk data set and the navigation ship parameters; The fifth module is used to generate the monthly covariance of daily navigation risk in the corresponding month according to the generative daily navigation risk monthly covariance prediction model and the timestamp information; The sixth module is used to generate a daily navigation risk value for the navigation risk within the prediction time window according to the monthly information of the risk prediction time window, through the monthly navigation risk prediction model and the monthly covariance of the daily navigation risk.

9. An electronic device, characterized in that: including a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 7.

10. A computer-readable storage medium, characterized in that: The storage medium stores a program, and the program is executed by a processor to implement the method according to any one of claims 1 to 7.

Images