Navigation area division method, system and equipment adaptive to sea conditions and medium

Abstract

The invention relates to the technical field of route planning, and discloses a navigation area division method, system, equipment and medium adaptive to sea conditions, and the method comprises the steps: firstly obtaining a large circle route with the shortest navigation distance of a target ship in a target navigation area based on the navigation data of the target ship, and then obtaining a navigation area with the shortest navigation distance of the target ship based on the navigation data on the large circle route by using a spatio-temporal interpolation method; according to the method, the time-space sea condition data is subjected to the time-space sea condition data to obtain accurate and real time-space sea condition data, and then the time-space sea condition data is subjected to iterative clustering by using a clustering algorithm after the weight coefficient of the sea condition features is improved to obtain a refined clustering cluster, so that accurate and refined navigation area division can be realized; reliable data support is provided for ocean-going ship route optimization and unmanned ship route planning, and the quality of ocean-going ship route optimization and unmanned ship route planning is further improved.

Description

Technical Field

[0001] The present invention relates to the technical field of route planning, and in particular to a method, system, equipment and medium for dividing a navigation area adaptive to sea conditions. Background Art

[0002] The optimization of ocean-going ship routes and the path planning of unmanned ships require seeking the safest or most energy-efficient navigation strategy in the target navigation area. Therefore, the reasonable division of the navigation area is of great significance for route planning and path planning of unmanned ships. However, most of the existing navigation area methods use resolution as a constant value to divide the navigation area into grids. When the resolution is large, the navigation area division is relatively rough, and when the resolution is small, the navigation area division is relatively complicated. Moreover, the temporal and spatial distribution of the actual external sea conditions is not very uniform. The existing gridded navigation area method cannot effectively and accurately describe the characteristics of the external sea conditions, resulting in low quality of ocean-going ship route optimization and unmanned ship path planning.

[0003] Therefore, there is an urgent need for a navigation area division method, system, equipment and medium that are adaptive to sea conditions, so as to achieve accurate and refined navigation area division and improve the quality of ocean-going ship route optimization and unmanned ship path planning. Summary of the invention

[0004] The present invention provides a method, system, device and medium for dividing a navigation area adaptive to sea conditions, so as to solve the defect that the existing rasterized navigation area method is not accurate and fine enough in dividing the navigation area.

[0005] The present invention provides a method for dividing a navigation area according to an adaptive sea condition, comprising:

[0006] Obtain navigation data of target ship;

[0007] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0008] Based on the great circle route of the target ship in the target navigation area, the spatiotemporal sea condition data on the great circle route in the target navigation area is obtained by using the spatiotemporal interpolation method;

[0009] The improved clustering algorithm is used to cluster the spatiotemporal sea state data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea state data clusters, wherein each of the several spatiotemporal sea state data clusters has a corresponding category label;

[0010] According to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, the navigation area is divided into regions.

[0011] According to a method for dividing a navigation area according to an adaptive sea condition provided by the present invention, the navigation data includes any one of the following items or any combination thereof: a departure port, an arrival port, and an estimated arrival time.

[0012] According to a method for dividing a navigation area according to an adaptive sea condition provided by the present invention, generating a great circle route of a target ship in a target navigation area according to navigation data of the target ship comprises:

[0013] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0014] According to the great circle route of the target ship in the target navigation area, the navigation data of the target ship on the great circle route is obtained, wherein the navigation data of the target ship on the great circle route includes any one of the following items or any combination thereof: time, speed, heading, longitude, and latitude.

[0015] According to a method for dividing a navigation area for adaptive sea conditions provided by the present invention, the method uses a spatiotemporal interpolation method based on a great circle route of a target ship in a target navigation area to obtain spatiotemporal sea condition data on the great circle route in the target navigation area, including:

[0016] According to the navigation data of the target ship on the great circle route, the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation method;

[0017] Based on the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area, the time dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the time interpolation method;

[0018] The spatial dimension sea condition data and the temporal dimension sea condition data of the target ship on the great circle route in the target navigation area are combined to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area.

[0019] According to a method for dividing a navigation area for adaptive sea conditions provided by the present invention, the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using a spatial interpolation method based on the navigation data of the target ship on the great circle route, including:

[0020] According to the navigation data of the target ship on the great circle route, the spatial dimension sea state data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation expression, where the spatial interpolation expression is:

[0021]

[0022] In the spatial interpolation expression, E ship(t) represents the sea state value of the spatial position of the target ship on the great circle route in the target navigation area; E 1 (t), E 2 (t), E 3 (t), E 4 (t) represents the sea condition values ​​at four preset sampling positions near the target ship on the great circle route in the target navigation area; Δlon and Δlat represent the lengths of the minimum grid in the longitude and latitude directions of the minimum resolution in the target navigation area after gridding; d lon d lat They represent the horizontal distance of the target ship's current position from the left grid boundary and the vertical distance from the upper grid boundary respectively.

[0023] According to a method for dividing a navigation area based on an adaptive sea condition, the method uses a time interpolation method to obtain the time dimension sea condition data of the target ship on the great circle route in the target navigation area based on the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area, including:

[0024] Based on the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area, the time dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the quadratic interpolation function.

[0025] According to a method for dividing a navigation area based on adaptive sea conditions provided by the present invention, the spatiotemporal sea condition data includes any one of the following or any combination thereof: wind speed, wind direction, characteristic wave height of combined wind waves and swells, and average wave period.

[0026] According to a method for dividing a navigation area based on adaptive sea conditions provided by the present invention, the improved clustering algorithm is used to cluster the spatiotemporal sea condition data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea condition data clusters, including:

[0027] In the spatiotemporal sea state data on the great circle route in the target navigation area, K cluster centers (c 1 ,c 2 …c k ), where each of the K cluster centers includes several sea state characteristics;

[0028] By using the distance expression, calculate each sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i The distances to the K cluster centers are obtained respectively, and the distances to each sample x in the K cluster centers are obtained i The closest distance to the center c v , and for each sample x iClassify to the nearest distance center c v Type;

[0029] Based on each sample x of the spatiotemporal sea state data on the great circle route in the target navigation area i and its nearest center c v , update the expression through the cluster center, get the new cluster center and start a new round of clustering;

[0030] The convergence value is calculated through the convergence expression, and clustering is stopped when the convergence value no longer changes.

[0031] According to a method for dividing a navigation area according to an adaptive sea condition provided by the present invention, the distance expression is:

[0032]

[0033] In the distance expression, d(x i ,c v ) represents the sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i To the cluster center c among the K cluster centers v The distance, x il Represents sample x i The properties of the lth sea state feature, c vl Represents the cluster center c v The attribute of the lth sea state feature, p represents the number of sea state features, ω l Represents the weight coefficient of the improved sea state characteristics.

[0034] According to a method for dividing a navigation area for adaptive sea conditions provided by the present invention, sea condition characteristics include any one of the following or any combination thereof: wind speed, wind direction, characteristic wave height of combined wind waves and swells, and average wave period, and the weight coefficients of improved sea condition characteristics include any one of the following or any combination thereof: wind speed weight coefficient, wind direction weight coefficient, characteristic wave height weight coefficient, and average wave direction weight coefficient, wherein the wind speed weight coefficient is 0.25, the wind direction weight coefficient is 0.3, the characteristic wave height weight coefficient is 0.35, and the average wave direction weight coefficient is 0.1.

[0035] According to a method for dividing navigation areas according to sea conditions, the cluster center update expression is:

[0036]

[0037] In the cluster center update expression, c kN Represents the updated cluster center; N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ikRepresents sample x i Whether it belongs to the k-th category of binary numbers, when δ ik When it is 0, it represents sample x i Belongs to the kth category, when δ ik When it is 1, it represents sample x i Does not belong to the kth category.

[0038] According to a method for dividing a navigation area according to an adaptive sea condition provided by the present invention, the convergence expression is:

[0039]

[0040] In the convergence expression, E SSE represents the convergence value, N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ik Represents sample x i Whether the binary number belongs to the kth category; x il Represents sample x i The properties of the lth sea state feature; c kl represents the attribute of the lth sea condition feature of the kth cluster center; K represents the number of randomly selected cluster centers, p represents the number of sea condition features, ω l Represents the weight coefficient of the improved sea state characteristics.

[0041] The present invention also provides a navigation area division system adaptive to sea conditions, comprising:

[0042] The data acquisition module is used to: acquire the navigation data of the target ship;

[0043] A generating module, used for: generating a great circle route of the target ship in the target navigation area according to the navigation data of the target ship;

[0044] The data processing module is used to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area by using the spatiotemporal interpolation method based on the great circle route of the target ship in the target navigation area;

[0045] The clustering module is used to: cluster the spatiotemporal sea state data on the great circle route in the target navigation area using an improved clustering algorithm to obtain a number of spatiotemporal sea state data clusters, wherein each of the plurality of spatiotemporal sea state data clusters has a corresponding category label;

[0046] The division module is used to: realize regional division of the navigation area according to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label.

[0047] The present invention also provides an electronic device, comprising a processor and a memory storing a computer program, wherein the processor implements any of the above-mentioned methods for dividing a navigation area for adaptive sea conditions when executing the computer program.

[0048] The present invention also provides a non-transitory computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the method for dividing a navigation area according to any of the above-mentioned adaptive sea conditions is implemented.

[0049] The present invention also provides a computer program product, which includes a computer program. The computer program can be stored on a non-transitory computer-readable storage medium. When the computer program is executed by a processor, the computer can execute any of the above-mentioned methods for dividing the navigation area for adaptive sea conditions.

[0050] The present invention provides a method, system, device and medium for dividing a navigation area for adaptive sea conditions. First, based on the navigation data of a target ship, a great circle route with the shortest navigation distance of the target ship is obtained in the target navigation area. Then, based on the navigation data on the great circle route, a spatiotemporal interpolation method is used to obtain accurate and true spatiotemporal sea condition data. Then, a clustering algorithm with improved weight coefficients for sea condition characteristics is used to iteratively cluster the spatiotemporal sea condition data to obtain refined clustering clusters. Accurate and refined navigation area division can be achieved, and reliable data support can be provided for ocean-going ship route optimization and unmanned ship path planning, thereby further improving the quality of ocean-going ship route optimization and unmanned ship path planning. BRIEF DESCRIPTION OF THE DRAWINGS

[0051] In order to more clearly illustrate the technical solutions in the present invention or the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, the drawings described below are some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying creative work.

[0052] Figure 1 A schematic flow chart of a method for dividing a navigation area according to adaptive sea conditions provided by the present invention.

[0053] Figure 2 Schematic diagram of spatial interpolation method.

[0054] Figure 3 Schematic diagram of the time interpolation method.

[0055] Figure 4 The figure shows the effect comparison before and after the clustering method is improved.

[0056] Figure 5A schematic structural diagram of a navigation area division system for adaptive sea conditions provided by the present invention.

[0057] Figure 6 This is a schematic structural diagram of an electronic device provided by the present invention. DETAILED DESCRIPTION

[0058] In order to make the purpose, technical solution and advantages of the present invention clearer, the technical solution of the present invention will be clearly and completely described below in conjunction with the drawings in the present invention. Obviously, the described embodiments are part of the embodiments of the present invention, not all of the embodiments, and they should not be understood as limitations on the present invention. 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. In the description of the present invention, it should be understood that the terms used are only for descriptive purposes and cannot be understood as indicating or implying relative importance.

[0059] Figure 1 The flowchart of the method for dividing a navigation area according to an adaptive sea condition provided by the present invention is shown in FIG. The execution subject of the method for dividing a navigation area according to an adaptive sea condition provided by the present invention can be any applicable terminal side device or network side device, such as a navigation area division device according to an adaptive sea condition.

[0060] See also Figure 1 The present invention provides a method for dividing a navigation area according to an adaptive sea condition, which may include:

[0061] S101. Acquire the navigation data of the target ship. The navigation data in this embodiment includes: departure port, arrival port, and estimated arrival time.

[0062] S102: Generate a great circle route of the target ship in the target navigation area according to the navigation data of the target ship.

[0063] Specifically, according to the navigation data of the target ship, the discrete longitude intervals of the great circle route can be set to generate a great circle route with the shortest distance on the sphere between the departure port and the arrival port. Then, the average speed during the entire voyage can be approximately estimated based on the distance of the great circle route and the expected sailing time of the target ship. The generation of the great circle route is a reference for extracting the spatiotemporal sea condition data on the target route. Before the target ship sails, the great circle route represents the route with the shortest sailing distance between the two ports for the target ship. The optimized route should theoretically be distributed around the great circle route. Then the relevant sea condition data extracted by the great circle route and the average speed are also similar to the sea condition data on the actual optimized route.

[0064] In one embodiment, S102 may include:

[0065] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0066] According to the great circle route of the target ship in the target navigation area, the navigation data of the target ship on the great circle route is obtained, wherein the navigation data of the target ship on the great circle route in this embodiment includes: time, speed, heading, longitude, and latitude.

[0067] S103, based on the great circle route of the target ship in the target navigation area, using the spatiotemporal interpolation method, obtain the spatiotemporal sea condition data on the great circle route in the target navigation area.

[0068] In one embodiment, S103 may include:

[0069] According to the navigation data of the target ship on the great circle route, the spatial dimension sea state data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation expression, where the spatial interpolation expression is:

[0070]

[0071] In the spatial interpolation expression, E ship (t) represents the sea state value of the spatial position of the target ship on the great circle route in the target navigation area; E 1 (t), E 2 (t), E 3 (t), E 4 (t) represents the sea state values ​​at four preset sampling positions near the target ship on the great circle route in the target navigation area; Δlon and Δlat represent the lengths of the smallest grid corresponding to the minimum resolution of ECMWF in the longitude and latitude directions respectively; d lon d lat They represent the horizontal distance of the target ship's current position from the left grid boundary and the vertical distance from the upper grid boundary respectively;

[0072] Based on the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area, the time dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using a quadratic interpolation function;

[0073] The spatial dimension sea condition data and the temporal dimension sea condition data of the target ship on the great circle route in the target navigation area are combined to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area, wherein the spatiotemporal sea condition data in this embodiment include: wind speed, wind direction, characteristic wave height of combined wind waves and swell waves, and average wave period.

[0074] Specifically, global sea state data can be obtained from the European Centre for Medium-Range Weather Forecasts (ECMWF), but its minimum spatial resolution is currently 0.25°, and the position of a ship cannot always fall on the points of these spatial resolutions, so this embodiment uses spatial interpolation. The schematic diagram of the spatial interpolation method is shown in FIG. Figure 2 shown.

[0075] After completing the spatial interpolation, the sea conditions encountered by the target ship at any position can be calculated as spatial sea condition data. However, the sea condition has the characteristics of temporal change in addition to the spatial change. Therefore, this embodiment performs temporal interpolation on the basis of the spatial interpolation of the sea condition. The schematic diagram of the temporal interpolation method is shown in FIG. Figure 3 As shown. ship (t 1 ), E ship (t 2 ), E ship (t 3 ), E ship (t 4 ) represent the sea condition data of the two sampling time points before and after the current moment of the target ship respectively. The temporal sea condition data is obtained after time interpolation using the quadratic interpolation method.

[0076] S104. Clustering the spatiotemporal sea condition data on the great circle route in the target navigation area using an improved clustering algorithm to obtain a plurality of spatiotemporal sea condition data clusters, wherein each of the plurality of spatiotemporal sea condition data clusters has a corresponding category label.

[0077] This embodiment uses an improved K-means clustering algorithm to cluster the spatiotemporal sea state data on the great circle route in the target navigation area. After clustering, the spatiotemporal sea state data with similar data features are attributed to the same cluster, and the data types between different clusters are quite different. A key step in the calculation process of the traditional clustering algorithm is to calculate the distance between the points to be clustered and each cluster center, which is called the Euclidean distance. If the point to be clustered is closest to the kth cluster center, then it means that the point to be clustered belongs to the kth category. The Euclidean distance is calculated by taking the square root of the sum of the squares of the distances of the variables to be clustered in all dimensions. If the weights of different sea state factors are set to the same value in the process of calculating the Euclidean distance, the relevant sea state characteristics cannot be well reflected. In order to accurately characterize different sea state characteristics and to make clustering more reasonable, this embodiment refines and improves the relevant weight coefficients when the clustering algorithm calculates the Euclidean distance to form an improved K-means clustering algorithm.

[0078] In one embodiment, S104 may include:

[0079] In the spatiotemporal sea state data on the great circle route in the target navigation area, K cluster centers (c 1 ,c 2 …c k ), wherein each of the K cluster centers includes several sea condition characteristics, wherein the sea condition characteristics in this embodiment include: wind speed, wind direction, characteristic wave height of combined wind waves and swells, and average wave period;

[0080] By using the distance expression, calculate each sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i (One sample represents one sea state array. One sea state array in this embodiment includes four data: wind speed, wind direction, characteristic wave height of combined wind wave and swell, and average wave period) and the distance to K cluster centers respectively, and the distance to each sample x in the K cluster centers is obtained. i The closest distance to the center c v , and for each sample x i Classify to the nearest distance center c v The type of distance expression is:

[0081]

[0082] In the distance expression, d(x i ,c v ) represents the sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i To the cluster center c among the K cluster centers v The distance, x il Represents sample x i The properties of the lth sea state feature, c vl Represents the cluster center c v The attribute of the lth sea condition feature, p represents the number of sea condition features (4 in this embodiment), ω l The weight coefficient representing the improved sea state characteristics;

[0083] Based on each sample x of the spatiotemporal sea state data on the great circle route in the target navigation area i and its nearest center c v , through the cluster center update expression, get the new cluster center and start a new round of clustering, where the cluster center update expression is:

[0084]

[0085] In the cluster center update expression, c kNRepresents the updated cluster center; N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ik Represents sample x i Whether it belongs to the k-th category of binary numbers, when δ ik When it is 0, it represents sample x i Belongs to the kth category, when δ ik When it is 1, it represents sample x i Does not belong to the kth category;

[0086] The convergence value is calculated through the convergence expression. When the convergence value no longer changes, clustering is stopped. The convergence expression is:

[0087]

[0088] In the convergence expression, E SSE represents the convergence value, N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ik Represents sample x i Whether the binary number belongs to the kth category; x il Represents sample x i The properties of the lth sea state feature; c kl represents the attribute of the lth sea condition feature of the kth cluster center; K represents the number of randomly selected cluster centers, p represents the number of sea condition features, ω l Represents the weight coefficient of the improved sea state characteristics.

[0089] In this embodiment, the weight coefficients of the improved sea condition characteristics include: wind speed weight coefficient, wind direction weight coefficient, characteristic wave height weight coefficient, and average wave direction weight coefficient, wherein the wind speed weight coefficient is 0.25, the wind direction weight coefficient is 0.3, the characteristic wave height weight coefficient is 0.35, and the average wave direction weight coefficient is 0.1, as shown in Table 1.

[0090] Table 1

[0091]

[0092] S105 , according to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, realize regional division of the navigation area.

[0093] Specifically, the segmentation points can be found based on the labels of different samples after clustering. After clustering the spatiotemporal sea condition data on the great circle route, each group of sea condition data has its own category label. In areas where sea conditions are not very complex, the sea conditions tend to be stable, and the values ​​of the relevant sample labels are consistent. However, when the sea conditions change drastically, the sample labels in different spatiotemporal ranges are different. The sample labels can be used to identify and segment the critical points. When the segmentation points are identified, the division of the navigation area is achieved.

[0094] This embodiment adopts a specific embodiment to verify the effect of the method for dividing the navigation area according to the adaptive sea conditions provided by the present invention.

[0095] Taking wind speed as an example, the clustering effect of the K-means clustering algorithm before and after improvement is visualized and verified in the Indian Ocean (longitude range is 60° to 75°, latitude range is 5° to 25°). The results are as follows: Figure 4 As shown. In order to highlight the role of wind speed in the clustering effect, the weight coefficient of wind speed is increased from the original 0.25 to 0.3, and the weight coefficient of wind direction is reduced from 0.3 to 0.25. It can be seen from the figure that in the target navigation area, the change of wind speed is very complex, and the wind speed distribution is in the range of 1-9m / s. Overall, the regional division results after clustering before the improvement are concentrated in some sea areas, such as the area A marked by the dotted ellipse in the figure. Before the improvement, the two lines connected by the navigation area division points in area A are very close. After the improvement, the lines connected by the navigation area division points in area A are relatively large. In addition, the improved clustering algorithm can better reflect the boundaries of sea state changes. For example, in area B marked by the dotted ellipse in the figure, the wind speed changes are relatively large, and the boundaries of sea state changes are relatively obvious. In this area, the navigation area division points obtained by the clustering algorithm before the improvement are far away from the boundaries of sea state changes, but the navigation area division points obtained by the improved clustering algorithm are closer to the boundaries of sea state changes. It can be seen that the improved clustering algorithm can more reasonably divide the navigation area. It should be noted that this simulation comparison verification only visualizes the wind speed. Other factors such as wind direction, characteristic wave height of combined wind waves and swells, and average wave period will affect the division of the navigation area. Therefore, for the adjustment of the relevant sea condition weight coefficient, the impact of the relevant optimization variables on the ship's fuel consumption can also be comprehensively considered, or the parameters can be adjusted according to the optimization effect.

[0096] The present invention provides a method, system, device and medium for dividing a navigation area for adaptive sea conditions. First, based on the navigation data of a target ship, a great circle route with the shortest navigation distance of the target ship is obtained in the target navigation area. Then, based on the navigation data on the great circle route, a spatiotemporal interpolation method is used to obtain accurate and true spatiotemporal sea condition data. Then, a clustering algorithm with improved weight coefficients for sea condition characteristics is used to iteratively cluster the spatiotemporal sea condition data to obtain refined clustering clusters. Accurate and refined navigation area division can be achieved, and reliable data support can be provided for ocean-going ship route optimization and unmanned ship path planning, thereby further improving the quality of ocean-going ship route optimization and unmanned ship path planning.

[0097] The adaptive sea condition sailing area division system provided by the present invention is described below. The adaptive sea condition sailing area division system described below and the adaptive sea condition sailing area division method described above can be referenced to each other.

[0098] Reference Figure 5 The present invention provides a navigation area division system that is adaptive to sea conditions, comprising:

[0099] The data acquisition module is used to: acquire the navigation data of the target ship;

[0100] A generating module, used for: generating a great circle route of the target ship in the target navigation area according to the navigation data of the target ship;

[0101] The data processing module is used to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area by using the spatiotemporal interpolation method based on the great circle route of the target ship in the target navigation area;

[0102] The clustering module is used to: cluster the spatiotemporal sea state data on the great circle route in the target navigation area using an improved clustering algorithm to obtain a number of spatiotemporal sea state data clusters, wherein each of the plurality of spatiotemporal sea state data clusters has a corresponding category label;

[0103] The division module is used to: realize regional division of the navigation area according to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label.

[0104] Figure 6 An example of a physical structure diagram of an electronic device is shown in FIG. Figure 6As shown, the electronic device may include: a processor 810, a communication interface 820, a memory 830 and a communication bus 840, wherein the processor 810, the communication interface 820 and the memory 830 communicate with each other through the communication bus 840. The processor 810 may call the logic instructions in the memory 830 to perform the following steps:

[0105] Obtain navigation data of target ship;

[0106] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0107] Based on the great circle route of the target ship in the target navigation area, the spatiotemporal sea condition data on the great circle route in the target navigation area is obtained by using the spatiotemporal interpolation method;

[0108] The improved clustering algorithm is used to cluster the spatiotemporal sea state data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea state data clusters, wherein each of the several spatiotemporal sea state data clusters has a corresponding category label;

[0109] According to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, the navigation area is divided into regions.

[0110] In addition, the logic instructions in the above-mentioned memory 830 can be implemented in the form of a software functional unit and can be stored in a computer-readable storage medium when it is sold or used as an independent product. Based on such an understanding, the technical solution of the present invention, in essence, 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, and the computer software product is stored in a storage medium, including a number of 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 method 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 and other media that can store program codes.

[0111] On the other hand, the present invention further provides a computer program product, the computer program product comprising a computer program, the computer program can be stored on a non-transitory computer readable storage medium, and when the computer program is executed by a processor, the computer can perform the following steps:

[0112] Obtain navigation data of target ship;

[0113] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0114] Based on the great circle route of the target ship in the target navigation area, the spatiotemporal sea condition data on the great circle route in the target navigation area is obtained by using the spatiotemporal interpolation method;

[0115] The improved clustering algorithm is used to cluster the spatiotemporal sea state data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea state data clusters, wherein each of the several spatiotemporal sea state data clusters has a corresponding category label;

[0116] According to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, the navigation area is divided into regions.

[0117] In another aspect, the present invention further provides a non-transitory computer-readable storage medium having a computer program stored thereon, which is implemented to perform the following steps when executed by a processor:

[0118] Obtain navigation data of target ship;

[0119] Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship;

[0120] Based on the great circle route of the target ship in the target navigation area, the spatiotemporal sea condition data on the great circle route in the target navigation area is obtained by using the spatiotemporal interpolation method;

[0121] The improved clustering algorithm is used to cluster the spatiotemporal sea state data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea state data clusters, wherein each of the several spatiotemporal sea state data clusters has a corresponding category label;

[0122] According to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, the navigation area is divided into regions.

[0123] The device embodiments described above are merely illustrative, wherein the units described as separate components may or may not be physically separated, and the components displayed as units may or may not be physical units, that is, they may be located in one place, or they may be distributed on multiple network units. Some or all of the modules may be selected according to actual needs to achieve the purpose of the scheme of this embodiment. Ordinary technicians in this field can understand and implement it without paying creative labor.

[0124] Through the description of the above implementation methods, those skilled in the art can clearly understand that each implementation method can be implemented by means of software plus a necessary general hardware platform, and of course, it can also be implemented by hardware. Based on this understanding, the above technical solution is essentially or the part that contributes to the prior art can be embodied in the form of a software product, and the computer software product can be stored in a computer-readable storage medium, such as ROM / RAM, a disk, an optical disk, etc., including a number of instructions for a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods described in each embodiment or some parts of the embodiments.

[0125] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions 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 they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. 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 embodiments of the present invention.

Claims

1. A method for dividing a navigation area according to sea conditions, characterized in that: include: Obtain navigation data of target ship; Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship; Based on the great circle route of the target ship in the target navigation area, the spatiotemporal sea condition data on the great circle route in the target navigation area is obtained by using the spatiotemporal interpolation method; The improved clustering algorithm is used to cluster the spatiotemporal sea state data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea state data clusters, wherein each of the several spatiotemporal sea state data clusters has a corresponding category label; According to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label, the navigation area is divided into regions.

2. The method for dividing navigation areas according to sea conditions according to claim 1, characterized in that: The step of generating a great circle route of the target ship in the target navigation area according to the navigation data of the target ship comprises: Generate a great circle route of the target ship in the target navigation area based on the navigation data of the target ship; According to the great circle route of the target ship in the target navigation area, the navigation data of the target ship on the great circle route is obtained.

3. The method for dividing navigation areas according to sea conditions according to claim 2, characterized in that: The method of obtaining the spatiotemporal sea condition data on the great circle route in the target navigation area based on the great circle route of the target ship in the target navigation area by using the spatiotemporal interpolation method includes: According to the navigation data of the target ship on the great circle route, the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation method; Based on the spatial dimension sea condition data of the target ship on the great circle route in the target navigation area, the time dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the time interpolation method; The spatial dimension sea condition data and the temporal dimension sea condition data of the target ship on the great circle route in the target navigation area are combined to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area.

4. The method for dividing navigation areas according to sea conditions according to claim 3, characterized in that: The spatial dimension sea condition data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation method according to the navigation data of the target ship on the great circle route, including: According to the navigation data of the target ship on the great circle route, the spatial dimension sea state data of the target ship on the great circle route in the target navigation area is obtained by using the spatial interpolation expression, where the spatial interpolation expression is: In the spatial interpolation expression, E ship (t) represents the sea condition value of the spatial position of the target ship on the great circle route in the target navigation area; E1(t), E2(t), E3(t), and E4(t) respectively represent the sea condition values ​​at four preset sampling positions close to the position of the target ship on the great circle route in the target navigation area; Δlon and Δlat respectively represent the lengths of the minimum grid in the longitude and latitude directions of the minimum resolution in the target navigation area after gridding; d lon d lat They represent the horizontal distance of the target ship's current position from the left grid boundary and the vertical distance from the upper grid boundary respectively.

5. The method for dividing the navigation area according to any one of claims 1 to 4, characterized in that: The improved clustering algorithm is used to cluster the spatiotemporal sea condition data on the great circle route in the target navigation area to obtain a number of spatiotemporal sea condition data clusters, including: In the spatiotemporal sea state data on the great circle route in the target navigation area, K cluster centers (c1, c2…c k ), where each of the K cluster centers includes several sea state characteristics; By using the distance expression, calculate each sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i The distances to the K cluster centers are obtained respectively, and the distances to each sample x in the K cluster centers are obtained i The closest distance to the center c v , and for each sample x i Classify to the nearest distance center c v Type; Based on each sample x of the spatiotemporal sea state data on the great circle route in the target navigation area i and its nearest center c v , update the expression through the cluster center, get the new cluster center and start a new round of clustering; The convergence value is calculated through the convergence expression, and clustering is stopped when the convergence value no longer changes.

6. The method for dividing navigation areas according to sea conditions according to claim 5, characterized in that: The distance expression is: In the distance expression, d(x i ,c v ) represents the sample x in the spatiotemporal sea state data on the great circle route in the target navigation area i To the cluster center c among the K cluster centers v The distance, x il Represents sample x i The properties of the lth sea state feature, c vl Represents the cluster center c v The attribute of the lth sea state feature, p represents the number of sea state features, ω l The weight coefficient representing the improved sea state characteristics; The cluster center update expression is: In the cluster center update expression, c kN Represents the updated cluster center; N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ik Represents sample x i Whether it belongs to the k-th category of binary numbers, when δ ik When it is 0, it represents sample x i Belongs to the kth category, when δ ik When it is 1, it represents sample x i Does not belong to the kth category; The convergence expression is: In the convergence expression, E SSE represents the convergence value, N k Represents the total number of samples in the spatiotemporal sea state data on the great circle route in the target navigation area; δ ik Represents sample x i Whether the binary number belongs to the kth category; x il Represents sample x i The properties of the lth sea state feature; c kl represents the attribute of the lth sea condition feature of the kth cluster center; K represents the number of randomly selected cluster centers, p represents the number of sea condition features, ω l Represents the weight coefficient of the improved sea state characteristics.

7. The method for dividing navigation areas according to sea conditions according to claim 6, characterized in that: Sea state characteristics include any one or any combination of the following: wind speed, wind direction, characteristic wave height of combined wind waves and swells, average wave period; and / or, The weight coefficients of the improved sea condition characteristics include any one of the following items or any combination thereof: wind speed weight coefficient, wind direction weight coefficient, characteristic wave height weight coefficient, and average wave direction weight coefficient, wherein the wind speed weight coefficient is 0.25, the wind direction weight coefficient is 0.3, the characteristic wave height weight coefficient is 0.35, and the average wave direction weight coefficient is 0.

1.

8. A navigation area division system that is adaptive to sea conditions, characterized in that: include: The data acquisition module is used to: acquire the navigation data of the target ship; A generating module, used for: generating a great circle route of the target ship in the target navigation area according to the navigation data of the target ship; The data processing module is used to obtain the spatiotemporal sea condition data on the great circle route in the target navigation area by using the spatiotemporal interpolation method based on the great circle route of the target ship in the target navigation area; The clustering module is used to: cluster the spatiotemporal sea state data on the great circle route in the target navigation area using an improved clustering algorithm to obtain a number of spatiotemporal sea state data clusters, wherein each of the plurality of spatiotemporal sea state data clusters has a corresponding category label; The division module is used to: realize regional division of the navigation area according to each of the plurality of spatiotemporal sea state data clusters and its corresponding category label.

9. An electronic device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein: When the processor executes the program, the method for dividing the navigation area according to the adaptive sea conditions as described in any one of claims 1 to 7 is implemented.

10. A non-transitory computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method for dividing the navigation area according to the adaptive sea conditions as described in any one of claims 1 to 7 is implemented.

Images