Ship collision warning methods and related equipment

Abstract

The present application is applicable to the field of ship collision avoidance technology, and provides a ship collision warning method and related equipment, the method comprising: obtaining navigation data of each ship in the target sea area, the navigation data at least including location information, historical trajectory information, heading information and speed information; predicting the predicted position of each ship based on the navigation data, preset time interval and preset generative adversarial network; fitting the predicted trajectory of each ship in combination with the time axis according to the location information and the predicted position; judging the collision risk of each ship in the target sea area based on the predicted trajectory, and generating alarm information. By predicting the trajectory of each ship in the target sea area and issuing collision warnings based on the predicted trajectory, the safety of ship navigation and the self-adaptive navigation capability of the target sea area are improved, providing technical support for realizing intelligent navigation and regional perception.

Description

Technical Field

[0001] The present application belongs to the technical field of ship collision avoidance, and in particular, relates to a ship collision warning method and related equipment. Background Art

[0002] Since ships in the same sea area have different speeds, headings, types and different maneuverability, and considering the huge inertia of ships at sea, it is crucial to perceive and control the safe distance between ships and avoid collision risks.

[0003] Modern vessel traffic management systems (VTS, Vessel Traffic Management System) can accurately display the position, heading and other information of ships on the electronic chart platform. However, in actual applications, it is not possible to accurately judge whether a ship will collide during the shipping process only by relying on the position, heading and other information of ships displayed on the VTS. When observing the collision of ships based on the position and heading of ships displayed on the electronic chart platform, there is an obvious lag, and it is impossible to issue an alarm in time before the collision, that is, it is impossible to effectively avoid ship collision. Summary of the invention

[0004] The embodiment of the present application provides a ship collision warning method, which can solve the problem that ship collisions cannot be effectively avoided in the prior art.

[0005] In a first aspect, an embodiment of the present application provides a ship collision warning method, comprising:

[0006] Acquire navigation data of each ship in the target sea area, wherein the navigation data at least includes location information, historical track information, heading information and speed information;

[0007] Predicting the predicted positions of each ship at different times based on the navigation data, the preset time interval and the preset generative adversarial network;

[0008] According to the position information and the predicted position, the predicted trajectory of each ship is fitted in combination with the time axis;

[0009] The collision risk of each ship in the target sea area is determined based on the predicted trajectory, and an alarm message is generated.

[0010] Optionally, the step of acquiring navigation data of each ship in the target sea area includes:

[0011] Acquire first identification information and first navigation data of known ships in the target sea area through the AIS base station in the VTS system;

[0012] Acquiring second identification information and second navigation data of unknown ships in the target sea area through a ship-side radar of any ship in the target sea area;

[0013] Based on the first identification information and the second identification information, the first navigation data and the second navigation data are integrated into the same electronic nautical chart to obtain the navigation data of each ship in the target sea area.

[0014] Optionally, before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes:

[0015] The tonnage data of each ship in the target sea area is obtained, and the preset time interval is determined based on the tonnage data, wherein the preset time interval is positively correlated with the tonnage data.

[0016] Optionally, before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes:

[0017] Acquire historical prediction information corresponding to the target ship and the position information;

[0018] Matching the position information with the historical prediction information, and if the position information does not match the historical prediction information, obtaining the actual historical track of the target ship as the historical track information in the navigation data;

[0019] If the position information matches the historical prediction information, the historical prediction information is corrected based on the position information to obtain corrected data, and based on the corrected data, a historical prediction trajectory is generated through a step-by-step prediction strategy, and the historical prediction trajectory is used as the historical trajectory information in the navigation data.

[0020] Optionally, the step of predicting the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network includes:

[0021] If the location information matches the historical prediction information, obtaining the target time corresponding to the predicted location;

[0022] Obtaining historical trajectory information of each preset time interval before the target moment, inputting the preset time interval, the historical trajectory information of each preset time interval, the position information of the ship at a previous node at the target moment, the heading information of the ship at the previous node at the target moment, and the speed information of the ship at the previous node at the target moment into a preset generative adversarial network, and predicting the predicted position of the ship at the target moment, wherein the previous node at the target moment is a time node before the target moment and at a preset time interval from the target moment;

[0023] If the position information does not match the historical prediction information, the preset time interval, the actual historical trajectory, the position information of the last point in the actual historical trajectory in chronological order, the heading information of the ship at the last point and the speed information of the ship at the last point are input into the preset generative adversarial network to predict the predicted position of the ship at different times.

[0024] Optionally, the step of determining the collision risk of each ship in the target sea area based on the predicted trajectory and generating alarm information includes:

[0025] The predicted trajectories of the various ships are plotted on the same nautical chart to obtain a target nautical chart, and the collision risk of the various ships in the target sea area is determined based on the minimum distance between the predicted trajectories in the target nautical chart;

[0026] The step of judging the collision risk of each ship in the target sea area based on the minimum distance between each predicted track in the target sea chart comprises:

[0027] If the two predicted tracks in the target chart do not intersect and / or overlap at any time point in the future, and the minimum distance between the two predicted tracks is greater than or equal to the threshold, the two ships corresponding to the two predicted tracks are judged to be in a low risk state, and no alarm information is generated;

[0028] If the two predicted tracks in the target chart do not intersect and / or overlap at any future time point, and the minimum distance between the two predicted tracks is less than the threshold, it is determined that the two ships corresponding to the two predicted tracks are in a medium risk state, and a medium risk warning message is generated;

[0029] If the two predicted tracks in the target chart intersect and / or overlap at any time point in the future, it is judged that the two ships corresponding to the two predicted tracks are in a high-risk state, and a high-risk warning message is generated.

[0030] Optionally, the method further includes:

[0031] When there are medium-risk and / or high-risk ships in the target chart, the medium-risk and / or high-risk ships shall be regarded as risk ships;

[0032] The attribute data of the risk ship is obtained, and based on the attribute data, a risk level is set for the medium risk warning information and / or the high risk warning information of the risk ship according to a preset rule.

[0033] On the other hand, an embodiment of the present application provides a ship collision warning device, the device comprising:

[0034] A data acquisition module is used to obtain the navigation data of each ship in the target sea area, wherein the navigation data at least includes location information, historical track information, heading information and speed information;

[0035] A prediction module, used to predict the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network;

[0036] A trajectory generation module, used to fit the predicted trajectory of each ship according to the position information and the predicted position in combination with the time axis;

[0037] The alarm module is used to determine the collision risk of each ship in the target sea area based on the predicted trajectory and generate alarm information.

[0038] In a third aspect, an embodiment of the present application provides a terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the above method when executing the computer program.

[0039] In a fourth aspect, an embodiment of the present application provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and the computer program implements the above method when executed by a processor.

[0040] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0041] Obtain the navigation data of each ship in the target sea area, the navigation data includes at least position information, historical trajectory information, heading information and speed information; predict the predicted position of each ship at different times based on the navigation data, preset time interval and preset generative adversarial network; fit the predicted trajectory of each ship based on the position information and the predicted position in combination with the time axis; judge the collision risk of each ship in the target sea area based on the predicted trajectory, and generate alarm information. By predicting the predicted position of each ship at different times through generative adversarial network, fitting the predicted trajectory of each ship in combination with the time axis, it is possible to infer the ships with collision risk in the future, issue alarms to ships with collision risk in advance, and avoid accidents. BRIEF DESCRIPTION OF THE DRAWINGS

[0042] In order to more clearly illustrate the technical solutions in the embodiments of the present application, 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 only some embodiments of the present application. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0043] Figure 1 It is a flow chart of a ship collision warning method provided by an embodiment of the present application;

[0044] Figure 2 is a flow chart of a ship collision warning method provided by another embodiment of the present application;

[0045] Figure 3 It is a schematic diagram of ship position prediction based on a generative adversarial network in a ship collision warning method provided in an embodiment of the present application;

[0046] Figure 4 This is a schematic diagram of trajectory prediction in a ship collision warning method provided in an embodiment of the present application;

[0047] Figure 5 It is a structural schematic diagram of a ship collision warning device provided in one embodiment of the present application. DETAILED DESCRIPTION

[0048] In the following description, specific details such as specific system structures, technologies, etc. are provided for the purpose of illustration rather than limitation, so as to provide a thorough understanding of the embodiments of the present application. However, it should be clear to those skilled in the art that the present application may also be implemented in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted to prevent unnecessary details from obstructing the description of the present application.

[0049] It should be understood that when used in the present specification and the appended claims, the term "comprising" indicates the presence of described features, wholes, steps, operations, elements and / or components, but does not exclude the presence or addition of one or more other features, wholes, steps, operations, elements, components and / or combinations thereof.

[0050] It should also be understood that the term “and / or” used in the specification and appended claims refers to any and all possible combinations of one or more of the associated listed items, and includes these combinations.

[0051] As used in the specification and appended claims of this application, the term "if" can be interpreted as "when" or "uponce" or "in response to determining" or "in response to detecting", depending on the context. Similarly, the phrase "if it is determined" or "if [described condition or event] is detected" can be interpreted as meaning "uponce it is determined" or "in response to determining" or "uponce [described condition or event] is detected" or "in response to detecting [described condition or event]", depending on the context.

[0052] In addition, in the description of the present application specification and the appended claims, the terms "first", "second", "third", etc. are only used to distinguish the descriptions and cannot be understood as indicating or implying relative importance.

[0053] References to "one embodiment" or "some embodiments" etc. described in the specification of this application mean that one or more embodiments of the present application include specific features, structures or characteristics described in conjunction with the embodiment. Therefore, the statements "in one embodiment", "in some embodiments", "in some other embodiments", "in some other embodiments", etc. that appear in different places in this specification do not necessarily refer to the same embodiment, but mean "one or more but not all embodiments", unless otherwise specifically emphasized in other ways. The terms "including", "comprising", "having" and their variations all mean "including but not limited to", unless otherwise specifically emphasized in other ways.

[0054] Figure 1 A schematic flow chart of a ship collision warning method provided by the present application is shown. An embodiment of the present application provides a ship collision warning method, comprising:

[0055] S101, obtaining navigation data of each ship in the target sea area, wherein the navigation data at least includes location information, historical track information, heading information and speed information;

[0056] In a possible implementation, the step of acquiring navigation data of each ship in the target sea area includes:

[0057] Acquire first identification information and first navigation data of known ships in the target sea area through the AIS base station in the VTS system;

[0058] Acquiring second identification information and second navigation data of unknown ships in the target sea area through a ship-side radar of any ship in the target sea area;

[0059] Based on the first identification information and the second identification information, the first navigation data and the second navigation data are integrated into the same electronic nautical chart to obtain the navigation data of each ship in the target sea area.

[0060] For example, Figure 2 As shown, at the shore-based information acquisition end, the position, speed, heading, tonnage and other information of all known ships in the target sea area are obtained based on the AIS base station in the VTS system (the first navigation data). At the ship-side information acquisition end, the ships equipped with ship-side radars in the target sea area are used to obtain the position, route, heading and other information of unknown ships in the nearby area (the second navigation data) and track and monitor in real time.

[0061] Exemplarily, when the first navigation data and the second navigation data are integrated based on the first identification information and the second identification information, duplicate data can be removed based on whether the first identification information and the second identification information are the same, and it can also be determined whether the ship is a known ship or an unknown ship based on the data display. That is, if the shore-based data and the ship-side data are displayed at the same time and the data overlap, it is a known ship equipped with a ship-side radar; if only the ship-side data is displayed and the shore-based data is missing, it is an unknown ship without a ship-side radar installed.

[0062] For example, considering that some ships still lack supporting equipment for VTS systems in actual applications, the ship-side information acquisition end uses ships equipped with ship-side radars in the target sea area to obtain the location, route, heading and other information of unknown ships in the nearby area, so as to further improve the safety of ship navigation and the self-adaptability of the target sea area.

[0063] S102, predicting the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network;

[0064] Exemplarily, the real-time position, speed, heading, historical trajectory and other information (the navigation data) of the target ship are obtained and input into the generator of the generative adversarial network to predict the ship's position at the next moment. The discriminator judges the predicted information of the generator based on the historical information of the ship, thereby completing the training of the generator. The trained generator can more accurately predict the set of positions of the ship at the next moment (i.e., the high probability density displacement area). The set of ship position data predicted by the generator at the next moment (after a preset time interval) is input into the discriminator, and the discriminator is trained for identification. The trained discriminator can more accurately discriminate the predicted information. After repeatedly cross-training the generator and discriminator of the generative adversarial network, an accurate predicted coordinate (predicted position) can be obtained.

[0065] S103, fitting the predicted trajectory of each ship based on the position information and the predicted position in combination with the time axis;

[0066] Exemplarily, a trajectory analysis timeline is established, and based on the position, speed, heading and other information of known and unknown ships at specific time points on the timeline, calculations are performed in combination with the longitude and latitude coordinates of the electronic nautical chart to draw the trajectory of the ship as it changes along the timeline.

[0067] S104: Determine the collision risk of each ship in the target sea area based on the predicted trajectory and generate alarm information.

[0068] By acquiring the navigation data of each ship in the target sea area, the navigation data includes at least location information, historical trajectory information, heading information and speed information; predicting the predicted position of each ship at different times based on the navigation data, preset time interval and preset generative adversarial network; fitting the predicted trajectory of each ship based on the location information and the predicted position in combination with the time axis; judging the collision risk of each ship in the target sea area based on the predicted trajectory, and generating alarm information. By predicting the predicted position of each ship at different times through generative adversarial network, fitting the predicted trajectory of each ship in combination with the time axis, it is possible to infer the ships with collision risk in the future, and issue alarms to the ships with collision risk in advance to avoid accidents.

[0069] In a possible implementation, before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes:

[0070] The tonnage data of each ship in the target sea area is obtained, and the preset time interval is determined based on the tonnage data, wherein the preset time interval is positively correlated with the tonnage data.

[0071] For example, considering that larger tonnage ships have lower flexibility and can make slower maneuvers per unit time, a longer prediction interval can be appropriately selected; while smaller tonnage ships are relatively flexible and can make larger maneuvers per unit time, so a smaller prediction interval should be appropriately selected.

[0072] In a possible implementation, before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes:

[0073] Acquire historical prediction information corresponding to the target ship and the position information;

[0074] Matching the position information with the historical prediction information, and if the position information does not match the historical prediction information, obtaining the actual historical track of the target ship as the historical track information in the navigation data;

[0075] If the position information matches the historical prediction information, the historical prediction information is corrected based on the position information to obtain corrected data, and based on the corrected data, a historical prediction trajectory is generated through a step-by-step prediction strategy, and the historical prediction trajectory is used as the historical trajectory information in the navigation data.

[0076] Exemplarily, in order to prevent erroneous prediction results from affecting subsequent prediction processes, the location information is matched with the historical prediction information to promptly discover erroneous prediction results, thereby ensuring the reliability of the overall prediction process.

[0077] In a possible implementation, the step of predicting the predicted position of each ship at different times based on the navigation data, the preset time interval and the preset generative adversarial network includes:

[0078] If the location information matches the historical prediction information, obtaining the target time corresponding to the predicted location;

[0079] Obtaining historical trajectory information of each preset time interval before the target moment, inputting the preset time interval, the historical trajectory information of each preset time interval, the position information of the ship at a previous node at the target moment, the heading information of the ship at the previous node at the target moment, and the speed information of the ship at the previous node at the target moment into a preset generative adversarial network, and predicting the predicted position of the ship at the target moment, wherein the previous node at the target moment is a time node before the target moment and at a preset time interval from the target moment;

[0080] If the position information does not match the historical prediction information, the preset time interval, the actual historical trajectory, the position information of the last point in the actual historical trajectory in chronological order, the heading information of the ship at the last point and the speed information of the ship at the last point are input into the preset generative adversarial network to predict the predicted position of the ship at different times.

[0081] Exemplarily, if the position information matches the historical prediction information, the prediction of the next stage starts after the prediction of the previous time segment is completed and the route fitting is completed, and it should be ensured that all the fitting trajectories from the 1st stage to the (n-1th) stage are used as the historical trajectories input into the generative adversarial network of the nth stage, that is, according to all the fitting trajectories from the 1st stage to the (n-1th) stage (the historical trajectory information of each preset time interval before the target moment), the preset time interval, the position information of the ship at the previous node at the target moment, the heading information of the ship at the previous node at the target moment and the speed information of the ship at the previous node at the target moment are input into the preset generative adversarial network to predict the predicted position of the ship at the target moment.

[0082] For example, Figure 4 As shown, (1) First, the generative adversarial network is used to predict the high probability density displacement area (gray area) and the terminal position (question mark coordinate cell) of the ship in the next period of time by combining the ship's speed, tonnage and other parameters; (2) Secondly, the predicted position of the target ship at the next moment is finally selected through the completed generative adversarial network (updated black coordinate cell), and the ship trajectory in this time interval is fitted; (3) After the generative adversarial network completes a prediction stage, it starts the next stage of prediction, which is generally a step-by-step prediction strategy; (4) Finally, the generative adversarial network trained in the new stage finally selects the predicted position of the target ship at the next moment, and fits the ship trajectory in this time interval; (5) The predicted route within two adjacent time intervals is obtained. Among them, the process of finally selecting the predicted position of the target ship at the next moment (updated black coordinate cell) through the completed generative adversarial network is as follows: Figure 3 As shown, the historical trajectory, current speed, heading, positioning and other parameters of the target ship are input into the generator of the generative adversarial network, and the predicted position of the target ship in the next period is transmitted to the discriminator. The discriminator discriminates the predicted position of the target ship in the next period (the predicted position of the target ship at the next moment) and outputs true and false data (True / False), which are used to optimize the generator.

[0083] Exemplarily, if the position information does not match the historical prediction information, the preset time interval, the actual historical trajectory (historical data recorded in real time), the position information of the last point in the actual historical trajectory in chronological order, the heading information of the ship at the last point and the speed information of the ship at the last point are input into the preset generative adversarial network to predict the predicted position of the ship at different times.

[0084] In a possible implementation, the step of determining the collision risk of each ship in the target sea area based on the predicted trajectory and generating alarm information includes:

[0085] The predicted trajectories of the various ships are plotted on the same nautical chart to obtain a target nautical chart, and the collision risk of the various ships in the target sea area is determined based on the minimum distance between the predicted trajectories in the target nautical chart;

[0086] The step of judging the collision risk of each ship in the target sea area based on the minimum distance between each predicted track in the target sea chart comprises:

[0087] If the two predicted tracks in the target chart do not intersect and / or overlap at any time point in the future, and the minimum distance between the two predicted tracks is greater than or equal to the threshold, the two ships corresponding to the two predicted tracks are judged to be in a low risk state, and no alarm information is generated;

[0088] If the two predicted tracks in the target chart do not intersect and / or overlap at any future time point, and the minimum distance between the two predicted tracks is less than the threshold, it is determined that the two ships corresponding to the two predicted tracks are in a medium risk state, and a medium risk warning message is generated;

[0089] If the two predicted tracks in the target chart intersect and / or overlap at any time point in the future, it is judged that the two ships corresponding to the two predicted tracks are in a high-risk state, and a high-risk warning message is generated.

[0090] Exemplarily, when there are ships in a medium-risk state and / or a high-risk state in the target nautical chart, the ships in a medium-risk state and / or a high-risk state are regarded as risk ships;

[0091] The attribute data of the risk ship is obtained, and based on the attribute data, a risk level is set for the medium risk warning information and / or the high risk warning information of the risk ship according to a preset rule.

[0092] Exemplarily, the different risk levels of different risks as shown in Table 1 are:

[0093] Table 1: Different risk levels for different risks

[0094]

[0095] Specifically, if the predicted trajectories of the two ships cannot intersect or overlap at any time point in the future and are far apart, it is judged to be a low-risk state and no warning is issued; if the predicted trajectories of the two ships are close to each other at a certain time point in the future but cannot intersect or overlap, it is judged to be a medium-risk state and a medium-risk warning is issued; if the predicted trajectories of the two ships intersect or overlap at a certain time point in the future, it is judged to be a high-risk state and a high-risk warning is issued. At the same time, considering that different ships in the target sea area have different types, tonnages and operating performances, there are also differences in their turning radius and speed adjustment capabilities. Therefore, the warning priority is set according to the ship information obtained by the VTS system. When both ships in a risk state are medium and large ships, it is a level I warning; when one of the two ships in a risk state is a medium and large ship and the other is a small ship, it is a level II warning; when both ships in a risk state are small ships, it is a level III warning.

[0096] In a possible implementation, Figure 5 As shown, an embodiment of the present application provides a ship collision warning device, the device comprising:

[0097] The data acquisition module 201 is used to obtain the navigation data of each ship in the target sea area, and the navigation data at least includes position information, historical track information, heading information and speed information;

[0098] A prediction module 202, configured to predict the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network;

[0099] A trajectory generation module 203, used to fit the predicted trajectory of each ship according to the position information and the predicted position in combination with the time axis;

[0100] The alarm module 204 is used to determine the collision risk of each ship in the target sea area based on the predicted trajectory and generate alarm information.

[0101] In one possible implementation, an electronic device includes a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor implements the following steps when executing the computer program: obtaining navigation data of each ship in a target sea area, the navigation data including at least position information, historical trajectory information, heading information, and speed information; predicting the predicted position of each ship at different times based on the navigation data, a preset time interval, and a preset generative adversarial network; fitting the predicted trajectory of each ship based on the position information and the predicted position in combination with a time axis; and judging the collision risk of each ship in the target sea area based on the predicted trajectory, and generating an alarm message.

[0102] In one possible implementation, an embodiment of the present application 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 following steps are implemented: obtaining navigation data of each ship in the target sea area, wherein the navigation data includes at least position information, historical trajectory information, heading information and speed information; predicting the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network; fitting the predicted trajectory of each ship based on the position information and the predicted position in combination with the time axis; judging the collision risk of each ship in the target sea area based on the predicted trajectory, and generating an alarm message.

[0103] Those of ordinary skill in the art will appreciate that the units and algorithm steps of each example described in conjunction with the embodiments disclosed herein can be implemented in electronic hardware, or a combination of computer software and electronic hardware. Whether these functions are performed in hardware or software depends on the specific application and design constraints of the technical solution. Professional and technical personnel can use different methods to implement the described functions for each specific application, but such implementation should not be considered to be beyond the scope of this application.

[0104] In the embodiments provided in the present application, it should be understood that the disclosed devices / network equipment / terminal equipment and methods can be implemented in other ways. For example, the device / network equipment / terminal equipment embodiments described above are only schematic. For example, the division of the modules or units is only a logical function division. There may be other division methods in actual implementation, such as multiple units or components can be combined or integrated into another system, or some features can be ignored or not executed. Another point is that the mutual coupling or direct coupling or communication connection shown or discussed can be through some interfaces, indirect coupling or communication connection of devices or units, which can be electrical, mechanical or other forms.

[0105] The units described as separate components may or may not be physically separated, and the components shown as units may or may not be physical units, that is, they may be located in one place or distributed on multiple network units. Some or all of the units may be selected according to actual needs to achieve the purpose of the solution of this embodiment.

[0106] The embodiments described above are only used to illustrate the technical solutions of the present application, rather than to limit them. Although the present application has been described in detail with reference to the aforementioned embodiments, a person skilled in the art should understand that the technical solutions described in the aforementioned embodiments may still be modified, or some of the technical features may be replaced by equivalents. Such 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 application, and should all be included in the protection scope of the present application.

Claims

1. A ship collision warning method, characterized in that: include: Acquire navigation data of each ship in the target sea area, wherein the navigation data at least includes location information, historical track information, heading information and speed information; Acquire tonnage data of each ship in the target sea area, and determine a preset time interval based on the tonnage data, wherein the preset time interval is positively correlated with the tonnage data; Predicting the predicted positions of each ship at different times based on the navigation data, the preset time interval and the preset generative adversarial network; The step of predicting the predicted position of each ship at different times based on the navigation data, the preset time interval and the preset generative adversarial network includes: If the location information matches the historical prediction information, obtaining the target time corresponding to the predicted location; Obtaining historical trajectory information of each preset time interval before the target moment, inputting the preset time interval, the historical trajectory information of each preset time interval, the position information of the ship at a previous node at the target moment, the heading information of the ship at the previous node at the target moment, and the speed information of the ship at the previous node at the target moment into a preset generative adversarial network, and predicting the predicted position of the ship at the target moment, wherein the previous node at the target moment is a time node before the target moment and at a preset time interval from the target moment; If the position information does not match the historical prediction information, the preset time interval, the actual historical trajectory, the position information of the last point in the actual historical trajectory in chronological order, the heading information of the ship at the last point, and the speed information of the ship at the last point are input into a preset generative adversarial network to predict the predicted position of the ship at different times; Before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes: Acquire historical prediction information corresponding to the target ship and the position information; Matching the position information with the historical prediction information, and if the position information does not match the historical prediction information, obtaining the actual historical track of the target ship as the historical track information in the navigation data; If the position information matches the historical prediction information, the historical prediction information is corrected based on the position information to obtain corrected data, and based on the corrected data, a historical prediction trajectory is generated through a step-wise prediction strategy, and the historical prediction trajectory is used as the historical trajectory information in the navigation data; According to the position information and the predicted position, the predicted trajectory of each ship is fitted in combination with the time axis; Based on the predicted trajectory, the collision risk of each ship in the target sea area is determined, and an alarm message is generated; The step of judging the collision risk of each ship in the target sea area based on the predicted trajectory and generating alarm information includes: The predicted trajectories of the various ships are plotted on the same nautical chart to obtain a target nautical chart, and the collision risk of the various ships in the target sea area is determined based on the minimum distance between the predicted trajectories in the target nautical chart; The step of judging the collision risk of each ship in the target sea area based on the minimum distance between each predicted track in the target sea chart comprises: If the two predicted tracks in the target chart do not intersect and / or overlap at any time point in the future, and the minimum distance between the two predicted tracks is greater than or equal to the threshold, the two ships corresponding to the two predicted tracks are judged to be in a low risk state, and no alarm information is generated; If the two predicted tracks in the target chart do not intersect and / or overlap at any future time point, and the minimum distance between the two predicted tracks is less than the threshold, it is determined that the two ships corresponding to the two predicted tracks are in a medium risk state, and a medium risk warning message is generated; If the two predicted tracks in the target chart intersect and / or overlap at any time point in the future, it is judged that the two ships corresponding to the two predicted tracks are in a high-risk state, and a high-risk warning message is generated.

2. The ship collision warning method according to claim 1, characterized in that: The step of obtaining navigation data of each ship in the target sea area includes: Acquire first identification information and first navigation data of known ships in the target sea area through the AIS base station in the VTS system; Acquiring second identification information and second navigation data of unknown ships in the target sea area through a ship-side radar of any ship in the target sea area; Based on the first identification information and the second identification information, the first navigation data and the second navigation data are integrated into the same electronic nautical chart to obtain the navigation data of each ship in the target sea area.

3. The ship collision warning method according to claim 1, characterized in that: The method further comprises: When there are medium-risk and / or high-risk ships in the target chart, the medium-risk and / or high-risk ships shall be regarded as risk ships; The attribute data of the risk ship is obtained, and based on the attribute data, a risk level is set for the medium risk warning information and / or the high risk warning information of the risk ship according to a preset rule.

4. A ship collision warning device, characterized in that: The device comprises: A data acquisition module is used to obtain navigation data of each ship in the target sea area, wherein the navigation data at least includes location information, historical track information, heading information and speed information; obtain tonnage data of each ship in the target sea area, and determine a preset time interval based on the tonnage data, wherein the preset time interval is positively correlated with the tonnage data; A prediction module, used to predict the predicted position of each ship at different times based on the navigation data, a preset time interval and a preset generative adversarial network; The step of predicting the predicted position of each ship at different times based on the navigation data, the preset time interval and the preset generative adversarial network includes: If the location information matches the historical prediction information, obtaining the target time corresponding to the predicted location; Obtaining historical trajectory information of each preset time interval before the target moment, inputting the preset time interval, the historical trajectory information of each preset time interval, the position information of the ship at a previous node at the target moment, the heading information of the ship at the previous node at the target moment, and the speed information of the ship at the previous node at the target moment into a preset generative adversarial network, and predicting the predicted position of the ship at the target moment, wherein the previous node at the target moment is a time node before the target moment and at a preset time interval from the target moment; If the position information does not match the historical prediction information, the preset time interval, the actual historical trajectory, the position information of the last point in the actual historical trajectory in chronological order, the heading information of the ship at the last point, and the speed information of the ship at the last point are input into a preset generative adversarial network to predict the predicted position of the ship at different times; Before the step of predicting the predicted position of each ship based on the navigation data, the preset time interval and the preset generative adversarial network, the method further includes: Acquire historical prediction information corresponding to the target ship and the position information; Matching the position information with the historical prediction information, and if the position information does not match the historical prediction information, obtaining the actual historical track of the target ship as the historical track information in the navigation data; If the position information matches the historical prediction information, the historical prediction information is corrected based on the position information to obtain corrected data, and based on the corrected data, a historical prediction trajectory is generated through a step-wise prediction strategy, and the historical prediction trajectory is used as the historical trajectory information in the navigation data; A trajectory generation module, used to fit the predicted trajectory of each ship according to the position information and the predicted position in combination with the time axis; An alarm module, used to determine the collision risk of each ship in the target sea area based on the predicted trajectory and generate alarm information; The step of judging the collision risk of each ship in the target sea area based on the predicted trajectory and generating alarm information includes: The predicted trajectories of the various ships are plotted on the same nautical chart to obtain a target nautical chart, and the collision risk of the various ships in the target sea area is determined based on the minimum distance between the predicted trajectories in the target nautical chart; The step of judging the collision risk of each ship in the target sea area based on the minimum distance between each predicted track in the target sea chart comprises: If the two predicted tracks in the target chart do not intersect and / or overlap at any time point in the future, and the minimum distance between the two predicted tracks is greater than or equal to the threshold, the two ships corresponding to the two predicted tracks are judged to be in a low risk state, and no alarm information is generated; If the two predicted tracks in the target chart do not intersect and / or overlap at any future time point, and the minimum distance between the two predicted tracks is less than the threshold, it is determined that the two ships corresponding to the two predicted tracks are in a medium risk state, and a medium risk warning message is generated; If the two predicted tracks in the target chart intersect and / or overlap at any time point in the future, it is judged that the two ships corresponding to the two predicted tracks are in a high-risk state, and a high-risk warning message is generated.

5. A terminal device, comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 3 is implemented.

6. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 3 is implemented.

Images