Wave berth planning method and device for marine vessels

Abstract

The application provides a berth planning method and device for a marine ship. The berth planning method comprises the following steps: acquiring a berth number and corresponding first sailing time and second sailing time, wherein the second sailing time is obtained based on a pre-trained network model; obtaining third sailing time based on the first sailing time and the second sailing time; and uploading the first sailing time, the third sailing time and the berth number to a satellite, so that the satellite serves a berth corresponding to the berth number within a time period from the first sailing time to the third sailing time. The time of the gazing scene in the application is divided into multiple time domains, and the berth number of the gazing can be added according to the prediction result in each time domain, so that a time-domain-divided gazing scene is finally formed. Compared with the existing satellite gazing scheme, the ship communication can be effectively guaranteed, and the allocation and utilization efficiency of satellite resources can be optimized.

Description

TECHNICAL FIELD

[0001] The present application relates to the technical field of satellite communication, and in particular to a wave position planning method and device for marine ships. BACKGROUND

[0002] Wave position planning is performed by a satellite network management system, and the entire process includes that the satellite network management system calculates a basic wave position list that needs to be covered by a satellite in the future in advance, and then uploads the basic wave position list to the satellite, and then the satellite performs beam scheduling based on the basic wave position list to realize coverage of a specific wave position. The wave position planning supports two scenarios of full coverage and staring, the full coverage scenario refers to that the satellite performs beam scanning on all wave positions in its coverage area to meet the communication requirements of all wave positions in the coverage area. The staring scenario refers to that the satellite performs beam coverage on several specific wave positions in its coverage area, and the satellite only guarantees the communication requirements of the wave positions covered by the beam.

[0003] For users of ocean-going ships, staring can usually be used to guarantee communication, but if the existing wave position staring method is used to perform full-period staring on the wave positions that the ship may pass through, satellite resources will be greatly wasted. Therefore, there is an urgent need for a wave position planning method for marine ships to effectively guarantee the communication coverage of marine ships while reducing the waste of satellite resources. SUMMARY

[0004] In view of the above, the present application provides a wave position planning method and device for marine ships to solve at least one of the above problems.

[0005] To achieve the above purpose, the present application adopts the following scheme:

[0006] According to a first aspect of the present application, a wave position planning method for marine ships is provided, the method comprising: obtaining a wave position number and corresponding first sailing time and second sailing time, the second sailing time being obtained based on a pre-trained network model; obtaining third sailing time based on the first sailing time and the second sailing time; uploading the first sailing time, the third sailing time and the wave position number to a satellite, so that the satellite serves a wave position corresponding to the wave position number in a period from the first sailing time to the third sailing time.

[0007] As an embodiment of the present application, in the above method, obtaining the wave position number comprises determining the wave position number based on the coordinates of the trajectory points.

[0008] As an embodiment of the present application, in the above method, obtaining the third sailing time based on the first sailing time and the second sailing time comprises adding the first sailing time and the second sailing time to obtain the third sailing time.

[0009] As an embodiment of the present application, the method further comprises: obtaining ship attribute data and environment data; inputting a feature matrix comprising the berth number, the ship attribute data and the environment data into a pre-trained network model to obtain the second sailing time.

[0010] As an embodiment of the present application, the method further comprises: converting the ship attribute data and the environment data into digital codes after obtaining the ship attribute data and the environment data.

[0011] As an embodiment of the present application, the ship attribute data comprises ship type and ship load, and the environment data comprises wind direction and wave height, and the conversion of the ship attribute data and the environment data into digital codes comprises: digitally numbering all ship types and binary coding the ship types according to the digital numbers; digitally valuing the ship load in tons; binary coding and converting the wind direction according to a binary coding correspondence table; converting the wind force level and the wave height level into corresponding level numbers based on a preset standard.

[0012] As an embodiment of the present application, the method further comprises: obtaining a fourth sailing time and a fifth sailing time of a corresponding berth according to the berth number; obtaining a sixth sailing time corresponding to the fourth sailing time and the fifth sailing time; and obtaining the feature matrix based on the berth number, the sixth sailing time, the ship attribute data and the environment data.

[0013] As an embodiment of the present application, the obtaining of the fourth sailing time and the fifth sailing time of the corresponding berth according to the berth number comprises: determining a target berth according to the berth number; calculating a distance relationship between a trajectory point coordinate and a boundary of the target berth; determining a target trajectory point for entering or exiting the target berth based on the distance relationship; and determining the corresponding fourth sailing time and the fifth sailing time according to the target trajectory point.

[0014] As an embodiment of the present application, the method further comprises: obtaining historical trajectory data, historical ship attribute data and historical environment data; obtaining historical stay times of the ship in each berth based on the historical trajectory data; associating the berth number of each berth, the historical stay time, the historical ship attribute data, the historical environment data and the actual stay time of each berth known to form a training data set; and training a model using the training data set to obtain the network model.

[0015] According to a second aspect of the present application, a berth planning method for a marine vessel is provided, the method comprising: receiving a berth number and corresponding predicted entry time and predicted exit time; and serving the berth corresponding to the berth number based on the predicted entry time and the predicted exit time.

[0016] According to a third aspect of the present application, a berth planning device for a marine vessel is provided, the device comprising: a first data acquisition unit configured to acquire a berth number and corresponding first sailing time and second sailing time, the second sailing time being obtained based on a pre-trained network model; a second data acquisition unit configured to obtain a third sailing time based on the first sailing time and the second sailing time; and a data uploading unit configured to upload the first sailing time, the third sailing time and the berth number to a satellite, so that the satellite serves the berth corresponding to the berth number within a period from the first sailing time to the third sailing time.

[0017] As an embodiment of the present application, the first data acquisition unit comprises a number acquisition module configured to determine the berth number based on a trajectory point coordinate.

[0018] As an embodiment of the present application, the second data acquisition unit is specifically configured to add the first sailing time and the second sailing time to obtain the third sailing time.

[0019] As an embodiment of the present application, the first data acquisition unit comprises: an influence data acquisition module configured to acquire vessel attribute data and environment data; and a berth sailing time acquisition module configured to input a feature matrix comprising the berth number, the vessel attribute data and the environment data into a pre-trained network model to obtain the second sailing time.

[0020] As an embodiment of the present application, the first data acquisition unit further comprises a digital encoding module configured to convert the vessel attribute data and the environment data into digital codes.

[0021] As an embodiment of the present application, the vessel attribute data comprises a vessel type and a vessel load, the environment data comprises a wind direction and a wave height, and the digital encoding module comprises: a vessel type encoding submodule configured to digitally number all vessel types and to binary encode the vessel types according to the digital numbers; a vessel load encoding submodule configured to digitally value the vessel load in tons; a wind direction encoding submodule configured to binary encode the wind direction according to a binary code corresponding table; and a wind force and wave height encoding submodule configured to convert a wind force level and a wave height level into corresponding level numbers based on a preset standard.

[0022] As an embodiment of the present application, the first data acquisition unit further comprises: a planned in-out time acquisition module, configured to obtain a fourth sailing time and a fifth sailing time of a corresponding berth according to the berth number; a planned stay time acquisition module, configured to obtain a sixth sailing time according to the fourth sailing time and the fifth sailing time; and a feature matrix acquisition module, configured to obtain the feature matrix based on the berth number, the sixth sailing time, the ship attribute data and the environment data.

[0023] As an embodiment of the present application, the planned in-out time acquisition module comprises: a target berth determination submodule, configured to determine a target berth according to the berth number; a distance calculation submodule, configured to calculate a distance relationship between a trajectory point coordinate and a boundary of the target berth; a target trajectory point determination submodule, configured to determine a target trajectory point for entering or exiting the target berth based on the distance relationship; and a planned in-out time determination submodule, configured to determine the fourth sailing time and the fifth sailing time according to the target trajectory point.

[0024] As an embodiment of the present application, the device further comprises: a historical data acquisition unit, configured to acquire historical trajectory data, historical ship attribute data and historical environment data; a historical stay time acquisition unit, configured to obtain historical stay times of a ship in each berth based on the historical trajectory data; a training data set construction unit, configured to associate the berth number of each berth, the historical stay times, the historical ship attribute data, the historical environment data and actual stay times of each berth known to construct a training data set; and a network training unit, configured to perform model training using the training data set to obtain the network model.

[0025] According to a fourth aspect of the present application, a berth planning device for a marine ship is provided, the device comprising: a data receiving unit, configured to receive a berth number and corresponding predicted entering time and predicted exiting time; and a berth service unit, configured to serve a berth corresponding to the berth number based on the predicted entering time and the predicted exiting time.

[0026] According to a fifth aspect of the present application, an electronic device is provided, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, wherein the processor implements the steps of the above method when executing the computer program.

[0027] According to a sixth aspect of the present application, a computer readable storage medium is provided, having a computer program stored thereon, wherein the computer program is executed by a processor to implement the steps of the above method.

[0028] According to a seventh aspect of the present application, there is provided a computer program product comprising computer programs / instructions which, when executed by a processor, implement the steps of the above method.

[0029] Other features and advantages of the present application will be set forth in the following description, and in part will become apparent to those skilled in the art upon examination of the following or can be learned by practice of the present application. The objects and other advantages of the present application can be realized and attained by the structure particularly pointed out in the written description and claims hereof as well as the appended drawings. BRIEF DESCRIPTION OF DRAWINGS

[0030] In order to more clearly illustrate the technical solutions in the embodiments of the present application or the prior art, the drawings needed to be used in the embodiments or prior art description will be briefly introduced as follows. Obviously, the drawings in the following description are only some embodiments of the present application, and for those skilled in the art, other drawings can also be obtained from these drawings without creative labor. In the drawings:

[0031] Figure 1 is a flowchart of a wave berth planning method for a marine vessel provided by an embodiment of the present application;

[0032] Figure 2 is a flowchart of determining a wave berth number based on a trajectory point coordinate provided by an embodiment of the present application;

[0033] Figure 3 is a schematic diagram of a wave berth number sequence of a navigation trajectory provided by an embodiment of the present application;

[0034] Figure 4 is a flowchart of obtaining a second navigation time provided by an embodiment of the present application;

[0035] Figure 5 is a flowchart of converting ship attribute data and environment data into digital codes provided by an embodiment of the present application;

[0036] Figure 6 is a schematic diagram of a binary code correspondence table provided by an embodiment of the present application;

[0037] Figure 7 is a flowchart of obtaining a feature matrix provided by an embodiment of the present application;

[0038] Figure 8 is a flowchart of obtaining a fourth navigation time and a fifth navigation time of a marine vessel passing through a wave berth according to a wave berth number provided by an embodiment of the present application;

[0039] Figure 9 is a schematic diagram of a target in-out wave berth provided by an embodiment of the present application;

[0040] Figure 10 is a structural diagram of an improved BiGRU-Attention model provided by an embodiment of the application;

[0041] Figure 11 is a schematic diagram of a training process of a network model provided by an embodiment of the application;

[0042] Figure 12 is a training flowchart for pre-processing a historical trajectory spatio-temporal sequence provided by an embodiment of the application;

[0043] Figure 13 is a simplified schematic diagram of a network model provided by an embodiment of the application;

[0044] Figure 14 is a flowchart of a berth planning method for a marine ship provided by another embodiment of the application;

[0045] Figure 15 is a structural diagram of a berth planning device for a marine ship provided by an embodiment of the application;

[0046] Figure 16 is a structural diagram of a first data acquisition unit provided by an embodiment of the application;

[0047] Figure 17 is a structural diagram of a first data acquisition unit provided by another embodiment of the application;

[0048] Figure 18 is a structural diagram of a first data acquisition unit provided by another embodiment of the application;

[0049] Figure 19 is a structural diagram of a digital coding module provided by an embodiment of the application;

[0050] Figure 20 is a structural diagram of a first data acquisition unit provided by another embodiment of the application;

[0051] Figure 21 is a structural diagram of a planning in-out time acquisition module provided by an embodiment of the application;

[0052] Figure 22 is a structural diagram of a berth planning device for a marine ship provided by an embodiment of the application;

[0053] Figure 23 is a schematic block diagram of a system structure of an electronic device provided by an embodiment of the application. DETAILED DESCRIPTION

[0054] In order to make the purpose, technical solutions and advantages of the embodiments of the present application more clear, the embodiments of the present application are further described in detail below with reference to the accompanying drawings. Here, the illustrative embodiments of the present application and their descriptions are used to explain the present application, but are not intended to limit the present application.

[0055] The information collected in the technical solution of this application is information and data authorized by the user or fully authorized by all parties, and the collection, storage, use, processing, transmission, provision, disclosure and application of relevant data comply with the relevant laws, regulations and standards of relevant countries and regions, take necessary confidentiality measures, do not violate public order and good morals, and provide corresponding operation entrances for users to choose to authorize or refuse.

[0056] The acquisition, transmission, storage, use, and processing of data in the technical solution of this application comply with the relevant provisions of national laws and regulations.

[0057] It should be noted that in the embodiments of the present application, certain software, components, models and other existing solutions in the industry may be mentioned. They should be regarded as exemplary. Their purpose is only to illustrate the feasibility of implementing the technical solution of the present application, but it does not mean that the applicant has or will necessarily use the solution.

[0058] like Figure 1 FIG. 1 is a flow chart of a method for wave position planning for a maritime vessel provided in an embodiment of the present application. This embodiment describes the present application from the perspective of a satellite network management system. The method includes the following steps:

[0059] Step S101: Acquire a wave position number and a corresponding first flight time and second flight time, where the second flight time is obtained based on a pre-trained network model.

[0060] In this embodiment, the beam position number is a unique identifier for the target beam position, which is used to determine the specific geographical area that the satellite needs to cover. The first navigation time is the estimated starting time for the ship to enter the target beam position, which can be understood as the predicted moment when the ship reaches the boundary of the target beam position. The second navigation time is the estimated length of time the ship will sail within the target beam position, which can be understood as the predicted time the ship will stay in the target beam position, which can be obtained through a pre-trained network model. Therefore, in this embodiment, the first navigation time is a time point, such as Xh:Xm, Xm, Xm, Xm, 20XX; while the second navigation time is a time period, such as 5 hours.

[0061] Step S102: Obtain a third flight time based on the first flight time and the second flight time.

[0062] In this embodiment, the third sailing time is the estimated time for the ship to leave the target wave position, which is also a time point. After the first sailing time for entering the target wave position and the second sailing time for staying at the target wave position are obtained in step S101, the third sailing time of this step can be calculated by adding the first sailing time and the second sailing time.

[0063] Since adjacent wave positions share a common boundary, the third flight time for each wave position is the first flight time of the next adjacent wave position. Therefore, after obtaining the estimated flight time length (second flight time) for each wave position, the predicted wave position flight times are accumulated based on the departure time to obtain the first and third flight times for each wave position. For example, the first wave position is numbered 1, the first flight time is the departure time, and the second flight time is a specific number of predicted times. The third flight time is calculated as the departure time plus the second flight time. This third flight time can then be used as the first flight time for the next wave position numbered 2.

[0064] Assume that the wave position number sequence of the ship is {b1, b2, ..., b m}, m is the number of waves that the ship's planned route passes through; it can be calculated based on the ship's departure time. T 0 , wave number sequence {b1, b2, ..., b m} and the predicted sailing time of the ship at different wave positions {t1, t2, ..., t m}, we can get the ship's entry wave position b x The time is , exit wave position b x The time is , where x∈[1,m].

[0065] Step S103: the first flight time, the third flight time and the wave position number are added to the satellite, so that the satellite provides service for the wave position corresponding to the wave position number during the period from the first flight time to the third flight time.

[0066] The first navigation time (estimated entry time) and the third navigation time (estimated departure time) and the corresponding wave position number in this step are a kind of wave position planning information. The satellite network management system notifies the satellite of the estimated entry time, estimated departure time and corresponding wave position number of the ship that needs attention. After receiving this information, the satellite can perform subsequent beam scheduling and resource allocation based on this information, so as to provide effective communication coverage and guarantee when the ship sails to a specific wave position.

[0067] In the present embodiment, the satellite network management system can be modified as follows to accommodate the wave position planning method of the present application:

[0068] 1. The satellite network management system front-end page supports inputting the gazing wave position number and the corresponding time interval.

[0069] 2. The gazing wave position number and the time interval support dynamic maintenance, and can be added or deleted on the front-end page.

[0070] 3. A configuration is added to the front-end, which can select to add a gazing position or a wave position number to the satellite.

[0071] After the satellite network management system obtains the predicted entry time, the predicted exit time, and the corresponding wave position number, it can select a suitable satellite for adding by the following five stages:

[0072] Stage one: For each gazing position, all satellites are traversed, the distance between the gazing position and each satellite is calculated, and the associated satellite and the neighboring satellite of the gazing position are determined accordingly.

[0073] Stage two: All gazing positions are traversed, and the stage one process is performed to obtain the associated satellite and the neighboring satellite of all gazing positions.

[0074] Stage three: All snapshot times are traversed, and if the snapshot time belongs to the time interval of the gazing wave position, the stage one and stage two processes are performed to obtain the associated wave position of all satellites at all snapshot times in the time interval.

[0075] Stage four: For a specific satellite at a snapshot T, the in-out wave position identifier of all associated wave positions in the snapshot is determined by comparing the associated wave positions of the specific satellite at snapshot T-1 and snapshot T+1, all satellites at snapshot T are traversed, and all snapshots are traversed.

[0076] Stage five: Backfill operation is performed for all exit wave positions.

[0077] As can be seen from the above, the wave position planning method of the present application divides the time of the gazing scenario into multiple time domains, each time domain can add the wave position number of the gazing according to the prediction result, and finally forms a time-domain gazing scenario. Compared with the existing satellite gazing scheme, not only can the ship communication be effectively guaranteed, but also the allocation and utilization efficiency of satellite resources can be optimized. The method of the present application is particularly suitable for providing high-priority uninterrupted communication services for key users on the sea (such as research vessels, important transport fleets, offshore operation platforms, etc.).

[0078] In one embodiment of the present application, obtaining the wave position number in step S101 includes determining the wave position number based on the track point coordinates. Maritime transport routes are typically planned in advance. Nearshore voyages are typically planned three to four days in advance, while ocean voyages are typically planned one to two weeks in advance. A planned route is the vessel's intended route, typically consisting of a set of latitude and longitude coordinates (track point coordinates) or flight segments. Therefore, the wave position numbers of the wave positions passed through in this step can be obtained from the vessel's planned route.

[0079] In another embodiment of the present application, the above-mentioned determination of the wave position number based on the trajectory point coordinates may further include the following: Figure 2 Steps shown:

[0080] Step S201: extracting the coordinates of the track points from the planned route of the ship at sea.

[0081] As previously discussed, a planned route typically consists of a sequence of ordered trackpoint coordinates, which, when connected, form the vessel's intended navigation path. By extracting the trackpoint coordinates from the planned route, we can construct a trackpoint coordinate sequence, where each element represents a key location in the vessel's planned voyage.

[0082] The planned route can also include time information, that is, each trajectory point coordinate can correspond to the expected time point information. Therefore, the trajectory point coordinates extracted from the planned route can also form a trajectory time-space sequence with the time information. Each element in the trajectory time-space sequence represents each key position of the ship's planned voyage and the corresponding planned time point.

[0083] The planned route may not directly include the coordinates of the trajectory points and the corresponding time information. In this case, the static planned route can be converted into a dynamic, time-stamped trajectory space-time sequence in the following way: First, the continuous planned route is divided into a series of sufficiently dense discrete trajectory points (for example, one point is taken every small distance or a small period of time), and each trajectory point has its latitude and longitude coordinates. Then, based on the departure time of the ship and an initial speed model (for example, the design speed of the ship, the average planned speed, or the constant speed assumption within a voyage), the estimated time for the ship to arrive at each discrete trajectory point is estimated. In this way, the trajectory space-time sequence of the ship to be served can be obtained, which contains the trajectory points and the corresponding timestamp information. For example, the trajectory space-time sequence can be [(t 1， lon 1， lat1),(t 2， lon 2， lat2),...,(t n， lon n， lat n )], where t1-tn lon n , lat n are longitude and latitude coordinates.

[0084] The planned route of the ship can exist in multiple formats, but it can be uniformly extracted into a standard sequence of track point coordinates through this step.

[0085] Step S202: Obtain the corresponding wave position number based on the track point coordinates.

[0086] In satellite Internet, the entire surface of the earth is divided into a plurality of basic wave positions, and the position of each basic wave position on the ground is fixed, so a track point coordinate must correspond to a wave position number. In this step, each track point in the sequence of track point coordinates or the sequence of track space-time can be traversed. For the longitude and latitude coordinates of each track point, a query is performed in the basic wave position definition data to determine which predefined basic wave position region the longitude and latitude coordinates fall into, and then the unique wave position number of the basic wave position is recorded.

[0087] If a track point exactly falls on the boundary of two basic wave positions, a wave position number can be assigned by a preset rule, for example, selecting the wave position corresponding to the expected service satellite with better signal quality, or selecting according to a certain priority, etc.

[0088] Through this step, geographic spatial information (coordinates) can be converted into wave position information directly related to the satellite system, so that the route data can be directly served for satellite wave position planning.

[0089] Step S203: Perform a de-duplication operation on the obtained wave position number.

[0090] Since a wave position usually includes a plurality of track points, the wave position number obtained in step S202 needs to be de-duplicated, that is, only one of the repeated wave position numbers is retained, so that a track wave position number set in which all wave position numbers are unique can be obtained, and the track wave position number set is a wave position number sequence. Figure 3 As shown in FIG. 6, a wave position number sequence of a navigation track provided by an embodiment of the present application is shown, in which a hexagon represents a wave position, an arrow represents a navigation track, and a gray diagram represents a wave position passed through by the ship. Through this step, a clear and non-redundant wave position number list can be provided.

[0091] It should be noted that the operations of steps S101 to S103 above are performed for each wave position number in the wave position number list, so that satellite communication services can be provided for the ship at all times during navigation.

[0092] In another embodiment of the present application, as shown in FIG. 7, a wave position number sequence of a navigation track provided by an embodiment of the present application is shown, in which a hexagon represents a wave position, an arrow represents a navigation track, and a gray diagram represents a wave position passed through by the ship. Through this step, a clear and non-redundant wave position number list can be provided. Figure 4As shown, the acquiring of the second sailing time in step S101 can include:

[0093] Step S401: acquiring ship attribute data and environment data.

[0094] The ship attribute data refers to data related to the characteristics of the ship itself, which can affect its sailing speed and stability, including but not limited to: ship type, ship load, ship size, designed speed of the ship, ship age, etc. The environment data refers to factors that can affect the sailing state of the ship in the environment during sailing, including but not limited to: meteorological data such as wind power, wind direction, visibility, etc.; hydrological data such as ocean current direction, wave height, flow rate, tide, etc.

[0095] In an embodiment of the present application, the ship attribute data is selected as the ship type and the ship load, because the ship type directly determines the basic characteristics of the ship, such as the hydrodynamic shape, the designed speed range, the power system configuration, etc. The ship load can significantly change the displacement and the wet surface area of the ship, thereby directly affecting the water resistance and then the actual speed under a certain main engine power. Relative to other internal factors, these two factors have a higher weight on the sailing time and are easier to obtain. This data can be directly obtained from the Automatic Identification System (AIS).

[0096] The environment data is selected as meteorological data and hydrological data, among which the meteorological data is selected as wind power and wind direction data, and the hydrological data is selected as wave height data. Wind power and wind direction are standard meteorological forecast parameters, with mature forecast models and data services, and are relatively easy to obtain and quantify. Wave height is one of the most core and most intuitive parameters to describe sea conditions, and is also a standard output in marine environment prediction. This environment data can be obtained from a third-party system, and here the obtained is a forecast value, i.e. the corresponding meteorological and hydrological data forecast value within the time and space range of the planned route.

[0097] Of course, the selection of the above ship attribute data and environment data is not limited in the present application, and in other embodiments of the present application, more internal and external influencing factors can be added to obtain more accurate prediction results.

[0098] In another embodiment of the present application, after acquiring the ship attribute data and environment data that affect the sailing state of the ship, the step further includes: converting the ship attribute data and environment data into digital codes.

[0099] This is to convert various types of ship attribute data and environment data into numerical formats that can be processed by machine learning models, and to integrate them with sailing information later.

[0100] In another embodiment of the present application, as Figure 5 The converting the ship attribute data and the environment data into digital codes in this step can further include:

[0101] Step S501: digitally numbering all ship types and binary coding the ship types according to the digital numbers.

[0102] In this step, first, all ship types are digitally numbered, for example, a list of ship types can be predefined (for example, container ship, bulk carrier, oil tanker, LNG ship, passenger ship, etc.). Then, each type of ship in the list is assigned a unique digital number. For example, container ship: number 1, bulk carrier: number 2, oil tanker: number 3,..., etc. Then, the ship types are binary coded according to the above numbers, that is, the decimal number is converted to binary form.

[0103] If the number of ship types is not large, the number can be directly converted to its standard binary form (for example, number 3 is directly converted to binary "11"). The number can also be converted to binary form in one-hot encoding, such as converting the above container ship to [1, 0, 0], bulk carrier to [0, 1, 0], and oil tanker to [0, 0, 1]. The specific conversion method is not limited in this embodiment.

[0104] Step S502: digitally valuing the ship load in tons.

[0105] For the continuous numerical variable "ship load", this embodiment directly digitally values it. Generally, the ship load is in tons, and this information is directly recorded in AIS, so it can be directly obtained and digitally valued from AIS.

[0106] Step S503: binary coding conversion of wind direction according to the binary coding correspondence table.

[0107] In this embodiment, a binary coding correspondence table is first prepared, in which 8 basic wind directions (east, south, west, north, southeast, southwest, northeast, northwest) are corresponded to binary codes, and then the corresponding wind direction can be converted to binary code by querying the binary coding correspondence table. The specific example of the binary coding correspondence table can be seen from Figure 6 Of course, the division of wind direction can be more detailed, such as 16 basic wind directions, which is not limited in this application.

[0108] Step S504: converting the wind force level and wave level into corresponding level numbers based on a preset standard.

[0109] In the present embodiment, the definition of wind force level can adopt the Typhoon Business and Service Regulation issued by the Meteorological Bureau, and the wind force level is set to 0-17, a total of 18 levels; and the wave height level also adopts the standard level division method, such as the internationally used sea state level table.

[0110] Through the above steps S501-S504, the selected ship attribute data and environment data can be converted from the original form to a numerical or binary coded form that is easier for the machine learning model to understand and process.

[0111] Step S402: input the feature matrix containing the berth number, ship attribute data and environment data into the pre-trained network model to obtain the second sailing time.

[0112] The processed berth number, ship attribute data and environment data are combined into a structured data set, which is a feature matrix, which is usually a two-dimensional matrix, each row representing a sample (a specific berth sailing time prediction), and each column representing a feature.

[0113] The pre-trained network model here refers to a neural network model that has been learned and optimized through historical data. The network model can be a deep neural network (DNN), a recurrent neural network (RNN), a long short-term memory network (LSTM), a gated recurrent unit (GRU), etc. The feature matrix constructed for the current ship and berth to be predicted is input into this trained network model, and the model uses its internal learned parameters and weights to calculate and infer, and finally outputs a prediction value, i.e. the ship is expected to sail in the specific berth for a length of time (for example, 3.5 hours).

[0114] In an embodiment of the present application, the above method further includes a feature matrix acquisition process, as shown in Figure 7 which includes the following steps:

[0115] Step S701: obtain the fourth sailing time and the fifth sailing time of the corresponding berth according to the berth number.

[0116] The fourth sailing time here is the planned entry time of the berth, and the fifth sailing time is the planned exit time of the berth, i.e. the entry and exit time of a specific berth in the route planning. The purpose of this step is to calculate the specific time points at which the ship enters and leaves each passing berth in the route planning. As shown in Figure 8 this step can further include the following sub-steps:

[0117] Step S7011: determine the target berth according to the berth number.

[0118] Step S7012: Calculate the distance relationship between the trajectory point coordinates and the target wave position boundary.

[0119] Step S7013: Based on the distance relationship, determine the target trajectory point entering or exiting the target wave position.

[0120] Step S7014: Determine the corresponding planned entry time and planned exit time according to the target trajectory point.

[0121] Specifically, after determining the target wave position according to the wave position number, the distance between the coordinates of each track point of the ship and the longitude and latitude coordinates of the six wave position boundary points of the target wave position can be calculated first.

[0122] Assume that the ship has n track points, and the wave positions it passes through are numbered 3-9. When the target wave position is number 3, calculate the longitude and latitude coordinates (lon i ,lat i ), i∈(0, n+1) and the six wave positions (lon j ,lat j ), i∈[1,6] The distance L between the longitude and latitude coordinates of the boundary point ij , the distance calculation formula uses the haversine equation, which is as follows:

[0123] ;

[0124] Then, the two boundary points with the shortest distance from the current trajectory point are selected to obtain the distance between the current trajectory point and the two boundary points. The distances between all trajectory points and the two boundary points with the shortest distance can form a first distance sequence. The first distance sequence can be expressed as {L im , L in}, i∈(0, n+1), m, n∈[1, 6], i is the trajectory point number, m, n are the two boundary points with the shortest distance to the trajectory point i.

[0125] Then, the distance between each trajectory point and the two corresponding boundary points with the shortest distance is added to obtain the second distance sequence. im +L in ), the second distance sequence obtained is L' i , i∈(0,n+1).

[0126] Finally, the two smallest values ​​in the second distance sequence are selected as the distance values ​​corresponding to the target trajectory points of the ship to be served entering or leaving the target wave position, and the time corresponding to the target trajectory point is the time when the ship to be served enters and leaves each wave position.

[0127] The methods of steps S7011-S7014 can be found in Figure 9 As shown, the sum of the distances from point i to the boundary points O1 and O2 is the shortest, and the sum of the distances from point j to the boundary points O3 and O4 is the shortest. Therefore, points i and j are the trajectory points entering or leaving the current wave position. Whether it is entering or leaving can be determined according to the heading or the timestamp of the trajectory point. Figure 9 For example, the wave position boundary determined by O1 and O2 is the boundary of the target entering the wave position, point i is the trajectory point of the target entering the wave position, and the time when the target enters the wave position is the time t corresponding to the trajectory point i. i The wave position boundary determined by O3 and O4 is the boundary of the target leaving the wave position, point j is the trajectory point of the target leaving the wave position, and the time when the target leaves the wave position is the time t corresponding to the trajectory point j. j .

[0128] Step S702: Obtaining a corresponding sixth flight time according to the fourth flight time and the fifth flight time.

[0129] In this embodiment, the sixth sailing time is the planned stay time for the port, which is obtained by subtracting the planned entry time from the planned departure time. For example, if the planned entry time for a port is Day 1 10:00 and the planned departure time is Day 1 15:00, the planned stay time is 5 hours.

[0130] Step S703: Obtaining the characteristic matrix based on the wave position number, the sixth navigation time, the ship attribute data and the environmental data.

[0131] Steps S701-S703 construct a more comprehensive and information-rich feature matrix by introducing and processing the “planned time” information and combining it with dynamic internal and external influencing data (ship attribute data and environmental data), thereby improving the accuracy and reliability of the subsequent network model prediction of the “actual wave position sailing time”.

[0132] In one embodiment of the present application, the above network model adopts an improved BiGRU-Attention network model. The improved BiGRU-Attention network model is introduced below. Figure 10 Shown is the structural diagram of the improved BiGRU-Attention model.

[0133] Gated Recurrent Unit (GRU) is a high-efficiency simplified variant of Long Short-Term Memory (LSTM), which simplifies the three gate structures of LSTM into reset gate and update gate structures, while retaining the characteristics of LSTM and improving the training efficiency of the network. During training, the update gate determines the proportion of the state information of the previous moment to the current moment information; the reset gate determines the degree of forgetting historical state information, thereby ensuring the important time sequence information to be passed down, and the internal function relationship is as follows:

[0134]

[0135] wherein sigma is a Sigmoid activation function, tanh is a hyperbolic tangent function; h t , h t-1 are the hidden states at t moment and t-1 moment respectively; is a weight matrix; and is a Hadamard product of matrices. The GRU determines the selection of information by controlling the update gate z t and the reset gate r t When the reset gate r t is closed to 0, the historical information is ignored and the more useful current information is captured; when the update gate z t is 1, the historical information is passed down to realize the function of "remembering" long-term information.

[0136] BiGRU is constructed on the basis of the typical GRU structure to construct a bidirectional propagation structure, but the structure of the recurrent neural network can only remember information of a relative time length, and the influence of the input sequence on the current output sequence is equal. In order to emphasize the influence of the trajectory attribute information of different times on the current trajectory correlation, the local attention mechanism is added to the BiGRU network model. The hidden state vector output by the BiGRU model is (h1, h2, h3,..., h n ), and the hidden state vector at t moment is , and each output in the target sequence y1, y2, y3,..., y n output by the model satisfies the following conditional distribution:

[0137] ;

[0138] wherein h' t is the hidden state vector with attention introduced, and the formula is as follows:

[0139] ;

[0140] h tis the hidden state vector at time t, W s , W c is the weight matrix, c t is the context vector, which is calculated by the context hidden vector of the current time. The calculation formula is as follows:

[0141] ;

[0142] The local attention mechanism uses a fixed window size method to reduce the computational cost. The window size is 2D+1, p t is the window center, and its calculation formula is as follows:

[0143] ;

[0144] Where σ is the sigmoid function, and Wp is the weight matrix;

[0145] ;

[0146] The improved BiGRU-Attention network model in this embodiment uses the mean squared error (MSE) loss function, which is the mean of the sum of squared differences between the model-predicted association probability f(x) and the target's true association value y:

[0147] .

[0148] Correspondingly, the above-mentioned wave position planning method for marine ships also includes the training process of the network model, such as Figure 11 As shown, it includes the following steps:

[0149] Step S111: Acquire historical trajectory data, historical ship attribute data, and historical environment data.

[0150] The historical trajectory data and historical ship attribute data in this step can be directly obtained from the Automatic Identification System (AIS). AIS data includes dynamic data (such as position, speed, and heading) of the ship during navigation, static information (such as ship name, MMSI, and ship type), and voyage-related information (such as load). Therefore, the ship type and ship load used for model training can be obtained from AIS data, as well as the corresponding historical trajectory data and timestamp information. This historical trajectory data and timestamp information can then constitute the historical trajectory spatiotemporal sequence.

[0151] Based on the timestamps of the historical trajectory data, the associated historical environmental data, i.e. historical meteorological data and historical hydrological data, can be obtained from a third-party system, which can be a commercial meteorological service provider, a historical database of a national meteorological and oceanic agency, etc. Specifically, for each point (or each time period) on the historical trajectory data, the corresponding historical weather conditions such as wind direction, wind speed, etc. are obtained, and for the corresponding historical trajectory point or time period, the corresponding historical hydrological data such as wave height, etc. are obtained. Then, the historical environmental data is encoded into historical numbers according to the descriptions of S501-S504.

[0152] In another embodiment of the present application, for the obtained historical trajectory spatio-temporal sequence, it can also be pre-processed, which includes removing noise and abnormal data, and supplementing missing values, so as to further include the following steps as shown in Figure 12

[0153] Step S1111: Abnormal values in the historical trajectory data that do not conform to the standard normal distribution are removed by using the Z-Score method.

[0154] The Z-Score method is to use the mean and standard deviation of the original data for standardization, remove abnormal values in the trajectory data that do not conform to the standard normal distribution, and reduce the influence of noise data on the trajectory prediction algorithm.

[0155] ;

[0156] Wherein, μ is the mean, σ is the standard deviation, X i is the original data, Z i is the score of X i . Generally, |Z|>3 is considered as an abnormal value.

[0157] Step S1112: Obtain the first timestamp at the missing position in the historical trajectory data.

[0158] After the abnormal value removal in step S1111, it is further checked whether the historical trajectory data sequence has data missing. The missing is usually manifested as discontinuity of the timestamp sequence (for example, the timestamp interval of two consecutive AIS records is much larger than the normal reporting frequency), or there is no position data at some time points. When the data missing is detected, the first timestamp at the missing position is determined, and the description of the first timestamp here is only to indicate that the timestamp is for the missing position, and there is no sequence.

[0159] Step S1113: Obtain the longitude and latitude coordinates of each of the three trajectory data points before and after the first timestamp, calculate the average of the longitude and latitude coordinates, and fill the missing position corresponding to the first timestamp to obtain the historical trajectory spatio-temporal sequence.

[0160] ​For the missing point represented by the "first timestamp" located in S1112: obtain the longitude and latitude coordinates of the three valid historical trajectory data points immediately before the missing point, and obtain the longitude and latitude coordinates of the three valid historical trajectory data points immediately after the missing point. If the missing point is close to the beginning or end of the trajectory, it may not be possible to obtain the three points before and after, at which time the filling of the point can be abandoned.

[0161] Add the longitude and latitude values of these six trajectory points respectively and divide by the number of points to get the average longitude and average latitude, and use the calculated average longitude and average latitude as the coordinates of the missing position corresponding to the "first timestamp" to fill in. The formula is as follows:

[0162]

[0163] Where (lon i , lat i ) is the longitude and latitude of the missing timestamp trajectory point.

[0164] Step S112: obtaining the historical stay time of the ship at each berth based on the historical trajectory data.

[0165] This step can be referred to the description of S7011-S7014, the difference is that now the "history" data is processed, not the "planned route", so it will not continue to be described.

[0166] Step S113: associating the berth number of each berth, the historical stay time, the historical ship attribute data, the historical environment data, and the known actual stay time of each berth to form a training data set.

[0167] Specifically, in this step, the berth number of each berth is extracted, and then the ship type code and ship load value of the ship are associated, and the corresponding historical meteorological data code and historical hydrological data code (such as wind level number, wind direction code, wave height level number) during the historical stay time period of the berth are associated. Combine these information to form a model input data sequence. The known actual stay time of each berth refers to the "target value or label" corresponding to the feature set of each model input data sequence, that is, the historical actual stay time of the ship in the berth. These contents together constitute the model training data set.

[0168] Each row of the relationship matrix in the training data set represents a training sample (a historical berth navigation event). The columns of the relationship matrix can be divided into two parts:

[0169] Feature column: corresponding to each input feature in the model input data sequence.

[0170] Label column: Corresponds to the actual dwell time of this historical berth voyage (from the known berth voyage time series).

[0171] In this embodiment, in order to avoid the influence of the generated gradient update and learning rate in the model training process, the constructed relationship matrix can be subjected to standard deviation normalization processing, and the normalization formula is as follows:

[0172] matrix*=(matrix-μ) / σ;

[0173] Wherein μ is the mean value set of each attribute, and σ is the standard deviation set of each attribute.

[0174] Step S114: training the model using the training data set to obtain the network model.

[0175] The training parameters of the network model include but are not limited to learning rate, batch size, training round number, BiGRU layer parameter, Attention mechanism parameter, optimizer, loss function, etc. This step specifically includes:

[0176] Through forward calculation, the predicted running time of the pilot ship at each berth is calculated by BiGRU-Attention. That is, a batch of input features is taken out from the normalized training data, and these features are input into the improved BiGRU-Attention network model. The model calculates through its internal BiGRU layer and Attention layer, and outputs the predicted value of the running time of each berth in the batch sample.

[0177] The mean square error loss function is used to calculate the error value between the predicted running time and the true running time label, and the current model parameters are compared with the historical model parameters, and the model parameters with smaller error value are saved. For the current batch of samples, the "predicted running time" output by the model is compared with the corresponding "true running time label", and the total error value (loss) is calculated using the mean square error (MSE) formula. At the end of each batch, the performance of the current model is evaluated (for example, the MSE on the validation set is calculated) on the validation set (a part of the training data, which does not participate in gradient update). If the error value of the current model on the validation set is smaller than the historical best error value, the parameters of the current model are saved. This ensures that after the training is completed, the model version with the best performance on the validation data can be selected, preventing overfitting.

[0178] According to the error, the results obtained by BiGRU-Attention are back propagated, and BiGRU-Attention is forward and backward propagated along the sequence direction of the input parameters, which is used to extract the key information in the input relationship matrix.

[0179] The neuron parameters are optimized using the optimizer.

[0180] The training process is repeated until the set number of training rounds is reached.

[0181] After all the training is completed, the prediction result with the highest accuracy is selected as the target ship’s

[0182] The final travel time of the wave position.

[0183] A simplified diagram of the above training process can be found in Figure 13 As shown in Figure 1, data preprocessing refers to the processing flow of steps S112-S113. It can be seen that through the above iterative optimization process, the model parameters are systematically adjusted, enabling it to learn the complex patterns of predicting wave position and sailing time from the input data, and ultimately obtain a model that performs optimally for this task.

[0184] like Figure 14 FIG2 is a flow chart of a wave position planning method for a maritime vessel provided in another embodiment of the present application. The method is applied to a satellite and includes the following steps:

[0185] Step S141: Receive the wave position number and the corresponding predicted entry time and predicted exit time.

[0186] The wave position number and the corresponding predicted entry time and predicted exit time here are from the satellite network management system or similar management and control center on the ground side. The specific process of obtaining this information can be found in the corresponding description in the above embodiment and will not be repeated here.

[0187] Step S142: providing service to the wave position corresponding to the wave position number based on the predicted entry time and the predicted exit time.

[0188] Beam staring involves a satellite with a steerable beam continuously and centrally directing its communication beam to cover a specific geographic area identified by a "beam number" within a specific time period. "Staring" emphasizes the stability and focus of the beam within that time window, ensuring that target vessels within that area receive stable, high-quality communication services.

[0189] The mission scheduling system inside the satellite will arrange the beam pointing according to the received "predicted entry time" and "predicted exit time". Before the "predicted entry time" arrives, the satellite starts to adjust its antenna or electronically points the beam to the target wave position. From the "predicted entry time" to the "predicted exit time", the satellite will maintain the beam coverage to the wave position. If the ship sails in the wave position, it can access the communication network provided by the satellite. Once the "predicted exit time" arrives, the satellite will release the beam resource or adjust it to point to the next wave position that needs to be covered according to the subsequent plan.

[0190] As can be seen from the above, the wave position planning method for marine ships provided in the embodiment is no longer blindly broadcasting signals or equally distributing resources, but accurately puts the communication resources into the place and time that needs it according to the actual predicted path and time window of the ship. By preparing beam coverage in advance before the ship arrives and continuously providing services during its passing, the stability and reliability of the communication connection are greatly improved. Moreover, since the "staring" is time-based and only carried out in the predicted time window, when the ship leaves or does not arrive, the related resources can be used to serve other users or areas, avoiding the waste of valuable satellite resources. This method is particularly suitable for providing high-priority and uninterrupted communication services for key users on the sea (such as research ships, important transport fleets, offshore operation platforms, etc.).

[0191] As Figure 15 A structure schematic diagram of a wave position planning device for marine ships provided in an embodiment of the present application is applied to a satellite network management system, and the device comprises a first data acquisition unit 151, a second data acquisition unit 152 and a data uploading unit 153, which are sequentially connected. Wherein:

[0192] The first data acquisition unit 151 is configured to acquire a wave position number and corresponding first sailing time and second sailing time, wherein the second sailing time is obtained based on a pre-trained network model.

[0193] The second data acquisition unit 152 is configured to obtain third sailing time based on the first sailing time and the second sailing time.

[0194] The data uploading unit 153 is configured to upload the first sailing time, the third sailing time and the wave position number to a satellite, so that the satellite serves a wave position corresponding to the wave position number in a period from the first sailing time to the third sailing time.

[0195] In an embodiment of the present application, as Figure 16 shown, the first data acquisition unit 151 comprises a number acquisition module 1511 configured to determine a wave position number based on trajectory point coordinates.

[0196] In another embodiment of the present application, the second data acquisition unit 152 is specifically configured to add the first sailing time and the second sailing time to obtain a third sailing time.

[0197] In another embodiment of the present application, as shown in Figure 17 the first data acquisition unit 151 further comprises:

[0198] The influence data acquisition module 1512 is configured to acquire ship attribute data and environment data.

[0199] The berth sailing time acquisition module 1513 is configured to input a feature matrix containing the berth number, the ship attribute data and the environment data into a pre-trained network model to obtain a second sailing time.

[0200] In another embodiment of the present application, as shown in Figure 18 the first data acquisition unit 151 further comprises a digital coding module 1514 configured to convert the ship attribute data and the environment data into digital codes.

[0201] In another embodiment of the present application, the ship attribute data includes ship type and ship load, and the environment data includes wind direction and wave height, as shown in Figure 19 the digital coding module 1514 comprises:

[0202] The ship type coding sub-module 15141 is configured to digitally number all ship types and to binary code the ship types according to the digital numbers.

[0203] The ship load coding sub-module 15142 is configured to digitally value the ship load in tons.

[0204] The wind direction coding sub-module 15143 is configured to binary code convert the wind direction according to a binary coding correspondence table.

[0205] The wind force and wave height coding sub-module 15144 is configured to convert wind force levels and wave height levels into corresponding level numbers based on a preset standard.

[0206] In another embodiment of the present application, as shown in Figure 20 the first data acquisition unit 151 further comprises:

[0207] The planned in-out time acquisition module 1515 is configured to obtain a planned sailing-in time and a planned sailing-out time of the corresponding berth according to the berth number.

[0208] The planned stay time acquisition module 1516 is configured to obtain a corresponding planned stay time according to the planned sailing-in time and the planned sailing-out time.

[0209] The feature matrix obtaining module 1517 is configured to obtain the feature matrix based on the berth number, the planned stay time, the ship attribute data, and the environment data.

[0210] In another embodiment of the present application, as shown in Figure 21 The planning in-out time obtaining module 1515 includes:

[0211] The target berth determination sub-module 15151 is configured to determine a target berth according to the berth number.

[0212] The distance calculation sub-module 15152 is configured to calculate a distance relationship between the trajectory point coordinate and the target berth boundary.

[0213] The target trajectory point determination sub-module 15153 is configured to determine a target trajectory point for driving into or out of the target berth based on the distance relationship.

[0214] The planning in-out time determination sub-module 15154 is configured to determine corresponding planning driving-in time and planning driving-out time according to the target trajectory point.

[0215] In another embodiment of the present application, the device further includes:

[0216] The historical data obtaining unit is configured to obtain historical trajectory data, historical ship attribute data, and historical environment data.

[0217] The historical stay time obtaining unit is configured to obtain historical stay time of a ship in each berth based on the historical trajectory data.

[0218] The training data set constituting unit is configured to associate the berth number of each berth, the historical stay time, the historical ship attribute data, the historical environment data, and the actual stay time of each berth known to constitute a training data set.

[0219] The network training unit is configured to train the model using the training data set to obtain the network model.

[0220] The detailed description of each unit and module can be found in the foregoing method embodiments, which will not be described here.

[0221] As can be seen from the foregoing technical solutions, the time of the gazing scene in the present application is divided into multiple time domains, and the berth number of the gaze can be added according to the prediction result in each time domain, so as to finally form a time-domain-divided gazing scene. Compared with the existing satellite gazing scheme, the ship communication can be effectively guaranteed, and the allocation and utilization efficiency of satellite resources can be optimized.

[0222] AsFigure 22 Fig. 1 shows a schematic diagram of a wave berth planning device for a marine vessel according to an embodiment of the present application, which is applied to a satellite, the device comprising a data receiving unit 221 and a wave berth service unit 222, wherein:

[0223] The data receiving unit 221 is configured to receive a wave berth number and corresponding predicted entry time and predicted exit time.

[0224] The wave berth service unit 222 is configured to serve a wave berth corresponding to the wave berth number based on the predicted entry time and the predicted exit time.

[0225] As can be seen from the above, the wave berth planning device for a marine vessel provided by the embodiment is no longer blindly broadcasting signals or equally distributing resources, but rather accurately puts communication resources into the right place and time according to the actual predicted path and time window of the vessel. By preparing beam coverage in advance before the vessel arrives and continuously providing services during its passing, the stability and reliability of communication connection are greatly improved. Moreover, since the "gaze" is time-based and only performed within the predicted time window, when the vessel leaves or does not arrive, the related resources can be used to serve other users or areas, avoiding the waste of valuable satellite resources.

[0226] The embodiment of the present application further provides an electronic device, comprising a memory, a processor and a computer program stored in the memory and executable on the processor, and the processor implements the above method when executing the program.

[0227] The embodiment of the present application further provides a computer readable storage medium, which stores a computer program, and the computer program is executed by a processor to implement the steps of the above method.

[0228] The embodiment of the present application further provides a computer program product, comprising computer programs / instructions, and the computer programs / instructions are executed by a processor to implement the steps of the above method.

[0229] As shown in Fig. 6, the electronic device 600 can further comprise a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to include all the components shown in Fig. 6; in addition, the electronic device 600 can further include components not shown in Fig. 6, which can be referred to the prior art. Figure 23 Figure 23 As shown in Fig. 6, the electronic device 600 can further comprise a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to include all the components shown in Fig. 6; in addition, the electronic device 600 can further include components not shown in Fig. 6, which can be referred to the prior art. Figure 23

[0230] As shown in Fig. 6, the electronic device 600 can further comprise a communication module 110, an input unit 120, an audio processor 130, a display 160, and a power supply 170. It is worth noting that the electronic device 600 does not necessarily have to include all the components shown in Fig. 6; in addition, the electronic device 600 can further include components not shown in Fig. 6, which can be referred to the prior art. Figure 23 ​​As shown, the central processing unit 100, which is sometimes referred to as a controller or operating control, can include a microprocessor or other processor device and / or logic device that receives input and controls the operation of the various components of the electronic device 600.

[0231] The memory 140, for example, can be one or more of a buffer, a flash memory, a hard drive, a removable media, a volatile memory, a non-volatile memory, or other suitable device. Information relating to failures can be stored, as well as programs for executing the information. The central processing unit 100 can execute the programs stored in the memory 140 to perform information storage or processing, etc.

[0232] The input unit 120 provides input to the central processing unit 100. The input unit 120 is, for example, a key or touch input device. The power supply 170 is used to provide power to the electronic device 600. The display 160 is used to display display objects such as images and text. The display can be, for example, an LCD display, but is not limited thereto.

[0233] The memory 140 can be a solid state memory such as a read only memory (ROM), a random access memory (RAM), a SIM card, etc. It can also be a memory that retains information even when power is off, can be selectively erased, and is provided with more data, examples of which are sometimes referred to as an ERPOM, etc. The memory 140 can also be some other type of device. The memory 140 includes a buffer memory 141 (sometimes referred to as a buffer). The memory 140 can include an application / function storage section 142 for storing application programs and function programs or for storing a flow for operating the electronic device 600 by the central processing unit 100.

[0234] The memory 140 can also include a data storage section 143 for storing data such as contacts, digital data, pictures, sounds, and / or any other data used by the electronic device. A driver program storage section 144 of the memory 140 can include various driver programs of the electronic device for communication functions and / or for performing other functions of the electronic device such as a messaging application, an address book application, etc.

[0235] The communication module 110 is a transmitter / receiver that transmits and receives signals via the antenna 111. The communication module 110 (transmitter / receiver) is coupled to the central processing unit 100 to provide input signals and receive output signals, which can be the same as in the case of a conventional mobile communication terminal.

[0236] Based on different communication technologies, multiple communication modules 110, such as a cellular network module, a Bluetooth module, and / or a wireless local area network module, can be provided in the same electronic device. The communication modules 110 (transmitters / receivers) are also coupled to a speaker 131 and a microphone 132 via an audio processor 130 to provide audio output via the speaker 131 and to receive audio input from the microphone 132 to enable typical telecommunication functions. The audio processor 130 can include any suitable buffers, decoders, amplifiers, etc. In addition, the audio processor 130 is coupled to the central processor 100 to enable recording on-board via the microphone 132 and to enable playing on-board stored sounds via the speaker 131.

[0237] Those skilled in the art will appreciate that embodiments of the present application can be readily used as a method, apparatus, or computer program product. Accordingly, the present application can take the form of an entirely hardware embodiment, an entirely software embodiment or an embodiment combining software and hardware aspects. Furthermore, the present application can take the form of a computer program product on one or more computer-usable storage media (including, but not limited to, disk storage, CD-ROMs, optical storage devices, etc.) embodying computer readable program code.

[0238] The present application is described in reference to the flowchart illustrations and / or block diagrams of methods, apparatus (systems) and computer program products according to embodiments of the application. It will be understood that each block of the flowchart illustrations and / or block diagrams, and combinations of blocks in the flowchart illustrations and / or block diagrams, can be implemented by computer program instructions. These computer program instructions can be provided to a processor of a general purpose computer, special purpose computer, embedded processor, or other programmable data processing apparatus to produce a machine, such that the instructions, which execute via the processor of the computer or other programmable data processing apparatus, create means for implementing the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0239] These computer program instructions can also be stored in a computer- readable memory that can direct a computer or other programmable data processing apparatus to function in a particular manner, such that the instructions stored in the computer-readable memory produce an article of manufacture including instructions which implement the functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams. Figure 1 one or more functions specified in the flowchart illustrations and / or block diagrams.

[0240] These computer program instructions can also be loaded into a computer or other programmable data processing devices, so that a series of operational steps are generated to realize the computer-implemented processes in the computer or other programmable devices, and the instructions executed in the computer or other programmable devices provide the steps for realizing the functions specified in the flowchart Figure 1 one flow or multiple flows and / or the functions specified in the block Figure 1 one block or multiple blocks.

[0241] The principles and implementation manners of the present application are described in the specific embodiments in the present application, and the above embodiment descriptions are only used to help understand the method of the present application and its core idea; meanwhile, for those skilled in the art, according to the idea of the present application, the specific implementation manners and application ranges will have changes, and the above descriptions should not be understood as limitations on the present application.

Claims

1. A wave position planning method for marine vessels, applied to a satellite network management system, characterized in that: The method comprises: Obtain a wave position number and the corresponding first and second navigation times. The wave position number is a unique identifier of the target wave position. The first navigation time is the estimated start time of the ship entering the target wave position. The second navigation time is the estimated length of time the ship will sail within the target wave position. The second navigation time is obtained based on a pre-trained network model. Obtaining a third navigation time based on the first navigation time and the second navigation time, wherein the third navigation time is an estimated time when the ship leaves the target wave position; annotating the first flight time, the third flight time, and the wave position number to a satellite, so that the satellite provides service to the wave position corresponding to the wave position number during a time period from the first flight time to the third flight time; Obtaining the second flight time includes: Obtain ship attribute data and environmental data; A feature matrix including the wave position number, the ship attribute data and the environmental data is input into a pre-trained network model to obtain a second navigation time.

2. The wave position planning method for marine vessels according to claim 1, characterized in that: Obtaining the wave number includes: The wave position number is determined based on the track point coordinates.

3. The wave position planning method for marine vessels according to claim 1, characterized in that: The obtaining of a third navigation time based on the first navigation time and the second navigation time includes: The first flight time and the second flight time are added together to obtain a third flight time.

4. The wave position planning method for marine vessels according to claim 1, characterized in that: After obtaining the ship attribute data and the environmental data, the method further includes: The ship attribute data and the environmental data are converted into digital codes.

5. The wave position planning method for ships at sea according to claim 4, characterized in that: The ship attribute data includes ship type and ship load, and the environmental data includes wind direction and wave height. Converting the ship attribute data and the environmental data into digital codes includes: Digitally numbering the ship type, and performing binary coding on the ship type according to the digital number; Take digital value of ship load; Convert the wind direction into binary code according to the binary code corresponding table; Convert wind force levels and wave height levels into corresponding levels based on preset standards.

6. The wave position planning method for marine vessels according to claim 1, characterized in that: The method further comprises: Obtaining a fourth navigation time and a fifth navigation time of the corresponding wave position according to the wave position number, wherein the fourth navigation time is a planned entry time of the wave position, and the fifth navigation time is a planned exit time of the wave position; Obtaining a corresponding sixth navigation time according to the fourth navigation time and the fifth navigation time, wherein the sixth navigation time is a planned stay time at the wave position; The characteristic matrix is ​​obtained based on the wave position number, the sixth navigation time, the ship attribute data and the environmental data.

7. The method for wave position planning for ships at sea according to claim 6, characterized in that: The obtaining of the fourth navigation time and the fifth navigation time corresponding to the wave position according to the wave position number includes: Determine the target wave position according to the wave position number; Calculating the distance relationship between the trajectory point coordinates and the target wave position boundary; Determining a target trajectory point entering or exiting the target wave position based on the distance relationship; The corresponding fourth flight time and fifth flight time are determined according to the target trajectory point.

8. The wave position planning method for marine vessels according to claim 1, characterized in that: The method further comprises: Obtain historical trajectory data, historical ship attribute data and historical environmental data; Obtaining the historical stay time of the ship at each wave position based on the historical trajectory data; Associating the wave position number of each wave position, the historical stay time, the historical ship attribute data, the historical environmental data and the known actual stay time of each wave position to form a training data set; The training data set is used to perform model training to obtain the network model.

9. A wave position planning device for marine vessels, applied to satellite network management systems, characterized in that: The device comprises: a first data acquisition unit, configured to acquire a wave position number and corresponding first and second navigation times, wherein the wave position number is a unique identifier of a target wave position, the first navigation time is an estimated start time of the ship entering the target wave position, and the second navigation time is an estimated length of time the ship will sail within the target wave position, wherein the second navigation time is obtained based on a pre-trained network model; a second data acquisition unit, configured to obtain a third navigation time based on the first navigation time and the second navigation time, wherein the third navigation time is an estimated time when the ship leaves the target wave position; a data annotation unit, configured to annotate the first flight time, the third flight time, and the wave position number to the satellite, so that the satellite provides service to the wave position corresponding to the wave position number during a time period from the first flight time to the third flight time; The first data acquisition unit includes: Impact data acquisition module, used to obtain ship attribute data and environmental data; The wave position sailing time acquisition module is used to input the feature matrix including the wave position number, the ship attribute data and the environmental data into a pre-trained network model to obtain a second sailing time.

10. 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 computer program, the steps of the method according to any one of claims 1 to 8 are implemented.

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

12. A computer program product comprising a computer program / instructions, characterized in that When the computer program / instructions are executed by a processor, the steps of the method according to any one of claims 1 to 8 are implemented.

Images