Network AIS data request method and device

Abstract

The invention provides a network AIS (Automatic Identification System) data request method and device. The method comprises the following steps: respectively acquiring ship navigation information, nautical chart operation information, ship position information and nautical chart view center position information at each moment; according to ship navigation information, nautical chart operation information, ship position information and nautical chart view center position information at a moment, obtaining a feature vector at the moment; according to the feature vector of each moment of a time sequence, obtaining ship position information and nautical chart view center position information at the next preset moment; according to the position information of the ship at the next preset moment and the central position information of the nautical chart view, predicting whether the ship at the next preset moment is located in a nautical chart view bounding box; and requesting the network AIS data in the second bounding box.

Description

Technical Field

[0001] The present invention relates to the field of information technology, and in particular to a method and device for requesting network AIS data. Background Art

[0002] The Automatic Identification System (AIS) is composed of shore-based (base station) facilities and ship-borne equipment. It is a new type of digital navigation aid system and equipment that integrates network technology, modern communication technology, computer technology, and electronic information display technology. The AIS system cooperates with the global positioning system (GPS, Beidou, etc.) to broadcast dynamic information such as ship position, speed, and heading, as well as static information such as the Maritime Mobile Service Identification Code (MMSI), ship name, call sign, and draft to nearby shore-based and water vessels through very high frequency (VHF), so that nearby shore-based and water vessels can timely grasp the dynamic and static information of all ships in nearby waters, avoid ship collisions, and effectively ensure the safety of ship navigation.

[0003] Due to the influence of multiple factors such as transmission power limitation, antenna height, terrain and obstacle obstruction, climate conditions, electromagnetic interference, etc., the coverage and timeliness of AIS system signals are limited. Therefore, each shore-based facility and ship-borne equipment relies on the Internet to upload all the dynamic and static information of AIS ships received by itself to the cloud platform, and the cloud platform monitors and stores all AIS ship information. In addition to relying on the AIS system to obtain all AIS ship information on the nearby sea surface, each ship-borne terminal can also request AIS ship information from the cloud platform through the current ship and the center position of the chart view, and integrate it with the nearby ship information obtained by the AIS system. This can make up for the lack of signal reception range and timeliness of the AIS system, reduce the risk of ship collision, and improve ship navigation safety.

[0004] However, faced with a large amount of network AIS ship information, how to improve the real-time rendering of network AIS ships on the shipboard terminal chart interface and better supplement the AIS ships missing from the AIS system has become an urgent problem to be solved. Summary of the invention

[0005] The present disclosure provides a network AIS data request method and device, which can effectively solve the above problems.

[0006] The present disclosure is implemented as follows:

[0007] In a first aspect, the present disclosure provides a network AIS data request method, the method comprising:

[0008] Obtain the ship navigation information, chart operation information, ship position information and chart view center position information at each moment respectively;

[0009] According to the ship navigation information, chart operation information, ship position information and chart view center position information at a moment, a feature vector at that moment is obtained;

[0010] According to the feature vector of each moment of a time series, the ship position information and the center position information of the chart view at the next scheduled moment are obtained, wherein the time series is composed of the current moment and the moments before the current moment;

[0011] According to the ship position information at the next scheduled time and the center position information of the chart view, predict whether the ship is located in the bounding box of the chart view at the next scheduled time;

[0012] Request network AIS data in the second bounding box; wherein, if the ship is located in the chart view bounding box, the first bounding box is obtained according to the ship's focus range; if the ship is not located in the chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted at the next scheduled moment.

[0013] In a second aspect, the present disclosure provides a network AIS data request device, the device comprising:

[0014] An information acquisition module is used to respectively acquire the ship navigation information, chart operation information, ship position information and chart view center position information at each moment;

[0015] A feature acquisition module is used to obtain a feature vector at a moment according to the ship navigation information, chart operation information, ship position information and chart view center position information at that moment;

[0016] A prediction module, used for obtaining the ship position information and the center position information of the chart view at the next scheduled moment according to the feature vector at each moment of a time series, wherein the time series consists of the current moment and the moments before it;

[0017] A judgment module, used to predict whether the ship is located in the bounding box of the chart view at the next scheduled moment according to the ship position information at the next scheduled moment and the center position information of the chart view;

[0018] A request module is used to request network AIS data in a second bounding box; wherein, if the ship is located in a chart view bounding box, a first bounding box is obtained according to the ship's focus range; if the ship is not located in the chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted at the next scheduled moment.

[0019] In a third aspect, the present disclosure provides an electronic device, including:

[0020] a memory storing execution instructions; and

[0021] A processor, wherein the processor executes the execution instruction stored in the memory, so that the processor executes the method described in the first aspect.

[0022] In a fourth aspect, the present disclosure provides a readable storage medium, wherein the readable storage medium stores execution instructions, and when the execution instructions are executed by a processor, they are used to implement the method described in the first aspect.

[0023] Compared with the prior art, the beneficial effects of the present invention are:

[0024] 1. The present disclosure provides a network AIS data request method, which predicts the future center position of the ship and the chart view based on the center position information of the ship and the chart view, the information of the positioning system (ship speed, heading, AIS system refresh time), and the behavior information of the user operating the shipboard terminal chart interface (moving distance, moving direction, operation preference, operation time); according to the predicted future center position of the ship and the chart view and the chart view size, it is judged whether the future ship is located in the chart view; if the future ship is located in the chart view, the network AIS request bounding box is obtained based on its focus range, and the bounding box is used to request the cloud platform to preload all AIS ship information in the bounding box, which can reduce the bounding box range of the network AIS ship request, thereby reducing the amount of data requested from the cloud platform and the workload of rendering on the shipboard terminal chart interface.

[0025] 2. The method compares the current network AIS request bounding box and the predicted bounding box. The repeated area directly obtains the AIS ship information from the buffer, and the non-repeated area re-requests the AIS ship information from the cloud platform. By preloading the repeated area, the bounding box range of the current network AIS ship that needs to be requested in real time can be reduced, and the real-time rendering of the network AIS ship on the shipboard terminal chart interface can be improved, which can better supplement the AIS ships missing from the AIS system.

[0026] 3. The method preloads the location information of places of interest such as ports and islands, so that the network AIS request bounding box includes the places of interest, so that ships can obtain information about these places of interest in real time, thereby better planning and monitoring navigation and improving navigation safety and efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0027] In order to more clearly illustrate the technical solutions of the embodiments of the present disclosure, the drawings required for use in the embodiments will be briefly introduced below. It should be understood that the following drawings only show certain embodiments of the present disclosure and therefore should not be regarded as limiting the scope. For ordinary technicians in this field, other related drawings can be obtained based on these drawings without creative work.

[0028] Figure 14 is a flowchart of a network AIS data request method S100 provided in an embodiment of the present disclosure.

[0029] Figure 2 It is a flow chart of LSTM model training provided by an embodiment of the present disclosure.

[0030] Figure 3 This is a first schematic diagram of a network AIS request bounding box provided by an embodiment of the present disclosure.

[0031] Figure 4 This is a second schematic diagram of a network AIS request bounding box provided by an embodiment of the present disclosure.

[0032] Figure 5 This is the third schematic diagram of the network AIS request bounding box provided by the embodiment of the present disclosure.

[0033] Figure 6 This is the fourth schematic diagram of the network AIS request bounding box provided by the embodiment of the present disclosure.

[0034] Figure 7 It is a flow chart of AIS vessel information loading provided by an embodiment of the present disclosure.

[0035] Figure 8 Schematic diagram of the structure of a network AIS data requesting device 1000 provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0036] The present disclosure is further described in detail below in conjunction with the accompanying drawings and implementations. It is understood that the specific implementations described herein are only used to explain the relevant content, rather than to limit the present disclosure. It should also be noted that, for ease of description, only the parts related to the present disclosure are shown in the accompanying drawings.

[0037] It should be noted that, in the absence of conflict, the embodiments and features of the embodiments in the present disclosure can be combined with each other. The technical solution of the present disclosure will be described in detail below with reference to the accompanying drawings and in combination with the embodiments.

[0038] Unless otherwise specified, the exemplary embodiments / embodiments shown will be understood as providing exemplary features of various details of some ways in which the technical concept of the present disclosure can be implemented in practice. Therefore, unless otherwise specified, the features of the various embodiments / embodiments can be combined, separated, interchanged and / or rearranged without departing from the technical concept of the present disclosure.

[0039] Embodiment 1

[0040] refer to Figure 1 , the embodiment of the present disclosure provides a network AIS data request method S100.

[0041] Specifically, the method S100 includes:

[0042] S102, respectively obtaining the ship navigation information, chart operation information, ship position information and chart view center position information at each moment.

[0043] S104. Obtain a feature vector at a moment according to the ship navigation information, chart operation information, ship position information and chart view center position information at that moment.

[0044] S106, according to the feature vector of each moment of a time series, obtain the ship position information and the center position information of the chart view at the next scheduled moment The time series consists of the current moment and the moments before it.

[0045] S108. Predict whether the ship is located in the bounding box of the chart view at the next scheduled moment according to the ship position information at the next scheduled moment and the center position information of the chart view.

[0046] S110, requesting network AIS data in a second bounding box; wherein, if the ship is located in a chart view bounding box, a first bounding box is obtained according to the ship's focus range; if the ship is not located in a chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted for the next scheduled moment.

[0047] Ship navigation information is ship positioning information.

[0048] In step S102, the ship navigation information may be obtained by an AIS system in conjunction with a global positioning system.

[0049] In step S102, the ship navigation information, chart operation information, ship position information and chart view center position information of each moment are obtained respectively. For example, the ship navigation information, chart operation information, ship position information and chart view center position information of moments t, t+1, ..., t+n-1, t+n are obtained respectively, where n is an integer greater than 1.

[0050] In some implementations, in step S102, the time interval for acquiring adjacent moments is 1 second.

[0051] In some implementations, in step S102, various types of information obtained are stored in a memory buffer for prediction.

[0052] In some implementations, in step S102, obtaining the ship navigation information, chart operation information, ship position information and chart view center position information at each moment respectively includes:

[0053] Get the first eigenvector The second eigenvector and the third eigenvector Among them, v n represents the ship speed, θ n Indicates the ship's heading, Δt indicates the network AIS timing refresh time, d n Indicates the distance the chart is moved, r n Indicates the direction of chart movement, opt n Indicates the user's chart operation preferences, including zooming and moving, t indicates the timestamp of the user's chart operation, Indicates the longitude of the ship's position, Indicates the latitude of the ship's position, Indicates the longitude of the center of the chart. It indicates the latitude of the center of the chart, and n indicates the time n.

[0054] Specifically, opt n For scaling, the value is 1, opt n For movement, the value is 0.

[0055] Specifically, when the user does not operate the nautical chart, the network AIS refreshes the nautical chart interface periodically, and Δt is 10s.

[0056] Specifically, the ship speed v n Unit: nautical mile / hour, preset range: 0~60. Ship heading θ n Unit: degree, preset range: 0~360.

[0057] The method further includes: setting the width width and height height of the chart interface, in pixels.

[0058] Chart moving distance d n The moving distance on the chart interface. Chart moving distance d n Unit: pixel. Chart moving direction r n Unit: degree, preset range: 0 to 360. The time stamp t of the user operating the chart is the current time, and the unit of the time stamp t of the user operating the chart is second.

[0059] Vessel position longitude Unit: degree, preset range: -179~180, ship position latitude Unit: degree, preset range: -89~90, longitude of the center of the chart Unit: degrees, preset range: -179~180, latitude of the center of the chart Unit: degree, preset range: -89~90.

[0060] The preset range is the preset range of data in each type of information, and the maximum value of the data and the preset maximum value can be determined to determine whether there is an abnormality in the acquired original data.

[0061] The timestamp t of the user operating the nautical chart is used to determine the time difference between the current moment when the user operates the nautical chart and the last moment when the user operated the nautical chart.

[0062] In some implementations, in step S102, obtaining the ship navigation information, chart operation information, ship position information and chart view center position information at each moment respectively includes:

[0063] Normalize the data. Among them, X represents the original data, X max Indicates the preset maximum value of the data, X min Indicates the preset minimum value of the data, X norm Represents normalized data.

[0064] Abnormal data may be caused by recording errors, equipment failures, or human factors. Normalizing abnormal data can identify and correct abnormal data in the data set, improve the accuracy and stability of the feature vector used for prediction, and avoid the algorithm model being unable to extract accurate information for prediction, thereby improving the generalization ability and prediction accuracy of the algorithm model.

[0065] Especially in the training phase of the model, ensuring that the data values ​​of all feature vectors are within the predetermined range improves the quality of the data, thereby facilitating model training and enabling the model to better understand the feature vectors and extract more meaningful information from them can significantly improve the performance of the model and help avoid problems such as overfitting and bias.

[0066] In some implementations, the data normalized in step S102 and the data used to obtain the feature vector in step S104 are data used for prediction.

[0067] In some implementations, in step S104, obtaining a feature vector at a moment according to the ship navigation information, chart operation information, ship position information and chart view center position information at a moment includes:

[0068] The first eigenvector Multiply by the first weight w 1 , the second eigenvector Multiply by the second weight w 2 , then with the third eigenvector P n Concatenate to get the feature vector If the time difference between the current time when the user operates the nautical chart and the time when the user last operated the nautical chart is less than the first threshold, the first weight w 1and the second weight w 2 Take the corresponding values ​​in the first weight value combination respectively. If the time difference between the current time when the user operates the nautical chart and the time when the user last operated the nautical chart is not less than the first threshold, the first weight w 1 and the second weight w 2 The corresponding values ​​in the second weight value combination are respectively taken.

[0069] Specifically, w 1 +w 2 =1.

[0070] Specifically, the first threshold for determining whether the user is operating the nautical chart at the current moment is 10 seconds.

[0071] When the time difference from the last time the user operated the chart is less than 10s, it means that the user is operating the chart. Therefore, the current chart operation information is used more to predict the future position of the ship and the center of the chart view. 1 The value is 0.1, w 2 The value is 0.9. When the time difference from the last time the user operated the chart is not less than 10s, it means that the user has not operated the chart. In this case, the ship navigation information is used to predict the future center position of the ship and the chart view. 1 The value is 1, w 2 The value is 0.

[0072] Specifically,

[0073]

[0074] The following is an example:

[0075] At time n, the ship is located at the center of the chart view. The longitude of the center of the chart view is 118.26 degrees, and the latitude is 24.25 degrees. The ship's speed is 10 kn, the heading is 30 degrees, and the user has not performed any chart operations.

[0076] 1). Vessel navigation information:

[0077] 2). Chart operation information:

[0078] 3). Ship and chart view center position information: P n =[118.26,24.25,118.26,24.25].

[0079] 4). The first weight w 1 and the second weight w 2 The corresponding values ​​1 and 0 in the first weight value combination are taken respectively.

[0080] 5). Construct feature vector: xn =[118.26,24.25,118.26,24.25,10,30,10,0,0,0,0].

[0081] In some embodiments, in step S106, the time series consists of the current moment and the moment before it. For example, the current moment may be n, and the time series consists of moments nm, n-m+1, ..., n-1, n in chronological order, where nm is an integer greater than 1.

[0082] In some embodiments, in step S106, the ship position information and the center position information of the chart view at the next predetermined time are obtained according to the feature vector at each time of a time series. include:

[0083] When the AIS system refresh time is reached or the user stops the chart interface of the shipboard terminal, the ship position information and the center position information of the chart view at the next scheduled time are obtained according to the characteristic vector of each moment in a time series.

[0084] In some implementations, the AIS system refresh time is reset after the user stops operating the shipboard terminal chart interface.

[0085] In some implementations, in step S106, the next scheduled time is a time 10 seconds later.

[0086] In some embodiments, in step S106, the ship position information and the center position information of the chart view at the next predetermined time are obtained according to the feature vector at each time of a time series. include:

[0087] According to the feature vector at each moment of a time series, based on the constraint of the long-term dependency of the feature vector at each moment of the time series, the ship position information and the center position information of the chart view at the next scheduled moment are obtained.

[0088] Further, in some embodiments, in step S106, the ship position information and the center position information of the chart view at the next predetermined moment are obtained according to the feature vector at each moment of a time series. include:

[0089] Call the Long Short-Term Memory (LSTM) network for analysis.

[0090] Input sequence data Q = [x 1 ,x 2 ,…,x k-1 ,x k], each element is a feature vector of a moment constructed in step S104, and the time series includes k moments. Specifically, k is 50000.

[0091] The internal mechanism formula of LSTM unit is as follows:

[0092] Forget Gate:

[0093] f k =σ(W f ·[h k-1 ,x k ]+b f )

[0094] Input gate and candidate memory:

[0095] i k =σ(W i ·[h k-1 ,x k ]+b i )

[0096]

[0097] Update cell status:

[0098]

[0099] Output Gate:

[0100] o k =σ(W o ·[h k-1 ,x k ]+b o )

[0101] h k =o k *tanh(C k )

[0102] in:

[0103] f k ,i k , o k are the activation values ​​of the forget gate, input gate, and output gate respectively.

[0104] σ is the sigmoid function.

[0105] tanh is the hyperbolic tangent function.

[0106] W f , W i , W C , W o is the weight matrix.

[0107] bf , b i , b C , b o is the bias term.

[0108] h k-1 is the hidden state of the previous moment k-1.

[0109] x k is the feature vector of k at the current moment.

[0110] C k is the state of the memory unit at the current time k.

[0111] The output of the LSTM unit is converted into the final prediction result through a fully connected layer, and a linear activation function is used to predict the center position information of the ship and the chart view at the next scheduled moment.

[0112] z k =W z ·h k +b z

[0113]

[0114] Loss function:

[0115] To measure the difference between the predicted future ship and chart view center positions and the actual positions, the mean square error (MSE) is used as the loss function.

[0116]

[0117] in:

[0118] N is the sample size.

[0119] It is the predicted future ship and chart view center position information.

[0120] B i It is the actual ship and chart view center position information.

[0121] The Adam optimization algorithm is used to update the weights of the neural network. The weights here refer to the weight matrix W inside the neural network. f , W i , W C , W o and the bias term b f , b i , b C , b o .

[0122] m k =β 1 mk-1 +(1-β 1 ) k

[0123]

[0124]

[0125] in:

[0126] g k is the parameter W k With respect to the gradient of the loss function.

[0127] m k , v k They are the gradient g k The first and second moment estimates of .

[0128] α is the learning rate.

[0129] β 1 , β 2 are the decay rates respectively.

[0130] ε is a small constant that prevents division by zero.

[0131] Model training process reference Figure 2 shown.

[0132] In step S108, based on the predicted future ship and chart view center position information Determine whether the ship is within the bounding box of the chart view.

[0133] according to The center longitude and latitude of the chart view in the chart view and the width width and height height of the set chart interface are calculated to obtain the bounding box of the chart view at the next scheduled time: bbox = [lat min ,lat max ,lng min ,lng max ], where lat min Indicates the minimum latitude contained in the bounding box of the chart view, lat max Indicates the maximum latitude contained in the bounding box of the chart view, lng min Indicates the minimum longitude contained in the bounding box of the chart view, lng max Indicates the maximum value of the longitude contained in the bounding box of the chart view.

[0134] according to The ship position information and the chart view bounding box bbox in the nautical chart are used to predict whether the ship is located in the chart view bounding box at the next scheduled moment.

[0135] In some embodiments, the method further comprises:

[0136] Get the location information of the place of interest.

[0137] According to the location information of the point of interest and the bounding box of the nautical chart view, it is predicted whether the bounding box of the nautical chart view at the next scheduled time contains at least one point of interest.

[0138] It should be noted that “contained” can be located within the boundary of the chart view bounding box.

[0139] The location information of the places of interest is preloaded.

[0140] In step S110, requesting the network AIS data in the second bounding box includes: obtaining a predicted network AIS bounding box at the next scheduled moment.

[0141] Network AIS data includes all AIS vessel information.

[0142] In step S110, according to international standards (International Regulations for Preventing Collisions at Sea, International Chamber of Shipping's AIS User Guide, etc.) and actual operating experience, in busy waters, it is recommended that ships set a smaller range of concern (such as 5-10 nautical miles); in open waters, ships can set a larger range of concern (such as 20-30 nautical miles). Since the average speed of the ship is 10 to 20 nautical miles per hour, the reaction time is set to 30 minutes. The calculation formula for the ship's range of concern is as follows:

[0143] range=v n *0.5

[0144] It should be noted that, according to the ship's focus range or the ship's first focus range, the first bounding box is obtained, which does not include the range that is not in the chart view bounding box, that is, only the overlapping area is taken.

[0145] The chart view bounding box includes the border of the chart view bounding box.

[0146] The ship is located in the bounding box of the chart view, which refers to the status of the ship and the bounding box of the chart view at the same moment.

[0147] In some implementations, obtaining a first bounding box according to the focus range of the ship includes:

[0148] If the chart view bounding box contains at least one place of interest, determine whether the chart view bounding box contains at least one first place of interest according to the location information of the place of interest and the range of interest of the ship; if the chart view bounding box contains at least one first place of interest, obtain the first range of interest of the ship, and the first bounding box is the first range of interest of the ship;

[0149] If the first location of interest is not included in the bounding box of the chart view, the first bounding box is the vessel’s focus area;

[0150] If the chart view bounding box does not contain the location of interest, the first bounding box is the ship's area of ​​interest;

[0151] The first point of interest is located in a bounding box of a nautical chart view, and the first point of interest is not located in a range of interest of the ship; the first range of interest of the ship includes all first points of interest.

[0152] Reference Figure 3 As shown, if the ports, islands and other locations of interest are within the ship's range of interest, the ship's range of interest is expanded to include all ports, islands and other locations of interest, and this range is output as the network AIS request bounding box.

[0153] Reference Figure 4 As shown, if the ports, islands, etc. of interest are within the ship's range of interest, the ship's range of interest is directly output as the network AIS request bounding box.

[0154] Reference Figure 5 As shown, if the ship is located in the bounding box of the chart view, and there are no places of interest such as ports and islands in the bounding box of the chart view, the ship's focus range is output as the network AIS request bounding box.

[0155] Reference Figure 6 As shown, if the ship is not located in the chart view bounding box, the chart view bounding box is output as the network AIS request bounding box.

[0156] In some implementations, all AIS vessel information in the second bounding box is requested from the cloud platform and stored in a memory buffer.

[0157] That is, all AIS vessel information in the second bounding box at the next scheduled time is preloaded.

[0158] In some embodiments, the method further comprises:

[0159] The network AIS requests a third bounding box output; wherein the third bounding box is a non-overlapping range of the first bounding box at the current moment and the first bounding box at the current moment obtained through prediction.

[0160] When the AIS system refresh time is reached or the user stops operating the shipboard terminal chart interface, the same method is used to calculate the current network AIS request bounding box and compare it with the predicted chart view bounding box. The repeated areas of the two directly obtain the AIS ship information from the memory buffer, and the non-repeated areas re-request the AIS ship information from the cloud platform, which can reduce the bounding box range of the real-time requested AIS ship information.

[0161] Specifically, when the time difference from the last time the user operated the nautical chart reaches a second threshold, it is determined that the user stops operating the nautical chart interface of the shipborne terminal.

[0162] Please refer to the AIS vessel information loading flow chart Figure 7 shown.

[0163] In some embodiments, the method further comprises:

[0164] The network AIS requests the fourth bounding box to be output, wherein the chart view bounding box is composed of the second bounding box, the third bounding box and the fourth bounding box at the previous moment.

[0165] That is, in the spare time, the information in the bounding box of the chart view is loaded completely.

[0166] In some embodiments, the method further comprises: rendering the AIS vessel information (including real-time requested and pre-loaded) at the current moment in real time on the nautical chart interface of the shipborne terminal.

[0167] Embodiment 2

[0168] An embodiment of the present disclosure provides a network AIS data request device.

[0169] The device may include a corresponding module for executing each or several steps in the first flow chart above. Therefore, each step or several steps in the flow chart above may be executed by a corresponding module, and the device may include one or more modules in these modules. The module may be one or more hardware modules specially configured to execute the corresponding steps, or implemented by a processor configured to execute the corresponding steps, or stored in a computer-readable medium for implementation by a processor, or implemented by some combination.

[0170] Specifically, Figure 8 As shown, the device 1000 includes:

[0171] The information acquisition module 1002 is used to respectively acquire the ship navigation information, chart operation information, ship position information and chart view center position information at each moment;

[0172] The feature acquisition module 1004 is used to obtain a feature vector at a moment according to the ship navigation information, chart operation information, ship position information and chart view center position information at that moment;

[0173] A prediction module 1006, for obtaining the ship position information and the chart view center position information at the next scheduled moment according to the feature vector at each moment of a time series, wherein the time series is composed of the current moment and the moments before it;

[0174] A judgment module 1008, for predicting whether the ship is located in the bounding box of the chart view at the next scheduled moment according to the ship position information at the next scheduled moment and the center position information of the chart view;

[0175] The request module 1010 is used to request the network AIS data in the second bounding box; wherein, if the ship is located in the chart view bounding box, the first bounding box is obtained according to the ship's focus range; if the ship is not located in the chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted at the next scheduled time.

[0176] The embodiment of the present disclosure also provides an electronic device, including: a memory, the memory storing execution instructions; and a processor or other hardware module, the processor or other hardware module executes the execution instructions stored in the memory, so that the processor or other hardware module executes the above-mentioned network AIS request bounding box method.

[0177] The present disclosure also provides a readable storage medium, in which execution instructions are stored. When the execution instructions are executed by a processor, they are used to implement the above-mentioned method for requesting a bounding box of a network AIS.

[0178] Among them, the hardware structure adopted by the device of the network AIS request enclosing box based on the hardware implementation of the processor disclosed in the present invention can be implemented using a bus architecture. The bus architecture may include any number of interconnecting buses and bridges, depending on the specific application and overall design constraints of the hardware. The bus connects various circuits including one or more processors, memories and / or hardware modules together. The bus may also connect various other circuits such as peripherals, voltage regulators, power management circuits, external antennas, etc.

[0179] The bus can be an Industry Standard Architecture (ISA) bus, a Peripheral Component Interconnect (PCI) bus, or an Extended Industry Standard Component (EISA) bus, etc. The bus can be divided into an address bus, a data bus, a control bus, etc. For ease of representation, only one connecting line is used in this figure, but it does not mean that there is only one bus or one type of bus.

[0180] Any process or method description in the flowchart or otherwise described herein can be understood as a module, fragment or portion of a code representing one or more executable instructions for implementing the steps of a specific logical function or process, and the scope of the preferred embodiments of the present disclosure includes other implementations, in which the functions may not be performed in the order shown or discussed, including performing the functions in a substantially simultaneous manner or in a reverse order according to the functions involved, which should be understood by a person skilled in the art of the present disclosure. The processor performs the various methods and processes described above. For example, the method implementation in the present disclosure can be implemented as a software program, which is tangibly contained in a machine-readable medium, such as a memory. In some embodiments, part or all of the software program can be loaded and / or installed via a memory and / or a communication interface. When the software program is loaded into the memory and executed by the processor, one or more steps in the method described above can be performed. Alternatively, in other embodiments, the processor can be configured to perform one of the above methods in any other appropriate manner (e.g., by means of firmware).

[0181] The logic and / or steps represented in the flowchart or otherwise described herein may be embodied in any readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other system that can fetch instructions from and execute instructions on an instruction execution system, apparatus, or device), or in combination with such instruction execution systems, apparatuses, or devices.

[0182] For the purposes of this specification, a "readable storage medium" may be any device that can contain, store, communicate, propagate or transmit a program for use with or in conjunction with an instruction execution system, device or apparatus. More specific examples of readable storage media (a non-exhaustive list) include the following: an electrical connection with one or more wirings (electronic device), a portable computer disk case (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable and editable read-only memory (EPROM or flash memory), a fiber optic device, and a portable read-only memory (CDROM). In addition, the readable storage medium may even be paper or other suitable medium on which the program can be printed, since the program can be obtained electronically, for example, by optically scanning the paper or other medium, followed by editing, deciphering or, if necessary, processing in another suitable manner, and then stored in a memory.

[0183] It should be understood that the various parts of the present disclosure can be implemented in hardware, software, or a combination thereof. In the above-mentioned embodiments, multiple steps or methods can be implemented in software stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, it can be implemented by any one of the following technologies known in the art or their combination: a discrete logic circuit having a logic gate circuit for implementing a logic function for a data signal, a dedicated integrated circuit having a suitable combination of logic gate circuits, a programmable gate array (PGA), a field programmable gate array (FPGA), etc.

[0184] A person skilled in the art may understand that all or part of the steps of implementing the above-mentioned implementation method may be completed by instructing related hardware through a program, and the program may be stored in a readable storage medium, which, when executed, includes one or a combination of the steps of the implementation method.

[0185] In addition, each functional unit in each embodiment of the present disclosure may be integrated into a processing module, or each unit may exist physically separately, or two or more units may be integrated into one module. The above-mentioned integrated module may be implemented in the form of hardware or in the form of a software functional module. If the integrated module is implemented in the form of a software functional module and sold or used as an independent product, it may also be stored in a readable storage medium. The storage medium may be a read-only memory, a disk or an optical disk, etc.

[0186] Those skilled in the art should understand that the above embodiments are only for the purpose of clearly illustrating the present disclosure, and are not intended to limit the scope of the present disclosure. For those skilled in the art, other changes or modifications may be made based on the above disclosure, and these changes or modifications are still within the scope of the present disclosure.

Claims

1. A network AIS data request method, characterized in that: The method comprises: Obtain the ship navigation information, chart operation information, ship position information and chart view center position information at each moment respectively; According to the ship navigation information, chart operation information, ship position information and chart view center position information at a moment, a feature vector at that moment is obtained; According to the feature vector of each moment of a time series, the ship position information and the center position information of the chart view at the next scheduled moment are obtained, wherein the time series is composed of the current moment and the moments before the current moment; According to the ship position information at the next scheduled time and the center position information of the chart view, predict whether the ship is located in the bounding box of the chart view at the next scheduled time; Request network AIS data in the second bounding box; wherein, if the ship is located in the chart view bounding box, the first bounding box is obtained according to the ship's focus range; if the ship is not located in the chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted at the next scheduled moment.

2. The method according to claim 1, characterized in that The method further comprises: Get location information of places of interest; predicting, based on the location information of the place of interest, whether a bounding box of a nautical chart view at a next scheduled time contains at least one place of interest; According to the focus range of the ship, the first bounding box is obtained, including: If the chart view bounding box contains at least one place of interest, determine whether the chart view bounding box contains at least one first place of interest according to the location information of the place of interest and the range of interest of the ship; if the chart view bounding box contains at least one first place of interest, obtain the first range of interest of the ship, and the first bounding box is the first range of interest of the ship; If the first location of interest is not included in the bounding box of the chart view, the first bounding box is the vessel’s focus area; If the chart view bounding box does not contain the location of interest, the first bounding box is the ship's area of ​​interest; The first point of interest is located in a bounding box of a nautical chart view, and the first point of interest is not located in a range of interest of the ship; the first range of interest of the ship includes all first points of interest.

3. The method according to claim 1, characterized in that Obtain the ship's navigation information, chart operation information, ship position information and chart view center position information at each moment, including: Get the first eigenvector The second eigenvector and the third eigenvector Among them, v n represents the ship speed, θ n Indicates the ship's heading, Δt indicates the network AIS timing refresh time, d n Indicates the distance the chart is moved, r n Indicates the direction of chart movement, opt n Indicates the user's chart operation preferences, including zooming and moving, t indicates the timestamp of the user's chart operation, Indicates the longitude of the ship's position, Indicates the latitude of the ship's position, Indicates the longitude of the center of the chart. It represents the latitude of the center of the chart, and n represents the time.

4. The method according to claim 3, characterized in that According to the ship navigation information, chart operation information, ship position information and chart view center position information at a moment, the feature vector at that moment is obtained, including: The first eigenvector Multiply by the first weight w1, the second eigenvector Multiply by the second weight w2 and then with the third eigenvector P n Concatenate to get the feature vector Among them, if the user operates the nautical chart at the current moment, and the time difference between the time when the user operated the nautical chart last time is less than the first threshold, the first weight w1 and the second weight w2 respectively take the corresponding values ​​in the first weight value combination; if the user operates the nautical chart at the current moment, and the time difference between the time when the user operated the nautical chart last time is not less than the first threshold, the first weight w1 and the second weight w2 respectively take the corresponding values ​​in the second weight value combination.

5. The method according to claim 1, characterized in that Obtain the ship's navigation information, chart operation information, ship position information and chart view center position information at each moment, including: Normalize the data. Among them, X represents the original data, X max Indicates the preset maximum value of the data, X min Indicates the preset minimum value of the data, X norm Represents normalized data.

6. The method according to claim 1, characterized in that The method further comprises: The network AIS requests a third bounding box output; wherein the third bounding box is a non-overlapping range of the first bounding box at the current moment and the second bounding box at the previous moment.

7. The method according to claim 1, characterized in that According to the feature vector at each moment of a time series, the ship position information and the center position information of the chart view at the next scheduled moment are obtained, including: calling the LSTM network for analysis.

8. A network AIS data request device, characterized in that: The device comprises: An information acquisition module is used to respectively acquire the ship navigation information, chart operation information, ship position information and chart view center position information at each moment; A feature acquisition module is used to obtain a feature vector at a moment according to the ship navigation information, chart operation information, ship position information and chart view center position information at that moment; A prediction module, used for obtaining the ship position information and the center position information of the chart view at the next scheduled moment according to the feature vector at each moment of a time series, wherein the time series consists of the current moment and the moments before it; A judgment module, used to predict whether the ship is located in the bounding box of the chart view at the next scheduled moment according to the ship position information at the next scheduled moment and the center position information of the chart view; A request module is used to request network AIS data in a second bounding box; wherein, if the ship is located in a chart view bounding box, a first bounding box is obtained according to the ship's focus range; if the ship is not located in the chart view bounding box, the first bounding box is the chart view bounding box; wherein, the second bounding box is the first bounding box predicted at the next scheduled moment.

9. An electronic device, characterized in that: include: A memory storing execution instructions; as well as A processor, wherein the processor executes the execution instruction stored in the memory so that the processor executes the method according to any one of claims 1 to 7.

10. A readable storage medium, characterized in that: The readable storage medium stores execution instructions, which are used to implement the method according to any one of claims 1 to 7 when executed by a processor.

Images