WO2022114302A1

WO2022114302A1 - Server and method for determination of ship route

Info

Publication number: WO2022114302A1
Application number: PCT/KR2020/017171
Authority: WO
Inventors: 김영도
Original assignee: 주식회사 웨더아이
Priority date: 2020-11-27
Filing date: 2020-11-27
Publication date: 2022-06-02
Also published as: KR102514765B1; KR20220074439A

Abstract

A sea route determination server for determining a ship route on the sea may comprise: a database which stores information on multiple waypoints; a network graph generator which, for each of the waypoints, connects the corresponding waypoint to multiple other waypoints on the basis of latitude data and longitude data included in the information on the multiple waypoints to generate multiple network graphs; a harbor information receiver which receives information on a departure and a destination from a user terminal; a network graph selector which selects one network graph from the multiple network graphs on the basis of the information on the departure and the destination; and a sea route information transmitter which transmits information on a sea route corresponding to the selected network graph to the user terminal.

Description

Server and method for determining the route of a vessel

The present invention relates to a server and method for determining the course of a ship.

The ship routing problem is basically a route optimization problem, and various algorithms have been proposed to solve it. For example, a typical example is the TREAD (Traffic Route Extraction and Anomaly Detection) algorithm for marine route discovery.

In addition, there is a method of unsupervised learning of recorded ship location data using AIS (Automatic Identication System) technology, predicting an effective ship movement route through this, and classifying a high-risk location. This method is useful for searching for and recommending a safe route by analyzing the route that ships usually travel, but has a disadvantage in that it does not provide an optimal route and does not reflect changing weather and tide information.

On the other hand, there was a way to approach the ship route optimization problem using the Strength Pareto Evolutionary Algorithm (SPEA2) optimization algorithm. The SPEA2 optimization algorithm is an algorithm designed to solve the multi-objective optimization problem. It is an algorithm that searches a path optimized for multiple goals by considering risk. Although the SPEA2 optimization algorithm is an algorithm that searches for optimal routes under various conditions in consideration of sea wind and current by reflecting weather information, it takes a considerable amount of time to calculate the first set of routes, so there is a limit to using it on an actual ship.

Also, there is an attempt to solve the shortest path problem of a ship by using the Dijkstra algorithm. However, Dijkstra's algorithm can only calculate a short-distance ship route, and when weather or tide information is taken into account, the calculation becomes too complicated to be used in practice.

Furthermore, recently, by improving the A* algorithm, which is an advanced version of Dijkstra's algorithm, an optimized route search method in consideration of ocean currents, maritime traffic, and anchoring has been proposed. Although the efficiency of calculating the optimal route was achieved by using the A* algorithm, the optimized route search method using the A* algorithm is more efficient in minimizing risks such as collision risk, traffic, and anchoring in short-distance routes rather than route optimization considering complex sea conditions. The viewpoint was considered, and the simulation was also performed only in a very short section, so the possibility of expansion for long-distance operation was low.

(Patent Document 1) Korean Patent Publication No. 10-1556723 (published on September 23, 2015)

The present invention derives an improved A* algorithm by substituting weather, sea wind information, and current information in the route calculation using the existing A* algorithm to provide an artificial intelligence-based ship route optimization service using marine weather data, We want to provide an optimal ship route using the improved A* algorithm.

Specifically, according to the present invention, a plurality of network graphs are generated by connecting a plurality of different waypoints for each of a plurality of waypoints, and an optimal ship route can be recommended to the user terminal by using the plurality of generated network graphs.

However, the technical problems to be achieved by the present embodiment are not limited to the technical problems described above, and other technical problems may exist.

As a technical means for achieving the above-mentioned technical problem, the route determination server for determining the route of the ship according to the first aspect of the present invention includes a database for storing information about a plurality of waypoints; a network graph generator for generating a plurality of network graphs by connecting a plurality of different waypoints for each waypoint based on latitude data and longitude data included in the information on the plurality of waypoints; a port information receiver configured to receive information on a departure point and a destination from the user terminal; a network graph selection unit for selecting one of the plurality of network graphs based on the information on the origin and destination; and a route information transmitter configured to transmit information on a route corresponding to the selected network graph to the user terminal.

A method for determining a route of a ship performed by a route determination server according to a second aspect of the present invention comprises the steps of: storing information about a plurality of waypoints; generating a plurality of network graphs by connecting a plurality of different waypoints for each waypoint based on latitude data and longitude data included in the information on the plurality of waypoints; Receiving information on the origin and destination from the user terminal; selecting one of the plurality of network graphs based on the information on the origin and destination; The method may include transmitting information on a route corresponding to the selected network graph to the user terminal.

The above-described problem solving means are merely exemplary, and should not be construed as limiting the present invention. In addition to the exemplary embodiments described above, there may be additional embodiments described in the drawings and detailed description.

According to any one of the above-described problem solving means of the present invention, the present invention connects a plurality of different waypoints for each of a plurality of waypoints to generate a plurality of network graphs, and an optimal ship using the plurality of generated network graphs A route may be recommended to the user terminal. In addition, the present invention can provide the search for the shortest route while minimizing the search in unnecessary parts by setting the direction from the starting point to the target location.

1 is a block diagram of a route determination server according to an embodiment of the present invention.

2A is a diagram illustrating information on a plurality of waypoints stored in a database according to an embodiment of the present invention.

2B is a diagram illustrating information on a plurality of waypoints stored in a database according to an embodiment of the present invention.

2C is a diagram illustrating information on a plurality of waypoints stored in a database according to an embodiment of the present invention.

3 is a diagram for explaining a method of generating a plurality of network graphs according to an embodiment of the present invention.

4A is a view for explaining a method for determining a route of a ship according to an embodiment of the present invention.

4B is a view for explaining a method of determining a route of a ship according to an embodiment of the present invention.

5 is a flowchart illustrating a method of generating a plurality of network graphs for route determination according to an embodiment of the present invention.

6 is a flowchart illustrating a method of determining a route of a ship according to an embodiment of the present invention.

DETAILED DESCRIPTION OF THE PREFERRED EMBODIMENTS Hereinafter, embodiments of the present invention will be described in detail with reference to the accompanying drawings so that those of ordinary skill in the art can easily implement them. However, the present invention may be embodied in several different forms and is not limited to the embodiments described herein. And in order to clearly explain the present invention in the drawings, parts irrelevant to the description are omitted, and similar reference numerals are attached to similar parts throughout the specification.

Throughout the specification, when a part is "connected" with another part, this includes not only the case of being "directly connected" but also the case of being "electrically connected" with another element interposed therebetween. . Also, when a part "includes" a certain component, it means that other components may be further included, rather than excluding other components, unless otherwise stated.

In this specification, a "part" includes a unit realized by hardware, a unit realized by software, and a unit realized using both. In addition, one unit may be implemented using two or more hardware, and two or more units may be implemented by one hardware.

Some of the operations or functions described as being performed by the terminal or device in this specification may be instead performed by a server connected to the terminal or device. Similarly, some of the operations or functions described as being performed by the server may also be performed in a terminal or device connected to the server.

Hereinafter, detailed contents for carrying out the present invention will be described with reference to the accompanying configuration diagram or process flow diagram.

1 is a block diagram of a route determination server 10 according to an embodiment of the present invention.

Referring to FIG. 1 , the route determining server 10 includes a database 100 , a network graph generating unit 110 , a port information receiving unit 120 , a network graph selecting unit 130 , and a route information transmitting unit 140 . can do. However, the route determination server 10 shown in FIG. 1 is only one implementation example of the present invention, and various modifications are possible based on the components shown in FIG.

Hereinafter, FIG. 1 will be described with reference to FIGS. 2A to 4B together.

The database 100 may collect and store offshore meteorological information including ocean currents, depth and wave heights, wind speed, wind power, and the like, for each sea zone for the global sea provided by the public and private sectors.

The database 100 may store information about a plurality of waypoints. Here, the plurality of waypoints means a point at which a plurality of ships intersect in a plurality of navigable routes or a significant point on the route. Such a plurality of waypoints may be changed due to, for example, a point through which a ship passes when sailing between sea zones, when a new port is built or a new route is opened, or an artifact is installed in the sea.

For example, referring to FIG. 2A , the database 100 may store latitude data and route data for each waypoint, and store a list of adjacent waypoints connected for each waypoint. For example, the database 100 stores latitude data and route data for waypoint No. 1, and waypoint No. 2, Waypoint No. 3, Waypoint No. 6 adjacent to Waypoint No. 1 with Waypoint No. 1 It can be mapped and saved.

The information processing unit (not shown) may subdivide the list of adjacent waypoints connected for each waypoint stored in the database 100 into information about each connected waypoint through a melt technique, and process it for future data utilization. have.

Referring to FIG. 2B , the database 100 includes distance values between other waypoints connected for each waypoint, latitude data and route data for other connected waypoints, and connection line information (edge information) connected between waypoints. Information can be stored for each waypoint. Here, the distance value between the two waypoints may be calculated through a predefined distance calculation function based on latitude data and longitude data of each of the two waypoints. In this case, the predefined distance calculation function may be defined as follows.

For example, the database 100 may store a distance value between waypoint No. 1 and waypoint No. 2 connected to waypoint No. 1, edge information between waypoint No. 1 and waypoint No. 2, latitude data for waypoint No. 2, and Route data can be mapped to waypoint No. 1 and stored. In addition, the database 100 stores a distance value between waypoint No. 1 and waypoint No. 3 connected to waypoint No. 1, edge information between waypoint No. 1 and waypoint No. 3, latitude data and route data for waypoint No. 3 can be mapped to waypoint No. 1 and stored.

On the other hand, when drawing a network graph in software or the like, a relationship matrix (or adjacency matrix) indicating whether each node is connected to or not connected to the other node is often used. Therefore, it is possible to express whether each node is connected to which node as a relationship matrix, and then express the relationship matrix as a network graph using, for example, a Python program.

Referring to FIG. 2C , the relation matrix information generating unit (not shown) generates relation matrix information indicating whether each waypoint is connected to another waypoint by using the relation information stored in the database 100 . can do. In this case, a network graph in which each waypoint created through the relationship matrix information becomes a node and a connection line between each waypoint becomes an edge may be generated.

The network graph generator 110 may generate a plurality of network graphs by connecting a plurality of other waypoints connected to each waypoint by using the relationship information and the relationship matrix information stored in the database 100 .

Referring to FIG. 3 together, the network graph generating unit 110 connects a plurality of different waypoints for each waypoint based on latitude data and longitude data included in information on a plurality of waypoints for each waypoint. You can create a network graph of

Here, each of the plurality of waypoints constituting the network graph is a node, and a connection line connecting each node is an edge. That is, the network graph generating unit 110 may generate a network graph including nodes and edges.

The network graph generating unit 110 may calculate a distance between waypoints based on latitude data and longitude data of each waypoint connected to each waypoint, and generate a network graph based on the calculated distance between the waypoints.

For example, when waypoints connected to waypoint No. 1 are waypoint 2, waypoint 3, and waypoint 6, the network graph generating unit 110 may store relationship information and relationship matrix information stored in the database 100 in the database 100 . is used to calculate distance

values connecting waypoints

1, 2, 3 and 6, and based on the calculated distance values,

waypoints

1, 2, 3 A first network graph connecting the waypoint and waypoint 6 may be generated.

After changing the route problem to the graph route optimization problem, the network graph generating unit 110 may generate a plurality of network graphs by connecting a plurality of other waypoints connected for each waypoint by using an optimization algorithm.

The network graph generating unit 110 generates a plurality of network graphs by connecting a plurality of other waypoints connected to each waypoint by utilizing weather information on ocean currents, depths, and meteorology of the world provided by the public and private sectors. can

The network graph generator 110 may give weights to edges between waypoints based on the calculated distances between waypoints. For example, the network graph generating unit 110 may assign a first weight to the edge between the corresponding waypoints because the greater the distance between the calculated waypoints, the higher the fuel consumption and the required sailing time for the vessel to navigate. The network graph generating unit 110 may assign a second weight greater than the first weight to the edge between the waypoints because the fuel consumption and voyage required for the vessel to navigate decreases as the distance between the calculated waypoints decreases. have. As another example, the network graph generator 110 may assign different additional weights or adjust weights to edges between waypoints calculated based on maritime weather information.

Here, the weight given to the edge between each waypoint (node) may be utilized as a heuristic distance of the improved A* algorithm (optimized route derivation algorithm). That is, the weight given to the edge between each waypoint may mean a heuristic distance calculated using latitude data and longitude data of each waypoint.

The network graph generating unit 110 reflects the marine weather information (eg, sea wind, ocean current, information on the speed and direction of waves, etc.) on the sea to the existing A* algorithm, thereby improving the A* algorithm (optimized route derivation algorithm). ) can be derived.

Here, the A* algorithm may be defined as follows.

< A* Algorithm >

The A* algorithm first selects the node with the smallest expected distance to the target point on the Openlist (ie, f(x), which is the sum of cost + heuristic function). Here, Openlist is a list to which all possible nodes on a path are added, and the expected distance function f(x) is the cost function g(x) corresponding to the sum of distance consumption values of the paths passed so far, and the current point and target. As the sum of h(x), which is the heruistic function of the estimated distance to the point, it means the estimated distance and fuel consumption for the entire route from the departure port to the arrival port. If the node is the destination node, it means that all path finding has been completed, so the algorithm is terminated. Among the nodes adjacent to the corresponding node, the nodes not belonging to the Closelist are one of the possible paths, so they are added to the Openlist, and the estimated distance f(x) to the destination of the adjacent nodes is calculated. If the neighbor node was already in the Openlist, and the calculated f(x) value is smaller, it means that the current path is more optimal, so the f(x) value is updated, and the neighbor node and the node are set as Parent-Child relationship. connect If the above steps are repeated until the path finding is completed, an optimized path according to the A* algorithm is derived.

In addition, the network graph generating unit 110 may reflect the estimated sailing time and fuel consumption for each of a plurality of routes corresponding to the plurality of network graphs in the improved A* algorithm. Through this, an optimized route can be derived using the improved A* algorithm.

The database 100 stores a plurality of network graphs generated by the network graph generating unit 110, and for each network graph, relationship information related to each network graph, and distances and edges between a plurality of waypoints included in each network graph. Information can be mapped and stored.

The port information receiver 120 may receive information on the departure point and the destination of the ship from the user terminal. For example, the ship's departure point information includes a port name corresponding to the departure port from which the ship departs or latitude and longitude information where the departure port is located, and the ship's destination information includes a port name or Latitude and longitude information where the destination port is located may be included.

The network graph selection unit 130 may select one of a plurality of network graphs based on information on the origin and destination.

For example, the network graph selection unit 130 may search for information on a waypoint corresponding to the source information and the waypoint corresponding to the destination information using relationship information related to a plurality of network graphs stored in the database 100 . can Also, the network graph selection unit 130 may select a plurality of network graphs including a waypoint corresponding to the searched source information and a waypoint corresponding to the destination information from among the plurality of network graphs stored in the database 100 .

For example, referring to FIG. 4A , when the waypoint corresponding to the departure point information is the waypoint number 11 and the waypoint corresponding to the destination information is the waypoint number 2374, the network graph selection unit 130 is configured in the database 100 ), a network graph with waypoint 11 as a starting point and waypoint 2374 as a destination among a plurality of network graphs stored in Latitude data and route data of each waypoint can be retrieved.

The network graph selection unit 130 may select a network graph having the shortest path based on weights of a plurality of edges included in a plurality of network graphs including a waypoint corresponding to a departure point and a waypoint corresponding to a destination. For example, the network graph selection unit 130 may search a network graph having the shortest path using a shortest path search algorithm (eg, A* algorithm).

The network graph selection unit 130 may calculate the estimated sailing time and fuel usage information for each network graph with respect to a plurality of network graphs including a waypoint corresponding to a departure point and a waypoint corresponding to a destination.

The network graph selection unit 130 extracts a network graph having a distance value equal to or less than a preset threshold value from among a plurality of network graphs including a waypoint corresponding to a departure point and a waypoint corresponding to a destination, and at least one extracted network An optimal network graph may be selected based on the voyage required time and fuel usage information for the graph.

The network graph selection unit 130 extracts a network graph having a distance value that is less than or equal to a preset threshold value from among a plurality of network graphs including a waypoint corresponding to a departure point and a waypoint corresponding to a destination, and corresponds to the extracted network graph. It is possible to select an optimal network graph from among the network graphs extracted based on maritime weather information on the route. Here, the marine weather information may include, for example, at least one of wave height, wave direction, wind direction, surface pressure, swell height, swell direction, current, tropical typhoon, and ice cover. .

The network graph selection unit 130 extracts a network graph having a distance value that is less than or equal to a preset threshold value from among a plurality of network graphs including a waypoint corresponding to a departure point and a waypoint corresponding to a destination, and corresponds to the extracted network graph. It is possible to select an optimal network graph from among the extracted network graphs based on maritime traffic information on the route.

The route information transmitter 140 may transmit information on a route corresponding to a network graph having the selected shortest route to the user terminal. For example, referring to FIG. 4B , the route information transmitter 140 may display a route corresponding to the selected network graph on the map UI and transmit it to the user terminal.

Here, the information on the route corresponding to the selected network graph may include, for example, information on the estimated sailing distance according to the route, information on the sailing time, the average sailing speed of the ship, fuel usage information for the operation of the ship, and the like. In addition, the information on the route corresponding to the selected network graph may include expected maritime weather information for each flight date, current maritime weather information, maritime traffic information, depth information of the sea on the route, and the like.

For example, the weather forecast information providing unit (not shown) reflects the weather forecast information selected by the user terminal among information included in the information on the route corresponding to the selected network graph on the sea of the map and provides it to the user terminal. have.

For example, when the user terminal requests information on the wave height of the sea, the weather forecast information providing unit (not shown) reflects the current wave height information by changing the color of the sea level on the route corresponding to the selected network graph. may be provided to the user terminal. When the user terminal requests information on the wave direction or the wind direction in the sea, the weather forecast information providing unit (not shown) provides information on the direction in which waves travel on the sea of the map or wind direction information on the route corresponding to the selected network graph. can be displayed and provided to the user terminal.

The weather forecast information providing unit (not shown) provides summary information of at least one weather forecast information on the route to the user terminal based on the information on the route corresponding to the network graph selected by the user terminal, and provides the user terminal with the route from the user terminal. Upon receiving a request for detailed information of the weather forecast information for , detailed information of the weather forecast information may be provided to the user terminal. Here, the summary information of the weather forecast information for the route may include, for example, a map on which the location of a port corresponding to each departure and destination is displayed, and wind and wave strength information for each date on the route. Detailed information of the weather forecast information for the route includes the port name, latitude and longitude, port country information, local time information, etc. corresponding to the departure point and destination, detailed information on the port including the direction and speed of the wind on the route by date. It may include wind weather information, wave weather information including the travel direction and height of waves by date, and visible weather information including current visibility distance information of ports corresponding to departures and destinations.

Meanwhile, for those skilled in the art, each of the database 100 , the network graph generating unit 110 , the port information receiving unit 120 , the network graph selecting unit 130 , and the route information transmitting unit 140 is implemented separately, or one of them It will be fully understood that the above may be integrated and implemented.

Referring to FIG. 5 , in step S501 , the route determining server 10 may store information on a plurality of waypoints in the database 100 . Here, the information on the plurality of waypoints may include latitude data and longitude data of the waypoints.

In step S503, the route determination server 10 may generate a plurality of network graphs by connecting a plurality of different waypoints for each waypoint based on latitude data and longitude data included in the information on the plurality of waypoints. In this case, a plurality of network graphs generated for each waypoint may be stored in the database 100 .

In the above description, steps S501 to S503 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted if necessary, and the order between steps may be changed.

Referring to FIG. 6 , in step S601 , the route determination server 10 may receive information on a departure point and a destination from the user terminal.

In step S603, the route determination server 10 may select one of a plurality of network graphs stored in the database 100 based on the information on the departure point and the destination.

In step S605, the route determination server 10 may transmit information on a route corresponding to the selected network graph to the user terminal.

In the above description, steps S601 to S607 may be further divided into additional steps or combined into fewer steps, according to an embodiment of the present invention. In addition, some steps may be omitted if necessary, and the order between steps may be changed.

An embodiment of the present invention may also be implemented in the form of a recording medium including instructions executable by a computer, such as a program module executed by a computer. Computer-readable media can be any available media that can be accessed by a computer and includes both volatile and nonvolatile media, removable and non-removable media. Also, computer-readable media may include all computer storage media. Computer storage media includes both volatile and nonvolatile, removable and non-removable media implemented in any method or technology for storage of information such as computer readable instructions, data structures, program modules or other data.

The above description of the present invention is for illustration, and those of ordinary skill in the art to which the present invention pertains can understand that it can be easily modified into other specific forms without changing the technical spirit or essential features of the present invention. will be. Therefore, it should be understood that the embodiments described above are illustrative in all respects and not restrictive. For example, each component described as a single type may be implemented in a dispersed form, and likewise components described as distributed may be implemented in a combined form.

The scope of the present invention is indicated by the following claims rather than the detailed description, and all changes or modifications derived from the meaning and scope of the claims and their equivalent concepts should be construed as being included in the scope of the present invention. .

Claims

In the route determination server for determining the route of the ship,

a database for storing information about a plurality of waypoints;

a network graph generator for generating a plurality of network graphs by connecting a plurality of different waypoints for each waypoint based on latitude data and longitude data included in the information on the plurality of waypoints;

a port information receiver configured to receive information on a departure point and a destination from the user terminal;

a network graph selection unit for selecting one of the plurality of network graphs based on the information on the origin and destination; and

A route information transmitter for transmitting information on a route corresponding to the selected network graph to the user terminal

That comprising a, route determination server.
The method of claim 1,

Each of the plurality of waypoints is a node, and a connecting line connecting each node is an edge,

The network graph generating unit will generate a network graph including the node and the edge, the route determination server.
3. The method of claim 2,

The network graph generating unit

calculating a distance between waypoints based on latitude data and longitude data of each of the plurality of waypoints;

and generating the network graph based on the calculated distance between waypoints.
4. The method of claim 3,

The network graph generating unit

The route determination server, wherein a weight is given to the edge based on the distance between the waypoints.
4. The method of claim 3,

Wherein the database maps and stores the distances between a plurality of waypoints included in each network graph for each network graph.
5. The method of claim 4,

The network graph selection unit selects a network graph having a shortest path based on weights of a plurality of edges included in a plurality of network graphs including a waypoint corresponding to the source and a waypoint corresponding to the destination, routing server.
In the method of determining the route of a ship performed by the route determination server,

storing information about a plurality of waypoints;

generating a plurality of network graphs by connecting a plurality of different waypoints for each waypoint based on latitude data and longitude data included in the information on the plurality of waypoints;

Receiving information on the origin and destination from the user terminal;

selecting one of the plurality of network graphs based on the information on the origin and destination;

Transmitting information on a route corresponding to the selected network graph to the user terminal

That comprising a, route determination method.
8. The method of claim 7,

Each of the plurality of waypoints is a node, and a connecting line connecting each node is an edge,

The step of generating the plurality of network graphs

A method for determining a route comprising generating a network graph including the node and the edge.
9. The method of claim 8,

The step of generating the plurality of network graphs

calculating a distance between waypoints based on latitude data and longitude data of each of the plurality of waypoints;

and generating the network graph based on the calculated distance between waypoints.
10. The method of claim 9,

The step of generating the plurality of network graphs

and weighting the edge based on the distance between the waypoints.
10. The method of claim 9,

The method further comprising the step of mapping and storing distances between a plurality of waypoints included in each network graph for each network graph for each network graph.
11. The method of claim 10,

The selecting step

Selecting a network graph having a shortest path based on weights of a plurality of edges included in a plurality of network graphs including a waypoint corresponding to the departure point and a waypoint corresponding to the destination How to decide.