Method for estimating waiting time of vessel and device using same

Abstract

The present invention relates to a method for estimating the waiting time of a vessel and a device using same, and the method may comprise the steps of: obtaining specification information and destination information of a specific vessel; and inputting the specification information and the destination information into a waiting time estimation model to output an estimated waiting time, which is the result of estimating the interval from a first time point at which the state of the specific vessel is switched to a first state in a first area corresponding to a destination to a second time point at which the state of the specific vessel is switched to a second state in a second area corresponding to the destination.

Description

Method for estimating the waiting time of a vessel and device using the same

[0001] Cross-citation with related applications

[0002] This invention claims the benefit of priority to Korean Patent Application No. 10-2024-0045558, filed April 3, 2024, the entire contents of which are incorporated herein by reference.

[0003] Technology field

[0004] The embodiments disclosed in this document relate to a method for estimating the waiting time of a ship and a device using the same.

[0005] Typically, ships are left anchored in the anchorage area waiting to berth due to the lack of facilities within the port, which results in waiting times for the ships.

[0006] In the past, the average waiting time that occurred at a specific port during a specific period (e.g., the last month) was generated as waiting time prediction information, and the waiting time prediction information generated in this way was provided to ships arriving at the anchorage area.

[0007] However, if the conventional method as above is followed, several problems will arise.

[0008] For example, using the average wait time over a specific period as a predictive value for wait times, as per the conventional method, can lead to significant inaccuracies. For example, while the average-based wait time prediction may be ten days, the actual wait time may be three days, a much shorter time, or vice versa.

[0009] As another example, if waiting time prediction information is provided retroactively to a vessel that has arrived at the anchorage area, there is a problem in that the waiting time prediction information has no significance beyond simple reference.

[0010] Therefore, there is a need for a solution to the above problems.

[0011] The embodiments disclosed in this document are intended to provide a method and apparatus for estimating the waiting time of a vessel.

[0012] The embodiments disclosed in this document are intended to provide a method and apparatus for deriving an optimal route for a vessel based on an estimated waiting time.

[0013] The embodiments disclosed in this document are intended to provide a method and device for establishing an efficient operation plan for a ship.

[0014] The embodiments disclosed in this document are intended to provide a method and device for reducing greenhouse gas emissions from a ship.

[0015] The technical problems of the present invention are not limited to the technical problems mentioned above, and other technical problems not mentioned will be clearly understood by those skilled in the art from the description below.

[0016] A method according to one embodiment disclosed in this document may include the steps of: obtaining specification information and destination information of a specific vessel; and inputting the specification information and the destination information into a waiting time estimation model, and outputting an estimated waiting time, which is a result of estimating an interval from a first point in time when the state of the specific vessel is switched to a first state in a first area corresponding to the destination to a second point in time when the state of the specific vessel is switched to a second state in a second area corresponding to the destination.

[0017] In one embodiment, prior to the step of outputting the estimated waiting time, the method may further include a step of learning the waiting time estimation model using a learning dataset including learning specification information and learning destination information of a plurality of learning vessels.

[0018] In one embodiment, the step of learning the waiting time estimation model may include the steps of inputting the learning specification information and the learning destination information into the waiting time estimation model and estimating an interval from a first learning point in time when the state of the learning vessel is switched to a first learning state to a second learning point in time when the state of the learning vessel is switched to a second learning state, thereby outputting a learning estimated waiting time, which is a result of estimating the interval; the step of generating a loss using the learning estimated waiting time and a ground truth (GT) waiting time corresponding thereto; and the step of updating at least some of the parameters of the waiting time estimation model based on the loss.

[0019] In one embodiment, the first learning state may be a state in which the location of the learning vessel is within a first learning area corresponding to the learning destination and the speed of the learning vessel is less than or equal to a first reference speed, and the second learning state may be a state in which the location of the learning vessel is within a second learning area corresponding to the learning destination and the speed of the learning vessel is less than or equal to a second reference speed.

[0020] In one embodiment, the first learning area and the second learning area may be set based on AIS (Automatic Identification System) data corresponding to the plurality of learning vessels.

[0021] In one embodiment, the first reference speed may be greater than the second reference speed.

[0022] In one embodiment, the destination information may include at least some of port location information, port operation information, congestion information of the first area, and congestion information of the second area, and the learning destination information may include at least some of learning port location information, learning port operation information, congestion information of the first area for learning, and congestion information of the second area for learning.

[0023] In one embodiment, the learning dataset further includes learning weather information, and in the step of acquiring the specification information and the destination information, weather information is additionally acquired, and in the step of outputting the estimated waiting time, the specification information, the destination information, and the weather information can be input into the waiting time estimation model to output the estimated waiting time.

[0024] In one embodiment, after the step of outputting the estimated waiting time, the method may further include a step of generating optimal route information for the specific vessel to reach the destination by referring to the estimated waiting time.

[0025] In one embodiment, after the step of generating the optimal route information, the method may further include a step of generating at least a portion of an estimated CII (Carbon Intensity Indicator) rating and an estimated fuel consumption of the specific vessel based on the optimal route information.

[0026] In one embodiment, after the step of generating at least a portion of the estimated CII grade and the estimated fuel consumption, the method may further include the step of providing at least a portion of the estimated waiting time, the optimal route information, the estimated CII grade, and the estimated fuel consumption to a user of the vessel through a human machine interface.

[0027] In one embodiment, after the step of generating the optimal route information, the method may further include a step of controlling the vessel by referring to the optimal route information.

[0028] A device according to one embodiment disclosed in the present document comprises a memory storing computer-executable instructions; and at least one processor accessing the memory to execute the instructions, wherein the at least one processor inputs specification information and destination information of a specific vessel into a waiting time estimation model to output an estimated waiting time, which is the time required for the specific vessel to berth in a berthing area corresponding to the destination from the time the vessel enters an anchoring area corresponding to the destination.

[0029] In one embodiment, the at least one processor may generate optimal route information for the specific vessel to reach the destination by referring to the estimated waiting time.

[0030] In one embodiment, the at least one processor may generate at least a portion of an estimated Carbon Intensity Indicator (CII) rating and an estimated fuel consumption of the specific vessel based on the optimal route information.

[0031] According to the present disclosure, a method and device for estimating the waiting time of a ship can be provided.

[0032] According to the present disclosure, a method and device for deriving an optimal route for a vessel based on an estimated waiting time can be provided.

[0033] According to the present disclosure, a method and device for establishing an efficient operation plan for a ship can be provided.

[0034] According to the present disclosure, a method and device for reducing greenhouse gas emissions from a ship can be provided.

[0035] In addition, various effects may be provided directly or indirectly through this document.

[0036] FIG. 1 is a flowchart illustrating a method for estimating the waiting time of a vessel according to one embodiment of the present disclosure.

[0037] FIG. 2 is a flowchart illustrating a learning process of a waiting time estimation model according to one embodiment of the present disclosure.

[0038] FIGS. 3A to 4B are diagrams illustrating a process of setting a first learning area and a second learning area according to one embodiment of the present disclosure.

[0039] FIGS. 5A to 5C are diagrams for explaining a process of determining a first learning point and a second learning point according to one embodiment of the present disclosure.

[0040] FIG. 6 is a flowchart illustrating a process of generating optimal route information by utilizing estimated waiting time information according to one embodiment of the present disclosure.

[0041] FIG. 7 is a block diagram illustrating a device according to one embodiment of the present disclosure.

[0042] In connection with the description of the drawings, the same or similar reference numerals may be used for identical or similar components.

[0043] Hereinafter, some embodiments of the present invention will be described in detail with reference to exemplary drawings. When adding reference numerals to components in each drawing, it should be noted that, as much as possible, identical components are given the same numerals even if they are shown in different drawings. In addition, when describing embodiments of the present invention, if a detailed description of a related known configuration or function is judged to hinder the understanding of the embodiments of the present invention, a detailed description thereof will be omitted. In particular, various embodiments of the present document are described with reference to the attached drawings. However, this is not intended to limit the technology described in the present document to a specific embodiment, and it should be understood that the embodiments of the present document include various modifications, equivalents, and / or alternatives. With regard to the description of the drawings, similar reference numerals may be used for similar components.

[0044] When describing components of embodiments of the present invention, terms such as first, second, A, B, (a), and (b) may be used. These terms are only intended to distinguish the components from other components and do not limit the nature, order, or sequence of the components. Furthermore, unless otherwise defined, all terms, including technical or scientific terms, used herein have the same meaning as commonly understood by a person of ordinary skill in the art to which the present invention pertains. Terms defined in commonly used dictionaries should be interpreted as having a meaning consistent with their meaning in the context of the relevant technology and shall not be interpreted in an idealized or overly formal sense unless explicitly defined in this application. For example, expressions such as "first," "second," "first," or "second," used in this document may modify various components, regardless of order and / or importance, and are only used to distinguish one component from another and do not limit the components. For example, the first user device and the second user device may represent different user devices, regardless of order or priority. For example, without departing from the scope of the rights set forth in this document, the first component may be referred to as the second component, and similarly, the second component may be referred to as the first component.

[0045] In this document, the expressions "has," "may have," "includes," or "may include" indicate the presence of a feature (e.g., a number, function, operation, or component such as a part), but do not exclude the presence of additional features.

[0046] When it is said that a component (e.g., a first component) is "(operatively or communicatively) coupled with / to" or "connected to" another component (e.g., a second component), it should be understood that the component is directly coupled to the other component, or can be connected via another component (e.g., a third component). Conversely, when it is said that a component (e.g., a first component) is "directly coupled to" or "directly connected to" another component (e.g., a second component), it should be understood that no other component (e.g., a third component) exists between the first component and the other component.

[0047] The expression "configured to" as used in this document can be used interchangeably with, for example, "suitable for," "having the capacity to," "designed to," "adapted to," "made to," or "capable of."

[0048] The term "configured (or set to)" may not necessarily mean "specifically designed to" in hardware. Instead, in some situations, the phrase "a device configured to" may mean that the device, in conjunction with other devices or components, is "capable of" doing something. For example, the phrase "a processor configured (or set to) perform A, B, and C" may refer to a dedicated processor (e.g., an embedded processor) for performing the operations, or a general-purpose processor (e.g., a CPU or an application processor) that can perform the operations by executing one or more software programs stored in a memory device. The terminology used herein is for the purpose of describing particular embodiments only and may not be intended to limit the scope of other embodiments. The singular form may include the plural form unless the context clearly dictates otherwise. Terms used herein, including technical or scientific terms, have the same meaning as commonly understood by one of ordinary skill in the art described in this document. Terms used in this document, defined in common dictionaries, may be interpreted as having the same or similar meaning within the context of the relevant technology. Unless explicitly defined herein, they shall not be interpreted in an idealized or overly formal sense. In some cases, even if a term is defined herein, it cannot be interpreted to exclude the embodiments of this document.

[0049] In this document, phrases such as "A or B," "at least one of A and / or B," or "one or more of A or / and B" can include all possible combinations of the items listed together. For example, phrases such as "A or B," "at least one of A and B," or "at least one of A or B" can all refer to (1) including at least one A, (2) including at least one B, or (3) including both at least one A and at least one B. Furthermore, in describing components of embodiments of the present invention, phrases such as "A or B," "at least one of A and B," "at least one of A or B," "A, B, or C," "at least one of A, B, and C," "at least one of A, B, or C," and "at least one of A, B, C, or any combination thereof" can include any one of the items listed together in that phrase, or all possible combinations thereof. In particular, a phrase such as "at least one of A, B, C, or any combination thereof" may include A or B or C, or any combination thereof, such as AB or ABC.

[0050] Hereinafter, embodiments of the present invention will be described in detail with reference to FIGS. 1 to 7.

[0051] FIG. 1 is a flowchart illustrating a method according to one embodiment of the present disclosure.

[0052] First, the specification information and destination information of a specific ship can be obtained (S110).

[0053] At this time, the destination information may include location information of the port that the ship is targeting.

[0054] As another example, the destination information may include at least some of the following: location information of the port targeted by the vessel, berthing time information required for the vessel, port operation information (e.g., operation time information), anchorage area corresponding to the target port, congestion information of the berthing area, departure location information of the vessel, planned draft information of the vessel, international oil price information, and freight index information.

[0055] Additionally, in step S110, additional weather information corresponding to the target port may be acquired. For example, the weather information may be weather information for an area located within a preset distance from the target port. In another example, the weather information may be weather information for an anchorage area and a berthing area corresponding to the target port. In yet another example, the weather information may be weather information for an area corresponding to the vessel's route.

[0056] And, when the specification information and destination information are acquired according to step S110, the estimated waiting time, which is the result of estimating the time required for a specific vessel to dock at the destination, can be output (S120).

[0057] For example, by inputting the specification information and the destination information into the waiting time estimation model, the estimated waiting time, which is the result of estimating the interval from the first point in time when the state of a specific vessel in the first area corresponding to the destination is changed to the first state to the second point in time when the state of a specific vessel in the second area corresponding to the destination is changed to the second state, can be output.

[0058] For example, the first area may be an anchoring area, and the second area may be a berthing area. In other words, the estimated waiting time may be the time from the first point in time when a specific vessel transitions from an anchoring area to an anchored state to the second point in time when it transitions from a berthing area to a berthing state.

[0059] For example, when additional weather information is obtained, the specification information, destination information, and weather information can be input into the waiting time estimation model to output the estimated waiting time.

[0060] At this time, the waiting time estimation model may be an estimation model based on machine learning.

[0061] For example, the waiting time estimation model may be pre-trained using a training dataset that includes training specification information and training destination information of multiple training vessels.

[0062] FIG. 2 is a flowchart illustrating a learning process of a waiting time estimation model according to one embodiment of the present disclosure.

[0063] First, by inputting the learning specification information and learning destination information into the waiting time estimation model, the estimated waiting time for learning, which is the result of estimating the time required for the learning vessel to dock at the learning destination, can be output (S210).

[0064] Specifically, by inputting learning source information and learning destination information into a waiting time estimation model, an estimated learning waiting time, which is the result of estimating the interval from the first learning point in time when the state of the learning ship is switched to the first learning state to the second learning point in time when the state of the learning ship is switched to the second learning state, can be output.

[0065] At this time, the learning destination information may include location information of the learning port targeted by the learning vessel.

[0066] As another example, the destination information for learning may include at least some of the following: location information of the learning port targeted by the learning vessel, berthing time information required for the learning vessel, operation information of the learning port (e.g., operation time information), congestion information of the anchoring area (first learning area) corresponding to the learning port, berthing area (second learning area), departure location information of the learning vessel, planned draft information of the learning vessel, international oil price information for learning, and freight index information for learning.

[0067] And, when the estimated waiting time for learning is output according to step S210, a loss can be generated using the error between the estimated waiting time for learning and the corresponding ground truth (GT) waiting time (S220).

[0068] And, when the loss is generated according to step S220, at least some of the parameters of the waiting time estimation model can be updated based on the loss (S230).

[0069] At this time, the first learning state may be a state in which the learning vessel is located within the first learning area corresponding to the learning destination, and the speed of the learning vessel is lower than the first reference speed. For example, the first learning area may be an anchoring area.

[0070] For example, when the first reference speed is set to 1.1 knots, the point in time when the learning vessel enters the first learning area and its speed decreases to 1.1 knots or less can be the first learning point in time when the state of the learning vessel is switched to the first learning state.

[0071] Additionally, the second learning state may be a state in which the learning vessel is located within a second learning area corresponding to the learning destination, and the speed of the learning vessel is lower than or equal to the second reference speed. The second learning area may be a berthing area.

[0072] For example, when the second reference speed is set to 0.5 knots, the point in time when the learning vessel enters the second learning area and its speed decreases to 0.5 knots or less can become the second learning point in time when the state of the learning vessel is switched to the second learning state.

[0073] For example, a first reference speed corresponding to a first learning area may be greater than a second reference speed corresponding to a second learning area.

[0074] For example, the first learning area and the second learning area can be set based on AIS (Automatic Identification System) data corresponding to multiple learning vessels.

[0075] Figures 3a to 4b are drawings showing the process of setting up a first learning area and a second learning area.

[0076] First, referring to FIGS. 3a and 3b, it is possible to confirm the process of establishing a first learning area (e.g., anchoring area) and a second learning area (e.g., berthing area) around the first learning port based on AIS data for learning vessels around the first learning port among AIS data collected for multiple learning vessels.

[0077] Specifically, as illustrated in FIG. 3a, a filtering process may be applied to AIS data for learning vessels around the first learning port to generate polygons (311). Furthermore, as illustrated in FIG. 3b, a grouping process may be applied to the polygons (311) to establish anchoring and berthing areas (310).

[0078] For example, a polygon group (310) located within a preset distance (or route length) from the first port for learning may be set as a docking area, and a polygon group (310) located outside the preset distance may be set as an anchoring area.

[0079] In addition, referring to FIGS. 4A and 4B, similar to the description in FIGS. 3A and 3B, it is possible to confirm the process of setting the first learning area (e.g., anchoring area) and the second learning area (e.g., berthing area) around the second learning port based on the AIS data for the learning vessels around the second learning port among the AIS data collected for a plurality of learning vessels.

[0080] Specifically, as illustrated in FIG. 4a, a filtering process may be applied to AIS data for learning vessels around the second learning port to generate polygons (411). Furthermore, as illustrated in FIG. 4b, a grouping process may be applied to the polygons (411) to establish anchoring and berthing areas (410).

[0081] For example, a polygon group (410) located within a preset distance (or route length) from a second port for learning may be set as a docking area, and a polygon group (410) located outside the preset distance may be set as a mooring area.

[0082] Figures 5a to 5c are drawings for explaining the process of determining the first learning point and the second learning point as described above.

[0083] First, referring to FIG. 5a, it can be confirmed that a first learning area (510) and a second learning area (520) are set around the third learning port based on AIS data (500) for a learning vessel around the third learning port.

[0084] In order for a ship to anchor, a process of reducing speed within the anchoring area is required, and as shown in Fig. 5b, it can be confirmed through AIS data (500) that the trajectories of ships are concentrated in some areas within the anchoring area.

[0085] Accordingly, when the first point in time at which the speed of the learning vessel becomes lower than the first reference speed within the first learning area (510, anchoring area) is confirmed through AIS data (500), that point in time can be set as the first learning point in time (i.e., anchoring point in time).

[0086] Similarly, in order for a ship to berth, a process of reducing speed within the berthing area is required, and as shown in FIG. 5c, it can be confirmed through AIS data (500) that the ship's speed is 0 in some areas within the berthing area.

[0087] Accordingly, when the first point in time at which the speed of the learning vessel within the second learning area (520, berthing area) becomes lower than the second reference speed (e.g., 0.5 knots) is confirmed through AIS data (500), that point in time can be set as the second learning point in time (i.e., berthing point in time).

[0088] Meanwhile, in the above, specification information and destination information are exemplarily described as input variables for learning a waiting time estimation model, but the method according to an embodiment disclosed in this document is not limited to the above example.

[0089] For example, the training dataset may additionally include weather information for learning.

[0090] Meanwhile, when the estimated waiting time is output according to step S120, the optimal route information for a specific vessel to reach the destination can be generated by referring to the estimated waiting time.

[0091] At this time, the optimal route information may be route information for reaching the first area (anchoring area) corresponding to the destination, but is not limited thereto. For example, the optimal route information may be route information for reaching the second area (berthing area) corresponding to the destination.

[0092] Meanwhile, once optimal route information reflecting the estimated waiting time is generated, the vessel can be controlled by referring to the optimal route information.

[0093] As another example, when optimal route information reflecting the estimated waiting time is generated, at least a portion of the estimated Carbon Intensity Indicator (CII) rating and estimated fuel consumption of a specific vessel can be generated based on the optimal route information.

[0094] And, at least some of the estimated waiting time, optimal route information, estimated CII class, and estimated fuel consumption can be provided to the ship's user through a human machine interface.

[0095] In the past, optimal route information was provided to the user of the ship without considering the waiting time of the ship, whereas the optimal route information generated by the method according to an embodiment disclosed in this document provides the user with the waiting time optimized for each port, thereby enabling the user to efficiently plan the operation of the ship.

[0096] FIG. 6 is a flowchart illustrating a process of generating optimal route information by utilizing estimated waiting time information according to one embodiment disclosed in this document.

[0097] Referring to Figure 6, vessel performance can be estimated by inputting vessel specifications and weather information (e.g., weather information provided by NOAA) into the vessel performance estimation module (S610_1). For example, the vessel's hydrostatic resistance and additional resistance can be estimated. Additionally, the relationship between the vessel's speed, power output, engine RPM, and fuel can be modeled.

[0098] Additionally, the vessel's specifications, destination information, and required berthing time information can be input into the waiting time estimation model to output the vessel's estimated waiting time (S610_2). For example, recommended arrival time information for the vessel's port of arrival can be additionally output.

[0099] Additionally, the ship's departure point, destination, departure time, arrival time, and loading condition information can be input into the optimal route generation unit to generate an initial optimal route solution for the ship (S610_3). For example, the optimal route generation unit can generate an initial optimal route solution based on a graph search algorithm, and the initial optimal route solution can be defined as the parent solution of the evolution strategy algorithm.

[0100] In addition, the optimal route generation unit can evaluate the initial optimal route solution using the vessel performance information and estimated waiting time information generated according to steps S610_1 and S610_2 (S620). For example, the optimal route generation unit can determine the vessel's optimal RPM through leg-specific power estimation and predict fuel consumption according to the initial optimal route solution.

[0101] And, the optimal route generation unit can generate an optimal route child solution by adding a random value of a normal distribution to an arbitrary waypoint coordinate (S630).

[0102] Furthermore, the optimal route generation unit can evaluate the optimal route child solution using the vessel performance information and estimated waiting time information generated according to steps S610_1 and S610_2 (S640). For example, the optimal route generation unit can determine the vessel's optimal RPM through leg-specific power estimation and predict fuel consumption according to the optimal route child solution.

[0103] Additionally, the optimal route generation unit can compare the optimal route parent solution and the optimal route child solution (S650). For example, the optimal route generation unit can compare the fuel consumption of the optimal route parent solution and the fuel consumption of the optimal route child solution.

[0104] If the fuel consumption of the optimal route parent solution is greater, the optimal route child solution can be used to update the optimal route parent solution (S660).

[0105] And, it can be determined whether the iteration criterion is satisfied (S670).

[0106] If the generation number condition is satisfied, the final updated solution can be defined as the optimal route solution.

[0107] If, at step S650, the fuel consumption of the optimal route parent solution is determined to be equal to or less than that of the optimal route parent solution, a new optimal route child solution can be generated. Furthermore, at step S670, if the generation count condition is not met, a new optimal route child solution can be generated.

[0108] For convenience of explanation, FIG. 6 exemplifies a method using a genetic algorithm to generate optimal route information. However, the optimal route information generation method disclosed in one embodiment of this document is not limited to a genetic algorithm. For example, optimal route information can be generated based on an optimization algorithm different from the genetic algorithm.

[0109] FIG. 7 is a block diagram illustrating a device according to one embodiment of the present disclosure.

[0110] A device (100) according to one embodiment may include a memory (120) storing computer-executable instructions and at least one processor (110) accessing the memory (120) to execute the instructions (122).

[0111] At this time, the processor (110) can input the specification information and destination information of a specific vessel into a waiting time estimation model to output an estimated waiting time, which is the time required from the time the specific vessel enters the anchoring area corresponding to the destination until it docks in the berthing area corresponding to the destination.

[0112] The above description is merely an example of the technical idea of ​​the present invention, and those skilled in the art will appreciate that various modifications and variations can be made without departing from the essential characteristics of the present invention.

[0113] The embodiments described above may be implemented using hardware components, software components, and / or a combination of hardware components and software components. For example, the devices, methods, and components described in the embodiments may be implemented using a general-purpose computer or a special-purpose computer, such as, for example, a processor, a controller, an arithmetic logic unit (ALU), a digital signal processor, a microcomputer, a field programmable gate array (FPGA), a programmable logic unit (PLU), a microprocessor, or any other device capable of executing instructions and responding to them. The processing device may execute an operating system (OS) and software applications running on the operating system. Furthermore, the processing device may access, store, manipulate, process, and generate data in response to the execution of the software. For ease of understanding, the processing device is sometimes described as being used alone; however, one of ordinary skill in the art will recognize that the processing device may include multiple processing elements and / or multiple types of processing elements. For example, a processing unit may include multiple processors, or a processor and a controller. Other processing configurations, such as parallel processors, are also possible.

[0114] Software may include a computer program, code, instructions, or a combination of one or more of these, and may configure a processing device to perform a desired operation or, independently or collectively, command the processing device. The software and / or data may be permanently or temporarily embodied in any type of machine, component, physical device, virtual equipment, computer storage medium or device, or transmitted signal wave, for interpretation by the processing device or for providing instructions or data to the processing device. The software may also be distributed over networked computer systems and stored or executed in a distributed manner. The software and data may be stored on a computer-readable recording medium.

[0115] The method according to the embodiment may be implemented in the form of program commands that can be executed through various computer means and recorded on a computer-readable medium. The computer-readable medium may include program commands, data files, data structures, etc., alone or in combination, and the program commands recorded on the medium may be those specially designed and configured for the embodiment or may be known and available to those skilled in the art of computer software. Examples of the computer-readable recording medium include magnetic media such as hard disks, floppy disks, and magnetic tapes, optical media such as CD-ROMs and DVDs, magneto-optical media such as floptical disks, and hardware devices specially configured to store and execute program commands such as ROMs, RAMs, and flash memories. Examples of program commands include not only machine language codes such as those generated by a compiler, but also high-level language codes that can be executed by a computer using an interpreter, etc.

[0116] The hardware device described above may be configured to operate as one or more software modules to perform the operations of the embodiment, and vice versa.

[0117] Although the embodiments described above have been described with limited drawings, those skilled in the art will appreciate that various technical modifications and variations can be applied based on the described embodiments. For example, appropriate results can still be achieved even if the described techniques are performed in a different order than described, and / or components of the described systems, structures, devices, circuits, etc. are combined or combined in a different manner than described, or are replaced or substituted with other components or equivalents.

[0118] Therefore, other implementations, other embodiments, and equivalents to the claims also fall within the scope of the claims described below.

[0119] Accordingly, the embodiments disclosed in the present invention are intended to illustrate, rather than limit, the technical concept of the present invention, and the scope of the technical concept of the present invention is not limited by these embodiments. The scope of protection of the present invention should be interpreted by the following claims, and all technical concepts within the scope equivalent thereto should be construed as being included within the scope of the present invention.

Claims

1. A step of obtaining information on the specifications and destination of a specific vessel; and A step of inputting the above specification information and the destination information into a waiting time estimation model and outputting an estimated waiting time, which is a result of estimating the interval from the first point in time when the state of the specific vessel in the first area corresponding to the destination is switched to the first state to the second point in time when the state of the specific vessel in the second area corresponding to the destination is switched to the second state. How to include.

2. In claim 1, Before the step of outputting the above estimated waiting time, A method characterized by further comprising a step of learning the waiting time estimation model using a learning dataset including learning specification information and learning destination information of a plurality of learning vessels.

3. In claim 2, The step of learning the above waiting time estimation model is: A step of inputting the above learning specification information and the learning destination information into the waiting time estimation model, and outputting the learning estimated waiting time, which is the result of estimating the interval from the first learning point in time when the state of the learning vessel is switched to the first learning state to the second learning point in time when the state of the learning vessel is switched to the second learning state; A step of generating a loss using the above learning-use estimated waiting time and the corresponding GT (ground truth) waiting time; and A method characterized by comprising the step of updating at least some of the parameters of the waiting time estimation model based on the loss.

4. In claim 3, A method characterized in that the first learning state is a state in which the location of the learning vessel is within a first learning area corresponding to the learning destination and the speed of the learning vessel is less than or equal to a first reference speed, and the second learning state is a state in which the location of the learning vessel is within a second learning area corresponding to the learning destination and the speed of the learning vessel is less than or equal to a second reference speed.

5. In claim 4, A method characterized in that the first learning area and the second learning area are set based on AIS (Automatic Identification System) data corresponding to the plurality of learning vessels.

6. In claim 4, A method characterized in that the first reference speed is greater than the second reference speed.

7. In claim 4, A method characterized in that the destination information includes at least some of port location information, port operation information, congestion information of the first area, and congestion information of the second area, and the learning destination information includes at least some of learning port location information, learning port operation information, congestion information of the first area for learning, and congestion information of the second area for learning.

8. In claim 2, The above learning dataset additionally includes learning weather information, In the step of acquiring the above specification information and the above destination information, Get additional weather information, In the step of outputting the above estimated waiting time, A method characterized in that the above specification information, the destination information, and the weather information are input into the waiting time estimation model and the estimated waiting time is output.

9. In claim 1, After the step of outputting the above estimated waiting time, A method characterized by further comprising the step of generating optimal route information for the specific vessel to reach the destination by referring to the estimated waiting time.

10. In claim 9, After the step of generating the above optimal route information, A method characterized by further comprising the step of generating at least a portion of an estimated Carbon Intensity Indicator (CII) rating and an estimated fuel consumption of the specific vessel based on the optimal route information.

11. In claim 10, After the step of generating at least a portion of the above estimated CII grade and the above estimated fuel consumption, A method characterized by further comprising the step of providing at least a portion of the estimated waiting time, the optimal route information, the estimated CII rating, and the estimated fuel consumption to a user of the vessel through a human machine interface.

12. In claim 9, After the step of generating the above optimal route information, A method characterized by further comprising a step of controlling the vessel by referring to the optimal route information.

13. In a device for estimating the waiting time of a ship, Memory that stores computer-executable instructions; and At least one processor that accesses the memory and executes the instructions Including, At least one processor above, By inputting the specification information and destination information of a specific vessel into a waiting time estimation model, the estimated waiting time, which is the time required for the specific vessel to berth in the berthing area corresponding to the destination from the time it enters the anchoring area corresponding to the destination, is output. device.

14. In claim 13, At least one processor above, A device characterized in that it generates optimal route information for the specific vessel to reach the destination by referring to the estimated waiting time.

15. In claim 14, At least one processor above, A device characterized in that it generates at least a portion of the estimated CII (Carbon Intensity Indicator) rating and estimated fuel consumption of the specific vessel based on the optimal route information.

Images