Apparatus, method and program

Abstract

To provide a control device, a control method, and a program to control an own ship according to recommended control parameters for reaching the destination from the current location of the ship.SOLUTION: A control device comprises: an acquisition unit that acquires status data indicating the information about a sea route from the current position to the destination of a ship and indicating residual time until the deadline for the arrival at the destination, and a control parameter indicating the control contents of the ship; and a learning processing unit that performs a learning process of a model to output the recommended control parameter indicating the recommended control content of the ship using learning data including the status data and the control parameter acquired by the acquisition unit in response to input of the status data. The information related to the sea route includes a distance from the current ship position to the destination.SELECTED DRAWING: Figure 1

Description

[Technical Field]

[0001] The present invention relates to an apparatus, a method, and a program. [Background technology]

[0002] Patent documents 1 to 4 state that "the attitude A of the ship relative to the pier or mooring point where the ship is to be docked or departed, the speed V of the ship, and the propulsive force F applied to the ship are learned by machine learning..." (Claim 1 of Patent document 1). [Prior art document] [Patent documents] [Patent Document 1] JP 2020-26208 A [Patent Document 2] JP 2021-18484 A [Patent Document 3] JP 2021-195076 A [Patent Document 4] JP 2021-195077 A Summary of the Invention

[0003] In a first aspect of the present invention, there is provided an apparatus comprising: an acquisition unit that acquires information regarding the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the control content of the ship; and a learning processing unit that performs a learning process for a model using learning data including the status data and control parameters acquired by the acquisition unit to output recommended control parameters indicating the recommended control content of the ship in response to input of status data.

[0004] In the above device, the information about the route may include the distance from the ship's current position to the destination.

[0005] In any of the above devices, the information about the route may include information about at least one of weather and sea conditions on the route.

[0006] In any of the above devices, the status data may include information relating to the current state of the ship.

[0007] In the above device, the information regarding the current ship status may indicate at least one of the ship's speed, inclination, magnitude of rolling, amount of cargo, weight of ballast, draft level, engine output, fuel consumption, power generation, electricity consumption, or internal pressure of liquefied gas tanks installed on the ship.

[0008] In any of the above devices, the control content may relate to at least one of ballast weight, draft level, engine output, ship speed, and power generation amount.

[0009] In any of the above devices, the learning processing unit may perform a learning process for the model using the learning data and a reward value determined by a preset reward function, and the model may output recommended control parameters indicating control content recommended for increasing the reward value determined by the reward function above a reference reward value in response to input of situation data.

[0010] In the above device, the reward function may have at least one parameter related to the fuel consumption of the ship, the magnitude of pitching of the ship, or the difference between the amount of power generated and the amount of power consumed by the ship.

[0011] Any of the above devices may be provided with a supply unit that supplies situation data acquired by the acquisition unit to the model that has undergone learning processing by the learning processing unit, and a control unit that controls the ship in accordance with recommended control parameters output from the model in response to the supply of situation data to the model by the supply unit.

[0012] In a second aspect of the present invention, a method is provided that includes an acquisition step of acquiring information about the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the ship's control content, and a learning processing step of performing a model learning process using learning data including the status data and control parameters acquired in the acquisition step to output recommended control parameters indicating the ship's recommended control content in response to input status data.

[0013] In a third aspect of the present invention, a program is provided that causes a computer to function as an acquisition unit that acquires information about the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the control content of the ship, and a learning processing unit that performs a model learning process using learning data including the status data and control parameters acquired by the acquisition unit to output recommended control parameters indicating the recommended control content of the ship in response to input of status data.

[0014] The above summary of the invention does not list all of the necessary features of the present invention, and subcombinations of these features may also constitute inventions. [Brief explanation of the drawings]

[0015] [Figure 1] 1 shows a device 1 according to the present embodiment. [Figure 2] An example of training data is shown below. [Figure 3] 10 shows the operation of the device 1 according to the present embodiment in the learning stage. [Figure 4] 1 shows the operation of the device 1 according to this embodiment in the operation stage. [Figure 5] 22 illustrates an example computer 2200 in which aspects of the present invention may be embodied, in whole or in part. DETAILED DESCRIPTION OF THE INVENTION

[0016] The present invention will be described below through embodiments of the invention, but the following embodiments do not limit the scope of the invention according to the claims. Furthermore, not all of the combinations of features described in the embodiments are necessarily essential to the solution of the invention.

[0017] <1.Device 1> 1 shows a device 1 according to this embodiment. The device 1 is installed on a ship to support the operation of the ship, and includes a data acquisition unit 10, a reward value acquisition unit 11, a memory unit 12, a learning processing unit 13, a model 14, a supply unit 15, and a control unit 16.

[0018] The ship on which the device 1 is installed may be any of a passenger ship, a cargo ship (for example, an LNG tanker or a container ship), a fishing ship (for example, a whaling ship or a trawler), a work boat (for example, a tugboat), or a naval vessel. The ship may also be one that operates multiple times along a predetermined route. In this embodiment, as an example, the ship may be an LNG tanker that transports liquefied gas (for example, LNG gas).

[0019] <1.1. Data Acquisition Unit 10> The data acquisition unit 10 is an example of an acquisition unit, and acquires information regarding the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the control content of the ship.

[0020] Here, the information about the route may include the distance from the ship's current position to the destination. The information about the route may include information about the environment along the route, for example, information about at least one of weather and sea conditions along the route. The information about weather may indicate, for example, temperature, air pressure, wind direction, wind speed, and amount of precipitation (snowfall). The information about sea conditions may indicate, for example, sea wind, significant wave height, wind waves, and ocean currents. The information about the environment along the route may indicate the environment at the current time. In addition, the information about the environment along the route may indicate the environment predicted at each point from the ship's current position to the destination at each point from the present to the arrival deadline.

[0021] The status data may further include information regarding the current state of the ship. The information regarding the current state of the ship may indicate at least one of the ship's speed, inclination, magnitude of pitching, cargo volume, ballast weight, draft level, engine output, fuel consumption, power generation, electricity consumption, or internal pressure of liquefied gas tanks installed on the ship. The inclination of the ship may be the inclination in the fore-and-aft direction or the inclination in the lateral direction. The magnitude of pitching may be seismic intensity (for example, engineering seismic intensity) or the maximum change in inclination within a reference time period. The amount of cargo may be the weight of the cargo or the volume of cargo on deck. The amount of fuel consumption may be the amount of fuel consumed per unit time, i.e., the fuel consumption rate, or may be the cumulative amount of fuel consumed up to the present time. The amount of electricity consumption may be the amount of electricity consumed on board the ship per unit time. The amount of electricity generated by an onboard generator per unit time. The internal pressure of a liquefied gas tank on board the ship may be the internal pressure of a tank on board the ship that contains liquefied gas, and may indicate the amount of gas available for use as vaporized fuel. The data acquisition unit 10 may acquire the situation data from an external device (not shown) of the device 1, for example, from a sensor installed on the ship, from a server on land or the like via a communication device, or from a crew member via an input device. When the data acquisition unit 10 acquires information indicating the predicted environment at each point from the current position of the ship to the destination at each time point between the present and the arrival deadline as information regarding the environment on the route, the data acquisition unit 10 may acquire the information from a server on land or the like.

[0022] The control content of the ship may be related to at least one of ballast weight, draft level, engine output, ship speed, and power generation amount. The data acquisition unit 10 may acquire control parameters indicating the control content from the control unit 16 described below.

[0023] The data acquisition unit 10 may associate the acquired situation data and control parameters and supply them to the storage unit 12. In the present embodiment, as an example, the data acquisition unit 10 will be described as associating the control parameters with situation data after the ship has been controlled with the control content indicated by the control parameters and supplying them, but the situation data may also be associated with control parameters indicating the control content of the ship controlled in the situation indicated by the situation data and supplied. The data acquisition unit 10 may further supply the acquired situation data to the reward value acquisition unit 11 and the supply unit 15.

[0024] <1.2. Reward value acquisition unit 11> The reward value acquisition unit 11 acquires a reward value used in reinforcement learning by the learning processing unit 13, and acquires a reward value for evaluating the operational status of the ship. The reward value may be a value determined by a preset reward function. Here, the function is a mapping having a rule that associates each element of a set with each element of another set in a one-to-one relationship, and may be, for example, a mathematical formula or a table. In this embodiment, as an example, the reward value acquisition unit 11 acquires a reward value by inputting situation data from the data acquisition unit 10 into the reward function. However, the reward value may also be acquired from a crew member who uses the reward function via an input device. The reward value acquisition unit 11 may supply the acquired reward value to the memory unit 12.

[0025] The reward function may be arbitrarily set and may have one or more parameters indicated by the situation data. The reward function may have at least one parameter related to the amount of fuel consumed by the ship, the magnitude of the ship's pitching, or the difference between the amount of power generated and the amount of power consumed by the ship.

[0026] <1.3.Storage section 12> The storage unit 12 stores a plurality of pieces of learning data including situation data and control parameters acquired by the data acquisition unit 10. The storage unit 12 may store the situation data and control parameters supplied from the data acquisition unit 10 in association with each other as learning data. The storage unit 12 may store the reward value supplied from the reward value acquisition unit 11 in association with learning data (for example, learning data including situation data that is the basis of the reward value).

[0027] <1.4. Learning Processing Unit 13> The learning processing unit 13 performs a learning process for the model 14 using the learning data. The learning processing unit 13 may perform reinforcement learning, and may perform the learning process for the model 14 using the learning data and a reward value determined by a preset reward function. The learning processing unit 13 may perform the learning process for the model 14 using the learning data and the reward value stored in association with each other in the storage unit 12. The learning processing unit 13 may perform learning using an algorithm such as Kernel Dynamic Policy Programming (KDPP), a steepest descent method, a support vector machine, a logistic regression, a decision tree, or a neural network, for example.

[0028] <1.5.Model 14> The model 14 outputs recommended control parameters indicating recommended ship control details in response to input situation data. The model 14 may output recommended control parameters indicating recommended control details for increasing the reward value determined by the reward function above a base reward value in response to input situation data. The base reward value may be a reward value corresponding to the situation at a predetermined time (for example, the present) (for example, a reward value obtained by inputting situation data at that time into the reward function), or may be a preset fixed value (for example, a value obtained by subtracting an allowable value from the maximum reward value).

[0029] For example, in response to newly input status data, the model 14 may comprehensively calculate predicted status data transitions when one of multiple control contents is selected at each of multiple future time points until the arrival deadline. If the status data includes environmental information such as weather or sea conditions along the route, the model 14 may calculate a predicted status data transition using forecast information for each time point and each location between the present and the arrival deadline, acquired by the data acquisition unit 10. For each of the status data transitions, the model 14 may calculate the sum of reward values ​​obtained by inputting the status data at each time point into a reward function, and may identify one status data transition that maximizes the sum of reward values. The model 14 may identify any status data transition in which the reward value at the most recent time point is higher than the reference reward value. The model 14 may output, as a recommended control parameter, a control parameter indicating the most recent control content among the control contents at each time point corresponding to the identified status data transitions.

[0030] <1.6. Supply section 15> The supply unit 15 supplies the situation data acquired by the data acquisition unit 10 to the model 14 that has been subjected to learning processing by the learning processing unit 13. As a result, recommended control parameters according to the situation data may be output from the model 14 to the control unit 16.

[0031] <1.7. Control Unit 16> The control unit 16 controls each part of the ship. The control unit 16 may control the ship according to recommended control parameters output from the model 14 in response to the supply unit 15 supplying the model 14 with situation data. The control unit 16 may control the ship according to the control content indicated by the recommended control parameters, and may control the ship by supplying the recommended control parameters as control parameters to each part of the ship. Targets to which the control parameters are supplied may include, for example, pumps or valves for increasing or decreasing ballast water, engines, generators, and steering gears. The control unit 16 may also supply the control parameters to the data acquisition unit 10.

[0032] According to the above-described device 1, information about the route from the current position to the destination, situation data indicating the time remaining until the deadline for arrival at the destination, and control parameters indicating the control content of the ship are acquired, and a learning process for the model 14 is performed using learning data including the acquired situation data and control parameters. Therefore, it is possible to acquire a model 14 that outputs recommended control content according to the remaining route and remaining time in response to input of situation data. As a result, for example, when there is ample time remaining and weather conditions are poor on the remaining route, it is possible to acquire, as the recommended control content, control content such as anchoring the ship rather than forcing it to proceed toward the destination, or heading for a waypoint with good weather conditions.

[0033] Furthermore, since the information about the route includes the distance from the ship's current position to the destination, it is possible to obtain a model 14 that outputs recommended control content according to the remaining route distance and remaining time.

[0034] Furthermore, since the information about the route includes information about at least one of the weather and sea conditions along the route, it is possible to obtain a model 14 that outputs recommended control content according to the environment of the remaining route and the remaining time.

[0035] Furthermore, since the status data includes information regarding the current state of the ship, it is possible to obtain a model 14 that outputs recommended control content according to the current state of the ship, the remaining route, and the remaining time.

[0036] Furthermore, since the information regarding the current ship condition indicates at least one of the ship's speed, inclination, rolling, cargo volume, ballast weight, draft level, engine output, power generation amount, power consumption, or internal pressure of the liquefied gas tanks installed on the ship, it is possible to obtain a model 14 that outputs recommended control content according to the specific ship condition indicated by the information.

[0037] In addition, since the control content relates to at least one of ballast weight, draft level, engine output, ship speed, or power generation, it is possible to obtain a model 14 that outputs recommended control content for any of fuel consumption, ship rolling, and the difference between supply and demand of electricity.

[0038] In addition, model 14 outputs recommended control parameters indicating recommended control content for increasing the reward value determined by the reward function above the reference reward value in response to input situation data, so that model 14 that outputs recommended control content for increasing the reward value can be obtained.

[0039] The reward function also includes at least one parameter related to the ship's fuel consumption, the magnitude of ship pitching, and the difference between the ship's power generation and power consumption. Therefore, it is possible to obtain a model 14 that outputs recommended control content to adjust any one of the fuel consumption, the ship's pitching, and the power supply and demand difference to an appropriate value. For example, when a reward function in which the reward value increases as the fuel consumption decreases is used, it is possible to obtain a model 14 that outputs recommended control content to reduce fuel consumption. When a reward function in which the reward value increases as the pitching decreases is used, it is possible to obtain a model 14 that outputs recommended control content to reduce the pitching magnitude. When a reward function in which the reward value decreases as the difference between the power generation and power consumption increases, it is possible to obtain a model 14 that outputs recommended control content to prevent excessive power generation while preventing power outages due to power shortages by reducing the difference between the power generation and power consumption.

[0040] Furthermore, since the situation data is supplied to the trained model 14 and the ship is controlled according to the recommended control parameters that are output, the ship can be automatically controlled according to the recommended control parameters according to the remaining route and remaining time.

[0041] <2. Learning Data> FIG. 2 shows an example of learning data. The status data of the learning data may include information about the route (also referred to as route information), remaining time, and information about the state of the ship (also referred to as state information). The route information may include route identification information (also referred to as route ID), the ship's current position, the distance to the destination, and the route environment. The route ID may indicate any one of multiple pre-set routes. Note that the route information may include information indicating the departure point, one or more waypoints, and the destination instead of the route ID. The ship's current position may be indicated by longitude and latitude, or by the progress on the route (for example, the ratio of the route length that has been navigated to the total route length). The distance to the destination may be the distance along the route from the ship's current position to the destination. The route environment may be information regarding at least one of weather and sea conditions along the route. The ship status information may include the ship's speed, inclination, magnitude of pitching, cargo volume, ballast weight, draft level, engine output, fuel consumption, power generation, electricity consumption, and internal pressure of liquefied gas tanks installed on the ship, etc. Furthermore, the control parameters of the learning data may include the ballast weight, draft level, engine output, ship speed, and power generation, etc.

[0042] <3.Operation> <3.1. Learning Stage> 3 shows the operation in the learning stage of the device 1 according to this embodiment. The device 1 performs the processes of steps S11 to S25 to learn the model 14 while sailing the ship.

[0043] First, in step S11, the data acquisition unit 10 acquires situation data. As a result, situation data in an initial state is acquired. The data acquisition unit 10 may store the situation data in the storage unit 12.

[0044] In step S13, the control unit 16 controls each part of the ship. The control unit 16 may determine control parameters to perform control. The determined control parameters may be those that increase or decrease the reward value, or may be determined independently of the reward value. The control unit 16 may determine the control parameters in response to an operation by the operator. Alternatively, the control unit 16 may determine the recommended control parameters output from the model 14 as the control parameters.

[0045] For example, when the processing of step S13 is performed for the first time, the control unit 16 may determine, as the control parameters for the next control cycle, the recommended control parameters output from the model 14 in response to inputting the situation data acquired in step S11 into the model 14. When the processing of steps S13 to S19 is repeated and the processing of step S13 is performed multiple times, the control unit 16 may determine, as the control parameters for the next control cycle, the recommended control parameters output from the model 14 in response to inputting the situation data acquired in the last processing of step S17 into the model 14. When the processing of step S13 is performed multiple times, different control parameters may be determined between at least some of the multiple processing of step S13. The control unit 16 may output the determined control parameters to control each part of the ship.

[0046] In step S15, the data acquiring unit 10 acquires the control parameters output from the control unit 16. The data acquiring unit 10 may store the control parameters in the storage unit 12 in association with the situation data acquired in step S11. When the processes of steps S13 to S19 are repeated and the process of step S15 is performed multiple times, the data acquiring unit 10 may store the control parameters in the storage unit 12 in association with the situation data acquired in the most recent process of step S17. As a result, learning data including the situation data and the control parameters is stored in the storage unit 12.

[0047] In step S17, the data acquisition unit 10 acquires the status data again. This acquires the status data when each part of the ship is controlled according to the control content indicated by the control parameters. The data acquisition unit 10 may store the status data in the memory unit 12.

[0048] In step S19, the reward value acquisition unit 11 acquires a reward value determined by the reward function. As an example, the reward value acquisition unit 11 may acquire the reward value by inputting the situation data acquired in step S17 into the reward function. The reward value acquisition unit 11 may store the acquired reward value in the storage unit 12. The reward value acquisition unit 11 may store the reward value in association with the learning data stored in the last processing of step S15.

[0049] In step S21, the control unit 16 determines whether the processing of steps S13 to S19 has been performed a reference number of steps. If it is determined that the processing has not been performed a reference number of steps (step S21; No), the process proceeds to step S13. As a result, learning data in which at least one of the situation data and the control parameters is different is sampled a reference number of steps and stored together with the reward value. Note that when the processing of steps S13 to S19 is repeatedly performed, the cycle of step S13 (i.e., the control cycle) may be determined according to the time constant of each part of the ship, and may be 5 minutes, for example. If it is determined in step S21 that the processing has been performed a reference number of steps (step S21; Yes), the process proceeds to step S23.

[0050] In step S23, the learning processing unit 13 performs a learning process on the model 14 using the situation data acquired in steps S11 and S17 and learning data including the control parameters acquired in step S15, thereby updating the model 14.

[0051] The learning processing unit 13 may perform a learning process for the model 14 using each pair of learning data and reward value associated and stored in the storage unit 12. The learning processing unit 13 may perform a learning process for the model 14 such that a control parameter with a higher reward value is preferentially output as a recommended control parameter.

[0052] In step S25, the control unit 16 determines whether the processing of steps S13 to S23 has been performed a standard number of times (iterations). If it is determined that the processing has not been performed a standard number of times (step S25; No), the process proceeds to step S11. If it is determined that the processing has been performed a standard number of times (step S25; Yes), the process ends.

[0053] <3.2. Operational Phase> 4 shows the operation of the device 1 according to this embodiment in the operation stage. The device 1 operates the ship using the model 14 by performing the processes of steps S31 to S37.

[0054] In step S31, the data acquisition unit 10 acquires situation data. As a result, situation data in an initial state is acquired. The situation data may be supplied from the supply unit 15 to the model 14.

[0055] In step S33, the control unit 16 acquires the recommended control parameters output by the model 14 in response to the situation data being supplied to the model 14. Then, in step S35, the control unit 16 outputs the recommended control parameters to control each part of the ship, and in step S37 the data acquisition unit 10 acquires the situation data. As a result, situation data is acquired in a state in which each part of the ship is controlled with the recommended control parameters. After the processing of step S37 is completed, the device 1 may proceed to step S33.

[0056] <4. Modifications> In the above embodiment, the device 1 has been described as including the reward value acquisition unit 11, the memory unit 12, the model 14, the supply unit 15, and the control unit 16, but any of these may be omitted. If the device 1 does not include the reward value acquisition unit 11, the learning processing unit 13 may perform learning processing of the model 14 using a learning algorithm other than reinforcement learning. If the device 1 does not include the memory unit 12, it may be connected to an external storage device. If the device 1 does not include the model 14, the model 14 may be stored in a server external to the device 1. If the device 1 does not include the supply unit 15 or the control unit 16, the device 1 does not need to control the ship using the model 14.

[0057] Various embodiments of the present invention may also be described with reference to flowcharts and block diagrams, where the blocks may represent (1) stages of a process in which operations are performed or (2) sections of an apparatus responsible for performing the operations. Particular stages and sections may be implemented by dedicated circuitry, programmable circuitry provided with computer-readable instructions stored on a computer-readable medium, and / or a processor provided with computer-readable instructions stored on a computer-readable medium. Dedicated circuitry may include digital and / or analog hardware circuitry, and may include integrated circuits (ICs) and / or discrete circuits. Programmable circuitry may include reconfigurable hardware circuitry, including logical AND, OR, XOR, NAND, NOR, and other logic operations, flip-flops, registers, memory elements such as field programmable gate arrays (FPGAs), programmable logic arrays (PLAs), and the like.

[0058] A computer-readable medium may include any tangible device capable of storing instructions that are executed by an appropriate device, such that the computer-readable medium having instructions stored thereon comprises an article of manufacture containing instructions that can be executed to create means for performing the operations specified in the flowcharts or block diagrams. Examples of computer-readable media may include electronic, magnetic, optical, electromagnetic, and semiconductor storage media. More specific examples of computer-readable media may include floppy disks, diskettes, hard disks, random access memory (RAM), read-only memory (ROM), erasable programmable read-only memory (EPROM or flash memory), electrically erasable programmable read-only memory (EEPROM), static random access memory (SRAM), compact disc read-only memory (CD-ROM), digital versatile disc (DVD), Blu-ray (RTM) disc, memory stick, integrated circuit card, and the like.

[0059] The computer readable instructions may include either assembler instructions, Instruction Set Architecture (ISA) instructions, machine instructions, machine-dependent instructions, microcode, firmware instructions, state-setting data, or source or object code written in any combination of one or more programming languages, including object-oriented programming languages ​​such as Smalltalk®, JAVA®, C++, etc., and conventional procedural programming languages ​​such as the “C” programming language or similar programming languages.

[0060] The computer-readable instructions may be provided to a processor or programmable circuitry of a general-purpose computer, special-purpose computer, or other programmable data processing apparatus, either locally or over a wide-area network (WAN) such as a local area network (LAN), the Internet, etc., which executes the computer-readable instructions to create means for performing the operations specified in the flowcharts or block diagrams. Examples of processors include computer processors, processing units, microprocessors, digital signal processors, controllers, microcontrollers, etc.

[0061] 5 illustrates an example of a computer 2200 in which aspects of the present invention may be embodied, in whole or in part. Programs installed on the computer 2200 may cause the computer 2200 to function as or perform operations associated with an apparatus or one or more sections of the apparatus according to embodiments of the present invention, and / or to perform a process or steps of a process according to embodiments of the present invention. Such programs may be executed by the CPU 2212 to cause the computer 2200 to perform specific operations associated with some or all of the blocks of the flowcharts and block diagrams described herein.

[0062] A computer 2200 according to this embodiment includes a CPU 2212, a RAM 2214, a graphics controller 2216, and a display device 2218, which are interconnected by a host controller 2210. The computer 2200 also includes input / output units such as a communication interface 2222, a hard disk drive 2224, a DVD-ROM drive 2226, and an IC card drive, which are connected to the host controller 2210 via an input / output controller 2220. The computer also includes legacy input / output units such as a ROM 2230 and a keyboard 2242, which are connected to the input / output controller 2220 via an input / output chip 2240.

[0063] The CPU 2212 operates according to programs stored in the ROM 2230 and RAM 2214, thereby controlling each unit. The graphics controller 2216 acquires image data generated by the CPU 2212 into a frame buffer or the like provided in the RAM 2214 or into the graphics controller 2216 itself, and causes the image data to be displayed on the display device 2218.

[0064] The communication interface 2222 communicates with other electronic devices via a network. The hard disk drive 2224 stores programs and data used by the CPU 2212 in the computer 2200. The DVD-ROM drive 2226 reads programs or data from the DVD-ROM 2201 and provides the programs or data to the hard disk drive 2224 via the RAM 2214. The IC card drive reads programs and data from an IC card and / or writes programs and data to an IC card.

[0065] The ROM 2230 stores therein a boot program or the like that is executed by the computer 2200 upon activation, and / or programs that depend on the hardware of the computer 2200. The input / output chip 2240 may also connect various input / output units to the input / output controller 2220 via a parallel port, a serial port, a keyboard port, a mouse port, etc.

[0066] The programs are provided by a computer-readable medium such as a DVD-ROM 2201 or an IC card. The programs are read from the computer-readable medium, installed in the hard disk drive 2224, RAM 2214, or ROM 2230, which are also examples of computer-readable media, and executed by the CPU 2212. Information processing described in these programs is read by the computer 2200, and brings about cooperation between the programs and the various types of hardware resources described above. An apparatus or method may be configured by realizing information manipulation or processing in accordance with the use of the computer 2200.

[0067] For example, when communication is performed between the computer 2200 and an external device, the CPU 2212 may execute a communication program loaded into the RAM 2214 and instruct the communication interface 2222 to perform communication processing based on the processing described in the communication program. Under the control of the CPU 2212, the communication interface 2222 reads transmission data stored in a transmission buffer processing area provided in the RAM 2214, the hard disk drive 2224, the DVD-ROM 2201, or a recording medium such as an IC card, and transmits the read transmission data to the network, or writes reception data received from the network to a reception buffer processing area or the like provided on the recording medium.

[0068] The CPU 2212 may also cause all or a necessary portion of a file or database stored on an external recording medium such as the hard disk drive 2224, the DVD-ROM drive 2226 (DVD-ROM 2201), an IC card, etc. to be read into the RAM 2214, and perform various types of processing on the data on the RAM 2214. The CPU 2212 then writes back the processed data to the external recording medium.

[0069] Various types of information, such as various types of programs, data, tables, and databases, may be stored on the recording medium and may undergo information processing. The CPU 2212 may perform various types of processing on data read from the RAM 2214, including various types of operations, information processing, conditional judgment, conditional branching, unconditional branching, information search / replacement, etc., as described throughout this disclosure and specified by the instruction sequences of the programs, and write the results back to the RAM 2214. The CPU 2212 may also search for information in a file, database, etc. on the recording medium. For example, if multiple entries each having an attribute value of a first attribute associated with an attribute value of a second attribute are stored on the recording medium, the CPU 2212 may search for an entry that matches a condition specified by the attribute value of the first attribute from among the multiple entries, read the attribute value of the second attribute stored in the entry, and thereby obtain the attribute value of the second attribute associated with the first attribute that satisfies a predetermined condition.

[0070] The above-described programs or software modules may be stored in a computer-readable medium on or near the computer 2200. A recording medium such as a hard disk or RAM provided in a server system connected to a dedicated communication network or the Internet can also be used as a computer-readable medium, thereby providing the programs to the computer 2200 via the network.

[0071] Although the present invention has been described above using embodiments, the technical scope of the present invention is not limited to the scope described in the above embodiments. It will be apparent to those skilled in the art that various modifications and improvements can be made to the above embodiments. It is clear from the claims that such modifications and improvements can also be included within the technical scope of the present invention.

[0072] It should be noted that the execution order of each process, such as operations, procedures, steps, and stages, in the devices, systems, programs, and methods shown in the claims, specifications, and drawings is not specifically stated as "before," "prior to," etc., and that the processes can be performed in any order unless the output of a previous process is used in a subsequent process. Even if the operational flow in the claims, specifications, and drawings is described using "first," "next," etc. for convenience, this does not mean that the processes must be performed in this order. [Explanation of symbols]

[0073] 1 device 10 Data Acquisition Section 11 Reward value acquisition unit 12 Storage section 13 Learning processing unit 14 models 15 Supply section 16 Control Unit 2200 Computer 2201 DVD-ROM 2210 host controller 2212 CPU 2214 RAM 2216 Graphics Controller 2218 Display Device 2220 Input / Output Controller 2222 communication interface 2224 hard disk drive 2226 DVD-ROM drive 2230 ROM 2240 I / O chip 2242 keyboard

Claims

1. an acquisition unit that acquires information about the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the control content of the ship; a learning processing unit that performs model learning processing using learning data including the situation data and control parameters acquired by the acquisition unit, and outputs recommended control parameters that indicate recommended ship control content in response to input of the situation data; and An apparatus comprising:

2. The apparatus of claim 1 , wherein the information about the route includes a distance from the vessel's current position to the destination.

3. The device according to claim 1 , wherein the information about the route includes information about at least one of weather and sea conditions along the route.

4. The apparatus of claim 1 , wherein the status data includes information regarding a current vessel condition.

5. 5. The device of claim 4, wherein the information regarding the current ship status indicates at least one of the ship's speed, inclination, magnitude of rolling, cargo volume, ballast weight, draft level, engine output, fuel consumption, power generation, electricity consumption, or internal pressure of a liquefied gas tank installed on the ship.

6. 2. The apparatus of claim 1, wherein the control content relates to at least one of ballast weight, draft level, engine power, ship speed, or power generation.

7. the learning processing unit performs a learning process for the model using the learning data and a reward value determined by a preset reward function; The device according to claim 1 , wherein the model outputs, in response to input of situation data, recommended control parameters indicating control content recommended for increasing the reward value determined by the reward function above a reference reward value.

8. The apparatus of claim 7 , wherein the reward function has at least one parameter related to fuel consumption of the vessel, a magnitude of pitching of the vessel, or a difference between power generation and power consumption of the vessel.

9. a supply unit that supplies the situation data acquired by the acquisition unit to the model that has undergone learning processing by the learning processing unit; a control unit that controls the ship in accordance with recommended control parameters output from the model in response to the supply of situation data to the model by the supply unit; 9. The apparatus of claim 1, comprising:

10. an acquisition stage for acquiring information about the ship's route from its current position to its destination, status data indicating the remaining time until the deadline for reaching the destination, and control parameters indicating the ship's control content; a learning processing step of performing a model learning process using learning data including the situation data and control parameters acquired in the acquisition step, and outputting recommended control parameters indicating recommended ship control content in response to input of the situation data; A method for providing the above.

11. Computer, an acquisition unit that acquires information about the route from the ship's current position to the destination, status data indicating the remaining time until the deadline for arrival at the destination, and control parameters indicating the control content of the ship; a learning processing unit that performs a model learning process using learning data including the situation data and control parameters acquired by the acquisition unit, and outputs recommended control parameters that indicate recommended ship control content in response to input of situation data; A program that functions as a

Images