Ship scheduling strategy determination method and device, storage medium and electronic device

Abstract

The embodiment of the invention provides a ship scheduling strategy determination method and device, a storage medium and an electronic device, and the method comprises the steps: determining the driving state information of a first ship in a target region, the resource distribution information of a target port in the target region, and the environment information of the target region; constructing a target mathematical model based on the driving state information, the resource allocation information and the environment information; determining a scheduling strategy matrix based on the target mathematical model, the scheduling strategy matrix having a low-rank structure; and controlling the second ship to travel according to the scheduling strategy matrix. Through the ship scheduling method and device, the problem of low ship scheduling efficiency is solved, and the effect of improving the ship scheduling efficiency is achieved.

Description

TECHNICAL FIELD

[0001] Embodiments of the present application relate to the field of computer, and in particular, to a method and device for determining a ship scheduling strategy, a storage medium and an electronic device. BACKGROUND

[0002] In the related art, the traditional ship scheduling method has low efficiency in dealing with nonlinear and complex dynamic constraint optimization problems, long solving time and insufficient robustness of results.

[0003] Therefore, there is a technical problem of low ship scheduling efficiency in the related art.

[0004] In view of the above problems in the related art, no effective solution has been proposed so far. SUMMARY

[0005] Embodiments of the present application provide a method and device for determining a ship scheduling strategy, a storage medium and an electronic device to at least solve the problem of low ship scheduling efficiency in the related art.

[0006] According to an embodiment of the present application, a method for determining a ship scheduling strategy is provided, comprising: determining driving state information of a first ship included in a target area, resource allocation information of a target port included in the target area, and environment information of the target area; constructing a target mathematical model based on the driving state information, the resource allocation information, and the environment information; determining a scheduling strategy matrix based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure; and controlling a second ship to travel according to the scheduling strategy matrix.

[0007] In one exemplary embodiment, constructing a target mathematical model based on the driving state information, the resource allocation information, and the environment information comprises: determining a departure time and a sailing speed of the second ship based on the driving state information; constructing a target cost function based on the departure time and the sailing speed; constructing a target constraint condition based on the driving state information, the resource allocation information, and the environment information; and constructing the target mathematical model based on the target cost function and the target constraint condition.

[0008] In one exemplary embodiment, constructing a target cost function based on the departure time and the sailing speed comprises: constructing a cost function based on the departure time of each of the second ships to obtain a plurality of first cost functions; constructing a cost function based on the sailing speed of each of the second ships to obtain a plurality of second cost functions; and determining a sum value of the plurality of first cost functions and the plurality of second cost functions as the target cost function.

[0009] In an example embodiment, constructing the target constraint condition based on the sailing state information, the resource allocation information and the environment information comprises: determining a sailing track constraint condition of the second ship in the target area, a berth constraint condition of the second ship in the target port and a waterway capacity constraint condition of the second ship in the target area based on the sailing state information, the resource allocation information and the environment information; and determining the sailing track constraint condition, the berth constraint condition and the waterway capacity constraint condition as the target constraint condition.

[0010] In an example embodiment, constructing the target mathematical model based on the target cost function and the target constraint condition comprises: the target mathematical model is represented as follows: wherein S n represents an n x n symmetric matrix space, C represents the target cost function, X represents the scheduling strategy matrix, A j represents the jth target constraint condition, b j represents a preset constant.

[0011] In an example embodiment, determining the scheduling strategy matrix based on the target mathematical model comprises: determining an initial solution satisfying the target constraint condition included in the target mathematical model, wherein the initial solution is a solution of the target mathematical model; repeatedly performing a target operation until an iterative solution obtained satisfies a convergence condition, wherein the iterative solution is a solution of the target mathematical model, and the target operation comprises: determining a target function for solving the target mathematical model; determining a target update amount of a target variable included in the target function; updating the target variable based on the target update amount to obtain an update function; determining the iterative solution satisfying the target constraint condition based on the update function; in a case where the iterative solution satisfies the convergence condition, determining the iterative solution as the scheduling strategy matrix; and in a case where the iterative solution does not satisfy the convergence condition, updating the initial solution as the iterative solution and continuing to perform the target operation.

[0012] In an example embodiment, after determining the iterative solution satisfying the target constraint condition based on the update function, the method further comprises: determining a target relationship between the iterative solution and a preset target cost value by using a preconditioner; and in a case where the target relationship indicates that the iterative solution is equal to the target cost value, determining that the iterative solution satisfies the convergence condition.

[0013] According to another embodiment of the present application, a device for determining a ship scheduling strategy is provided, comprising a first memory, a first processor, and a first computer program stored in the first memory and executable on the first processor, wherein the first processor implements the following operations when executing the first computer program: determining travel state information of a first ship included in a target region, resource allocation information of a target port included in the target region, and environment information of the target region; constructing a target mathematical model based on the travel state information, the resource allocation information, and the environment information; determining a scheduling strategy matrix based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure; and controlling a second ship to travel according to the scheduling strategy matrix.

[0014] According to still another embodiment of the present application, a computer readable storage medium is also provided, wherein the computer readable storage medium stores a computer program, and the computer program is configured to execute the steps of any of the method embodiments when executed.

[0015] According to still another embodiment of the present application, an electronic device is also provided, comprising a memory and a processor, wherein the memory stores a computer program, and the processor is configured to execute the computer program to execute the steps of any of the method embodiments.

[0016] According to still another embodiment of the present application, a computer program product is also provided, comprising a computer program, wherein the computer program is executed by a processor to implement the steps of the method in the embodiments of the present application.

[0017] According to the present application, the travel state information of a first ship included in a target region, the resource allocation information of a target port included in the target region, and the environment information of the target region can be determined first, and a target mathematical model for determining a scheduling strategy matrix having a low-rank structure can be constructed based on the travel state information, the resource allocation information, and the environment information. After the scheduling strategy matrix is determined, a second ship can be controlled to travel according to the scheduling instructions indicated by the scheduling strategy matrix. Since the mapping relationship between the target function and the constraint condition can be determined based on the travel state information of the ship, the resource allocation information of the port, and the environment information of the target region collected in real time, and the low-rank assumption (the scheduling strategy matrix having a low-rank structure) is introduced to simplify the solving process of the target mathematical model, the solving efficiency can be greatly improved, and thus the technical problem of low ship scheduling efficiency in the related art can be solved, and the effect of improving the ship scheduling efficiency can be achieved. BRIEF DESCRIPTION OF DRAWINGS

[0018] Figure 1 is a hardware structure block diagram of a mobile terminal according to a ship scheduling strategy determination method of an embodiment of the present application;

[0019] Figure 2 This is a flowchart of a method for determining a ship scheduling strategy according to an embodiment of the present invention;

[0020] Figure 3 This is a data preprocessing flowchart according to an embodiment of the present invention;

[0021] Figure 4 This is a diagram illustrating the solution process of the interior point solver according to an embodiment of the present invention;

[0022] Figure 5 This is a flowchart of a method for determining a ship scheduling strategy according to a specific embodiment of the present invention;

[0023] Figure 6 This is a schematic diagram of the construction of a semidefinite programming model according to an embodiment of the present invention;

[0024] Figure 7 This is a schematic diagram of scheduling instruction generation according to an embodiment of the present invention;

[0025] Figure 8 This is a structural block diagram of a device for determining ship scheduling strategies according to an embodiment of the present invention. Detailed Implementation

[0026] The embodiments of the present invention will be described in detail below with reference to the accompanying drawings and examples.

[0027] It should be noted that the terms "first," "second," etc., in the specification, claims, and drawings of this invention are used to distinguish similar objects and are not necessarily used to describe a specific order or sequence.

[0028] The methods and embodiments provided in this application can be executed on a mobile terminal, computer terminal, or similar computing device. Taking running on a mobile terminal as an example, Figure 1 This is a hardware structure block diagram of a mobile terminal for a method of determining a ship scheduling strategy according to an embodiment of the present invention. Figure 1 As shown, a mobile terminal may include one or more ( Figure 1 Only one is shown in the diagram. A processor 102 (which may include, but is not limited to, a microprocessor MCU or a programmable logic device FPGA, etc.) and a memory 104 for storing data are also shown. The mobile terminal may further include a transmission device 106 for communication functions and an input / output device 108. Those skilled in the art will understand that... Figure 1 The structure shown is for illustrative purposes only and does not limit the structure of the mobile terminal described above. For example, the mobile terminal may also include components that are more... Figure 1 The more or fewer components shown, or having the same Figure 1 The different configurations shown.

[0029] The memory 104 can be used to store computer programs, such as software programs of application software and modules, such as a computer program corresponding to the method for determining a ship scheduling strategy in the embodiments of the present application. The processor 102 can execute various functional applications and data processing, i.e., implement the above method, by running the computer program stored in the memory 104. The memory 104 can include a high-speed random access memory, and can further include a non-volatile memory, such as one or more magnetic storage devices, flash memories, or other non-volatile solid-state memories. In some examples, the memory 104 can further include memories remotely arranged with respect to the processor 102, which can be connected to the mobile terminal through a network. Examples of the above network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0030] The transmission device 106 is configured to receive or send data via a network. Specific examples of the above network can include a wireless network provided by a communication provider of the mobile terminal. In one example, the transmission device 106 includes a network adapter (NIC), which can be connected to other network devices through a base station so as to communicate with the Internet. In one example, the transmission device 106 can be a radio frequency (RF) module, which is configured to communicate with the Internet in a wireless manner.

[0031] In the embodiments, a method for determining a ship scheduling strategy is provided, Figure 2 is a flowchart of the method for determining a ship scheduling strategy according to the embodiments of the present application, as shown in Figure 2 The flowchart includes the following steps:

[0032] In step S202, travel state information of a first ship included in a target region, resource allocation information of a target port included in the target region, and environment information of the target region are determined.

[0033] In step S204, a target mathematical model is constructed based on the travel state information, the resource allocation information, and the environment information.

[0034] In step S206, a scheduling strategy matrix is determined based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure.

[0035] In step S208, a second ship is controlled to travel according to the scheduling strategy matrix.

[0036] In the above embodiment, the real-time position, speed, heading, etc. (i.e., the running state information) of a plurality of ships (i.e., the first ship) in a certain port (i.e., the target port to be reached by the second ship to which the scheduling strategy is to be formulated) and its nearby channel (i.e., the target area) can be collected through an AIS (Automatic Identification System) system, wherein the AIS can be understood as a ship real-time data acquisition system that can provide dynamic data such as the position, speed, heading, etc. of a ship, as well as static information such as the type and size of the ship. At the same time, relevant data such as the use of berths included in the target port, channel capacity restrictions (i.e., the resource allocation information), and weather conditions (i.e., the environmental information) can also be obtained. The collection time of the data can be set to 5 minutes to ensure the real-time and accuracy of the data. In addition, the collected data can be cleaned and preprocessed, Figure 3 is a data preprocessing flowchart according to an embodiment of the present application, as Figure 3 shown, the collected data can be cleaned and the missing values can be processed to remove noise and outliers caused by equipment failure or signal interference. For example, for speed data, a reasonable speed range can be set, and data outside this range can be considered as outliers and removed; interpolation processing can also be performed on missing data to ensure the integrity and continuity of the data.

[0037] In the above embodiment, based on the preprocessed data (i.e., the running state information, resource allocation information, and environmental information), a SDP (Semidefinite Programming) model (i.e., the target mathematical model) can be constructed, i.e., the ship scheduling problem can be converted into a semidefinite programming problem, and by solving the semidefinite programming problem, the optimal solution (i.e., the scheduling strategy matrix) can be determined, and the scheduling strategy matrix can be decoded into the scheduling strategy of the second ship, which can include the departure time, sailing speed, etc. The scheduling strategy can then be converted into specific scheduling instructions and sent to the second ship through a communication system to guide it to sail and dock according to the plan. The semidefinite programming can be understood as an optimization algorithm that can be used to solve problems with matrix variables and linear matrix inequality constraints, and performs well in handling complex constraints and optimization objectives.

[0038] In the above embodiment, after the second ship sails and docks according to the scheduling plan, actual sailing data (such as actual arrival time, fuel consumption, etc.) can be collected and compared with the scheduling plan for analysis. Based on the analysis results, the scheduling strategy can be evaluated and optimized to improve the accuracy and efficiency of future scheduling. At the same time, the new sailing data can be fed back to the data preprocessing stage to update and improve the semidefinite programming model.

[0039] By the present application, the running state information of the first ship included in the target area, the resource allocation information of the target port included in the target area, and the environment information of the target area can be determined first, and a target mathematical model for determining a scheduling strategy matrix with a low-rank structure can be constructed through the running state information, the resource allocation information, and the environment information. After the scheduling strategy matrix is determined, the second ship can be controlled to run according to the scheduling instructions indicated by the scheduling strategy matrix. Since the mapping relationship between the objective function and the constraint condition can be determined through the real-time collected running state information of the ship, the resource allocation information of the port, and the environment information of the target area, and the low-rank assumption (the scheduling strategy matrix with a low-rank structure) is introduced to simplify the solving process of the target mathematical model, the solving efficiency can be greatly improved, and thus the technical problem of low ship scheduling efficiency in the related art can be solved, and the effect of improving the ship scheduling efficiency can be achieved.

[0040] Optionally, the execution subject of the above steps can be a processor, a terminal, a server, and other devices with similar processing capabilities, but is not limited thereto.

[0041] In an example embodiment, constructing a target mathematical model based on the running state information, the resource allocation information, and the environment information includes: determining a departure time and a sailing speed of the second ship based on the running state information; constructing a target cost function based on the departure time and the sailing speed; constructing a target constraint condition based on the running state information, the resource allocation information, and the environment information; and constructing the target mathematical model based on the target cost function and the target constraint condition.

[0042] In the above embodiment, the target mathematical model can include a target cost function and a target constraint condition, wherein the target cost function can be determined through the running state information of the first ship included in the target area, i.e., the real-time position, speed, heading, etc. of the first ship can have different effects on the cost of the second ship under different departure times and sailing speeds. For example, in the case of narrow or busy waterways, the speed of the first ship determines the passage rate of the waterway. If the speed of the first ship is too slow, it will lead to a decrease in waterway utilization and an increase in the number of ships waiting in line, i.e., it can affect the delayed departure of the second ship, increasing the waiting cost and potential demurrage.

[0043] In the above embodiment, the target constraint condition included in the target mathematical model can be determined by the running state information of the first ship included in the target area, the resource allocation information, and the environmental information, that is, the scheduling strategy of the second ship needs to consider the real-time position, speed, heading, etc. of the first ship, the number of berths of the target port, the channel capacity, or the constraint of the weather, for example: when formulating the departure time of the second ship, the number of idle berths of the target port needs to be considered when the second ship arrives at the target port. If the number of berths is insufficient, the departure time or the running speed of the second ship needs to be changed to avoid the time period when the number of berths is insufficient.

[0044] In an example embodiment, the target cost function is constructed based on the to-be-departure time and the to-be-navigation speed, including: constructing a cost function based on the to-be-departure time of each of the second ships to obtain a plurality of first cost functions; constructing a cost function based on the to-be-navigation speed of each of the second ships to obtain a plurality of second cost functions; and determining the sum of the plurality of first cost functions and the plurality of second cost functions as the target cost function.

[0045] In the above embodiment, the target cost function can be defined as minimizing the scheduling cost of the ship, and can be constructed by the following formula: Wherein, N can be understood as the number of ships, T i And V i Can be understood as the departure time and navigation speed of the i-th ship, respectively, f i (T i ) and g i (V i ) can be understood as the cost function related to time and speed (i.e. the above first cost function and the second cost function), respectively, wherein the cost related to time and speed can include fuel consumption, time cost, operation cost, or environmental cost, service cost, etc.

[0046] In an example embodiment, the target constraint condition is constructed based on the running state information, the resource allocation information, and the environmental information, including: determining the navigation trajectory constraint condition of the second ship in the target area, the berth constraint condition of the second ship in the target port, and the channel capacity constraint condition of the second ship in the target area based on the running state information, the resource allocation information, and the environmental information; and determining the navigation trajectory constraint condition, the berth constraint condition, and the channel capacity constraint condition as the target constraint condition.

[0047] In the above embodiment, the target constraint condition can be defined as the navigation trajectory constraint, the port berth constraint, the channel capacity constraint, etc. of the ship, and can be determined by the following formula: wherein M can be understood as the number of constraints, P j represents parameters related to port berth constraints (i.e. the above-mentioned berth constraints), channel capacity (i.e. the above-mentioned channel capacity constraints), track constraints (i.e. the above-mentioned track constraints), and environmental constraints, h i (T i , V i , P j ) represents the track function of the i-th ship under the j-th constraint. Taking the track constraints as an example, the track function of each first ship included in the target area can be determined first, and after determining the track function of each ship, the track constraints can be constructed to ensure that the second ship does not violate the channel and speed rules, and also needs to avoid collision with other first ships, i.e. a linear matrix inequality can be set to ensure that the track of all second ships meets the safety conditions within a certain time period. The determination process of the channel capacity constraints, the berth constraints and the environmental constraints is the same as the above-mentioned track constraints, and will not be repeated here.

[0048] In an example embodiment, the target mathematical model is constructed based on the target cost function and the target constraints, including: the target mathematical model is represented as follows: wherein S n represents an n x n symmetric matrix space, C represents the target cost function, X represents the scheduling strategy matrix, A j represents the j-th target constraint, b j represents a preset constant.

[0049] In the above embodiment, the target cost function and the target constraints can be converted into a standard SDP form by introducing a symmetric matrix variable X, and the target mathematical model can be constructed: wherein S n can be understood as an n x n symmetric matrix space, C (i.e. the above-mentioned target cost function) and A j (i.e. the above-mentioned target constraints) are known symmetric matrices, b j can be understood as the expected cost value, i.e. the scheduling strategy of the ship (such as the departure time, the sailing speed, etc.) can be encoded as the elements of the symmetric matrix X, the matrix C and A j can be constructed through AIS data and related constraints, and the scheduling strategy X can be solved by solving the minimum value of the target mathematical model.

[0050] In the above embodiments, since the ship scheduling problem usually has large-scale and complex characteristics, direct solution can be very difficult. Therefore, a low-rank assumption can be introduced, that is, assuming that the solution matrix X (i.e., the above scheduling strategy matrix) has a low-rank structure, it can be considered that only a few major ships or factors have a significant impact on the entire system during the solution process, which can help to simplify the problem and improve the solution efficiency.

[0051] In an example embodiment, determining the scheduling strategy matrix based on the target mathematical model comprises: determining an initial solution satisfying a target constraint condition included in the target mathematical model, wherein the initial solution is a solution of the target mathematical model; repeatedly performing a target operation until an iteration solution obtained satisfies a convergence condition, wherein the iteration solution is a solution of the target mathematical model, and the target operation comprises: determining a target function for solving the target mathematical model; determining a target update amount of a target variable included in the target function; updating the target variable based on the target update amount to obtain an update function; determining the iteration solution satisfying the target constraint condition based on the update function; in the case that the iteration solution satisfies the convergence condition, determining the iteration solution as the scheduling strategy matrix; in the case that the iteration solution does not satisfy the convergence condition, updating the initial solution as the iteration solution and continuing to perform the target operation.

[0052] In the above embodiments, the semi-definite programming problem can be solved by using an interior point solver, which can be understood as an algorithm for solving optimization problems by finding a path inside the feasible region to approach the optimal solution. Figure 4 is an interior point solver solving process diagram according to an embodiment of the present application, as shown in Figure 4 , an initial solution satisfying the target constraint condition can be generated first, and then the following update formula (i.e., the above target function) can be used in the interior point solver to continuously adjust the target variable to continuously iterate the initial solution, generate an estimate of the updated solution (i.e., the above iteration solution), until the convergence condition is satisfied: Where ΔX, Δy and ΔS constitute the target update amount of the target variable, r prim and R dual can be understood as the residual vectors of the original problem and the dual problem, respectively; H P is a linear transformation that ensures the symmetry of the result matrix; σ and μ are parameters in the interior point method, which can be used to control the convergence of the iteration process. Wherein, the specific form of the A matrix can be: A j represents the matrix related to the jth constraint condition; the residual vectors r prim and R dual can be represented as yj represents a dual variable related to the jth constraint condition.

[0053] In the above embodiment, the Schur complement equation HΔy=r can also be solved, where H can be understood as a Schur complement matrix, Δy can be understood as an update amount of the decision variable, r can be understood as a residual vector, which can be obtained by decomposing the KKT (Karush-Kuhn-Tucker) condition of the original problem, and the solution of the optimization problem can be effectively found. Through the above formula, the updated function of the target variable can be constantly updated through the target update amount, and the iterative solution that satisfies the target constraint condition can be constantly determined through the updated function. When the iterative solution satisfies the convergence condition, the iterative solution can be determined as the scheduling strategy matrix; when the iterative solution does not satisfy the convergence condition, the initial solution can be updated as the iterative solution to constantly update the iteration until a certain iterative solution satisfies the convergence condition.

[0054] In one exemplary embodiment, after the iterative solution that satisfies the target constraint condition is determined based on the updated function, the method further comprises: determining a target relationship between the iterative solution and a target cost value preset by using a preconditioner; and determining that the iterative solution satisfies the convergence condition in a case where the target relationship indicates that the iterative solution is equal to the target cost value.

[0055] In the above embodiment, in order to improve the solving efficiency of the iteration, a preconditioner H_α vector and a H_β vector can also be introduced to improve the performance of the iterative solver, and the convergence can be accelerated by using an approximate inverse matrix, that is, the target relationship between the iterative solution and the target cost value preset by using the preconditioner can be determined. When the target relationship indicates that the iterative solution is not equal to the target cost value, the correct solution can be approximated by adjusting the residual vector; when the target relationship indicates that the iterative solution is equal to the target cost value, it can be explained that the iterative solution satisfies the convergence condition. That is, in the solving process, the result of the iterative update can not be calculated, and the scheduling strategy of the ship can be constantly adjusted until the scheduling strategy matrix that satisfies the constraint condition and has the minimum cost is found. Then, the scheduling strategy matrix obtained by solving can be converted into specific scheduling instructions, which are sent to the second ship through a communication system to guide the second ship to sail and dock according to the plan.

[0056] The method for determining the ship scheduling strategy will be described below in combination with a specific embodiment:

[0057] Figure 5 is a flowchart of the method for determining the ship scheduling strategy according to an embodiment of the present application, as shown in Figure 5 The flowchart includes the following steps:

[0058] Step S502, data preprocessing;

[0059] Step S504, model construction;

[0060] Step S506, model solving;

[0061] Step S508, scheduling strategy.

[0062] In the above embodiment, the construction of the semi-definite programming model (i.e., the above-mentioned objective mathematical model) can refer to Figure 6 , Figure 6 is a semi-definite programming model construction schematic diagram according to an embodiment of the present application, as shown in Figure 6 , the objective function (i.e., the above-mentioned objective cost function) can be constructed according to the pre-processed static and dynamic data collected by the AIS system, and the minimum scheduling cost (fuel consumption, time cost, etc.) is defined by the objective function; the scheduling-related constraint conditions (i.e., the above-mentioned objective constraint conditions) can also be determined according to the pre-processed static and dynamic data: flight path constraint conditions, berth constraint conditions, channel capacity constraint conditions, and environmental constraint conditions, etc.; then the decision variables (i.e., the above-mentioned scheduling strategy matrix) that are desired to be obtained can be determined, such as: departure time, sailing speed, etc.

[0063] In the above embodiment, after the objective function and the constraint conditions are constructed, the matrix variable and the linear matrix inequality can be used to convert the problem into the standard form of SDP, that is, the construction of the semi-definite programming model can be completed. The above-mentioned semi-definite programming model is solved by using an interior point solver, that is, an initial solution that satisfies the objective constraint conditions can be determined first, and the target change amount is adjusted continuously until the generated iterative solution satisfies the convergence condition, in addition, in order to speed up the convergence speed, a preconditioner can also be introduced to improve the solving efficiency.

[0064] In the above embodiment, the process of determining the scheduling instruction can refer to Figure 7 , Figure 7 is a scheduling instruction generation schematic diagram according to an embodiment of the present application, as shown in Figure 7 , the optimal scheduling strategy matrix can be extracted from the solving result, the optimal scheduling strategy matrix is converted into specific scheduling instructions that adapt to the ship execution system, and the scheduling instructions are sent to the second ship through the communication system, that is, the second ship can be instructed to travel or dock according to the scheduling instructions. Actual sailing data (such as actual arrival time, fuel consumption, etc.) can also be collected and compared and analyzed with the scheduling plan. According to the analysis result, the scheduling strategy can be evaluated and optimized to improve the accuracy and efficiency of future scheduling. At the same time, the new sailing data can also be fed back to the data preprocessing stage for updating and perfecting the semi-definite programming model.

[0065] In the above embodiment, the dynamic and static data of the ship are collected in real time by the AIS system, and through data cleaning and preprocessing, the correlation characteristics of the data can be fully mined, the ship scheduling problem is modeled as a semi-definite programming (SDP) problem with complex constraints, and the scheduling efficiency and accuracy are greatly improved. In view of the complexity of the ship scheduling problem, a low-rank assumption can be introduced to simplify the model solution, an interior point method is used to solve the high-efficiency optimization problem, and a preconditioner is designed to improve the iteration solving efficiency, which is more suitable for large-scale and multi-variable ship scheduling scenarios. In addition, during the scheduling execution process, the dynamic information updated in real time according to the AIS data can be used to generate an efficient dynamic adjustment strategy through the rapid reconstruction and solution of the model, thereby ensuring the rapid response of the scheduling system to unexpected events. Moreover, the fuel consumption and sailing time cost are comprehensively considered in the scheduling optimization, and an economic and environmentally friendly scheduling scheme is developed, which can promote the intelligentization and sustainable development of the shipping industry.

[0066] In the above embodiment, the semi-definite programming (SDP) algorithm is used for ship scheduling optimization, which can more effectively handle multi-constraint and multi-objective optimization problems. In particular, by introducing a low-rank assumption, the problem solving process is further simplified, and the solving efficiency is greatly improved, making it suitable for large-scale scheduling scenarios. By combining static information (such as ship type and size) and dynamic information (such as speed and heading), a multi-variable correlation model can be constructed to fully exploit data value and improve scheduling accuracy. The dynamic adjustment of the scheduling scheme is also supported, which can quickly respond to unexpected events (such as weather changes and channel congestion), significantly enhancing the robustness and flexibility of the system. In addition, economic and environmental factors such as fuel consumption and time cost are fully considered in the objective function, and by optimizing the scheduling path and time arrangement, the energy consumption and waiting time of the ship are significantly reduced, achieving a more green and low-carbon scheduling scheme.

[0067] Through the above description of the embodiments, those skilled in the art can clearly understand that the method according to the above embodiments can be implemented by means of software and the necessary general hardware platform, of course, it can also be implemented by hardware, but in many cases the former is a better implementation. Based on such understanding, the technical solutions of the present application can be embodied in the form of a software product, which is stored in a storage medium (such as ROM / RAM, magnetic disk, optical disk) and includes a plurality of instructions for causing a terminal device (which can be a mobile phone, computer, server, or network device, etc.) to execute the methods described in the various embodiments of the present application.

[0068] A device for determining a ship scheduling strategy is also provided in the embodiments, which is used to implement the above embodiments and preferred embodiments, and will not be described again. As used below, the term "module" can be a combination of software and / or hardware that implements a predetermined function. Although the device described in the following embodiments is preferably implemented in software, implementation of hardware, or a combination of software and hardware, is also possible and contemplated.

[0069] Figure 8 is a structural block diagram of a device for determining a ship scheduling strategy according to an embodiment of the present application, as shown in Figure 8 the device comprises a first memory 802, a first processor 804, and a first computer program 80202 stored on the first memory 802 and executable on the first processor 804, and the first processor 804 implements the following operations when executing the first computer program 80202:

[0070] determining travel state information of a first ship included in a target area, resource allocation information of a target port included in the target area, and environmental information of the target area;

[0071] constructing a target mathematical model based on the travel state information, the resource allocation information, and the environmental information;

[0072] determining a scheduling strategy matrix based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure;

[0073] controlling a second ship to travel according to the scheduling strategy matrix.

[0074] In one exemplary embodiment, the device implements the construction of the target mathematical model based on the travel state information, the resource allocation information, and the environmental information by: determining a departure time and a sailing speed of the second ship based on the travel state information; constructing a target cost function based on the departure time and the sailing speed; constructing a target constraint condition based on the travel state information, the resource allocation information, and the environmental information; and constructing the target mathematical model based on the target cost function and the target constraint condition.

[0075] In one exemplary embodiment, the device implements the construction of the target cost function based on the departure time and the sailing speed by: constructing a cost function based on the departure time of each of the second ships, to obtain a plurality of first cost functions; constructing a cost function based on the sailing speed of each of the second ships, to obtain a plurality of second cost functions; and determining a sum value of the plurality of first cost functions and the plurality of second cost functions as the target cost function.

[0076] In an example embodiment, the apparatus implements constructing the target constraint condition based on the sailing state information, the resource allocation information and the environment information by: determining, based on the sailing state information, the resource allocation information and the environment information, a sailing track constraint condition of the second ship in the target area, a berth constraint condition of the second ship in the target port and a channel capacity constraint condition of the second ship in the target area; and determining the sailing track constraint condition, the berth constraint condition and the channel capacity constraint condition as the target constraint condition.

[0077] In an example embodiment, the apparatus implements constructing the target mathematical model based on the target cost function and the target constraint condition by: the target mathematical model representing as follows: wherein S n represents an n*n symmetric matrix space, C represents the target cost function, X represents the scheduling strategy matrix, A j represents the jth target constraint condition, b j represents a preset constant.

[0078] In an example embodiment, the apparatus implements determining the scheduling strategy matrix based on the target mathematical model by: determining an initial solution satisfying the target constraint condition included in the target mathematical model, wherein the initial solution is a solution of the target mathematical model; and repeatedly performing a target operation until an iterative solution obtained satisfies a convergence condition, wherein the iterative solution is a solution of the target mathematical model, the target operation includes: determining a target function for solving the target mathematical model; determining a target update amount of a target variable included in the target function; updating the target variable based on the target update amount to obtain an update function; determining, based on the update function, the iterative solution satisfying the target constraint condition; in a case where the iterative solution satisfies the convergence condition, determining the iterative solution as the scheduling strategy matrix; and in a case where the iterative solution does not satisfy the convergence condition, updating the initial solution as the iterative solution and continuing to perform the target operation.

[0079] In an example embodiment, the apparatus is further configured to, after determining, based on the update function, the iterative solution satisfying the target constraint condition: determine, by using a preconditioner, a target relationship between the iterative solution and a target cost value preset; and in a case where the target relationship indicates that the iterative solution is equal to the target cost value, determine that the iterative solution satisfies the convergence condition.

[0080] It should be noted that the above modules can be implemented by software or hardware. For the latter, they can be implemented in the following ways, but are not limited to: all the above modules are located in the same processor; or, the above modules are located in different processors in any combination.

[0081] Embodiments of the present invention also provide a computer-readable storage medium storing a computer program, wherein the computer program is configured to perform the steps in any of the above method embodiments when executed.

[0082] In one exemplary embodiment, the aforementioned computer-readable storage medium may include, but is not limited to, various media capable of storing computer programs, such as a USB flash drive, read-only memory (ROM), random access memory (RAM), portable hard disk, magnetic disk, or optical disk.

[0083] Embodiments of the present invention also provide an electronic device including a memory and a processor, the memory storing a computer program and the processor being configured to run the computer program to perform the steps in any of the above method embodiments.

[0084] In one exemplary embodiment, the electronic device may further include a transmission device and an input / output device, wherein the transmission device is connected to the processor and the input / output device is connected to the processor.

[0085] Embodiments of the present invention also provide a computer program product, including a computer program that, when executed by a processor, implements the steps of the methods in various embodiments of the present application.

[0086] Specific examples in this embodiment can be found in the examples described in the above embodiments and exemplary implementations, and will not be repeated here.

[0087] It is obvious to those skilled in the art that the modules or steps of the present invention described above can be implemented using general-purpose computing devices. They can be centralized on a single computing device or distributed across a network of multiple computing devices. They can be implemented using computer-executable program code, and thus can be stored in a storage device for execution by a computing device. In some cases, the steps shown or described can be performed in a different order than those described herein, or they can be fabricated as separate integrated circuit modules, or multiple modules or steps can be fabricated as a single integrated circuit module. Thus, the present invention is not limited to any particular combination of hardware and software.

[0088] The above merely provides the preferred embodiments of the present application, and is not used to limit the present application. For those skilled in the art, the present application can have various modifications and changes. Any modifications, equivalent replacements, improvements, etc. made within the principles of the present application shall fall into the protective scope of the present application.

Claims

1. A method for determining a ship scheduling strategy, characterized in that, include: Determine the navigation status information of the first vessel included in the target area, the resource allocation information of the target port included in the target area, and the environmental information of the target area; A target mathematical model is constructed based on the driving status information, the resource allocation information, and the environmental information; The scheduling strategy matrix is ​​determined based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure; Control the second vessel to navigate according to the aforementioned scheduling strategy matrix.

2. The method according to claim 1, characterized in that, Based on the driving status information, the resource allocation information, and the environmental information, a target mathematical model is constructed, including: Based on the aforementioned driving status information, the departure time and speed of the second vessel are determined. Construct a target cost function based on the departure time and the sailing speed; Target constraints are constructed based on the driving status information, the resource allocation information, and the environmental information. The target mathematical model is constructed based on the target cost function and the target constraints.

3. The method according to claim 2, characterized in that, Construct a target cost function based on the expected departure time and the expected sailing speed, including: Based on the departure time of each of the second vessels, a cost function is constructed to obtain multiple first cost functions; Based on the speed to be traversed for each of the second vessels, a cost function is constructed to obtain multiple second cost functions; The sum of the plurality of first cost functions and the plurality of second cost functions is determined as the target cost function.

4. The method according to claim 2, characterized in that, Based on the driving status information, the resource allocation information, and the environmental information, target constraints are constructed, including: Based on the driving status information, the resource allocation information, and the environmental information, determine the navigation trajectory constraints of the second vessel in the target area, the berth constraints of the second vessel in the target port, and the channel capacity constraints of the second vessel in the target area. The target constraint is determined by the navigation trajectory constraint, the berth constraint, and the channel capacity constraint.

5. The method according to claim 2, characterized in that, The objective mathematical model is constructed based on the objective cost function and the objective constraints, including: The target mathematical model is represented as follows: Among them, S n Let C represent the n×n symmetric matrix space, C represent the objective cost function, X represent the scheduling policy matrix, and A represent the scheduling policy matrix. j Let b represent the j-th objective constraint. j This represents a preset constant.

6. The method according to claim 1, characterized in that, Determining the scheduling strategy matrix based on the target mathematical model includes: Determine an initial solution that satisfies the target constraints included in the target mathematical model, wherein the initial solution is a solution of the target mathematical model; Repeat the target operation until the obtained iterative solution satisfies the convergence condition, wherein the iterative solution is the solution of the target mathematical model, and the target operation includes: Determine the objective function used to solve the target mathematical model; Determine the target update amount of the target variables included in the objective function; The target variable is updated based on the target update amount to obtain the update function; The iterative solution that satisfies the target constraint is determined based on the update function; If the iterative solution satisfies the convergence condition, the iterative solution is determined as the scheduling strategy matrix; If the iterative solution does not satisfy the convergence condition, the initial solution is updated to the iterative solution, and the target operation continues to be executed.

7. The method according to claim 6, characterized in that, After determining the iterative solution that satisfies the target constraint based on the update function, the method further includes: The target relationship between the iterative solution and the pre-set target cost value is determined using a preconditioner. If the target relation indicates that the iterative solution is equal to the target cost value, then the iterative solution is determined to satisfy the convergence condition.

8. A device for determining a ship scheduling strategy, characterized in that, It includes a first memory, a first processor, and a first computer program stored in the first memory and executable on the first processor. When the first processor executes the first computer program, it performs the following operations: Determine the navigation status information of the first vessel included in the target area, the resource allocation information of the target port included in the target area, and the environmental information of the target area; A target mathematical model is constructed based on the driving status information, the resource allocation information, and the environmental information; The scheduling strategy matrix is ​​determined based on the target mathematical model, wherein the scheduling strategy matrix has a low-rank structure; Control the second vessel to navigate according to the aforementioned scheduling strategy matrix.

9. A computer-readable storage medium, characterized in that, The computer-readable storage medium stores a computer program, wherein the computer program is configured to perform the method described in any one of claims 1 to 7 when executed.

10. An electronic device comprising a memory and a processor, characterized in that, The memory stores a computer program, and the processor is configured to run the computer program to perform the method as described in any one of claims 1 to 7.

11. A computer program product, comprising a computer program, characterized in that, When the computer program is executed by a processor, it implements the steps of the method described in any one of claims 1 to 7.

Images