Intelligent recommendation method, terminal device and storage medium for low-conflict route group

Abstract

The present invention relates to a method, terminal device and storage medium for intelligent recommendation of low-conflict route groups, the method comprising: S1: calculating the probability density function of the trajectory area of ​​the ship to be analyzed based on kernel density estimation, and calculating the trajectory area of ​​the ship to be analyzed according to the probability density function; S2: recommending the route of the ship to be analyzed by a composite particle swarm optimization algorithm based on the area of ​​the trajectory area of ​​the ship to be analyzed. The present invention is used to find the best position while avoiding collision, with constraints such as water depth, collision avoidance and detours in other water functional areas as fitness functions, which not only achieves a faster search speed, but also improves positioning accuracy, proving its convergence.

Description

Technical Field

[0001] The present invention relates to the field of route recommendation, and in particular to a method, terminal device and storage medium for intelligently recommending a route group with low encounter conflict. Background Art

[0002] In recent years, with the rapid development of the yacht industry and the continuous planning and construction of yacht terminals, the number of yachts sailing in the sea will continue to increase. The disorderly navigation or activities of existing yachts will have a certain impact on the navigation environment and safety of port waters, and interact with ships sailing in and out of the port and anchored. Therefore, it is necessary to demonstrate and study the adaptability of the waters for yacht navigation activities, so as to delineate the scope of yacht activity areas, recommend routes for yachts, ensure the safety of yacht activities and the normal navigation order of ships in ports, and better serve the development of the yacht industry. Summary of the invention

[0003] In order to solve the above problems, the present invention proposes a method for intelligently recommending route groups with low encounter conflicts, a terminal device and a storage medium.

[0004] The specific plan is as follows:

[0005] A method for intelligently recommending a route group with low conflict encounter, comprising the following steps:

[0006] S1: Calculate the probability density function of the trajectory area of ​​the ship to be analyzed based on kernel density estimation, and calculate the trajectory area of ​​the ship to be analyzed according to the probability density function;

[0007] S2: Based on the area of ​​the trajectory region of the ship to be analyzed, the route of the ship to be analyzed is recommended by the composite particle swarm optimization algorithm.

[0008] Furthermore, the specific recommendation process in step S2 includes the following steps:

[0009] S201: Initialize the population;

[0010] S202: Evaluate the objective function of each particle;

[0011] S203: Update the local optimal solution of each particle;

[0012] S204: Update the global optimal solution of the population;

[0013] S205: Update the speed and position of each particle;

[0014] S206: Determine whether the end condition is met, if yes, go to S207; otherwise, return to S202;

[0015] S207: Output the optimal solution, and recommend a route for the ship to be analyzed based on the optimal solution.

[0016] Furthermore, the objective function F of the particle is:

[0017]

[0018] f1=S Domain ∩S KDE

[0019]

[0020] Among them, l represents the sequence number of the sub-goal, f l represents the lth sub-goal, w l represents the weight of the lth sub-goal, S Domain The area of ​​the ship field corresponding to the historical ship trajectory in the route area, S KDE represents the trajectory area of ​​the ship to be analyzed, i represents the sequence number of the waypoint, and W i represents the i-th waypoint, N represents the number of waypoints, H(W i ) represents the height above sea level of the i-th waypoint, j represents the serial number of the functional area, M represents the number of functional areas, S represents the area of ​​the ship's navigation waters, S other,j Represents the area of ​​water area in the jth functional zone.

[0021] Furthermore, the speed and position update formula of the particle in step S205 is:

[0022] v i,k+1 =v i,k +c1r(p i -x i,k )+c2r(p g -x i,k )

[0023] x i,k+1 =x i,k +v i,k

[0024] Among them, c1, c2 are learning factors; r is a random number; x i,k represents the position of the i-th particle in the k-th iteration; v i,k represents the velocity of the i-th particle in the k-th iteration; p g represents the global optimal solution obtained in the first k iterations; p i represents the local optimal solution obtained by the i-th particle in the first k iterations;

[0025] c1 and c2 are updated using the following formula:

[0026]

[0027] Among them, sinh() represents the hyperbolic sine function, λ represents the variable coefficient of the hyperbolic sine function in the numerator of c2, u represents the variable coefficient of the hyperbolic sine function in the denominator of c2, T represents the maximum number of iterations, and k represents the number of iterations.

[0028] A terminal device for intelligently recommending low-conflict route groups includes a processor, a memory, and a computer program stored in the memory and executable on the processor. When the processor executes the computer program, the steps of the method described above in the embodiment of the present invention are implemented.

[0029] A computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the method described above in an embodiment of the present invention are implemented.

[0030] The present invention adopts the above technical solution to find the best position while avoiding collision, with constraints such as water depth, collision avoidance and detours to other water functional areas as the fitness function. It not only achieves a faster search speed, but also improves the positioning accuracy, proving its convergence. BRIEF DESCRIPTION OF THE DRAWINGS

[0031] Figure 1 Shown is a flow chart of Embodiment 1 of the present invention.

[0032] Figure 2 The figure is a schematic diagram showing the intersection of the area of ​​the ship field corresponding to the historical ship trajectory in this embodiment and the trajectory area of ​​the ship to be analyzed.

[0033] Figure 3 Shown is a schematic diagram of the ship field in this embodiment. DETAILED DESCRIPTION

[0034] To further illustrate various embodiments, the present invention provides drawings. These drawings are part of the disclosure of the present invention, which are mainly used to illustrate the embodiments and can be used in conjunction with the relevant descriptions in the specification to explain the operating principles of the embodiments. With reference to these contents, ordinary technicians in this field should be able to understand other possible implementations and advantages of the present invention.

[0035] The present invention will now be further described with reference to the accompanying drawings and specific implementation methods.

[0036] Embodiment 1:

[0037] The embodiment of the present invention provides a method for intelligently recommending a route group with low conflict. Figure 1 As shown, the method comprises the following steps:

[0038] S1: Calculate the probability density function of the trajectory area of ​​the ship to be analyzed based on kernel density estimation, and calculate the trajectory area of ​​the ship to be analyzed according to the probability density function.

[0039] S2: Based on the area of ​​the trajectory region of the ship to be analyzed, the route of the ship to be analyzed is recommended by the composite particle swarm optimization (HPSO) algorithm.

[0040] Composite particle swarm optimization algorithm is a type of random global optimization technology with the advantages of strong search ability, fast convergence speed and high search accuracy.

[0041] In this embodiment, the specific recommendation process includes the following steps:

[0042] S201: Initialize the population;

[0043] S202: Evaluate the objective function of each particle;

[0044] S203: Update the local optimal solution of each particle;

[0045] S204: Update the global optimal solution of the population;

[0046] S205: Update the speed and position of each particle;

[0047] S206: Determine whether the end condition is met, if yes, go to S207; otherwise, return to S202;

[0048] S207: Output the optimal solution, and recommend a route for the ship to be analyzed based on the optimal solution.

[0049] In this embodiment, the objective function F of the particle is set to consist of three sub-objective functions, namely:

[0050]

[0051] Among them, l represents the sequence number of the sub-goal, f l represents the lth sub-goal, w l represents the weight of the lth sub-goal.

[0052] The first sub-objective function is the measurement of the area of ​​intersection between the area of ​​the ship field corresponding to the historical ship trajectory of the route area and the trajectory area of ​​the ship to be analyzed, such as Figure 2 As shown, the calculation formula is:

[0053] f1=S Domain ∩S KDE

[0054] Among them, S Domain The area of ​​the ship field corresponding to the historical ship trajectory in the route area, S KDE Indicates the track area of ​​the ship to be analyzed. Figure 3 As shown, the calculation formula for setting the ship field in this embodiment is as follows:

[0055]

[0056] R starb =(0.2+k DT )L

[0057] R port =(0.2+0.75k DT )L

[0058] k AD =10 0.3591lgv+0.0952

[0059] k DT =10 0.5441lgv-0.0795

[0060] Where v is the speed of the ship, L is the length of the ship, and R fore and R aft Respectively represent the longitudinal radius of the ship area in the bow and stern directions, R starb and R port are the transverse radii of the ship domain in the starboard and port directions, respectively, k AD and k DT All are coefficient parameters. Calculate R according to the above formula fore , R aft , R starb , R port Then, with the ship's center of mass as the center O, draw a vector OA along the bow direction so that |OA|=R fore ; Draw OB along the starboard side so that |OB|=R starb ; Draw vector OC along the stern direction so that |OC|=R aft ; Draw OD along the port side so that |OD|=R port . Connect A, B, C, and D, and the resulting quadrilateral is the ship area. The area of ​​this quadrilateral is S Domain .

[0061] Since the type of ship to be analyzed in this embodiment is a medium-sized yacht, considering that a medium-sized yacht with a length of 16.5 meters and a draft of 1.2 meters can sail at full tide when the water depth is 2 meters, the second sub-objective function is set as the water depth cost that the ship should not collide with the coastline, and the calculation formula is:

[0062]

[0063] Where i represents the number of the waypoint, W i represents the i-th waypoint, N represents the number of waypoints, H(W i ) represents the height above sea level of the ith waypoint.

[0064] The second sub-objective function is that the ship navigation waters should not overlap with other functional areas (such as anchorages, breeding areas, beaches, etc.). Therefore, the calculation formula is set as:

[0065]

[0066] Where j represents the serial number of the functional area, M represents the number of functional areas, S represents the area of ​​the ship's navigation waters, and S other,j Represents the area of ​​water area in the jth functional zone.

[0067] In step S205, the speed and position of the particle are updated, and the update formula is set as:

[0068] v i,k+1 =v i,k +c1r(p i -x i,k )+c2r(p g -x i,k )

[0069] x i,k+1 =x i,k +v i,k

[0070] Among them, c1, c2 are learning factors; r is a random number; x i,k represents the position of the i-th particle in the k-th iteration; v i,k represents the velocity of the i-th particle in the k-th iteration; p g represents the global optimal solution obtained in the first k iterations; p i represents the local optimal solution obtained by the i-th particle in the first k iterations.

[0071] In order to better update, an adaptive gravitational search algorithm is proposed in this embodiment. In the calculation of the learning factor, the traditional fixed value method is improved, and a nonlinear attenuation mechanism is designed to update the learning factor, that is, the hyperbolic sine function is used. The hyperbolic sine function is a type of hyperbolic function. The hyperbolic sine function increases monotonically in the entire real number interval. By introducing the hyperbolic sine function, the diversity of solutions can be improved. The update formulas of the learning factors c1 and c2 are as follows:

[0072]

[0073] Among them, sinh() represents the hyperbolic sine function, λ represents the variable coefficient of the hyperbolic sine function in the numerator of c2, u represents the variable coefficient of the hyperbolic sine function in the denominator of c2, T represents the maximum number of iterations, and k represents the number of iterations.

[0074] The embodiment of the present invention adopts the above scheme to provide a feasible, safe and optimal position for ship maneuvering. Due to the small fitness, the HPSO algorithm performs particularly well in complex scenarios, where different types of obstacles and threats can be reflected. The search space is effectively converted from longitude and latitude space to Cartesian space to obtain high-quality solutions. Collision avoidance constraints can be integrated into variables to reduce the search space. HPSO introduces relatively fast convergence, improves development capabilities through mutation and recombination, and its corresponding randomization mechanism helps to solve the problem of premature convergence.

[0075] Embodiment 2:

[0076] The present invention also provides a low-conflict route group intelligent recommendation terminal device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, and when the processor executes the computer program, the steps in the above-mentioned method embodiment of the first embodiment of the present invention are implemented.

[0077] Further, as an executable solution, the low-conflict route group intelligent recommendation terminal device can be a computing device such as a desktop computer, a notebook, a PDA, and a cloud server. The low-conflict route group intelligent recommendation terminal device can include, but is not limited to, a processor and a memory. Those skilled in the art can understand that the composition structure of the above-mentioned low-conflict route group intelligent recommendation terminal device is only an example of a low-conflict route group intelligent recommendation terminal device, and does not constitute a limitation on the low-conflict route group intelligent recommendation terminal device, and may include more or less components than the above-mentioned, or a combination of certain components, or different components. For example, the low-conflict route group intelligent recommendation terminal device may also include input and output devices, network access devices, buses, etc., and the embodiments of the present invention do not limit this.

[0078] Further, as an executable solution, the processor may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA) or other programmable logic devices, discrete gate or transistor logic devices, discrete hardware components, etc. The general-purpose processor may be a microprocessor or any conventional processor, etc. The processor is the control center of the low-conflict route group intelligent recommendation terminal device, and uses various interfaces and lines to connect various parts of the entire low-conflict route group intelligent recommendation terminal device.

[0079] The memory can be used to store the computer program and / or module, and the processor realizes various functions of the low-conflict route group intelligent recommendation terminal device by running or executing the computer program and / or module stored in the memory, and calling the data stored in the memory. The memory can mainly include a program storage area and a data storage area, wherein the program storage area can store an operating system and at least one application required for a function; the data storage area can store data created according to the use of the mobile phone, etc. In addition, the memory can include a high-speed random access memory, and can also include a non-volatile memory, such as a hard disk, a memory, a plug-in hard disk, a smart memory card (Smart Media Card, SMC), a secure digital (Secure Digital, SD) card, a flash card (Flash Card), at least one disk storage device, a flash memory device, or other volatile solid-state storage devices.

[0080] The present invention also provides a computer-readable storage medium, wherein the computer-readable storage medium stores a computer program, and when the computer program is executed by a processor, the steps of the above method in the embodiment of the present invention are implemented.

[0081] If the module / unit integrated in the terminal device for intelligent recommendation of low-conflict route groups is implemented in the form of a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present invention implements all or part of the processes in the above-mentioned embodiment method, and can also be completed by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium, and the computer program can implement the steps of the above-mentioned method embodiments when executed by the processor. Among them, the computer program includes computer program code, and the computer program code can be in source code form, object code form, executable file or some intermediate form. The computer-readable medium may include: any entity or device capable of carrying the computer program code, recording medium, U disk, mobile hard disk, disk, optical disk, computer memory, read-only memory (ROM, Read-Only Memory), random access memory (RAM, Random Access Memory) and software distribution medium, etc.

[0082] Although the present invention has been specifically shown and described in conjunction with the preferred embodiments, it should be understood by those skilled in the art that various changes may be made to the present invention in form and details without departing from the spirit and scope of the present invention as defined by the appended claims, all of which are within the scope of protection of the present invention.

Claims

1. A method for intelligently recommending low-conflict route groups, characterized in that: The following steps are involved: S1: Calculate the probability density function of the trajectory area of ​​the ship to be analyzed based on kernel density estimation, and calculate the trajectory area of ​​the ship to be analyzed according to the probability density function; S2: Based on the area of ​​the trajectory region of the ship to be analyzed, the composite particle swarm optimization algorithm is used to recommend the route of the ship to be analyzed; the calculation formula of the objective function F of the particle in the composite particle swarm optimization algorithm is: f1=S Domain ∩S KDE Among them, l represents the sequence number of the sub-goal, f l represents the lth sub-goal, w l represents the weight of the lth sub-goal, S Domain The area of ​​the ship field corresponding to the historical ship trajectory in the route area, S KDE represents the trajectory area of ​​the ship to be analyzed, i represents the sequence number of the waypoint, and W i represents the i-th waypoint, N represents the number of waypoints, H(W i ) represents the height above sea level of the i-th waypoint, j represents the serial number of the functional area, M represents the number of functional areas, S represents the area of ​​the ship's navigation waters, S other,j Represents the area of ​​water area in the jth functional zone.

2. The method for intelligently recommending low-conflict route groups according to claim 1, characterized in that: The specific recommendation process in step S2 includes the following steps: S201: Initialize the population; S202: Evaluate the objective function of each particle; S203: Update the local optimal solution of each particle; S204: Update the global optimal solution of the population; S205: Update the speed and position of each particle; S206: Determine whether the end condition is met, if yes, go to S207; otherwise, return to S202; S207: Output the optimal solution, and recommend a route for the ship to be analyzed based on the optimal solution.

3. The method for intelligently recommending low-conflict route groups according to claim 2, characterized in that: The speed and position update formula of the particle in step S205 is: v i,k+1 =v i,k +c1r(p i -x i,k )+c2r(p g -x i,k ) x i,k+1 =x i,k +v i,k Among them, c1, c2 are learning factors; r is a random number; x i,k represents the position of the i-th particle in the k-th iteration; v i,k represents the velocity of the i-th particle in the k-th iteration; p g represents the global optimal solution obtained in the first k iterations; p i represents the local optimal solution obtained by the i-th particle in the first k iterations; c1 and c2 are updated using the following formula: Among them, sinh() represents the hyperbolic sine function, λ represents the variable coefficient of the hyperbolic sine function in the numerator of c2, u represents the variable coefficient of the hyperbolic sine function in the denominator of c2, T represents the maximum number of iterations, and k represents the number of iterations.

4. A low-conflict route group intelligent recommendation terminal device, characterized in that: The method comprises a processor, a memory and a computer program stored in the memory and running on the processor, wherein the processor implements the steps of the method according to any one of claims 1 to 3 when executing the computer program.

5. A computer-readable storage medium storing a computer program, characterized in that: When the computer program is executed by a processor, the steps of the method according to any one of claims 1 to 3 are implemented.

Images