Logistics management method and device in multimodal transport

Abstract

The invention discloses a logistics management method and device in multimodal transport, and relates to the technical field of logistics management, and the method comprises the steps: obtaining a transportation starting point and a transportation terminal point of to-be-transported goods in multimodal transport, and obtaining transportation nodes between the transportation starting point and the transportation terminal point, and a transportation mode between the transportation nodes; according to the transportation starting point, the transportation ending point, the transportation nodes and the transportation modes between the transportation nodes, an initial transportation path between the transportation starting point and the transportation ending point is determined according to a preset rule; and establishing a target optimization function of transportation of the to-be-transported goods, encoding the initial transportation path to obtain a corresponding initial fish school, performing iterative optimization on the transportation path by using the initial fish school until a fitness value of the target optimization function calculated by using the transportation path meets a preset threshold value, and obtaining an optimal transportation path in multimodal transportation. According to the invention, the problem that the method for determining the optimal path in multimodal transport in the prior art is not ideal enough is solved.

Description

Technical Field

[0001] The present invention relates to the technical field of logistics management, and particularly to a logistics management method and device in multimodal transportation. Background Art

[0002] Multimodal transportation refers to the comprehensive use of two or more transportation modes such as road transportation, railway transportation, and waterway transportation. Through scientific coordination, smooth conversion, and close connection, an efficient and convenient integrated transportation system is constructed to meet the transportation needs of goods in different scenarios.

[0003] In the process of multimodal transportation, determining the optimal path is one of the core links to achieve efficient transportation. The determination of the shortest path does not merely mean the shortest in terms of geographical distance, but the optimal choice after comprehensively considering various factors. These factors include, but are not limited to, the costs of different transportation modes and transportation time. Reasonably planning the shortest path can reduce logistics costs, improve the timeliness of goods transportation, and enhance the reliability of logistics services.

[0004] However, the existing methods for determining the optimal path have limitations such as difficulty in dealing with multi-objective and high-dimensional problems, resulting in less-than-ideal determined transportation paths. Summary of the Invention

[0005] In view of this, the purpose of the present invention is to provide a logistics management method and device in multimodal transportation, aiming to solve the problem that the method for determining the optimal path in existing multimodal transportation is not ideal.

[0006] On the one hand, the present invention proposes a logistics management method in multimodal transportation, and the method includes: Obtain the transportation starting point and the transportation ending point of the goods to be transported in multimodal transportation, and obtain the transportation nodes between the transportation starting point and the transportation ending point and the transportation modes between each transportation node; According to the transportation starting point, the transportation ending point, the transportation nodes, and the transportation modes between each transportation node, determine the initial transportation path between the transportation starting point and the transportation ending point according to preset rules; Establish an objective optimization function for the transportation of the goods to be transported, encode the initial transportation path to obtain a corresponding initial fish swarm, and use the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation.

[0007] Further, in the above logistics management method in multimodal transportation, the step of using the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets a preset threshold includes: For each fish in the initial fish swarm, foraging, schooling, and following behaviors are respectively performed to obtain corresponding new positions; Based on their respective fitness values, the optimal target positions are selected from the corresponding new positions obtained from foraging, schooling, and following behaviors; The target positions of all the fish in the initial fish swarm are combined to form a temporary fish swarm. Non-dominated sorting and crowding degree calculation are performed on the temporary fish swarm, and the first preset number of fish are selected from the temporary fish swarm to form a new generation of fish swarm; The new generation of fish swarm replaces the initial fish swarm to iteratively optimize the transportation route until the fitness value of the objective optimization function calculated using the transportation route meets the preset threshold.

[0008] Furthermore, in the above logistics management method for multimodal transport, the step of, for each fish in the initial fish swarm, respectively performing foraging, schooling, and following behaviors to obtain corresponding new positions includes: For each fish in the initial fish swarm, a target position is randomly selected within the sensing range. If the target position dominates the current position of the fish, then move one step towards the target position; For each fish in the initial fish swarm, find the set of partner fish within the field of view, calculate the center position of the set of partner fish. If the center position dominates the current position of the fish, then move one step towards the center position; For each fish in the initial fish swarm, find the optimal partner fish within the field of view. If the optimal partner fish dominates the current position of the fish, then move one step towards the optimal partner fish.

[0009] Furthermore, in the above logistics management method for multimodal transport, the step of, for each fish in the initial fish swarm, randomly selecting a target position within the sensing range and moving one step towards the target position if the target position dominates the current position of the fish further includes: Based on the historical movement trajectory of the fish, calculate the historical optimal direction and generate a random direction, and determine the hybrid direction using the historical optimal direction and the random direction; Select a target point at a set distance in the hybrid direction and use the target point as the corresponding target position; Among them, the formula for determining the hybrid direction is: ; Among them, is the historical optimal direction, is the random direction, is the weight.

[0010] Further, in the above logistics management method in multimodal transport, for each fish in the initial fish school, finding the set of partner fish within the field of vision, calculating the central position of the set of partner fish, if the central position dominates the current position of the fish, the step of moving one step towards the central position further includes: Finding the set of partner fish within the field of vision, calculating the local density for each neighbor, and calculating the comprehensive score according to the local density; Selecting the target neighbor with the highest score, if the position of the target neighbor dominates the current position of the fish, moving one step towards the position of the target neighbor; Among them, the calculation formula for the comprehensive score is: ; Among them, is the fitness of the j th neighbor, is the density influence factor, is the j th neighbor's local density.

[0011] Further, in the above logistics management method in multimodal transport, for each fish in the initial fish school, finding the optimal partner fish within the field of vision, if the optimal partner fish dominates the current position of the fish, the step of moving one step towards the optimal partner fish further includes: Selecting the first k optimal individuals in the initial fish school as leaders, and calculating the leader fitness weight: Calculating the synthetic direction according to the leader fitness weight and the direction of the leader, and moving in the synthetic direction with a preset probability.

[0012] Further, in the above logistics management method in multimodal transport, the expression of the objective optimization function is:

[0013] ; ; Among them, is the transportation cost objective function, is the transportation time objective function, i and j respectively represent nodes, k represents the transportation mode, represents the number of transportation containers, is the unit transportation cost of the transportation mode k , is the distance between the goods at node i and node j , is the distance between the goods at node iAnd node j Whether to adopt a transportation method k Variable, Is the transfer cost per unit of the yard unit converted from the transportation method k To the transportation method m ; Is the unit feeder transportation cost, Is the transfer distance converted from the transportation method k To the transportation method m ; Is the variable of the goods switching from the transportation method i At the node k To m ; Is the transfer speed, Is the unit transfer time for the transportation method k, m To switch at the yard, Is the feeder distance between the container yard and the shipper / consignee warehouse, Is the feeder distance between the shipper / consignee warehouse and the railway / waterway yard, Is the unit loading time, Is the unit feeder transportation speed.

[0014] Another object of the present invention is to provide a logistics management device in multimodal transportation, and the device includes: An acquisition module, configured to acquire the transportation origin and destination of the goods to be transported in multimodal transportation, and acquire the transportation nodes between the transportation origin and destination and the transportation methods between each transportation node; A determination module, configured to determine an initial transportation path between the transportation origin and destination according to the transportation origin, destination, transportation nodes, and the transportation methods between each transportation node according to a preset rule; A transportation module, configured to establish an objective optimization function for transporting the goods to be transported, encode the initial transportation path to obtain a corresponding initial fish swarm, and iteratively optimize the transportation path by using the initial fish swarm until the fitness value of the objective optimization function calculated by using the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation.

[0015] Another object of the present invention is to provide a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the above method are implemented.

[0016] Another object of the present invention is to provide an electronic device, including a memory, a processor, and a computer program stored on the memory and running on the processor, and when the processor executes the program, the steps of the above method are implemented.

[0017] The present invention obtains the transportation starting point and the transportation ending point of the goods to be transported in multimodal transportation, and obtains the transportation nodes between the transportation starting point and the transportation ending point and the transportation modes between each transportation node; determines the initial transportation path between the transportation starting point and the transportation ending point according to the transportation starting point, the transportation ending point, the transportation nodes and the transportation modes between each transportation node according to a preset rule; establishes an objective optimization function for the transportation of the goods to be transported, encodes the initial transportation path to obtain a corresponding initial fish swarm, and uses the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated by the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation. Encodes the initial path to obtain an initial fish swarm and performs iterative optimization. The fish swarm algorithm simulates the behavior of a fish swarm, can continuously explore in the transportation path search space, and gradually approaches the optimal solution through multiple iterations. As the iteration progresses, each link of the transportation path (such as transportation mode selection, transfer node arrangement, etc.) is continuously adjusted to make the path more and more in line with the requirements of the objective optimization function until the fitness value meets the preset threshold, finds the relatively optimal transportation path in multimodal transportation, and finally obtains a high-quality best transportation path. It solves the problem that the method for determining the optimal path in multimodal transportation in the prior art is not ideal enough. BRIEF DESCRIPTION OF THE DRAWINGS

[0018] Figure 1 It is a flowchart of the logistics management method in multimodal transportation in the first embodiment of the present invention; Figure 2 It is a structural block diagram of the logistics management device in multimodal transportation in the third embodiment of the present invention.

[0019] The following specific embodiments will further illustrate the present invention in conjunction with the above-mentioned drawings. SPECIFIC EMBODIMENTS

[0020] To facilitate the understanding of the present invention, the present invention will be described more comprehensively below with reference to the relevant drawings. Several embodiments of the present invention are shown in the drawings. However, the present invention can be implemented in many different forms and is not limited to the embodiments described herein. On the contrary, these embodiments are provided to make the disclosure of the present invention more thorough and comprehensive.

[0021] It should be noted that when an element is referred to as being "fixedly installed on" another element, it can be directly on the other element or there may also be an intermediate element. When an element is considered to be "connected" to another element, it can be directly connected to the other element or there may be an intermediate element at the same time. The terms "vertical", "horizontal", "left", "right" and similar expressions used herein are only for the purpose of illustration.

[0022] Unless otherwise defined, all technical and scientific terms used herein have the same meaning as commonly understood by one of ordinary skill in the technical field to which this invention belongs. The terms used in the description of the present invention herein are for the purpose of describing specific embodiments only and are not intended to limit the present invention. The term "and / or" used herein includes any and all combinations of one or more of the related listed items.

[0023] Embodiment 1 Please refer to Figure 1 , which shows the logistics management method in multimodal transportation in the first embodiment of the present invention. The method includes steps S10 to S12.

[0024] Step S10: Obtain the starting point and ending point of the goods to be transported in multimodal transportation, and obtain the transportation nodes between the starting point and the ending point and the transportation modes between each transportation node.

[0025] Among them, in the complex logistics transportation scenario of multimodal transportation, the entire transportation process often involves the coordinated operation of multiple links and multiple transportation modes. First, it is necessary to determine the starting point of the goods to be transported. At the same time, it is also necessary to determine the ending point of the goods, that is, the target location where the goods will ultimately be delivered. Between the starting point and the ending point of transportation, there are usually a series of transportation nodes. These transportation nodes are like key stations on the transportation route. They are transfer hubs between different transportation modes, such as the transfer station between railway and road transportation, the transshipment terminal between waterway and railway transportation, etc. It should be noted that the starting point and the ending point of transportation are also one type of transportation nodes.

[0026] In addition, it is also necessary to clarify the transportation modes between each transportation node. In multimodal transportation, the transportation modes are rich and diverse. Common ones include road transportation, railway transportation, waterway transportation, and air transportation, etc. Different transportation modes may be adopted between different transportation nodes. For example, road transportation is used from the starting point to the first transportation node, railway transportation is used from the first transportation node to the second transportation node, and waterway transportation is used from the second transportation node to the ending point of transportation. Obtaining the transportation modes between each transportation node provides a basis for subsequent optimization of the transportation route.

[0027] Step S11: Determine the initial transportation route between the starting point and the ending point according to the starting point, the ending point, the transportation nodes, and the transportation modes between each transportation node according to a preset rule.

[0028] Among them, after determining the transportation origin, transportation destination, transportation nodes, and the transportation modes between each transportation node, a series of initial transportation paths that meet the actual requirements can be obtained according to the actual situation. Specifically, the transportation nodes available for selection and the transportation modes between each transportation node can be obtained first, and each is formed into a set. Then, some of these nodes or transportation modes are randomly selected from the set to form a preliminary transportation path.

[0029] Step S12, establish an objective optimization function for the transportation of goods to be transported, encode the initial transportation path to obtain the corresponding initial fish swarm, and use the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets the preset threshold, and obtain the best transportation path in multimodal transportation.

[0030] Among them, the objective optimization function integrates various key factors in multimodal transportation into a quantifiable mathematical formula for measuring the pros and cons of each transportation path. In actual transportation, the factors to be considered are complex and diverse, such as transportation cost factors or transportation time factors.

[0031] Exemplarily, in the embodiment of the present invention, the expression of the objective optimization function is:

[0032] ; ; Among them, is the transportation cost objective function, is the transportation time objective function, i and j respectively represent nodes, k represents the transportation mode, represents the number of transportation containers, is the transportation mode k of the unit transportation cost, is the distance between the goods at node i and node j , is the distance between the goods at node i and node j whether to adopt the transportation mode k of the variable, is from the transportation mode k converted to the transportation mode m of the yard unit transfer cost, is the unit connection transportation cost, is from the transportation mode k converted to the transportation mode m of the transfer distance, is the goods at the nodei At this point, from the transportation mode k Switch to m The variable, Is the transfer speed, Is the transportation mode k, m The unit transfer time for transfer at the station, Is the connection distance between the container yard and the shipper / consignee warehouse, Is the connection distance between the shipper / consignee warehouse and the railway and waterway stations, Is the unit loading time, Is the unit connection transportation speed.

[0033] In specific implementation, the target optimization function aims to minimize the transportation cost and minimize the transportation time. Additionally, in specific implementation, to ensure the accuracy of optimization, certain constraint conditions can also be set. For example, it is necessary to satisfy the flow conservation constraint, where the inflow and outflow of nodes are consistent, only one transportation mode can be selected between two nodes, the transportation mode of goods can be converted at most once at a node, and when the transportation mode is converted at a node, it needs to be consistent with the transportation modes before and after the node transfer, etc.

[0034] Furthermore, encoding the initial transportation path to obtain the corresponding initial fish swarm. In the fish swarm algorithm, it is necessary to convert the actual transportation path into a form that can be processed by a computer. Each initial transportation path will be encoded into a "chromosome", which consists of a series of genes, and each gene can represent a key piece of information in the transportation path, such as a certain transportation node, the selected transportation mode, etc. For example, a path containing three transportation nodes and two transportation modes may be encoded in the form of [Node A, highway, Node B, railway, Node C]. After encoding all the initial transportation paths, the initial fish swarm is formed. Here, the "fish" is actually the encoded transportation path, and the fish swarm is the set of these paths. The initial fish swarm contains different initial path schemes generated based on preset rules, providing a rich starting point for subsequent optimization searches.

[0035] The fish swarm algorithm continuously optimizes the transportation path by simulating the foraging, schooling, and chasing behaviors of the fish swarm. After each iteration, the fitness value of each "fish" (transportation path) will be calculated using the target optimization function, and this value reflects the degree to which the path meets the optimization goal. The preset threshold is a standard set in advance. When the fitness value of a certain path in the fish swarm reaches or exceeds this threshold, it means that a high-quality path that meets the requirements has been found, and at this time, the iteration stops, and this path is the best transportation path in multimodal transportation.

[0036] In summary, the logistics management method in multimodal transportation in the above embodiments of the present invention obtains the transportation starting point and the transportation end point of the goods to be transported in multimodal transportation, and obtains the transportation nodes between the transportation starting point and the transportation end point and the transportation modes between each transportation node; according to the transportation starting point, the transportation end point, the transportation nodes and the transportation modes between each transportation node, determine the initial transportation path between the transportation starting point and the transportation end point according to a preset rule; establish an objective optimization function for the transportation of the goods to be transported, encode the initial transportation path to obtain a corresponding initial fish swarm, and use the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation. Encode the initial path to obtain an initial fish swarm and perform iterative optimization. The fish swarm algorithm simulates the behavior of a fish swarm, can continuously explore in the transportation path search space, and gradually approaches the optimal solution through multiple iterations. As the iteration progresses, each link of the transportation path (such as transportation mode selection, transfer node arrangement, etc.) is continuously adjusted to make the path more and more in line with the requirements of the objective optimization function until the fitness value meets the preset threshold, find the relatively optimal transportation path in multimodal transportation, and finally obtain a high-quality best transportation path. It solves the problem that the method for determining the optimal path in multimodal transportation in the prior art is not ideal enough.

[0037] Embodiment 2 This embodiment also proposes a logistics management method in multimodal transportation. The difference between the logistics management method in multimodal transportation in this embodiment and the logistics management method in multimodal transportation in Embodiment 1 is as follows: The step of using the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets a preset threshold includes: For each fish in the initial fish swarm, perform foraging, clustering, and chasing behaviors respectively to obtain corresponding new positions; Select the optimal target position from the corresponding new positions obtained from the foraging, clustering, and chasing behaviors according to their respective fitness values; Merge the target positions of all the fish in the initial fish swarm to form a temporary fish swarm, perform non-dominated sorting and crowding degree calculation on the temporary fish swarm, and select the first preset number of fish from the temporary fish swarm to form a new generation of fish swarm; Replace the initial fish swarm with the new generation of fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated using the transportation path meets a preset threshold.

[0038] First, for each fish in the initial fish swarm, simulate the three behaviors of real fish swarms: foraging, schooling, and following. Generate corresponding new positions respectively. The foraging behavior randomly explores the nearby area, tries to change factors such as transportation nodes and transportation modes, and generates new path variants; the schooling behavior makes the fish move closer to the area of the fish swarm with high fitness and relatively less crowded around, simulating information sharing and collective wisdom selection; the following behavior makes the fish track the path of the "leader" with the highest fitness in the current fish swarm.

[0039] Next, calculate the fitness value of each new position according to the objective optimization function. From the new positions obtained by foraging, schooling, and following, select the position with the optimal fitness value for each fish as the target position. Then, merge the target positions of all the fish in the initial fish swarm to form a temporary fish swarm containing many candidate path plans. For the temporary fish swarm, perform non-dominated sorting and crowding degree calculation: non-dominated sorting is to stratify the paths according to the domination relationship based on multi-objective optimization, and screen out the Pareto front solutions that are not dominated by other solutions; the crowding degree calculation is used to measure the density of the paths in the objective space, and retain the paths in the sparse area to maintain the diversity of the population. Based on the sorting and calculation results, select the top pre-set number of high-quality fish from the temporary fish swarm to form a new generation of fish swarm. Finally, replace the initial fish swarm with the new generation of fish swarm, repeat the above processes of simulating behaviors, selecting the optimal position, and screening the new fish swarm, and continuously perform iterative optimization on the transportation path until the fitness value of the objective optimization function calculated for a certain transportation path reaches or exceeds the pre-set threshold. At this time, the obtained path is the best transportation path plan that meets the multi-modal transportation optimization goal.

[0040] Specifically, the steps of performing foraging, schooling, and following behaviors on each fish in the initial fish swarm respectively to obtain corresponding new positions include: For each fish in the initial fish swarm, randomly select a target position within the perception range. If the target position dominates the current position of the fish, move one step towards the target position; For each fish in the initial fish swarm, find the set of partner fish within the field of vision, calculate the central position of the set of partner fish. If the central position dominates the current position of the fish, move one step towards the central position; For each fish in the initial fish swarm, find the optimal partner fish within the field of vision. If the optimal partner fish dominates the current position of the fish, move one step towards the optimal partner fish.

[0041] Among them, for the foraging behavior: each fish (transportation path) randomly selects a target position (i.e., tries a new path) within its perception range, and calculates the fitness value of the target position (such as total cost, total time, etc.). If the fitness value of the new position is better than the current position (i.e., "dominates" the current position, indicating that at least one objective is better and other objectives are not worse in multi-objective optimization), the fish moves one step towards the target position and generates a new path.

[0042] For the clustering behavior: Each fish searches for all partner fish (i.e., other paths) within its field of vision and calculates the central position of these partner fish. If the fitness value of the central position is better than the current position, the fish moves one step towards the center.

[0043] For the following behavior: Each fish searches for the partner fish with the optimal fitness value (i.e., the currently found best path) within its field of vision. If the fitness value of the optimal partner fish is better than its own, it moves one step towards it. This simulates the following of the fish school to the leader, ensuring that the algorithm can quickly converge to the known optimal area.

[0044] Through the synergistic effect of these three behaviors, the fish school continuously explores, aggregates, and follows during the iteration process, gradually approaching the global optimal solution.

[0045] Furthermore, in the actual implementation process, it is found that due to problems such as low search efficiency in the random search of the foraging behavior, over-concentration easily caused by clustering, and premature algorithm caused by a single leader (the optimal partner fish) in the following behavior, the search efficiency and accuracy are relatively low. Therefore, in some preferred embodiments of the present invention, for each fish in the initial fish school, randomly selecting a target position within the sensing range, if the target position dominates the current position of the fish, the step of moving one step towards the target position further includes: Based on the historical movement trajectory of the fish, calculate the historical optimal direction and generate a random direction, and determine the mixed direction by using the historical optimal direction and the random direction; Select a target point at a set distance in the mixed direction and use the target point as the corresponding target position; Among them, the formula for determining the mixed direction is: ; Among them, is the historical optimal direction, is the random direction, is the weight.

[0046] Specifically, based on the random selection of the target position in the feeding behavior, a hybrid mechanism of "historical optimal direction" and "random direction" is introduced. First, the algorithm analyzes the historical movement trajectories of each fish and extracts the historical optimal direction from them, that is, the direction that has the most significant improvement in fitness during past movements. This direction condenses the successful experience accumulated by the fish in the previous exploration. At the same time, a completely random direction is generated to ensure that the algorithm does not fall into local optimal solutions and maintains the ability to widely explore the search space. Subsequently, the historical optimal direction and the random direction are fused through a weighted formula, where the weight determines the influence degree of the two on the hybrid direction: the larger the weight, the stronger the guiding role of historical experience on the new direction; the smaller the weight, the more the random exploration component. After determining the hybrid direction, the algorithm selects a target point at a set distance along this direction and uses it as the new target position. The target position determined by the hybrid direction not only draws on the characteristics of the past successful path but also injects innovative exploration elements, enabling the fish swarm to efficiently utilize existing information to accelerate convergence and flexibly jump out of local optimal regions when searching for the optimal transportation path, thereby enhancing the overall optimization ability of the algorithm.

[0047] In addition, for each fish in the initial fish swarm, the step of finding the set of partner fish within the field of vision, calculating the central position of the set of partner fish, and moving one step towards the central position if the central position dominates the current position of the fish further includes: Finding the set of partner fish within the field of vision, calculating the local density for each neighbor, and calculating the comprehensive score based on the local density; Selecting the target neighbor with the highest score and moving one step towards the position of the target neighbor if the position of the target neighbor dominates the current position of the fish; Among them, the calculation formula for the comprehensive score is: ; Among them, is the fitness of the j th neighbor, is the density influence factor, is the j th neighbor's local density.

[0048] Specifically, each fish first identifies a set of partner fish within its field of vision, which are other transportation path options. Then, for each neighbor (partner fish), the algorithm calculates its "local density". This metric reflects the degree of congestion around the neighbor. The higher the local density, the more similar path options there are in the area, which may indicate that the search has fallen into a local clustering state; the lower the local density, the lower the degree of exploration in the area, suggesting the existence of potential high-quality solutions. Next, combining the "fitness" of the neighbor and the local density, a comprehensive score is calculated. Among them, the density influence factor is an adjustable parameter that determines the impact of local density on the comprehensive score. In this way, neighbors with high scores not only have good path quality (high fitness) but also are in a relatively sparse search area (low local density), achieving a dual screening of high-quality and under-explored areas. Finally, the fish selects the target neighbor with the highest score. If the fitness of its position is better than that of the current fish's position (i.e., "dominates" the current position), the fish moves one step towards the target neighbor and updates its own transportation path option. This enables the fish swarm to approach high-quality solutions using collective wisdom during the clustering process and maintain search diversity through density perception, thereby more efficiently finding the globally optimal transportation path.

[0049] When, for each fish in the initial fish swarm, looking for the optimal partner fish within the field of vision, and if the optimal partner fish dominates the current position of the fish, the step of moving one step towards the optimal partner fish further includes: Select the first k optimal individuals in the initial fish swarm as leaders, and calculate the leader fitness weights: According to the leader fitness weights and the directions of the leaders, calculate the synthesized direction and move in the synthesized direction with a preset probability.

[0050] Among them, screen out the individuals with the top k fitness values from the initial fish swarm as "leaders". These leaders represent the best-performing transportation path options in the current fish swarm. Then, calculate the fitness weights for each leader. Subsequently, the algorithm calculates a "synthesized direction" by weighted summation based on the direction of each leader (i.e., the vector from the current fish position to the leader position) and its fitness weight. This direction integrates the guidance of multiple leaders, enabling the movement direction of the current fish to no longer be limited to following a single optimal individual but rather comprehensively considering the trends of multiple high-quality paths. In this way, the following behavior in multimodal transportation path optimization can utilize the experience of multiple high-quality paths for rapid iteration and maintain the flexibility of exploration, thereby enhancing the algorithm's ability to find the globally optimal transportation path.

[0051] In summary, the logistics management method in multimodal transportation in the above embodiments of the present invention obtains the transportation starting point and the transportation ending point of the goods to be transported in multimodal transportation, and obtains the transportation nodes between the transportation starting point and the transportation ending point and the transportation modes between each transportation node; determines the initial transportation path between the transportation starting point and the transportation ending point according to the transportation starting point, the transportation ending point, the transportation nodes and the transportation modes between each transportation node according to a preset rule; establishes an objective optimization function for the transportation of the goods to be transported, encodes the initial transportation path to obtain a corresponding initial fish swarm, and uses the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated by the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation. Encoding the initial path to obtain an initial fish swarm and performing iterative optimization. The fish swarm algorithm simulates the behavior of a fish swarm, can continuously explore in the transportation path search space, and gradually approaches the optimal solution through multiple iterations. As the iteration progresses, each link of the transportation path (such as transportation mode selection, transfer node arrangement, etc.) is continuously adjusted to make the path more and more in line with the requirements of the objective optimization function until the fitness value meets the preset threshold, and a relatively optimal transportation path in multimodal transportation is found, and finally a high-quality best transportation path is obtained. It solves the problem that the method for determining the optimal path in multimodal transportation in the prior art is not ideal enough.

[0052] Embodiment III Please refer to Figure 2 , which shows the logistics management device in multimodal transportation proposed in the third embodiment of the present invention. The device includes: An acquisition module 100, configured to acquire the transportation starting point and the transportation ending point of the goods to be transported in multimodal transportation, and acquire the transportation nodes between the transportation starting point and the transportation ending point and the transportation modes between each transportation node; A determination module 200, configured to determine an initial transportation path between the transportation starting point and the transportation ending point according to the transportation starting point, the transportation ending point, the transportation nodes and the transportation modes between each transportation node according to a preset rule; A transportation module 300, configured to establish an objective optimization function for the transportation of the goods to be transported, encode the initial transportation path to obtain a corresponding initial fish swarm, and use the initial fish swarm to iteratively optimize the transportation path until the fitness value of the objective optimization function calculated by the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation.

[0053] Further, in the above-mentioned logistics management device in multimodal transportation, the first preset selection rule and the second preset selection rule both select character elements according to a preset selection order, and the selection order of the first preset rule is different from the selection order of the second preset rule.

[0054] The functions or operation steps realized when the above modules are executed are substantially the same as those in the above method embodiment, and will not be described in detail here.

[0055] Example 4 On the other hand, the present invention also provides a readable storage medium, on which a computer program is stored, and when the program is executed by a processor, the steps of the method according to any one of the above-mentioned Embodiments 1 to 2 are implemented.

[0056] Example 5 On the other hand, the present invention also provides an electronic device, which includes a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the program, the steps of the method according to any one of the above-mentioned Embodiments 1 to 2 are implemented.

[0057] The technical features of the above-mentioned various embodiments can be combined arbitrarily. For the sake of brevity of description, not all possible combinations of the technical features in the above-mentioned embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope recorded in this specification.

[0058] Those skilled in the art can understand that the logic and / or steps represented in the flowchart or described in other ways herein, for example, can be considered as a definite sequence list of executable instructions for implementing logical functions, and can be specifically implemented in any computer-readable storage medium for use by an instruction execution system, apparatus, or device (such as a computer-based system, a system including a processor, or other systems that can fetch instructions from the instruction execution system, apparatus, or device and execute the instructions), or used in combination with these instruction execution systems, apparatus, or devices. For the purposes of this specification, a "computer-readable storage medium" can be any device that can contain, store, communicate, propagate, or transport a program for use by or in connection with an instruction execution system, apparatus, or device.

[0059] More specific examples (non-exhaustive list) of computer-readable storage media include the following: an electrical connection part with one or more wirings (electronic device), a portable computer disk cartridge (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). In addition, the computer-readable storage medium can even be paper or other suitable media on which the program can be printed, because the program can be obtained electronically, for example, by optically scanning the paper or other media, then editing, interpreting, or processing it in other suitable ways as necessary, and then storing it in a computer memory.

[0060] It should be understood that the various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented by hardware, as in another embodiment, any one of the following techniques known in the art or a combination thereof can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), etc.

[0061] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0062] The above-described embodiments merely represent several implementation manners of the present invention, and their descriptions are relatively specific and detailed, but should not be construed as limiting the scope of the patent of the present invention. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present invention, several modifications and improvements can still be made, and these all belong to the protection scope of the present invention. Therefore, the protection scope of the patent of the present invention should be subject to the appended claims.

Claims

1. A logistics management method in multimodal transport, characterized in that, The method includes: Obtaining the transport origin and transport destination of the goods to be transported in multimodal transport, and obtaining the transport nodes between the transport origin and transport destination and the transport modes between each transport node; Determining an initial transport path between the transport origin and transport destination according to the transport origin, transport destination, transport nodes and the transport modes between each transport node according to a preset rule; Establishing an objective optimization function for the transport of the goods to be transported, encoding the initial transport path to obtain a corresponding initial fish swarm, and using the initial fish swarm to iteratively optimize the transport path until the fitness value of the objective optimization function calculated using the transport path meets a preset threshold, so as to obtain the best transport path in multimodal transport.

2. The logistics management method in multimodal transport according to claim 1, characterized in that, The step of using the initial fish swarm to iteratively optimize the transport path until the fitness value of the objective optimization function calculated using the transport path meets a preset threshold includes: Performing foraging, schooling and chasing behaviors on each fish in the initial fish swarm respectively to obtain corresponding new positions; Selecting the optimal target position from the corresponding new positions obtained from the foraging, schooling and chasing behaviors according to their respective fitness values; Merging the target positions of all the fish in the initial fish swarm to form a temporary fish swarm, performing non-dominated sorting and crowding degree calculation on the temporary fish swarm, and selecting the first preset number of fish from the temporary fish swarm to form a new generation of fish swarm; Replacing the initial fish swarm with the new generation of fish swarm to iteratively optimize the transport path until the fitness value of the objective optimization function calculated using the transport path meets a preset threshold.

3. The logistics management method in multimodal transport according to claim 2, characterized in that, The step of performing foraging, schooling and chasing behaviors on each fish in the initial fish swarm respectively to obtain corresponding new positions includes: For each fish in the initial fish swarm, randomly select a target position within the sensing range. If the target position dominates the current position of the fish, move one step towards the target position; For each fish in the initial fish swarm, find the set of partner fish within the field of view, calculate the central position of the set of partner fish. If the central position dominates the current position of the fish, move one step towards the central position; For each fish in the initial fish swarm, find the optimal partner fish within the field of view. If the optimal partner fish dominates the current position of the fish, move one step towards the optimal partner fish.

4. The logistics management method in multimodal transport according to claim 3, characterized in that The step of for each fish in the initial fish swarm, randomly select a target position within the sensing range. If the target position dominates the current position of the fish, move one step towards the target position further includes: Based on the historical movement trajectory of the fish, calculate the historical optimal direction and generate a random direction, and use the historical optimal direction and the random direction to determine the mixed direction; Select a target point at a set distance in the mixed direction and use the target point as the corresponding target position; Among them, the formula for determining the mixed direction is: ； Among them, is the historical optimal direction, is the random direction, is the weight.

5. The logistics management method in multimodal transport according to claim 4, characterized in that, The step of for each fish in the initial fish swarm, find the set of partner fish within the field of view, calculate the central position of the set of partner fish. If the central position dominates the current position of the fish, move one step towards the central position further includes: Find the set of partner fish within the field of view, calculate the local density for each neighbor, and calculate the comprehensive score according to the local density; Select the target neighbor with the highest score. If the position of the target neighbor dominates the current position of the fish, move one step towards the position of the target neighbor; Among them, the calculation formula of the comprehensive score is as follows: ； Among them, is the fitness of the j th neighbor, is the density influence factor, is the j th local density of the neighbor.

6. The logistics management method in multimodal transport according to claim 5, characterized in that, For each fish in the initial fish school, to find the optimal partner fish within the field of vision, if the optimal partner fish dominates the current position of the fish, the step of moving one step towards the optimal partner fish further includes: Select the first k optimal individuals in the initial fish swarm as leaders, and calculate the fitness weights of the leaders: Calculate the synthetic direction according to the leader fitness weight and the direction of the leader, and move in the synthetic direction with a preset probability.

7. The logistics management method in multimodal transport according to claim 1, characterized in that, The expression of the objective optimization function is: ； ； Among them, is the transportation cost objective function, is the transportation time objective function, i and j respectively represent nodes, k represents the transportation mode, represents the quantity of transported containers, is the unit transportation cost of the transportation mode k ; is the distance between the goods at node i and node j ; is the variable indicating whether the transportation mode i is adopted between the goods at node j and node k ; is the yard unit transfer cost for converting from transportation mode k to transportation mode m ; is the unit feeder transportation cost, is the transfer distance for converting from transportation mode k to transportation mode m ; is the variable for the goods to switch from transportation mode i to k at node m ; is the transfer speed, is the unit transfer time for the transportation mode k, m to switch at the yard, is the feeder distance between the container yard and the shipper / consignee warehouse, is the feeder distance between the shipper / consignee warehouse and the railway / waterway yard, is the unit loading time, is the unit feeder transportation speed.

8. A logistics management device in multimodal transport, characterized in that, The device includes: An acquisition module, configured to acquire the transportation starting point and the transportation ending point of the goods to be transported in multimodal transportation, and acquire the transportation nodes between the transportation starting point and the transportation ending point and the transportation modes between each transportation node; A determination module, configured to determine the initial transportation path between the transportation starting point and the transportation ending point according to the transportation starting point, the transportation ending point, the transportation nodes, and the transportation modes between each transportation node according to a preset rule; A transportation module, configured to establish an objective optimization function for transporting the goods to be transported, encode the initial transportation path to obtain a corresponding initial fish school, and iteratively optimize the transportation path by using the initial fish school until the fitness value of the objective optimization function calculated by using the transportation path meets a preset threshold, so as to obtain the best transportation path in multimodal transportation.

9. A readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by a processor, it implements the steps of the method according to any one of claims 1 to 7.

10. An electronic device, characterized in that, It includes a memory, a processor, and a computer program stored on the memory and running on the processor. When the processor executes the program, it implements the steps of the method according to any one of claims 1 to 7.

Images