An international logistics multimodal transport path recommendation method and system

Abstract

This invention discloses a method and system for recommending multimodal transport routes in international logistics, belonging to the field of logistics route recommendation technology. By acquiring order task data and transportation data, a set of multimodal transport routes is determined. Minimizing total cost and minimizing the comprehensive transportation risk coefficient are used as optimization objectives to construct a multi-objective route optimization model. A hybrid intelligent optimization algorithm is used to select routes from the multimodal transport route set, resulting in multiple intermodal transport route schemes. These schemes include complete routes from the origin node to the destination node and the combinations of transportation modes used. The optimal recommended route is determined from these schemes based on customer preferences. This invention, through multimodal transport data, can flexibly recommend suitable combinations of transportation modes based on order task data, effectively shortening international logistics arrival times. Furthermore, by constructing a multi-objective route optimization model, the recommended routes possess stronger robustness and reliability.

Description

Technical Field

[0001] This invention belongs to the field of logistics route recommendation technology, specifically relating to a method and system for recommending international multimodal transport routes. Background Technology

[0002] Multimodal transport is a transportation process jointly completed by the interconnection and transshipment of two or more modes of transport, collectively known as combined transport. International multimodal transport contracts stipulate the use of at least two different modes of transport, with the multimodal transport operator transporting goods from a point of acceptance within one country to a designated point of delivery within another country. Currently, international container multimodal transport integrates multiple modes of transport to form a complete transport chain, making it a highly efficient form of transport organization. However, due to the characteristics of international container multimodal transport—long distances, wide scope, and numerous intermediate links—it faces various uncertainties and risks during transport. Accidents can cause significant economic losses. Furthermore, existing technologies in multimodal transport often focus on a single objective, leading to risks such as transport delays, affecting transport costs and timeliness, and thus impacting the arrival time of international logistics.

[0003] Therefore, how to provide an effective technical solution to address the various uncertainties and risks encountered in the transportation process and the technical problems affecting the arrival time of international logistics in existing technologies has become an urgent problem to be solved in existing technologies. Summary of the Invention

[0004] The purpose of this invention is to provide a method and system for recommending international multimodal transport routes, in order to solve the above-mentioned problems existing in the prior art.

[0005] To achieve the above objectives, the present invention adopts the following technical solution: In a first aspect, the present invention provides a method for recommending international multimodal transport routes, including: Obtain international logistics transportation order task data, which includes node data and cargo data, and the node data includes origin node, transit node and destination node; The transport data of multimodal transport includes multiple transport nodes, transport arcs connecting the transport nodes, at least one transport mode corresponding to each transport arc, and the transport cost, transport time and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing the risk factors. Based on order task data and transportation data, a set of multimodal transport routes is determined, and a multi-objective route optimization model is constructed with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to select paths from the multimodal transport path set, resulting in multiple intermodal transport path schemes. These multiple intermodal transport path schemes include the complete path from the origin node to the destination node and the combination of transport modes used in each transport segment. The optimal recommended route is determined from multiple intermodal transport options based on customer preferences.

[0006] In one possible design, the mode of transport includes at least two or more of the following: road transport, rail transport, water transport, and air transport. The risk factors include general risks and regional conflict risks. The general risks include infrastructure risks, environmental risks, cargo damage risks, and node congestion risks. The regional conflict risks include transportation delay risks and operation suspension risks.

[0007] In one possible design, the quantitative assessment process of the comprehensive transportation risk coefficient includes: Acquire historical risk event data and regional conflict event data, and construct a risk assessment indicator system based on the historical risk event data and regional conflict event data; Based on the risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation segment. For each transit node and transportation arc, the risk coefficient of each risk factor is calculated based on the probability level and impact level, and the risk coefficient of each risk factor is normalized to obtain the comprehensive risk coefficient of the transit node and transportation arc.

[0008] In one possible design, based on a risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation segment, including: Based on the preset risk level, the risk assessment indicators in the risk assessment indicator system are classified into levels to obtain the classified risk assessment indicator system. Probability statistics are performed on historical risk event data and regional conflict event data for each transit node and transportation arc to obtain the historical cargo damage probability and historical transportation delay risk probability for each transit node and transportation arc. Furthermore, data statistics are performed on cost increase data or time increase data caused by risk events for each transit node and transportation arc to obtain the cost increase value or time increase value caused by risk events for each transit node and transportation arc. Based on the risk assessment index system after classification, the historical cargo damage probability and historical transportation delay risk probability of each transit node and transportation arc are evaluated to obtain the occurrence probability level corresponding to each transit node and transportation arc. Based on the risk assessment index system after classification, the cost increase or time increase caused by risk events for each transit node and transportation arc is evaluated to obtain the impact level corresponding to each transit node and transportation arc.

[0009] In one possible design, based on a multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to select paths from a set of multimodal transport paths, resulting in multiple intermodal transport path schemes, including: Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to screen the set of multimodal transport paths. The screened multimodal transport paths are used as path chromosomes, and multiple path chromosomes are used as the initial population. Multiple path chromosomes in the initial population are encoded to divide the path chromosomes into domestic path chromosomes and foreign path chromosomes, with the domestic path chromosomes corresponding to domestic transit cities and domestic ports of entry, respectively. A multimodal transport directed network graph is constructed based on the overseas route chromosome, and the initial in-degree of each node in the multimodal transport directed network graph is calculated. Nodes with an initial in-degree of zero are added to a preset sorting sequence in sequence, and the in-degree of their adjacent nodes is updated after each addition, until a topological sorting sequence from the port of exit to the destination node is generated. Based on the topological sorting sequence, multiple intermodal transport route schemes are selected from the set of multimodal transport routes.

[0010] In one possible design, based on a multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to filter the set of multimodal transport paths, including: A fitness function is constructed based on a multi-objective path optimization model. The fitness value corresponding to each multimodal transport path in the multimodal transport path set is calculated based on the fitness function. Based on the fitness value of each multimodal transport route, the multimodal transport routes are sorted in descending order, and multimodal transport routes are selected as elite chromosomes based on a preset quantity ratio. Using a roulette wheel approach, supplementary chromosomes are selected from the remaining multimodal transport routes. The elite chromosome and the supplementary chromosome are merged to obtain a composite chromosome. Crossover and mutation operations are then performed on the composite chromosome to screen the newly generated population. The selected multimodal transport routes are used as the route chromosomes.

[0011] In one possible design, the order task data further includes a hybrid arrival time window, which includes an allowed arrival time window and a desired arrival time window; The multi-objective path optimization model also includes a hybrid time window constraint, which includes: When the arrival time of goods exceeds the allowed arrival time window, the multimodal transport route corresponding to the goods is deemed invalid; Storage and storage costs are incurred when the arrival time of goods is earlier than the lower limit of the expected arrival time window, but within the allowed arrival time window. When the arrival time of goods is later than the upper limit of the expected arrival time window, but within the allowed arrival time window, a delay penalty cost is incurred. No additional costs are incurred if the goods arrive within the expected arrival time window.

[0012] Secondly, the present invention provides an international logistics multimodal transport route recommendation system, comprising: The first acquisition module is used to acquire international logistics transportation order task data, which includes node data and cargo data. The node data includes the origin node, transit node and destination node. The second acquisition module is used to acquire multimodal transport data. The transport data includes multiple transport nodes, transport arcs connecting each transport node, at least one transport mode corresponding to each transport arc, and transport cost, transport time, and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing risk factors. The model building module is used to determine the set of multimodal transport routes based on order task data and transportation data, and to construct a multi-objective route optimization model with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. The route selection module is used to select routes from a set of multimodal transport routes based on a multi-objective route optimization model and a hybrid intelligent optimization algorithm, resulting in multiple intermodal transport route schemes. The multiple intermodal transport route schemes include a complete route from the origin node to the destination node and a combination of transport modes used in each transport segment. The route recommendation module is used to determine the optimal recommended route from multiple intermodal route options based on customer preferences.

[0013] Thirdly, the present invention provides an international logistics multimodal transport route recommendation device, comprising a memory, a processor, and a transceiver connected in sequence and communication, wherein the memory is used to store a computer program, the transceiver is used to send and receive messages, and the processor is used to read the computer program and execute the international logistics multimodal transport route recommendation method as described in the first aspect above.

[0014] Fourthly, the present invention provides a computer-readable storage medium storing instructions that, when executed on a computer, perform the international logistics multimodal transport route recommendation method as described in the first aspect above.

[0015] Fifthly, the present invention provides a computer program product containing instructions that, when executed on a computer, cause the computer to perform the international logistics multimodal transport route recommendation method as described in the first aspect above.

[0016] The beneficial effects of this invention are as follows: This invention discloses a method and system for recommending multimodal transport routes in international logistics. It acquires order task data and multimodal transport data for international logistics transportation. Based on this data, it determines a set of multimodal transport routes and constructs a multi-objective route optimization model, using minimizing total cost and minimizing the comprehensive transport risk coefficient as optimization objectives. Based on this model, a hybrid intelligent optimization algorithm is used to select routes from the multimodal transport route set, resulting in multiple route schemes. These schemes include complete routes from the origin node to the destination node and combinations of transport modes used in each transport segment. The optimal recommended route is determined from these schemes based on customer preferences. This invention, through multimodal transport data, can flexibly recommend suitable transport mode combinations based on order task data, meeting the diverse needs of different goods and effectively shortening international logistics arrival times. Furthermore, by constructing a multi-objective route optimization model, it considers both economy and safety during route recommendation, solving the technical problems of existing technologies that focus only on a single objective or ignore regional conflict risks. This makes the recommended routes more robust and reliable in complex international environments, facilitating application and promotion. Attached Figure Description

[0017] Figure 1 A flowchart of an international logistics multimodal transport route recommendation method provided in an embodiment of the present invention; Figure 2 A block diagram of an international logistics multimodal transport route recommendation system provided in an embodiment of the present invention; Figure 3 This is a structural block diagram of the international logistics multimodal transport route recommendation device provided in an embodiment of the present invention. Detailed Implementation

[0018] To more clearly illustrate the technical solutions in the embodiments of the present invention or the prior art, the present invention will be briefly introduced below in conjunction with the accompanying drawings and descriptions of the embodiments or the prior art. Obviously, the following description of the structure of the accompanying drawings is only some embodiments of the present invention. For those skilled in the art, other drawings can be obtained based on these drawings without creative effort. It should be noted that the description of these embodiments is for the purpose of helping to understand the present invention, but does not constitute a limitation of the present invention.

[0019] It should be understood that although the terms first, second, etc., may be used herein to describe various units, these units should not be limited by these terms. These terms are only used to distinguish one unit from another. For example, a first unit may be referred to as a second unit, and similarly, a second unit may be referred to as a first unit, without departing from the scope of the exemplary embodiments of the invention.

[0020] It should be understood that the term "and / or" that may appear in this document is merely a description of the relationship between related objects, indicating that three relationships can exist. For example, A and / or B can mean: A exists alone, B exists alone, and A and B exist simultaneously. The term " / and" that may appear in this document describes another relationship between related objects, indicating that two relationships can exist. For example, A / and B can mean: A exists alone, and A and B exist alone. In addition, the character " / " that may appear in this document generally indicates that the related objects before and after it are in an "or" relationship.

[0021] Example: like Figure 1 As shown, the first aspect of this embodiment provides a method for recommending international multimodal transport routes, which can be executed, but is not limited to, by a computer device or virtual machine with certain computing resources, such as a personal computer or smartphone, or by a virtual machine; the method for recommending international multimodal transport routes includes, but is not limited to, the following steps: S1. Obtain international logistics transportation order task data, the order task data including node data and cargo data, the node data including origin node, transit node and destination node; In specific implementation, the order task data also includes a mixed arrival time window, which includes an allowed arrival time window and a desired arrival time window. The cargo data includes cargo type and cargo value information. In this embodiment, the order data is obtained from the platform based on customer orders placed on the platform. The order data is extracted to obtain order task data, which includes node data, cargo data, and a mixed arrival time window. The node data is used to represent the origin and destination of the cargo. The cargo data is used to represent the type of cargo that the customer needs to transport, cargo value information, and cargo weight, etc. The cargo type is used to distinguish the sensitivity of different cargoes to transportation timeliness. The mixed arrival time window is used to represent the earliest acceptable cargo arrival time, the latest acceptable cargo arrival time, the desired earliest cargo arrival time, and the desired latest cargo arrival time.

[0022] S2. Obtain multimodal transport data, which includes multiple transport nodes, transport arcs connecting each transport node, at least one transport mode corresponding to each transport arc, and transport cost, transport time, and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing risk factors. It should be noted that the transportation modes include at least two or more combinations of road transportation, rail transportation, water transportation, and air transportation; the risk factors include general risks and regional conflict risks. General risks include infrastructure risks, environmental risks, cargo damage risks, and node congestion risks. Regional conflict risks include transportation delay risks and operation suspension risks. Specifically, general risks refer to routine risks, while regional conflict risks refer to sudden risks. This embodiment acquires transportation data including multiple transportation modes such as road, rail, water, and air, and supports combinations of various transportation modes such as waterway and road transport, waterway and rail transport, air and road transport, air and rail transport, and rail and road transport. It can flexibly recommend suitable transportation mode combinations based on cargo type, customer's expected delivery time, and cargo value information, meeting the different needs of diverse goods for transportation timeliness and cost, and effectively shortening the arrival time of international logistics.

[0023] Specifically, in step S2, the quantitative assessment process of the comprehensive transportation risk coefficient includes: S21. Obtain historical risk event data and regional conflict event data, and construct a risk assessment indicator system based on the historical risk event data and regional conflict event data; S22. Based on the risk assessment index system, determine the probability level and impact level of each risk factor for each transit node and transportation segment; S23. For each transit node and transportation arc, calculate the risk coefficient of each risk factor according to the probability level and impact level, and normalize the risk coefficient of each risk factor to obtain the comprehensive risk coefficient of the transit node and transportation arc.

[0024] It is important to note that after acquiring historical risk event data and regional conflict event data from the online platform, these data undergo preprocessing to remove anomalies and blank events. Subsequently, a risk assessment indicator system is constructed based on this data. This system includes multiple risk assessment indicators. According to this system, the probability level and impact level of each risk factor are determined for each transit node and transportation arc. The probability level characterizes the likelihood of the corresponding risk occurring at that transit node or transportation arc, while the impact level... The risk level is used to characterize the probability of the corresponding risk occurring at the transit node or transportation arc affecting the cargo transportation. By collecting and analyzing historical risk event data and regional conflict event data, an evaluation index system covering multi-dimensional risk factors is constructed, laying the foundation for subsequent risk level determination and coefficient calculation. Subsequently, the occurrence probability level and impact level of each risk factor are determined for each transit node and transportation arc. By calculating the product of the occurrence probability level and impact level, the risk coefficient of each risk factor is obtained. After normalization, the comprehensive risk coefficient is obtained, thereby transforming the qualitative risk description into a quantitative indicator and ensuring the comparability and consistency of risk assessment results.

[0025] In practice, the first step is to collect historical risk event data from official authoritative databases, news media, or historical transportation records, covering infrastructure failure reports, natural disaster records, cargo damage cases, node congestion, and regional conflict-related events. This data is then categorized and organized according to transit nodes and transportation arcs to construct a risk assessment index system. Subsequently, based on this risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation arc. The risk coefficient of each risk factor is calculated based on the product of the probability level and the impact level. The risk coefficients of all risk factors are then normalized to eliminate dimensional differences, thereby obtaining the comprehensive transportation risk coefficient for that transit node or transportation arc.

[0026] Furthermore, in step S22, based on the risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation segment, including: S22.1. Based on the preset risk level, classify the risk assessment indicators in the risk assessment indicator system to obtain the classified risk assessment indicator system; S22.2. Perform probability statistics on historical risk event data and regional conflict event data for each transit node and transportation arc to obtain the historical cargo damage probability and historical transportation delay risk probability corresponding to each transit node and transportation arc. Perform data statistics on cost increase data or time increase data based on risk events for each transit node and transportation arc to obtain the cost increase value or time increase value based on risk events corresponding to each transit node and transportation arc. S22.3. Based on the risk assessment index system after classification, the historical cargo damage probability and historical transportation delay risk probability of each transit node and transportation arc are evaluated to obtain the occurrence probability level corresponding to each transit node and transportation arc. S22.4. Based on the risk assessment index system after grading, evaluate the cost increase or time increase caused by risk events for each transit node and transportation arc to obtain the impact level corresponding to each transit node and transportation arc.

[0027] In practice, each risk factor is classified according to a pre-set classification standard. For example, the probability of occurrence is classified into 1 to 5 levels, and the impact level is classified into 1 to 5 levels. For each transit node and transportation segment, the probability of historical cargo damage and the probability of historical transportation delay are calculated using probability statistics. Data is also collected based on the percentage increase in cost or the increase in time caused by the risk event. Then, the classified risk assessment index system is used to compare the statistically obtained probability data and cost or time increase data with the classification standard to determine the probability of occurrence and the impact level of each risk factor.

[0028] S3. Based on order task data and transportation data, determine the set of multimodal transport routes, and construct a multi-objective route optimization model with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. In a preferred embodiment, the multi-objective path optimization model further includes a hybrid time window constraint, which includes: When the arrival time of goods exceeds the allowed arrival time window, the multimodal transport route corresponding to the goods is deemed invalid; Storage and storage costs are incurred when the arrival time of goods is earlier than the lower limit of the expected arrival time window, but within the allowed arrival time window. When the arrival time of goods is later than the upper limit of the expected arrival time window, but within the allowed arrival time window, a delay penalty cost is incurred. No additional costs are incurred if the goods arrive within the expected arrival time window.

[0029] In practice, when the arrival time of goods exceeds the allowed arrival time window, the multimodal transport route is deemed unacceptable and invalid, and will not be selected in subsequent steps. When the arrival time of goods is earlier than the lower limit of the expected arrival time window but within the allowed arrival time window, the goods need to be stored, incurring corresponding warehousing and storage costs. When the arrival time of goods is later than the upper limit of the expected arrival time window but within the allowed arrival time window, it will cause inconvenience to customers, resulting in corresponding delay penalty costs. No additional costs are incurred only when the arrival time of goods is within the expected arrival time window.

[0030] S4. Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to select paths from the multimodal transport path set to obtain multiple intermodal transport path schemes. The multiple intermodal transport path schemes include the complete path from the starting node to the destination node and the combination of transport modes used in each transport segment. Specifically, in step S4, based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to select paths from the multimodal transport path set, resulting in multiple intermodal transport path schemes, including: S41. Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to screen the multimodal transport path set, and the screened multimodal transport paths are used as path chromosomes, and multiple path chromosomes are used as the initial population. S42. Encode multiple path chromosomes in the initial population to divide the path chromosomes into domestic path chromosomes and foreign path chromosomes, wherein the domestic path chromosomes correspond to domestic transit cities and domestic ports, respectively. S43. Construct a multimodal transport directed network graph based on the overseas route chromosome, calculate the initial in-degree of each node in the multimodal transport directed network graph, add the nodes with an initial in-degree of zero to the preset sorting sequence in sequence, and update the in-degree of its neighboring nodes after each addition, until a topological sorting sequence from the port of exit to the destination node is generated. S44. Based on the topological sorting sequence, select multiple intermodal transport route schemes from the set of multimodal transport routes.

[0031] In specific implementation, the multimodal transport path set is first screened based on a multi-objective path optimization model, and the screened multimodal transport paths are used as path chromosomes. Multiple path chromosomes are combined to form an initial population. Then, each path chromosome in the initial population is encoded to split it into domestic path chromosomes and foreign path chromosomes. The domestic path chromosomes include domestic transit cities and domestic port information, while the foreign path chromosomes include foreign transport nodes from the departure port to the destination node. For foreign path chromosomes, a multimodal transport directed network graph is constructed, and the initial in-degree of each node in the multimodal transport directed network graph is calculated. Nodes with an initial in-degree of zero are added to a preset sorting sequence in sequence, and the in-degree of its neighboring nodes is updated after each node is added. The above addition and update process is repeated until a complete topological sorting sequence is generated, ensuring that each generated chromosome corresponds to a feasible path from the departure port to the destination node. Based on the topological sorting sequence, multiple multimodal transport path schemes are selected from the multimodal transport solution set. This embodiment can effectively simplify the search space, avoid interference from invalid solutions, and improve the solution efficiency and solution quality of the algorithm.

[0032] Furthermore, in step S41, based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to filter the multimodal transport path set, including: S41.1. Construct a fitness function, which is based on a multi-objective path optimization model. Calculate the fitness value corresponding to each multimodal transport path in the multimodal transport path set based on the fitness function. S41.2. Based on the fitness values ​​corresponding to each multimodal transport route, sort each multimodal transport route in descending order, and select multimodal transport routes as elite chromosomes based on a preset quantity ratio. S41.3. Using the roulette wheel method, select supplementary chromosomes from the remaining multimodal transport paths, merge the elite chromosomes and supplementary chromosomes to obtain a composite chromosome, and perform crossover and mutation operations on the composite chromosome to screen the newly generated population, and use the screened multimodal transport paths as path chromosomes.

[0033] In practice, a fitness function is first constructed based on a multi-objective path optimization model. The fitness value of a multimodal transport path is determined by its lower total cost and integrated transportation risk. For each multimodal transport path in the set, its corresponding fitness value is calculated. All multimodal transport paths are then sorted in descending order based on their fitness values. The top-ranked paths are selected as elite chromosomes according to a predetermined ratio, and these elite individuals are directly added to the next generation population. For the remaining paths, a roulette wheel selection method is used. Specifically, the probability of each individual being selected is calculated by determining the proportion of its fitness value to the sum of the fitness values ​​of all remaining individuals. Random numbers are generated to simulate the roulette wheel's rotation and multiple selections are made until the predetermined number of chromosomes is reached, resulting in supplementary chromosomes. The process involves merging elite chromosomes with supplementary chromosomes to obtain a composite chromosome. Partial crossover is then performed based on a preset crossover probability, randomly exchanging chromosome segments and repairing duplicate genes. Next, a dynamic mixed neighborhood search is conducted on a portion of the chromosomes using a preset mutation probability, including insertion and reversal neighborhood operations, to generate a new population. This newly generated population is then screened. In this embodiment, the preset number ratio is 10%, the preset crossover probability ranges from 60% to 90%, and the preset mutation probability ranges from 10% to 20%. An elite retention strategy ensures that superior individuals are not destroyed by subsequent operations, while a roulette wheel algorithm maintains population diversity. New individuals are generated through crossover and mutation operations, expanding the search range and enabling the population to continuously evolve.

[0034] S5. Determine the optimal recommended route from multiple intermodal transport options based on customer preferences.

[0035] It should be noted that the selection of intermodal transport routes can be made by obtaining customers' keyword preferences on the platform, or customers can choose the optimal recommended route from multiple intermodal transport routes themselves.

[0036] like Figure 2 As shown, the second aspect of this embodiment provides an international logistics multimodal transport route recommendation system, including: The first acquisition module is used to acquire international logistics transportation order task data, which includes node data and cargo data. The node data includes the origin node, transit node and destination node. The second acquisition module is used to acquire multimodal transport data. The transport data includes multiple transport nodes, transport arcs connecting each transport node, at least one transport mode corresponding to each transport arc, and transport cost, transport time, and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing risk factors. The model building module is used to determine the set of multimodal transport routes based on order task data and transportation data, and to construct a multi-objective route optimization model with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. The route selection module is used to select routes from a set of multimodal transport routes based on a multi-objective route optimization model and a hybrid intelligent optimization algorithm, resulting in multiple intermodal transport route schemes. The multiple intermodal transport route schemes include a complete route from the origin node to the destination node and a combination of transport modes used in each transport segment. The route recommendation module is used to determine the optimal recommended route from multiple intermodal route options based on customer preferences.

[0037] The working process, working details and technical effects of the international logistics multimodal transport route recommendation system provided in the second aspect of this embodiment can be found in the international logistics multimodal transport route recommendation method described in the first aspect, and will not be repeated here.

[0038] like Figure 3 As shown, the third aspect of this embodiment provides an international logistics multimodal transport route recommendation device, including a memory, a processor, and a transceiver connected in sequence. The memory stores a computer program, the transceiver sends and receives messages, and the processor reads the computer program and executes the international logistics multimodal transport route recommendation method as described in the first aspect. Specifically, the memory may include, but is not limited to, random-access memory (RAM), read-only memory (ROM), flash memory, first-in-first-out (FIFO) memory, and / or first-in-last-out (FILO) memory, etc.; the processor may include, but is not limited to, an STM32F105 series microprocessor. Furthermore, the international logistics multimodal transport route recommendation device may also include, but is not limited to, a power module, a display screen, and other necessary components.

[0039] The working process, working details and technical effects of the aforementioned international logistics multimodal transport route recommendation device provided in the third aspect of this embodiment can be found in the international logistics multimodal transport route recommendation method described in the first aspect, and will not be repeated here.

[0040] The fourth aspect of this embodiment provides a computer-readable storage medium, wherein the computer-readable storage medium stores instructions, and when the instructions are executed on a computer, the international logistics multimodal transport route recommendation method as described in the first aspect is performed. The computer-readable storage medium refers to a carrier for storing data, and may include, but is not limited to, computer-readable storage media such as floppy disks, optical disks, hard disks, flash memory, USB flash drives, and / or Memory Sticks. The computer may be a general-purpose computer, a special-purpose computer, a computer network, or other programmable devices.

[0041] The working process, working details and technical effects of the aforementioned computer-readable storage medium provided in the fourth aspect of this embodiment can be found in the international logistics multimodal transport route recommendation method as described in the first aspect, and will not be repeated here.

[0042] The fifth aspect of this embodiment provides a computer program product, including a computer program or instructions, which, when executed by a computer, are used to implement the international logistics multimodal transport route recommendation method as described in the first aspect.

[0043] The working process, working details, and technical effects of the aforementioned computer program product provided in this embodiment can be found in the international logistics multimodal transport route recommendation method described in the first aspect, and will not be repeated here.

[0044] Finally, it should be noted that the above description is merely a preferred embodiment of the present invention and is not intended to limit the scope of protection of the present invention. Any modifications, equivalent substitutions, improvements, etc., made within the spirit and principles of the present invention should be included within the scope of protection of the present invention.

Claims

1. An international logistics multimodal transport path recommendation method characterized by, include: Obtain international logistics transportation order task data, which includes node data and cargo data, and the node data includes origin node, transit node and destination node; The transport data of multimodal transport includes multiple transport nodes, transport arcs connecting the transport nodes, at least one transport mode corresponding to each transport arc, and the transport cost, transport time and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing the risk factors. Based on order task data and transportation data, a set of multimodal transport routes is determined, and a multi-objective route optimization model is constructed with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to select paths from the multimodal transport path set, resulting in multiple intermodal transport path schemes. These multiple intermodal transport path schemes include the complete path from the origin node to the destination node and the combination of transport modes used in each transport segment. The optimal recommended route is determined from multiple intermodal transport options based on customer preferences.

2. The international logistics multimodal transport path recommendation method according to claim 1, characterized in that, The mode of transport includes at least two or more of the following: road transport, rail transport, water transport, and air transport. The risk factors include general risks and regional conflict risks. The general risks include infrastructure risks, environmental risks, cargo damage risks, and node congestion risks. The regional conflict risks include transportation delay risks and operation suspension risks. 3.The international logistics multimodal transport path recommendation method of claim 1, wherein, The quantitative assessment process for the comprehensive transportation risk coefficient includes: Acquire historical risk event data and regional conflict event data, and construct a risk assessment indicator system based on the historical risk event data and regional conflict event data; Based on the risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation segment. For each transit node and transportation arc, the risk coefficient of each risk factor is calculated based on the probability level and impact level, and the risk coefficient of each risk factor is normalized to obtain the comprehensive risk coefficient of the transit node and transportation arc.

4. The method for recommending international multimodal transport routes according to claim 3, characterized in that, Based on the risk assessment index system, the probability level and impact level of each risk factor are determined for each transit node and transportation segment, including: Based on the preset risk level, the risk assessment indicators in the risk assessment indicator system are classified into levels to obtain the classified risk assessment indicator system. Probability statistics are performed on historical risk event data and regional conflict event data for each transit node and transportation arc to obtain the historical cargo damage probability and historical transportation delay risk probability for each transit node and transportation arc. Furthermore, data statistics are performed on cost increase data or time increase data caused by risk events for each transit node and transportation arc to obtain the cost increase value or time increase value caused by risk events for each transit node and transportation arc. Based on the risk assessment index system after classification, the historical cargo damage probability and historical transportation delay risk probability of each transit node and transportation arc are evaluated to obtain the occurrence probability level corresponding to each transit node and transportation arc. Based on the risk assessment index system after classification, the cost increase or time increase caused by risk events for each transit node and transportation arc is evaluated to obtain the impact level corresponding to each transit node and transportation arc.

5. The method for recommending international multimodal transport routes according to claim 1, characterized in that, Based on a multi-objective route optimization model, a hybrid intelligent optimization algorithm is used to select routes from a set of multimodal transport routes, resulting in multiple intermodal transport route schemes, including: Based on the multi-objective path optimization model, a hybrid intelligent optimization algorithm is used to screen the set of multimodal transport paths. The screened multimodal transport paths are used as path chromosomes, and multiple path chromosomes are used as the initial population. Multiple path chromosomes in the initial population are encoded to divide the path chromosomes into domestic path chromosomes and foreign path chromosomes, with the domestic path chromosomes corresponding to domestic transit cities and domestic ports of entry, respectively. A multimodal transport directed network graph is constructed based on the overseas route chromosome, and the initial in-degree of each node in the multimodal transport directed network graph is calculated. Nodes with an initial in-degree of zero are added to a preset sorting sequence in sequence, and the in-degree of their adjacent nodes is updated after each addition, until a topological sorting sequence from the port of exit to the destination node is generated. Based on the topological sorting sequence, multiple intermodal transport route schemes are selected from the set of multimodal transport routes.

6. The method for recommending international multimodal transport routes according to claim 5, characterized in that, Based on a multi-objective route optimization model, a hybrid intelligent optimization algorithm is used to filter the set of multimodal transport routes, including: A fitness function is constructed based on a multi-objective path optimization model. The fitness value corresponding to each multimodal transport path in the multimodal transport path set is calculated based on the fitness function. Based on the fitness value of each multimodal transport route, the multimodal transport routes are sorted in descending order, and multimodal transport routes are selected as elite chromosomes based on a preset quantity ratio. Using a roulette wheel approach, supplementary chromosomes are selected from the remaining multimodal transport routes. The elite chromosome and the supplementary chromosome are merged to obtain a composite chromosome. Crossover and mutation operations are then performed on the composite chromosome to screen the newly generated population. The selected multimodal transport routes are used as the route chromosomes.

7. The method for recommending international multimodal transport routes according to claim 1, characterized in that, The order task data also includes a mixed arrival time window, which includes an allowed arrival time window and a desired arrival time window; The multi-objective path optimization model also includes a hybrid time window constraint, which includes: When the arrival time of goods exceeds the allowed arrival time window, the multimodal transport route corresponding to the goods is deemed invalid; Storage and storage costs are incurred when the arrival time of goods is earlier than the lower limit of the expected arrival time window, but within the allowed arrival time window. When the arrival time of goods is later than the upper limit of the expected arrival time window, but within the allowed arrival time window, a delay penalty cost is incurred. No additional costs are incurred if the goods arrive within the expected arrival time window.

8. An international logistics multimodal transport route recommendation system, used to implement the method according to any one of claims 1 to 7, characterized in that, include: The first acquisition module is used to acquire international logistics transportation order task data, which includes node data and cargo data. The node data includes the origin node, transit node and destination node. The second acquisition module is used to acquire multimodal transport data. The transport data includes multiple transport nodes, transport arcs connecting each transport node, at least one transport mode corresponding to each transport arc, and transport cost, transport time, and comprehensive transport risk coefficient corresponding to each transport mode. The comprehensive transport risk coefficient is obtained by quantitatively assessing risk factors. The model building module is used to determine the set of multimodal transport routes based on order task data and transportation data, and to construct a multi-objective route optimization model with minimizing total cost and minimizing the comprehensive transportation risk coefficient as optimization objectives. The total cost includes transportation cost, transshipment cost and time cost. The route selection module is used to select routes from a set of multimodal transport routes based on a multi-objective route optimization model and a hybrid intelligent optimization algorithm, resulting in multiple intermodal transport route schemes. The multiple intermodal transport route schemes include a complete route from the origin node to the destination node and a combination of transport modes used in each transport segment. The route recommendation module is used to determine the optimal recommended route from multiple intermodal route options based on customer preferences.

9. An international logistics multimodal transport route recommendation device, characterized in that, The system includes a memory, a processor, and a transceiver that are sequentially and communicatively connected. The memory is used to store computer programs, the transceiver is used to send and receive messages, and the processor is used to read the computer programs and execute the international logistics multimodal transport route recommendation method as described in any one of claims 1 to 7.

10. A computer program product, comprising a computer program or instructions, characterized in that, When the computer program or the instructions are executed by the computer, they implement the international logistics multimodal transport route recommendation method as described in any one of claims 1 to 7.

Images