Scheduling method, device, electronic device and medium based on multimodal transport

Abstract

The present disclosure provides a scheduling method, device, electronic device and medium based on multimodal transport, which relates to the fields of artificial intelligence and logistics management technology, and in particular to the field of logistics scheduling technology. The implementation scheme is: obtaining a transportation network and current transportation demand, wherein the transportation network includes multiple transportation nodes and sub-transportation paths connecting adjacent transportation nodes, and each of the multiple sub-transportation paths corresponds to one of multiple transportation modes; for at least one optimization goal, using the shortest path algorithm to determine the initial path set corresponding to the current transportation demand; using a genetic algorithm to perform evolutionary operations on the initial path set to obtain a candidate path set; based on the current transportation demand and the candidate path set, establishing a scheduling model; and based on the objective function and constraints, determining the optimal solution of the scheduling model, wherein the optimal solution represents the optimal transportation path for the current transportation demand.

Description

Technical Field

[0001] The present disclosure relates to the field of artificial intelligence and logistics management technology, in particular to the field of logistics scheduling technology, and specifically to a scheduling method, device, electronic device, computer-readable storage medium and computer program product based on multimodal transport. Background Art

[0002] Artificial intelligence is a discipline that studies how to use computers to simulate certain human thought processes and intelligent behaviors (such as learning, reasoning, thinking, planning, etc.). It includes both hardware-level and software-level technologies. Artificial intelligence hardware technologies generally include technologies such as sensors, dedicated artificial intelligence chips, cloud computing, distributed storage, and big data processing. Artificial intelligence software technologies mainly include computer vision technology, speech recognition technology, natural language processing technology, as well as machine learning / deep learning, big data processing technology, knowledge graph technology, and other major directions.

[0003] Intermodal transport is an efficient form of transport that utilizes multiple modes of transport and has important applications in logistics and transportation. However, due to the complexity of the transportation network and the uncertainty of transportation demand, traditional scheduling methods often fail to effectively meet the needs of optimizing transportation efficiency in intermodal transport. In particular, when transportation involves multiple transportation routes and multiple modes of transport, how to optimize between multiple objectives, how to improve the utilization efficiency of transportation resources, and how to quickly schedule under dynamic demand have become technical problems that need to be solved urgently.

[0004] The methods described in this section are not necessarily methods that have been previously conceived or employed. Unless otherwise indicated, it should not be assumed that any method described in this section is considered to be prior art simply because it is included in this section. Similarly, unless otherwise indicated, the issues mentioned in this section should not be considered to have been recognized in any prior art. Summary of the invention

[0005] The present disclosure provides a scheduling method, device, electronic device, computer-readable storage medium and computer program product based on multimodal transport.

[0006] According to one aspect of the present disclosure, a scheduling method based on multimodal transport is provided, the method comprising: obtaining a transportation network and a current transportation demand, wherein the transportation network comprises a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand comprises a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node comprises a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one of a plurality of transportation modes; for at least one optimization objective, determining an initial path set corresponding to the current transportation demand using a shortest path algorithm; performing an evolution operation on the initial path set using a genetic algorithm to obtain a candidate path set; establishing a scheduling model based on the current transportation demand and the candidate path set; and determining an optimal solution of the scheduling model based on an objective function and constraints, wherein the optimal solution represents an optimal transportation path for the current transportation demand, and wherein the objective function targets the at least one optimization objective.

[0007] According to another aspect of the present disclosure, a scheduling device based on multimodal transport is provided, comprising: an acquisition module, configured to acquire a transportation network and a current transportation demand, wherein the transportation network comprises a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand comprises a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node comprises a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one of a plurality of transportation modes; a first determination module, configured to determine an initial path set corresponding to the current transportation demand using a shortest path algorithm for at least one optimization objective; an evolution module, configured to perform an evolution operation on the initial path set using a genetic algorithm to obtain a candidate path set; an establishment module, configured to establish a scheduling model based on the current transportation demand and the candidate path set; and a second determination module, configured to determine an optimal solution of the scheduling model based on an objective function and constraints, wherein the optimal solution represents an optimal transportation path for the current transportation demand, and wherein the objective function targets the at least one optimization objective.

[0008] According to another aspect of the present disclosure, an electronic device is provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the above method.

[0009] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is provided, wherein the computer instructions are used to enable the computer to execute the above method.

[0010] According to another aspect of the present disclosure, a computer program product is provided, comprising a computer program, wherein the computer program implements the above method when executed by a processor.

[0011] According to one or more embodiments of the present disclosure, a scheduling method based on multimodal transport is provided, which determines the corresponding path for each transportation demand, and then performs global optimization based on the objective function and constraints to optimize the path selection in the transportation network for the current transportation demand, thereby improving the efficiency and accuracy of transportation path planning.

[0012] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present disclosure, nor is it intended to limit the scope of the present disclosure. Other features of the present disclosure will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0013] The accompanying drawings exemplarily illustrate the embodiments and constitute a part of the specification, and together with the text description of the specification, are used to explain the exemplary implementation of the embodiments. The embodiments shown are for illustrative purposes only and do not limit the scope of the claims. In all drawings, the same reference numerals refer to similar but not necessarily identical elements.

[0014] Figure 1 is a schematic diagram illustrating an example system in which the various methods described herein may be implemented according to an exemplary embodiment.

[0015] Figure 2 A flowchart of a scheduling method based on multimodal transport according to an embodiment of the present disclosure is shown;

[0016] Figure 3 A flowchart of a scheduling method based on multimodal transport according to an embodiment of the present disclosure is shown;

[0017] Figure 4 A structural block diagram of a scheduling method and device based on multimodal transport according to an embodiment of the present disclosure is shown; and

[0018] Figure 5 A structural block diagram of an exemplary electronic device that can be used to implement the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may be made to the embodiments described herein without departing from the scope of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well-known functions and structures is omitted in the following description.

[0020] In the present disclosure, unless otherwise specified, the use of the terms "first", "second", etc. to describe various elements is not intended to limit the positional relationship, temporal relationship, or importance relationship of these elements, and such terms are only used to distinguish one element from another element. In some examples, the first element and the second element may refer to the same instance of the element, and in some cases, based on the description of the context, they may also refer to different instances.

[0021] The terms used in the description of various examples in this disclosure are only for the purpose of describing specific examples and are not intended to be limiting. Unless the context clearly indicates otherwise, if the number of elements is not specifically limited, the element can be one or more. In addition, the term "and / or" used in this disclosure covers any one of the listed items and all possible combinations.

[0022] In the related technologies, for the problem of multimodal transport, most heuristic algorithms are used to find the optimal path that meets the conditions. The calculation complexity is high, more computing resources are consumed, and a long calculation time is required. In addition, the overall consideration is not taken into account and the overall constraints are ignored.

[0023] To solve the above problems, the present disclosure provides a scheduling method based on multimodal transport, which determines the corresponding path for each transportation demand, and then performs global optimization based on the objective function and constraints to optimize the path selection in the transportation network for the current transportation demand, thereby improving the efficiency and accuracy of transportation path planning.

[0024] The embodiments of the present disclosure will be described in detail below with reference to the accompanying drawings.

[0025] Figure 1 FIG. 1 is a schematic diagram of an exemplary system 100 in which various methods and apparatuses described herein may be implemented according to an embodiment of the present disclosure. Figure 1 , the system 100 includes one or more client devices 101, 102, 103, 104, 105, and 106, a server 120, and one or more communication networks 110 coupling the one or more client devices to the server 120. The client devices 101, 102, 103, 104, 105, and 106 may be configured to execute one or more applications.

[0026] In an embodiment of the present disclosure, the server 120 may run one or more services or software applications that enable execution of a multimodal based dispatch method.

[0027] In some embodiments, server 120 may also provide other services or software applications that may include non-virtualized environments and virtualized environments. In some embodiments, these services may be provided as web-based services or cloud services, such as provided to users of client devices 101, 102, 103, 104, 105, and / or 106 under a software as a service (SaaS) model.

[0028] exist Figure 1 In the configuration shown, the server 120 may include one or more components that implement the functions performed by the server 120. These components may include software components, hardware components, or a combination thereof that can be executed by one or more processors. Users operating client devices 101, 102, 103, 104, 105, and / or 106 may in turn utilize one or more client applications to interact with the server 120 to utilize the services provided by these components. It should be understood that a variety of different system configurations are possible, which may differ from the system 100. Therefore, Figure 1 is an example of a system for implementing the methods described herein and is not intended to be limiting.

[0029] The user may use client devices 101, 102, 103, 104, 105 and / or 106 to perform the multimodal scheduling method. The client device may provide an interface that enables the user of the client device to interact with the client device. The client device may also output information to the user via the interface. Figure 1 Only six client devices are depicted, but one skilled in the art will appreciate that the present disclosure may support any number of client devices.

[0030] Client devices 101, 102, 103, 104, 105 and / or 106 may include various types of computer devices, such as portable handheld devices, general-purpose computers (such as personal computers and laptop computers), workstation computers, wearable devices, smart screen devices, self-service terminal devices, service robots, game systems, thin clients, various messaging devices, sensors or other sensing devices, etc. These computer devices may run various types and versions of software applications and operating systems, such as MICROSOFT Windows, APPLE iOS, UNIX-like operating systems, Linux or Linux-like operating systems (such as GOOGLE Chrome OS); or include various mobile operating systems, such as MICROSOFT Windows Mobile OS, iOS, Windows Phone, Android. Portable handheld devices may include cellular phones, smart phones, tablet computers, personal digital assistants (PDAs), etc. Wearable devices may include head-mounted displays (such as smart glasses) and other devices. Game systems may include various handheld game devices, Internet-enabled game devices, etc. Client devices are capable of executing various different applications, such as various Internet-related applications, communication applications (such as email applications), short message service (SMS) applications, and may use various communication protocols.

[0031] The network 110 may be any type of network known to those skilled in the art that may support data communications using any of a variety of available protocols, including but not limited to TCP / IP, SNA, IPX, etc. By way of example only, the one or more networks 110 may be a local area network (LAN), an Ethernet-based network, a token ring, a wide area network (WAN), the Internet, a virtual network, a virtual private network (VPN), an intranet, an extranet, a public switched telephone network (PSTN), an infrared network, a wireless network (e.g., Bluetooth, WIFI), and / or any combination of these and / or other networks.

[0032] Server 120 may include one or more general purpose computers, dedicated server computers (e.g., PC (personal computer) servers, UNIX servers, mid-range servers), blade servers, mainframe computers, server clusters, or any other suitable arrangement and / or combination. Server 120 may include one or more virtual machines running virtual operating systems, or other computing architectures involving virtualization (e.g., one or more flexible pools of logical storage devices that may be virtualized to maintain a server's virtual storage device). In various embodiments, server 120 may run one or more services or software applications that provide the functionality described below.

[0033] The computing units in the server 120 may run one or more operating systems including any of the above operating systems and any commercially available server operating systems. The server 120 may also run any of a variety of additional server applications and / or middle-tier applications, including HTTP servers, FTP servers, CGI servers, JAVA servers, database servers, etc.

[0034] In some implementations, server 120 may include one or more applications to analyze and consolidate data feeds and / or event updates received from users of client devices 101, 102, 103, 104, 105, and 106. Server 120 may also include one or more applications to display data feeds and / or real-time events via one or more display devices of client devices 101, 102, 103, 104, 105, and 106.

[0035] In some embodiments, the server 120 may be a server of a distributed system, or a server combined with a blockchain. The server 120 may also be a cloud server, or an intelligent cloud computing server or intelligent cloud host with artificial intelligence technology. A cloud server is a host product in a cloud computing service system to solve the defects of difficult management and weak business scalability in traditional physical hosts and virtual private servers (VPS) services.

[0036] The system 100 may also include one or more databases 130. In some embodiments, these databases may be used to store data and other information. For example, one or more of the databases 130 may be used to store information such as audio files and video files. The databases 130 may reside in various locations. For example, the database used by the server 120 may be local to the server 120, or may be remote from the server 120 and may communicate with the server 120 via a network-based or dedicated connection. The databases 130 may be of different types. In some embodiments, the databases used by the server 120 may be, for example, relational databases. One or more of these databases may store, update, and retrieve data to and from the databases in response to commands.

[0037] In some embodiments, one or more of the databases 130 may also be used by applications to store application data. The databases used by the applications may be different types of databases, such as a key-value store, an object store, or a conventional store backed by a file system.

[0038] Figure 1 The system 100 may be configured and operated in various ways to enable the application of various methods and apparatuses described in the present disclosure.

[0039] Figure 2 A flowchart of a scheduling method based on multimodal transport according to an embodiment of the present disclosure is shown.

[0040] like Figure 2 As shown, the scheduling method 200 based on multimodal transport includes:

[0041] Step S201, obtaining a transportation network and a current transportation demand, wherein the transportation network includes a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand includes a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node includes a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one transportation mode among a plurality of transportation modes;

[0042] Step S202: for at least one optimization objective, determine an initial path set corresponding to the current transportation demand using a shortest path algorithm;

[0043] Step S203: using a genetic algorithm to perform an evolution operation on the initial path set to obtain a candidate path set;

[0044] Step S204: establishing a scheduling model based on the current transportation demand and the candidate path set;

[0045] Step S205: Determine the optimal solution of the scheduling model based on the objective function and the constraints, wherein the optimal solution represents the optimal transportation path for the current transportation demand, and wherein the objective function takes the at least one optimization objective as a target.

[0046] First, in step S201, a transportation network and transportation demand are obtained. Exemplarily, the transportation network is pre-constructed and includes multiple transportation nodes and sub-transportation paths connecting these nodes. In one example, the transportation network includes multiple types of node bases, such as warehouses, platforms, ports, distribution warehouses, cache warehouses, and feasible segmented routes between nodes, i.e., sub-transportation paths. The segmented routes include multiple modes of transportation such as road, rail, and water, and involve segmented transportation costs, transportation time, and transit costs.

[0047] The transportation demand includes a source transportation node and a target transportation node. It is understandable that the transportation path from the source transportation node to the target transportation node may include multiple sub-transportation paths, and the scheduling method 200 based on multimodal transport plans and schedules the transportation path according to the source transportation node and the target transportation node included in the transportation demand to obtain the optimal transportation path.

[0048] In step S202, according to the optimization goal set by the user (such as the lowest transportation cost, the shortest transportation time), a group of initial paths are generated from the source transportation node to the target transportation node using the shortest path algorithm as the initial path set.

[0049] Exemplarily, the current transportation demand may include multiple sub-demands, such as transporting a batch of commodity vehicles from multiple production bases (or warehouses) to hundreds of destinations. In step S202, the shortest path algorithm may be used to generate an initial path corresponding to each sub-demand based on the sub-demand.

[0050] In step S203, the initial path set is evolved using a genetic algorithm to form a candidate path set. It can be understood that these paths are optimized versions of the initial paths after the evolution operation.

[0051] In step S204, the scheduling model is established based on the current transportation demand and the candidate path set, so that in step S205, based on the objective function and constraints, the optimal solution of the scheduling model, that is, the optimal transportation path for the current transportation demand, can be determined.

[0052] In this way, transport scheduling based on multimodal transport is realized. By combining genetic algorithms with the shortest path algorithm, a balance is achieved among multiple optimization objectives, and global optimization is performed based on objective functions and constraints, thereby improving the accuracy and efficiency of path planning.

[0053] According to some embodiments, the multiple modes of transportation include: road transportation, rail transportation and water transportation. Compared with a single mode of transportation, multimodal transportation uses multiple modes of transportation to work together, which helps to improve transportation efficiency and reduce transportation costs.

[0054] Figure 3 FIG. 1 is a flow chart of a scheduling method based on multimodal transport according to an embodiment of the present disclosure. Figure 3 As shown, based on steps S201 to S205, the scheduling method 200 based on multimodal transport further includes:

[0055] Step S301: Based on historical transportation demand, use a pre-trained neural network model to predict future transportation demand within a preset period;

[0056] Step S302: allocating transportation resources based on the predicted transportation demand within the preset period, wherein the transportation resources include the transportation capacity of the multiple transportation modes and the transportation capacity of the multiple transportation nodes;

[0057] Step S303, in response to receiving the actual transportation demand within the preset period, updating the constraint condition based on the deployed transportation resources; and

[0058] Step S304: Determine the optimal transportation path corresponding to the actual transportation demand based on the updated constraint conditions.

[0059] Step S301 predicts future demand based on historical transportation demand. Specifically, a pre-trained neural network model is used to predict transportation demand within a preset period in the future based on historical transportation demand. Exemplarily, the pre-trained neural network model can be a long short-term memory network. Through the learning ability of the neural network, the trend of transportation demand changes can be predicted in advance, and the adaptability and planning of future transportation demand can be improved.

[0060] In one example, historical data can be used to train a neural network model, and a cross-validation method can be used to evaluate the performance of the neural network model to ensure that its performance on different data sets is stable. During the model training process, the optimization goal of the training can be to minimize transportation costs, reduce transportation time, reduce carbon emissions, maximize resource utilization, etc., in order to adjust model parameters and optimize prediction results.

[0061] In some embodiments, the real-time input data of the model may include: real-time acquisition of traffic, weather, business information such as season, etc., and demand change data to improve the prediction accuracy of the model. Exemplarily, real-time data can be continuously received and processed to maintain the accuracy of dynamic optimization. Data sources may include: traffic information, such as road congestion, traffic accidents, etc., which affect transportation routes and times. Weather data, it is understandable that weather changes may affect the capacity of certain transportation routes, especially in bad weather. Business information, such as seasonal changes, market demand fluctuations, etc., will affect overall transportation demand. Demand change data, such as a sudden increase in demand for a certain type of goods, requires the system to adjust transportation routes and scheduling in a timely manner. These real-time data will be integrated into the dynamic optimization model and combined with the forecast data to ensure the system's response speed to changing conditions.

[0062] Step S302 allocates transportation resources based on predicted demand. Specifically, according to the predicted demand, transportation resources (such as the transportation capacity of various transportation modes, transportation routes, vehicle scheduling, and resource allocation) are allocated and adjusted to optimize resource allocation in advance, reduce resource waste, improve transportation efficiency, and reduce the difficulty of resource scheduling caused by sudden demand.

[0063] In step S303, the constraints in the scheduling model are dynamically updated according to the received actual transportation demand and the allocated resources, so as to determine the optimal path based on the updated constraints in step S304. Specifically, the scheduling model is re-optimized according to the updated constraints to obtain the optimal path for the actual transportation demand. Thus, the transportation path can be dynamically adjusted to ensure that the path planning results meet the actual demand and optimize the transportation efficiency and cost.

[0064] Therefore, after receiving the actual transportation demand, multimodal transport solutions can be solved based on the allocated road, rail and water resources, thus avoiding the problem of unmet transportation demand due to insufficient resources in a certain place and excess transportation resources (road transport vehicles) in some areas.

[0065] According to some embodiments, the constraint conditions include at least one of the following: an upper limit on the transportation volume corresponding to the transportation node serving as the departure station among the multiple transportation nodes; an upper limit on the transportation volume corresponding to the transportation node serving as the destination station among the multiple transportation nodes; an upper limit on the ratio of rail transportation and water transportation corresponding to the transportation path from the source transportation node to the target transportation node; and a volume limit on road transportation corresponding to the transportation path from the source transportation node to the target transportation node.

[0066] It is understandable that in multimodal transport, the proportion restrictions of different modes of transport reflect actual policy requirements (such as reducing the proportion of road transport to reduce carbon emissions, etc.). Therefore, by setting constraints reasonably and optimizing resource allocation, it is possible to ensure that the path planning results are practical.

[0067] In some embodiments, the constraints involved can be summarized into the following three categories:

[0068] Constraint 1: Upper limit of the proportion of hot metal shipped by each base

[0069] The railway transportation volume + water transportation volume from the base does not exceed a certain proportion of the total transportation volume of the base. Constraint 2: Platform / port shipping arrival capacity

[0070] There are capacity restrictions on the shipping routes flowing into or out of a platform / port; for the same platform or port, the outflow and inflow restrictions are different.

[0071] Constraint 3: Base-destination province highway capacity limit

[0072] Starting from a certain base, transportation to the destination distributor in the same province is subject to the "base-destination province" road transport capacity limit.

[0073] It can be understood that a base in a transportation network refers to a facility or location that serves to transfer, aggregate, distribute or store goods in the transportation system.

[0074] The following example provides a specific construction of the scheduling model and the definition of the constraints:

[0075] Transportation demand set: R = {1,...,n}, representing n transportation demands.

[0076] The set of optional transportation modes: M = {1, 2, 3}, where 1 represents road transportation, 2 represents railway transportation, and 3 represents water transportation.

[0077] The quantity of the rth transportation demand: Qr,r∈R.

[0078] Transport path collection: P.

[0079] Transportation cost of path p: Cp,p∈P.

[0080] The transportation demand corresponding to path p: rp, rp∈R.

[0081] The transportation mode corresponding to path p: mp, mp∈M.

[0082] Assembly at departure station / port: A.

[0083] The upper limit of the shipping capacity of the originating station a: Ua,a∈A.

[0084] The originating station corresponding to the path p: ap, ap∈A.

[0085] Destination station / destination port collection: B.

[0086] The upper limit of the reachability of the destination station b: Ub,b∈B.

[0087] The destination station corresponding to the path p: bp, bp∈B.

[0088] Base Collection: O.

[0089] The upper limit of the railway and water transport capacity of base o: Uo,o∈O.

[0090] The base corresponding to the path p: op, op∈O.

[0091] The province collection of the target marketers: Y.

[0092] The upper limit of highway transport capacity from base o to destination province y is: Uoy,o∈O,y∈Y.

[0093] The lower limit of road transport volume from base o to destination province y is: Loy,o∈O,y∈Y.

[0094] The destination marketing province corresponding to path p: yp, yp∈Y.

[0095] The quantity of cargo allocated to path p: xp, p∈P.

[0096] Objective function (in this embodiment, the objective is to minimize the transportation cost):

[0097] Constraints:

[0098] 1. Non-negativity constraints:

[0099] 2. Transportation demand meets constraints:

[0100]

[0101] For any transport demand r, the sum of all assigned route volumes should be equal to the demand quantity Qr.

[0102] 3. Capacity constraints of the departure station / port:

[0103]

[0104] For any originating station a, the sum of all path volumes allocated to the station shall not exceed its upper limit of shipping capacity Ua.

[0105] 4. Destination station / port capacity constraints:

[0106]

[0107] For any destination station b, the sum of all path volumes allocated to the station shall not exceed its upper limit of arrival capacity Ub.

[0108] 5. Base capacity constraints:

[0109]

[0110] For any base o, the sum of the volumes of all routes passing through the base and using rail or water transport modes shall not exceed its rail and water transport capacity limit Uo.

[0111] 6. Highway transportation capacity constraints from base to destination province:

[0112]

[0113] For any base o and any destination province y, the sum of the transport volumes of all road transport routes starting from the base shall not exceed Uoy and shall not be less than Loy.

[0114] Through the construction of the above scheduling model, the objective function is minimized through path selection XP optimization to obtain the optimal solution as the optimal transportation path.

[0115] According to some embodiments, step S202 includes: for each of the at least one optimization target, using the shortest path algorithm to determine a transportation path that meets the optimization target based on the source transportation node and the target transportation node; and merging the set of transportation paths corresponding to each optimization target to obtain the initial path set, wherein the at least one optimization target includes at least one of the following items: minimum transportation cost, shortest transportation time, and minimum carbon emissions during transportation.

[0116] For each optimization target, the shortest path algorithm is used to generate a path set that meets the target, and the path sets of all targets are merged as the initial path set. This ensures the diversity and pertinence of the initial path set, providing more options and a better foundation for subsequent optimization.

[0117] According to one embodiment, the shortest path algorithm can be used to generate transportation paths that meet the three optimization goals of minimizing transportation costs, minimizing transportation time, and minimizing carbon emissions during transportation, and then the transportation paths for each optimization goal of each transportation sub-demand are merged to obtain an initial path set, so that global optimization can be performed in subsequent stages.

[0118] Exemplarily, the objective function may be used to solve the optimal solution of the scheduling model with the three optimization goals of minimizing target transportation cost, minimizing transportation time, and minimizing carbon emissions during transportation as the objectives.

[0119] In one example, the carbon emissions calculation formula is: E = d × w × EF

[0120] Among them, the transport distance (d) represents the actual distance of transportation on the route, the cargo weight (w) represents the total weight of the cargo to be transported, and the carbon emission factor (EF) is provided by industry standards or government guidelines according to different modes of transportation. For example, road transportation is 0.1-0.2 kg CO2 / ton·km, rail transportation is 0.01-0.05 kg CO2 / ton·km, and water transportation is 0.005-0.02 kg CO2 / ton·km. The purpose of this carbon emission calculation method is to quantify the environmental impact in the scheduling of transportation routes, so as to take into account environmental protection indicators during optimization and comply with corporate social responsibility or environmental protection policies.

[0121] According to some embodiments, the shortest path algorithm is Dijkstra's algorithm or Yen's K shortest path algorithm.

[0122] Shortest path algorithms such as Dijkstra and Yen's K shortest path algorithm can find the shortest path from the starting point to the end point in the transportation network. The "shortest" here usually refers to a single goal (such as minimum transportation cost, shortest transportation time, or minimum carbon emissions in transportation). Through the shortest path algorithm, a set of high-quality path candidate sets can be quickly generated. These path sets generated by the shortest path algorithm are used as the initial population for subsequent evolutionary operations. Each solution (path) in the initial population will be assigned a different target value (such as the transportation cost, time and carbon emissions of the path), providing a basis for subsequent multi-objective optimization. At the same time, these solutions can help subsequent evolutionary operations converge quickly in the early stages, while providing a certain diversity basis.

[0123] For example, when it is necessary to optimize the transportation path from a certain base to a certain dealer, the Dijkstra algorithm can be used to find the shortest path based on transportation cost, and the Yen's K shortest path algorithm can be used to find multiple suboptimal paths (such as the second shortest path, the third shortest path, etc.). These paths constitute the initial solution (population), which is used as the input of the evolutionary operation and further optimized to meet the needs of multiple objectives (such as time and carbon emissions).

[0124] According to some embodiments, step S203 includes: taking the initial path set as the initial population, using the genetic algorithm to perform an evolutionary operation on the initial population to generate a offspring population for iteration of the evolutionary operation; in response to satisfying an iteration termination condition, merging the initial population and each offspring population obtained in the iteration to obtain a population set; and performing a fitness evaluation on each transport path in the population set to obtain the candidate path set based on the population set.

[0125] The initial path set is used as the initial population, and the offspring population is generated through multiple iterations using the genetic algorithm. Finally, the initial population and the offspring population are merged to form a population set. The global search capability of the genetic algorithm is used to gradually optimize the population and improve the quality and fitness of the candidate path set.

[0126] The fitness of each path in the population set is evaluated to select a set of candidate paths. The set of paths with the best performance is selected to provide high-quality input for subsequent scheduling model optimization.

[0127] According to some embodiments, the genetic algorithm is a NSGA-II algorithm.

[0128] The NSGA-II algorithm is used as a genetic algorithm to optimize the population by combining non-dominated sorting and crowding distance evaluation. The algorithm's ability to handle multi-objective optimization is enhanced to achieve a better balance between efficiency and path quality, ensuring that the candidate path set can better meet multi-objective requirements.

[0129] In the above scheme, path optimization can be performed for multiple objectives. Specifically, when generating a path, the following three key objectives need to be calculated and considered: Transportation cost: usually includes the cost required for the transportation of goods, which may be related to factors such as transportation mode, distance, congestion, etc. Transportation time: The time required to complete the transportation task, which can be affected by factors such as traffic, weather, and route. Carbon emissions: The amount of carbon dioxide emissions during transportation is usually closely related to the mode of transportation (such as trucks, ships, airplanes, etc.) and its efficiency. In order to consider these multiple objectives, NSGA-II (Non-dominated Sorting Genetic Algorithm-II) is used for multi-objective optimization to calculate and select the optimal path set.

[0130] For each transport demand, the NSGA-II algorithm is used to generate a set of Pareto optimal paths. Pareto optimal paths refer to a set of paths that cannot improve on one objective without causing losses in other objectives when considering multiple objectives. Traditional shortest path algorithms (such as Dijkstra or Yen's K shortest path algorithm) usually focus on only one objective (such as shortest distance or least cost), while in multi-objective path optimization, multiple objectives need to be optimized simultaneously. In order to adapt to the multi-objective scenario, the shortest path algorithm is adjusted and combined with NSGA-II for diversified path selection. This helps to generate multiple paths with different characteristics during the search process, thereby providing decision makers with more options. The Pareto optimal path set for each transport demand is merged into a total path set to form a candidate path set considering multiple objectives. A set of Pareto optimal paths is generated for each transport demand, which achieves a balance in cost, time and carbon emissions. The Pareto optimal paths of multiple transport demands are combined to form a total path set containing multiple objectives for subsequent selection and optimization.

[0131] In the design of the NSGA-II algorithm, the path set generated by the shortest path algorithm is used as the initial population to ensure the diversity of the population and the diversity of the initial solution. The cost, time and carbon emissions of each individual (path) are calculated to evaluate the fitness of each individual using non-dominated sorting. Non-dominated sorting is part of NSGA-II and is used to measure the dominance relationship of individuals. The crowding distance is used to maintain the diversity of the population and avoid premature convergence to a local optimal solution.

[0132] In some embodiments, the evolutionary operation specifically includes three operations: selection, crossover, and mutation. Among them, the selection is to select the parent individuals based on the non-dominated sorting to ensure that individuals with both high fitness and diversity are selected. The crowding distance is used to further maintain the diversity of the population. By designing a crossover operation suitable for the path, such as partial mapping crossover (PMX), nodes can be effectively exchanged between paths to generate new paths. For path mutation operations, such as node exchange or path segment reversal, the exploration ability of the population is enhanced to avoid falling into a local optimal solution.

[0133] The current population and the newly generated offspring are merged, and then a new population is selected based on the non-dominated sorting and crowding distance. This ensures the diversity and excellent characteristics of each generation of population. The maximum number of iterations or convergence criteria are set as the termination condition of the algorithm. When the predetermined conditions are met, the algorithm ends to obtain a population set. The fitness of each transportation path in the population set is evaluated to obtain the candidate path set based on the population set.

[0134] According to another aspect of the present disclosure, a scheduling device based on multimodal transport is provided. Figure 4As shown, the scheduling device 400 based on multimodal transport includes: an acquisition module 401, configured to acquire a transportation network and a current transportation demand, wherein the transportation network includes a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand includes a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node includes a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one of a plurality of transportation modes; a first determination module 402, configured to determine the optimal transportation mode for at least one transportation mode; Optimization target, using the shortest path algorithm to determine the initial path set corresponding to the current transportation demand; an evolution module 403, configured to use a genetic algorithm to evolve the initial path set to obtain a candidate path set; an establishment module 404, configured to establish a scheduling model based on the current transportation demand and the candidate path set; and a second determination module 405, configured to determine the optimal solution of the scheduling model based on the objective function and constraints, wherein the optimal solution represents the optimal transportation path for the current transportation demand, and wherein the objective function takes the at least one optimization target as a target.

[0135] First, the acquisition module 401 acquires the transportation network and transportation demand. Exemplarily, the transportation network is pre-constructed and includes multiple transportation nodes and sub-transportation paths connecting these nodes. In one example, the transportation network includes multiple types of node bases, such as warehouses, platforms, ports, distribution warehouses, cache warehouses, and feasible segmented routes between nodes, i.e., sub-transportation paths. The segmented routes include multiple transportation modes such as road, rail, and water, and involve segmented transportation costs, transportation time, and transit costs.

[0136] The transportation demand includes a source transportation node and a target transportation node. It is understandable that the transportation path from the source transportation node to the target transportation node may include multiple sub-transportation paths, and the scheduling device 400 based on multimodal transport plans and schedules the transportation path according to the source transportation node and the target transportation node included in the transportation demand to obtain the optimal transportation path.

[0137] The first determination module 402 generates a set of initial paths from the source transportation node to the target transportation node using the shortest path algorithm according to the optimization goal set by the user (such as the lowest transportation cost and the shortest transportation time), as the initial path set.

[0138] Exemplarily, the current transportation demand may include multiple sub-demands, such as transporting a batch of commodity vehicles from multiple production bases (or warehouses) to hundreds of destinations. The first determination module 402 may generate an initial path corresponding to each sub-demand using the shortest path algorithm.

[0139] The evolution module 403 uses a genetic algorithm to evolve the initial path set to form a candidate path set. It can be understood that these paths are optimized versions of the initial paths after the evolution operation.

[0140] The establishment module 404 establishes the scheduling model based on the current transportation demand and the candidate path set, so that the second determination module 405 can determine the optimal solution of the scheduling model, that is, the optimal transportation path for the current transportation demand, based on the objective function and the constraints.

[0141] In this way, transport scheduling based on multimodal transport is realized. By combining genetic algorithms with the shortest path algorithm, a balance is achieved among multiple optimization objectives, and global optimization is performed based on objective functions and constraints, thereby improving the accuracy and efficiency of path planning.

[0142] According to some embodiments, the multiple modes of transportation include: road transportation, rail transportation and water transportation. Compared with a single mode of transportation, multimodal transportation uses multiple modes of transportation to work together, which helps to improve transportation efficiency and reduce transportation costs.

[0143] According to some embodiments, the scheduling device 400 based on multimodal transport also includes: a prediction module, configured to predict the transportation demand within a preset period in the future based on historical transportation demand using a pre-trained neural network model; an allocation module, configured to allocate transportation resources based on the predicted transportation demand within the preset period, wherein the transportation resources include the transportation capacity of the multiple transportation modes and the transportation capacity of the multiple transportation nodes; an update module, configured to update the constraint conditions based on the allocated transportation resources in response to receiving the actual transportation demand within the preset period; and a third determination module, configured to determine the optimal transportation path corresponding to the actual transportation demand based on the updated constraint conditions.

[0144] In one example, historical data can be used to train a neural network model, and a cross-validation method can be used to evaluate the performance of the neural network model to ensure that its performance on different data sets is stable. During the model training process, the optimization goal of the training can be to minimize transportation costs, reduce transportation time, reduce carbon emissions, maximize resource utilization, etc., in order to adjust model parameters and optimize prediction results.

[0145] In some embodiments, the real-time input data of the model may include: real-time acquisition of traffic, weather, business information such as season, etc., and demand change data to improve the prediction accuracy of the model. Exemplarily, real-time data can be continuously received and processed to maintain the accuracy of dynamic optimization. Data sources may include: traffic information, such as road congestion, traffic accidents, etc., which affect transportation routes and times. Weather data, it is understandable that weather changes may affect the capacity of certain transportation routes, especially in bad weather. Business information, such as seasonal changes, market demand fluctuations, etc., will affect overall transportation demand. Demand change data, such as a sudden increase in demand for a certain type of goods, requires the system to adjust transportation routes and scheduling in a timely manner. These real-time data will be integrated into the dynamic optimization model and combined with the forecast data to ensure the system's response speed to changing conditions.

[0146] The dispatching module dispatches transportation resources based on predicted demand. Specifically, according to the predicted demand, transportation resources (such as the capacity of various transportation modes, transportation routes, vehicle scheduling, and resource allocation) are allocated and adjusted to optimize resource allocation in advance, reduce resource waste, improve transportation efficiency, and reduce the difficulty of resource scheduling caused by sudden demand.

[0147] The updating module dynamically updates the constraints in the scheduling model according to the received actual transportation demand and the allocated resources, so that the third determination module determines the optimal path based on the updated constraints. Specifically, according to the updated constraints, the scheduling model is re-optimized to obtain the optimal path for the actual transportation demand. Thus, the transportation path can be dynamically adjusted to ensure that the path planning results meet the actual demand and optimize the transportation efficiency and cost.

[0148] Therefore, after receiving the actual transportation demand, multimodal transport solutions can be solved based on the allocated road, rail and water resources, thus avoiding the problem of unmet transportation demand due to insufficient resources in a certain place and excess transportation resources (road transport vehicles) in some areas.

[0149] According to some embodiments, the constraint conditions include at least one of the following: an upper limit on the transportation volume corresponding to the transportation node serving as the departure station among the multiple transportation nodes; an upper limit on the transportation volume corresponding to the transportation node serving as the destination station among the multiple transportation nodes; an upper limit on the ratio of rail transportation and water transportation corresponding to the transportation path from the source transportation node to the target transportation node; and a volume limit on road transportation corresponding to the transportation path from the source transportation node to the target transportation node.

[0150] It is understandable that in multimodal transport, the proportion restrictions of different modes of transport reflect actual policy requirements (such as reducing the proportion of road transport to reduce carbon emissions, etc.). Therefore, by setting constraints reasonably and optimizing resource allocation, it is possible to ensure that the path planning results are practical.

[0151] According to some embodiments, the first determination module 402 includes: a first determination unit, for each of the at least one optimization target, determining a transportation path that meets the optimization target based on the source transportation node and the target transportation node using the shortest path algorithm; and a first merging unit, configured to merge the sets of transportation paths corresponding to each optimization target to obtain the initial path set.

[0152] For each optimization target, the shortest path algorithm is used to generate a path set that meets the target, and the path sets of all targets are merged as the initial path set. This ensures the diversity and pertinence of the initial path set, providing more options and a better foundation for subsequent optimization.

[0153] According to one embodiment, the shortest path algorithm can be used to generate transportation paths that meet the three optimization goals of minimizing transportation costs, minimizing transportation time, and minimizing carbon emissions during transportation, and then the transportation paths for each optimization goal of each transportation sub-demand are merged to obtain an initial path set, so that global optimization can be performed in subsequent stages.

[0154] Exemplarily, the objective function may be used to solve the optimal solution of the scheduling model with the three optimization goals of minimizing target transportation cost, minimizing transportation time, and minimizing carbon emissions during transportation as the objectives.

[0155] According to some embodiments, the shortest path algorithm is Dijkstra's algorithm or Yen's K shortest path algorithm.

[0156] Shortest path algorithms such as Dijkstra and Yen's K shortest path algorithm can find the shortest path from the starting point to the end point in the transportation network. The "shortest" here usually refers to a single goal (such as minimum transportation cost, shortest transportation time, or minimum carbon emissions in transportation). Through the shortest path algorithm, a set of high-quality path candidate sets can be quickly generated. These path sets generated by the shortest path algorithm are used as the initial population for subsequent evolutionary operations. Each solution (path) in the initial population will be assigned a different target value (such as the transportation cost, time and carbon emissions of the path), providing a basis for subsequent multi-objective optimization. At the same time, these solutions can help subsequent evolutionary operations converge quickly in the early stages, while providing a certain diversity basis.

[0157] For example, when it is necessary to optimize the transportation path from a certain base to a certain dealer, the Dijkstra algorithm can be used to find the shortest path based on transportation cost, and the Yen's K shortest path algorithm can be used to find multiple suboptimal paths (such as the second shortest path, the third shortest path, etc.). These paths constitute the initial solution (population), which is used as the input of the evolutionary operation and further optimized to meet the needs of multiple objectives (such as time and carbon emissions).

[0158] According to some embodiments, the evolution module 403 includes: an evolution unit, configured to use the initial path set as the initial population, and use the genetic algorithm to perform an evolution operation on the initial population to generate a offspring population for iteration of the evolution operation; a second merging unit, configured to merge the initial population and each offspring population obtained in the iteration in response to meeting the iteration termination condition to obtain a population set; and an evaluation unit, configured to perform fitness evaluation on each transport path in the population set to obtain the candidate path set based on the population set.

[0159] The initial path set is used as the initial population, and the offspring population is generated through multiple iterations using the genetic algorithm. Finally, the initial population and the offspring population are merged to form a population set. The global search capability of the genetic algorithm is used to gradually optimize the population and improve the quality and fitness of the candidate path set.

[0160] The fitness of each path in the population set is evaluated to select a set of candidate paths. The set of paths with the best performance is selected to provide high-quality input for subsequent scheduling model optimization.

[0161] According to some embodiments, the genetic algorithm is a NSGA-II algorithm.

[0162] The NSGA-II algorithm is used as a genetic algorithm to optimize the population by combining non-dominated sorting and crowding distance evaluation. The algorithm's ability to handle multi-objective optimization is enhanced to achieve a better balance between efficiency and path quality, ensuring that the candidate path set can better meet multi-objective requirements.

[0163] According to another aspect of the present disclosure, an electronic device is also provided, comprising: at least one processor; and a memory communicatively connected to the at least one processor; wherein the memory stores instructions executable by the at least one processor, and the instructions are executed by the at least one processor so that the at least one processor can execute the aforementioned method.

[0164] According to another aspect of the present disclosure, a non-transitory computer-readable storage medium storing computer instructions is further provided, wherein the computer instructions are used to enable the computer to execute the aforementioned method.

[0165] According to another aspect of the present disclosure, a computer program product is also provided, including a computer program, wherein the computer program implements the aforementioned method when executed by a processor.

[0166] like Figure 5 As shown, the electronic device 500 includes a computing unit 501, which can perform various appropriate actions and processes according to a computer program stored in a read-only memory (ROM) 502 or a computer program loaded from a storage unit 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the electronic device 500 can also be stored. The computing unit 501, the ROM 502, and the RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0167] Multiple components in the electronic device 500 are connected to the I / O interface 505, including: an input unit 506, an output unit 507, a storage unit 508 and a communication unit 509. The input unit 506 can be any type of device that can input information to the electronic device 500. The input unit 506 can receive input digital or character information, and generate key signal input related to user settings and / or function control of the electronic device, and can include but is not limited to a mouse, a keyboard, a touch screen, a trackpad, a trackball, a joystick, a microphone and / or a remote control. The output unit 507 can be any type of device that can present information, and can include but is not limited to a display, a speaker, a video / audio output terminal, a vibrator and / or a printer. The storage unit 508 can include but is not limited to a disk, an optical disk. The communication unit 509 allows the electronic device 500 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunication networks, and can include but is not limited to a modem, a network card, an infrared communication device, a wireless communication transceiver and / or a chipset, such as Bluetooth TM devices, 802.11 devices, WiFi devices, WiMax devices, cellular communication devices, and / or the like.

[0168] The computing unit 501 may be a variety of general and / or special processing components with processing and computing capabilities. Some examples of the computing unit 501 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various dedicated artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, digital signal processors (DSPs), and any appropriate processors, controllers, microcontrollers, etc. The computing unit 501 performs the various methods and processes described above, such as a scheduling method based on multimodal transport. For example, in some embodiments, the scheduling method based on multimodal transport may be implemented as a computer software program, which is tangibly contained in a machine-readable medium, such as a storage unit 508. In some embodiments, part or all of the computer program may be loaded and / or installed on the electronic device 500 via the ROM 502 and / or the communication unit 509. When the computer program is loaded into the RAM 503 and executed by the computing unit 501, one or more steps of the scheduling method based on multimodal transport described above may be performed. Alternatively, in other embodiments, the computing unit 501 may be configured to execute the multimodal transport-based scheduling method in any other appropriate manner (eg, by means of firmware).

[0169] Various implementations of the systems and techniques described above herein can be implemented in digital electronic circuit systems, integrated circuit systems, field programmable gate arrays (FPGAs), application specific integrated circuits (ASICs), application specific standard products (ASSPs), systems on chips (SOCs), complex programmable logic devices (CPLDs), computer hardware, firmware, software, and / or combinations thereof. These various implementations can include: being implemented in one or more computer programs that can be executed and / or interpreted on a programmable system including at least one programmable processor, which can be a special purpose or general purpose programmable processor that can receive data and instructions from a storage system, at least one input device, and at least one output device, and transmit data and instructions to the storage system, the at least one input device, and the at least one output device.

[0170] The program code for implementing the method of the present disclosure may be written in any combination of one or more programming languages. These program codes may be provided to a processor or controller of a general-purpose computer, a special-purpose computer, or other programmable data processing device, so that the program code, when executed by the processor or controller, enables the functions / operations specified in the flow chart and / or block diagram to be implemented. The program code may be executed entirely on the machine, partially on the machine, partially on the machine and partially on a remote machine as a stand-alone software package, or entirely on a remote machine or server.

[0171] In the context of the present disclosure, a machine-readable medium may be a tangible medium that may contain or store a program for use by or in conjunction with an instruction execution system, device, or equipment. A machine-readable medium may be a machine-readable signal medium or a machine-readable storage medium. A machine-readable medium may include, but is not limited to, an electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, device, or equipment, or any suitable combination of the foregoing. A more specific example of a machine-readable storage medium may include an electrical connection based on one or more lines, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0172] To provide interaction with a user, the systems and techniques described herein can be implemented on a computer having: a display device (e.g., a CRT (cathode ray tube) or LCD (liquid crystal display) monitor) for displaying information to the user; and a keyboard and pointing device (e.g., a mouse or trackball) through which the user can provide input to the computer. Other types of devices can also be used to provide interaction with the user; for example, the feedback provided to the user can be any form of sensory feedback (e.g., visual feedback, auditory feedback, or tactile feedback); and input from the user can be received in any form (including acoustic input, voice input, or tactile input).

[0173] The systems and techniques described herein may be implemented in a computing system that includes back-end components (e.g., as a data server), or a computing system that includes middleware components (e.g., an application server), or a computing system that includes front-end components (e.g., a user computer with a graphical user interface or a web browser through which a user can interact with implementations of the systems and techniques described herein), or a computing system that includes any combination of such back-end components, middleware components, or front-end components. The components of the system may be interconnected by any form or medium of digital data communication (e.g., a communication network). Examples of communication networks include: a local area network (LAN), a wide area network (WAN), and the Internet.

[0174] A computer system may include a client and a server. The client and the server are generally remote from each other and usually interact through a communication network. The relationship of client and server is generated by computer programs running on respective computers and having a client-server relationship with each other. The server may be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0175] It should be understood that the various forms of processes shown above can be used to reorder, add or delete steps. For example, the steps described in this disclosure can be performed in parallel, sequentially or in different orders, as long as the desired results of the technical solutions disclosed in this disclosure can be achieved, and this document does not limit this.

[0176] Although the embodiments or examples of the present disclosure have been described with reference to the accompanying drawings, it should be understood that the above-mentioned methods, systems and devices are merely exemplary embodiments or examples, and the scope of the present invention is not limited by these embodiments or examples, but only by the claims after authorization and their equivalent scope. Various elements in the embodiments or examples can be omitted or replaced by their equivalent elements. In addition, each step can be performed in an order different from that described in the present disclosure. Further, the various elements in the embodiments or examples can be combined in various ways. It is important that with the evolution of technology, many elements described herein can be replaced by equivalent elements that appear after the present disclosure.

Claims

1. A scheduling method based on multimodal transport, comprising: Acquire a transportation network and a current transportation demand, wherein the transportation network includes a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand includes a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node includes a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one transportation mode among a plurality of transportation modes; For at least one optimization objective, using a shortest path algorithm to determine an initial path set corresponding to the current transportation demand; Using a genetic algorithm to perform an evolution operation on the initial path set to obtain a candidate path set; Establishing a scheduling model based on the current transportation demand and the set of candidate routes; and Based on the objective function and the constraints, an optimal solution of the scheduling model is determined, wherein the optimal solution represents an optimal transportation path for the current transportation demand, and wherein the objective function targets the at least one optimization goal.

2. The method according to claim 1, further comprising: Based on historical transportation demand, use the pre-trained neural network model to predict future transportation demand within a preset period; Based on the predicted transportation demand within the preset period, transport resources are deployed, wherein the transport resources include the transport capacity of the multiple transport modes and the transport capacity of the multiple transport nodes; In response to receiving actual transportation demand within the preset period, updating the constraint condition based on the deployed transportation resources; and Based on the updated constraints, an optimal transportation path corresponding to the actual transportation demand is determined.

3. The method according to claim 1 or 2, wherein: The various modes of transportation include: Road transport, rail transport and water transport.

4. The method according to claim 3, wherein: The constraints include at least one of the following: An upper limit of the transport volume corresponding to the transport node serving as the departure station among the plurality of transport nodes; An upper limit of the transport volume corresponding to the transport node serving as the destination station among the multiple transport nodes; An upper limit of the ratio of rail transport to water transport corresponding to the transport path from the source transport node to the target transport node; The transport capacity limit of the road transport corresponding to the transport path from the source transport node to the target transport node.

5. The method according to any one of claims 1 to 4, wherein: The determining of the initial path set corresponding to the current transportation demand by using the shortest path algorithm for at least one optimization objective includes: For each of the at least one optimization target, using the shortest path algorithm to determine a transportation path that meets the optimization target based on the source transportation node and the target transportation node; and The set of transport paths corresponding to each optimization objective is merged to obtain the initial path set, wherein the at least one optimization objective includes at least one of the following: Minimum shipping costs, minimum shipping time, and minimum carbon emissions from shipping.

6. The method according to claim 5, wherein: The shortest path algorithm is Dijkstra's algorithm or Yen's K shortest path algorithm.

7. The method according to any one of claims 1 to 6, wherein: The using of a genetic algorithm to perform an evolution operation on the initial path set to obtain a candidate path set comprises: Taking the initial path set as an initial population, and using the genetic algorithm to perform an evolution operation on the initial population to generate a descendant population for iteration of the evolution operation; In response to satisfying an iteration termination condition, merging the initial population with each of the child populations obtained in the iteration to obtain a population set; and A fitness evaluation is performed on each transport path in the population set to obtain the candidate path set based on the population set.

8. The method according to claim 7, wherein: The genetic algorithm is the NSGA-II algorithm.

9. A dispatching device based on multimodal transport, comprising: an acquisition module configured to acquire a transportation network and a current transportation demand, wherein the transportation network includes a plurality of transportation nodes and sub-transportation paths connecting adjacent transportation nodes, the current transportation demand includes a corresponding source transportation node and a target transportation node in the transportation network, and the transportation path from the source transportation node to the target transportation node includes a plurality of sub-transportation paths, and wherein each of the plurality of sub-transportation paths corresponds to one transportation mode among a plurality of transportation modes; A first determination module is configured to determine an initial path set corresponding to the current transportation demand using a shortest path algorithm for at least one optimization objective; An evolution module is configured to perform an evolution operation on the initial path set using a genetic algorithm to obtain a candidate path set; An establishing module configured to establish a scheduling model based on the current transportation demand and the candidate path set; and The second determination module is configured to determine the optimal solution of the scheduling model based on the objective function and the constraints, wherein the optimal solution represents the optimal transportation path for the current transportation demand, and wherein the objective function targets the at least one optimization goal.

10. The apparatus according to claim 9, further comprising: A prediction module, configured to predict transportation demand within a preset period in the future based on historical transportation demand using a pre-trained neural network model; A dispatching module, configured to dispatch transportation resources based on the predicted transportation demand within the preset period, wherein the transportation resources include the transportation capacity of the multiple transportation modes and the transportation capacity of the multiple transportation nodes; an updating module, configured to update the constraint condition based on the deployed transportation resources in response to receiving the actual transportation demand within the preset period; and The third determination module is configured to determine the optimal transportation path corresponding to the actual transportation demand based on the updated constraint conditions.

11. The device according to claim 9 or 10, wherein: The multiple modes of transportation include: road transportation, railway transportation and water transportation.

12. The device according to claim 11, wherein The constraints include at least one of the following: An upper limit of the transport volume corresponding to the transport node serving as the departure station among the plurality of transport nodes; An upper limit of the transport volume corresponding to the transport node serving as the destination station among the multiple transport nodes; An upper limit of the ratio of rail transport to water transport corresponding to the transport path from the source transport node to the target transport node; The transport capacity limit of the road transport corresponding to the transport path from the source transport node to the target transport node.

13. The device according to any one of claims 9 to 12, wherein: The first determining module comprises: A first determining unit, for each of the at least one optimization target, using the shortest path algorithm to determine a transportation path that meets the optimization target based on the source transportation node and the target transportation node; and The first merging unit is configured to merge the set of transport paths corresponding to each optimization target to obtain the initial path set, wherein the at least one optimization target includes at least one of the following: Minimum shipping costs, minimum shipping time, and minimum carbon emissions from shipping.

14. The device according to claim 13, wherein: The shortest path algorithm is Dijkstra's algorithm or Yen's K shortest path algorithm.

15. The device according to any one of claims 9 to 14, wherein: The evolution module comprises: An evolution unit, configured to use the initial path set as an initial population, and use the genetic algorithm to perform an evolution operation on the initial population to generate a descendant population for iteration of the evolution operation; a second merging unit, configured to merge the initial population with each of the child populations obtained in the iteration to obtain a population set in response to satisfying an iteration termination condition; and An evaluation unit is configured to perform fitness evaluation on each transportation path in the population set to obtain the candidate path set based on the population set.

16. The device according to claim 15, wherein: The genetic algorithm is the NSGA-II algorithm.

17. An electronic device comprising: at least one processor; as well as a memory communicatively coupled to the at least one processor; in The memory stores instructions that can be executed by the at least one processor, and the instructions are executed by the at least one processor to enable the at least one processor to perform the method according to any one of claims 1 to 8.

18. A non-transitory computer-readable storage medium storing computer instructions, wherein: The computer instructions are used to cause the computer to execute the method according to any one of claims 1-8.

19. A computer program product comprising a computer program, wherein: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

Images