A multimodal transport-oriented low-altitude logistics global coordination and dynamic scheduling method

Abstract

In view of the technical difficulties such as resource fragmentation, rigid scheduling, insufficient path planning, imperfect conflict processing and limited scalability existing in the current low-altitude logistics and multimodal transport process, the embodiment of the disclosure provides a low-altitude logistics global collaboration and dynamic scheduling method for multimodal transport. The method is applied to the technical field of low-altitude logistics, and includes steps 1-6. Based on the mechanisms such as unified modeling of transport nodes, time slicing and cross-node dynamic resource pool, combined with recommendation algorithm and multi-constraint scheduling optimization, the method can realize global collaboration, real-time conflict resolution and efficient resource allocation in the multimodal transport environment, and effectively improve the flexibility, adaptability and execution efficiency of the low-altitude logistics transport process.

Description

TECHNICAL FIELD

[0001] The present disclosure relates to the technical field of low-altitude logistics, and particularly relates to a low-altitude logistics global coordination and dynamic scheduling method for multimodal transport. BACKGROUND

[0002] With the rapid development of e-commerce, instant delivery and cross-regional supply chain, the timeliness, flexibility and reliability of the logistics transportation system are put forward with higher requirements. Low-altitude logistics, especially unmanned aerial vehicle delivery, gradually becomes an important supplement to traditional transportation methods due to its advantages of rapidness, flexibility and adaptability to complex terrain. However, in the complex environment of multimodal transport, the existing logistics system generally has the following problems: firstly, the multi-type resources such as warehouse, transfer, low-altitude transport, water transport, ground transport and terminal delivery cannot be uniformly modeled and globally scheduled, resulting in scattered resources and low utilization rate; secondly, the transportation node capacity, equipment state and environmental conditions have significant dynamics and uncertainty, and the traditional scheduling is mostly based on static planning, which is difficult to adjust flexibly during execution, and is easy to cause transportation interruption or delay; thirdly, the existing path planning method often only considers single target such as distance or cost, and lacks comprehensive trade-off of multi-dimensional conditions such as transportation tool characteristics, node attributes, goods demand and time constraints, resulting in insufficient feasibility and robustness of the generated transportation path; fourthly, when multiple batches of goods compete for the same transportation tool or node, there is a lack of effective conflict resolution and dynamic priority adjustment mechanism, which is easy to cause congestion and delay; fifthly, the current system is limited in scalability, and when new nodes or new transportation methods are connected, large-scale modification is often required, which is difficult to support cross-regional and multi-modal transport development. It can be seen that the existing technology has deficiencies in resource coordination, dynamic scheduling, conflict processing and system scalability. SUMMARY

[0003] In a first aspect, the embodiments of the present disclosure provide a low-altitude logistics global coordination and dynamic scheduling method for multimodal transport, which comprises:

[0004] Step 1: building a multimodal transport network, uniformly modeling warehouse, transfer, low-altitude transport, water transport, ground transport and terminal delivery station as a schedulable transportation node; wherein each transportation node is bound with static attributes and dynamic state, and the transportation tool records attribute parameters;

[0005] Step 2: in the scheduling process, introducing a time slicing mechanism to record and update the availability, capacity and equipment state of each transportation node and transportation tool in different time periods; constructing a dynamic resource pool across transportation nodes through the distance weight and connectivity relationship between transportation nodes, realizing resource linkage and dynamic scheduling in the global range, and continuously correcting the transportation node state according to the goods occupation, transportation node congestion degree and equipment allocation;

[0006] Step 3: According to the starting point, end point and inventory of the goods, the available warehouses are screened to generate a multimodal transport path candidate set; in this process, the transportation tools, transportation node attributes, time constraints and goods characteristics are comprehensively considered to generate transportation segments that meet the feasibility under multiple constraint conditions, and then a complete candidate path set, i.e. a multimodal transport path candidate set, is constructed;

[0007] Step 4: Considering the time matching degree, bearing adaptation degree, path efficiency and cost advantage, the Top-N optimal path is selected, and the predicted arrival time and total transportation cost are calculated; in the scheduling execution, when multiple batches of goods compete for the same resource, the time slice splitting and rearrangement strategy, the priority weight dynamic adjustment strategy, and the resource reallocation strategy between the transportation nodes and the transportation tools are adopted to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints;

[0008] Step 5: Based on real-time transportation data, the predicted arrival time is corrected, and the path comprehensive score weight is iteratively adjusted based on the optimization algorithm to realize adaptive optimization of the scheduling scheme under different goods types, time efficiency and cost constraints; when a new transportation node is added, only the static attributes and connectivity of the transportation node need to be modeled to access;

[0009] Step 6: Based on the path selection, multi-constraint resource scheduling is performed in real time, the transportation node capacity, equipment and transportation tools are dynamically allocated, the transportation segment order is adjusted, and the resource conflict is solved.

[0010] In some implementable manners of the first aspect, in step 1:

[0011] A multimodal transport network is constructed, and the warehouse nodes, transfer nodes, low-altitude transport nodes, water transport nodes, ground transport nodes and end delivery nodes are modeled as schedulable transportation nodes ; wherein any transportation node has static attributes and dynamically updated dynamic states over time; the static attributes include: transportation node capacity , used to represent the maximum capacity of the transportation node for storing goods and serve as a storage constraint; transportation tool accessibility , used to limit the set of transportation tools supported by the transportation node; and transportation node entrance and exit distance , used to calculate the loading and unloading and linking time; the dynamic state is updated over time , including: transportation node occupancy rate to ensure that the transportation node capacity is not exceeded; a set of transportation node goods types , used to reflect the goods types stored within a time and implement goods adaptation constraints; and transportation node equipment busy state ; any transportation tool has attribute parameters, including: average transportation speed , for determining transportation segment time consumption; load capacity , for constraining cargo weight ; voyage limit , for constraining transportation segment distance; processing time length , for counting transportation segment total time length; unit transportation cost , for path total cost calculation.

[0012] In some implementable manners of the first aspect, in step 2:

[0013] A time slicing mechanism is introduced in the scheduling process, and the total scheduling time is divided into discrete time slices, each time slice is recorded as , in each time slice, the transportation node state and the transportation tool state are updated, and dynamic scheduling and global resource optimization are performed;

[0014] Each transportation node In the dynamic state update of the time slice , the transportation node occupancy rate , the remaining capacity , the cargo type set , and the equipment busy state :

[0015] ;

[0016] ;

[0017] ;

[0018] ;

[0019] When the transportation node occupancy rate exceeds the threshold value, a congestion correction mechanism is triggered, and part of the cargo is re-routed to the adjacent transportation node according to the linkage weight to alleviate congestion, and the occupancy rate and the remaining capacity are updated; wherein, is:

[0020] ;

[0021] wherein, is a distance attenuation coefficient for adjusting the priority of resource allocation between nodes; is the spatial distance from the transportation node to the transportation node , is the spatial distance from the transportation node to the transportation node ;

[0022] Each transport vehicle In a time slice The state update includes: transport vehicle availability , transport time consumption , weight constraint and voyage constraint :

[0023] ;

[0024] ;

[0025] When the transport vehicle performs a task in a time slice Its busy state will remain busy within , where:

[0026] ;

[0027] Where, Is a discrete time slice.

[0028] In some implementations of the first aspect, in step 3:

[0029] In each time slice According to the transport node occupancy , equipment busy state , transport vehicle availability And the set of goods types , dynamically generate transport task allocation scheme , build scheduling model within the future rolling window The objective function Is:

[0030] ;

[0031] Where, Is the congestion penalty function of the transport node ; Is the goods delay penalty; Is the weight coefficient; The constraint conditions include node capacity, goods type matching, tool load and voyage limit and the busy state of transport vehicle and transport node in each time slice.

[0032] In some implementations of the first aspect, in step 3:

[0033] After completing the transport node modeling and dynamic scheduling preparation, according to the goods starting point , end point And inventory, for each piece of goods , screen the warehouse nodes set that can be received or transited in the time slice :

[0034] ;

[0035] to adjacent nodes and available transport means , generate transport segment candidates , and verify feasibility constraints and time constraints:

[0036] ;

[0037] ;

[0038] wherein, is the arrival time of the goods from the transport node to the transport node ; is the transport time of the transport means from the transport node to the transport node ; is the latest delivery time of the goods ;

[0039] The candidate set of transport segments that are feasible is denoted as , and is expressed as:

[0040] ;

[0041] Through recursive search, the candidate set of transport segments is connected to generate a complete candidate path set from the starting point to the ending point :

[0042] .

[0043] In some implementable manners of the first aspect, in step 4:

[0044] The complete candidate path set further introduces multi-dimensional evaluation indexes to preferentially rank the candidate paths, and for each candidate path , calculates four indexes of time matching degree , carrying adaptation degree , path efficiency and cost dominance :

[0045] , ​​denotes the expected arrival time;

[0046] ;

[0047] , denotes the number of transportation segments contained in the path;

[0048] ;

[0049] On the basis of the above indicators, the path comprehensive score function is defined :

[0050] ;

[0051] wherein, is an adjustable weight parameter;

[0052] According to , the candidate paths are sorted, and the top paths are selected to form a preferred path set , for any preferred path , its expected arrival time and total transportation cost are calculated as follows:

[0053] ;

[0054] .

[0055] In some implementable manners of the first aspect, in step 4:

[0056] In the process of scheduling execution, when there are multiple batches of goods simultaneously competing for the same transportation tool or transportation node resources, the following three strategies are used to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints:

[0057] Time slice splitting and rearrangement strategy:

[0058] The scheduling time is divided into discrete time slices , if there is a conflict task set in a time slice , then a delay operation is performed on the low-priority task:

[0059] ;

[0060] wherein is the priority weight of the goods , and is the conflict allocation threshold;

[0061] Priority weight dynamic adjustment strategy:

[0062] According to the timeliness, weight and value of the goods :

[0063] ;

[0064] Among them, is the weight of the goods; is the value of the goods; is the adjustable coefficient; is the normalization factor; through dynamic updating Make the key goods get the conflict resources in priority;

[0065] Resource redistribution strategy between transport nodes and transport tools:

[0066] In the dynamic resource pool across transport nodes , redistribute the idle transport node capacity and transport tools, so that the conflict resources are balanced and utilized:

[0067] ;

[0068] ;

[0069] Among them, is a decision variable, indicating whether the goods are allocated to the transport path from the transport node to the transport node .

[0070] In some implementable modes of the first aspect, in step 5:

[0071] During the scheduling execution, the expected arrival time is dynamically corrected based on real-time transport data:

[0072] ;

[0073] Among them, represents the corrected expected arrival time; represents the dynamic correction amount caused by delay, path deviation or congestion within the time slice ; while combining the rolling horizon optimization algorithm, the weight parameter is iteratively updated:

[0074] ;

[0075] Among them, is the updated weight parameter; is the weight parameter before updating; is a path synthesis loss function; is a learning rate; is a gradient of the loss function with respect to the weight parameter , indicating how to minimize the path synthesis loss function by adjusting ;

[0076] When a new transport node is added, only the static properties of the transport node and the connectivity relationship with the existing nodes need to be modeled, so that the transport node can be connected to the dynamic resource pool across transport nodes ; and the resource allocation and path planning are automatically updated in the next rolling window .

[0077] In a second aspect, the embodiments of the present disclosure provide an electronic device, which comprises at least one processor, and a memory connected with the at least one processor; the memory stores instructions executable 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 described above.

[0078] In a third aspect, the embodiments of the present disclosure provide a non-transitory computer-readable storage medium storing computer instructions, and the computer instructions are used to enable a computer to perform the method described above.

[0079] In the embodiments of the present disclosure, based on the mechanisms such as unified modeling of transport nodes, time slicing, and dynamic resource pool across nodes, combined with recommendation algorithms and multi-constraint scheduling optimization, global collaboration, real-time conflict resolution, and efficient resource allocation in a multimodal transport environment can be achieved, and the flexibility, adaptability, and execution efficiency of the low-altitude logistics transport process can be effectively improved.

[0080] It should be understood that the content described in the summary section is not intended to limit the key or important features of the embodiments of the present disclosure, nor to limit the scope of the present disclosure. Other features of the present disclosure will become apparent through the following description. BRIEF DESCRIPTION OF DRAWINGS

[0081] The above and other features, advantages, and aspects of the embodiments of the present disclosure will become more apparent by describing in detail the following embodiments with reference to the attached drawings. The accompanying drawings are used to better understand the present disclosure, and do not limit the present disclosure, and the same or similar reference numerals in the accompanying drawings represent the same or similar elements, in which:

[0082] Figure 1 A flowchart of a multimodal transport-oriented low-altitude logistics global collaboration and dynamic scheduling method provided by the embodiments of the present disclosure is shown;

[0083] Figure 2A radar chart of candidate path scoring is shown.

[0084] Figure 3 A time slicing and dynamic scheduling schematic diagram is shown.

[0085] Figure 4 A structural diagram of an exemplary electronic device capable of implementing the embodiments of the present disclosure is shown. DETAILED DESCRIPTION

[0086] To make the objectives, technical solutions and advantages of the embodiments of the present disclosure clearer, the technical solutions in the embodiments of the present disclosure will be described clearly and completely below with reference to the drawings in the embodiments of the present disclosure. Obviously, the described embodiments are some but not all of the embodiments of the present disclosure. Based on the embodiments in the present disclosure, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present disclosure.

[0087] In addition, the term "and / or" herein is only to describe the association relationship of the associated objects, which means that there can be three relationships, for example, A and / or B can mean that A exists alone, A and B exist together, and B exists alone. In addition, the character " / " herein generally represents an "or" relationship between the front and rear associated objects.

[0088] To solve the technical problems in the background art, the embodiments of the present disclosure provide a multi-modal transport-oriented low-altitude logistics global collaboration and dynamic scheduling method, which can realize global collaboration, real-time conflict resolution and resource efficient allocation in a multi-modal transport environment based on mechanisms such as unified modeling of transport nodes, time slicing and cross-node dynamic resource pool, combined with recommendation algorithms and multi-constraint scheduling optimization, and effectively improve the flexibility, adaptability and execution efficiency of the low-altitude logistics transport process.

[0089] The multi-modal transport-oriented low-altitude logistics global collaboration and dynamic scheduling method provided by the embodiments of the present disclosure will be described in detail below with reference to the drawings and specific embodiments.

[0090] Figure 1 A flowchart of the multi-modal transport-oriented low-altitude logistics global collaboration and dynamic scheduling method provided by the embodiments of the present disclosure is shown, as shown in Figure 1 The method 100 can include the following steps:

[0091] Step 1: Build a multi-modal transport network, and uniformly model warehouses, transit stations, low-altitude transport, water transport, ground transport and end delivery stations as schedulable transport nodes; wherein each transport node is bound to static attributes and dynamic states, and the transport tool records attribute parameters.

[0092] In some embodiments, a multi-modal transportation network is constructed, in which warehouse nodes, transfer nodes, low-altitude transportation nodes, water transportation nodes, ground transportation nodes, and end-delivery nodes are modeled as schedulable transportation nodes . Each transportation node has static attributes and dynamic states that are updated over time. Further, the static attributes include: transportation node capacity , which represents the maximum capacity of the transportation node for storing goods and serves as a storage constraint; transportation tool accessibility , which defines a set of transportation tools supported by the transportation node; and transportation node access distance , which is used to calculate the loading and unloading and interfacing time. The dynamic states are updated over time and include: transportation node occupancy , which ensures that the transportation node capacity is not exceeded; a set of transportation node goods types , which reflects the types of goods stored over time and implements a goods matching constraint; and transportation node device busy state . Each transportation tool (e.g., a drone, a truck, a ship, etc.) has attribute parameters, including: average transportation speed , which is used to determine the transportation segment time consumption; load capacity , which is used to constrain the weight of the goods ; range limit , which is used to constrain the distance of the transportation segment; processing time , which is used to account for the total transportation segment time; and unit transportation cost , which is used for total path cost calculation.

[0093] Step 2: In the scheduling process, a time slicing mechanism is introduced to record and update the availability, capacity, and device state of each transportation node and transportation tool at different time periods; a dynamic resource pool across transportation nodes is constructed based on the distance weight and connectivity relationship between transportation nodes, to achieve resource linkage and dynamic scheduling in a global range, and the transportation node state is continuously corrected based on the goods occupancy, transportation node congestion level, and device allocation.

[0094] In some embodiments, a time slicing mechanism is introduced in the scheduling process to record and update the availability, capacity, and device state of each transportation node and transportation tool at different time periods.

[0095] Specifically, the total scheduling time is divided into discrete time slices, each time slice is denoted as , and in each time slice, the transportation node state and the transportation tool state are updated, and dynamic scheduling and global resource optimization are performed.

[0096] Each transportation node In time slice Dynamic status updates include: transport node occupancy rate Remaining capacity Goods type set and equipment busy / idle status .

[0097] (1)

[0098] (2)

[0099] (3)

[0100] (4)

[0101] When the occupancy rate of a transportation node exceeds a threshold, a congestion correction mechanism is triggered, and some goods are affected according to the linkage weight. Rerouting to nearby transport nodes To alleviate congestion and update occupancy and remaining capacity. Among these, for:

[0102] (5)

[0103] in, This is the distance decay coefficient, used to adjust the priority of resource allocation between nodes; For transportation nodes To the transportation node Spatial distance, For transportation nodes To the transportation node Spatial distance.

[0104] Each means of transport In time slice Status updates include: availability of transportation vehicles Transportation time Weight constraints and range constraints .

[0105] (6)

[0106] (7)

[0107] When the transportation vehicle is in time slice When performing a task, its busy / idle status will be... The internal environment remains busy. Among them, for:

[0108] (8)

[0109] in, It is a discrete time slice.

[0110] Furthermore, a dynamic resource pool across transportation nodes is constructed by using distance weights and connectivity relationships between transportation nodes. It enables global resource linkage and dynamic scheduling, and continuously corrects the status of transportation nodes based on cargo occupancy, transportation node congestion, and equipment allocation.

[0111] Step 3: Based on the origin, destination and inventory status of the goods, select available warehouses and generate a candidate set of multimodal transport routes. In this process, the attributes of transport vehicles, transport nodes, time constraints and cargo characteristics are comprehensively considered to generate feasible transport segments under multiple constraints, thereby constructing a complete candidate route set, that is, a candidate set of multimodal transport routes.

[0112] In some embodiments, available warehouses are selected based on the origin, destination, and inventory status of the goods.

[0113] Specifically, in each time slice Internally, based on the occupancy rate of transportation nodes Equipment busy / idle status Transportation availability and cargo type set Dynamically generate transportation task allocation schemes Building future scrolling windows The scheduling model within the system. Its objective function. for:

[0114] (9)

[0115] in, For transportation nodes The congestion penalty function; Penalties for delayed shipments; The weighting coefficients are used for the constraints, which include node capacity, cargo type matching, tool load and range limits, and the busy / idle status of transport tools and transport nodes in each time slice.

[0116] According to the origin of the goods ,end And inventory status, for each item Filtering in time slices The set of warehouse nodes that can be received or transferred within the system. .

[0117] (10)

[0118] Further, for adjacent nodes and available transport means , a transport segment candidate is generated, and the feasibility constraint and time constraint are verified.

[0119] (11)

[0120] (12)

[0121] wherein, is the arrival time of the goods from the transport node to the transport node ; is the transport time of the transport means from the transport node to the transport node ; is the latest delivery time of the goods .

[0122] The candidate set of transport segments that are feasible is denoted as , and is expressed as:

[0123] (13)

[0124] Finally, through recursive search, the candidate set of transport segments is connected to generate a complete candidate path set from the starting point to the ending point .

[0125] (14)

[0126] Step 4: Considering the time matching degree, the carrying adaptation degree, the path efficiency, and the cost superiority, Top-N optimal paths are selected, and the expected arrival time and the total transport cost are calculated; in the scheduling execution, when multiple batches of goods compete for the same resource, the time slice splitting and rearrangement strategy, the priority weight dynamic adjustment strategy, and the resource reallocation strategy between the transport nodes and the transport means are adopted to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints.

[0127] In some embodiments, considering the time matching degree, the carrying adaptation degree, the path efficiency, and the cost superiority, Top-N optimal paths are selected, and the expected arrival time and the total transport cost are calculated.

[0128] Specifically, further introducing multi-dimensional evaluation indexes, the candidate paths are optimally sorted, and for each candidate path , the time matching degree , the carrying adaptation degree path efficiency and cost dominance Four indicators.

[0129] , denotes the estimated arrival time (15)

[0130] (16)

[0131] , denotes the number of transportation segments contained in the path (17)

[0132] (18)

[0133] Based on the above indicators, different paths can be comprehensively evaluated. As shown in Figure 2 , the larger the radar chart area, the better the overall performance of the path under the multi-dimensional indicators, and the priority is also correspondingly improved. In practical applications, different weights can be assigned to each indicator according to different transportation needs, and the total score of each path can be calculated through the path comprehensive scoring formula .

[0134] (19)

[0135] wherein, is an adjustable weight parameter.

[0136] According to , the candidate paths are sorted, and the top paths are selected to form the preferred path set , for any preferred path , its estimated arrival time and total transportation cost are calculated as follows:

[0137] (20)

[0138] (21)

[0139] Further, in the scheduling execution process, as shown in Figure 3 , when there are multiple batches of goods competing for the same transportation tool or transportation node resources at the same time, the following three strategies are used to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints.

[0140] Time slice splitting and rearrangement strategy:

[0141] Divide the scheduling time into discrete time slices , if there are multiple batches of goods competing for the same transportation tool or transportation node resources in a certain time slice ,Intra-process memory conflict task set If the low priority task is executed, a delay operation is performed.

[0142] (22)

[0143] Wherein The priority weight of the goods , the conflict allocation threshold .

[0144] Priority weight dynamic adjustment strategy:

[0145] According to the timeliness, weight and value of the goods .

[0146] (23)

[0147] Wherein, The weight of the goods The value of the goods Adjustable coefficient Normalization factor; By dynamically updating The critical goods are given priority to obtain conflict resources.

[0148] Resource redistribution strategy between transport nodes and transport tools:

[0149] In the dynamic resource pool across transport nodes , the idle transport node capacity and transport tools are redistributed to balance the utilization of conflict resources.

[0150] (24)

[0151] (25)

[0152] Wherein, A decision variable, indicating whether the goods Is allocated to the transport path from the transport node To transport node .

[0153] Step 5: Based on real-time transportation data, the estimated arrival time is corrected, and the path comprehensive score weight is adjusted iteratively combined with optimization algorithm to realize adaptive optimization of scheduling scheme under different goods types, timeliness and cost constraints; When a new transport node is added, only the static attributes and connectivity of the transport node need to be modeled to quickly access, maintain scalability and resource scheduling consistency.

[0154] In some embodiments, during the scheduling execution process, the estimated arrival time Is dynamically corrected based on real-time transportation data.

[0155] (26)

[0156] wherein, represents the corrected expected arrival time; represents the dynamic correction amount caused by delay, path deviation or congestion within the time slice ; and the weight parameter is iteratively updated in combination with the rolling horizon optimization algorithm.

[0157] (27)

[0158] wherein, is the updated weight parameter; is the weight parameter before updating; is the path comprehensive loss function; is the learning rate; is the gradient of the loss function with respect to the weight parameter , indicating how to minimize the path comprehensive loss function by adjusting .

[0159] When a new transportation node is added, only the static attribute and the connectivity relationship with the existing nodes need to be modeled, and the transportation node can be connected to the dynamic resource pool across transportation nodes . In the next rolling window , the resource allocation and path planning are automatically updated to ensure scalability and resource scheduling consistency.

[0160] Step 6: Based on the selected path, real-time multi-constraint resource scheduling is performed to dynamically allocate transportation node capacity, equipment and transportation tools, adjust transportation segment order, solve resource conflicts, and ensure efficient, continuous and controllable transportation scheme in actual execution.

[0161] In summary, the embodiments of the present disclosure can realize global collaboration, real-time conflict resolution and efficient resource allocation in a multimodal transport environment based on unified modeling of transportation nodes, time slicing and cross-node dynamic resource pool mechanisms, in combination with recommendation algorithms and multi-constraint scheduling optimization, effectively improving the flexibility, adaptability and execution efficiency of the low-altitude logistics transportation process.

[0162] ​It should be noted that, for the foregoing method embodiments, the purposes of simple description, the foregoing method embodiments are all described as a series of action combinations, but those skilled in the art should know that the present disclosure is not limited to the action sequence described, because according to the present disclosure, certain steps can be performed in other sequences or simultaneously. Secondly, those skilled in the art should know that the embodiments described in the specification are all optional embodiments, and the actions and modules involved are not necessarily required by the present disclosure.

[0163] The above is the introduction of the method embodiment, and the scheme of the present disclosure is further described through the electronic device embodiment.

[0164] Figure 4 A structural diagram of an exemplary electronic device capable of implementing the embodiments of the present disclosure is shown. The electronic device 400 is intended to represent various forms of digital computers, such as laptops, desktops, tablets, personal digital assistants, servers, blade servers, mainframes, and other appropriate computers. The electronic device 400 can also represent various forms of mobile devices, such as personal digital processors, cellular telephones, smart phones, wearable devices, and other similar computing devices. The components shown here, their connections and relationships, and their functions, are meant to be examples only, and are not intended to limit the implementations of the present disclosure described and / or claimed in this document.

[0165] As shown in Figure 4 The electronic device 400 can include a computing unit 401 that can perform various appropriate actions and processes according to computer programs stored in a read-only memory (ROM) 402 or loaded into a random access memory (RAM) 403 from a storage unit 408. Various programs and data required for the operation of the electronic device 400 can also be stored in the RAM 403. The computing unit 401, the ROM 402, and the RAM 403 are connected to each other through a bus 404. An input / output (I / O) interface 405 is also connected to the bus 404.

[0166] Various components in the electronic device 400 are connected to the I / O interface 405, including an input unit 406 such as a keyboard, a mouse, etc., an output unit 407 such as various types of displays, a speaker, etc., a storage unit 408 such as a magnetic disk, an optical disk, etc., and a communication unit 409 such as a network card, a modem, a wireless communication transceiver, etc. The communication unit 409 allows the electronic device 400 to exchange information / data with other devices through a computer network such as the Internet and / or various telecommunications networks.

[0167] The computing unit 401 can be various general and / or special purpose processing components with processing and computing capabilities. Some examples of the computing unit 401 include, but are not limited to, a central processing unit (CPU), a graphics processing unit (GPU), various specialized artificial intelligence (AI) computing chips, various computing units running machine learning model algorithms, a digital signal processor (DSP), and any appropriate processor, controller, microcontroller, etc. The computing unit 401 performs various methods and processes described above, such as the method 100. For example, in some embodiments, the method 100 can be implemented as a computer program product, including a computer program tangibly embodied in a computer-readable medium, such as the storage unit 408. In some embodiments, part or all of the computer program can be loaded and / or installed onto the device 400 via the ROM 402 and / or the communication unit 409. When the computer program is loaded onto the RAM 403 and executed by the computing unit 401, one or more steps of the method 100 described above can be performed. Alternatively, in other embodiments, the computing unit 401 can be configured to perform the method 100 by any other appropriate means, such as by means of firmware.

[0168] The various implementations described above can be implemented in digital electronic circuitry, integrated circuitry, a field programmable gate array (FPGA), an application specific integrated circuit (ASIC), a system on a chip (SOC), a programmable logic device (PLD), a computer hardware, firmware, software, and / or combinations thereof. These various implementations can include implementation in one or more computer programs that are executable and / or interpretable on a programmable system including at least one programmable processor, which can be special or general purpose, coupled to receive data and instructions from, and to transmit data and instructions to, a storage system, at least one input device, and at least one output device.

[0169] Program code for carrying out methods of the present disclosure can be written in any combination of one or more programming languages. The program code can be provided to a processor or controller of a general purpose computer, special purpose computer, or other programmable data processing apparatus to produce a machine, such that the program code, when executed by the processor or controller, produces a means for implementing the functions / operations specified in the flowchart and / or block diagram. The program code can be executed entirely on a machine, partially on a machine, partially on a machine as a stand-alone software package, partially on a machine and partially on a remote machine or entirely on a remote machine or server.

[0170] In the context of the present disclosure, a computer-readable medium can be a tangible medium that can contain or store a program for use by or in connection with an instruction execution system, apparatus, or device. The computer-readable medium can be a computer-readable signal medium or a computer-readable storage medium. The computer-readable medium can include, but is not limited to, electronic, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any suitable combination of the foregoing. More specific examples of the computer-readable storage medium will include one or more of: a portable computer diskette, 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 disc read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the foregoing.

[0171] It should be noted that the present disclosure also provides a non-transitory computer-readable storage medium storing computer instructions, where the computer instructions are used to make a computer execute the method 100, and achieve the corresponding technical effects achieved by the embodiments of the present disclosure executing the method. For brevity, the description will not be repeated here.

[0172] In addition, the present disclosure also provides a computer program product, which includes a computer program, and the computer program, when executed by a processor, implements the method 100.

[0173] To provide for interaction with a user, the above described embodiments 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 a pointing device (e.g., a mouse or a trackball) by which the user can provide input to the computer. Other kinds of devices can be used to provide for interaction with a user as well; for example, 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, speech, or tactile input.

[0174] The embodiments described above can be implemented in a computing system that includes a back end component, e.g., as a data server, or that includes a middleware component, e.g., an application server, or that includes a front end component, e.g., a user computer having a graphical user interface or a Web browser through which a user can interact with an implementation of the systems and techniques described here, or any combination of such back end, middleware, or front end components. The components of the system can 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.

[0175] The computer system can include clients and servers. The clients and the servers are generally remote from each other and typically interact through a communication network. The relationship of client and server arises by virtue of computer programs running on the respective computers and having a client-server relationship to each other. The server can be a cloud server, a server of a distributed system, or a server combined with a blockchain.

[0176] It should be understood that the various forms of flow shown above can be re-ordered, added to, or deleted from without departing from the scope of the present disclosure. For example, the steps recited in the disclosure can be executed in parallel, executed in sequence, or executed in different orders, as long as the desired results of the technical solutions disclosed in the disclosure are achieved, and the present disclosure is not limited herein.

[0177] The specific embodiments described above are not intended to be limiting, and persons skilled in the art will appreciate that various modifications, combinations, sub-combinations and alternatives can be made to the specific embodiments without departing from the spirit and principles of the disclosure. Any further modifications, equivalents, alternatives, and / or improvements made to the specific embodiments described above are intended to fall within the scope of the disclosure.

Claims

1. A method for multi-modal low-altitude logistics global coordination and dynamic scheduling, characterized in that, The method comprises: Step 1: Constructing a multimodal transport network, integrating warehouses, transfer stations, low-altitude transport, water transport, ground transport and end delivery stations into schedulable transport nodes; wherein each transport node is bound to static attributes and dynamic states, and the transport tool records attribute parameters; Step 2: In the scheduling process, introduce a time slicing mechanism to record and update the availability, capacity and equipment state of each transport node and transport tool in different time periods; through the distance weight and connectivity relationship between transport nodes, a dynamic resource pool across transport nodes is constructed to realize resource linkage and dynamic scheduling in the global range, and the transport node state is continuously corrected according to the cargo occupation, transport node congestion degree and equipment allocation; Step 3: According to the cargo starting point, end point and inventory, filter available warehouses to generate a multimodal transport path candidate set; wherein the transport tool, transport node attribute, time constraint and cargo characteristics are considered in this process to generate a transport section that meets the feasibility under multiple constraint conditions, and then a complete candidate path set, i.e. a multimodal transport path candidate set, is constructed; Step 4: Considering time matching degree, bearing adaptation degree, path efficiency and cost dominance, selecting Top-N optimal paths and calculating the predicted arrival time and total transportation cost; in the scheduling execution, when multiple batches of goods compete for the same resource, time slice splitting and rearrangement strategy, priority weight dynamic adjustment strategy, resource reallocation strategy between transport nodes and transport tools are adopted to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints; Step 5: Based on real-time transport data, the predicted arrival time is corrected, and the path comprehensive score weight is iteratively adjusted combined with the optimization algorithm to realize adaptive optimization of the scheduling scheme under different cargo types, time efficiency and cost constraints; when a new transport node is added, only the static attributes and connectivity of the transport node need to be modeled to access; Step 6: Based on path selection, real-time multi-constraint resource scheduling is performed to dynamically allocate transport node capacity, equipment and transport tools, adjust transport segment order and solve resource conflicts.

2. The method of claim 1, wherein, In step 1: Construct a multimodal transport network, unifying the modeling of warehousing nodes, transshipment nodes, low-altitude transport nodes, water transport nodes, ground transport nodes, and last-mile delivery nodes as schedulable transport nodes. ; among them, any transportation node It has static attributes and dynamic states that update over time; the static attributes include: transport node capacity. This represents the maximum capacity for storing goods at a transportation node and serves as a storage constraint; transportation vehicle accessibility. This is used to limit the set of transportation vehicles supported by a transportation node; and the distance between the entrance and exit of the transportation node. Used to calculate loading, unloading, and connection times; dynamic status over time. Updates include: transport node occupancy rate To ensure that the capacity of transportation nodes is not exceeded; the set of cargo types for transportation nodes. Used to reflect time The system stores the types of goods in memory and implements goods adaptation constraints; it also tracks the busy / idle status of transportation node equipment. Any means of transport It has attribute parameters, including: average transport speed Used to determine the time taken for each transport segment; load capacity Used to constrain the weight of goods Flight range restrictions Used to constrain the distance of transportation segments; processing time Used to calculate the total duration of the transportation segment; unit transportation cost , used for calculating total path cost.

3. The method of claim 2, wherein, In step 2: In the scheduling process, a time slicing mechanism is introduced to divide the total scheduling time into discrete time slices, each of which is denoted as In each time slice, the transport node state and the transport tool state are updated, and dynamic scheduling and global resource optimization are performed. Each transport node In time slice The dynamic state update includes: transport node occupancy , remaining capacity , cargo type set and equipment busy state : ； ； ； ； When the transport node occupancy exceeds a threshold, trigger a congestion correction mechanism, part of the goods according to the linkage weight Re-route to adjacent transport nodes To alleviate congestion, and update the occupancy and remaining capacity; wherein, For: ； wherein, is a distance attenuation coefficient, used to adjust the priority of resource allocation between nodes; is a transport node is a spatial distance from a transport node to a transport node is a spatial distance from a transport node to a transport node to a transport node Each transport vehicle At the time slice The status update includes: transport vehicle availability , transport duration , weight constraints and voyage constraints : ； ； When the transport is executing a task, its busy state will be kept as busy within the time slice wherein:​ ； wherein is a discrete time slice.

4. The method of claim 3, wherein, In step 3: In each time slice Internally, based on the occupancy rate of transportation nodes Equipment busy / idle status Transportation availability and the set of goods types Dynamically generate transportation task allocation schemes Building future scrolling windows The scheduling model within the system, its objective function for: ； wherein, is a congestion penalty function for the transport node ; is a cargo delay penalty; is a weight coefficient; constraints include node capacity, cargo type matching, vehicle load and journey limits, and busy status of transport nodes and vehicles in each time slice.

5. The method of claim 4, wherein, In step 3: After the modeling of transport nodes and the preparation of dynamic scheduling, according to the origin , destination and inventory of each piece of cargo , the set of warehouse nodes that can receive or transit the cargo in the time slice is screened : ； to neighboring nodes and available transportation means generating transportation segment candidates and verifying feasibility constraints and time constraints: ； ； wherein, is the cargo arrival time from the transport node to the transport node arrival time from the transport node is the transport means transport time from the transport node to the transport node transport time from the transport node is the cargo latest delivery time The feasible candidate set of the transport segment is denoted as is expressed as: ； By recursive search, the candidate set of transport segments is connected, generating a complete candidate path set from the start to the end point : 。 6. The method of claim 5, wherein, In step 4: Complete candidate path set Furthermore, multi-dimensional evaluation indicators are introduced to optimize and rank the candidate paths, and for each candidate path... Calculate time matching degree Load-bearing adaptability Path efficiency and cost advantage Four indicators: , represents the estimated time of arrival; ； , represents the number of transport segments comprised by the path; ； On the basis of the above indexes, the path comprehensive score function is defined : ； wherein, is an adjustable weight parameter; According to the candidate paths are ranked and the top paths are selected to form a set of preferred paths For any preferred path its predicted arrival time and total transportation cost are calculated as follows: ； 。 7. The method of claim 6, wherein, In step 4: In the scheduling execution process, when multiple batches of goods compete for the same transport tool or transport node resource at the same time, the following three strategies are used to ensure that the scheduling scheme still has feasibility and continuity under multi-dimensional constraints: Time slice splitting and rearrangement strategy: Divide the dispatch time into discrete time slices If there is a set of conflicting tasks in a time slice , perform a defer operation on the lower priority task: ； wherein is a priority weight for the goods of the goods, assigns a threshold value to the conflict; Priority weight dynamic adjustment strategy: According to the time-sensitive, weight and value of the goods comprehensive calculation : ； wherein, is the weight of the cargo; is the value of the cargo; is an adjustable coefficient; is a normalization factor; dynamically updated prioritizes critical cargo for conflict resources; Resource reallocation strategy between transport nodes and transport tools: Dynamic resource pooling across transport nodes In which idle transport node capacity and transport means are redistributed to equalize the utilization of conflicting resources: ； ； wherein, is a decision variable representing whether a cargo is assigned to a transport path from a transport node to a transport node .

8. The method of claim 7, wherein, In step 5: During dispatch execution, the estimated time of arrival is dynamically revised based on real-time transportation data revised: ； wherein, represents the revised expected arrival time; represents the dynamic correction amount caused by delay, path deviation or congestion within the time slice ; and the weight parameter is iteratively updated in combination with the rolling horizon optimization algorithm. ； wherein, is the updated weight parameter; is the weight parameter before update; is the path synthesis loss function; is the learning rate; is the gradient of the loss function with respect to the weight parameter denotes how to minimize the path synthesis loss function by adjusting the weight parameter When a new transport node is added , only its static properties and connectivity with existing nodes need to be modeled , and the new transport node is automatically connected to the dynamic resource pool across transport nodes ; resource allocation and path planning are automatically updated in the next rolling window .

9. An electronic device, comprising: The electronic device comprises at least one processor and a memory connected in communication with 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 to enable the at least one processor to perform the method of any one of claims 1-8.

10. A non-transitory computer-readable storage medium having stored thereon computer instructions, wherein, The computer instructions are used to make the computer execute the method of any one of claims 1-8.

Images