Low-altitude and ground traffic cooperative passenger and freight mixed transport multimodal transport planning method

Abstract

The invention relates to a low-altitude and ground traffic cooperative passenger and freight mixed transport multimodal transport planning method. The method comprises the steps that firstly, transportation order information and traffic basic information are acquired, the transportation order information comprises pickup and delivery places, information of parcels or passengers, time limitation and order priority, and the traffic basic information comprises station information and transportation tool information; then, a mixed integer linear programming model is constructed based on the traffic basic information, constraint conditions are determined in combination with the transportation order information, and a target function of low-altitude collaborative mixed passenger and freight multimodal transport planning is defined; and finally, solving based on the objective function and the constraint condition by adopting an adaptive large neighborhood search algorithm to obtain a low-altitude collaborative hybrid passenger and freight multimodal transport planning scheme. And optimization of vehicle paths and resource allocation of the electric vertical take-off and landing aircraft and the unmanned aerial vehicle in low-altitude transportation is facilitated, the transportation efficiency is improved, and the method has important reference value for promoting sustainable development of low-altitude economy.

Description

Technical Field

[0001] The present application relates to the fields of traffic engineering and low-altitude economic technology, and in particular to a multimodal transport planning method for mixed passenger and freight transportation in coordination with low-altitude and ground transportation. Background Art

[0002] In the traditional multimodal transport planning system, it mainly relies on ground transportation, such as road truck transportation and rail transportation, as well as conventional modes such as air transportation. However, this planning model has gradually exposed many defects in dealing with the complex and changing transportation needs of modern times. Especially today when drone technology is becoming increasingly mature, traditional planning has seriously insufficient consideration of the application of drones as an emerging mode of transportation.

[0003] The traditional multimodal transport model seems to be unable to cope with complex transportation needs. In the scenarios of emergency material transportation and rapid personnel transfer, traditional transportation methods are difficult to meet the requirements of efficiency. For example, in rescue operations after natural disasters, medical supplies, food and rescue personnel are urgently needed to be quickly delivered to the disaster-stricken areas. However, traditional ground transportation may be hindered by road damage and traffic control. Although air transportation is fast, it is limited by airport facilities and take-off and landing conditions, and cannot directly transport materials to the core disaster area. In addition, the traditional model lacks flexibility in dealing with time window restrictions. In commercial distribution, customers often have strict requirements on the delivery time of goods, but traditional transportation methods are difficult to flexibly adjust transportation routes within the specified time window to ensure that the goods are delivered on time when faced with uncertain factors such as traffic congestion and weather changes.

[0004] In terms of the coordinated operation of multiple modes of transportation, traditional planning has also failed to fully consider the optimization of costs and resources. The connection between different modes of transportation is often not smooth enough, resulting in the goods staying too long during the transit process, increasing transportation costs and reducing resource utilization efficiency. For example, when goods are transferred from railway transportation to road transportation, they may be piled up due to imperfect transit facilities and unreasonable scheduling, which not only wastes storage resources but also prolongs the transportation cycle.

[0005] In the case of urban traffic congestion and inconvenient transportation in remote areas, the drawbacks of traditional transportation planning are more prominent. In the urban distribution scenario, with the expansion of the urban scale and the booming development of e-commerce business, the urban road congestion is becoming increasingly serious. Traditional ground transportation vehicles frequently encounter traffic jams, resulting in delayed cargo delivery and unable to meet the requirements of customers for timeliness. According to statistics, in some big cities, the average speed of ground delivery vehicles during peak hours is only 15-20 kilometers per hour, seriously affecting the delivery efficiency. When rescuing in remote areas, due to poor road conditions and weak infrastructure, traditional transportation methods, such as road transportation, cannot deliver rescue supplies and personnel in time. For example, after a geological disaster occurs in the mountainous area, the narrow and rugged mountain roads make it difficult for large trucks to pass, and traditional air transportation is limited by the terrain and it is difficult to find a suitable landing site, resulting in delays in rescue work and the affected people cannot be rescued in time. These problems not only lead to increased transportation costs and low transportation efficiency, but also make it difficult to guarantee the service quality, seriously restricting the development of the multimodal transport industry.

[0006] Therefore, in the related technologies, there is an urgent need for a method that can optimize the multimodal transport route and resource allocation, improve the transportation efficiency and reduce the transportation cost. Summary of the Invention

[0007] Based on this, it is necessary to provide a passenger and cargo mixed transport multimodal transport planning method for low-altitude and ground traffic coordination that can optimize the multimodal transport route and resource allocation, improve the transportation efficiency and reduce the transportation cost for the above technical problems.

[0008] In the first aspect, the present application provides a passenger and cargo mixed transport multimodal transport planning method for low-altitude and ground traffic coordination. The method includes:

[0009] Obtain transportation order information and basic traffic information, where the transportation order information includes pick-up and delivery locations, information of parcels or passengers, time limit and order priority, and the basic traffic information includes station information and transportation tool information;

[0010] Based on the basic traffic information, construct a mixed-integer linear programming model, determine the constraint conditions in combination with the transportation order information, and define the objective function of the low-altitude coordinated mixed passenger and cargo multimodal transport planning;

[0011] Use the adaptive large neighborhood search algorithm to solve based on the objective function and constraint conditions to obtain the low-altitude coordinated mixed passenger and cargo multimodal transport planning scheme.

[0012] Optionally, in an embodiment of the present application, the transportation order information includes:

[0013] Calculate the geospatial distance using the Haversine formula, and represent the random arrival of traffic orders using a non-homogeneous Poisson process.

[0014] Optionally, in an embodiment of the present application, the objective function is:

[0015] minF = F1 + F2 + F3 + F4 + F5

[0016]

[0017] where F is the total cost, F1 is the transportation cost, F2 is the transshipment cost, F3 is the storage cost, F4 is the carbon tax, F5 is the delay penalty, K is the set of transportation tools, including drones, electric vertical takeoff and landing aircraft, and fixed transportation tools; A is the set of arcs, A p is the set of pickup arcs, A d is the set of delivery arcs; R is the set of orders; T is the transshipment point; is the unit cost of different items, n ∈ 1, 1′, 2, 3, 4, c k 1 / c k 1′ is the transportation cost per hour per kilometer per kilogram when using transportation tool k ∈ K; c k 2 is the loading (or unloading) cost per kilogram; c k 3 is the storage cost per kilogram per hour; c k 4 is the carbon tax coefficient per ton; c k 5 is the delay penalty cost per kilogram per hour; is the travel time of transportation tool k on arc (i, j), is the distance between stations i and j for transportation tool k, q r is the quantity of order r; is a binary variable, which is 1 if order r transported by transportation tool k uses arc (i, j), otherwise 0; is a binary variable, which is 1 if order r is transferred from transportation tool k to transportation tool l at transshipment station i, otherwise 0; and are the service start times of transportation tools k and l for order r at station i, is the service end time of transportation tool k for order r at station i, a p(r) is the pickup start time of order r, e k is the emission of transportation tool k ∈ K per kilogram per kilometer, is the delay time of order r at the delivery location.

[0018] Optionally, in an embodiment of the present application, the constraint conditions include space-related constraints, transfer-related constraints, flow conservation constraints, transport vehicle characteristic-related constraints, and time-related constraints.

[0019] Optionally, in an embodiment of the present application, the space-related constraints include origin-destination and route restrictions, sub-tour route constraints, cargo pick-up and delivery point constraints, and capacity limitations; the transfer-related constraints include transfer number limitations and transfer transport vehicle limitations; the flow conservation constraints include transport vehicle flow conservation, order flow conservation, and order-transport vehicle association constraints; the transport vehicle characteristic-related constraints include route applicability constraints, predefined route constraints, and transfer terminal matching constraints; and the time-related constraints include service time sequence constraints, travel time and speed-distance constraints, time window constraints, waiting and delay time constraints, and drone time constraints.

[0020] Optionally, in an embodiment of the present application, the solving of the adaptive large neighborhood search algorithm based on the objective function and the constraint conditions includes:

[0021] Selecting an insertion operator, a removal operator, and a swap operator according to the transport order information, and adjusting the low-altitude collaborative hybrid passenger and cargo multimodal transport plan based on the insertion operator, the removal operator, and the swap operator.

[0022] Optionally, in an embodiment of the present application, the insertion operator includes a greedy insertion operator, a transfer insertion operator, and a regret insertion operator; the removal operator includes a worst removal operator, a random removal operator, a correlation removal operator, a historical removal operator, and a route removal operator.

[0023] In a second aspect, the present application further provides a device for low-altitude and ground traffic collaborative passenger and cargo mixed transport multimodal transport planning. The device includes:

[0024] A demand acquisition module, configured to acquire transport order information and basic traffic information, where the transport order information includes pick-up and delivery locations, information of parcels or passengers, time restrictions, and order priorities, and the basic traffic information includes station information and transport vehicle information;

[0025] A mixed integer programming model construction module, configured to construct a mixed integer linear programming model based on the basic traffic information, determine constraint conditions in combination with the transport order information, and define an objective function for low-altitude collaborative passenger and cargo multimodal transport planning;

[0026] A low-altitude collaborative passenger and cargo multimodal transport planning module, configured to solve using an adaptive large neighborhood search algorithm based on the objective function and the constraint conditions to obtain a low-altitude collaborative passenger and cargo multimodal transport planning scheme.

[0027] In a third aspect, the present application also provides a computer device. The computer device includes a memory and a processor. The memory stores a computer program, and the processor executes the steps of the methods described in the above various embodiments.

[0028] In a fourth aspect, the present application also provides a computer-readable storage medium. On the computer-readable storage medium, a computer program is stored, and when the computer program is executed by a processor, the steps of the methods described in the above various embodiments are implemented.

[0029] For the above method for planning a mixed passenger and freight multimodal transport with coordinated low-altitude and ground transportation, first, transportation order information and basic traffic information are obtained. Among them, the transportation order information includes pick-up and delivery locations, information about packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information; then, a mixed-integer linear programming model is constructed based on the basic traffic information, constraint conditions are determined in combination with the transportation order information, and an objective function for planning the coordinated low-altitude mixed passenger and freight multimodal transport is defined; finally, an adaptive large neighborhood search algorithm is used to solve based on the objective function and constraint conditions to obtain a coordinated low-altitude mixed passenger and freight multimodal transport planning scheme. That is to say, by constructing a mixed-integer linear programming (MIP) model and comprehensively considering various cost factors, including transshipment costs, delay penalty costs, and carbon emission taxes, the carbon emissions generated by various vehicles and service orders are evaluated, and an adaptive large neighborhood search (ALNS) heuristic algorithm is introduced, which helps to optimize the vehicle routes and resource allocation of electric vertical takeoff and landing aircraft and drones in low-altitude transportation, improve transportation efficiency, and has important reference value for promoting the sustainable development of the low-altitude economy. BRIEF DESCRIPTION OF THE DRAWINGS

[0030] Figure 1 It is an application environment diagram of a method for planning a mixed passenger and freight multimodal transport with coordinated low-altitude and ground transportation in an embodiment;

[0031] Figure 2 It is a flowchart of a method for planning a mixed passenger and freight multimodal transport with coordinated low-altitude and ground transportation in an embodiment;

[0032] Figure 3 It is a schematic diagram of an application scenario of a method for planning a mixed passenger and freight multimodal transport with coordinated low-altitude and ground transportation in an embodiment;

[0033] Figure 4 It is a structural block diagram of a device for planning a mixed passenger and freight multimodal transport with coordinated low-altitude and ground transportation in an embodiment;

[0034] Figure 5 It is an internal structure diagram of a computer device in an embodiment. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0035] In order to make the objectives, technical solutions, and advantages of this application more clear and understandable, the following further elaborates on this application in conjunction with the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely used to explain this application and are not intended to limit this application.

[0036] A method for planning a passenger and cargo mixed - mode intermodal transportation that coordinates low - altitude and ground transportation provided by an embodiment of this application can be applied to an application environment as Figure 1 shown. Among them, the terminal communicates with the server through a network. The data storage system can store the data that the server needs to process. The data storage system can be integrated on the server, or placed in the cloud or on other network servers. Among them, the terminal can be, but is not limited to, various personal computers, laptop computers, smartphones, tablet computers, Internet of Things devices, and portable wearable devices. The Internet of Things devices can be smart speakers, smart TVs, smart air conditioners, smart in - vehicle devices, etc. The portable wearable devices can be smart watches, smart bracelets, head - mounted devices, etc. The server can be implemented by an independent server or a server cluster composed of multiple servers.

[0037] In one embodiment, as Figure 2 shown, a method for planning a passenger and cargo mixed - mode intermodal transportation that coordinates low - altitude and ground transportation is provided. Taking the application of this method to the Figure 1 server as an example for illustration, it includes the following steps:

[0038] S201: Obtain transportation order information and basic traffic information. Among them, the transportation order information includes pick - up and delivery locations, information about packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information.

[0039] In an embodiment of this application, first, obtain transportation order information and basic traffic information. Among them, the transportation order information includes pick - up and delivery locations, the weight of packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information. Specifically, as Figure 3 shown, the traffic scenarios involved in this application mainly include urban traffic and rescue in remote areas. The transportation vehicles include electric vertical take - off and landing aircraft (eVTOLs), drones, and ground transportation vehicles, which cooperate within and between cities to transport emergency supplies and passengers, and also support emergency rescue work in mountainous or remote areas by transporting medical supplies and rescue personnel. These scenarios involve different orders, time limits, emergency levels, and priority weights for packages and personnel.

[0040] In an embodiment of this application, the transportation order information includes:

[0041] The Haversine formula is used to calculate the geospatial distance, and the non - homogeneous Poisson process is used to represent the random arrival of transportation orders.

[0042] In one embodiment of the present application, each transportation order information corresponds to a service demand, such as a passenger travel order or a package delivery order. Each order includes a departure station, an arrival station, a time window, a size, and a weight. To generate realistic and comprehensive order data, it is best to combine previous data on the travel demands of drones and ground transportation. However, for the currently considered drone - ground vehicle system which is still in the conceptual stage, there is no actual historical demand application data. Therefore, by combining the typical time and space demand patterns of passenger and package services in transportation, this set of orders is formed. To accurately define the spatial context of transportation orders, the Nominatim service is used. This service can obtain the geographical coordinates (latitude and longitude) of each location. Through geocoding, place names can be converted into precise geographical coordinates. Based on the geocoding data, the Haversine formula is used to accurately calculate the geospatial distance. Compared with the traditional Euclidean distance measurement method, this method more accurately reflects the true spatial relationship between two points on the Earth's surface by considering the curvature of the Earth. For the time - dimension modeling, the non - homogeneous Poisson process is used to characterize the random arrival of transportation orders. Let X represent the number of orders occurring within the time interval T, and it follows a Poisson distribution:

[0043]

[0044] where λ represents the expected arrival rate per unit time. Each order r ∈ R contains spatio - temporal constraints: the departure time window: [a p(r) ,b p(r) and the destination time window: [a d(r) ,b d(r) . Then the order feature vector is formally defined as:

[0045] r = <p(r), d(r), [a p(r) ,b p(r) , [a d(r) ,b d(r) , q r , w r >

[0046] where p(r), d(r) ∈ P are the origin - destination (OD) pair coordinates; q r ∈ [0, 240] is the transportation order volume demand (mass unit); w r~U(1, 10): Priority weights that follow a uniform distribution. This method generates an order set R = {r1, r2, …, rm} through Monte Carlo simulation. Spatially, the OD pair sampling strategy based on the Haversine distance ensures geographical rationality. The random generation mechanism of time parameters and feature weights effectively simulates the inherent time heterogeneity and task priority changes in the real-world transportation system. It enables the generated order set to exhibit strong real-world consistency in terms of spatial distribution characteristics, time series correlation, and task attribute diversity.

[0047] S203: Construct a mixed-integer linear programming model based on the basic traffic information, determine the constraint conditions in combination with the transportation order information, and define the objective function for the low-altitude collaborative mixed passenger and cargo multimodal transportation plan.

[0048] In the embodiments of this application, a mixed-integer linear programming model is constructed based on the basic traffic information, and a mode set W = {e, g, u} is defined, where the index w represents one of the three modes, e represents eVTOL, g represents ground transportation, and u represents drones. These three modes can be flexibly combined to adapt to different route requirements. For each transportation mode, the transportation vehicle is represented by the set Kw (where w ∈ W). With L kg as the threshold, transportation vehicles with a maximum load capacity U less than 60 kg are limited to package transportation (such as small drones); if U > L kg, the transportation vehicle can carry passengers and packages simultaneously, thereby improving space utilization and significantly reducing time costs. N represents a set of stations (indexed by i and j); R represents a set of orders (indexed by R); Tw2 represents a transfer station that allows switching between modes w1 and w2. When an order appears, ground transportation vehicles and unmanned aerial vehicles can leave the stations in N and transfer at stations indexed by T if necessary. These transfer stations usually operate as regular stations and can serve as pick-up (or package collection) and drop-off (or delivery) points. During the transfer process, the transportation mode may switch between ground transportation and drones.

[0049] Note that although electric vertical takeoff and landing vehicles and drones can operate flexibly, ground transportation vehicles are usually fixed - they only operate between pre - determined stations with fixed departure and arrival times. In contrast, flexible transportation tools can go to any station at any time without a preset schedule. Therefore, the transportation tools involved in this application mainly include five types: fixed electric vertical takeoff and landing vehicles, flexible electric vertical takeoff and landing vehicles, ground transportation vehicles, fixed drones, and flexible drones. An electric vertical takeoff and landing vehicle refers to a single electric vertical takeoff and landing aircraft that can fly continuously between multiple locations (e.g., A→B→C) once loaded. In contrast, drones represent a group of independent aircraft that all depart from the same starting point. Once any individual drone is loaded, it can depart - usually executing routes like A→B or A→C - and each drone independently plans its itinerary and schedule. The takeoff / landing locations of electric vertical takeoff and landing vehicles and drones and the departure and arrival points of ground transportation vehicles are fixed and known in the set of stations N; the model does not consider layovers or mid - journey pickups / deliveries. Each transportation tool only accepts orders with a total demand not exceeding its maximum capacity, and passengers or packages in any order cannot be split (i.e., delivery is indivisible). It is assumed that the transportation tools have sufficient power and there are sufficient charging facilities along the way to ensure that the drones can complete their scheduled trips.

[0050] Meanwhile, determine the constraints in combination with the transportation order information. Under the consideration of constraints such as time windows, transportation tool capacities, and transfer possibilities, define the objective function to minimize the total transportation cost and achieve the synchronous planning of the transportation tool routes and order routes.

[0051] Specifically, in an embodiment of this application, the objective function is:

[0052] minF = F1 + F2 + F3 + F4 + F5

[0053]

[0054] where F is the total cost, F1 is the transportation cost, F2 is the transfer cost, F3 is the storage cost, F4 is the carbon tax, F5 is the delay penalty, K is the set of transportation tools, including drones, electric vertical takeoff and landing vehicles, and fixed transportation tools; A is the set of arcs, A p is the set of pickup arcs, A d is the set of delivery arcs; R is the set of orders; T is the transfer point; is the unit cost of different items, n ∈ 1, 1′, 2, 3, 4, c k 1 / c k 1′is the transportation cost per hour / per kilometer per kilogram when using transportation vehicle \(k\in K\); \(c\) k 2 is the loading (or unloading) cost per kilogram; \(c\) k 3 is the storage cost per kilogram per hour; \(c\) k 4 is the carbon tax coefficient per ton; \(c\) k 5 is the delay penalty cost per kilogram per hour; is the travel time of transportation vehicle \(k\) on arc \((i,j)\), is the distance between stations \(i\) and \(j\) for transportation vehicle \(k\), \(q\) r is the quantity of order \(r\); is a binary variable, which is 1 if the order \(r\) transported by transportation vehicle \(k\) uses arc \((i,j)\), otherwise 0; is a binary variable, which is 1 if order \(r\) is transferred from transportation vehicle \(k\) to transportation vehicle \(l\) at transfer station \(i\), otherwise 0; and are the service start times of transportation vehicles \(k\) and \(l\) for order \(r\) at station \(i\), is the service end time of transportation vehicle \(k\) for order \(r\) at station \(i\), \(a\) p(r) is the pick-up start time of order \(r\), \(e\) k is the \(\mathrm{emission}\) per kilogram per kilometer of transportation vehicle \(k\in K\), is the delay time of order \(r\) at the delivery location.

[0055] In an embodiment of the present application, the constraint conditions include space-related constraints, transfer-related constraints, flow conservation constraints, transportation vehicle characteristic-related constraints, and time-related constraints.

[0056] In an embodiment of the present application, the space-related constraints include start and end points and route restrictions, sub-tour route constraints, cargo pick-up and delivery point constraints, capacity constraints, the transfer-related constraints include transfer times constraints, transfer transportation vehicle constraints, the flow conservation constraints include transportation vehicle flow conservation, order flow conservation, order and transportation vehicle association constraints, the transportation vehicle characteristic-related constraints include route applicability constraints, predefined route constraints, transfer terminal matching constraints, and the time-related constraints include service time sequence constraints, travel time and speed-distance constraints, time window constraints, waiting and delay time constraints, and drone time constraints.

[0057] In one embodiment of the present application, the constraint conditions include space-related constraints, transfer-related constraints, flow conservation constraints, vehicle characteristic-related constraints, and time-related constraints. Among them, the space-related constraints include origin-destination and route restrictions, sub-tour route constraints, cargo pickup and delivery point constraints, and capacity restrictions; the transfer-related constraints include transfer times restrictions, transfer vehicle restrictions; the flow conservation constraints include vehicle flow conservation, order flow conservation, and order-vehicle association constraints; the vehicle characteristic-related constraints include route applicability constraints, predefined route constraints, and transfer terminal matching constraints; the time-related constraints include service time sequence constraints, travel time and speed-distance constraints, time window constraints, waiting and delay time constraints, and drone time constraints.

[0058] The origin-destination and route restrictions are used to ensure that the vehicle departs from the origin and returns to the destination, restricting the routes of eVTOLs and drones, and not involving specific route restrictions for ground traffic vehicles, which are expressed as follows:

[0059]

[0060] Among them, represents the origin, represents a binary variable indicating whether to select this route for transportation, represents the destination on the return trip (the origin of the outbound trip), represents a binary variable indicating whether to select this route for transportation on the return trip, K e\&dr represents the set of eVTOLs and drone vehicles.

[0061] The sub-tour elimination is used to avoid sub-tours in the vehicle route and provide a reasonable route planning boundary for the model, which is expressed as follows:

[0062]

[0063] Among them, is a binary variable, which is 1 if vehicle k uses arc (i, j), and 0 otherwise; is a binary variable, which is 1 if station i is before station j (not necessarily adjacent) in the route of vehicle k, and 0 otherwise.

[0064] The cargo pickup and delivery point constraints ensure that the goods of each order are picked up at the corresponding pickup terminal and delivered at the delivery terminal, which are expressed as follows:

[0065]

[0066] Among them, p(r) represents the pickup terminal, and d(r) represents the delivery terminal.

[0067] The capacity restriction is used to limit the weight of goods transported by the vehicle not to exceed the maximum carrying capacity, which is expressed as follows:

[0068]

[0069] where q r is the quantity of order r, is a binary variable, which is 1 if the order r transported by vehicle k uses arc (i, j), and 0 otherwise; u k is the capacity of vehicle k, is a binary variable, which is 1 if vehicle k uses arc (i, j), and 0 otherwise.

[0070] The transshipment times limit is used to limit that the same order can only be transshipped once at the same transshipment terminal, which is expressed as follows:

[0071]

[0072] where and are binary variables, which are 1 if the order r transported by vehicle k or vehicle l uses arc (i, j) or arc (j, i), and 0 otherwise; is a binary variable, which is 1 if order r is transferred from vehicle k to vehicle l at transshipment site i, and 0 otherwise.

[0073] The transshipment vehicle limit is used to prohibit the transshipment operation between the same vehicles, which is expressed as follows:

[0074]

[0075] where is a binary variable, indicating that order r is transferred from vehicle k to vehicle k at transshipment site i, and is 0.

[0076] The vehicle flow conservation means that at ordinary terminals other than the starting and ending terminals, the inflow and outflow of vehicles are balanced, which is expressed as follows:

[0077]

[0078] The order flow conservation means that the inflow and outflow of orders at ordinary terminals and transshipment terminals (other than pick-up and delivery points) are equal, and the flow conservation is also satisfied in special cases (when the vehicle passes through the transshipment terminal but the order is not transferred), which is expressed as follows:

[0079]

[0080] The order-vehicle association constraint means that the order can only be transported by the vehicle when the vehicle passes through the relevant arc, which is expressed as follows:

[0081]

[0082] The route applicability constraint is used to prevent the transportation vehicle from traveling on unsuitable routes. For example, drones do not operate on inland waterways, which is expressed as follows:

[0083]

[0084] The predefined route constraint is used to restrict a specific transportation vehicle to travel along a preset route, which is expressed as follows:

[0085]

[0086] The transfer terminal matching constraint is used to ensure that the transfer occurs at the correct terminal. For example, the transfer between eVTOL and drones needs to be carried out at the corresponding supporting terminals, which is expressed as follows:

[0087]

[0088] The service time sequence constraints include: the service start time is later than the arrival time of the goods; the service end time is the start time plus the service duration; the transportation vehicle departs after all services are completed; the order arrival time is not earlier than the arrival time of the transportation vehicle; define the last service start time of the transportation vehicle, which is expressed as follows:

[0089]

[0090] Among them, is the arrival time of transportation vehicle k at station i, is the last service start time of transportation vehicle k at station i, is the departure time of transportation vehicle k at station i.

[0091] The travel time and speed - distance constraint ensures that the travel time, distance, and speed of eVTOL and ground vehicles match, considering the impact of waiting time on travel time, which is expressed as follows:

[0092]

[0093] Among them, M is a sufficiently large positive number.

[0094] The time - window constraint is used to restrict that the service time at the pick - up terminal and the fixed terminal must be within the specified time window, which is expressed as follows:

[0095]

[0096] Among them, is the service start time of order r served by transportation vehicle k, is the service end time of order i served by transportation vehicle k,[[a p(r) ,b p(r) is the pick - up time window of order r, To fix the opening time window of vehicle k at station i.

[0097] Waiting and delay time constraints are used to calculate the waiting time of the transportation vehicle during transshipment and the delay time of the order at the delivery terminal to control costs, which are expressed as follows:

[0098]

[0099] Where, is the waiting time of transportation vehicle k at station i, is the service end time of transportation vehicle k for order r, b d(r) is the delivery end time of order r.

[0100] Drone time constraints are used to linearize the travel time function related to drone time and handle problems related to drone arrival time, which are expressed as follows:

[0101]

[0102] S205: Solve using the adaptive large neighborhood search algorithm based on the objective function and constraint conditions to obtain a low-altitude collaborative hybrid passenger and cargo multimodal transportation planning scheme.

[0103] In the embodiment of the present application, in the problem of the vehicle routing of passenger and cargo hybrid transportation with the collaboration of electric vertical takeoff and landing vehicles (eVTOLs), ground transportation, and drones, challenges such as the continuous increase in the number of orders, the continuous expansion of the problem scale, and complex constraint conditions (such as vehicle capacity, time windows, transshipment rules, etc.) are faced. Precise optimization techniques have obvious disadvantages in terms of computing time and resource consumption, and it is difficult to provide an effective solution within a reasonable time. Therefore, the adaptive large neighborhood search (ALNS) algorithm is used to solve based on the objective function and constraint conditions to obtain a low-altitude collaborative hybrid passenger and cargo multimodal transportation planning scheme. Specifically, the input includes a set of transportation vehicles and a set of orders. The set of transportation vehicles covers detailed information about various transportation vehicles participating in the transportation, such as the capacity, travel speed, starting point, and ending point of the transportation vehicle. This information determines the basic capabilities and limitations of the transportation vehicle during transportation. The set of orders contains the specific content of all transportation demands, including pick-up and delivery locations, the weight of the transported goods or the number of passengers, time window information, and the priority of the order. These input data completely describe the actual situation of the transportation problem and provide the necessary basic data for the algorithm to solve. The output of the algorithm is a solution close to the optimal one. Due to the complexity of the transportation problem itself, finding the global optimal solution is usually both difficult and time-consuming. With its unique search strategy, the adaptive large neighborhood search (ALNS) algorithm can find a solution close to the optimal one within a reasonable time.

[0104] Specifically, in an embodiment of the present application, the solving by using the adaptive large neighborhood search algorithm based on the objective function and the constraint conditions includes:

[0105] Select an insertion operator, a removal operator, and a swap operator according to the transportation order information, and adjust the low-altitude collaborative mixed passenger and cargo multimodal transportation plan based on the insertion operator, the removal operator, and the swap operator

[0106] In an embodiment of the present application, the insertion operators include a greedy insertion operator, a transshipment insertion operator, and a regret insertion operator, and the removal operators include a worst removal operator, a random removal operator, a correlation removal operator, a historical removal operator, and a route removal operator.

[0107] In an embodiment of the present application, all insertion operators are designed to insert an order into one or more routes. When an order is inserted into a single route of vehicle k, vehicle k will be responsible for picking up and delivering the goods without any transshipment. When inserted into multiple routes, the order will be split at potential transshipment points and served by multiple vehicles, and the order will be transferred between these vehicles.

[0108] Greedy insertion operator: This operator explores all possible insertion positions and selects the position with the lowest cost. For each order, it calculates the cost change at different insertion positions and selects the position with the lowest cost for insertion.

[0109] Transshipment insertion operator: This operator allows the order to be split and transferred through a transshipment center. It prioritizes multi-vehicle cooperation to reduce costs. In actual transportation, this is very useful for long-distance or complex transportation orders. For example, a large order can first be transported by a large-capacity vehicle to a transshipment point and then allocated to smaller vehicles for final delivery.

[0110] Regret insertion operator: The regret insertion operates based on the regret value. For order r, it calculates the regret value for each possible insertion route where is the k-th lowest insertion cost, is the lowest insertion cost. Generally, the order with the highest C r is inserted first. To save calculation time, instead of inserting orders one by one, multiple orders are inserted at once. These orders are divided into two groups: non-conflicting orders (group a) that can be directly inserted and conflicting orders (group b). For the orders in group b that attempt to be inserted into the same vehicle, they are sorted according to the regret value. If the order with the highest regret value uses only one vehicle, then it can be inserted. If it uses multiple vehicles, the algorithm checks the situation where these vehicles are used by other orders. Based on the comparison of the regret values, it decides whether to insert Or insert the order with the second highest regret value when the conditions are met. Other orders in group b will not be inserted at this step.

[0111] All removal operators have a basic operation of removing the pick-up, transfer, and delivery of an order from the route and then recalculating the time of the relevant route. However, they differ in the orders they choose to remove.

[0112] Worst removal operator: This operator removes the order that contributes the most to the cost in the current solution. By removing the order with the highest cost, it is expected to reduce the total cost in the subsequent repair process. For example, if an order requires a long-distance transportation and consumes a large amount of resources, removing it may create an opportunity to optimize the route.

[0113] Random removal operator: Randomly remove some transportation tools randomly, and then randomly remove one order from each of these transportation tools. This increases the randomness of the search process and helps to avoid getting stuck in local optimal solutions, which is particularly useful in the early stages of the algorithm.

[0114] Relevant removal operator: It randomly removes an order r, and then removes some similar orders r′ according to factors such as distance, time, load, and transportation tool compatibility. This operator considers the relationships between orders and can adjust the route structure more comprehensively, thus achieving better optimization results.

[0115] Historical removal operator: Historical removal uses the historical data during the execution of the algorithm to identify orders that may be in suboptimal positions. Then, it guides the insertion operator to insert the orders into positions where the cost may be lower. By analyzing the past insertion costs and positions, it can optimize the quality of the solution.

[0116] Route removal operator: This operator clears inefficient routes. When the utilization rate of the transportation tool on a route is low or the cost is high, the route removal moves all the orders on this route back to the order pool. This helps to re-optimize the transportation plan, with the goal of minimizing the number of transportation tools used and maximizing the loading rate.

[0117] The main goal of the exchange operator is to maximize the utilization rate of transportation tools and reduce costs. By rearranging the orders between vehicles, it aims to better utilize the transportation tool resources, reduce idle time and empty running distance. When a vehicle cannot serve an order due to time window or capacity constraints, the exchange operator is triggered. For example, if a transportation tool arrives at the pick-up location after the pick-up time window of the order, or its capacity is insufficient to meet the order, reallocation is required. First, it uses the historical removal operator to remove inefficient orders that may cause constraint conflicts. Then, it uses the greedy insertion operator to reassign the orders to other transportation tools. During this process, it tries to find the best insertion position to minimize the cost while meeting the constraints.

[0118] In an embodiment of the present application, first, a greedy insertion operator is used to construct an initial solution Xinitial. This operator traverses all orders to find the insertion position that minimizes the cost. If there are still unprocessed orders after greedy insertion in the order pool Rpool, a random removal operator is combined. First, some orders are randomly removed, and then these orders are re-inserted using greedy insertion until Rpool is empty, laying a good foundation for subsequent iterations.

[0119] Within the preset number of iterations, the algorithm searches with the optimization objective as the guidance. At the beginning of every s iterations, the weights of the operators are refreshed according to the changes in the objective function values before and after the application of each operator. The better the performance, the higher the weight. Then, a roulette wheel strategy is used to select the operators for the next s iterations.

[0120] Each iteration alternates between destruction and repair operations. In the destruction operation, different removal operators play their respective roles: the worst removal operator removes the order that contributes the most to the cost; random removal increases the randomness of the search; related removal adjusts the route structure by comprehensively considering the relationships between orders; historical removal uses historical data to identify sub-optimal orders.

[0121] In the repair operation, the insertion operator is used to re-insert the removed orders into the route. Greedy insertion continues to find the position with the minimum cost; transshipment insertion allows orders to be split and transferred through a transshipment hub; regret value insertion reasonably inserts multiple orders according to the regret value. When the transportation vehicle cannot serve an order due to time window or capacity constraints, the swap operator naturally participates. It reallocates orders and optimizes the solution using historical removal and greedy insertion to meet the constraints and reduce the cost. Throughout the iteration process, the algorithm continuously updates and optimizes the solution, tracks the optimal solution, monitors the performance of the solution, and adjusts the strategy in a timely manner to gradually improve the quality of the solution.

[0122] Finally, the algorithm selects the solution with the best performance from the solution set X as the final output. The initial solution is generated by greedy insertion and random removal. In subsequent iterations, all operators with an adaptive mechanism jointly generate new solutions. The algorithm comprehensively evaluates the performance of these solutions in terms of cost and other relevant factors and selects the optimal solution as the final result.

[0123] In the above-mentioned multimodal transportation planning method for combined passenger and cargo transportation with low-altitude and ground transportation coordination, first, transportation order information and basic traffic information are obtained. Among them, the transportation order information includes pick-up and delivery locations, information on parcels or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information. Then, a mixed-integer linear programming model is constructed based on the basic traffic information, constraint conditions are determined in combination with the transportation order information, and an objective function for low-altitude coordinated combined passenger and cargo multimodal transportation planning is defined. Finally, an adaptive large neighborhood search algorithm is used to solve based on the objective function and constraint conditions to obtain a low-altitude coordinated combined passenger and cargo multimodal transportation planning scheme. That is to say, by constructing a mixed-integer linear programming (MIP) model, various cost factors are comprehensively considered, including transshipment costs, delay penalty costs, and carbon emission taxes, the carbon emissions generated by various vehicles and service orders are evaluated, and an adaptive large neighborhood search (ALNS) heuristic algorithm is introduced, which helps to optimize the vehicle routes and resource allocation of electric vertical takeoff and landing aircraft and drones in low-altitude transportation, improve transportation efficiency, and has important reference value for promoting the sustainable development of the low-altitude economy.

[0124] It should be understood that although the steps in the flowcharts involved in the above-described embodiments are shown sequentially according to the indications of the arrows, these steps do not necessarily have to be executed in the order indicated by the arrows. Unless there is a clear indication in this article, there is no strict order limit for the execution of these steps, and these steps can be executed in other orders. Moreover, at least some of the steps in the flowcharts involved in the above-described embodiments may include multiple steps or multiple stages. These steps or stages do not necessarily have to be executed at the same moment, but can be executed at different moments, and the execution order of these steps or stages does not necessarily have to be sequential, but can be executed alternately or in turn with at least a part of other steps or steps or stages in other steps.

[0125] Based on the same inventive concept, an embodiment of the present application also provides a multimodal transportation planning device for combined passenger and cargo transportation with low-altitude and ground transportation coordination for implementing the above-mentioned multimodal transportation planning method for combined passenger and cargo transportation with low-altitude and ground transportation coordination. The implementation solutions provided by this device for solving problems are similar to the implementation solutions described in the above method. Therefore, the specific limitations in one or more embodiments of the multimodal transportation planning device for combined passenger and cargo transportation with low-altitude and ground transportation coordination provided below can refer to the limitations on the multimodal transportation planning method for combined passenger and cargo transportation with low-altitude and ground transportation coordination in the above text, and will not be repeated here.

[0126] In one embodiment, as Figure 4As shown, a multi-modal transportation planning device 400 for coordinated low-altitude and ground transportation of passengers and goods is provided, including: a demand acquisition module 401, a mixed-integer programming model construction module 403, and a low-altitude coordinated mixed passenger and freight multi-modal transportation planning module 405, where:

[0127] The demand acquisition module 401 is used to acquire transportation order information and basic traffic information. Among them, the transportation order information includes pick-up and delivery locations, information on packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation tool information.

[0128] The mixed-integer programming model construction module 403 is used to construct a mixed-integer linear programming model based on the basic traffic information, determine constraint conditions in combination with the transportation order information, and define the objective function of the low-altitude coordinated mixed passenger and freight multi-modal transportation planning.

[0129] The low-altitude coordinated mixed passenger and freight multi-modal transportation planning module 405 is used to solve based on the objective function and constraint conditions by using an adaptive large neighborhood search algorithm to obtain a low-altitude coordinated mixed passenger and freight multi-modal transportation planning scheme.

[0130] In an embodiment of the present application, the transportation order information includes:

[0131] The geographical spatial distance is calculated using the Harvard-Sin formula, and the random arrival of traffic orders is represented by a non-homogeneous Poisson process.

[0132] In an embodiment of the present application, the objective function is:

[0133] minF = F1 + F2 + F3 + F4 + F5

[0134]

[0135] Among them, F is the total cost, F1 is the transportation cost, F2 is the transshipment cost, F3 is the storage cost, F4 is the carbon tax, F5 is the delay fine, K is the set of transportation tools, including drones, electric vertical takeoff and landing aircraft, and fixed vehicles; A is the set of arcs, A p is the set of pick-up arcs, A d is the set of delivery arcs; R is the set of orders; T is the transfer point; is the unit cost of different items, n ∈ 1, 1′, 2, 3, 4, c k 1 / c k 1′ is the transportation cost per hour / per kilometer per kilogram when using the transportation tool k ∈ K; c k 2 is the loading (or unloading) cost per kilogram; c k 3is the storage cost per kilogram per hour; c k 4 is the carbon tax coefficient per ton; c k 5 is the delay penalty cost per kilogram per hour; is the travel time of vehicle k on arc (i, j), is the distance between stations i and j for vehicle k, q r is the quantity of order r; is a binary variable, which is 1 if order r transported by vehicle k uses arc (i, j), otherwise 0; is a binary variable, which is 1 if order r is transferred from vehicle k to vehicle l at transfer station i, otherwise 0; and are the service start times of vehicles k and l for order r at station i, is the service end time of vehicle k for order r at station i, a p(r) is the pick-up start time of order r, e k is the emission of vehicle k ∈ K per kilogram per kilometer, is the delay time of order r at the delivery location.

[0136] In an embodiment of the present application, the constraint conditions include space-related constraints, transfer-related constraints, flow conservation constraints, vehicle characteristic-related constraints, and time-related constraints.

[0137] In an embodiment of the present application, the space-related constraints include start and end points and route restrictions, sub-tour route constraints, cargo pick-up and delivery point constraints, and capacity restrictions. The transfer-related constraints include transfer times restrictions and transfer vehicle restrictions. The flow conservation constraints include vehicle flow conservation, order flow conservation, and order-vehicle association constraints. The vehicle characteristic-related constraints include route applicability constraints, predefined route constraints, and transfer terminal matching constraints. The time-related constraints include service time sequence constraints, travel time and speed-distance constraints, time window constraints, waiting and delay time constraints, and drone time constraints.

[0138] In an embodiment of the present application, the solution of the adaptive large neighborhood search algorithm based on the objective function and constraint conditions includes:

[0139] Select an insertion operator, a removal operator, and a swap operator according to the transportation order information, and adjust the low-altitude collaborative hybrid passenger and cargo multimodal transportation plan based on the insertion operator, the removal operator, and the swap operator.

[0140] In one embodiment of the present application, the insertion operator includes a greedy insertion operator, a transshipment insertion operator, and a regret insertion operator, and the removal operator includes a worst removal operator, a random removal operator, a correlation removal operator, a historical removal operator, and a route removal operator.

[0141] Each module in the above-mentioned passenger and cargo mixed transport multimodal transport planning device for low-altitude and ground traffic coordination can be implemented in whole or in part by software, hardware, and their combination. Each of the above modules can be embedded in the processor of the computer device in hardware form or independent of it, or stored in the memory of the computer device in software form, so that the processor can call and execute the operations corresponding to each of the above modules.

[0142] In one embodiment, a computer device is provided. The computer device can be a terminal, and its internal structure diagram can be as Figure 5 shown. The computer device includes a processor, a memory, a communication interface, a display screen, and an input device connected through a system bus. Among them, the processor of the computer device is used to provide computing and control capabilities. The memory of the computer device includes a non-volatile storage medium and an internal memory. The non-volatile storage medium stores an operating system and a computer program. The internal memory provides an environment for the operation of the operating system and the computer program in the non-volatile storage medium. The communication interface of the computer device is used to communicate with an external terminal in a wired or wireless manner. The wireless manner can be achieved through WIFI, a mobile cellular network, NFC (Near Field Communication), or other technologies. When the computer program is executed by the processor, it implements a passenger and cargo mixed transport multimodal transport planning method for low-altitude and ground traffic coordination. The display screen of the computer device can be a liquid crystal display screen or an electronic ink display screen. The input device of the computer device can be a touch layer covering the display screen, or a button, a trackball, or a touchpad provided on the housing of the computer device, or an external keyboard, touchpad, or mouse, etc.

[0143] Those skilled in the art can understand that Figure 5 the structure shown in

[0144] is only a block diagram of some structures related to the solution of the present application, and does not constitute a limitation on the computer device to which the solution of the present application is applied. The specific computer device may include more or fewer components than those shown in the figure, or combine some components, or have a different component layout.

[0145] In one embodiment, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0146] In one embodiment, a computer program product is provided, including a computer program. When the computer program is executed by a processor, the steps in the above method embodiments are implemented.

[0147] It should be noted that the user information (including but not limited to user device information, user personal information, etc.) and data (including but not limited to data for analysis, stored data, displayed data, etc.) involved in this application are all information and data authorized by the user or fully authorized by all parties.

[0148] Those of ordinary skill in the art can understand that all or part of the processes in the above method embodiments can be completed by instructing relevant hardware through a computer program. The computer program can be stored in a non-volatile computer-readable storage medium. When the computer program is executed, it can include the processes of the above method embodiments. Among them, any reference to a memory, database, or other medium used in the embodiments provided in this application can include at least one of non-volatile and volatile memories. Non-volatile memory can include read-only memory (ROM), magnetic tape, floppy disk, flash memory, optical memory, high-density embedded non-volatile memory, resistive random access memory (ReRAM), magnetoresistive random access memory (MRAM), ferroelectric random access memory (FRAM), phase change memory (PCM), graphene memory, etc. Volatile memory can include random access memory (RAM) or external cache memory, etc. By way of illustration and not limitation, RAM can be in various forms, such as static random access memory (SRAM) or dynamic random access memory (DRAM), etc. The databases involved in the embodiments provided in this application can include at least one of relational databases and non-relational databases. Non-relational databases can include distributed databases based on blockchain, etc., without limitation. The processors involved in the embodiments provided in this application can be general-purpose processors, central processors, graphics processors, digital signal processors, programmable logic devices, data processing logics based on quantum computing, etc., without limitation.

[0149] The technical features of the above embodiments can be combined arbitrarily. For the sake of concise description, not all possible combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, it should be considered as the scope described in this specification.

[0150] The above-described embodiments merely represent several implementation manners of the present application. The description is relatively specific and detailed, but it should not be construed as a limitation on the scope of the patent of the present application. It should be noted that for those of ordinary skill in the art, without departing from the concept of the present application, several modifications and improvements can still be made, and these all belong to the protection scope of the present application. Therefore, the protection scope of the present application shall be subject to the appended claims.

Claims

1. A planning method for mixed passenger and freight multimodal transport coordinated by low-altitude and ground transportation, characterized in that, The method includes: Obtaining transportation order information and basic traffic information, where the transportation order information includes pick-up and delivery locations, information about packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information; Constructing a mixed-integer linear programming model based on the basic traffic information, determining constraint conditions in combination with the transportation order information, and defining the objective function for the low-altitude collaborative mixed passenger and cargo multimodal transportation plan; Using an adaptive large neighborhood search algorithm to solve based on the objective function and constraint conditions to obtain a low-altitude collaborative mixed passenger and cargo multimodal transportation plan.

2. The multimodal transport planning method for mixed passenger and freight transportation with low-altitude and ground transportation collaboration according to claim 1, wherein The transportation order information includes: Calculating the geospatial distance using the Haversine formula and representing the random arrival of traffic orders using a non-homogeneous Poisson process.

3. A method for planning a passenger and freight mixed multimodal transport that coordinates low-altitude and ground transportation according to claim 1, characterized in that, The objective function is: minF = F1 + F2 + F3 + F4 + F5 Among them, F is the total cost, F1 is the transportation cost, F2 is the transshipment cost, F3 is the storage cost, F4 is the carbon tax, F5 is the delay penalty, K is the set of transportation tools, including drones, electric vertical takeoff and landing aircraft, and fixed vehicles; A is the set of arcs, A p is the set of pickup arcs, A d is the set of delivery arcs; R is the set of orders; T is the transshipment point; is the unit cost of different items, n ∈ 1, 1′, 2, 3, 4, c k 1 / C k 1′ is the transportation cost per hour per kilometer per kilogram when using transportation tool k ∈ K; c k 2 is the loading (or unloading) cost per kilogram; c k 3 is the storage cost per kilogram per hour; c k 4 is the carbon tax coefficient per ton; c k 5 is the delay penalty cost per kilogram per hour; is the travel time of transportation tool k on arc (i, j), is the distance between stations i and j for transportation tool k, q r is the quantity of order r; is a binary variable, which is 1 if order r transported by transportation tool k uses arc (i, j), otherwise 0; is a binary variable, which is 1 if order r is transferred from transportation tool k to transportation tool l at transshipment station i, otherwise 0; and are the start times of service of transportation tools k and l for order r at station i, is the end time of service of transportation tool k for order r at station i, a p(r) is the pickup start time of order r, e k is the emission of transportation tool k ∈ K per kilogram per kilometer, is the delay time of order r at the delivery location.

4. A method for planning mixed passenger and cargo multimodal transportation with coordinated low-altitude and ground transportation according to claim 1, characterized in that, The constraint conditions include space-related constraints, transfer-related constraints, flow conservation constraints, transportation vehicle characteristic-related constraints, and time-related constraints.

5. A method for planning a passenger and freight mixed multi-modal transport that coordinates low-altitude and ground transportation according to claim 4, characterized in that, The space-related constraints include origin-destination and route restrictions, sub-tour route constraints, cargo pick-up and delivery point constraints, and capacity constraints. The transfer-related constraints include transfer times limit, transfer transportation vehicle limit. The flow conservation constraints include transportation vehicle flow conservation, order flow conservation, and order-transportation vehicle association constraints. The transportation vehicle characteristic-related constraints include route applicability constraints, predefined route constraints, and transfer terminal matching constraints. The time-related constraints include service time sequence constraints, travel time and speed-distance constraints, time window constraints, waiting and delay time constraints, and drone time constraints.

6. A method for planning a passenger and freight mixed multimodal transport for low-altitude and ground traffic collaboration according to claim 1, characterized in that, The step of using an adaptive large neighborhood search algorithm to solve based on the objective function and constraint conditions includes: Selecting an insertion operator, a removal operator, and a swap operator according to the transportation order information, and adjusting the low-altitude collaborative mixed passenger and cargo multimodal transportation plan based on the insertion operator, the removal operator, and the swap operator.

7. A method for planning a passenger and freight mixed multi-modal transportation for low-altitude and ground transportation collaboration according to claim 6, characterized in that, The insertion operator includes a greedy insertion operator, a transfer insertion operator, and a regret insertion operator. The removal operator includes a worst removal operator, a random removal operator, a related removal operator, a historical removal operator, and a route removal operator.

8. An apparatus for planning a mixed passenger and freight multimodal transport in coordination with low-altitude and ground transportation, characterized in that, The device includes: A demand acquisition module for obtaining transportation order information and basic traffic information, where the transportation order information includes pick-up and delivery locations, information about packages or passengers, time limits, and order priorities, and the basic traffic information includes station information and transportation vehicle information; A mixed-integer programming model construction module for constructing a mixed-integer linear programming model based on the basic traffic information, determining constraint conditions in combination with the transportation order information, and defining the objective function for the low-altitude collaborative mixed passenger and cargo multimodal transportation plan; A low-altitude collaborative mixed passenger and cargo multimodal transportation planning module for using an adaptive large neighborhood search algorithm to solve based on the objective function and constraint conditions to obtain a low-altitude collaborative mixed passenger and cargo multimodal transportation plan.

9. A computer device, comprising a memory and a processor, the memory storing a computer program, characterized in that, When the processor executes the computer program, it implements the steps of the method according to any one of claims 1 to 7.

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

Images