A method, system and device for generating an air-rail intermodal route and a storage medium

Abstract

The application discloses an air-rail combined transport route generation method, comprising the following steps: generating virtual nodes composed of an airport and multiple railway stations based on the maximum distance or passenger transfer preference, and forming a virtual node dataset; constructing a transfer node priority optimization model according to the virtual node information, a railway operation timetable and a flight plan within a pre-sale period, and traffic route data in the node, and calculating a candidate set of optimal transfer nodes of a national railway and civil aviation passenger transport network; calculating the minimum transfer time in the node; receiving a travel request of an air-rail combined transport route to be generated, querying the candidate set of optimal transfer nodes, and filtering and splicing the combined transport route by the minimum transfer time according to the combined transport forms of railway first and flight first and flight first and railway first, and displaying the finally generated air-rail combined transport route in sequence according to predetermined recommendation rules. The application also discloses an air-rail combined transport route generation system.

Description

Technical Field

[0001] This application relates to a method for generating intermodal transport routes, and more particularly to a method and system for generating air-rail intermodal transport routes. Background Technology

[0002] Currently, the transportation infrastructure network is becoming increasingly sophisticated, with the total mileage of the comprehensive transportation network exceeding 6 million kilometers. The "ten vertical and ten horizontal" comprehensive transportation corridors are basically completed, the operating mileage of high-speed railways has doubled, and the coverage rate of cities with a population of over one million exceeds 95%. The coverage rate of expressways in cities with a population of over 200,000 exceeds 98%, and civil transport airports cover approximately 92% of prefecture-level cities. Rail transit networks in megacities and super-large cities are rapidly taking shape. Innovative service models for air-rail, road-air, and road-rail intermodal transport are being developed, encouraging the joint construction and sharing of facilities and equipment among different modes of transport. Efforts are being accelerated to promote integrated ticketing for intermodal transport, convenient baggage services, and information resource sharing, while also accelerating the upgrading of air-rail intermodal transport products.

[0003] Promoting integrated air-rail intermodal ticketing and innovating air-rail intermodal product design are important directions for the future development of a comprehensive transportation system, aiming to improve air-rail intermodal services and optimize the allocation of air-rail transport capacity resources. Calculating scientifically sound air-rail intermodal travel routes is a prerequisite for achieving integrated air-rail intermodal ticketing. According to the "2021 China Statistical Yearbook," as of 2020, my country had built approximately 240 civil aviation airports and over 5,000 railway passenger stations, opened nearly 6,000 air routes, and completed the "eight vertical and eight horizontal" high-speed railway network, forming a complex and vast integrated air-rail transportation network. Furthermore, the dynamic changes in air-rail transport capacity resources and flight ticket prices, along with the increasingly complex intermodal travel demand resulting from the interweaving of railway and civil aviation travel needs, pose significant challenges to the rapid and accurate calculation of air-rail intermodal routes. However, current technology still lacks an effective method for generating air-rail intermodal routes.

[0004] Therefore, there is an urgent need to propose a method for generating air-rail intermodal transport routes that analyzes the distribution patterns of railway passenger stations and civil aviation airports, extracts the main constraints in the calculation process of air-rail intermodal transport routes, and takes into account factors such as the dynamic changes in air-rail transport capacity and flight ticket prices, the large differences in the preferences of intermodal transport groups, and the need for intermodal transport services to handle high-concurrency requests, in order to solve the existing technical problems faced in air-rail intermodal transport. Summary of the Invention

[0005] This application provides a method for generating air-rail intermodal transport routes to address the problems faced by existing technologies in air-rail intermodal travel.

[0006] In a first aspect, embodiments of this application provide a method for generating air-rail intermodal transport routes, including:

[0007] Virtual node generation steps: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, multiple virtual nodes are generated with the airport as the center. Each virtual node includes an airport and a railway station. The presence of a convenient transfer passage within the virtual node is marked according to the distance between the airport and the railway station within the virtual node.

[0008] The optimal transfer node calculation steps are as follows: Based on virtual nodes, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual nodes, construct a priority optimization model for transfer nodes within the virtual nodes, which includes estimates based on walking distance, number of transfers, cost and transfer time. Then, calculate the optimal transfer node candidate set of the national railway and civil aviation passenger networks. The optimal transfer node includes the departure node, transfer node, arrival node, optimization objective and priority.

[0009] Minimum transfer time calculation steps: Calculate the minimum transfer time for the air-rail intermodal transport route based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node;

[0010] The steps for calculating and generating intermodal transport routes are as follows: Receive requests for generating air-rail intermodal transport routes, query the candidate set of optimal transfer nodes, and combine intermodal transport routes according to the real-time availability of railway and flight tickets, respectively, in the form of railway first then flight and flight first then railway. Filter the combined intermodal transport routes using the minimum transfer time, and sort and display the final generated air-rail intermodal transport routes according to the predetermined recommendation rules.

[0011] Preferably, the above-mentioned method for generating air-rail intermodal transport routes further includes:

[0012] Public transportation data collection steps: Traverse all virtual nodes and collect public transportation route information between railway stations and airports within the virtual nodes at a certain frequency at the current time to generate public transportation route data within the virtual nodes.

[0013] Preferably, the above-mentioned virtual node generation steps include:

[0014] Based on the current longitude and latitude information of railway passenger stations and civil aviation airports across the country, or other relevant information that can calculate the distance between railway passenger stations and civil aviation airports, an offline virtual node dictionary table is constructed. The dictionary table includes virtual node number, railway passenger station name, airport name, diameter, and information on the main city and secondary city to which it belongs.

[0015] Preferably, the above-mentioned steps for calculating the optimal transfer node include:

[0016] The calculation steps for the full-network direct virtual OD dataset are as follows: Based on virtual nodes, and combined with railway operation plans and flight flight plans within the current period up to the maximum pre-sale date of the railway, the full-network direct virtual OD dataset is generated offline.

[0017] The calculation steps for the network-wide reachable virtual OD dataset are as follows: Traverse the network-wide direct virtual OD dataset, and for the same transfer node, sort and calculate multiple corresponding initial priority values ​​based on the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest duration, and the minimum cost, as well as the distance between virtual reachable ODs, to form the network-wide reachable virtual OD dataset.

[0018] The steps for calculating the distance between virtual reachable ODs are as follows: Taking the center point of the starting node as the starting point and the center point of the destination node as the ending point, calculate the distance between the starting point and the ending point to obtain the distance between virtual reachable ODs.

[0019] The steps for constructing the transfer node optimization model are as follows: Based on the public transportation route data within the node, construct a prediction model for walking distance, number of transfers, cost, and transfer time within the node; iteratively optimize the priority of transfer nodes to obtain the comprehensive priority of transfer nodes; and finally form a candidate set of optimal transfer nodes under multiple different optimization objectives. The optimization objectives include: number of first-journey routes, number of second-journey routes, number of connecting routes, shortest duration, minimum cost, and comprehensive objective.

[0020] The steps for determining the maximum priority of transfer nodes are as follows: the maximum priority of transfer nodes between a pair of virtual reachable ODs is determined according to a predetermined priority rule. The predetermined priority rule is: specifying the maximum priority of transfer nodes for different dates and regional ranges, or making a personalized definition of the maximum priority of transfer nodes based on the differences in time and space requirements and transportation infrastructure construction.

[0021] Steps for determining the number of transfers: Calculate the maximum number of transfers according to the predetermined number of transfers rule. The predetermined number of transfers rule is as follows: Calculate the air-rail intermodal transfer nodes containing N segments of the journey. The whole network virtual reachable OD dataset containing N-1 segments of the journey can be associated with the whole network direct virtual OD dataset once to obtain N-1 transfer nodes.

[0022] Preferably, the above-mentioned minimum transfer time calculation steps include:

[0023] The calculation steps for the minimum transfer time within a transfer node are as follows: Using predetermined values ​​or prediction results output by a transfer time estimation model within the node, the minimum transfer time within the transfer node is calculated offline for different date categories and time periods.

[0024] Convenient transfer time calculation steps: The convenient transfer time is calculated offline using a fixed minimum transfer time or adjusted according to various factors.

[0025] Preferably, the above-mentioned intermodal transport route calculation and generation steps include:

[0026] Fuzzy matching requirement steps: Compare air-rail intermodal transport requests and virtual nodes, and automatically match multiple virtual nodes belonging to the departure and arrival points;

[0027] Intermodal route splicing steps: Based on the matched virtual nodes, query the corresponding optimal transfer node candidate set, and splice all available air-rail intermodal routes.

[0028] Steps to check available tickets: Based on the assembled air-rail intermodal route, check the available tickets for trains and flights within the range of departure date from departure node to transfer node and from transfer node to arrival node within the range of departure date plus a maximum transfer time. Filter out trains and flights without tickets. The maximum transfer time range can be specified or calculated according to certain rules.

[0029] Filtering steps for connecting routes: For connecting routes with available tickets for each segment of the journey, if the transfer time is less than the minimum transfer time, then the connecting route is filtered.

[0030] The sorting and display steps are as follows: The final air-rail intermodal transport routes are displayed according to multiple dimensions such as intermodal fare, duration, and transfer time.

[0031] Preferably, the above-mentioned intermodal transport route splicing step further includes:

[0032] Traverse all virtual reachable destinations obtained by fuzzy matching, and query the transfer nodes and priority of each pair of destinations in the candidate set of optimal transfer nodes.

[0033] Intermodal routes are spliced ​​together in two ways: first rail then flight, and first flight then rail, according to the order of distance between virtual reachable origins and destinations from smallest to largest, the priority of transfer nodes from highest to lowest, or other specified order.

[0034] Secondly, embodiments of this application provide an air-rail intermodal transport route generation system, employing the air-rail intermodal transport route generation method described above. The air-rail intermodal transport route generation system includes:

[0035] Virtual node generation module: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, multiple virtual nodes are generated with the airport as the center. The virtual nodes include an airport and a railway station. The module also marks whether there is a convenient transfer passage within the node according to the distance between the airport and the railway station within the virtual node.

[0036] Optimal transfer node calculation module: Based on virtual nodes, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual nodes, construct a priority optimization model for transfer nodes within the virtual nodes, which includes walking distance, number of transfers, cost and transfer time. It also calculates the candidate set of optimal transfer nodes for the national railway and civil aviation passenger networks. The optimal transfer node includes departure node, transfer node, arrival node, optimization objective and priority.

[0037] Minimum transfer time calculation module: Calculates the minimum transfer time for air-rail intermodal transport routes based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node;

[0038] Intermodal route calculation and generation module: Receives requests for generating air-rail intermodal routes, queries the candidate set of optimal transfer nodes, and splices intermodal routes according to the strategy of prioritizing rail over flight and the strategy of prioritizing flight over rail, based on real-time availability of rail and flight tickets. It filters the spliced ​​intermodal routes using the minimum transfer time and displays the final generated air-rail intermodal routes in order according to the pre-defined recommendation rules.

[0039] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the air-rail intermodal transport route generation method as described above.

[0040] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program that, when executed by a processor, implements the air-rail intermodal transport route generation method described above.

[0041] Compared with existing technologies, it has the following outstanding advantages:

[0042] 1. The present invention proposes a solution technology for air-rail intermodal transport routes based on virtual elastic nodes and hierarchical decoupling. The solution process for air-rail intermodal transport routes is divided into two main parts: offline and real-time calculation. The offline part includes three modules: virtual node generation, transfer node calculation, and minimum transfer time calculation. The real-time part includes public transportation data collection and intermodal transport route calculation modules.

[0043] 2. The method of this invention proposes that a large number of optimization processes be completed offline. It can be based on traditional data warehouses, big data platforms or general servers, and can be implemented using various programming languages ​​such as Spark, Python, and Java. The relevant results can be stored in a memory database or cache with high-speed read and write capabilities, which facilitates the improvement of the splicing, filtering and sorting efficiency of intermodal routes according to real-time requests. Attached Figure Description

[0044] The accompanying drawings, which are included to provide a further understanding of this application and form part of this application, illustrate exemplary embodiments and are used to explain this application, but do not constitute an undue limitation of this application. In the drawings:

[0045] Figure 1 This is a schematic diagram of the air-rail intermodal transport route generation method of the present invention;

[0046] Figure 2This is a schematic diagram of a virtual node according to a specific embodiment of the present invention;

[0047] Figure 3 This is a schematic diagram of an air-rail intermodal transport route according to a specific embodiment of the present invention;

[0048] Figure 4 This is a flowchart illustrating the calculation of air-rail intermodal transport routes according to a specific embodiment of the present invention;

[0049] Figure 5 This is a schematic diagram of the virtual reachable OD obtained after fuzzy matching requirements in a specific embodiment of the present invention;

[0050] Figure 6 This is a schematic diagram of the air-rail intermodal transport route generation system of the present invention;

[0051] Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application.

[0052] In the above image:

[0053] 10 Virtual Node Generation Modules 20 Optimal Transfer Node Calculation Modules

[0054] 30 Minimum transfer time calculation module; 40 Intermodal route calculation and generation module. Detailed Implementation

[0055] To make the objectives, technical solutions, and advantages of this application clearer, the application is described and illustrated below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative and not intended to limit the scope of this application. All other embodiments obtained by those skilled in the art based on the embodiments provided in this application without inventive effort are within the scope of protection of this application.

[0056] Obviously, the accompanying drawings described below are merely some examples or embodiments of this application. Those skilled in the art can apply this application to other similar scenarios based on these drawings without any inventive effort. Furthermore, it is understood that although the efforts made in this development process may be complex and lengthy, for those skilled in the art related to the content disclosed in this application, any changes to design, manufacturing, or production based on the technical content disclosed in this application are merely conventional technical means and should not be construed as insufficient disclosure of the content of this application.

[0057] Details of one or more embodiments of this application are set forth in the following drawings and description to make other features, objects and advantages of this application more readily apparent.

[0058] In this application, the reference to "embodiment" means that a specific feature, structure, or characteristic described in connection with an embodiment may be included in at least one embodiment of this application. The appearance of this phrase in various places in the specification does not necessarily refer to the same embodiment, nor is it a separate or alternative embodiment that is mutually exclusive with other embodiments. It will be explicitly and implicitly understood by those skilled in the art that the embodiments described in this application may be combined with other embodiments without conflict.

[0059] Unless otherwise defined, the technical or scientific terms used in this application shall have the ordinary meaning understood by one of ordinary skill in the art to which this application pertains. The terms “a,” “an,” “an,” “the,” and similar words used in this application do not indicate quantity limitation and may indicate singular or plural. The terms “comprising,” “including,” “having,” and any variations thereof used in this application are intended to cover non-exclusive inclusion; for example, a process, method, system, product, or device that includes a series of steps or modules (units) is not limited to the listed steps or units, but may also include steps or units not listed, or may include other steps or units inherent to these processes, methods, products, or devices. The terms “connected,” “linked,” “coupled,” and similar words used in this application are not limited to physical or mechanical connections, but may include electrical connections, whether direct or indirect. “Multiple” used in this application refers to two or more. “And / or” describes the relationship between related objects, indicating that three relationships may exist; for example, “A and / or B” can represent: A alone, A and B simultaneously, and B alone. The character " / " generally indicates that the preceding and following objects are in an "or" relationship. The terms "first," "second," and "third" used in this application are merely to distinguish similar objects and do not represent a specific ordering of the objects.

[0060] This invention aims to provide a method for generating air-rail intermodal transport routes. In the passenger transport sector, the number of airports and railway stations nationwide is limited, and both flight and railway tickets are sold in advance. Under normal circumstances, regardless of changes in railway operations and flight schedules, most airports and railway stations may have flight or train schedules within a certain date range. Based on these factors, this invention proposes a method for solving air-rail intermodal transport routes for the complex transportation network composed of railway passenger stations and civil airports. This method involves constructing virtual nodes consisting of one railway station and one airport, transforming the actual travel destination (OD) of passengers into virtual ODs, and employing a hierarchical decoupling algorithm that combines offline and real-time computation. Specifically, this includes offline construction of virtual nodes, estimation of candidate sets of virtual transfer nodes, calculation of transfer time constraints, and real-time splicing of a set of air-rail intermodal transport routes based on the latest railway and flight timetables, train ticket availability, and other information. This algorithm comprehensively utilizes various technologies and tools such as Spark, distributed caching, traditional databases, and data warehouses, achieving a time complexity of O(1), and can quickly calculate air-rail intermodal transport routes in high-concurrency environments.

[0061] like Figure 1 As shown in the embodiment of this application, a method for generating air-rail intermodal transport routes is provided. The method includes:

[0062] Virtual node generation step S10: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, generate multiple virtual nodes centered on the airport. The virtual node includes an airport and a railway station. The presence of a convenient transfer passage within the node is marked according to the distance between the airport and the railway station within the virtual node.

[0063] Step S20 for calculating the optimal transfer node: Based on the virtual node, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual node, construct a priority optimization model for the transfer node within the virtual node, which includes the estimated transfer node priority based on walking distance, number of transfers, cost and transfer time. Calculate the candidate set of optimal transfer nodes for the national railway and civil aviation passenger networks. The optimal transfer node includes the departure node, transfer node, arrival node, optimization objective and priority.

[0064] Minimum transfer time calculation step S30: Calculate the minimum transfer time for the air-rail intermodal transport route based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node.

[0065] Step S40 of the intermodal route calculation and generation: Receive the request to generate an air-rail intermodal route, query the candidate set of the optimal transfer nodes, and splice the intermodal routes according to the form of first rail then flight and first flight then rail, respectively, based on the real-time ticket availability information of rail and flight. Filter the spliced ​​intermodal routes using the minimum transfer time, and sort and display the final generated air-rail intermodal routes according to the predetermined recommendation rules.

[0066] Preferably, the above-mentioned method for generating air-rail intermodal transport routes further includes:

[0067] Public transportation data collection steps: Traverse all virtual nodes and collect public transportation route information between railway stations and airports within the virtual nodes at a certain frequency at the current time to generate public transportation route data within the virtual nodes.

[0068] Preferably, the virtual node generation step S10 includes:

[0069] Based on the current longitude and latitude information of railway passenger stations and civil aviation airports across the country, or other relevant information that can calculate the distance between railway passenger stations and civil aviation airports, an offline virtual node dictionary table is constructed. The dictionary table includes virtual node number, railway passenger station name, airport name, diameter, and information on the main city and secondary city to which it belongs.

[0070] Preferably, the above-mentioned optimal transfer node calculation step S20 includes:

[0071] The calculation steps for the full-network direct virtual OD dataset are as follows: Based on virtual nodes, and combined with railway operation plans and flight flight plans within the current period up to the maximum pre-sale date of the railway, the full-network direct virtual OD dataset is generated offline.

[0072] The calculation steps for the network-wide reachable virtual OD dataset are as follows: Traverse the network-wide direct virtual OD dataset, and for the same transfer node, sort and calculate multiple corresponding initial priority values ​​based on the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest duration, and the minimum cost, as well as the distance between virtual reachable ODs, to form the network-wide reachable virtual OD dataset.

[0073] The steps for calculating the distance between virtual reachable ODs are as follows: Taking the center point of the starting node as the starting point and the center point of the destination node as the ending point, calculate the distance between the starting point and the ending point to obtain the distance between virtual reachable ODs.

[0074] The steps for constructing the transfer node optimization model are as follows: Based on the public transportation route data within the node, construct a prediction model for walking distance, number of transfers, cost, and transfer time within the node; iteratively optimize the priority of transfer nodes to obtain the comprehensive priority of transfer nodes; and finally form a candidate set of optimal transfer nodes under multiple different optimization objectives. The optimization objectives include: number of first-journey routes, number of second-journey routes, number of connecting routes, shortest duration, minimum cost, and comprehensive objective.

[0075] The steps for determining the maximum priority of transfer nodes are as follows: the maximum priority of transfer nodes between a pair of virtual reachable ODs is determined according to a predetermined priority rule. The predetermined priority rule is: specifying the maximum priority of transfer nodes for different dates and regional ranges, or making a personalized definition of the maximum priority of transfer nodes based on the differences in time and space requirements and transportation infrastructure construction.

[0076] Steps for determining the number of transfers: Calculate the maximum number of transfers according to the predetermined number of transfers rule. The predetermined number of transfers rule is as follows: Calculate the air-rail intermodal transfer nodes containing N segments of the journey. The whole network virtual reachable OD dataset containing N-1 segments of the journey can be associated with the whole network direct virtual OD dataset once to obtain N-1 transfer nodes.

[0077] Preferably, the minimum transfer time calculation step S30 includes:

[0078] The calculation steps for the minimum transfer time within a transfer node are as follows: Using predetermined values ​​or prediction results output by a transfer time estimation model within the node, the minimum transfer time within the transfer node is calculated offline for different date categories and time periods.

[0079] Convenient transfer time calculation steps: The convenient transfer time is calculated offline using a fixed minimum transfer time or adjusted according to various factors.

[0080] Preferably, the above-mentioned intermodal transport route calculation and generation step S40 includes:

[0081] Fuzzy matching requirement steps: Compare air-rail intermodal transport requests and virtual nodes, and automatically match multiple virtual nodes belonging to the departure and arrival points;

[0082] Intermodal route splicing steps: Based on the matched virtual nodes, query the corresponding optimal transfer node candidate set, and splice all available air-rail intermodal routes.

[0083] Steps to check available tickets: Based on the assembled air-rail intermodal route, check the available tickets for trains and flights within the range of departure date from departure node to transfer node and from transfer node to arrival node within the range of departure date plus a maximum transfer time. Filter out trains and flights without tickets. The maximum transfer time range can be specified or calculated according to certain rules.

[0084] Filtering steps for connecting routes: For connecting routes with available tickets for each segment of the journey, if the transfer time is less than the minimum transfer time, then the connecting route is filtered.

[0085] The sorting and display steps are as follows: The final air-rail intermodal transport routes are displayed according to multiple dimensions such as intermodal fare, duration, and transfer time.

[0086] Preferably, the above-mentioned intermodal transport route splicing step S40 further includes:

[0087] Traverse all virtual reachable destinations obtained by fuzzy matching, and query the transfer nodes and priority of each pair of destinations in the candidate set of optimal transfer nodes.

[0088] Intermodal routes are spliced ​​together in two ways: first rail then flight, and first flight then rail, according to the order of distance between virtual reachable origins and destinations from smallest to largest, the priority of transfer nodes from highest to lowest, or other specified order.

[0089] The specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings:

[0090] The specific inventive points of this invention are as follows:

[0091] (1) The concept of flexible virtual nodes is proposed, and a data representation method for virtual nodes is constructed to simplify the search calculation of the optimal transfer station or airport in air-rail intermodal transport.

[0092] A virtual node consists of one railway passenger station and one civilian airport located at a certain distance from each other. Since there are fewer civilian airports than railway passenger stations nationwide, the virtual node is centered on the airport, radiating outwards to determine the corresponding railway passenger stations. For example... Figure 2 As shown, airport a and five railway passenger stations s1, s2, s3, s4, and s5 form five virtual nodes L1, L2, L3, L4, and L5.

[0093] A flexible virtual node (hereinafter referred to as a "node") refers to a node where the distance between a railway station and an airport is a variable, called the virtual node diameter (or simply "diameter"). Figure 2 The diameters of the five virtual nodes L1, L2, L3, L4, and L5 are d1, d2, d3, d4, and d5, respectively. The diameter is determined by factors such as the transportation infrastructure of each city and business experience, and can be continuously optimized iteratively based on the final connecting travel route planning results and user order data.

[0094] like Figure 3 As shown, after determining the virtual nodes, with Figure 3 Taking the air-rail intermodal transport route diagram as an example, L o L c L dThere are three virtual nodes. The user inputs an fuzzy OD (Original Demand), and the backend program automatically matches the corresponding virtual node ID, returning the railway station and airport corresponding to that ID. After the user precisely selects the railway station or airport corresponding to that ID, the system converts the air-rail intermodal travel demand into L (Large Demand). O →L c →L d The scenario assumes that O1, C1, and D1 are all railway passenger stations, and O2, C2, and D2 are all airports. Ultimately, two intermodal routes may be generated: O1→(C1,C2)→D2 and O2→(C2,C1)→D1, representing "railway first, then flight" and "flight first, then rail" intermodal transport, respectively. In this air-rail intermodal route consisting of two segments, the precise calculation of the transfer node L is not considered. c The connection method between C1 and C2. Figure 3 The dashed arrows within the nodes indicate that the mode of transportation within the nodes is uncertain and is not within the scope of this patent. However, C1 and C2 in the intermediate transfer nodes must be reachable, otherwise transfer cannot be achieved.

[0095] (2) A hierarchical decoupling calculation method is proposed to make the calculation of the optimal transfer node, the constraint conditions and the specific intermodal travel route independent of each other, thereby improving the efficiency of the algorithm.

[0096] In the offline computing layer, three types of data need to be defined or calculated. First, basic data for generating virtual nodes is needed. Based on the common sense that passengers often prefer transfer stations with shorter transfer distances and travel times, a maximum diameter is set as a condition for constructing virtual nodes. If the virtual node diameter is too large, it may result in more than two air-rail transfers, or require the use of other modes of transportation to connect rail and air journeys, increasing the complexity of air-rail transfers.

[0097] Second, calculate the optimal candidate set of transfer nodes for the national railway and civil aviation passenger networks. Since the number of railway stations and airports typically varies very little, and railway operations and flight schedules generally do not affect accessibility between stations within a certain date range, the optimal candidate set of transfer nodes can be derived by correlating railway operations and flight schedules within the pre-sale period with flight schedules and train timetables. Specific information includes departure nodes, transfer nodes, arrival nodes, optimization objectives, and priorities. The smaller the distance between nodes, the lower the priority value, and the more likely the transfer node is to be selected when forming intermodal routes.

[0098] Thirdly, the minimum transfer time is calculated. The minimum transfer time is a primary constraint considered in this patent. According to... Figure 2Since most railway stations in my country are some distance from surrounding airports, a minimum transfer time needs to be set to ensure passengers can complete their transfers in the shortest possible time and prevent connection failures between air and rail lines due to excessively short transfer times. For railway stations and airports with long distances, the minimum transfer time is calculated based on statistical analysis of collected urban traffic travel time data.

[0099] At the real-time computing layer, after a user submits an air-rail intermodal transport request, the program matches the actual travel origin (OD) to the corresponding virtual OD node. It then assembles the intermodal transport route based on the real-time availability of railway and flight tickets, following the order of "rail first, then flight" and "flight first, then rail," respectively, and displays the travel routes in a sorted manner according to certain recommendation rules or algorithms.

[0100] (3) Taking into account the ticket price characteristics of railways and flights, and considering multiple optimization objectives such as minimum time, minimum cost, and minimum number of transfers, calculate the air-rail intermodal travel route.

[0101] Generally, for the same origin-destination (OD) route, railway fares are relatively stable, while the travel time varies depending on the type of train; airfares, on the other hand, fluctuate dynamically, but the travel time difference is not significant. Therefore, when displaying real-time combined calculations of intermodal routes, routes with shorter railway travel times and lower airfares are prioritized by default. A personalized filtering rule is also set up to avoid displaying too many similar routes and interfering with user selection.

[0102] Figure 4 The calculation process for air-rail intermodal transport routes in this invention is as follows: Figure 4 As shown, the calculation process for an air-rail intermodal transport route comprising two segments includes two main parts: offline and real-time calculation. The offline part includes three modules: virtual node generation, transfer node calculation, and minimum transfer time calculation. Offline calculation can be performed on traditional data warehouses, big data platforms, or general servers, using various programming languages ​​such as SQL, Spark, Python, and Java. The results can be stored in a high-speed in-memory database or cache. The real-time part includes modules for public transportation data collection and intermodal route calculation. An air-rail intermodal transport route can consist of multiple segments. Multi-segment air-rail intermodal transport routes can be constructed by increasing the number of times the candidate set of transfer nodes is calculated, based on the two segments.

[0103] 1. Virtual node generation

[0104] In the virtual node generation module, a virtual node dictionary table needs to be constructed based on the current geographical location information of railway passenger stations and civil aviation airports nationwide, including longitude, latitude, and other geographical location information. This dictionary table mainly includes information such as virtual node number, railway passenger station name, airport name, diameter, major city, and minor city. The geographical location information of railway passenger stations and airports is only updated when new railway passenger stations or civil aviation airports are opened. Based on the common knowledge that intermodal travelers often prefer to transfer between railway passenger stations and airports with shorter distances, the maximum diameter range d of the virtual nodes is initially set by the business personnel. max Later, through optimization of passenger selection preferences, d max This reduces the search space for the next step of calculating the optimal candidate set of transfer nodes and connecting routes. Centered on an airport, select nodes whose distance from that airport does not exceed d. max The railway passenger station may form multiple virtual nodes centered on the airport.

[0105] The virtual node information is used to calculate the optimal candidate set of transfer nodes and to collect public transportation data. It can be stored in any database, data warehouse, in-memory database or file, depending on the actual situation.

[0106] 2. Public Transportation Data Collection

[0107] Traverse all virtual nodes and collect public transportation route information between railway stations and airports within the nodes at a certain frequency at the current time to form detailed traffic route data within the nodes. This data mainly includes information such as travel costs, time, number of transfers, and walking distance between railway stations and airports within each virtual node under various route planning methods, including public transportation, driving, cycling, and walking.

[0108] The collected traffic route details within virtual nodes are used to evaluate the priority of transfer nodes and can be stored in any database, data warehouse, in-memory database, or file, depending on the actual situation.

[0109] 3. Calculation of transfer nodes

[0110] A direct virtual OD (Origin-Destination, or OD for short) refers to two virtual nodes that have at least one direct train or flight. A reachable virtual OD refers to two virtual nodes that have at least one transfer node.

[0111] (1) Calculate the entire network directly accessible virtual OD dataset

[0112] Based on the defined virtual node information, combined with railway operation plans and flight plans within the current period up to the maximum pre-sale date of the railway, a network-wide direct virtual OD dataset is calculated. This dataset mainly includes information such as departure nodes, arrival nodes, number of direct trains / shortest duration / minimum cost, and number of direct flights / shortest duration / minimum cost. For example, given two virtual nodes L1 and L2 with the forms (A1, A2) and (B1, B2) respectively, where A1 and B1 are railway passenger stations and A2 and B2 are airports, L1 and L2 are considered reachable if one of the following two conditions is met; L1 and L2 are then considered a pair of virtual direct ODs:

[0113] ①There is a direct train between A1 and B1, regardless of whether there is a direct flight between A2 and B2;

[0114] ②There are direct flights between A2 and B2, regardless of whether there is a direct train between A1 and B1.

[0115] (2) Calculate the entire network reachable virtual OD dataset

[0116] For three virtual nodes L1, L2 and L3 with the composition (A1, A2), (B1, B2) and (C1, C2) respectively, if L1 and L2 are reachable and L2 and L3 are reachable, then L1 and L3 are considered to be reachable, L2 is a transfer node, and the two intermodal networks formed by L1, L2 and L3 are A1→(B1, B2)→C2 and A2→(B2, B1)→C1 respectively. According to this rule, the entire network-wide reachable virtual OD dataset is traversed. For the same transfer node, multiple corresponding initial priority values ​​are calculated based on objectives such as the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest travel time, and the minimum cost. Finally, the entire network-wide reachable virtual OD dataset can be calculated, which mainly includes information such as departure node, arrival node, transfer node, estimated number of first-leg routes / number of second-leg routes / number of connecting routes / shortest travel time / minimum cost, and initial priority values ​​of transfer nodes under the categories of first-leg routes / number of second-leg routes / number of connecting routes / shortest travel time / minimum cost.

[0117] (3) Transfer node priority model

[0118] In the nationwide reachable virtual OD dataset, the initial priority values ​​of transfer nodes in each intermodal network may differ under categories such as number of routes, shortest duration, and minimum cost. For example, a transfer node L2 with a lower priority calculated based on the shortest duration may have a higher priority calculated based on the minimum cost. Transportation costs, walking distances, durations, and number of transfers within a transfer node are also major factors influencing passenger travel. Therefore, it is necessary to construct prediction models for walking distances, number of transfers, costs, and transfer durations within nodes based on traffic route data. This allows for further adjustment and optimization of transfer node priorities, resulting in a comprehensive priority for transfer nodes based on the fusion of multiple prediction models. Initial priority values ​​for transfer nodes are recorded according to different optimization objectives, ultimately forming multiple candidate sets of optimal transfer nodes under different optimization objectives. These sets mainly include departure nodes, arrival nodes, transfer nodes, optimization objectives (number of first-leg routes / number of second-leg routes / number of intermodal routes / shortest duration / minimum cost / comprehensive objective, etc.), and priority information.

[0119] If the priority is represented by a numerical value, the candidate set of optimal transfer nodes with the maximum priority value not exceeding the specified value N can be selected. The maximum priority value for different dates and regions can be specified uniformly or defined individually based on the differences in time and space requirements and transportation infrastructure construction.

[0120] Calculate the priority of transfer nodes under different optimization objectives to facilitate the display of differentiated routes to users with different preferences when calculating intermodal routes. If personalized route display is not required, the priority of transfer nodes under one or more optimization objectives can be selected based on actual data and demand.

[0121] To reduce the search space for transfer nodes in the process of connecting intermodal transport routes, it is necessary to determine the maximum priority of transfer nodes between a pair of virtual reachable origin-destination (OD) pairs according to certain rules. This maximum priority is defined as the maximum number of transfer nodes between OD pairs with a specified number of transfers. The maximum priority of transfer nodes for different dates and regions can be uniformly specified, or it can be customized based on differences in spatiotemporal needs and transportation infrastructure development. For example, if the number of OD pairs with relatively few routes in both the first and second legs is small, the number of transfer nodes can be set to be larger to facilitate the creation of more intermodal transport routes. The priority can be represented numerically or using other methods.

[0122] To calculate air-rail intermodal transfer nodes containing three trip segments, a network-wide reachable virtual OD dataset containing two trip segments can be associated with a network-wide direct virtual OD dataset once, resulting in two transfer nodes. To calculate air-rail intermodal transfer nodes containing four trip segments, a network-wide reachable virtual OD dataset containing three trip segments can be associated with a network-wide direct virtual OD dataset once, resulting in three transfer nodes. To calculate air-rail intermodal transfer nodes containing N trip segments, a network-wide reachable virtual OD dataset containing N-1 trip segments can be associated with a network-wide direct virtual OD dataset once, resulting in N-1 transfer nodes.

[0123] 4. Calculation of minimum transfer time

[0124] Transfer time refers to the difference between the departure time of the second leg of the journey and the arrival time of the first leg. To avoid the risk that passengers will miss the second leg of their journey due to a short transfer time, the transfer time of the air-rail intermodal route displayed to users cannot be lower than a minimum value. This minimum value is called the minimum transfer time, which is divided into minimum transfer time within a node and convenient transfer time.

[0125] (1) Minimum transfer time within the node

[0126] The minimum transfer time within a node can be specified by business personnel based on experience, or it can be obtained by statistical analysis and classification comparison based on the prediction results output by the transfer time estimation model within the node, under different date categories and time periods.

[0127] (2) Convenient transfer time

[0128] For virtual nodes with relatively certain transfer options, such as those with convenient transfer channels (e.g., Shanghai Hongqiao Railway Station and the airport), connecting buses, and road routes, a fixed minimum transfer time can be specified. The convenient transfer time within a node can be adjusted based on various factors, including station / airport construction, unforeseen events, and management requirements.

[0129] 5. Calculation of intermodal transport routes

[0130] (1) Fuzzy matching of requirements

[0131] Users submit air-rail intermodal transport requests, including departure station or city, arrival station or city, and departure date. The system compares the request with virtual node information and automatically matches virtual nodes to the departure and arrival locations. Because the diameter of virtual nodes is flexible and variable, multiple virtual nodes may be matched.

[0132] (2) Intermodal transport routes

[0133] Based on the matched virtual node information, the corresponding optimal transfer node candidate set is queried, and all available air-rail intermodal routes are concatenated. For example, if a user submits a request for a departure station, arrival station, and departure date, x virtual departure nodes may be matched, forming a virtual departure node dataset F = [F1, F2, F3, ..., F...]. i F x It is possible to match y virtual arrival nodes, forming a virtual arrival node dataset T = [T1, T2, T3, ..., T]. j ,…,T y The program needs to query the candidate set of optimal transfer nodes for N = x*y pairs of virtual reachable ODs, containing all virtual departure and arrival nodes. All virtual reachable ODs are shown in the figure below. If the number of optimal transfer nodes for each pair of virtual reachable ODs is B... q (q = 1, 2, ..., N), at least traversal is required. The candidate set of the second-best transfer nodes.

[0134] After completing the fuzzy matching of demand, the steps for splicing air-rail intermodal transport routes are as follows:

[0135] ①For example Figure 5 As shown, traversal Figure 5 All virtual reachable destinations are identified, and the transfer nodes and their priorities for each pair of destinations are queried in the optimal transfer node candidate set.

[0136] ② Connecting routes can be arranged in two ways: "rail first, then flight" and "flight first, then rail," following the order of increasing distance between virtual reachable origins / destinations (ODs), decreasing priority of transfer nodes, or other specified sequences. For example, in the "rail first, then flight" connecting route mode, a direct rail train is selected for the first leg. Based on the optimal transfer nodes and their priority data obtained in step ①, the transfer nodes are iterated sequentially, and the corresponding flight for the second leg is selected, completing the connecting route where the first leg is rail and the second leg is flight. This process can be repeated to obtain the "flight first, then rail" connecting route method.

[0137] (3) Check ticket availability

[0138] Based on the assembled air-rail intermodal route, query the availability of train and flight tickets for departure nodes to transfer nodes within the departure date T, and for transfer nodes to arrival nodes within the departure date T+Δt. Filter out trains and flights without tickets. Here, Δt is a flexible time period, such as 24 hours.

[0139] (4) Filtering connecting routes (no detour routes were considered because there may be situations where flights detour but the cost is lower, and detours are acceptable to passengers).

[0140] For connecting routes with available tickets for each segment, if the transfer time is less than the minimum transfer time calculated offline, the route is filtered out.

[0141] (5) Sorting display

[0142] Intermodal transport plans can be displayed according to multiple dimensions such as intermodal fare, duration, and transfer time.

[0143] Secondly, embodiments of this application provide an air-rail intermodal transport route generation system, employing the air-rail intermodal transport route generation method described above, such as... Figure 6 As shown, the air-rail intermodal transport route generation system includes:

[0144] Virtual node generation module 10: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, generate multiple virtual nodes centered on the airport. The virtual nodes include an airport and a railway station. The module also marks whether there is a convenient transfer passage within the virtual node according to the distance between the airport and the railway station.

[0145] Optimal transfer node calculation module 20: Based on virtual nodes, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual nodes, construct a priority optimization model for transfer nodes within the virtual nodes, which includes walking distance, number of transfers, cost and transfer time. It also calculates the candidate set of optimal transfer nodes for the national railway and civil aviation passenger networks. The optimal transfer nodes include departure nodes, transfer nodes, arrival nodes, optimization objectives and priorities.

[0146] Minimum transfer time calculation module 30: Calculates the minimum transfer time for air-rail intermodal transport routes based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node.

[0147] Intermodal route calculation and generation module 40: Receives requests for generating air-rail intermodal routes, queries the candidate set of optimal transfer nodes, and splices intermodal routes according to the strategy of prioritizing rail over flight and the strategy of prioritizing flight over rail, based on real-time availability of rail and flight tickets. It also filters the spliced ​​intermodal routes using the minimum transfer time and displays the final generated air-rail intermodal routes in order according to the pre-defined recommendation rules.

[0148] Thirdly, embodiments of this application provide a computer device, including a memory, a processor, and a computer program stored in the memory and executable on the processor, wherein the processor executes the computer program to implement the air-rail intermodal transport route generation method as described above.

[0149] Fourthly, embodiments of this application provide a computer-readable storage medium storing a computer program thereon, wherein the program, when executed by a processor, implements the air-rail intermodal transport route generation method as described above.

[0150] In addition, combined Figure 1 The air-rail intermodal transport route generation method described in this application embodiment can be implemented by computer equipment. Figure 7 This is a schematic diagram of the hardware structure of a computer device according to an embodiment of this application.

[0151] The computer device may include a processor 81 and a memory 82 storing computer program instructions.

[0152] Specifically, the processor 81 may include a central processing unit (CPU), an application specific integrated circuit (ASIC), or one or more integrated circuits that can be configured to implement the embodiments of this application.

[0153] The memory 82 may include a mass storage device for data or instructions. For example, and not limitingly, the memory 82 may include a hard disk drive (HDD), a floppy disk drive, a solid-state drive (SSD), flash memory, an optical disk drive, a magneto-optical disk drive, magnetic tape, or a Universal Serial Bus (USB) drive, or a combination of two or more of these. Where appropriate, the memory 82 may include removable or non-removable (or fixed) media. Where appropriate, the memory 82 may be internal or external to a data processing device. In a particular embodiment, the memory 82 is non-volatile memory. In a particular embodiment, the memory 82 includes read-only memory (ROM) and random access memory (RAM). Where appropriate, the ROM may be a mask-programmed ROM, a programmable read-only memory (PROM), an erasable programmable read-only memory (EPROM), an electrically erasable programmable read-only memory (EEPROM), an electrically alterable read-only memory (EAROM), or flash memory, or a combination of two or more of these. Where appropriate, the RAM can be Static Random-Access Memory (SRAM) or Dynamic Random-Access Memory (DRAM). DRAM can be Fast Page Mode Dynamic Random-Access Memory (FPMDRAM), Extended Data Out Dynamic Random-Access Memory (EDODRAM), Synchronous Dynamic Random-Access Memory (SDRAM), etc.

[0154] The memory 82 can be used to store or cache various data files that need to be processed and / or communicated, as well as possible computer program instructions executed by the processor 81.

[0155] The processor 81 reads and executes computer program instructions stored in the memory 82 to implement any of the air-rail intermodal transport route generation methods in the above embodiments.

[0156] In some embodiments, the computer device may further include a communication interface 83 and a bus 80. For example, Figure 7 As shown, the processor 81, memory 82, and communication interface 83 are connected through bus 80 and complete communication with each other.

[0157] The communication interface 83 is used to enable communication between the various modules, devices, units, and / or equipment in the embodiments of this application. The communication port 83 can also enable data communication with other components such as external devices, image / data acquisition devices, databases, external storage, and image / data processing workstations.

[0158] Bus 80 includes hardware, software, or both, that couples components of a computer device together. Bus 80 includes, but is not limited to, at least one of the following: data bus, address bus, control bus, expansion bus, and local bus. For example, and not as a limitation, bus 80 may include an Accelerated Graphics Port (AGP) or other graphics bus, an Extended Industry Standard Architecture (EISA) bus, a Front Side Bus (FSB), a Hyper Transport (HT) interconnect, an Industry Standard Architecture (ISA) bus, an InfiniBand interconnect, a Low Pin Count (LPC) bus, a memory bus, a Micro Channel Architecture (MCA) bus, a Peripheral Component Interconnect (PCI) bus, a PCI-Express (PCI-X) bus, a Serial Advanced Technology Attachment (SATA) bus, a Video Electronics Standards Association Local Bus (VLB) bus, or other suitable buses, or a combination of two or more of these. Where appropriate, bus 80 may include one or more buses. Although specific buses are described and illustrated in the embodiments of this application, this application considers any suitable bus or interconnection.

[0159] Compared to existing technologies, this invention proposes the concept of flexible virtual nodes and constructs a data representation method for virtual nodes, simplifying the search calculation for the optimal transfer station or airport in air-rail intermodal transport. This invention also proposes a hierarchical decoupling calculation method, ensuring that the calculation of the optimal transfer node, constraints, and specific intermodal travel routes are independent, thus improving algorithm efficiency. Furthermore, this invention comprehensively considers the ticket price characteristics of railways and flights, taking into account multiple optimization objectives such as minimum time, minimum cost, and minimum number of transfers, to calculate air-rail intermodal travel routes.

[0160] The embodiments described above are merely illustrative of several implementation methods of this application, and while the descriptions are relatively specific and detailed, they should not be construed as limiting the scope of the invention patent. It should be noted that those skilled in the art can make various modifications and improvements without departing from the concept of this application, and these all fall within the protection scope of this application. Therefore, the protection scope of this patent application should be determined by the appended claims.

Claims

1. A method for generating a route for air-rail intermodal transport, characterized by, The method for generating air-rail intermodal transport routes includes: Virtual node generation steps: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, multiple virtual nodes are generated with the airport as the center. Each virtual node includes an airport and a railway station at a certain distance apart. The distance between the railway station and the airport is a variable, which is the diameter of the virtual node. The virtual node is an elastic virtual node, and the diameter of the virtual node is a variable that can be iteratively optimized according to the urban transportation facilities and passenger travel data. The presence of a convenient transfer channel within the virtual node is marked based on the distance between the airport and the railway station. An offline virtual node dictionary table is constructed, which includes the virtual node number, railway station name, airport name, diameter, and information on the main city and secondary cities to which it belongs. The optimal transfer node calculation steps are as follows: Based on the virtual node, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual node, construct a priority optimization model for the transfer node within the virtual node, which includes estimates based on walking distance, number of transfers, cost and transfer time. Then, calculate the optimal transfer node candidate set of the national railway and civil aviation passenger networks. The optimal transfer node includes the departure node, transfer node, arrival node, optimization objective and priority. Based on the virtual nodes, and combined with railway operation plans and flight schedules within the current period up to the maximum pre-sale date of the railway, a network-wide direct virtual OD dataset is generated offline. The network-wide direct virtual OD dataset is then traversed, and for the same transfer node, multiple initial priority values ​​are calculated based on the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest travel time, and the minimum cost. These initial priority values ​​are then combined with the distances between virtual reachable ODs to form a network-wide reachable virtual OD dataset. Based on public transportation route data within the virtual nodes, a transfer node priority optimization model is constructed, incorporating walking distance, number of transfers, cost, and estimated transfer time. Iterative optimization yields a comprehensive priority for transfer nodes, ultimately forming multiple candidate sets of optimal transfer nodes under different optimization objectives. These optimization objectives include the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest travel time, the minimum cost, and the comprehensive objective. Minimum transfer time calculation steps: Calculate the minimum transfer time for the air-rail intermodal transport route based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node; The steps for calculating and generating intermodal transport routes are as follows: receiving requests for generating air-rail intermodal transport routes, querying the candidate set of the optimal transfer nodes, assembling intermodal transport routes according to the form of first rail then flight and first flight then rail, and combining the intermodal transport routes based on the real-time availability of railway and flight tickets, filtering the combined intermodal transport routes using the minimum transfer time, and sorting and displaying the finally generated air-rail intermodal transport routes according to the predetermined recommendation rules.

2. The method of claim 1, wherein, The method for generating air-rail intermodal transport routes also includes: Public transportation data collection steps: Traverse all virtual nodes and collect public transportation route information between railway stations and airports within the virtual nodes at a certain frequency at the current time to generate public transportation route data within the virtual nodes.

3. The method of claim 1 or 2, wherein, The virtual node generation steps include: Based on the current longitude and latitude information of railway passenger stations and civil aviation airports across the country, or other relevant information that can calculate the distance between railway passenger stations and civil aviation airports, the virtual node dictionary table is constructed offline. The dictionary table includes virtual node number, railway passenger station name, airport name, diameter, and information on the main city and secondary city to which it belongs.

4. The method for generating air-rail intermodal transport routes according to claim 1 or 2, characterized in that, The steps for calculating the optimal transfer node include: The calculation steps for the full-network direct virtual OD dataset are as follows: Based on the virtual nodes, and combined with railway operation plans and flight plan information within the current period up to the maximum pre-sale date of the railway, the full-network direct virtual OD dataset is generated offline. The calculation steps for the network-wide reachable virtual OD dataset are as follows: Traverse the network-wide direct virtual OD dataset, and for the same transfer node, sort and calculate multiple corresponding initial priority values ​​based on the number of first-leg routes, the number of second-leg routes, the number of connecting routes, the shortest duration, and the minimum cost, as well as the distance between virtual reachable ODs, to form the network-wide reachable virtual OD dataset. The steps for calculating the distance between virtual reachable ODs are as follows: Taking the center point of the starting node as the starting point and the center point of the destination node as the ending point, calculate the distance between the starting point and the ending point to obtain the distance between virtual reachable ODs. The steps for constructing the transfer node optimization model are as follows: Based on the public transportation route data within the node, construct a prediction model for walking distance, number of transfers, cost, and transfer time within the node; iteratively optimize the priority of transfer nodes to obtain the comprehensive priority of transfer nodes; and finally form a candidate set of optimal transfer nodes under multiple different optimization objectives. The optimization objectives include: number of first-journey routes, number of second-journey routes, number of connecting routes, shortest duration, minimum cost, and comprehensive objective. The steps for determining the maximum priority of transfer nodes are as follows: the maximum priority of transfer nodes between a pair of virtual reachable ODs is determined according to a predetermined priority rule. The predetermined priority rule is: specifying the maximum priority of transfer nodes for different dates and regional ranges, or making a personalized definition of the maximum priority of transfer nodes based on the differences in time and space requirements and transportation infrastructure construction. Steps for determining the number of transfers: Calculate the maximum number of transfers according to the predetermined number of transfers rule. The predetermined number of transfers rule is as follows: Calculate the air-rail intermodal transfer nodes containing N segments of the journey. The whole network virtual reachable OD dataset containing N-1 segments of the journey can be associated with the whole network direct virtual OD dataset once to obtain N-1 transfer nodes.

5. The method for generating air-rail intermodal transport routes according to claim 1 or 2, characterized in that, The steps for calculating the minimum transfer time include: The calculation steps for the minimum transfer time within a transfer node are as follows: Using predetermined values ​​or prediction results output by a transfer time estimation model within the node, the minimum transfer time within the transfer node is calculated offline for different date categories and time periods. Convenient transfer time calculation steps: The convenient transfer time is calculated offline using a fixed minimum transfer time or adjusted according to various factors.

6. The method for generating air-rail intermodal transport routes according to claim 1 or 2, characterized in that, The steps for calculating and generating the intermodal transport route include: Fuzzy matching requirement steps: Compare air-rail intermodal transport requests and virtual nodes, and automatically match multiple virtual nodes belonging to the departure and arrival points; Intermodal route splicing steps: Based on the matched virtual nodes, query the corresponding optimal transfer node candidate set, and splice all selectable air-rail intermodal routes; Steps to check available tickets: Based on the assembled air-rail intermodal transport route, check the available tickets for railways and flights within the range of departure date from departure node to transfer node and from transfer node to arrival node plus a maximum transfer time range, and filter out trains and flights without tickets. The maximum transfer time range can be specified or calculated according to certain rules. Intermodal route filtering steps: For intermodal routes with available tickets for each segment of the journey, if the transfer time is less than the minimum transfer time, then the intermodal route is filtered. The sorting and display steps are as follows: The final air-rail intermodal transport routes are displayed according to multiple dimensions such as intermodal fare, duration, and transfer time.

7. The method for generating air-rail intermodal transport routes according to claim 6, characterized in that, The intermodal transport route splicing step also includes: Traverse all virtual reachable destinations obtained by fuzzy matching, and query the transfer node of each pair of destinations and the priority of the transfer node in the candidate set of the optimal transfer node. The intermodal routes are spliced ​​together in the form of rail first then flight and flight first then rail, according to the order of distance between the virtual reachable ODs from smallest to largest, the priority of transfer nodes from high to low, or other specified order.

8. A system for generating air-rail intermodal transport routes, employing the air-rail intermodal transport route generation method as described in any one of claims 1-7, characterized in that, The air-rail intermodal transport route generation system includes: Virtual node generation module: Based on the preset maximum diameter of the virtual node or the diameter preferred by passengers, multiple virtual nodes are generated with the airport as the center. The virtual nodes include an airport and a railway station. The module also marks whether there is a convenient transfer channel within the virtual node according to the distance between the airport and the railway station. Optimal transfer node calculation module: Based on the virtual node, according to the railway timetable and flight plan within the pre-sale period and the traffic route data within the virtual node, constructs a priority optimization model for transfer nodes within the virtual node, which includes estimates based on walking distance, number of transfers, cost and transfer time. It also calculates the optimal transfer node candidate set of the national railway and civil aviation passenger networks. The optimal transfer node includes departure node, transfer node, arrival node, optimization objective and priority. Minimum transfer time calculation module: Calculates the minimum transfer time for air-rail intermodal transport routes based on whether the virtual node has a convenient transfer channel identifier and the estimated transfer time model within the virtual node; The steps for calculating and generating intermodal transport routes are as follows: receiving requests for generating air-rail intermodal transport routes, querying the candidate set of the optimal transfer nodes, assembling intermodal transport routes according to the form of first rail then flight and first flight then rail, and combining the intermodal transport routes based on the real-time availability of railway and flight tickets, filtering the combined intermodal transport routes using the minimum transfer time, and sorting and displaying the finally generated air-rail intermodal transport routes according to the predetermined recommendation rules.

9. A computer device comprising a memory, a processor, and a computer program stored in the memory and executable on the processor, characterized in that, When the processor executes the computer program, it implements the air-rail intermodal transport route generation method as described in any one of claims 1 to 7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the program is executed by the processor, it implements the air-rail intermodal transport route generation method as described in any one of claims 1 to 7.

Images