Collaborative organization method for efficient and collaborative configuration of public transport hub resources

Abstract

The invention discloses a cooperative organization method for efficient cooperative configuration of public transport hub resources, and relates to the technical field of traffic scheduling, and the method comprises the steps: analyzing the relation between hub transport capacity supply and passenger demands in different time periods according to a space-time path matching result; constructing a transport capacity matching optimization index system, calculating standard indexes, analyzing asynchronous correlation characteristics of various indexes in a time sequence state, and constructing a mapping relation graph between passenger travel characteristics and transport characteristics; analyzing the correlation degree between different mapping elements, constructing a public transportation hub supply and demand matching optimization model, and inputting the feature mapping relation graph into the public transportation hub supply and demand matching optimization model for matching optimization; a data-driven transfer scheduling optimization model is established, multi-mode traffic trip chain connection matching and self-adaptive scheduling are realized in combination with real-time matching measurement information, spatial and temporal mutual influence of multiple traffic demands on a traffic hub is fully considered, and spatial decomposition and collaborative prediction of the traffic demands are realized.

Description

Technical Field

[0001] The present application relates to the technical field of traffic dispatching, and in particular to a collaborative organization method for efficient collaborative allocation of public transportation hub resources. Background Art

[0002] The traffic flows involved in public transportation hubs are complex and diverse, and the diverse passenger gathering and distribution methods make it easy for transportation hubs to experience passenger congestion and tight transportation capacity resources in daily operations. On the one hand, it will cause congestion inside and near the hub, and on the other hand, it will reduce the travel quality of passengers and even cause chaos. Therefore, this puts higher demands on the hub's capacity and resource allocation.

[0003] The existing hub coordinated dispatching methods still have problems such as weak coordinated linkage capabilities between hubs, mismatched capabilities between hubs and connecting lines, uncoordinated connections between various transportation systems, low operation and dispatching efficiency, and unreasonable allocation of facilities and equipment, which make it impossible to effectively evacuate passengers during peak passenger flow periods, resulting in passenger delays and reduced travel quality. Summary of the invention

[0004] In view of this, the present application provides a collaborative organization method for the efficient and coordinated allocation of public transportation hub resources. Through the precise matching results based on the "people-vehicle-line-station" space-time path, the relationship between hub capacity matching and passenger demand in different time periods is analyzed. According to the travel behavior characteristic spectrum of the integrated multi-modal transportation space-time environment, the diversified composite spatial topological structure of the hub and other information, the integrated transportation hub integrated connection collaborative processing and intelligent matching optimization method is analyzed, and a data-driven transfer scheduling optimization model is established, thereby improving the transfer and connection efforts, realizing the integrated intelligent connection matching and adaptive scheduling of the entire multi-modal transportation travel chain, and solving the technical problems of the existing hub collaborative scheduling method, such as the mismatch between the hub and the connecting line capacity, low operation scheduling efficiency, and unreasonable allocation of facilities and equipment.

[0005] To achieve the above object, the present invention provides the following technical solutions: A collaborative organization method for efficient collaborative allocation of public transportation hub resources, including: obtaining the matching results of the "people-vehicle-line-station" spatiotemporal paths, and analyzing the relationship between hub capacity supply and passenger demand in different time periods based on the matching results; Construct a capacity matching optimization index system, obtain group travel behavior characteristics, hub composite spatial topological structure information and transportation characteristics of the multi-modal transportation space-time environment in the transportation hub, calculate standard indicators, analyze the asynchronous correlation characteristics of various indicators in the time series state, and construct a mapping relationship map between passenger travel characteristics and transportation characteristics; Analyze the degree of association between different mapping elements, build a public transportation hub supply and demand matching optimization model with the goal of optimizing resource coordination and minimizing operating costs, input the feature mapping relationship map into the public transportation hub supply and demand matching optimization model for matching optimization, and output real-time matching metrics for dynamic and static information; A data-driven transfer scheduling optimization model is established, combined with real-time matching measurement information, to achieve integrated connection matching and adaptive scheduling of the entire multi-modal transportation chain.

[0006] Furthermore, the matching results of the “passenger-vehicle-line-station” space-time path are obtained, and the relationship between hub capacity supply and passenger demand in different periods is analyzed based on the matching results, including: Construct a multi-modal transportation arrival-departure coupling coordination index system for transportation hubs, and use the entropy weight method to determine the parameter index weights; Construct a calculation model for the coordination degree of multi-modal transportation arrival-departure coupling at transportation hubs: , ,in, It is the overall comprehensive coordination index of the composite network system; is the development index of the g-th subsystem under the overall index; is the coefficient to be determined; is the overall coupling degree of the composite network system; Input the index data into the transportation hub multi-mode transportation arrival-departure coupling coordination degree calculation model to generate the hub multi-mode transportation coupling coordination degree matrix; The matching relationship between the hub's arrival and departure passenger flow and vehicle flow is analyzed based on the hub's equipment and facility layout, passenger flow organization plan, vehicle dispatch plan data and coupling coordination matrix. The feasible vehicle flow sets for passengers on different paths are analyzed from the timetables and passenger flow data of various transportation modes. Based on the hub's entry and exit travel time distribution and transfer travel time distribution, the degree of passenger-vehicle capacity matching at the hub in various time periods throughout the day is calculated and analyzed.

[0007] Furthermore, the line evacuation capacity matching degree is calculated according to the formula ,in, Passenger flow share of the i-th mode of transport, The passenger arrival capacity for transport, is the line evacuation capacity of the i-th type of transportation mode, and the hub equipment and facility capacity matching degree is calculated according to the formula ,in, Sending capacity for transporting passengers, The facility and equipment capacity of the i-th mode of transportation is used to calculate the overall comprehensive coordination index based on the matching degree of line evacuation capacity and the matching degree of hub equipment and facilities capacity. in accordance with Determine the matching relationship between the hub's arrival-departure passenger flow and vehicle flow.

[0008] Furthermore, the movement matching optimization indicators include operation schemes, scheduling characteristics, carrying capacity and timeliness impact, as well as travel OD, heterogeneity, migration efficiency and gradient characteristics. The calculation of standard indicators includes the use of hierarchical analysis method to transform various attribute indicators into standard indicators that can be uniformly measured.

[0009] Furthermore, analyzing the asynchronous correlation characteristics of various indicators in the time series state includes: using a dynamic time bending algorithm and fluctuation weights to analyze the asynchronous correlation characteristics of various indicators in the time series state.

[0010] Furthermore, the construction of a public transportation hub supply and demand matching optimization model includes: Construct an objective function, which aims to optimize resource coordination and match and minimize operating costs; The objective function is calculated using the power coefficient method. , , , where R1 is the resource coordination matching degree and R2 is the operating cost; Conduct proximal analysis of supply and demand matching, use distributed edge computing methods to analyze and process real-time data, simultaneously conduct multi-modal traffic multi-level information fixed-point transmission and remote analysis, and use data link real-time interaction methods to optimize resource matching under the global state of the current public transportation hub.

[0011] Furthermore, before establishing a data-driven transfer scheduling optimization model, it is necessary to verify the degree of correlation and connection between the multimodal transportation operation plans in the public transportation hub through the time series event matching filtering method, and then dynamically analyze the multi-dimensional characteristics of the team margin, time threshold, and cumulative load error between each operation plan.

[0012] It can be seen from the above technical solution that the advantages of the present invention are: 1. This application analyzes the relationship between hub capacity matching and passenger demand in different time periods based on the precise matching results of the "people-vehicle-line-station" space-time path, and analyzes the integrated connection coordination processing and intelligent matching optimization methods of comprehensive transportation hubs based on the travel behavior characteristic spectrum of the multi-modal transportation space-time environment, the diversified composite spatial topological structure of the hub, and other information, and establishes a data-driven transfer scheduling optimization model, thereby improving the transfer and connection efforts, and realizing the integrated intelligent connection matching and adaptive scheduling of the entire multi-modal transportation travel chain.

[0013] 2. Fully consider the spatial and temporal mutual influence of various transportation demands at transportation hubs, realize the spatial decomposition and coordinated prediction of transportation demands, improve the effective evacuation of passengers during peak hours, and improve the quality of passenger travel. BRIEF DESCRIPTION OF THE DRAWINGS

[0014] The drawings constituting a part of the present application are used to provide a further understanding of the present application. The illustrative embodiments of the present application and their descriptions are used to explain the present application and do not constitute an improper limitation on the present application.

[0015] Figure 1 A schematic diagram of the steps of this application.

[0016] Figure 2 This is a schematic diagram of the specific steps of step S1 of this application. DETAILED DESCRIPTION

[0017] In order to make the purpose, technical solution and advantages of the present application more clearly understood, the present application is further described in detail below in conjunction with the implementation modes and the accompanying drawings. Here, the illustrative implementation modes and descriptions of the present application are used to explain the present application, but are not intended to limit the present application.

[0018] As a key node of passenger flow, the comprehensive transportation hub undertakes the passenger flow exchange function of the comprehensive transportation network. The hub's capacity analysis and resource allocation are important links in integrating transportation resources and realizing integrated transportation.

[0019] refer to Figure 1 to Figure 2 ,like Figure 1 As shown, this embodiment provides a collaborative organization method for efficient collaborative allocation of public transportation hub resources. Based on actual travel data and passenger flow forecast data, the precise matching technology of the "people-vehicle-line-station" space-time path in the hub is studied. Based on the space-time path matching relationship in the hub, the collaborative scheduling optimization method between different transportation modes in the comprehensive transportation hub is studied, and a multi-modal transportation transfer connection algorithm for large-scale combinatorial optimization problems is proposed to improve the service level of the comprehensive transportation hub and improve the collaborative network between different transportation modes, enhance the reliability of passengers' travel and transfer in the city, and realize the integrated coordination of transportation operation organization and safety control business. The method specifically includes: Step S1: Obtain the matching results of the “person-vehicle-line-station” space-time path, and analyze the relationship between hub capacity supply and passenger demand in different time periods based on the matching results.

[0020] Step S1 is as follows: obtaining the matching result of the “passenger-vehicle-line-station” space-time path, and analyzing the relationship between hub capacity supply and passenger demand in different time periods according to the matching result, including: Step S11: construct a multi-modal transportation arrival-departure coupling coordination index system for transportation hubs, and use the entropy weight method to determine the parameter index weights; Step S12: Construct a calculation model for the coordination degree of multi-modal transportation arrival-departure coupling at a transportation hub: , ,in, It is the overall comprehensive coordination index of the composite network system; is the development index of the g-th subsystem under the overall index; is the coefficient to be determined; is the overall coupling degree of the composite network system; Step S13: input the index data into the transportation hub multi-mode transportation arrival-departure coupling coordination degree calculation model to generate the hub multi-mode transportation coupling coordination degree matrix; Step S14: Analyze the matching relationship between the hub's arrival-departure passenger flow and vehicle flow based on the hub's equipment and facility layout, passenger flow organization plan, vehicle dispatch plan data and coupling coordination matrix, analyze the feasible vehicle flow sets of passengers in different paths from the timetables and passenger flow data of each mode of transportation, and calculate and analyze the degree of passenger-vehicle capacity matching at the hub in each period of the day based on the hub's entry and exit travel time distribution and transfer travel time distribution.

[0021] Specifically, the line evacuation capacity matching degree is calculated according to the formula ,in, Passenger flow share of the i-th mode of transportation, The passenger arrival capacity for transport, is the line evacuation capacity of the i-th type of transportation mode, and the hub equipment and facility capacity matching degree is calculated according to the formula ,in, Sending capacity for transporting passengers, The facility and equipment capacity of the i-th mode of transportation is used to calculate the overall comprehensive coordination index based on the matching degree of line evacuation capacity and the matching degree of hub equipment and facilities capacity. in accordance with Determine the matching relationship between the hub's arrival-departure passenger flow and vehicle flow.

[0022] This application comprehensively measures the transport capacity matching degree from two aspects: line evacuation capacity and facility and equipment capacity. Based on the calculation of line evacuation and facility and equipment capacity of various modes of transportation at the hub, an optimization model for balanced matching of the transport capacity of various modes of transportation during peak passenger flow periods is formed. The line evacuation capacity includes passenger flow organization plans, vehicle scheduling plan data, and transportation information contained in the coupling coordination matrix, and the facility and equipment capacity includes the hub equipment and facility layout.

[0023] In this embodiment, before constructing the index system of the coupling coordination degree of multimodal transportation at the transportation hub, it is necessary to analyze the correlation between the arrival traffic flow at the hub, the inbound passenger flow at the hub, the outbound passenger flow at the hub, and the departure traffic flow at the hub, that is, the influence of the line-OD-line interaction, and consider the influence of factors such as the hub flow restriction scheme, channel capacity, platform capacity, equipment and facilities, and vehicle configuration on the passenger transfer and travel, and hierarchically convert them into the coupling relationship between the arrival and departure traffic flows at the hub; secondly, based on multi-source passenger flow, vehicle flow and other multi-modal characteristic data, hub operation parameter indicators such as the travel time of the hub passenger flow, the transfer waiting time, the operation cost of the hub public transportation vehicle, the dispatching cost, the vehicle load rate, the maximum number of passengers gathered at each platform, and the passenger flow dissipation speed are proposed. Then, the entropy weight method is used to determine the weights of the parameter indicators, and the calculation model of the coupling coordination degree of multimodal transportation at the public transportation hub is constructed, and then the coupling coordination degree matrix of the hub multimodal transportation is generated. On this basis, the spatiotemporal variation characteristics of the comprehensive flow coupling of the hub transportation system are studied.

[0024] Step S2: Construct a capacity matching optimization index system, obtain group travel behavior characteristics, hub composite spatial topological structure information and transportation characteristics of the multi-modal transportation space-time environment in the transportation hub, calculate standard indicators, analyze the asynchronous correlation characteristics of various indicators under the time series state, and construct a mapping relationship map between passenger travel characteristics and transportation characteristics.

[0025] Capacity matching is an important indicator to measure the coordination of capacity of various transportation modes in a comprehensive passenger transport hub. By analyzing the key elements of capacity matching, a capacity matching optimization indicator system can be constructed.

[0026] In this embodiment, the transport capacity matching optimization indicators include operation plans, scheduling characteristics (duration, gradient, path freedom, etc.), carrying performance (loading speed, radiation intensity, delivery boundary, etc.), timeliness impact (spread index, mutation speed, etc.), as well as travel OD, heterogeneity, migration efficiency and gradient characteristics. The calculation of standard indicators includes the use of hierarchical analysis method to transform various attribute indicators into standard indicators that can be uniformly measured.

[0027] Analyzing the asynchronous correlation characteristics of various indicators in the time series state includes using the dynamic time warping algorithm and volatility weights to analyze the asynchronous correlation characteristics of various indicators in the time series state. Specifically, the dynamic time warping (Dynamic Time Warping, DTW) algorithm and volatility weights are used to analyze the asynchronous correlation characteristics of various indicators in the time series state, mainly involving two aspects: similarity measurement and weight adjustment of time series data.

[0028] The DTW algorithm mainly uses a dynamic programming strategy to adjust the correspondence between the sampling time points of two sequences, calculate the minimum distance between the two time series data, and then measure the similarity of the two sequences. In the indicator time series state analysis, the DTW algorithm can help identify the similarity between different indicator time series, even if these sequences differ in length, rate or amplitude. By dynamically "bending" the time axis, the DTW algorithm can find the best alignment between the two sequences, thereby accurately measuring the similarity between them. The volatility weight is a method for adjusting the weight of time series data, and different weights can be assigned according to the volatility of the time series. In the indicator time series state analysis, the volatility weight can be used to emphasize those time points or segments with large fluctuations that may contain more useful information. The volatility weight of each time point or segment can be calculated based on its volatility (such as standard deviation, coefficient of variation, etc.), and then these weights can be applied to the similarity measurement of time series data. In the DTW algorithm, the volatility weight can be used as a weight factor for the distance calculation between different time points or segments to emphasize the impact of those time points or segments with large fluctuations on the overall similarity. In this way, the asynchronous correlation characteristics between different indicator time series can be identified, that is, the impact of their relative misalignment and fluctuation in time on their similarity. These asynchronous correlation characteristics reveal the temporal dependencies, mutual influences or potential risk factors between different indicators, which helps to gain a deeper understanding of their dynamic behaviors and interactions.

[0029] In summary, using the DTW algorithm and volatility weights to analyze the asynchronous correlation characteristics of various indicators in the time series state is an effective method, which can help us more accurately measure the similarity and asynchronous relationship between different indicator time series, and thus reveal the dynamic behavior and interaction between them. Step S3: Analyze the degree of association between different mapping elements, build a public transportation hub supply and demand matching optimization model with the goal of optimizing resource coordination matching and minimizing operating costs, input the feature mapping relationship map into the public transportation hub supply and demand matching optimization model for matching optimization, and output real-time matching metrics for dynamic and static information.

[0030] In this embodiment, step S3 is specifically as follows: analyzing the degree of association between different mapping elements includes: Step S31: Use policy gradient and Apriori to analyze the degree of association between different mapping elements.

[0031] The travel characteristics and transportation characteristics are regarded as items, and the support is calculated. The support represents the frequency of an item (or item set) in the data set. The frequent item sets are filtered out by the support threshold. Frequent item sets are item sets with support exceeding the threshold. The Apriori algorithm is then used to generate association rules. These rules represent the association between travel characteristics and transportation characteristics. By analyzing the generated association rules, we can understand which travel characteristics and transportation characteristics have strong associations. For example, if the rule shows that "80% of users traveling during the morning rush hour choose public transportation as a mode of transportation", it indicates that there is a strong association between the morning rush hour and public transportation. Use a policy gradient algorithm (such as the REINFORCE algorithm, the Actor-Critic algorithm, etc.) to train a policy network. By observing the performance of the policy network on the test data, we can understand the impact of different travel characteristics and transportation characteristics on the choice of transportation mode. If the policy network is more inclined to choose a certain mode of transportation when a certain travel characteristic is included, it can be considered that there is a strong association between the travel characteristic and the mode of transportation. When conducting analysis, the association rules generated by the Apriori algorithm are used as prior knowledge for policy gradient analysis. During the training process of the policy network, the association rules generated by the Apriori algorithm are used as regularization terms or constraints to ensure that the learned strategy conforms to the prior knowledge. By combining the results of the Apriori algorithm and policy gradient, the complex relationship between travel characteristics and transportation characteristics can be understood, and travel and transportation strategies can be optimized accordingly.

[0032] In this embodiment, constructing a public transportation hub supply and demand matching optimization model includes: Step S32: construct an objective function, the objective function aims to achieve the best resource coordination matching and the lowest operating cost; Step S33: Calculate the objective function using the efficacy coefficient method. , , , where R1 is the resource coordination matching degree and R2 is the operating cost; Step S34: Conduct proximal analysis of the matching degree of supply and demand, use distributed edge computing methods to analyze and process real-time data, perform multi-modal traffic multi-level information fixed-point transmission and remote analysis at the same time, and use data link real-time interaction methods to optimize resource matching under the global state of the current public transportation hub.

[0033] Comprehensive transportation hubs integrate multiple modes of transportation. While meeting the basic needs of passenger exchange and achieving a balance of transportation capacity between multiple modes of transportation, they also need to take certain measures to meet the growing travel needs of passengers and avoid capacity bottlenecks caused by limited transportation resources during peak passenger flow periods. It is necessary to effectively adjust transportation capacity resources to meet the needs of passenger exchange at different stages, while also avoiding waste of transportation capacity resources and achieving a balance between transportation capacity supply and demand.

[0034] Therefore, it is necessary to calculate and analyze the capacity matching degree. The capacity matching degree is the ratio between the actual arrival and departure capacity of passengers and the capacity provided by other modes of transportation. It can reflect the balance between the demand and supply of hub capacity, including three states: surplus capacity, coordination and bottleneck. Through the calculation and analysis of the capacity matching degree, we can obtain the mismatched links and time periods of various modes of transportation, and then analyze the corresponding travel characteristics and transportation characteristics to build a transportation hub supply and demand matching optimization model, and coordinate and optimize the weak links of the hub's capacity. This application aims to improve the hub's capacity efficiency and resource utilization, and achieve the ultimate goal of optimizing capacity matching with the lowest operating cost adjustment plan.

[0035] Step S4: Establish a data-driven transfer scheduling optimization model, combine it with real-time matching metric information, and realize integrated connection matching and adaptive scheduling of the entire multi-modal transportation chain.

[0036] Before establishing a data-driven transfer scheduling optimization model, it is necessary to verify the degree of correlation and connection of multimodal traffic operation plans in public transportation hubs through a time series event matching and filtering method, and then dynamically analyze the multi-dimensional characteristics of the shift margin, time threshold, and cumulative load error between each operation plan. This embodiment first verifies the degree of correlation and connection of multimodal traffic operation plans in public transportation hubs through a time series event matching and filtering method, and dynamically analyzes the multi-dimensional characteristics of the shift margin, time threshold, and cumulative load error between each operation plan. On this basis, the real-time interaction method of data links in a networked environment is studied in combination with vehicle-station edge collaborative computing. Through parallel computing at multiple levels such as data link time transmission, traffic data batch processing, autonomous matching of traffic characteristics, and traffic control correlation and coordination, the automatic processing of key traffic characteristic indicators of comprehensive hubs such as the connection characteristics of multimodal traffic, the degree of passenger flow heterogeneity, the cumulative gradient of load error, and the passenger diversion density is realized.

[0037] This application is aimed at the demand for fast and efficient transfer of multi-modal passenger flow in public transportation hubs. Based on the precise matching results of the "people-vehicle-line-station" space-time path, it explores the relationship between hub capacity matching and passenger demand in different time periods. According to the travel behavior characteristic spectrum of the multi-modal transportation space-time environment, the diversified complex spatial topological structure of the hub and other information, it studies the integrated connection collaborative processing and intelligent matching optimization technology of comprehensive transportation hubs, establishes a data-driven transfer scheduling optimization model, improves the transfer and connection strength, and realizes the integrated intelligent connection matching and adaptive scheduling of the whole process of the multi-modal transportation travel chain.

[0038] The above description is only the preferred embodiment of the present application and is not intended to limit the present application. For those skilled in the art, the embodiments of the present application may have various modifications and variations. Any modification, equivalent replacement, improvement, etc. made within the spirit and principle of the present application shall be included in the protection scope of the present application.

Claims

1. A collaborative organization method for efficient collaborative allocation of public transportation hub resources, characterized in that: The steps include: Obtain the matching results of the "passenger-vehicle-line-station" space-time path, and analyze the relationship between hub capacity supply and passenger demand in different time periods based on the matching results; Construct a capacity matching optimization index system, obtain group travel behavior characteristics, hub composite spatial topological structure information and transportation characteristics of the multi-modal transportation space-time environment in the transportation hub, calculate standard indicators, analyze the asynchronous correlation characteristics of various indicators in the time series state, and construct a mapping relationship map between passenger travel characteristics and transportation characteristics; Analyze the degree of association between different mapping elements, build a public transportation hub supply and demand matching optimization model with the goal of optimizing resource coordination matching and minimizing operating costs, input the feature mapping relationship map into the public transportation hub supply and demand matching optimization model for matching optimization, and output real-time matching metrics of dynamic and static information; A data-driven transfer scheduling optimization model is established, combined with real-time matching measurement information, to achieve integrated connection matching and adaptive scheduling of the entire multi-modal transportation chain.

2. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 1 is characterized in that: The obtaining of the matching result of the "passenger-vehicle-line-station" space-time path and analyzing the relationship between hub capacity supply and passenger demand in different time periods according to the matching result include: Construct a multi-modal transportation arrival-departure coupling coordination index system for transportation hubs, and use the entropy weight method to determine the parameter index weights; Construct a calculation model for the coordination degree of multi-modal transportation arrival-departure coupling at transportation hubs: , ,in, It is the overall comprehensive coordination index of the composite network system; is the development index of the g-th subsystem under the overall index; is the coefficient to be determined; is the overall coupling degree of the composite network system; Inputting the index data into the transportation hub multi-mode transportation arrival-departure coupling coordination degree calculation model to generate a hub multi-mode transportation coupling coordination degree matrix; The matching relationship between the hub's arrival and departure passenger flow and vehicle flow is analyzed based on the hub's equipment and facility layout, passenger flow organization plan, vehicle dispatch plan data and coupling coordination matrix. The feasible vehicle flow sets for passengers on different paths are analyzed from the timetables and passenger flow data of various transportation modes. Based on the hub's entry and exit travel time distribution and transfer travel time distribution, the degree of passenger-vehicle capacity matching at the hub in various time periods throughout the day is calculated and analyzed.

3. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 2 is characterized in that: Calculate the line evacuation capacity matching degree according to the formula ,in, Passenger flow share of the i-th mode of transport, The passenger arrival capacity for transport, is the line evacuation capacity of the i-th type of transportation mode, and the hub equipment and facility capacity matching degree is calculated according to the formula ,in, Sending capacity for transporting passengers, The facility and equipment capacity of the i-th mode of transportation is used to calculate the overall comprehensive coordination index based on the matching degree of line evacuation capacity and the matching degree of hub equipment and facilities capacity. in accordance with Determine the matching relationship between the hub's arrival-departure passenger flow and vehicle flow.

4. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 3 is characterized in that: The motion matching optimization indicators include operation plans, scheduling characteristics, carrying capacity and timeliness impact, as well as travel OD, heterogeneity, migration efficiency and gradient characteristics. The calculation standard indicators include using the hierarchical analysis method to transform various attribute indicators into standard indicators that can be uniformly measured.

5. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 1 is characterized in that: The analyzing the asynchronous correlation characteristics of various indicators in the time series state includes: using a dynamic time bending algorithm and fluctuation weights to analyze the asynchronous correlation characteristics of various indicators in the time series state.

6. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 1 is characterized in that: The construction of the public transportation hub supply and demand matching optimization model includes: Constructing an objective function, wherein the objective function aims to optimize resource coordination matching and minimize operating costs; The objective function is calculated using the power coefficient method. , , , where R1 is the resource coordination matching degree and R2 is the operating cost; Conduct proximal analysis of supply and demand matching, use distributed edge computing methods to analyze and process real-time data, simultaneously conduct multi-modal traffic multi-level information fixed-point transmission and remote analysis, and use data link real-time interaction methods to optimize resource matching under the global state of the current public transportation hub.

7. The collaborative organization method for efficient collaborative allocation of public transportation hub resources according to claim 1 is characterized in that: Before establishing a data-driven transfer scheduling optimization model, it is necessary to verify the degree of correlation and connection between multimodal transportation operation plans in public transportation hubs through the time series event matching filtering method, and then dynamically analyze the multi-dimensional characteristics of the team margins, time thresholds, and cumulative load errors between each operation plan.

Images