Public transport scheduling method and system based on urban scene

Abstract

The application discloses a public traffic scheduling method and system based on a city scene, relates to the technical field of public traffic, and comprises the following steps: obtaining a historical public traffic operation data sequence of a target city, constructing a passenger flow prediction model, combining real-time traffic data to perform passenger flow prediction, and obtaining a passenger flow prediction result; obtaining road traffic information of the target city and constructing a road traffic network; collecting public traffic information and embedding the public traffic information in the road traffic network to obtain a twin public traffic network; performing traffic scheduling simulation and scheduling scheme optimization based on the twin public traffic network according to the passenger flow prediction result, and performing public traffic scheduling through an optimal traffic scheduling scheme. The application solves the technical problem that the traditional public traffic scheduling mode in the prior art has hysteresis and cannot effectively respond to traffic demand, and achieves the technical effects of realizing effective scheduling of public traffic through pre-positioned passenger flow prediction and improving traffic operation efficiency.

Description

TECHNICAL FIELD

[0001] The present application relates to the field of public transportation technology, in particular to a public transportation scheduling method and system based on urban scenarios. BACKGROUND

[0002] The scheduling system needs to collect and analyze traffic data in real time to accurately grasp the traffic situation and make timely scheduling decisions according to the actual situation to realize the rational allocation and efficient use of resources.

[0003] However, the traditional traffic scheduling method cannot effectively respond to traffic demand, causing energy waste and affecting traffic efficiency. SUMMARY

[0004] The present application provides a public transportation scheduling method and system based on urban scenarios to solve the technical problem that the traditional public transportation scheduling method in the prior art has a lag and cannot effectively respond to traffic demand.

[0005] In a first aspect, the present application provides a public transportation scheduling method based on urban scenarios, which comprises: obtaining a historical public transportation operation data sequence of a target city; constructing a passenger flow prediction model based on the historical public transportation operation data sequence; predicting passenger flow according to the passenger flow prediction model combined with real-time traffic data to obtain a passenger flow prediction result; obtaining road traffic information of the target city and constructing a road traffic network based on the road traffic information; collecting public transportation information of the target city and embedding it in the road traffic network to obtain a twin public transportation network; simulating traffic scheduling and optimizing scheduling schemes based on the twin public transportation network according to the passenger flow prediction result to obtain an optimal traffic scheduling scheme; and scheduling public transportation through the optimal traffic scheduling scheme.

[0006] In a second aspect of the present application, a public transportation scheduling system based on a city scene is provided, and the system comprises: a historical public transportation data acquisition module, configured to acquire a historical public transportation operation data sequence of a target city; a passenger flow prediction model construction module, configured to construct a passenger flow prediction model based on the historical public transportation operation data sequence; a passenger flow prediction module, configured to perform passenger flow prediction according to the passenger flow prediction model in combination with real-time traffic data, and obtain a passenger flow prediction result; a road traffic network construction module, configured to acquire road traffic information of the target city, and construct a road traffic network based on the road traffic information; a twin public transportation network construction module, configured to collect public transportation information of the target city, and embed the public transportation information in the road traffic network to obtain a twin public transportation network; a scheduling scheme optimization module, configured to perform traffic scheduling simulation and scheduling scheme optimization based on the twin public transportation network according to the passenger flow prediction result, and obtain an optimal traffic scheduling scheme; and a public transportation scheduling module, configured to perform public transportation scheduling through the optimal traffic scheduling scheme.

[0007] One or more technical solutions provided in the present application have at least the following technical effects or advantages:

[0008] The public transportation scheduling method based on a city scene provided in the present application relates to the technical field of public transportation, and solves the technical problem that the traditional public transportation scheduling manner in the prior art has hysteresis and cannot effectively respond to traffic demand by constructing a passenger flow prediction model, performing traffic flow prediction to obtain a passenger flow prediction result, acquiring road traffic information and public transportation information of a target city, constructing a twin public transportation network, performing traffic scheduling simulation and scheduling scheme optimization in combination with the passenger flow prediction result, and performing public transportation scheduling according to an optimal traffic scheduling scheme, thereby achieving the technical effect of effectively scheduling public transportation through front-end passenger flow prediction and improving traffic operation efficiency. BRIEF DESCRIPTION OF DRAWINGS

[0009] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed in the embodiment description will be briefly introduced. Obviously, the drawings in the following description are only some embodiments of the present application, and other drawings can be obtained by those skilled in the art without creative effort.

[0010] Figure 1 A public transportation scheduling method based on a city scene provided in the embodiments of the present application is shown in the flowchart.

[0011] Figure 2 A public transportation scheduling system structure based on a city scene is provided in the embodiments of the present application.

[0012] The reference signs are explained as follows: a historical public transportation data acquisition module 11, a passenger flow prediction model construction module 12, a passenger flow prediction module 13, a road traffic network construction module 14, a twin public transportation network construction module 15, a scheduling scheme optimization module 16, and a public transportation scheduling module 17. DETAILED DESCRIPTION

[0013] The present application provides a public transportation scheduling method based on a city scene, which is used to solve the technical problem that the conventional public transportation scheduling manner in the prior art has a lag and cannot effectively cope with traffic demand.

[0014] The technical solutions in the embodiments of the present application will be clearly and completely described in the embodiments of the present application in combination with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present application, rather than all the embodiments. Based on the embodiments in the present application, all other embodiments obtained by a person of ordinary skill in the art without creative work fall within the protection scope of the present application.

[0015] It should be noted that the terms “first”, “second”, and the like in the specification and the above drawings of the present application are used to distinguish similar objects, and do not necessarily indicate a specific order or a chronological sequence. It should be understood that the data thus used can be interchanged under appropriate circumstances, so that the embodiments of the present application described herein can be implemented in an order other than that illustrated or described herein. In addition, the terms “include” and “have” and any variations thereof are intended to cover non-exclusive inclusion, for example, a process, method, system, product, or server including a series of steps or units does not necessarily have to be limited to those steps or units clearly listed, but can include other steps or modules that are not clearly listed or inherent to the process, method, product, or device.

[0016] Embodiment One

[0017] As shown in the following Figure 1 The present application provides a public transportation scheduling method based on a city scene, which comprises the following steps:

[0018] P10: acquiring a historical public transportation operation data sequence of a target city;

[0019] P20: constructing a passenger flow prediction model based on the historical public transportation operation data sequence;

[0020] Further, the step P20 of the embodiments of the present application further comprises:

[0021] P21: the historical public transportation operation data sequence includes vehicle trips, passenger capacity, operation trajectory, and road traffic conditions in a preset period;

[0022] P22: the historical public transportation operation data sequence is preprocessed to obtain historical traffic data;

[0023] P23: based on the historical traffic data, passenger flow related features are extracted;

[0024] P24: according to the historical traffic data and the passenger flow related features, a machine learning is combined for training to obtain the passenger flow prediction model.

[0025] Optionally, based on a preset period, historical operation data of public transportation in a target city is collected as a historical public transportation operation data sequence, and the historical public transportation operation data sequence is used as training data to construct a passenger flow prediction model. Specifically, the historical public transportation operation data sequence includes vehicle trips, passenger capacity, operation trajectory, and road traffic conditions of each road section in the target city in a preset period. The historical public transportation operation data sequence is preprocessed, including data cleaning, data conversion, and standardization processing, to obtain historical traffic data.

[0026] Further, from the historical traffic data, passenger flow related features are extracted, including time features such as season, holiday, time of day, space features such as station location, line length, and other factors related to passenger flow changes. Then, a machine learning algorithm is used to train the extracted passenger flow related features and the historical traffic data, and the network parameters are continuously adjusted until the output data converges, to obtain the passenger flow prediction model. The passenger flow prediction model can be used for passenger flow prediction to achieve more effective traffic scheduling effect.

[0027] P30: according to the passenger flow prediction model, real-time traffic data is combined to predict passenger flow to obtain passenger flow prediction results;

[0028] Illustratively, through a data collection window, real-time traffic data is obtained, including real-time vehicle position, road congestion, weather conditions, special events, etc., and after preprocessing and feature extraction of the real-time traffic data, the real-time traffic data is input into the passenger flow prediction model. According to the prediction period, passenger flow prediction is performed to obtain passenger flow prediction results of the future prediction period, including passenger flow prediction data of each public transportation line in the future period.

[0029] P40: obtain road traffic information of a target city, and construct a road traffic network based on the road traffic information;

[0030] Further, the step P40 of the embodiments of the present application further comprises:

[0031] P41: Obtain road traffic information of a target city, the road traffic information comprising road network information and traffic facility information;

[0032] P42: Integrate the road network information and the traffic facility information to obtain an initial road traffic network;

[0033] P43: Perform topological analysis on the initial road traffic network, label key nodes and key road sections, and obtain the road traffic network.

[0034] It should be understood that the road traffic information of the target city is obtained, and a road traffic network of the target city is constructed, wherein the road traffic information comprises road network information and traffic facility information, the road network information comprises road name, road grade, road length, lane number, road direction, road intersection information, etc., and can reflect the basic attributes and topological structure of the road, and is a core element for constructing the road traffic network, and the traffic facility information comprises the position, function and operating state of traffic signal lights, traffic signs, traffic monitoring equipment, parking lots, bus stations and subway stations.

[0035] Further, the road network information and the traffic facility information are integrated and data-processed to obtain an initial road traffic network, and topological analysis is performed on the initial road traffic network to identify key nodes and key road sections in the network, wherein the key nodes and the key road sections refer to areas with large traffic flow and prone to congestion. Further, the importance level of the key nodes and the key road sections is set through node importance evaluation based on the complex network theory, and then the key nodes and the key road sections are labeled according to the importance level to obtain the road traffic network.

[0036] P50: Collect public transportation information of the target city, and embed the public transportation information in the road traffic network to obtain a twin public transportation network;

[0037] Further, the step P50 of the embodiment of the present application further comprises:

[0038] P51: Collect, through a data collection window, the public transportation information of the target city in real time, the public transportation information comprising public transportation type, vehicle quantity information and schedule arrangement information;

[0039] P52: Embed the public transportation information in the road traffic network to obtain a twin public transportation network.

[0040] Optionally, a more comprehensive and accurate twin public transportation network is obtained by collecting public transportation information of the target city and embedding it in the road traffic network. Specifically, the public transportation information of the target city is collected in real time through a data collection window, including collecting public transportation types, vehicle quantity information, and schedule arrangement information. Further, by fusing and matching the public transportation information with the road network information and the traffic facility information, the public transportation information is embedded in the road traffic network to obtain the twin public transportation network, which can better simulate and reflect the operating conditions of the actual public transportation system.

[0041] P60: based on the traffic flow prediction result, traffic scheduling simulation and scheduling scheme optimization are performed based on the twin public transportation network to obtain an optimal traffic scheduling scheme.

[0042] Further, the step P60 of the embodiment of the present application further includes:

[0043] P61: based on the traffic flow prediction result, traffic scheduling simulation is performed in combination with the road traffic information and the public transportation information to obtain multiple traffic scheduling candidate schemes.

[0044] P62: the optimal traffic scheduling scheme is obtained by performing scheduling scheme optimization in combination with the multiple traffic scheduling candidate schemes based on the twin public transportation network.

[0045] Specifically, based on the traffic flow prediction result, traffic scheduling simulation is performed in combination with the twin public transportation network, and optimization is performed from the simulated scheduling schemes to obtain an optimal traffic scheduling scheme. First, based on the traffic flow prediction result, traffic scheduling simulation is performed with the road traffic information and the public transportation information as constraints. The simulation process needs to fully consider the topological structure of the road network, the configuration of the traffic facilities, the operating conditions of the public transportation, and the distribution characteristics of the predicted traffic flow, etc. By simulating the traffic operating conditions under different scheduling strategies, multiple traffic scheduling candidate schemes are preliminarily obtained.

[0046] Further, the scheme optimization is performed using the twin public transportation network. By simulating the effects of different scheduling schemes in the twin public transportation network, the key indicators such as the degree of congestion relief, the influence on passenger travel time, and the changes in operating cost of each scheme are evaluated, and then based on the key indicators, an optimization algorithm is used to perform scheme optimization to find an optimal traffic scheduling scheme that meets the constraints of operating cost, service quality, etc.

[0047] Further, the step P62 of the embodiment of the present application further includes:

[0048] P62-1: Obtain scheduling optimization parameters based on the twin public transport network, including traffic flow limits of each road segment, public transport types, vehicle quantity information, and schedule arrangement information;

[0049] P62-2: Construct a fitness function according to a mapping relationship between the traffic flow limits, the public transport types, the vehicle quantity information, the schedule arrangement information, and passenger flow information.

[0050] P62-3: Embed the fitness function in the twin public transport network, and perform scheduling scheme optimization according to the fitness function to obtain an optimal traffic scheduling scheme.

[0051] Optionally, scheduling optimization parameters are obtained through the twin public transport network, including traffic flow limits of each road segment, public transport types, vehicle quantity information, and schedule arrangement information, which can be used as key variables for traffic scheduling. Further, a fitness function is constructed according to a mapping relationship between the traffic flow limits, the public transport types, the vehicle quantity information, the schedule arrangement information, and passenger flow information. The fitness function is a key indicator for evaluating the pros and cons of a scheduling scheme, and its optimization objectives can be traffic congestion degree, passenger travel efficiency, operating cost, passenger satisfaction, etc.

[0052] Further, the fitness function is embedded in the twin public transport network, and the effects of different traffic scheduling candidate schemes are simulated through the twin public transport network. The fitness values of each traffic scheduling candidate scheme are calculated in real time, and the optimal traffic scheduling scheme is obtained by using an optimization algorithm to perform scheme optimization with reference to the fitness values.

[0053] Further, the step P62-3 of the embodiment of the application further includes:

[0054] P62-31: Randomly generate a first intelligent scheduling scheme based on the plurality of traffic scheduling candidate schemes, and calculate a first fitness value in combination with the fitness function.

[0055] P62-32: Randomly generate a second intelligent scheduling scheme based on the plurality of traffic scheduling candidate schemes, and calculate a second fitness value.

[0056] P62-33: Determine whether the second fitness value is greater than the first fitness value. If yes, the second intelligent scheduling scheme is used as a temporary optimal solution. If no, the second intelligent scheduling scheme is used as a temporary optimal solution according to optimization constraints.

[0057] P62-34: Continuously iterate and optimize until a preset iteration number is reached, and output an optimal traffic scheduling scheme.

[0058] In a possible embodiment of the present application, from the plurality of traffic scheduling alternatives, an arbitrary scheduling scheme is randomly selected as a first intelligent scheduling scheme, input into the twin public transport network for simulation operation, and the fitness function is used to calculate the fitness value of the scheme to obtain a first fitness. Similarly, based on the plurality of traffic scheduling alternatives, a second intelligent scheduling scheme is randomly obtained, and the fitness function is used to calculate a second fitness.

[0059] Further, it is judged whether the second fitness is greater than the first fitness. If it is greater, the second intelligent scheduling scheme is taken as a temporary optimal solution. If it is not greater, but the gap between the two is less than a preset optimization constraint, the second intelligent scheduling scheme is still taken as a temporary optimal solution to avoid falling into a local optimum too early, wherein the optimization constraint is used to control the search step size of the algorithm near the local optimal solution. Iterative optimization is continuously performed in this way until a preset iteration number is reached, and the last obtained temporary optimal solution is taken as an optimal traffic scheduling scheme.

[0060] P70: scheduling public transport through the optimal traffic scheduling scheme.

[0061] Specifically, scheduling public transport through the optimal traffic scheduling scheme can maximize the operating efficiency of the public transport system, reduce traffic congestion, and improve passenger satisfaction.

[0062] In summary, the embodiments of the present application have at least the following technical effects:

[0063] The present application constructs a passenger flow prediction model, predicts traffic flow, obtains a passenger flow prediction result, acquires road traffic information and public transport information of a target city, constructs a twin public transport network, combines the passenger flow prediction result, performs traffic scheduling simulation and scheduling scheme optimization, and schedules public transport according to the optimal traffic scheduling scheme.

[0064] The technical effect of realizing effective scheduling of public transport and improving traffic operation efficiency through pre-traffic flow prediction is achieved.

[0065] Embodiment Two

[0066] Based on the same inventive concept as the public transport scheduling method based on a city scene in the foregoing embodiments, as shown in Figure 2 The present application provides a public transport scheduling system based on a city scene, and the system and method embodiments in the present application are based on the same inventive concept. The system includes:

[0067] A historical public transport data acquisition module 11 is configured to acquire a historical public transport operation data sequence of a target city.

[0068] A passenger flow prediction model construction module 12 is configured to construct a passenger flow prediction model based on the historical public transportation operation data sequence;

[0069] A passenger flow prediction module 13 is configured to perform passenger flow prediction according to the passenger flow prediction model in combination with real-time traffic data to obtain a passenger flow prediction result;

[0070] A road traffic network construction module 14 is configured to obtain road traffic information of a target city and construct a road traffic network based on the road traffic information;

[0071] A twin public transportation network construction module 15 is configured to collect public transportation information of the target city and embed the public transportation information in the road traffic network to obtain a twin public transportation network;

[0072] A scheduling scheme optimization module 16 is configured to perform traffic scheduling simulation and scheduling scheme optimization based on the twin public transportation network according to the passenger flow prediction result to obtain an optimal traffic scheduling scheme;

[0073] A public transportation scheduling module 17 is configured to perform public transportation scheduling through the optimal traffic scheduling scheme.

[0074] Further, the passenger flow prediction model construction module 12 is further configured to perform the following steps:

[0075] The historical public transportation operation data sequence includes vehicle trips, passenger capacity, operation trajectories, and road traffic conditions in a preset period;

[0076] The historical public transportation operation data sequence is preprocessed to obtain historical traffic data;

[0077] Passenger flow-related features are extracted based on the historical traffic data;

[0078] The passenger flow prediction model is obtained by training in combination with machine learning according to the historical traffic data and the passenger flow-related features.

[0079] Further, the road traffic network construction module 14 is further configured to perform the following steps:

[0080] The road traffic information of the target city is obtained, and the road traffic information includes road network information and traffic facility information;

[0081] Integrate the road network information and the traffic facility information to obtain an initial road traffic network;

[0082] Perform topological analysis on the initial road traffic network, label key nodes and key road segments, and obtain the road traffic network.

[0083] Further, the twin public transport network construction module 15 is further configured to perform the following steps:

[0084] Collect public transport information of a target city in real time through a data collection window, wherein the public transport information includes public transport types, vehicle quantity information, and schedule arrangement information;

[0085] Embed the public transport information in the road traffic network to obtain a twin public transport network.

[0086] Further, the scheduling scheme optimization module 16 is further configured to perform the following steps:

[0087] Based on the passenger flow prediction result, combine the road traffic information and the public transport information to perform traffic scheduling simulation, and obtain a plurality of traffic scheduling candidate schemes;

[0088] Optimize the scheduling scheme based on the plurality of traffic scheduling candidate schemes and the twin public transport network to obtain an optimal traffic scheduling scheme.

[0089] Further, the scheduling scheme optimization module 16 is further configured to perform the following steps:

[0090] Based on the twin public transport network, obtain scheduling optimization parameters, including traffic flow limits of each road segment, public transport types, vehicle quantity information, and schedule arrangement information;

[0091] Construct a fitness function according to a mapping relationship between the traffic flow limits, the public transport types, the vehicle quantity information, the schedule arrangement information, and the passenger flow information;

[0092] Embed the fitness function in the twin public transport network, and optimize the scheduling scheme based on the fitness function to obtain an optimal traffic scheduling scheme.

[0093] Further, the scheduling scheme optimization module 16 is further configured to perform the following steps:

[0094] Based on the plurality of traffic scheduling candidate schemes, randomly generate a first intelligent scheduling scheme, and calculate a first fitness value based on the fitness function;

[0095] Based on the plurality of traffic scheduling candidate schemes, randomly generate a second intelligent scheduling scheme, and calculate a second fitness value;

[0096] determining whether the second fitness is greater than the first fitness, if yes, taking the second intelligent scheduling scheme as a temporary optimal solution, and if no, taking the second intelligent scheduling scheme as the temporary optimal solution according to the optimization constraint;

[0097] continuously iterating optimization until a preset iteration number is reached, and outputting an optimal traffic scheduling scheme.

[0098] It should be noted that the above sequence of the embodiments of the present application is only for description, and does not represent the advantages and disadvantages of the embodiments. Moreover, the above describes specific embodiments of the present specification. In addition, the processes depicted in the drawings do not necessarily require the specific order or continuous order shown to achieve the desired results. In some embodiments, multi-task processing and parallel processing are also possible or can be advantageous.

[0099] The above only describes the preferred embodiments of the present application, and does not limit the present application. 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.

[0100] The specification and drawings are merely exemplary of the present application, and any and all modifications, variations, combinations or equivalents that fall within the scope of the present application are considered to be covered by the present application. Obviously, those skilled in the art can make various modifications and variations to the present application without departing from the scope of the present application. Thus, if these modifications and variations of the present application belong to the scope of the present application and its equivalents, the present application is intended to include these modifications and variations.

Claims

1. A public transportation scheduling method based on a city scene, characterized by, The method comprises: obtaining a historical public transportation operation data sequence of a target city; based on the historical public transportation operation data sequence, a passenger flow prediction model is constructed; according to the passenger flow prediction model, combined with real-time traffic data, passenger flow prediction is carried out to obtain a passenger flow prediction result; obtaining road traffic information of the target city, and constructing a road traffic network based on the road traffic information; collecting public transportation information of the target city, and embedding the public transportation information in the road traffic network to obtain a twin public transportation network; based on the passenger flow prediction result, traffic scheduling simulation and scheduling scheme optimization are carried out based on the twin public transportation network to obtain an optimal traffic scheduling scheme; carrying out public transportation scheduling through the optimal traffic scheduling scheme; based on the passenger flow prediction result, traffic scheduling simulation and scheduling scheme optimization are carried out based on the twin public transportation network, comprising: based on the passenger flow prediction result, combined with the road traffic information and public transportation information, traffic scheduling simulation is carried out to obtain a plurality of traffic scheduling candidate schemes; through the twin public transportation network, combined with the plurality of traffic scheduling candidate schemes, scheduling scheme optimization is carried out to obtain an optimal traffic scheduling scheme; through the twin public transportation network, combined with the plurality of traffic scheduling candidate schemes, scheduling scheme optimization is carried out to obtain an optimal traffic scheduling scheme, comprising: based on the twin public transportation network, scheduling optimization parameters are obtained, including traffic flow limits of each road section, public transportation types, vehicle quantity information and schedule arrangement information; and according to the mapping relationship between the traffic flow limits, public transportation types, vehicle quantity information and schedule arrangement information and passenger flow information, an fitness function is constructed; the fitness function is embedded in the twin public transportation network, and scheduling scheme optimization is carried out according to the fitness function to obtain an optimal traffic scheduling scheme.

2. The method of claim 1, wherein, Based on the historical public transportation operation data sequence, a passenger flow prediction model is constructed, comprising: the historical public transportation operation data sequence includes vehicle schedule, passenger capacity, running track and road traffic condition in a preset period; the historical public transportation operation data sequence is preprocessed to obtain historical traffic data; based on the historical traffic data, passenger flow related features are extracted; according to the historical traffic data and the passenger flow related features, combined with machine learning, the passenger flow prediction model is obtained by training.

3. The method of claim 1, wherein, Obtaining road traffic information of the target city, and constructing a road traffic network based on the road traffic information, comprising: obtaining road traffic information of the target city, the road traffic information comprising road network information and traffic facility information; the road network information and traffic facility information are integrated to obtain an initial road traffic network; topological analysis is carried out on the initial road traffic network to label key nodes and key road sections to obtain the road traffic network.

4. The method of claim 3, wherein, Collecting public transportation information of the target city, and embedding the public transportation information in the road traffic network to obtain a twin public transportation network, comprising: The public transport information of the target city is collected in real time through a data collection window, and the public transport information includes public transport type, vehicle quantity information and schedule information; The public transport information is embedded in the road traffic network to obtain a twin public transport network.

5. The method of claim 1, wherein, The optimal traffic scheduling scheme is obtained by scheduling scheme optimization according to the fitness function, including: A first intelligent scheduling scheme is randomly generated based on the multiple traffic scheduling candidate schemes, and a first fitness is calculated according to the fitness function; A second intelligent scheduling scheme is randomly generated based on the multiple traffic scheduling candidate schemes, and a second fitness is calculated; If the second fitness is greater than the first fitness, the second intelligent scheduling scheme is taken as a temporary optimal solution, otherwise, the second intelligent scheduling scheme is taken as a temporary optimal solution according to optimization constraints; The optimization is iterated until a preset iteration number is reached, and the optimal traffic scheduling scheme is output.

6. A public transportation dispatching system based on urban market scenarios, characterized in that, The system includes: A historical public transport data acquisition module is configured to acquire a historical public transport operation data sequence of a target city; A passenger flow prediction model construction module is configured to construct a passenger flow prediction model based on the historical public transport operation data sequence; A passenger flow prediction module is configured to predict passenger flow according to the passenger flow prediction model and real-time traffic data to obtain a passenger flow prediction result; A road traffic network construction module is configured to acquire road traffic information of the target city, and construct a road traffic network based on the road traffic information; A twin public transport network construction module is configured to collect public transport information of the target city, and embed the public transport information in the road traffic network to obtain a twin public transport network; A scheduling scheme optimization module is configured to simulate traffic scheduling and optimize scheduling schemes based on the twin public transport network according to the passenger flow prediction result to obtain an optimal traffic scheduling scheme, and is further configured to simulate traffic scheduling and optimize scheduling schemes based on the twin public transport network according to the passenger flow prediction result, including: Traffic scheduling simulation is performed based on the passenger flow prediction result, the road traffic information and the public transport information to obtain multiple traffic scheduling candidate schemes; Optimization of scheduling schemes is performed through the twin public transport network and in combination with the multiple traffic scheduling candidate schemes to obtain an optimal traffic scheduling scheme, including: Optimization parameters are acquired based on the twin public transport network, including traffic flow limits of each road segment, public transport type, vehicle quantity information and schedule information; A fitness function is constructed according to a mapping relationship between the traffic flow limits, the public transport type, the vehicle quantity information, the schedule information and passenger flow information. The fitness function is embedded in the twin public transport network, and the optimal traffic scheduling scheme is obtained by scheduling scheme optimization according to the fitness function; The public transport scheduling module is configured to perform public transport scheduling by using the optimal traffic scheduling scheme.

Images