Inter-city high-speed railway transfer travel demand estimation method and system based on spatial correlation

Abstract

The invention provides an inter-city high-speed railway transfer travel demand estimation method based on spatial correlation, and the method comprises the steps: determining the membership between high-speed railway stations and cities, and dividing a city pair covered by a high-speed railway network into a direct city pair and a transfer city pair in combination with high-speed railway operation data; counting the direct passenger flow between every two stations in the high-speed railway network, and counting the classification set as the direct passenger flow between the corresponding direct city pairs according to the membership between the stations and the cities; calculating the earth spherical distance between the cities, and constructing a spatial weight matrix between the cities; constructing a spatial gravity model for representing a mapping relationship between the high-speed rail travel demand vectors among the cities and the spatial weight moments among the cities; and carrying out undetermined parameter calibration on the space gravity model to obtain an estimated value of a high-speed rail travel demand vector between the transfer city pairs. According to the invention, high-speed railway transfer travel demand estimation can be realized.

Description

TECHNICAL FIELD

[0001] The application belongs to the technical field of railway passenger transport, and particularly relates to a method and system for estimating inter-city high-speed railway transfer travel demand based on spatial correlation. BACKGROUND

[0002] China has a super-large high-speed railway network, and train network operation has shortened the time-space distance and promoted the development of regional social economy. However, the areas that cannot be directly reached by high-speed rail or the direct train tickets are sold out, and the time arrangement of direct high-speed rail is not suitable for travel plans, so more and more passengers choose to travel by connecting transfer. This not only affects the travel efficiency of passengers, but also brings challenges to the operation and management of high-speed rail. How to combine the actual operation of high-speed rail and propose an accurate method for estimating high-speed railway transfer travel demand so as to realize scientific, refined and efficient train operation organization and ensure smooth travel of passengers has become a problem to be solved in the current technical field of railway passenger transport.

[0003] At present, there are few existing methods for estimating high-speed railway transfer travel demand, and most of them focus on the transfer travel demand between high-speed rail and other public transportation (such as subway, bus, taxi, etc.). Limited by ticket privacy protection requirements and data retrieval difficulties, there is almost no research method for identifying and estimating the transfer travel demand between different trains in high-speed rail stations.

[0004] Therefore, it is necessary to study a method and system for estimating inter-city high-speed railway transfer travel demand. SUMMARY

[0005] The purpose of the present application is to provide a method and system for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, which can effectively estimate the inter-city high-speed railway transfer travel demand.

[0006] The technical scheme provided by the present application is as follows: In a first aspect, the present application provides a method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, characterized in that it comprises: Step S1: collecting high-speed railway network related data, determining the membership relationship between high-speed railway stations and cities according to the collected data, dividing the city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs, and counting the direct passenger flow between all stations in the high-speed railway network; Step S2: classifying and aggregating the direct passenger flow between all stations in the high-speed railway network into the direct passenger flow between the corresponding direct city pairs according to the membership relationship between the stations and the cities; Step S3: calculating the spherical distance between cities, and constructing a spatial weight matrix between cities; Step S4: constructing a spatial gravity model for representing a mapping relationship between a high-speed rail travel demand vector between cities and a spatial weight matrix between cities; wherein the high-speed rail travel demand vector between cities is composed of a high-speed rail travel demand vector between direct city pairs and a high-speed rail travel demand vector between transfer city pairs; Step S5: calibrating undetermined parameters of the spatial gravity model to obtain an estimated value of the high-speed rail travel demand vector between transfer city pairs; wherein calibrating undetermined parameters of the spatial gravity model comprises: counting direct passenger flow between direct city pairs to form the high-speed rail travel demand vector between direct city pairs, initializing the high-speed rail travel demand vector between transfer city pairs to obtain an initial high-speed rail travel demand vector.

[0007] In a possible implementation manner, the step S1 comprises: Step S1.1: collecting high-speed railway network related data, including geographical information data of stations in the high-speed railway network, city administrative division, and high-speed railway operation data; Step S1.2: determining a membership relationship between high-speed railway stations and cities according to the geographical information data of stations and the city administrative division; Step S1.3: dividing city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs according to the high-speed railway operation data and the membership relationship between stations and cities; Step S1.4: counting direct passenger flow between all stations in the high-speed railway network through the high-speed railway operation data.

[0008] In a possible implementation manner, the step S1 of dividing city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs comprises: dividing city pairs between which direct high-speed rail trains are opened into direct city pairs; and dividing city pairs between which direct high-speed rail trains are not opened and travel needs to be made through transfer into transfer city pairs.

[0009] In a possible implementation manner, the step S1 of counting direct passenger flow between any two stations in the high-speed railway network comprises: for high-speed rail network dynamic expansion characteristics, counting average daily direct passenger flow of existing lines for 365 days in a year, and counting average daily direct passenger flow of newly added lines in a statistical period according to actual operation days.

[0010] In a possible implementation manner, in the step S1.1, the collected high-speed railway network related data further comprises geographical information data of city centers (longitude and latitude coordinates of city centers).

[0011] In a possible implementation, in the step S3, the inter-city spherical distance is calculated by using the Haversine formula according to the longitude and latitude coordinates of the city centers to calculate the spherical distance between the city centers as the inter-city spherical distance.

[0012] In a possible implementation, in the step S3, the inter-city spatial weight matrix is constructed by constructing three spatial weight matrices respectively for capturing the spatial correlation based on the destination city, the spatial correlation based on the origin city and the spatial correlation between the origin-destination cities, and the calculation formula is as follows: 、 and , , wherein, is a unit matrix; the weight matrix is a row-standardized matrix, and the elements in the matrix are the inverses of the spherical distances between the city and centers, the main diagonal of the matrix is 0; represents the matrix Kronecker product.

[0013] In a possible implementation, in the step S4, the spatial gravity model includes: ; wherein, the dependent variable represents the high-speed rail travel demand vector between cities, and the vector , , is the number of cities where high-speed rail has been opened; and are the origin-end spatial correlation coefficient, the destination-end spatial correlation coefficient and the origin-destination-end spatial correlation coefficient respectively, and all are undetermined parameters; is the vector whose elements are all 1; is the coefficient of , which is an undetermined parameter; and are the matrices of , representing the city gravity characteristics of the origin and destination cities, representing the dimension of the city gravity characteristics; and are the origin city gravity characteristic coefficient and the destination city gravity characteristic coefficient respectively, and both are undetermined parameters; is the vector representing the average travel time of the high-speed rail trains between cities.​ is the average travel time coefficient, which is a parameter to be determined; is an interference term and satisfies the normal distribution.

[0014] The space gravity model, through 、 as well as It describes the spatial correlation between the starting city, the ending city, and the starting and ending cities, taking into account the spatial correlation between the starting and ending cities. It can reflect the spatial correlation of high-speed rail travel demand between cities and is used to estimate high-speed rail travel demand.

[0015] In a possible implementation, the step S5 calibrates the undetermined parameters of the space gravity model, including calibrating the undetermined parameters of the space gravity model using the maximum expectation algorithm (EM algorithm) and maximum likelihood estimation. The step S5 specifically includes: Step 1: Initialize the high-speed rail travel demand between transfer city pairs to zero, and combine it with the statistically obtained high-speed rail direct passenger flow between direct city pairs to form the initial high-speed rail travel demand vector ; Step 2: Perform iterative calculations according to the following steps until convergence; ①Calculate the Model parameters for the next iteration: Based on the current inter-city high-speed rail travel demand vector , the maximum likelihood method is used to estimate the unknown parameters of the space gravity model and obtain the model parameters 、 、 、 、 、 and Respectively represent The iterative 、 、 、 、 、 and value; ② Update the high-speed rail travel demand vector: ;in, Indicates the The high-speed rail travel demand vector of the second iteration; ③ Determine whether the algorithm converges: When the estimated value of the high-speed rail travel demand vector converges in two consecutive iterations, that is, , then stop the iteration, vector The value of the corresponding transfer city pair is the estimated inter-city high-speed rail transfer travel demand; otherwise, return to ②.

[0016] The first and second steps are a process of solving by using the maximum expectation algorithm, in which the maximum likelihood method is combined.

[0017] In a second aspect, the present application provides an inter-city high-speed railway transfer travel demand estimation system based on spatial correlation, comprising a memory and a processor. The memory is configured to store a computer program. The processor is configured to invoke the computer program to perform the method described above.

[0018] In a third aspect, the present application provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program, when running on an electronic device, causes the electronic device to implement the method described above.

[0019] In a fourth aspect, the present application provides a computer program product comprising a computer program, wherein the computer program, when running on an electronic device, causes the electronic device to implement the method described above.

[0020] The specific implementation of the second to fourth aspects of the present application can refer to the implementation of the first aspect described above, and will not be repeated here.

[0021] The present application has the following advantages: (1) The method disclosed by the present application fully excavates high-speed railway train ticket reservation data, estimates transfer travel demand through direct passenger flow, and fills the gap in high-speed railway transfer travel demand identification and estimation methods. (2) The method disclosed by the present application is based on a spatial gravity model, considers the influence of city attraction and spatial correlation on high-speed passenger travel demand, can more truly reflect the spatial flow characteristics of high-speed passenger, and uses EM algorithm for model estimation, thereby improving the estimation accuracy. (3) The method disclosed by the present application is suitable for high-speed railway networks of different scales at home and abroad, has strong universality, and the estimated value of inter-city high-speed railway transfer travel demand obtained can provide scientific decision support for the railway passenger transport industry, and helps to better meet the high-speed passenger travel demand. BRIEF DESCRIPTION OF DRAWINGS

[0022] Figure 1 The flow chart of the inter-city high-speed railway transfer travel demand estimation method based on spatial correlation in an embodiment of the present application; Figure 2 The principle block diagram of the first stage, data acquisition stage, in an embodiment of the present application; Figure 3 The principle block diagram of the second stage, model construction stage, in an embodiment of the present application; Figure 4A third stage, a model solving stage, in one embodiment of the present application. DETAILED DESCRIPTION

[0023] In order to make the person skilled in the art better understand the scheme of the present application, the technical scheme of the present application will be further described in detail below in combination with the embodiments of the present application and the drawings.

[0024] With the wide application of the spatial gravity model in the analysis of the determinants and the estimation of the flow in the population migration, the urban and inter-city traffic, the freight and the inter-regional trade, it provides a new idea for inferring the inter-city travel demand based on high-speed rail.

[0025] The present application provides an inter-city high-speed rail transfer travel demand estimation method based on spatial correlation, comprising: determining the affiliation relationship between the high-speed rail station and the city according to the geographic information data of the station and the urban administrative division; dividing the city pairs covered by the high-speed rail network into direct city pairs and transfer city pairs according to the high-speed rail operation data and the affiliation relationship between the station and the city; through the high-speed rail operation data, the direct passenger flow between all stations in the high-speed rail network is counted; the direct passenger flow between all stations in the high-speed rail network is classified and aggregated into the direct passenger flow between the corresponding direct city pairs according to the affiliation relationship between the station and the city; according to the geographic information data of the city center, the inter-city spherical distance is calculated, and the spatial weight matrix between cities is constructed; a spatial gravity model is constructed to represent the mapping relationship between the high-speed rail travel demand vector and the spatial weight matrix between cities; the high-speed rail travel demand vector is composed of the high-speed rail travel demand vector between the direct city pairs and the high-speed rail travel demand vector between the transfer city pairs; the direct passenger flow between the direct city pairs is counted to form the high-speed rail travel demand vector between the direct city pairs, and the high-speed rail travel demand vector between the transfer city pairs is initialized; the spatial gravity model is calibrated for the undetermined parameters to obtain the estimated value of the high-speed rail travel demand vector between the transfer city pairs. The present application solves the problem that the specific travel path of passengers cannot be directly obtained in the high-speed rail system, and thus the high-speed rail transfer travel demand cannot be accurately estimated.

[0026] This application is based on a spatial gravity model that can effectively capture the inherent geographical correlation of intercity travel modes. By introducing a spatial weight matrix to quantify spatial correlation and using direct passenger flow to estimate transfer travel demand, it can significantly improve the accuracy and robustness of demand estimation, and can more realistically reflect the complex network characteristics and dynamic evolution of intercity passenger flow. The estimated value of the transfer travel demand of inter-city high-speed railways can lay the foundation for the subsequent optimization of high-speed railway train schedules considering subsequent transfers, the preparation of train operation plans under network conditions, and the planning and construction of high-speed railway networks, and has strong practicality. It provides a scientific basis for improving the current situation of intercity travel, optimizing related railway capacity scheduling, etc., thereby supporting more efficient and reliable intercity transportation planning and operation decisions.

[0027] The technical solution of this application is further described in detail below with reference to the accompanying drawings.

[0028] Example 1: like Figure 1 As shown, an embodiment of the present invention provides a method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, which specifically includes the following steps: This application provides a method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, including: Step S1: Collecting data related to the high-speed railway network, determining the affiliation between high-speed railway stations and cities based on the collected data, and dividing the city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs, and calculating the direct passenger flow between all stations in the high-speed railway network; In some embodiments, step S1 includes: Step S1.1: Collect data related to the high-speed railway network, including geographic information data of stations in the high-speed railway network, urban administrative divisions, and high-speed railway operation data; For example, taking the Central Plains Urban Agglomeration as an example, the digital map platform is used to collect geographic information data of stations, lines and city centers in the actual high-speed railway network of the Central Plains Urban Agglomeration in 2015.

[0029] The geographic information data of stations and lines in the high-speed railway network are derived from cities in the Central Plains urban agglomeration that opened high-speed railways in 2015.

[0030] Step S1.2: Determine the affiliation between the high-speed railway station and the city based on the station's geographic information data and the city's administrative divisions; Step S1.3: Based on the high-speed rail operation data and the relationship between stations and cities, divide the city pairs covered by the high-speed rail network into direct city pairs and transfer city pairs; In some embodiments, the high-speed railway operation data in step S1.3 may be high-speed railway train schedule data.

[0031] In some embodiments, the step S1.3 of dividing the city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs comprises: dividing the city pairs between which direct high-speed trains are opened into direct city pairs; and dividing the city pairs between which direct high-speed trains are not opened and travel needs to be made by transfer into transfer city pairs. That is, the city pairs covered by the high-speed railway network are divided into direct city pairs and transfer city pairs according to whether direct high-speed trains are opened.

[0032] Exemplarily, the city pairs in the Central Plains Urban Agglomeration between which direct high-speed trains are not opened and travel needs to be made by transfer are transfer city pairs, as shown in Table 1: ; Step S1.4: counting the direct passenger flow between all pairs of stations in the high-speed railway network through high-speed railway operation data; In some embodiments, the high-speed railway operation data in step S1.4 can be high-speed train passenger ticket booking data.

[0033] The passenger flow can be the annual average daily passenger flow.

[0034] The high-speed train passenger ticket booking data contains the departure city, destination city, travel date, train number and travel time of each passenger, from which the annual average daily passenger flow between each pair of stations can be counted as the direct passenger flow between any two stations in the high-speed railway network.

[0035] In some embodiments, the step S1 of counting the direct passenger flow between any two stations in the high-speed railway network comprises: for the dynamic expansion characteristics of the high-speed railway network, calculating the average daily direct passenger flow of the existing lines for the whole year 365 days, and converting the average daily direct passenger flow of the newly added lines in the statistical period according to the actual operation days.

[0036] Exemplarily, for the high-speed train data in 2015, when counting the annual average daily passenger flow between each pair of stations, for the dynamic expansion characteristics of the high-speed railway network in China, the average daily passenger flow of the existing lines is calculated for the whole year 365 days, and the passenger flow of the newly added lines in 2015 is converted according to the actual operation days.

[0037] Step S2: classifying and counting the direct passenger flow between all pairs of stations in the high-speed railway network into the direct passenger flow between corresponding direct city pairs according to the affiliation of the stations and cities; Step S3: calculating the earth spherical distance between cities to construct a spatial weight matrix between cities; In some embodiments, the high-speed railway network related data collected in step S1.1 further includes geographical information data (latitude and longitude coordinates) of city centers.

[0038] In some embodiments, the Haversine formula can be used to calculate the spherical distance between city centers according to the latitude and longitude coordinates of the city centers. ; wherein, is the spherical distance between the centers of the cities and . is the radius of the earth (6378.137 kilometers); and are the latitudes of the centers of the cities and , respectively. and are the longitudes of the centers of the cities and , respectively.

[0039] The calculated spherical distance between the city centers can be taken as the spherical distance between the cities.

[0040] In some embodiments, constructing the spatial weight matrix between the cities in step S3 includes constructing three spatial weight matrices respectively for capturing the spatial correlation based on the destination city, the spatial correlation based on the origin city, and the spatial correlation between the origin-destination cities, and the calculation formula is: , and . , , wherein, is an identity matrix of ; the weight matrix is a row-normalized matrix, and the elements in the matrix are the inverses of the spherical distances between the centers of the cities and , and the main diagonal of the matrix is 0. represents the matrix Kronecker product.

[0041] Step S4: constructing a spatial gravity model for representing the mapping relationship between the high-speed rail travel demand vector between the cities and the spatial weight matrix between the cities; wherein the high-speed rail travel demand vector between the cities is composed of the high-speed rail travel demand vector between direct city pairs and the high-speed rail travel demand vector between transfer city pairs. In some embodiments, the spatial gravity model in step S4 comprises: ; wherein the dependent variable represents the high-speed rail travel demand vector between cities, is a vector, , is the number of cities with open high-speed rail; and are the spatial correlation coefficients of the origin end, the destination end and the origin-destination end, respectively, and are all undetermined parameters; is a vector with all elements being 1; is the coefficient of , which is an undetermined parameter; and are matrices of , representing the city gravity characteristics of the origin city and the destination city, representing the dimension of the city gravity characteristics; and are the origin city gravity characteristic coefficient and the destination city gravity characteristic coefficient, respectively, and are both undetermined parameters; is a vector representing the average travel time of high-speed rail trains between cities; is the average travel time coefficient, which is an undetermined parameter; is an interference term, which satisfies a normal distribution.

[0042] The spatial gravity model describes the spatial correlation based on the origin city, the destination city and the origin-destination city through , and , considers the spatial correlation of the origin city and the destination city, can reflect the spatial correlation of high-speed rail travel demand between cities, and is used for estimating high-speed rail travel demand.

[0043] Step S5: The undetermined parameters of the spatial gravity model are calibrated to obtain the estimated value of the high-speed rail travel demand vector between the transfer city pairs; wherein the calibration of the undetermined parameters of the spatial gravity model comprises: counting the direct passenger flow between the direct city pairs to form the high-speed rail travel demand vector between the direct city pairs, initializing the high-speed rail travel demand vector between the transfer city pairs to obtain an initial high-speed rail travel demand vector.

[0044] In some embodiments, the calibration of the undetermined parameters of the spatial gravity model in step S5 comprises calibrating the undetermined parameters of the spatial gravity model by using the expectation maximization (EM) algorithm and the maximum likelihood estimation; and step S5 specifically comprises: Step 1: initialize the high-speed rail transfer demand between transfer city pairs to zero, and form an initial high-speed rail transfer demand vector with the obtained high-speed rail direct passenger flow between direct city pairs ; Step 2: iteratively calculate until convergence according to the following steps: ①Calculate the model parameters of the n-th iteration: according to the current inter-city high-speed rail transfer demand vector , the undetermined parameters of the spatial gravity model are estimated by the maximum likelihood method, and the model parameters 、 、 、 and are obtained 、 、 、 and respectively represent the values of 、 、 、

[0045] 、 、 and obtained in the n-th iteration; ②Update the high-speed rail transfer demand vector: ; wherein represents the high-speed rail transfer demand vector of the n-th iteration; ③Judge whether the algorithm converges: when the estimated values of the high-speed rail transfer demand vector in the two consecutive iterations converge, i.e. , stop iteration, and the value corresponding to the vector of the transfer city pair is the estimated inter-city high-speed rail transfer demand; otherwise, return to ②.

[0047] Exemplarily, the final parameter calculation results of the Central Plains Urban Agglomeration are shown in Table 2: ; According to the model, the high-speed rail transfer demand between the cities in the Central Plains Urban Agglomeration can be finally obtained, and the values corresponding to the transfer city pairs can be extracted to obtain the inter-city high-speed rail transfer demand. Exemplarily, the average daily transfer demand between transfer city pairs in the Central Plains Urban Agglomeration in 2015 is shown in Tables 3-1, 3-2 and 3-3.

[0048] ;

[0049] ;

[0050] ; It should be understood that the above numbers S1.1-S5 are only used to distinguish and facilitate the expression of each different step, and do not necessarily constitute a limitation on the execution order between the steps.

[0047] Embodiment two: The embodiment provides an inter-city high-speed railway transfer travel demand estimation system based on spatial correlation, comprising a memory and a processor. The memory is used for storing a computer program. The processor is used for calling the computer program to execute the method in embodiment one.

[0048] Embodiment three: The embodiment provides a computer readable storage medium, wherein the computer readable storage medium stores a computer program, and the computer program enables an electronic device to implement the method in embodiment one when the computer program runs on the electronic device.

[0049] Embodiment four: The embodiment provides a computer program product, comprising a computer program, and the computer program enables an electronic device to implement the method in embodiment one when the computer program runs on the electronic device.

[0050] The specific implementation manners of the system, the electronic device, the computer readable storage medium and the computer program product provided in the embodiment of the application can refer to the specific embodiments of the above method, and details are not described herein.

[0051] The technical contents of the above embodiments can be mutually referred to. For the same or similar technical features, part of the embodiments are appropriately omitted.

[0052] Obviously, those skilled in the art should understand that each unit or each step of the above application can be realized by a general computing device, which can be concentrated on a single computing device, or distributed on a network composed of multiple computing devices, and can be realized by program codes executable by the computing device, so that they can be stored in a storage device and executed by the computing device, or they can be respectively manufactured into each integrated circuit module, or multiple modules or steps thereof can be manufactured into a single integrated circuit module. Thus, the application is not limited to any specific combination of hardware and software.

[0053] The above is only the preferred specific implementation manner of the application, but the protection scope of the application is not limited to this. Any changes or replacements easily thought by those skilled in the art within the technical scope disclosed by the application should be covered in the protection scope of the application, and thus the protection scope of the application should be subject to the protection scope of the claims.

Claims

1. A method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, characterized in that: include: Step S1: Collecting data related to the high-speed railway network, determining the affiliation between high-speed railway stations and cities based on the collected data, and dividing the city pairs covered by the high-speed railway network into direct city pairs and transfer city pairs, and calculating the direct passenger flow between all stations in the high-speed railway network; Step S2: The direct passenger flows between all pairs of stations in the high-speed railway network are classified and aggregated into direct passenger flows between corresponding pairs of directly connected cities according to the affiliation between the stations and the cities; Step S3: Calculate the earth's spherical distance between cities and construct a spatial weight matrix between cities; Step S4: Construct a spatial gravity model to characterize the mapping relationship between the high-speed rail travel demand vector between cities and the spatial weight matrix between cities; the high-speed rail travel demand vector between cities is composed of the high-speed rail travel demand vector between direct city pairs and the high-speed rail travel demand vector between transfer city pairs; Step S5: Calibrate the pending parameters of the spatial gravity model to obtain an estimated value of the high-speed rail travel demand vector between the transfer city pairs; wherein, calibrating the pending parameters of the spatial gravity model includes: counting the direct passenger flow between the direct city pairs to form the high-speed rail travel demand vector between the direct city pairs, initializing the high-speed rail travel demand vector between the transfer city pairs, and obtaining the initial high-speed rail travel demand vector.

2. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 1, characterized in that: In step S1, the city pairs covered by the high-speed railway network are divided into direct city pairs and transfer city pairs, including: dividing the two cities with direct high-speed railway trains into direct city pairs; dividing the two cities without direct high-speed railway trains and requiring travel by continuous transfer into transfer city pairs.

3. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 1, characterized in that: The step S1 counts the direct passenger flow between any two stations in the high-speed railway network, including: in view of the dynamic expansion characteristics of the high-speed railway network, calculating the average daily direct passenger flow for existing lines based on 365 days a year, and converting the average daily direct passenger flow for new lines added during the statistical period based on the actual number of operating days.

4. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 1, characterized in that: In step S3, the earth's spherical distance between cities is calculated, which includes: using the Haversine formula to calculate the earth's spherical distance between city centers according to the longitude and latitude coordinates of the city centers as the earth's spherical distance between cities.

5. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 1, characterized in that: The step S3 constructs the spatial weight matrix between cities, including: constructing 、 and Three spatial weight matrices are used to capture the spatial correlation based on the destination city, the spatial correlation based on the starting city, and the spatial correlation between the starting and ending cities. The calculation formula is: ； ； ； in, is a The identity matrix; weight matrix It is a row-normalized The matrix, the elements in the matrix For the city and The reciprocal of the distance on the Earth's spherical surface between the centers of The main diagonal of is 0; represents the matrix Kronecker product.

6. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 5, characterized in that: The space gravity model in step S4 includes: ； Among them, the dependent variable represents the high-speed rail travel demand vector between cities, vector, , is the number of cities with high-speed rail services; 、 and They are the spatial correlation coefficient of the starting point, the spatial correlation coefficient of the ending point, and the spatial correlation coefficient of the starting and ending points, all of which are unknown parameters; yes A vector whose elements are all 1; yes The coefficient of is an undetermined parameter; and for The matrix represents the urban gravity characteristics of the starting and ending cities, Dimensions that represent the gravitational characteristics of cities; and They are the starting city gravity characteristic coefficient and the end city gravity characteristic coefficient, both of which are unknown parameters; yes A vector of , representing the average travel time of high-speed trains between cities; is the average travel time coefficient, which is a parameter to be determined; is an interference term and satisfies the normal distribution.

7. The method for estimating inter-city high-speed railway transfer travel demand based on spatial correlation according to claim 1, characterized in that: In step S5, the space gravity model is calibrated for the undetermined parameters, including calibrating the space gravity model for the undetermined parameters using the maximum expectation algorithm and maximum likelihood estimation; The step S5 specifically includes: Step 1: Initialize the high-speed rail travel demand between transfer city pairs to zero, and combine it with the statistically obtained high-speed rail direct passenger flow between direct city pairs to form the initial high-speed rail travel demand vector ; Step 2: Perform iterative calculations according to the following steps until convergence; ①Calculate the Model parameters for the next iteration: Based on the current inter-city high-speed rail travel demand vector , the maximum likelihood method is used to estimate the unknown parameters of the space gravity model and obtain the model parameters 、 、 、 、 、 and ; 、 、 、 、 、 and Respectively represent The iterative 、 、 、 、 、 and value; ② Update the high-speed rail travel demand vector: ； in, Indicates the The high-speed rail travel demand vector of the second iteration; ③ Determine whether the algorithm converges: When the estimated value of the high-speed rail travel demand vector converges in two consecutive iterations, that is, , then stop the iteration, vector The value of the corresponding transfer city pair is the estimated inter-city high-speed rail transfer travel demand; otherwise, return to ②.

8. A system for estimating inter-city high-speed railway transfer travel demand based on spatial correlation, characterized in that: include: memory and processor; The memory is used to store computer programs; The processor is configured to call the computer program to execute the method according to any one of claims 1 to 7.

9. A computer-readable storage medium, characterized in that The computer-readable storage medium stores a computer program, and when the computer program is executed on an electronic device, the electronic device implements the method according to any one of claims 1 to 7.

10. A computer program product comprising a computer program, characterized in that When the computer program is executed on an electronic device, the electronic device is enabled to implement the method according to any one of claims 1 to 7.

Images