Bus corridor section passenger flow acquisition method based on IC card and GPS data

Abstract

The invention discloses a bus corridor section passenger flow acquisition method based on IC card and GPS data, and relates to the technical field of data fusion analysis, and the bus corridor section passenger flow acquisition method specifically comprises the following steps: defining a section space; the section space comprises a determined section range and a determined direction; calculating the time when the vehicle passes through the section space; constructing a space-time constraint condition according to the section space; predicting the vehicle arrival time of each station in the section space according to the IC card data record by taking the constructed space-time constraint condition as a reference; calculating the basic section passenger flow prediction quantity through the difference between the GPS data quality and the vehicle arrival time; based on a geographic position, optimizing the basic section passenger flow prediction quantity; errors are controlled through long-term iteration. Based on data fusion, the bus corridor section passenger flow in any time period can be obtained, and the limitation of a traditional station statistical method is broken through.

Description

Technical Field

[0001] The present invention relates to the technical field of data fusion analysis, and specifically to a method for obtaining cross-section passenger flow of a bus corridor based on IC card and GPS data. Background Art

[0002] Data Fusion technology is an information processing technology that integrates information from multiple data sources. By coordinating, combining, and interpreting data from different sources, it improves the accuracy, reliability, and integrity of the data.

[0003] Bus passenger flow analysis is crucial for public transportation planning, optimized dispatching, and improving the travel efficiency of passengers; IC card data provides information on the boarding time and boarding station of passengers, while GPS data records the running trajectory of buses; the fusion of these two types of data helps to obtain more accurate bus passenger flow information and provides a basis for optimizing the public transportation system; traditional bus passenger flow estimation methods mainly rely on passenger surveys, fixed monitoring point data, or empirical models based on historical data, but these methods have the disadvantages of data lag, limited coverage, and difficulty in adapting to real-time changes. Summary of the Invention

[0004] The purpose of the present invention is to provide a method for obtaining cross-section passenger flow of a bus corridor based on IC card and GPS data to solve the problems raised in the prior art.

[0005] To achieve the above purpose, the present invention provides the following technical solution: A method for obtaining cross-section passenger flow of a bus corridor based on IC card and GPS data, the method for obtaining cross-section passenger flow of the bus corridor specifically includes the following steps: Step S100, defining the cross-section space; the cross-section space includes determining the cross-section range and determining the direction; Step S200, calculating the time for the vehicle to pass through the cross-section space; Step S300, constructing spatio-temporal constraint conditions according to the cross-section space; Step S400, based on the constructed spatio-temporal constraint conditions, predicting the vehicle arrival time at each station within the cross-section space according to the IC card data record; Step S500, calculating the predicted value of the basic cross-section passenger flow through the GPS data quality and the vehicle arrival time difference; Step S600, optimizing the predicted value of the basic cross-section passenger flow based on the geographical location; Step S700, controlling the error through long-term iteration; Defining the cross-section space, the cross-section space includes determining the cross-section range and determining the direction, specifically: The cross-section space is established through the GIS coordinate system; The cross-section range is set as a rectangle; determined by the starting point coordinates (x1, y1) and the ending point coordinates (x m , y m ); the length is determined by the starting point coordinates and the ending point coordinates; the width is the actual width of the road; where, x1 and x m represent the abscissas of the starting point coordinates and the ending point coordinates respectively; y1 and y m represent the ordinates of the starting point coordinates and the ending point coordinates respectively; m is a positive integer; The direction is determined by the continuous displacement coordinates of the vehicle GPS trajectory points; Calculate the time for the vehicle to pass through the cross-section space, specifically: Step S3-1, obtain the GPS trajectory point sequence of the vehicle, and the GPS trajectory point sequence is characterized as ; where, (t i , x i , y i ) represents the i-th GPS trajectory point; t i represents the acquisition time of the GPS trajectory point; and represent the position coordinates of the vehicle's GPS trajectory points respectively; n represents the number of trajectory points in the GPS trajectory point sequence, n is a positive integer; i represents the number label of the trajectory points, i is a positive integer, 1 ≤ i ≤ n; Step S3-2, screen the set S in of points that enter the cross-section space from the trajectory points, and the set S in ={(t i , x i , y i )|(x1 ≤ x i ≤ x m ) ∩ (y1 ≤ y i ≤ y m )}; Step S3-3, if the set S in is non-empty, select the time t first of the first point and the time t last of the last point; Step S3-4, use linear interpolation to calculate the time to enter and exit the cross-section space; Specifically: ; ; where, t entry represents the time to enter the cross-section space; t exit represents the time to exit the cross-section space; L1 represents the minimum displacement value from the entry boundary of the cross-section space; L2 represents the minimum displacement value from the exit boundary of the cross-section space; v1 represents the instantaneous speed at the entry boundary; v2 represents the instantaneous speed at the exit boundary; Among them, further, v1 can be obtained from the acquisition time and position coordinates of the two minimum trajectory points in the GPS trajectory points that are closest to the boundary of the cross-section space; similarly, v2 can be obtained. Based on the cross-section space, construct spatio-temporal constraint conditions, and obtain GPS trajectory points that meet the spatio-temporal constraint conditions. Specifically: Ensure that the driving direction of the vehicle is consistent with the determined direction of the cross-section space. The driving time range of the vehicle is , ; where t entry represents the time of entering the cross-section space; t exit represents the time of leaving the cross-section space. Based on the constructed spatio-temporal constraint conditions, and according to the IC card data records, predict the vehicle arrival time at each station in the cross-section space. Specifically: Step S5-1: Obtain the boarding station and boarding time of the passenger, and obtain the line average travel time matrix according to historical data. Further, the specific method for obtaining the line average travel time matrix is as follows: ; Among them, represents the historical average travel time from station to station , u and v represent station identifiers; N represents the number of effective trips of all vehicles from station to station during the statistical period, and N is a positive integer; represents the arrival time at station ; represents the departure time from station , k represents the effective trip number mark of the vehicle, k is a positive integer, 1 ≤ k ≤ N; Among them, the specific number of effective trips is: If the time of a certain trip exceeds ±3 times the standard deviation of the average value, it is regarded as abnormal (such as traffic congestion caused by a traffic accident) and is not counted as an effective trip. Step S5-2: Adjust the historical average time according to the real-time road conditions, obtain the deviation of the actual travel time, and calculate the correction term. The correction term reflects the deviation between the actual travel time on the day and the historical average time, so as to more accurately estimate the passenger's alighting time. According to the GPS trajectory points of the vehicle, obtain the actual travel time T' between different stations of the vehicle. Among them, the specific calculation formula of the correction term is: ; where It represents the correction term; T represents the historical average travel time; Preferably, the selection of T can be calculated by selecting the nearest N valid trips from the current time; Step S5-3: According to the boarding time obtained in step S5-1 and the line average travel time matrix, combined with the correction term obtained in step S5-2, predict the vehicle arrival time at each station in the section space; Among them, the vehicle arrival time is the algebraic sum of the departure time of the previous station in the section space, the historical average travel time between the corresponding stations, and the correction term between the corresponding stations; Calculate the basic section passenger flow prediction volume through the GPS data quality and the vehicle arrival time difference, specifically: Step S6-1: Calculate the GPS data quality weight according to the obtained GPS trajectory point sequence of the vehicle; Furthermore, the calculation formula of the GPS data quality weight is characterized as: β = Q / Q'; where, β represents the GPS data quality weight; Q represents the number of GPS trajectory points in the section space, Q is a positive integer, Q ≤ n; Q' represents the theoretically required number of GPS trajectory points; Q' = c / l; where, c represents the length of the section space; l represents the GPS sampling interval distance; Step S6-2: Calculate the vehicle arrival time difference according to the historical error calibration; Specifically: ; Among them, represents the vehicle arrival time difference; e represents the natural constant; represents the actual arrival time of the corresponding station in history; represents the predicted vehicle arrival time; represents the time decay coefficient, obtained by fitting the historical data with the natural constant; Step S6-3: Calculate the basic section passenger flow prediction volume through the section space passenger flow aggregation model; Among them, the expression of the section space passenger flow aggregation model is characterized as: ; Among them, A represents the basic section passenger flow prediction volume; represents the GPS data quality weight of vehicle h; represents the set of vehicles that conform to the determined direction and entry and exit time of the section space; represents the vehicle arrival time difference of the vehicle taken by passenger p; represents the set of passengers on vehicle h; represents the probability that passenger p gets off in the section space, obtained based on the statistical frequency G of the number of people getting off between stations; I represents the spatio-temporal matching indicator function; Represents the current time identifier of passenger p; Where A is the predicted volume of passenger flow at the basic cross-section, and it can be rounded up or down according to the actual situation; Among them, the logical judgment condition of the spatio-temporal matching indication function I is: ; When the condition is met, take 1, otherwise take 0; The condition checks whether the boarding time period of passenger p overlaps with the time period when vehicle h passes through the cross-section space; that is, the boarding time of the passenger is earlier than the time when the vehicle leaves the cross-section, and the alighting time is later than the time when the vehicle enters the cross-section; This ensures that the passenger is on the vehicle when the vehicle passes through the cross-section and is thus counted into the passenger flow of this cross-section; In step S6-3, the statistical frequency of the historical number of alighting passengers is added to the cross-section space passenger flow aggregation model, specifically: Collect the number of boarding and alighting passengers at different stations in history; Based on the number of boarding and alighting passengers at the different stations, calculate the statistical frequency of the number of alighting passengers between different stations; Based on the influence of geographical location, optimize the predicted volume of passenger flow at the basic cross-section, specifically: Among them, the influence of geographical factors on the passenger flow of the bus corridor cross-section is mainly reflected in two aspects: the surrounding land use nature and spatial accessibility; Step S8-1: Construct a geographical influence coefficient function through the distance from the geographical location to the cross-section space, the average annual passenger flow of the geographical location, and the distance decay coefficient obtained by fitting historical data; Specifically: ; Among them, Represents the geographical influence coefficient; Represents the number of the f-th type of POI; Represents the straight-line distance from the POI to the cross-section space; Represents the weight of the f-th type of POI, reflecting the attractiveness of this type of facility to passenger flow, calibrated based on historical passenger flow regression analysis; σ represents the distance decay coefficient, controlling the decay rate of the influence of the POI with distance; f represents the category identifier of the POI; F is the total number of POI categories; The POI represents a specific location or target in the GIS map, including restaurants, hotels, gas stations, parks, schools, hospitals, etc.; Step S8-2: Calculate the geographical influence coefficient according to the actual cross-section space and optimize the predicted volume of passenger flow at the basic cross-section.

[0006] The specific characterization formula is: ; Among them, Represents the optimized predicted volume of passenger flow at the basic cross-section; Control the error through long-term iteration, specifically: Update the model parameters based on the accumulated historical data; Minimize the error using the gradient descent method; The minimizing the error using the gradient descent method is specifically ; Among them, it is only necessary to ensure that the error value is smaller than the model error composed of the parameters before the update.

[0007] Compared with the prior art, the beneficial effects of the present invention are as follows: Based on the fusion of IC card and GPS data, combined with spatio-temporal constraints, geographic information optimization and error control technologies, the present invention realizes the accurate acquisition of the cross-sectional passenger flow of the bus corridor, breaking through the limitations of traditional station statistics methods; this method can accurately monitor the passenger flow of the line, improve the prediction accuracy of vehicle arrival time, and improve the accuracy of passenger flow calculation through multi-source data fusion; in addition, the geographic influence coefficient is introduced to optimize the passenger flow prediction result, combined with the error control and long-term optimization mechanism, to improve the adaptability to sudden traffic conditions, providing a scientific basis for the optimization of the bus system, thereby improving the operation efficiency and management level of urban public transportation. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a schematic flow chart of the steps of the method for obtaining the cross-sectional passenger flow of the bus corridor based on IC card and GPS data of the present invention; Figure 2 is a schematic diagram of the change curve of POI with passenger flow density in Embodiment 2 of the method for obtaining the cross-sectional passenger flow of the bus corridor based on IC card and GPS data of the present invention. DETAILED DESCRIPTION OF THE EMBODIMENTS

[0009] The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present invention. Obviously, the described embodiments are only a part of the embodiments of the present invention, rather than all of the embodiments. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present invention without making creative efforts shall fall within the protection scope of the present invention.

[0010] Embodiment: As Figures 1 - 2 shown, the present invention provides a technical solution, a method for obtaining the cross-sectional passenger flow of the bus corridor based on IC card and GPS data. The method for obtaining the cross-sectional passenger flow of the bus corridor specifically includes the following steps: Step S100, define the cross-sectional space; the cross-sectional space includes determining the cross-sectional range and determining the direction; Step S200, calculate the time for the vehicle to pass through the cross-sectional space; Step S300, construct spatio-temporal constraint conditions according to the cross-sectional space; Step S400: Based on the constructed spatio-temporal constraint conditions, predict the vehicle arrival times at each station within the cross-section space according to the IC card data records; Step S500: Calculate the predicted passenger flow volume of the basic cross-section through the GPS data quality and the difference in vehicle arrival times; Step S600: Optimize the predicted passenger flow volume of the basic cross-section based on the geographical location; Step S700: Control the error through long-term iteration; Define the cross-section space, and the cross-section space includes determining the cross-section range and the direction, specifically: The cross-section space is established through the GIS coordinate system; The cross-section range is set as a rectangle; determined by the starting point coordinates (x1, y1) and the ending point coordinates (x m , y m ), the length is determined; the width is the actual width of the road; where, x1 and x m respectively represent the abscissas of the starting point coordinates and the ending point coordinates; y1 and y m respectively represent the ordinates of the starting point coordinates and the ending point coordinates; m is a positive integer; Determine the direction through the continuous displacement coordinates of the vehicle GPS trajectory points; Calculate the time for the vehicle to pass through the cross-section space, specifically: Step S3-1: Obtain the GPS trajectory point sequence of the vehicle, and the GPS trajectory point sequence is characterized as ; where, (t i , x i , y i ) represents the i-th GPS trajectory point; t i represents the acquisition time of the GPS trajectory point; and respectively represent the position coordinates of the vehicle's GPS trajectory points; n represents the number of trajectory points in the GPS trajectory point sequence, n is a positive integer; i represents the number label of the trajectory points, i is a positive integer, 1 ≤ i ≤ n; Step S3-2: Screen the set of points S in that enter the cross-section space among the trajectory points, and the set of points S in ={(t i , x i , y i )|(x1 ≤ x i ≤ x m ) ∩ (y1 ≤ y i ≤ y m )}; Step S3-3: If the set of points S in is non-empty, select the time t first of the first point and the time t last; Step S3-4: Calculate the time of entering and exiting the cross-section space using linear interpolation; Specifically: ; ; Among them, t entry represents the time of entering the cross-section space; t exit represents the time of exiting the cross-section space; L1 represents the minimum displacement value from the entry boundary of the cross-section space; L2 represents the minimum displacement value from the exit boundary of the cross-section space; v1 represents the instantaneous speed at the entry boundary; v2 represents the instantaneous speed at the exit boundary; Among them, further, v1 can be obtained from the acquisition times and position coordinates of the two minimum trajectory points in the GPS trajectory that are closest to the entry boundary of the cross-section space; similarly, v2 can be obtained; According to the cross-section space, construct spatio-temporal constraint conditions, and obtain GPS trajectory points that meet the spatio-temporal constraint conditions. Specifically: Ensure that the driving direction of the vehicle is consistent with the determined direction of the cross-section space; The driving time range of the vehicle is , ; Among them, t entry represents the time of entering the cross-section space; t exit represents the time of exiting the cross-section space; Based on the constructed spatio-temporal constraint conditions, predict the vehicle arrival times at each station within the cross-section space according to the IC card data records. Specifically: Step S5-1: Obtain the boarding station and boarding time of the passenger, and obtain the line average travel time matrix according to historical data; Further, the specific method for obtaining the line average travel time matrix is: ; Among them, represents the historical average travel time from station to station , u and v represent station identifiers; N represents the number of valid trips of all vehicles from station to station during the statistical period, and N is a positive integer; represents the arrival time at station ; represents the departure time from station , k represents the valid trip number mark of the vehicle, k is a positive integer, and 1 ≤ k ≤ N; Among them, the specific number of valid trips is: If the time of a certain trip exceeds ±3 times the standard deviation of the average value, it is regarded as abnormal (such as congestion caused by a traffic accident) and is not counted as a valid trip; Step S5-2: Adjust the historical average time according to the real-time road conditions, obtain the deviation of the actual travel time, and calculate the correction term; The correction term reflects the deviation between the actual travel time on the current day and the historical average time, so as to more accurately estimate the passenger getting-off time; According to the GPS trajectory points of the vehicle, obtain the actual travel time T' between different stations of the vehicle; Among them, the calculation formula of the correction term is specifically: ; Among them, represents the correction term; T represents the historical average travel time; Preferably, the selection of T can be calculated by selecting the nearest N valid trips to the current time; Step S5-3: According to the boarding time obtained in step S5-1 and the line average travel time matrix, and combining the correction term obtained in step S5-2, predict the vehicle arrival time at each station in the section space; Among them, the vehicle arrival time is the algebraic sum of the departure time of the previous station in the section space, the historical average travel time between the corresponding stations, and the correction term between the corresponding stations; Calculate the basic section passenger flow prediction volume through the GPS data quality and the vehicle arrival time difference, specifically: Step S6-1: Calculate the GPS data quality weight according to the obtained GPS trajectory point sequence of the vehicle; Furthermore, the calculation formula of the GPS data quality weight is characterized as: β = Q / Q'; where, β represents the GPS data quality weight; Q represents the number of GPS trajectory points in the section space, Q is a positive integer, Q ≤ n; Q' represents the theoretically required number of GPS trajectory points; Q' = c / l; where, c represents the length of the section space; l represents the GPS sampling interval distance; Step S6-2: Calculate the vehicle arrival time difference according to the historical error calibration; Specifically: ; Among them, represents the vehicle arrival time difference; e represents the natural constant; represents the actual arrival time of the corresponding station in history; represents the predicted vehicle arrival time; represents the time decay coefficient, obtained by fitting historical data with the natural constant; Step S6-3: Calculate the basic section passenger flow prediction volume through the section space passenger flow aggregation model; Among them, the expression of the cross-sectional space passenger flow aggregation model is characterized as follows: ; Among them, A represents the predicted value of the basic cross-sectional passenger flow; represents the GPS data quality weight of vehicle h; represents the set of vehicles that conform to the determined direction and entry / exit time of the cross-sectional space; represents the arrival time difference of the vehicle taken by passenger p; represents the set of passengers on vehicle h; represents the probability that passenger p gets off at the cross-sectional space, obtained based on the statistical frequency G of the number of passengers getting off between stations; I represents the spatio-temporal matching indicator function; represents the current time identifier of passenger p; Among them, the logical judgment condition of the spatio-temporal matching indicator function I is: ; take 1 when the condition is met, and take 0 otherwise; the condition checks whether the boarding time period of passenger p overlaps with the time period when vehicle h passes through the cross-sectional space; that is, the boarding time of the passenger is earlier than the time when the vehicle leaves the cross-section, and the getting-off time is later than the time when the vehicle enters the cross-section; this ensures that the passenger is on the vehicle when the vehicle passes through the cross-section, and thus is counted into the passenger flow of this cross-section; In step S6-3, the statistical frequency of the historical number of passengers getting off is added to the cross-sectional space passenger flow aggregation model, specifically: Collect the number of passengers getting on and off at different stations in history; Based on the number of passengers getting on and off at the different stations, calculate the statistical frequency of the number of passengers getting off between different stations; Based on the influence of geographical location, optimize the predicted value of the basic cross-sectional passenger flow, specifically: Among them, the influence of geographical factors on the cross-sectional passenger flow of the bus corridor is mainly reflected in two aspects: the surrounding land use nature and spatial accessibility; In step S8-1, construct a geographical influence coefficient function through the distance from the geographical location to the cross-sectional space, the average annual passenger flow of the geographical location, and the distance attenuation coefficient obtained by fitting historical data; Specifically: ; Among them, represents the geographical influence coefficient; represents the number of the f-th type of POI; represents the straight-line distance from the POI to the cross-sectional space; represents the weight of the f-th type of POI, reflecting the attraction of this type of facility to the passenger flow, calibrated based on historical passenger flow regression analysis; σ represents the distance attenuation coefficient, controlling the attenuation speed of the POI influence with distance; f represents the category identifier of the POI; F is the total number of POI categories; The POI represents a specific location or object in the GIS map, including restaurants, hotels, gas stations, parks, schools, hospitals, etc.; Example 1 Use ArcGIS Pro to load the road network vector data of a certain city (source: the Planning and Natural Resources Commission of a certain city), and supplement the real-time traffic condition layer in combination with the API of a certain map; Cross-section space definition: Cross-section range: Starting point coordinates: (x1, y1) = (116.455°E, 39.908°N); Measured based on the road center line, expanding 25 meters laterally to cover the bus lane; End point coordinates: (x m , y m ) = (116.470°E, 39.908°N); Length: approximately 1.5 kilometers (longitude span 0.015°, latitude unchanged); Width: The actual width of the road is 50 meters (including the bus lane), generating a rectangular geofence; Direction determination: Obtain the GPS trajectories of 10 sample vehicles from the bus group, verify that the proportion of eastward (increasing longitude) trajectories > 95%, and ensure the accuracy of the direction definition; That is, the continuous eastward displacement (increasing longitude) of the vehicle GPS trajectory points is the effective direction; Bus vehicle on-board GPS terminal (model: a certain Douxingtong **); GPS trajectory data (Bus Route 40* in a certain city, license plate *A72***); GPS trajectory point sequence:

[0011] ; Screen the set of points S that enter the cross-section in : Meet And There are 12 trajectory points in total; In-out time calculation: The time t of the first point first = 8:00:30; The time t of the last point last = 8:02:45; Calculate the in-out time by linear interpolation: t entry = 8:00:30 - (50m / 8.33m / s) ≈ 8:00:24; t exit=8:02:45+(50m / 7.14m / s)≈8:02:52; Calculate the GPS data quality weight according to the obtained GPS trajectory point sequence of the vehicle; Furthermore, the calculation formula of the GPS data quality weight is characterized as: β = Q / Q'; where, β represents the GPS data quality weight; Q represents the number of GPS trajectory points in the cross-section space, Q is a positive integer, Q ≤ n; Q' represents the theoretical number of GPS trajectory points that should be; Q' = c / l; where, c represents the length of the cross-section space; l represents the GPS sampling interval distance; Q' = c / l = 1500m / (8.33m / s * 10s) ≈ 18; β = Q / Q' ≈ 0.67; Calculate the vehicle arrival time difference according to historical error calibration: Extract 1% of the passenger records in the historical data, compare the predicted and actual getting-off times, and fit the exponential decay parameter λ; Calibration result of a certain city's data: λ = 0.1, When the error is 3 minutes, α = e −0.1×3 ≈0.74; Example 2,

[0012] In the cross-section space of a certain East Road Pedestrian Street in a certain city (from east to west direction), within a range of 500 meters around: Based on historical passenger flow regression analysis, obtain the weights of different categories of POIs, as shown in Table 1: Such as Figure 2 Shown, is the curve of POI changing with passenger flow density;

[0013] Table 1 Weight comparison table of different categories of POIs 2 subway stations (w = 0.8), 0.2 km and 0.4 km away from the cross-section; 3 large shopping malls (w = 0.5), 0.1 km, 0.3 km, and 0.5 km away; 5 office buildings (w = 0.6), with an average distance of 0.25 km; Distance attenuation coefficient: = 1.5; ; (POI is a subway station); Similarly obtained: Z2 = 0.66; (POI is a large shopping mall); Z3 = 1.66; (POI is an office building); Then the geographical influence coefficient Z of the cross-section space of a certain East Road Pedestrian Street in a certain city is 3.13.

[0014] Preferably, the ArcGIS Spatial Analyst tool is used to generate a POI density heat map through spatial interpolation to quantify the facility aggregation degree. A geographical influence coefficient function can also be constructed, specifically as follows: ; where peo represents the service population size of the f-th type of POI; Step S8-2: Calculate the geographical influence coefficient according to the actual section space and optimize the predicted passenger flow volume of the basic section.

[0015] The specific representation formula is: ; where represents the optimized predicted passenger flow volume of the basic section; Control the error through long-term iteration, specifically as follows: Update the model parameters based on the accumulated historical data; Use the gradient descent method to minimize the error; The use of the gradient descent method to minimize the error is specifically ; where it is only necessary to ensure that the error value is smaller than the model error composed of the parameters before the update.

[0016] For those skilled in the art, it is obvious that the present invention is not limited to the details of the above exemplary embodiments, and the present invention can be implemented in other specific forms without departing from the spirit or basic characteristics of the present invention. Therefore, from any point of view, the embodiments should be regarded as exemplary and non-limiting. The scope of the present invention is defined by the appended claims rather than the above description. Therefore, all changes falling within the meaning and scope of the equivalent elements of the claims are intended to be included in the present invention. Any reference signs in the claims should not be regarded as limiting the claimed rights.

Claims

1. A method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data, characterized in that: The method for obtaining the cross-section passenger flow of the bus corridor specifically includes the following steps: Step S100: Define the cross-section space; the cross-section space includes determining the cross-section range and determining the direction; Step S200: Calculate the time for the vehicle to pass through the cross-section space; Step S300: Construct spatio-temporal constraint conditions according to the cross-section space; Step S400: Based on the constructed spatio-temporal constraint conditions, predict the vehicle arrival time at each station within the cross-section space according to the IC card data record; Step S500: Calculate the basic cross-section passenger flow prediction volume through the GPS data quality and the vehicle arrival time difference; Step S600: Optimize the basic cross-section passenger flow prediction volume based on the geographical location; Step S700: Control the error through long-term iteration.

2. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 1, wherein: Define the cross-section space, which includes determining the cross-section range and determining the direction. Specifically: The cross-section space is established through the GIS coordinate system; The cross-section range is set as a rectangle; the length is determined by the starting coordinates (x1, y1) and the ending coordinates (x m , y m ); the width is the actual width of the road; where x1 and x m respectively represent the abscissas of the starting coordinates and the ending coordinates; y1 and y m respectively represent the ordinates of the starting coordinates and the ending coordinates; m is a positive integer; Determine the direction through the continuous displacement coordinates of the vehicle GPS trajectory points.

3. The method for obtaining the cross-section passenger flow of a bus corridor based on IC card and GPS data according to claim 2, wherein: Calculate the time for the vehicle to pass through the cross-section space. Specifically: Step S3-1: Obtain the GPS trajectory point sequence of the vehicle, and the GPS trajectory point sequence is characterized as ; where, (t i , x i , y i ) represents the i-th GPS trajectory point; t i represents the acquisition time of the GPS trajectory point; and respectively represent the position coordinates of the GPS trajectory points of the vehicle; n represents the number of trajectory points in the GPS trajectory point sequence, and n is a positive integer; i represents the quantity label of the trajectory points, and i is a positive integer, 1 ≤ i ≤ n; Step S3-2: Screen the set S of points that enter the cross-section space among the trajectory points in , the set S of points in ={(t i , x i , y i ) | (x1 ≤ x i ≤ x m ) ∩ (y1 ≤ y i ≤ y m )}; Step S3-3: If the point set S in is non-empty, select the first point time t first and the last point time t last ; Step S3-4: Use linear interpolation to calculate the time for entering and leaving the cross-section space.

4. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 3, characterized in that: According to the cross-section space, construct spatio-temporal constraint conditions and obtain the GPS trajectory points that meet the spatio-temporal constraint conditions. Specifically: Ensure that the driving direction of the vehicle is consistent with the determined direction of the cross-section space; The driving time range of the vehicle is , ; where t entry represents the time of entering the cross-section space; t exit represents the time of leaving the cross-section space.

5. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 4, wherein: Based on the constructed spatio-temporal constraint conditions, predict the vehicle arrival time at each station within the cross-section space according to the IC card data record. Specifically: Step S5-1: Obtain the boarding station and boarding time of the passenger, and obtain the line average travel time matrix according to historical data; Step S5-2: Adjust the historical average time according to the real-time road conditions, obtain the deviation of the actual travel time, and calculate the correction term; Step S5-3: According to the boarding time obtained in Step S5-1 and the line average travel time matrix, combined with the correction term obtained in Step S5-2, predict the vehicle arrival time at each station within the cross-section space.

6. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 5, characterized in that: Calculate the basic cross-section passenger flow prediction volume through the GPS data quality and the vehicle arrival time difference. Specifically: Step S6-1: Calculate the GPS data quality weight according to the obtained GPS trajectory point sequence of the vehicle; Step S6-2: Calculate the vehicle arrival time difference according to the historical error calibration; Step S6-3: Calculate the basic cross-section passenger flow prediction volume through the cross-section space passenger flow aggregation model.

7. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 6, wherein: In Step S6-3, the statistical frequency of the historical alighting number is added to the cross-section space passenger flow aggregation model. Specifically: Collect the alighting and boarding numbers at different stations in history; Based on the alighting and boarding numbers at different stations, calculate the statistical frequency of the alighting number between different stations, which is used to constitute the cross-section space passenger flow aggregation model.

8. The method for obtaining the cross-sectional passenger flow of a bus corridor based on IC card and GPS data according to claim 7, wherein: Optimize the basic cross-section passenger flow prediction volume based on the influence of geographical location. Specifically: Step S8-1: Construct a geographical influence coefficient function through the distance between the geographical location and the cross-section space, the average annual passenger flow of the geographical location, and the distance attenuation coefficient obtained by fitting historical data; Step S8-2: Calculate the geographical influence coefficient according to the actual cross-section space and optimize the basic cross-section passenger flow prediction volume.

9. The method for obtaining the cross-section passenger flow of a bus corridor based on IC card and GPS data according to claim 8, characterized in that: Control the error through long-term iteration. Specifically: Update the model parameters based on the accumulated historical data; Minimize the error using the gradient descent method.

Images