Passenger OD spatio-temporal distribution identification method and system based on multi-source data fusion

Abstract

The application discloses a kind of based on multi-source data fusion's passenger OD space-time distribution identification method and system, comprising: processing passenger bus GPS data, obtain the parking point sequence of passenger bus;Passenger bus line ticketing data and passenger departure data are associated, and the start and end point sequence of ticketing data is obtained;The parking point sequence of passenger bus is associated with the start and end point sequence of ticketing data, and passenger OD space-time distribution data is obtained.The application can realize the accurate identification of passenger OD, so as to accurately grasp the real arrival position of passenger.

Description

Technical Field

[0001] This invention relates to the field of passenger transport information, and specifically to a method and system for identifying the spatiotemporal distribution of passenger OD (Original Location) based on multi-source data fusion. Background Technology

[0002] Passenger origin-destination (OD) spatiotemporal distribution data is crucial for effective urban and regional transportation planning, management, and decision-making. This data can help cities better meet residents' travel needs, improve traffic efficiency, reduce traffic problems, and minimize negative environmental impacts. Therefore, acquiring or identifying passenger OD spatiotemporal distribution data plays a vital role in building intelligent and sustainable urban transportation systems.

[0003] Currently, the acquisition or identification of passenger OD spatiotemporal distribution mainly relies on manual questionnaire surveys to obtain information on the distribution of scheduled passenger routes. With the development of information technology, online ticketing generates a large amount of highway passenger ticketing data. However, since the ticketing data only records the passenger's estimated departure time and location, it is impossible to accurately determine the actual arrival location. Therefore, a passenger OD spatiotemporal distribution identification method and system based on multi-source data fusion is needed to solve the above problems. Summary of the Invention

[0004] In view of this, the purpose of the present invention is to overcome the defects in the prior art and provide a method and system for identifying the spatiotemporal distribution of passenger OD based on multi-source data fusion, which can achieve accurate identification of passenger OD and thus accurately grasp the actual arrival location of passengers.

[0005] The present invention provides a method for identifying the spatiotemporal distribution of passenger OD (Original Departure Point) based on multi-source data fusion, comprising the following steps:

[0006] The GPS data of passenger buses is processed to obtain the stop sequence of passenger buses;

[0007] By correlating passenger bus route ticketing data with passenger departure data, the origin and destination sequence of the ticketing data can be obtained;

[0008] By associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD is obtained.

[0009] Furthermore, the GPS data of passenger buses is processed to obtain the sequence of bus stop locations, specifically including:

[0010] S11. Collect the first GPS data where the instantaneous vehicle speed is 0 throughout the day, filter out the second GPS data where the time points are continuous from the first GPS data, and calculate the duration T of the second GPS data where the vehicle speed is 0;

[0011] S12. Determine whether the duration T exceeds the time threshold. If yes, use the data points corresponding to the latitude and longitude in the second GPS data as possible parking points and proceed to the next step. If no, return to step S11.

[0012] S13. Calculate the distance L between the possible parking point and its nearest service area, and determine whether the distance L is greater than the distance threshold. If yes, then take the possible parking point as the pre-parking point and proceed to the next step. If no, return to step S11.

[0013] S14. Following steps S11-S13, the pre-parking points for each day within the set time period are obtained, thus obtaining several pre-parking points. Spatial cluster analysis is performed on these pre-parking points to obtain several clusters. Clusters with more than a certain number of pre-parking points are taken as effective clusters, and the center point of the effective clusters is taken as the target parking point.

[0014] S15. Sort the obtained target parking spots according to the order of parking time to obtain the parking spot sequence. <ID,X1,Y1,T1,SS1,COT1;…;X i Y i T i SS i COT i ...>; where ID represents the passenger bus license plate number, X i With Y i T represents the longitude and latitude of parking point i. i SS represents the parking time at parking point i. i COT represents the duration of stay at parking point i. i This indicates the station sequence number corresponding to parking point i.

[0015] Furthermore, the distance L between the possible parking point and its nearest service area is calculated according to the following formula:

[0016] L=6371.0*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)];

[0017] Where X1 and Y1 represent the longitude and latitude of possible parking spots, and X2 and Y2 represent the longitude and latitude of service areas.

[0018] Furthermore, the passenger bus route ticketing data and passenger departure data are correlated to obtain the origin and destination sequence of the ticketing data, specifically including:

[0019] The passenger bus route ticketing data is associated with the three fields of bus number, origin station, and route destination station in the passenger departure data to obtain the association pair between the passenger bus route ticketing data and the passenger departure data. The license plate field of the passenger departure data in the association pair is mapped to the passenger bus route ticketing data, and the bus time of the passenger bus route ticketing data is updated according to the actual passenger departure data.

[0020] Based on the order of the waypoints, the waypoints of all ticket sales data for the same route are sorted to form a waypoint sequence for that route. <NAME1,COT1;…;NAME i COT i ;...>; where NAME i Indicates the name of waypoint i, COT i Indicates the sequence number of waypoint i;

[0021] By performing field association and adjustment on the waypoint sequence of a route, the origin and destination sequence of a single ticket sales data point can be obtained. <ROUTE,ID,NAME o COT o ,T O ,NAME d COT d >; where ROUTE represents the route number, ID represents the passenger bus license plate number, and NAME represents the route number. o Indicates the departure station name, COT o Indicates the departure station sequence number, T O Indicates departure time, NAME d Indicates the arrival station name, COT d Indicates the arrival station sequence number.

[0022] Furthermore, by associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD (Original Departure Point) is obtained, specifically including:

[0023] By linking and fusing data with the same license plate number and station sequence number, we can obtain the passenger's departure and arrival location names, latitude and longitude coordinates, and departure time, i.e., passenger OD spatiotemporal distribution data:

[0024] <ROUTE,ID,NAME o ,X o ,Y o COT o ,T O ,NAME d ,X d ,Y d COT d >;

[0025] Among them, X o With Yo Indicates the departure station name (NAME) o Longitude and latitude; X d With Y d Indicates the name of the arrival station. d The longitude and latitude.

[0026] A passenger OD spatiotemporal distribution identification system based on multi-source data fusion includes a stop point sequence unit, an origin-destination sequence unit, and a spatiotemporal distribution data unit.

[0027] The parking point sequence unit is used to process the GPS data of passenger buses to obtain the parking point sequence of passenger buses;

[0028] The origin-endpoint sequence unit is used to associate passenger bus route ticketing data with passenger departure data to obtain the origin-endpoint sequence of the ticketing data.

[0029] The spatiotemporal distribution data unit is used to associate the stop sequence of passenger buses with the origin and destination sequence of ticketing data to obtain the spatiotemporal distribution data of passenger OD.

[0030] Furthermore, the GPS data of passenger buses is processed to obtain the sequence of bus stop locations, specifically including:

[0031] S11. Collect the first GPS data where the instantaneous vehicle speed is 0 throughout the day, filter out the second GPS data where the time points are continuous from the first GPS data, and calculate the duration T of the second GPS data where the vehicle speed is 0;

[0032] S12. Determine whether the duration T exceeds the time threshold. If yes, use the data points corresponding to the latitude and longitude in the second GPS data as possible parking points and proceed to the next step. If no, return to step S11.

[0033] S13. Calculate the distance L between the possible parking point and its nearest service area, and determine whether the distance L is greater than the distance threshold. If yes, then take the possible parking point as a pre-parking point and proceed to the next step. If no, return to step S11.

[0034] S14. Following steps S11-S13, the pre-parking points for each day within the set time period are obtained, thus obtaining several pre-parking points. Spatial cluster analysis is performed on these pre-parking points to obtain several clusters. Clusters with more than a certain number of pre-parking points are taken as effective clusters, and the center point of each effective cluster is taken as the target parking point.

[0035] S15. Sort the obtained target parking spots according to the order of parking time to obtain the parking spot sequence. <ID,X1,Y1,T1,SS1,COT1;…;X i Yi T i SS i COT i ...>; where ID represents the passenger bus license plate number, X i With Y i T represents the longitude and latitude of parking point i. i SS represents the parking time at parking point i. i COT represents the duration of stay at parking point i. i This indicates the station sequence number corresponding to parking point i.

[0036] Furthermore, the distance L between the possible parking point and its nearest service area is calculated according to the following formula:

[0037] L=6371.0*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)];

[0038] Where X1 and Y1 represent the longitude and latitude of possible parking spots, and X2 and Y2 represent the longitude and latitude of service areas.

[0039] Furthermore, the passenger bus route ticketing data and passenger departure data are correlated to obtain the origin and destination sequence of the ticketing data, specifically including:

[0040] The passenger bus route ticketing data is associated with the three fields of bus number, origin station, and route destination station in the passenger departure data to obtain the association pair between the passenger bus route ticketing data and the passenger departure data. The license plate field of the passenger departure data in the association pair is mapped to the passenger bus route ticketing data, and the bus time of the passenger bus route ticketing data is updated according to the actual passenger departure data.

[0041] Based on the order of the waypoints, the waypoints of all ticket sales data for the same route are sorted to form a waypoint sequence for that route. <NAME1,COT1;…;NAME i COT i ;...>; where NAME i Indicates the name of the waypoint i, COT i Indicates the sequence number of the waypoint i;

[0042] By performing field association and adjustment on the waypoint sequence of a route, the origin and destination sequence of a single ticket sales data point can be obtained. <ROUTE,ID,NAME o COT o ,T O ,NAME d COT d >; where ROUTE represents the route number, ID represents the passenger bus license plate number, and NAME...o Indicates the departure station name, COT o Indicates the departure station sequence number, T O Indicates departure time, NAME d Indicates the arrival station name, COT d Indicates the arrival station sequence number.

[0043] Furthermore, by associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD (Original Departure Point) is obtained, specifically including:

[0044] By linking and fusing data with the same license plate number and station sequence number, we can obtain the passenger's departure and arrival location names, latitude and longitude coordinates, and departure time, i.e., passenger OD spatiotemporal distribution data:

[0045] <ROUTE,ID,NAME o ,X o ,Y o COT o ,T O ,NAME d ,X d ,Y d COT d >;

[0046] Among them, X o With Y o Indicates the departure station name (NAME) o Longitude and latitude; X d With Y d Indicates the name of the arrival station. d The longitude and latitude.

[0047] The beneficial effects of this invention are as follows: This invention discloses a method and system for identifying the spatiotemporal distribution of passenger transport origin-destination (OD) based on multi-source data fusion. By fusing multi-source data such as passenger transport route GPS data and ticketing data, the stopping point sequence of passenger buses is obtained. By associating passenger transport route ticketing data with passenger departure data, the origin-destination sequence of ticketing data is obtained. By associating the stopping point sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger transport OD is finally obtained, realizing accurate identification of passenger transport OD, thereby accurately grasping the actual arrival location of passengers and providing technical support for the intelligent construction of urban transportation. Attached Figure Description

[0048] The present invention will be further described below with reference to the accompanying drawings and embodiments:

[0049] Figure 1 This is a schematic diagram illustrating the principle of passenger OD spatiotemporal distribution identification in this invention;

[0050] Figure 2 This is a schematic diagram of the GPS data fields for passenger buses according to the present invention;

[0051] Figure 3 This is a schematic diagram of the passenger transport route ticketing data fields of the present invention;

[0052] Figure 4 This is a schematic diagram of the passenger departure data field of the present invention. Detailed Implementation

[0053] The present invention will be further described below with reference to the accompanying drawings, as shown in the figures:

[0054] The present invention provides a method for identifying the spatiotemporal distribution of passenger OD (Original Departure Point) based on multi-source data fusion, comprising the following steps:

[0055] The GPS data of passenger buses is processed to obtain the stop sequence of passenger buses;

[0056] By correlating passenger bus route ticketing data with passenger departure data, the origin and destination sequence of the ticketing data can be obtained;

[0057] By associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, we obtain the spatiotemporal distribution data of passenger OD (Original Departure Point). OD data is a type of spatiotemporal distribution data that records passenger flow, describing the movement of people or goods from their origin (starting point) to their destination (ending point).

[0058] In this embodiment, in step S1, the sequence of stopping points for passenger buses is identified by processing the GPS data of the passenger buses, such as... Figure 2 As shown, the GPS data of passenger buses can be represented as <ID,X1,Y1,T1,S1;ID,X2,Y2,T2,S 2… >(ID represents the license plate number, X1 and Y1 are the GPS latitude and longitude coordinates returned by the vehicle, T1 represents the time when the GPS data was returned by the vehicle, S1 represents the instantaneous speed of the vehicle when the GPS data was returned, and so on. X1 and Y1 are another GPS latitude and longitude coordinates returned by the vehicle, etc.).

[0059] The GPS data of passenger buses is processed to obtain the sequence of bus stops, specifically including:

[0060] S11. Collect the first GPS data where the instantaneous vehicle speed is 0 throughout the day, filter out the second GPS data where the time points are continuous from the first GPS data, and calculate the duration T of the second GPS data where the vehicle speed is 0;

[0061] S12. Determine if the duration T exceeds the time threshold. If yes, use the data points corresponding to the latitude and longitude in the second GPS data as possible parking points, indicating that the vehicle's dwell time exceeds the time threshold, thus ruling out the influence of factors such as traffic lights. Proceed to the next step. If no, return to step S11. The time threshold can be set according to the actual working conditions, for example, a value of 5 minutes.

[0062] S13. Calculate the distance L between the possible parking point and its nearest service area, and determine whether the distance L is greater than the distance threshold. If so, the possibility that the vehicle is refueling or entering a highway service station can be ruled out. Then, the possible parking point is designated as the pre-parking point, and the process proceeds to the next step. If not, return to step S11. The distance threshold can be set according to the actual working conditions, for example, a value of 50 meters. The service area includes highway service stations and gas stations.

[0063] The distance L between the possible parking spot and its nearest service area is calculated using the following formula:

[0064] L=6371.0*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)];

[0065] Here, X1 and Y1 represent the longitude and latitude of potential parking points, and X2 and Y2 represent the longitude and latitude of service areas. The longitude and latitude of service areas can be obtained from the POI data of the service areas.

[0066] S14. Following steps S11-S13, the pre-parking points for each day within a set time period are obtained, resulting in a number of pre-parking points. Spatial clustering analysis is then performed on these pre-parking points to obtain several clusters. Clusters with more than a certain number of pre-parking points are considered valid clusters, and the center point of each valid cluster is designated as the target parking point. The set time period can be one month; the threshold can be 10 points. Clusters with fewer than 10 points are not considered valid clusters to exclude the influence of factors such as congestion. Specifically, the pre-parking points identified each day for one month are analyzed using spatial clustering methods. The spatial distance between clusters is set to 50 meters, meaning that parking points within 50 meters of each other can be considered as one cluster. The spatial clustering analysis uses existing spatial clustering methods, which will not be elaborated upon here.

[0067] S15. Sort the obtained target parking spots according to the order of parking time to obtain the parking spot sequence. <ID,X1,Y1,T1,SS1,COT1;…;X i Y i T i SS i COT i...>; where ID represents the passenger bus license plate number, X i With Y i T represents the longitude and latitude of parking point i. i SS represents the parking time at parking point i. i COT represents the duration of stay at parking point i. i This indicates the station sequence number corresponding to parking point i.

[0068] In this embodiment, in step S2, the association between passenger bus route ticketing data and passenger departure data is established to identify the origin and destination sequence of the ticketing data;

[0069] like Figure 3 As shown, the fields for passenger bus route ticketing data include: <ticket number, route number, departure date, bus time, bus number, origin station, route destination station, ticket purchase destination station, purchase method, purchase time>, such as... Figure 4 As shown, the fields for passenger departure data include <reporting sequence number, route number, company name, departure date, route number, license plate, departure time, origin station, and route destination station>.

[0070] By correlating passenger bus route ticketing data with passenger departure data, the origin-destination sequence of the ticketing data is obtained, specifically including:

[0071] The passenger bus route ticketing data is associated with the three fields of bus number, origin station, and route destination station in the passenger departure data. That is, the same bus number, same origin station, and same route destination station are used to obtain the association pair between the passenger bus route ticketing data and the passenger departure data. The license plate field of the passenger departure data in the association pair is mapped to the passenger bus route ticketing data, and the bus time of the passenger bus route ticketing data is updated according to the actual passenger departure data.

[0072] Based on the order of the waypoints, the waypoints of all ticket sales data for the same route are sorted to form a waypoint sequence for that route. <NAME1,COT1;…;NAME i COT i ;...>; where NAME i Indicates the name of the waypoint i, COT i Indicates the sequence number of the waypoint i;

[0073] By performing field association and adjustment on the waypoint sequence of a route, the origin and destination sequence of a single ticket sales data point can be obtained. <ROUTE,ID,NAME o COT o ,T O ,NAME d COT d >; where ROUTE represents the route number, ID represents the passenger bus license plate number, and NAME... oIndicates the departure station name, COT o Indicates the departure station sequence number, T O Indicates departure time, NAME d Indicates the arrival station name, COT d Indicates the arrival station sequence number.

[0074] NAME o and NAME d It's data inherent in the ticketing information; for example, when buying a ticket from location A to location B, it's A and B. (COT) d It is a sequence number based on the ticketing information. For example, if there is a train that goes from A to B and then to C, then the numbers for A, B, and C are 1, 2, and 3 respectively.

[0075] In this embodiment, step S3 involves associating the bus stop sequence with the origin-destination sequence of ticketing data to obtain passenger OD spatiotemporal distribution data, specifically including:

[0076] By linking and fusing data with the same license plate number and station sequence number, we can obtain the passenger's departure and arrival location names, latitude and longitude coordinates, and departure time, i.e., passenger OD spatiotemporal distribution data:

[0077] <ROUTE,ID,NAME o ,X o ,Y o COT o ,T O ,NAME d ,X d ,Y d COT d >;

[0078] Among them, X o With Y o Indicates the departure station name (NAME) o Longitude and latitude; X d With Y d Indicates the name of the arrival station. d The longitude and latitude. Table 1 shows an example of the spatiotemporal distribution data of passenger OD.

[0079] Table 1

[0080]

[0081] The present invention also relates to a passenger OD spatiotemporal distribution identification system based on multi-source data fusion. The system corresponds to the above-mentioned passenger OD spatiotemporal distribution identification method based on multi-source data fusion and can be understood as a system that implements the above method. The system includes a parking point sequence unit, a start-end point sequence unit, and a spatiotemporal distribution data unit.

[0082] The parking point sequence unit is used to process the GPS data of passenger buses to obtain the parking point sequence of passenger buses;

[0083] The origin-endpoint sequence unit is used to associate passenger bus route ticketing data with passenger departure data to obtain the origin-endpoint sequence of the ticketing data.

[0084] The spatiotemporal distribution data unit is used to associate the stop sequence of passenger buses with the origin and destination sequence of ticketing data to obtain the spatiotemporal distribution data of passenger OD.

[0085] This invention provides an objective and scientific method and system for identifying the spatiotemporal distribution of passenger OD (Original Location) traffic, enabling accurate identification of passenger OD and thus accurately determining the true arrival location of passengers, providing technical support for the intelligent construction of urban transportation.

[0086] Finally, it should be noted that the above embodiments are only used to illustrate the technical solutions of the present invention and are not intended to limit it. Although the present invention has been described in detail with reference to preferred embodiments, those skilled in the art should understand that modifications or equivalent substitutions can be made to the technical solutions of the present invention without departing from the spirit and scope of the technical solutions of the present invention, and all such modifications or substitutions should be covered within the scope of the claims of the present invention.

Claims

1. A method for identifying the spatiotemporal distribution of passenger origin-destination (OD) based on multi-source data fusion, characterized in that: Includes the following steps: The GPS data of passenger buses is processed to obtain the sequence of bus stops, specifically including: S11. Collect the first GPS data where the instantaneous vehicle speed is 0 throughout the day, filter out the second GPS data where the time points are continuous from the first GPS data, and calculate the duration T of the second GPS data where the vehicle speed is 0; S12. Determine whether the duration T exceeds the time threshold. If yes, use the data points corresponding to the latitude and longitude in the second GPS data as possible parking points and proceed to the next step. If no, return to step S11. S13. Calculate the distance L between the possible parking point and its nearest service area, and determine whether the distance L is greater than the distance threshold. If yes, then take the possible parking point as a pre-parking point and proceed to the next step. If no, return to step S11. S14. Following steps S11-S13, the pre-parking points for each day within the set time period are obtained, thus obtaining several pre-parking points. Spatial cluster analysis is performed on these pre-parking points to obtain several clusters. Clusters with more than a certain number of pre-parking points are taken as effective clusters, and the center point of each effective cluster is taken as the target parking point. S15. Sort the obtained target parking spots according to the order of parking time to obtain the parking spot sequence. <ID,X1,Y1,T1,SS1,COT1;…;X i Y i T i SS i COT i ...>; where ID represents the passenger bus license plate number, X i With Y i T represents the longitude and latitude of parking point i. i SS represents the parking time at parking point i. i COT represents the duration of stay at parking point i. i This indicates the station sequence number corresponding to parking point i; By correlating passenger bus route ticketing data with passenger departure data, the origin and destination sequence of the ticketing data can be obtained; By associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD is obtained.

2. The method for identifying the spatiotemporal distribution of passenger OD based on multi-source data fusion according to claim 1, characterized in that: The distance L between the possible parking spot and its nearest service area is calculated using the following formula: L=6371.0*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)]; Where X1 and Y1 represent the longitude and latitude of possible parking spots, and X2 and Y2 represent the longitude and latitude of service areas.

3. The method for identifying the spatiotemporal distribution of passenger OD based on multi-source data fusion according to claim 1, characterized in that: By correlating passenger bus route ticketing data with passenger departure data, the origin-destination sequence of the ticketing data is obtained, specifically including: The passenger bus route ticketing data is associated with the three fields of bus number, origin station, and route destination station in the passenger departure data to obtain the association pair between the passenger bus route ticketing data and the passenger departure data. The license plate field of the passenger departure data in the association pair is mapped to the passenger bus route ticketing data, and the bus time of the passenger bus route ticketing data is updated according to the actual passenger departure data. Based on the order of the waypoints, the waypoints of all ticket sales data for the same route are sorted to form a waypoint sequence for that route. <NAME1,COT1;…;NAME i COT i ;...>; where NAME i Indicates the name of the waypoint i, COT i Indicates the sequence number of the waypoint i; By performing field association and adjustment on the waypoint sequence of a route, the origin and destination sequence of a single ticket sales data point can be obtained. <ROUTE,ID,NAME o COT o ,T O ,NAME d COT d >; where ROUTE represents the route number, ID represents the passenger bus license plate number, and NAME... o Indicates the departure station name, COT o Indicates the departure station sequence number, T O Indicates departure time, NAME d Indicates the arrival station name, COT d Indicates the arrival station sequence number.

4. The method for identifying the spatiotemporal distribution of passenger OD based on multi-source data fusion according to claim 1, characterized in that: By associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD (Original Departure Point) is obtained, specifically including: By linking and fusing data with the same license plate number and station sequence number, we can obtain the passenger's departure and arrival location names, latitude and longitude coordinates, and departure time, i.e., passenger OD spatiotemporal distribution data: <ROUTE,ID,NAME o ,X o ,Y o ,COT o ,T O ,NAME d ,X d ,Y d ,COT d >; Among them, X o With Y o Indicates the departure station name (NAME) o Longitude and latitude; X d With Y d Indicates the name of the arrival station. d The longitude and latitude.

5. A passenger OD spatiotemporal distribution identification system based on multi-source data fusion, characterized in that: This includes parking point sequence units, origin-end point sequence units, and spatiotemporal distribution data units; The parking spot sequence unit is used to process the GPS data of passenger buses to obtain the parking spot sequence of passenger buses, specifically including: S11. Collect the first GPS data where the instantaneous vehicle speed is 0 throughout the day, filter out the second GPS data where the time points are continuous from the first GPS data, and calculate the duration T of the second GPS data where the vehicle speed is 0; S12. Determine whether the duration T exceeds the time threshold. If yes, use the data points corresponding to the latitude and longitude in the second GPS data as possible parking points and proceed to the next step. If no, return to step S11. S13. Calculate the distance L between the possible parking point and its nearest service area, and determine whether the distance L is greater than the distance threshold. If yes, then take the possible parking point as the pre-parking point and proceed to the next step. If no, return to step S11. S14. Following steps S11-S13, the pre-parking points for each day within the set time period are obtained, thus obtaining several pre-parking points. Spatial cluster analysis is performed on these pre-parking points to obtain several clusters. Clusters with more than a certain number of pre-parking points are taken as effective clusters, and the center point of the effective clusters is taken as the target parking point. S15. Sort the obtained target parking spots according to the order of parking time to obtain the parking spot sequence. <ID,X1,Y1,T1,SS1,COT1;…;X i Y i T i SS i COT i ...>; where ID represents the passenger bus license plate number, X i With Y i T represents the longitude and latitude of parking point i. i SS represents the parking time at parking point i. i COT represents the duration of stay at parking point i. i This indicates the station sequence number corresponding to parking point i; The origin-endpoint sequence unit is used to associate passenger bus route ticketing data with passenger departure data to obtain the origin-endpoint sequence of the ticketing data. The spatiotemporal distribution data unit is used to associate the stop sequence of passenger buses with the origin and destination sequence of ticketing data to obtain the spatiotemporal distribution data of passenger OD.

6. The passenger OD spatiotemporal distribution identification system based on multi-source data fusion according to claim 5, characterized in that: The distance L between the possible parking point and its nearest service area is calculated using the following formula: L=6371.0*arcos[cos(Y1)*cos(Y2)*cos(X1-X2)+sin(Y1)*sin(Y2)]; Where X1 and Y1 represent the longitude and latitude of possible parking spots, and X2 and Y2 represent the longitude and latitude of service areas.

7. The passenger OD spatiotemporal distribution identification system based on multi-source data fusion according to claim 5, characterized in that: By correlating passenger route ticketing data with passenger departure data, the origin-destination sequence of the ticketing data is obtained, specifically including: The passenger bus route ticketing data is associated with the three fields of bus number, origin station, and route destination station in the passenger departure data to obtain the association pair between the passenger bus route ticketing data and the passenger departure data. The license plate field of the passenger departure data in the association pair is mapped to the passenger bus route ticketing data, and the bus time of the passenger bus route ticketing data is updated according to the actual passenger departure data. Based on the order of the waypoints, the waypoints of all ticket sales data for the same route are sorted to form a waypoint sequence for that route. <NAME1,COT1;…;NAME i COT i ;...>; where NAME i Indicates the name of the waypoint i, COT i Indicates the sequence number of the waypoint i; By performing field association and adjustment on the waypoint sequence of a route, the origin and destination sequence of a single ticket sales data point can be obtained. <ROUTE,ID,NAME o COT o ,T O ,NAME d COT d >; where ROUTE represents the route number, ID represents the passenger bus license plate number, and NAME... o Indicates the departure station name, COT o Indicates the departure station sequence number, T O Indicates departure time, NAME d Indicates the arrival station name, COT d This indicates the arrival station sequence number.

8. The passenger OD spatiotemporal distribution identification system based on multi-source data fusion according to claim 5, characterized in that: By associating the stop sequence of passenger buses with the origin-destination sequence of ticketing data, the spatiotemporal distribution data of passenger OD (Original Departure Point) is obtained, specifically including: By linking and fusing data with the same license plate number and station sequence number, we can obtain the passenger's departure and arrival location names, latitude and longitude coordinates, and departure time, i.e., passenger OD spatiotemporal distribution data: <ROUTE,ID,NAME o ,X o ,Y o ,COT o ,T O ,NAME d ,X d ,Y d ,COT d >; Among them, X o With Y o Indicates the departure station name (NAME) o Longitude and latitude; X d With Y d Indicates the name of the arrival station. d The longitude and latitude.

Images