An autonomous construction method for the supply-demand matrix of bus line networks based on multi-source data

Abstract

The present invention discloses an autonomous construction method for the supply-demand matrix of a bus network based on multi-source data. The method includes: matching the route names according to the GPS data of bus vehicles and the GPS data of bus stops to generate a bus arrival schedule; calculating the departure frequency of buses according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and the preset passenger capacity of buses; matching the route names and the card swiping times according to the bus arrival schedule and the IC card data, obtaining the boarding stops and inferring the alighting stops, and constructing an IC demand matrix of the bus network according to the route names, the card swiping times, the boarding stops and the inferred alighting stops; extracting the origin-destination base stations of users according to the mobile phone signaling data, and constructing a CSD demand matrix of the bus network after distributing the passenger flow demand through the distance mapping relationship. The present invention improves the accuracy and broadens the scope of application, and can be widely applied to the technical field of traffic data processing.

Description

Technical Field

[0001] The present invention relates to the technical field of traffic data processing, and in particular to an autonomous construction method for a bus network supply-demand matrix based on multi-source data. Background Art

[0002] Accurately grasping the operation characteristics of the bus network and the demand characteristics of residents' travel is of great significance for optimizing the urban bus network, improving the urban traffic environment, and alleviating urban traffic congestion. At present, there are mainly three ways to obtain the urban residents' travel demand matrix: traditional traffic survey methods, GPS data-based methods, and IC card data-based methods. Traditional traffic survey methods can obtain rich residents' travel information, but they have a long survey cycle, high cost, and small sample size, with great limitations. GPS data has rich spatio-temporal information, which can effectively make up for the defects of traditional surveys, but it only reflects the operation information of bus vehicles and fails to well reflect the travel information of passengers. IC card data records the travel time information of passengers and can analyze the spatio-temporal characteristics of passengers' travel in combination with GPS data, but it cannot obtain the characteristics of potential bus travel users. With the rapid development of the Internet and communication technologies, the popularity rate of mobile phones is getting higher and higher, and the resulting cellular signaling data (CSD) has the advantages of a large sample size, short sampling period, long observation period, strong followability, etc., and can effectively obtain the travel characteristics of potential bus users, which has received wide attention in the traffic field. Summary of the Invention

[0003] In view of this, an embodiment of the present invention provides an autonomous construction method for a bus network supply-demand matrix based on multi-source data, which is highly accurate and has a wide application range.

[0004] One aspect of the present invention provides an autonomous construction method for a bus network supply-demand matrix based on multi-source data, including:

[0005] Matching the line names according to the bus vehicle GPS data and the bus stop GPS data to generate a bus arrival schedule;

[0006] Calculating the departure frequency of the bus according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the bus;

[0007] Matching the line names and the card swiping times according to the bus arrival schedule and the IC card data, obtaining the boarding stops and inferring the alighting stops, and constructing an IC demand matrix of the bus network according to the line names, the card swiping times, the boarding stops, and the inferred alighting stops;

[0008] Extract the starting and ending base stations of users according to mobile phone signaling data. After allocating passenger flow demands through distance mapping relationships, construct the CSD demand matrix of the bus network.

[0009] Optionally, the matching of the line names according to the bus vehicle GPS data and the bus stop GPS data to generate the bus arrival schedule includes:

[0010] Calculate the distances between the GPS trajectory points of the bus vehicles on the target line and each stop of the line, and use the method of GPS data fusion to generate the bus arrival schedule;

[0011] When the GPS trajectory of the bus vehicle does not match the location of the stops on the line, use the DBSCAN spatio-temporal clustering method to generate the bus arrival schedule.

[0012] Optionally, the calculation of the departure frequency of the buses according to the bus arrival schedule, and the construction of the supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the buses include:

[0013] Calculate the peak-hour departure frequency of each line according to the bus arrival schedule;

[0014] According to the departure frequency, combined with the preset passenger capacity of the buses, calculate the supply between stops on each line;

[0015] Add up the supplies between stops on all lines to autonomously construct the supply matrix of the bus network.

[0016] Optionally, the calculation formula for the departure frequency is:

[0017]

[0018] where F i is the peak-hour departure frequency of line i; Bus j is the jth bus departing from the first stop of the line during the peak hour; the peak hours are 7:00 - 9:00 and 17:00 - 19:00;

[0019] The calculation formula for the supply between stops on each line is:

[0020]

[0021] where is the supply from stop m to stop n on the ith bus line, C is the passenger capacity of the bus, and N is the number of bus stops on the line;

[0022] The calculation formula for the supply matrix is:

[0023]

[0024] Among them, l is the number of lines passing through station m and station n.

[0025] Optionally, after matching the line name and the card swiping time according to the bus arrival schedule and the IC card data, obtaining the boarding station and inferring the alighting station, according to the line name, the card swiping time, the boarding station and the inferred alighting station, constructing an IC demand matrix of the bus network, including:

[0026] Matching the line name according to the bus arrival schedule and the IC card data;

[0027] Based on the time rule, matching the IC card swiping time and the bus arrival schedule to obtain the boarding station. Among them, the boarding stations of the card swiping records with the swiping time between station m and station m + 1 are all attributed to station m;

[0028] Integrating the travel chain method, the subway line data and the historical travel records to infer the alighting station.

[0029] Optionally, the integrating the travel chain method, the subway line data and the historical travel records to infer the alighting station includes:

[0030] The process of inferring the alighting station based on the travel chain method includes: inferring the alighting station of the user's previous bus trip as the boarding station of the next bus trip, or inferring the alighting station of the user's previous bus trip as the nearest station within the walking transfer distance near the boarding station of the next bus trip, and sorting the card swiping data of all days of the user in chronological order to infer the alighting station;

[0031] The process of inferring the alighting station based on the subway line data includes: if the next boarding station of the user is within the transfer distance range near the subway station, inferring that the user travels by bus - subway - bus transfer mode, and inferring the alighting station as the bus station near the intersection of the current subway line and the bus line that cannot be matched;

[0032] The process of inferring the alighting station based on the historical travel records includes: merging the alighting stations inferred based on the travel chain method and the alighting stations inferred based on the subway line data, extracting the records with multiple same trips among them as the historical record set, and matching the historical record set with the unrecognized data to infer the alighting station.

[0033] Optionally, after extracting the starting and ending base stations of the user according to the mobile phone signaling data, and allocating the passenger flow demand through the distance mapping relationship, constructing a CSD demand matrix of the bus network, including:

[0034] After cleaning the CSD data, extract the starting and ending base stations of users to form a passenger flow OD demand matrix between base stations;

[0035] Establish a distance mapping relationship between bus stops within the preset coverage range of a base station and the current base station, allocate the passenger flow OD demand between base stations to the bus stops, and autonomously construct a CSD demand matrix for the bus network.

[0036] Another aspect of the embodiments of the present invention also provides an apparatus for autonomously constructing a supply-demand matrix of a bus network based on multi-source data, including:

[0037] A first module for matching route names according to bus vehicle GPS data and bus stop GPS data to generate a bus arrival schedule;

[0038] A second module for calculating the departure frequency of buses according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and a preset passenger capacity of the buses;

[0039] A third module for matching route names and card swiping times according to the bus arrival schedule and IC card data, obtaining the boarding station and inferring the alighting station, and constructing an IC demand matrix of the bus network according to the route name, the card swiping time, the boarding station, and the inferred alighting station;

[0040] A fourth module for extracting the starting and ending base stations of users according to mobile phone signaling data, and constructing a CSD demand matrix of the bus network after allocating the passenger flow demand through the distance mapping relationship.

[0041] Another aspect of the embodiments of the present invention also provides an electronic device, including a processor and a memory;

[0042] The memory is used to store a program;

[0043] The processor executes the program to implement the method as described above.

[0044] Another aspect of the embodiments of the present invention also provides a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the method as described above.

[0045] The embodiments of the present invention also disclose a computer program product or a computer program. The computer program product or the computer program includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. A processor of a computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions to enable the computer device to execute the method as described above.

[0046] Embodiments of the present invention match route names based on bus vehicle GPS data and bus stop GPS data to generate a bus arrival schedule; calculate the departure frequency of buses according to the bus arrival schedule, and construct a supply matrix of the bus network according to the departure frequency and a preset passenger capacity of the buses; match the route name and the card swiping time according to the bus arrival schedule and IC card data, and after obtaining the boarding stop and inferring the alighting stop, construct an IC demand matrix of the bus network according to the route name, the card swiping time, the boarding stop and the inferred alighting stop; extract the origin and destination base stations of users from mobile phone signaling data, and construct a CSD demand matrix of the bus network after allocating passenger flow demands through a distance mapping relationship. The present invention improves accuracy and broadens the scope of application, and can be widely applied to the technical field of traffic data processing. Description of the Drawings

[0047] In order to more clearly illustrate the technical solutions in the embodiments of the present application, the following will briefly introduce the drawings required for the description of the embodiments. Obviously, the following drawings are only some embodiments of the present application. For those of ordinary skill in the art, other drawings can be obtained based on these drawings without creative efforts.

[0048] Figure 1 It is a flowchart of the steps of the embodiments of the present invention;

[0049] Figure 2 It is a flowchart for generating a bus arrival schedule provided by the embodiments of the present invention;

[0050] Figure 3 It is a flowchart for generating a bus arrival schedule by using a method of GPS data fusion provided by the embodiments of the present invention;

[0051] Figure 4 It is a flowchart for generating a bus arrival schedule by using a method of DBSCAN spatio-temporal clustering provided by the embodiments of the present invention;

[0052] Figure 5 It is a flowchart for autonomously constructing a supply matrix of the bus network provided by the embodiments of the present invention;

[0053] Figure 6 It is a flowchart for autonomously constructing an IC demand matrix of the bus network provided by the embodiments of the present invention;

[0054] Figure 7 It is a flowchart for obtaining the boarding stop of IC card data based on time rules provided by the embodiments of the present invention;

[0055] Figure 8(a) is a flowchart for fusing multi-source data to infer the alighting stop of IC card data based on the travel chain, combined with the subway line and based on historical travel records provided by the embodiments of the present invention;

[0056] Figure 8(b) is a flowchart of inferring the alighting stop based on the travel chain hypothesis provided by an embodiment of the present invention;

[0057] Figure 8(c) is a flowchart of inferring the alighting stop by combining subway line stations provided by an embodiment of the present invention;

[0058] Figure 8(d) is a flowchart of inferring the alighting stop based on historical travel records provided by an embodiment of the present invention;

[0059] Figure 9 It is a flowchart of the CSD demand matrix for autonomously constructing a bus network provided by an embodiment of the present invention;

[0060] Figure 10 It is a schematic diagram of extracting bus travel OD from mobile phone signaling data provided by an embodiment of the present invention. Detailed implementation manners

[0061] In order to make the objectives, technical solutions and advantages of the present application clearer, the present application will be further described in detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are only used to explain the present application and are not used to limit the present application.

[0062] In view of the problems existing in the prior art, one aspect of the present invention provides a method for autonomously constructing a supply-demand matrix of a bus network based on multi-source data, including:

[0063] Matching the line names according to the bus vehicle GPS data and the bus stop GPS data to generate a bus arrival schedule;

[0064] Calculating the departure frequency of the buses according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the buses;

[0065] Matching the line names and the card swiping times according to the bus arrival schedule and the IC card data, obtaining the boarding stops and inferring the alighting stops, and constructing an IC demand matrix of the bus network according to the line names, the card swiping times, the boarding stops and the inferred alighting stops;

[0066] Extracting the origin and destination base stations of the users according to the mobile phone signaling data, and constructing a CSD demand matrix of the bus network after allocating the passenger flow demand through the distance mapping relationship.

[0067] Optionally, the matching the line names according to the bus vehicle GPS data and the bus stop GPS data to generate a bus arrival schedule includes:

[0068] Calculate the distances between the GPS trajectory points of the buses on the target route and each stop of the route, and use the method of GPS data fusion to generate the bus arrival schedule;

[0069] When the GPS trajectory of the bus does not match the stop positions of the route it is on, use the DBSCAN spatio-temporal clustering method to generate the bus arrival schedule.

[0070] Optionally, calculating the departure frequency of the buses according to the bus arrival schedule, and constructing the supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the buses, includes:

[0071] Calculate the peak-hour departure frequency of each route according to the bus arrival schedule;

[0072] According to the departure frequency, combined with the preset passenger capacity of the buses, calculate the supply between stops on each route;

[0073] Add up the supplies between stops on all routes to autonomously construct the supply matrix of the bus network.

[0074] Optionally, the calculation formula for the departure frequency is:

[0075]

[0076] where F i is the peak-hour departure frequency of route i; Bus j is the j-th bus departing from the first stop of this route during the peak hour; the peak hours are 7:00 - 9:00 and 17:00 - 19:00;

[0077] The calculation formula for the supply between stops on each route is:

[0078]

[0079] where is the supply from stop m to stop n on the i-th bus route, C is the passenger capacity of the bus, and N is the number of bus stops on this route;

[0080] The calculation formula for the supply matrix is:

[0081]

[0082] where l is the number of routes passing through stops m and n.

[0083] Optionally, after matching the bus arrival schedule and IC card data to obtain the route name and card swiping time, and acquiring the boarding station and inferred alighting station, an IC demand matrix of the bus network is constructed according to the route name, the card swiping time, the boarding station, and the inferred alighting station, including:

[0084] Match the route name according to the bus arrival schedule and IC card data;

[0085] Based on the time rule, match the IC card swiping time and the bus arrival schedule to obtain the boarding station. Among them, the boarding stations of the card swiping records between station m and station m + 1 are all attributed to station m;

[0086] Integrate the travel chain method, subway line data, and historical travel records to infer the alighting station.

[0087] Optionally, the integration of the travel chain method, subway line data, and historical travel records to infer the alighting station includes:

[0088] The process of inferring the alighting station based on the travel chain method includes: inferring the alighting station of the user's previous bus trip as the boarding station of the next bus trip, or inferring the alighting station of the user's previous bus trip as the nearest station within the walking transfer distance near the boarding station of the next bus trip, and sorting the card swiping data of all days of the user in chronological order to infer the alighting station;

[0089] The process of inferring the alighting station based on the subway line data includes: if the next boarding station of the user is within the transfer distance range near the subway station, infer that the user travels by bus - subway - bus transfer mode, and infer the alighting station as the bus stop near the intersection of the current subway line and the bus line that cannot be matched;

[0090] The process of inferring the alighting station based on the historical travel records includes: merging the alighting stations inferred based on the travel chain method and the alighting stations inferred based on the subway line data, extracting the records with multiple identical trips as the historical record set, and matching the historical record set with the unrecognized data to infer the alighting station.

[0091] Optionally, after extracting the origin and destination base stations of the user from the mobile signaling data and allocating the passenger flow demand through the distance mapping relationship, a CSD demand matrix of the bus network is constructed, including:

[0092] After cleaning the CSD data, extract the origin and destination base stations of the user to form a passenger flow OD demand matrix between the base stations;

[0093] Establish the distance mapping relationship between bus stops and the current base station within the preset coverage range of the base station, allocate the passenger flow OD demand between base stations to the bus stops, and autonomously construct the CSD demand matrix of the bus network.

[0094] Another aspect of the embodiments of the present invention further provides an apparatus for autonomously constructing the supply-demand matrix of a bus network based on multi-source data, including:

[0095] The first module is used to match the line names according to the bus vehicle GPS data and the bus stop GPS data, and generate the bus arrival schedule.

[0096] The second module is used to calculate the departure frequency of the buses according to the bus arrival schedule, and construct the supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the buses.

[0097] The third module is used to match the line names and the card swiping times according to the bus arrival schedule and the IC card data, obtain the boarding stops and infer the alighting stops, and construct the IC demand matrix of the bus network according to the line names, the card swiping times, the boarding stops and the inferred alighting stops.

[0098] The fourth module is used to extract the starting and ending base stations of the users according to the mobile phone signaling data, and construct the CSD demand matrix of the bus network after allocating the passenger flow demand through the distance mapping relationship.

[0099] Another aspect of the embodiments of the present invention further provides an electronic device, including a processor and a memory;

[0100] The memory is used to store programs;

[0101] The processor executes the program to implement the method as described above.

[0102] Another aspect of the embodiments of the present invention further provides a computer-readable storage medium, where the storage medium stores a program, and the program is executed by a processor to implement the method as described above.

[0103] The embodiments of the present invention also disclose a computer program product or a computer program, which includes computer instructions, and the computer instructions are stored in a computer-readable storage medium. The processor of the computer device can read the computer instructions from the computer-readable storage medium, and the processor executes the computer instructions, so that the computer device executes the method as described above.

[0104] The following will describe the specific implementation process of the present invention in detail with reference to the accompanying drawings of the specification:

[0105] As shown in the process Figure 1As shown in the figure, a method for autonomously constructing a supply-demand matrix of an urban bus network based on multi-source data according to the present invention includes the following steps:

[0106] Step S1: Match the line names according to the bus vehicle GPS data and the bus stop GPS data, and generate a bus arrival schedule.

[0107] Step S2: Calculate the departure frequency according to the bus arrival schedule, set a certain passenger capacity of the bus, and autonomously construct the supply matrix of the bus network;

[0108] Step S3: Match the line names and the card swiping times according to the bus arrival schedule and the IC card data, obtain the boarding stops and infer the alighting stops, and autonomously construct the IC demand matrix of the bus network;

[0109] Step S4: Extract the origin and destination between user base stations according to the mobile phone signaling data, allocate the passenger flow demand through the distance mapping relationship, and autonomously construct the CSD demand matrix of the bus network.

[0110] In the above step S1, matching the line names according to the bus vehicle GPS data and the bus stop GPS data and generating a bus arrival schedule specifically includes the following steps:

[0111] Step 101: As shown in the process Figure 2 input the bus GPS Bus data and the GPS of the bus line stops Line data on a certain day, group the GPS Bus data by line name and vehicle number, match the GPS Bus with the line name in the GPS Line If the match is successful, use the method of GPS data fusion to generate a bus arrival schedule; for the mismatches caused by temporary scheduling, construction detours, etc., use the DBSCAN spatio-temporal clustering method to generate a bus arrival schedule.

[0112] Step 102: In the above step 101, the method of using GPS data fusion to generate a bus arrival schedule, as shown in the process Figure 3 taking the GPS trajectory of the bus Bus1 operating on the line Line1 on a certain day as an example, input the bus stops on the line Line1 and the bus vehicle data, calculate the distance from the Line1 terminal stations, judge the running direction of Bus1, extract all the bus stops in a certain direction calculate the distance from the bus vehicle and take the one with the smallest distance The corresponding time is taken as the arrival time of Bus1 at this station, and the arrival time table of the bus vehicle Bus1 on Line1 is obtained. By performing this operation in a loop for all vehicles on all lines, the arrival time tables of all vehicles on all lines can be autonomously obtained.

[0113] Step 103. Generate the bus arrival time table using the DBSCAN spatio-temporal clustering method in Step 101 above. As shown in the process Figure 4 shown, first input the GPS data of bus vehicles and the GPS data of bus stops on a certain day, group the GPS by vehicle number Bus Bus to obtain the GPS trajectory sequence of each vehicle: Line Use the DBSCAN algorithm to cluster BuS and merge adjacent stop points by averaging the longitude and latitude to obtain j several stop points of Search for bus stops in GPS with a radius of D = 50m centered on each stop point. If a qualified stop point is found, the nearest stop point is taken as the arrival station of vehicle Bus ; otherwise, it means that this trajectory cluster may be a stop point caused by congestion during the vehicle's driving. Calculate the start time of each as the arrival time of Bus R at each stop point. By performing this operation in a loop for all vehicles on all lines, the arrival time tables of all vehicles on all lines can be autonomously obtained. Line In step S2, according to the bus arrival time table, calculate the departure frequency, set a certain bus passenger capacity, and autonomously construct the supply matrix of the bus network, which specifically includes the following steps: j Step 201. As shown in the process shown, input the arrival time tables A of all vehicles on all lines, extract the arrival time tables of all vehicles Bus j on a certain line Line

[0114] Sort them in chronological order.

[0115] Step 202. Calculate the peak-hour departure frequency Figure 5 of Line i as shown in Equation (1): j where, is the line Line

[0116] Step 202. Calculate the peak-hour departure frequency i of Line as shown in Equation (1):

[0117]

[0118] Among them, is the line Linei Peak-hour departure frequency (vehicles / h); Bus j is the jth bus departing from the first station during peak hours; peak hours are from 7:00 - 9:00 and 17:00 - 19:00.

[0119] Step 203: Set the passenger capacity of each bus to C = 50, and calculate the supply i between stop m and stop n on line Line as shown in Equation (2):

[0120]

[0121] Step 204: Calculate for all lines to autonomously obtain the supply matrix S between stops of the bus network mn as shown in Equation (3):

[0122]

[0123] where l is the number of lines passing through stops m and n.

[0124] In step S3, according to the bus arrival schedule and IC card data, match the line name and swiping time, obtain the boarding stop and infer the alighting stop, and autonomously construct the IC demand matrix of the bus network, which specifically includes the following steps:

[0125] Step 301: As shown in the process Figure 6 input the IC card data of a certain day, sort by line name and swiping time. Input the arrival schedule A of all vehicles on all lines. Extract the arrival schedule and IC card data

[0126] Step 302: Match the boarding stop based on time rules. As shown in the process Figure 7 according to vehicle number Bus j extract the arrival schedule of this vehicle Match the swiping time with If the arrival time at stop m is between the arrival time at stop m + 1 then record the boarding stop as m. Perform time matching on all IC card data to obtain the boarding stops of all IC card data.

[0127] Step 303: Infer the alighting station of the IC card data by fusing multi-source data based on the travel chain hypothesis, combined with subway line stations and the method based on historical travel records, as shown in the flowchart of Figure 8(a).

[0128] Step 304: Infer the alighting station using the method based on the travel chain hypothesis in Step 303 above. Assume: ① The alighting station of the user's previous bus trip is the boarding station of the next bus trip; ② The alighting station of the user's previous bus trip is the nearest station within the acceptable walking transfer distance D near the boarding station of the next bus trip. The process is shown in Figure 8(b). First, input the user User i The set of all-day card swiping records Record, and extract a certain card swiping record Record j and the corresponding line name line and station sequence line station , extract Record j+1 The corresponding boarding station station j+1 . Determine whether station j+1 is in the station sequence line station . If it is, obtain the alighting station based on the above assumption ①; otherwise, calculate the distance distance between the boarding station station j+1 and all stations in the station sequence line station . If the minimum value is less than the acceptable walking transfer distance D, obtain the alighting station based on the above assumption ②.

[0129] Step 305: Infer the alighting station using the method combined with subway line stations in Step 303 above. If the next boarding station of a certain user is within the acceptable walking transfer distance D near the subway station, it is considered that the user may adopt the bus - subway - bus travel mode. The process is shown in Figure 8(c). Input the user User i The remaining unrecognized card swiping records Record, and extract the card swiping record Record j+1 and the corresponding card swiping time time j+1 . If time j+1 is within the subway operation time period, calculate the distance distance1 between the boarding station of the card swiping record Record j+1 and all subway stations Subway station . If the minimum value is less than the acceptable walking transfer distance D, extract the corresponding line of the card swiping record Record j and the station sequence line after the current boarding station station , calculate the distance between all subway stations Subway station and the station sequence line stationThe distance distance2. If its minimum value is less than the acceptable walking transfer distance D, the station corresponding to the minimum value is recorded as the swiping record Record j of the alighting station

[0130] Step 306: Infer the alighting station using the method based on historical travel records in Step 303 above. Merge the records of the alighting stations identified by the travel chain hypothesis method and the method combining subway lines, and extract the records with multiple identical trips as the historical record set. The process is shown in Figure 8(d). Input the swiping record Record of the identified alighting station IF , group it by user ID, line name, running direction, and alighting station, and extract the records with multiple trips Record g , and find the record g with the highest frequency in each group Record h to form the historical record set Record i . Input the remaining unrecognized Record of the user. Match Record according to the boarding station, line name, and direction information h to obtain the alighting station

[0131] Step 307: According to the matched boarding station and the inferred alighting station, count the travel OD between stations, and autonomously obtain the IC demand matrix of the bus network

[0132] In the above Step S4, the origin and destination between user base stations are extracted from the mobile phone signaling data, and the passenger flow demand is allocated through the distance mapping relationship to autonomously construct the CSD demand matrix of the bus network, which specifically includes the following steps

[0133] Step 401: As shown in the process Figure 9 , input the mobile phone signaling data CSD, base station GPS Base data, and bus stop GPS Bus data of a certain day, and clean the abnormal CSD data, including sparse data, same location data, drift data, and ping-pong data

[0134] Step 402: Group the CSD by user ID, sort it in chronological order, extract the CSD trajectory of the user's travel, classify the user's travel mode, and extract the signaling trajectory of bus travel users

[0135] Step 403: Extract the starting base station O and the ending base station D of the signaling trajectory. As shown in Figure 10 , map the user's travel OD to the base station, and obtain the travel demand matrix OD of the user between base stations Base .

[0136] Step 404: Extract a base station Base i All bus stops within 800m coverage, such as Figure 10 As shown, calculation and The distance R j , according to R j Inversely proportional relationship, as shown in formula (4), the demand OD between base stations Base Demand OD allocated to sites Station , the CSD demand matrix of the bus network can be obtained autonomously.

[0137]

[0138] In summary, compared with the prior art, the present invention has the following advantages:

[0139] 1) The present invention fully considers the deep fusion of multi-source sensory data and proposes a method for autonomously calculating the supply matrix of the bus network. The bus arrival schedule is generated using the GPS data fusion and DBSCAN spatiotemporal clustering method. By setting a certain bus passenger capacity, the supply matrix of the bus network can be further autonomously calculated, which helps to more accurately grasp the operating characteristics and status of the bus network.

[0140] 2) The present invention fully considers the characteristics of multi-source perception data, and uses a method based on time rules, a method based on traditional travel chains, a method combined with subway lines, and a method based on historical travel records to achieve boarding station matching and alighting station inference for IC card data, and can further autonomously construct an IC demand matrix for the bus network.

[0141] 3) The present invention fully considers the advantages of mobile phone signaling data in urban transportation applications, and proposes an autonomous construction method for the urban bus line network demand matrix based on mobile phone signaling data, which can effectively make up for the defect that traditional methods cannot tap the potential bus travel demand, and help to obtain the travel characteristics of potential users, so as to guide traffic management and decision makers to carry out policy planning and improve the attractiveness and service level of urban public transportation.

[0142] In some alternative embodiments, the functions / operations recited in the block diagrams may not occur in the order presented in the operational illustrations. For example, depending on the functions / operations involved, two blocks shown in succession may actually be executed substantially simultaneously or the blocks may sometimes be executed in the reverse order. Further, the embodiments presented and described in the flowcharts of the present invention are provided by way of example in order to provide a more thorough understanding of the technology. The disclosed methods are not limited to the operations and logical flows presented herein. Alternative embodiments are contemplated in which the order of various operations is altered and in which sub-operations described as part of a larger operation are executed independently.

[0143] Moreover, although the present invention has been described in the context of functional modules, it should be understood that, unless otherwise stated to the contrary, one or more of the described functions and / or features may be integrated in a single physical device and / or software module, or one or more functions and / or features may be implemented in separate physical devices or software modules. It should also be understood that a detailed discussion of the actual implementation of each module is not necessary for an understanding of the present invention. Rather, given the attributes, functions, and internal relationships of the various functional modules in the devices disclosed herein, the actual implementation of the modules will be understood within the ordinary skill of an engineer. Thus, those of ordinary skill in the art will be able to implement the present invention as set forth in the claims without undue experimentation. It should also be understood that the particular concepts disclosed are merely illustrative and not intended to limit the scope of the present invention, which scope is determined by the full scope of the appended claims and their equivalents.

[0144] If the described functions are implemented in the form of software functional units and sold or used as independent products, they may be stored in a computer-readable storage medium. Based on such understanding, the technical solution of the present invention, in essence or the part that contributes to the prior art, or a part of the technical solution, may be embodied in the form of a software product stored in a storage medium, including several instructions for causing a computer device (which may be a personal computer, a server, or a network device, etc.) to execute all or part of the steps of the methods described in the various embodiments of the present invention. The foregoing storage medium includes: various media that can store program codes, such as a USB flash drive, a removable hard disk, a read-only memory (ROM), a random access memory (RAM), a magnetic disk, or an optical disc.

[0145] The logic and / or steps represented in the flowchart or otherwise described herein can, for example, be considered as a definitional sequence of executable instructions for implementing logical functions, and can be embodied in any computer-readable medium for use by or in connection with an instruction execution system, apparatus, or device, such as a computer-based system, a system including a processor, or other systems that can fetch and execute instructions from the instruction execution system, apparatus, or device. As used in this specification, a "computer-readable medium" can be any device that can contain, store, communicate, propagate, or transport the program for use by or in connection with the instruction execution system, apparatus, or device.

[0146] More specific examples (a non-exhaustive list) of computer-readable media include the following: an electrical connection portion having one or more wirings (electronic device), a portable computer diskette (magnetic device), a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber device, and a portable compact disc read-only memory (CDROM). Additionally, the computer-readable medium can even be paper or other suitable media on which the program can be printed, as the program can be obtained electronically, for example, by optically scanning the paper or other media, followed by editing, interpretation, or otherwise processing as appropriate, and then storing it in a computer memory.

[0147] It should be understood that various parts of the present invention can be implemented by hardware, software, firmware, or a combination thereof. In the above-described embodiments, multiple steps or methods can be implemented by software or firmware stored in a memory and executed by a suitable instruction execution system. For example, if implemented in hardware, as in another embodiment, any one or a combination of the following techniques well known in the art can be used: discrete logic circuits having logic gate circuits for implementing logical functions on data signals, application specific integrated circuits having appropriate combinational logic gate circuits, programmable gate arrays (PGAs), field programmable gate arrays (FPGAs), and the like.

[0148] In the description of this specification, the description with reference to the terms "one embodiment", "some embodiments", "example", "specific example", or "some examples", etc. means that the specific features, structures, materials, or characteristics described in connection with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic representations of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials, or characteristics described can be combined in any one or more embodiments or examples in a suitable manner.

[0149] Although embodiments of the present invention have been shown and described, those of ordinary skill in the art can understand that various changes, modifications, substitutions, and variations can be made to these embodiments without departing from the principles and spirit of the present invention. The scope of the present invention is defined by the claims and their equivalents.

[0150] The above has specifically described the preferred embodiments of the present invention, but the present invention is not limited to the described embodiments. Those skilled in the art can also make various equivalent deformations or substitutions without violating the spirit of the present invention, and these equivalent deformations or substitutions are all included within the scope defined by the claims of this application.

Claims

1. An autonomous construction method for the supply-demand matrix of a bus network based on multi-source data, characterized in that, Including: Matching the route name based on the GPS data of bus vehicles and the GPS data of bus stops, and generating a bus arrival schedule; Calculating the departure frequency of buses according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and the preset passenger capacity of buses; Constructing an IC demand matrix of the bus network according to the route name, the card swiping time, the boarding stop, and the inferred alighting stop; Extracting the origin and destination base stations of users from the mobile signaling data, and constructing a CSD demand matrix of the bus network after allocating the passenger flow demand through the distance mapping relationship; Among them, the constructing a CSD demand matrix of the bus network by extracting the origin and destination base stations of users from the mobile signaling data and allocating the passenger flow demand through the distance mapping relationship includes: After cleaning the CSD data, extracting the origin and destination base stations of users to form a passenger flow OD demand matrix between base stations; Specifically, after cleaning the CSD data, the CSD data is grouped by user ID, sorted in chronological order, the CSD trajectory of user travel is extracted, the travel mode of the user is divided, and the signaling trajectory of the user is extracted; the starting base station O and the ending base station D of the signaling trajectory are extracted, the travel OD of the user is mapped to the base station, and the travel demand matrix OD between base stations of the user is obtained Base As the passenger flow OD demand matrix; Establishing a distance mapping relationship between the bus stops within the preset coverage range of the base station and the current base station, allocating the passenger flow OD demand between the base stations to the bus stops, and autonomously constructing a CSD demand matrix of the bus network; Specifically, extract base stations Base i All bus stops station within the preset coverage area, calculate the GPS of each base station Basei and the GPS of each bus stop Busj to obtain the distance R j . According to R j , distribute the passenger flow demand OD between base stations according to the inverse ratio relationship Base to the demand OD between stations station , and autonomously obtain the CSD demand matrix of the bus network.

2. The autonomous construction method of the bus network supply-demand matrix based on multi-source data according to claim 1, wherein, The matching the route name based on the GPS data of bus vehicles and the GPS data of bus stops, and generating a bus arrival schedule includes: Calculating the distances between the GPS track points of the bus vehicles on the target route and the stations of each route, and using the GPS data fusion method to generate a bus arrival schedule; When the GPS track of the bus vehicle does not match the location of the stations on the route, using the DBSCAN spatio-temporal clustering method to generate a bus arrival schedule.

3. A method for autonomously constructing a bus network supply-demand matrix based on multi-source data according to claim 1, characterized in that The calculating the departure frequency of buses according to the bus arrival schedule, and constructing a supply matrix of the bus network according to the departure frequency and the preset passenger capacity of buses includes: Calculating the peak-hour departure frequency of each route according to the bus arrival schedule; According to the departure frequency, combining the preset passenger capacity of buses, calculating the supply between the stations on each route; Adding up the supplies between the stations of all routes, and autonomously constructing a supply matrix of the bus network.

4. A method for autonomously constructing a supply-demand matrix of a bus network based on multi-source data according to claim 3, characterized in that, The calculation formula of the departure frequency is: Among them, F i is the peak-hour departure frequency of line i; Bus j is the jth bus departing from the first station during the peak hours; the peak hours are from 7:00 - 9:00 and 17:00 - 19:00; The calculation formula of the supply between the stations on each route is: Among them, is the supply from stop m to stop n on the i-th bus line, C is the passenger capacity of the bus, and N is the number of bus stops on this line; The calculation formula of the supply matrix is: Among them, l is the number of routes passing through station m and station n.

5. A method for autonomously constructing a bus network supply-demand matrix based on multi-source data according to claim 1, characterized in that The constructing an IC demand matrix of the bus network according to the route name, the card swiping time, the boarding stop, and the inferred alighting stop after matching the route name and the card swiping time according to the bus arrival schedule and the IC card data, and obtaining the boarding stop and the inferred alighting stop includes: Matching the route name according to the bus arrival schedule and the IC card data; Based on the time rule, matching the IC card swiping time and the bus arrival schedule to obtain the boarding stop, where the boarding stops of the card swiping records with the swiping time between station m and station m + 1 are all attributed to station m; Fusing the travel chain method, the subway line data, and the historical travel records to infer the alighting stop.

6. The autonomous construction method of the bus network supply-demand matrix based on multi-source data according to claim 5, wherein, The fusing the travel chain method, the subway line data, and the historical travel records to infer the alighting stop includes: The process of inferring the alighting stop based on the trip chain method includes: inferring the alighting stop of the user's previous bus trip as the boarding stop of the next bus trip, or inferring the alighting stop of the user's previous bus trip as the nearest stop within the walking transfer distance near the boarding stop of the next bus trip, and sorting the user's card swiping data for all days in chronological order to infer the alighting stop; The process of inferring the alighting stop based on the subway line data includes: if the user's next boarding stop is within the transfer distance range near the subway station, inferring that the user travels in the bus - subway - bus transfer mode, and inferring the alighting stop as the bus stop near the intersection of the current subway line and the non - matchable bus lines; The process of inferring the alighting stop based on the historical travel records includes: merging the alighting stops inferred based on the trip chain method and the alighting stops inferred based on the subway line data, extracting the records with multiple same trips as the historical record set, and matching the historical record set with the unrecognized data to infer the alighting stop.

7. An autonomous construction device for the supply-demand matrix of a bus network based on multi-source data, characterized in that, It includes: The first module is used to match the line name according to the bus vehicle GPS data and the bus stop GPS data to generate the bus arrival schedule; The second module is used to calculate the departure frequency of the bus according to the bus arrival schedule, and construct the supply matrix of the bus network according to the departure frequency and the preset passenger capacity of the bus; The third module is used to match the line name and the card swiping time according to the bus arrival schedule and the IC card data, obtain the boarding stop and infer the alighting stop, and construct the IC demand matrix of the bus network according to the line name, the card swiping time, the boarding stop and the inferred alighting stop; The fourth module is used to extract the starting and ending base stations of the user according to the mobile phone signaling data, allocate the passenger flow demand through the distance mapping relationship, and construct the CSD demand matrix of the bus network; Among them, the process of extracting the starting and ending base stations of the user according to the mobile phone signaling data, allocating the passenger flow demand through the distance mapping relationship, and constructing the CSD demand matrix of the bus network includes: After cleaning the CSD data, extract the starting and ending base stations of the user to form the passenger flow OD demand matrix between the base stations; Specifically, after cleaning the CSD data, the CSD data is grouped by user ID, sorted in chronological order, the CSD trajectories of user trips are extracted, the travel modes of users are classified, and the signaling trajectories of users are extracted; the starting base station O and the ending base station D of the signaling trajectory are extracted, the travel OD of the user is mapped to the base station, and the travel demand matrix OD between base stations of the user is obtained. Base As the passenger flow OD demand matrix; Establish the distance mapping relationship between the bus stops within the preset coverage range of the base station and the current base station, allocate the passenger flow OD demand between the base stations to the bus stops, and autonomously construct the CSD demand matrix of the bus network; Specifically, extract the base stations Base i of all bus stops station within the preset coverage range, and calculate the GPS of each base station Basei and the GPS of each bus stop Busj to obtain the distance R j . According to R j , allocate the passenger flow demand OD between base stations according to the inverse ratio relationship Base to the demand OD between stations station , and autonomously obtain the CSD demand matrix of the bus network.

8. An electronic device, characterized in that, It includes a processor and a memory; The memory is used to store programs; The processor executes the program to implement the method according to any one of claims 1 to 6.

9. A computer-readable storage medium, characterized in that, The storage medium stores a program, and the program is executed by the processor to implement the method according to any one of claims 1 to 6.

Images