CN110188923B - Multi-mode bus passenger flow calculation method based on big data technology - Google Patents

Multi-mode bus passenger flow calculation method based on big data technology Download PDF

Info

Publication number
CN110188923B
CN110188923B CN201910372322.1A CN201910372322A CN110188923B CN 110188923 B CN110188923 B CN 110188923B CN 201910372322 A CN201910372322 A CN 201910372322A CN 110188923 B CN110188923 B CN 110188923B
Authority
CN
China
Prior art keywords
point
trip
record
card
station
Prior art date
Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
Active
Application number
CN201910372322.1A
Other languages
Chinese (zh)
Other versions
CN110188923A (en
Inventor
刘晓波
徐占东
李瑞杰
曹阳
Current Assignee (The listed assignees may be inaccurate. Google has not performed a legal analysis and makes no representation or warranty as to the accuracy of the list.)
Southwest Jiaotong University
Original Assignee
Southwest Jiaotong University
Priority date (The priority date is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the date listed.)
Filing date
Publication date
Application filed by Southwest Jiaotong University filed Critical Southwest Jiaotong University
Priority to CN201910372322.1A priority Critical patent/CN110188923B/en
Publication of CN110188923A publication Critical patent/CN110188923A/en
Application granted granted Critical
Publication of CN110188923B publication Critical patent/CN110188923B/en
Active legal-status Critical Current
Anticipated expiration legal-status Critical

Links

Images

Classifications

    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q10/00—Administration; Management
    • G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
    • G06Q10/063—Operations research, analysis or management
    • G06Q10/0631—Resource planning, allocation, distributing or scheduling for enterprises or organisations
    • G—PHYSICS
    • G06—COMPUTING; CALCULATING OR COUNTING
    • G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
    • G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
    • G06Q50/40—Business processes related to the transportation industry

Landscapes

  • Business, Economics & Management (AREA)
  • Human Resources & Organizations (AREA)
  • Engineering & Computer Science (AREA)
  • Economics (AREA)
  • Strategic Management (AREA)
  • Tourism & Hospitality (AREA)
  • Theoretical Computer Science (AREA)
  • General Physics & Mathematics (AREA)
  • Entrepreneurship & Innovation (AREA)
  • General Business, Economics & Management (AREA)
  • Marketing (AREA)
  • Physics & Mathematics (AREA)
  • Operations Research (AREA)
  • Quality & Reliability (AREA)
  • Game Theory and Decision Science (AREA)
  • Development Economics (AREA)
  • Educational Administration (AREA)
  • Health & Medical Sciences (AREA)
  • General Health & Medical Sciences (AREA)
  • Primary Health Care (AREA)
  • Devices For Checking Fares Or Tickets At Control Points (AREA)
  • Traffic Control Systems (AREA)
  • Management, Administration, Business Operations System, And Electronic Commerce (AREA)

Abstract

The invention belongs to the technical field of intelligent transportation, and particularly relates to a multi-mode public transport passenger flow calculation method based on a big data technology. The method combines subway IC card data on the basis of bus IC card and GPS data, performs fusion analysis on bus travel passenger flow under various modes, optimizes a derivation method of a get-off point, provides a new idea of matching the get-off point based on travel characteristics, and considers multiple factors to expand results. The method can more accurately deduce the passenger flow OD distribution condition of the multi-mode bus trip, is more suitable for the traffic environment in which the current bus and subway combined public transportation trip mode is gradually common, and can provide help for planning and optimizing the public transportation industry.

Description

Multi-mode bus passenger flow calculation method based on big data technology
Technical Field
The invention belongs to the technical field of intelligent transportation, and particularly relates to a multi-mode public transport passenger flow calculation method based on a big data technology.
Background
The public transport has the characteristics of low road occupancy rate, large transportation volume, greenness and high efficiency, and has inherent advantages in the aspects of city blockage relieving and smoothness and environment improvement. An urban intelligent public transportation system is established in many major cities, and mass data stored in the urban intelligent transportation system can be used for calculating passenger flow.
In the prior art, the patent "a method for calculating bus passenger OD based on intelligent bus system data (application No. 201610229224.9)" discloses a method for calculating bus passenger OD based on intelligent bus system data, which calculates the passenger getting-on, getting-off and transfer stops by analyzing the time-space characteristics of the bus passenger going out by fusing a plurality of data sources of the intelligent bus system, obtains the inter-stop OD matrix of the passenger at the known getting-off stop, and calculates the matrix according to the number distribution of the passengers at the getting-off stop at the same getting-on stop, so as to obtain the inter-stop OD matrix of the full IC card sample. In addition, the situation that card swiping of passengers possibly occurs after the buses leave the station under the condition of crowded buses in China is considered, transfer behaviors are clearly distinguished, the travel modes of the passengers are mined by utilizing multi-day travel data, the stop getting-off calculation success rate of one-day travel is improved, a more reasonable and reliable OD matrix is obtained, the space-time data of getting-on, getting-off and transfer activities of the urban buses on the whole network can be quickly obtained, and the urban bus transfer planning operation management system can be better served for large-city bus planning operation management. However, the method still has the following technical problems:
(1) only passenger flow calculation under a single travel mode of a bus is researched, how to mine multi-source data combining the bus and the subway is not considered, and the passenger flow condition of a corresponding multi-mode integrated public transport system is deduced;
(2) the judgment method of the get-off point and the OD matrix sample expansion method are not comprehensive in consideration, only general conditions are analyzed in the judgment of the get-off point, accidental trips are ignored, and the calculation success rate needs to be improved; in the OD matrix sample expansion, only the sample expansion of data which is not successfully matched is considered, and the condition of non-card-swiping travel is not considered, which is different from the reality.
Disclosure of Invention
Aiming at the technical problem, the invention provides a multi-mode public transport passenger flow calculation method based on big data technology; the method combines subway IC card data on the basis of bus IC card and GPS data, performs fusion analysis on bus travel passenger flow under various modes, optimizes a derivation method of a get-off point, provides a new idea of matching the get-off point based on travel characteristics, and considers multiple factors to expand the result; the method can more accurately deduce the passenger flow OD distribution condition of the multi-mode bus trip, is more suitable for the traffic environment in which the current bus and subway combined public transportation trip mode is gradually common, and can provide help for planning and optimizing the public transportation industry.
The invention is realized by the following technical scheme:
a multi-mode bus passenger flow calculation method based on big data technology is disclosed, which is based on an IC card data set, a GPS data set and a station line basic data set to deduce the getting-on station of a passenger; analyzing the travel chain characteristics of a single passenger to reconstruct a complete travel chain by analyzing the travel chain characteristics of the passenger; based on the trip characteristics, a single card is used for recording non-centralized deduction of the corresponding trip point to obtain a final trip point of a trip chain; and obtaining an OD matrix between the integrated public transport stations covering the public transport and the subway by combining the getting-on point and the final getting-off point of the trip chain, and performing sample expansion processing on the OD matrix to obtain complete public transport passenger flow distribution.
Further, the station line basic data set comprises a subway terminal data set, a subway station line data set, a bus line station data set and a station serial number data set;
the IC card data set includes: the card swiping time, the subway terminal number or the bus number, the IC card number and the card swiping type for identifying the subway and the bus; the GPS data set includes: the GPS points sample time of day, vehicle number, travel route, instantaneous longitude and instantaneous latitude.
Further, the method specifically comprises:
and (3) getting-on station derivation: respectively deducing bus stations and subway stations according to the characteristics of buses and subways based on an IC card data set, a GPS data set and a station line basic data set;
and (3) reconstructing a trip chain: integrating card swiping records according to whether a transfer behavior exists in the passenger trip, and reconstructing a passenger trip chain, namely directly regarding a single record without the transfer behavior as a trip chain, and regarding a plurality of records with the transfer behavior as a trip chain after combining; the reconstructed trip chain comprises: the trip chain is formed by corresponding single card swiping records when the passenger only swipes the card once in the day and has no transfer behavior; when the passenger has a plurality of times of card swiping data and transfer points on the same day, combining the corresponding plurality of card swiping records with the reconstructed trip chain; the method comprises the following steps that a passenger has a closed public transportation trip chain corresponding to data of multiple card swiping times on the same day, wherein the closed public transportation trip chain comprises two types of commuting frequent trips and occasional trips;
and (3) final get-off point derivation: according to the trip characteristics, divide into the point of getting off: a transfer point, a closed strong trip point and a closed weak trip point; the transfer point can be obtained after the trip chain is reconstructed; the closed strong trip point and the closed weak trip point are used for representing a departure point of a non-transfer point; the closed strong trip point corresponds to commuting type frequent trips, represents places where passengers frequently trip, and can be obtained according to card swiping records of multiple days; the closed weak trip point corresponds to an accidental trip, represents a place representing the accidental trip of a passenger and can be obtained by analyzing the characteristics of the front and rear card swiping records; further deducing and obtaining a final getting-off point of a trip chain according to the closed strong trip point and the closed weak trip point;
and (3) generating an OD matrix of the passenger flow between stations: importing the extracted boarding points of each trip chain and the extracted final alighting points of the trip chains into an Excel data table, and obtaining an OD matrix of passenger flow between the integrated public transport stations covering buses and subways by using a data perspective function;
and (3) performing sample expansion treatment on the inter-station passenger flow OD matrix: aiming at the condition that certain card swiping records in an IC card data set can not be smoothly matched with bus-off stations and aiming at the group completing payment travel through paper money, different coefficients are respectively adopted for sample expansion.
Further, in the step of getting-on station derivation:
the derivation method of the subway boarding station comprises the following steps: the IC card data set records the number of a subway terminal during card swiping, the number of the subway terminal in the IC card data set and the number of the subway terminal in the subway terminal data set are matched through the number of the subway terminal, the subway terminal data set also comprises a station name corresponding to the number of the subway, and therefore a boarding station when taking the subway is obtained;
the derivation method of the bus getting-on station comprises the following steps: the method comprises three steps of vehicle number matching, time matching and nearest site searching; the method comprises the steps of firstly obtaining the serial number of a bus taken by a passenger through an IC card data set, then converting card swiping time in the IC card data set and GPS time in a GPS data set taken by the passenger into minutes and comparing the minutes, searching sampling time which is the same as or closest to the card swiping time in the GPS data set, and finally determining a bus stop which is closest to the bus on an operation line based on position coordinates at the sampling time point, namely the bus getting-on stop when the passenger takes the bus.
Further, the step of reconstructing the trip chain comprises: after sorting the passenger card swiping records, determining whether transfer behaviors exist or not by judging whether the distance interval and the time interval between the upper and lower bus points of two adjacent records meet a threshold value or not, and if the distance interval and the time interval are smaller than the threshold value, determining that the transfer behaviors exist; and combining a plurality of records with transfer behaviors to be regarded as a trip chain, and directly regarding a single record without the transfer behaviors as the trip chain.
Further, the step of reconstructing the trip chain specifically comprises:
the method comprises the following steps: sorting all card swiping records according to the IC card number and the card swiping time, extracting a first card swiping record as a current research record, and judging;
step two: judging whether the current research record and the next record belong to the same card number, if so, entering a third step; if not, judging whether the current record is combined with the previous record into a trip chain, if not, regarding the current record as an independent trip chain, then regarding the next record as the current research record, and re-entering the step two;
step three: judging whether the card swiping type recorded in the current research is public transport or subway;
for public transport: calculating the distance between the last vehicle point of the next record and all stations of the current route, judging whether the minimum distance value is smaller than a threshold value, if not, taking the current research record as an independent trip chain, and entering the step four; if the distance between the current line station and the next recorded boarding point is smaller than the threshold value, acquiring a station with the minimum distance from the next recorded boarding point in the current line station, recording the station as the current line distance minimum station, searching a sampling point which is closest to the current line distance minimum station through a GPS data set of the vehicle, regarding the corresponding moment as the moment when the vehicle reaches the station, further calculating the difference value between the moment when the next recorded boarding point and the moment when the vehicle reaches the current line distance minimum station, judging whether the difference value is smaller than the threshold value or not, if not, taking the current research record as an independent trip chain, and entering a fourth step; otherwise, combining the current research record with the next record, marking the obtained current line distance minimum station as a get-off point of the current research record, marking as a transfer point, and entering the step four;
for a subway: directly calculating the time difference and the distance interval between the getting-on point of the next record and the getting-off point of the current research record, comparing the time difference and the distance interval with a time threshold and a distance threshold respectively, if the time difference and the distance interval are smaller than the threshold, merging the current research record and the next record, marking the getting-off point of the current record as a transfer point, entering the fourth step, and if the time difference and the distance interval are not smaller than the threshold, considering the current research record as an independent travel chain, and entering the fourth step;
step four: and judging whether the next record is the last record in the whole IC card data set, if the next record does not meet the conditions, regarding the next record as the current research record, returning to the step two, otherwise, further judging whether the current record and the next record are combined, if the current record and the next record are combined, directly ending the whole process, and if the current record and the next record are not combined, regarding the next record as an independent trip chain, and ending the whole process.
Further, in the step of getting-off point derivation, the step of further deriving a final getting-off point of the trip chain according to the closed strong trip point and the closed weak trip point specifically includes:
the method comprises the following steps: extracting the reconstructed trip chain in the trip chain reconstruction step, and marking the getting-off point with transfer behavior as a transfer point;
step two: extracting the reconstructed single trip chain in sequence;
step three: extracting the last card swiping record aiming at the single trip chain, and directly extracting the single card swiping record if the passenger only has one card swiping data on the same day for one trip;
step four: the vehicle getting-off point is judged based on the closed strong trip point: extracting the vehicle-entering points in the card-swiping records of the same card number for multiple days, sequentially sorting the vehicle-entering points according to the occurrence times of the vehicle-entering points from large to small, selecting a plurality of vehicle-entering stations in front of the sorting as closed strong trip points, searching the station in the line in which the last card-swiping record is located, which is closest to the closed strong trip point, calculating the distance between the closed strong trip point and the station in the line closest to the closed strong trip point, selecting the station which meets the threshold value and is closest to the closed strong trip point as the final vehicle-leaving point of the trip chain, and entering step eight;
if the distances between the line station in the line recorded by the last card swiping and the plurality of closed forced travel points do not meet the threshold requirement, entering a fifth step;
step five: judging whether the next continuous trip chain record with the same card number exists, if so, entering the step six, and if not, entering the step seven;
step six: judging a get-off point based on the closed weak trip point: extracting a boarding point, namely a closed weak trip point, in the next continuous trip chain record, searching a line station which is closest to the closed weak trip point in a line where the current card swiping record is located, and calculating the distance between the closed weak trip point and the line station which is closest to the closed weak trip point; if the distance meets the threshold requirement, taking the route station closest to the closed weak trip point as a final departure point of the trip chain, and entering the step eight; if not, entering a seventh step;
step seven: the real get-off point cannot be accurately obtained due to the shortage of information resources, and the step is not operated;
step eight: and extracting the next trip chain, entering the step three until all trip chains are judged to be finished, and ending.
Further, the sample expansion processing of the inter-station OD matrix comprises the following steps:
aiming at the condition that certain card swiping records in an IC card data set cannot be smoothly matched with bus-off stops, a first sample expansion coefficient is adopted, and the expression is as follows:
Figure BDA0002050408810000081
in the formula (I), the compound is shown in the specification,
Figure BDA0002050408810000082
the first type sample expansion coefficient of the line i; t isiThe total amount of card swiping data of a line i in the IC card data set; siIdentifying the card swiping record of the line i through the vehicle number in the process of deducing the getting-off point, and calculating the total card swiping record of the line i of the final getting-off point deduced by adopting the step of deducing the final getting-off point;
for the group completing the payment trip through the paper money, adopting a second sample expansion coefficient to expand samples; the second sample expansion coefficient expression is as follows:
Figure BDA0002050408810000083
in the formula (I), the compound is shown in the specification,
Figure BDA0002050408810000084
the second type sample expansion coefficient of the line i; u shapeiThe total number of all travel times of the line i by using paper money and IC cards for card swiping payment; miAnd (4) the total quantity of travel times corresponding to the banknote fare income of the line i.
The invention has the beneficial technical effects that:
in the prior art, the passenger flow calculation method only considers the passenger flow calculation condition of the ground bus, but the method provided by the invention analyzes the travel modes of the ground bus, the rail transit and the combination of the ground bus and the rail transit, and can obtain the passenger flow analysis condition of the multi-mode integrated public transport system.
In the prior art, the derivation method for the final getting-off point of the trip chain is mostly obtained by calculating the getting-off probability based on the number of people getting on the bus at the station, belongs to an integrated model, or does not fully consider the trip behavior characteristics of travelers, and the calculation success rate needs to be improved; the method for deducing the final getting-off point of the travel chain is provided based on the travel characteristics of the passengers, three characteristics of the getting-off point, namely the transfer point, the closed strong travel point and the closed weak travel point are provided, the method is more suitable for actual conditions, the obtained final getting-off point is more accurate, and more information of the travel of a single passenger can be obtained.
The method comprehensively considers two conditions of missing information and paper money passengers when carrying out passenger flow OD sample expansion, and the obtained passenger flow distribution is closer to the real condition.
Drawings
FIGS. 1 a-1E are depictions of data entities E-R employed in the method described in an embodiment of the invention; wherein, FIG. 1a is a bus stop data set E-R description diagram; FIG. 1b is a depiction of a subway terminal data set E-R; FIG. 1c is a depiction of subway station line data sets E-R; FIG. 1d is a depiction of a GPS data set E-R; FIG. 1E is a depiction of an IC card data set E-R;
FIG. 2 is a flow chart of a pick-up station derivation according to an embodiment of the present invention;
FIG. 3 is a schematic diagram of passenger transfer behavior according to an embodiment of the present invention;
FIG. 4 is a flowchart illustrating a process of reconstructing a trip chain according to an embodiment of the present invention;
fig. 5 is a flowchart for deriving a get-off point based on a closed strong and weak trip point in the embodiment of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the present invention more apparent, the present invention is described in further detail below with reference to the accompanying drawings and embodiments. It should be understood that the specific embodiments described herein are merely illustrative of the invention and are not intended to limit the invention.
On the contrary, the invention is intended to cover alternatives, modifications, equivalents and alternatives which may be included within the spirit and scope of the invention as defined by the appended claims. Furthermore, in the following detailed description of the present invention, certain specific details are set forth in order to provide a better understanding of the present invention. It will be apparent to one skilled in the art that the present invention may be practiced without these specific details.
Aiming at the following technical problems existing in the public transport passenger flow estimation method in the prior art: (1) only passenger flow calculation under a single travel mode of the bus is researched, how to mine multi-source data combining the bus and the subway is not considered, and the passenger flow condition of the corresponding multi-mode integrated public transportation system is deduced. (2) Most of the methods belong to a centralized model or do not fully consider the travel behavior characteristics of travelers, the judgment method of the lower vehicle point and the OD matrix sample expansion method do not fully consider the factors, and the calculation success rate and the result accuracy are to be improved.
The embodiment of the invention provides a multi-mode bus passenger flow calculation method based on a big data technology, which is characterized in that the method deduces the boarding station of a passenger based on an IC card data set, a GPS data set and a station line basic data set; analyzing the travel chain characteristics of a single passenger to reconstruct a complete travel chain by analyzing the travel chain characteristics of the passenger; based on the trip characteristics, a single card is used for recording non-centralized deduction of the corresponding trip point to obtain a final trip point of a trip chain; and obtaining an OD matrix between the integrated public transport stations covering the public transport and the subway by combining the getting-on point and the final getting-off point of the trip chain, and performing sample expansion processing on the OD matrix to obtain complete public transport passenger flow distribution.
In the embodiment, the method comprises the steps of getting-on station derivation, trip chain reconstruction, final getting-off point derivation, interstation passenger flow OD matrix generation and sample expansion processing of the interstation passenger flow OD matrix.
The step of deriving the boarding station specifically comprises the following steps:
respectively deducing bus stations and subway stations according to the characteristics of buses and subways based on an IC card data set, a GPS data set and a station line basic data set;
wherein, as shown in fig. 1 a-1 e: the IC card data set includes: the card swiping time, the subway terminal number or the bus number, the IC card number and the card swiping type for identifying the subway and the bus; the GPS data set includes: GPS point sampling time, vehicle number, running line, instantaneous longitude and instantaneous latitude;
the station line basic data set comprises a subway terminal data set, a subway station line data set and a bus line station data set; specifically, the subway terminal data set comprises a subway terminal number, a subway station name, station longitude and latitude and a line name; the subway station line data set comprises: the subway station comprises a subway terminal number, mileposts, subway station names, station longitude and latitude and line names; the bus route stop data set includes: the bus stop name, the stop number, the stop longitude and latitude, the line number, the mileage mark and the line direction (up and down).
Fig. 2 is a flowchart of deriving a boarding station, and as shown in fig. 2, whether a public transportation type adopted by a passenger is a bus or a subway is determined according to a card swiping type in an IC card data set, and when the card swiping type is a subway, a method for deriving a subway boarding station is as follows: the IC card data set records the number of a subway terminal during card swiping, the number of the subway terminal in the IC card data set and the number of the subway terminal in the subway terminal data set are matched through the number of the subway terminal, the subway terminal data set also comprises a station name corresponding to the number of the subway, and therefore a boarding station when taking the subway is obtained;
when the card swiping type is a bus, the derivation method of the bus getting-on station comprises the following steps: the method comprises three steps of vehicle number matching, time matching and nearest site searching; the method comprises the steps of firstly obtaining the serial number of a bus taken by a passenger through an IC card data set, then converting card swiping time in the IC card data set and GPS time in a GPS data set taken by the passenger into minutes and comparing the minutes, searching sampling time which is the same as or closest to the card swiping time in the GPS data set, and finally determining a bus stop which is closest to the bus on an operation line based on position coordinates at the sampling time point, namely the bus getting-on stop when the passenger takes the bus.
A trip chain reconstruction step:
the public transport passengers travel in one day generally in a travel chain mainly from beginning to end. Generally, one card swiping record can deduce a get-off station, but not all get-off stations represent travel destinations, and passengers may need to transfer once or multiple times to reach the final destination point, so that travel chain reconstruction is needed;
FIG. 3 is a schematic diagram of passenger transfer behavior, as shown in FIG. 3, from the starting station S1At T1Time card swiping payment to finish getting-on, bus or subway running time t1To T2Time of arrival at site X1Get off, walk distance d, elapsed time t2At T3Arrive at the getting-on station S at the moment2Stay waiting at the station takes time t3To T4The card swiping and the vehicle loading are finished at any moment, and the final operation time t is4At T5Arrival at destination X2And finishing the public transportation travel behavior. Thus, site X1Is a transfer station, is not a stop getting-off station of the trip, and for the situations, T is required to be converted1Time and T4Combining the two card swiping records at the moment into a trip chain, and judging whether a transfer point exists or not by a key step of reconstructing the trip chain.
The reconstruction of the trip chain specifically comprises the following steps: integrating card swiping records according to whether a transfer behavior exists in the passenger trip, and reconstructing a passenger trip chain, namely directly regarding a single record without the transfer behavior as a trip chain, and regarding a plurality of records with the transfer behavior as a trip chain after combining; the reconstructed trip chain comprises: the trip chain is formed by corresponding single card swiping records when the passenger only swipes the card once in the day and has no transfer behavior; when the passenger has a plurality of times of card swiping data and transfer points on the same day, combining the corresponding plurality of card swiping records with the reconstructed trip chain; the method comprises the following steps that a passenger has a closed public transportation trip chain corresponding to data of multiple card swiping times on the same day, wherein the closed public transportation trip chain comprises two types of commuting frequent trips and occasional trips;
in the specific derivation, after sorting the card swiping records, determining whether a transfer behavior exists by judging whether the distance interval and the time interval between the two adjacent recorded getting-on and getting-off points meet the threshold value, taking fig. 3 as an example, judging the distance interval d and the time interval t in fig. 32+t3And if the transfer is smaller than the threshold, the transfer behavior is considered to exist. For subway data, the card swiping record covers the information of the lower bus stop point, and can be directly compared with the upper bus stop point of the next record. For the public transportation data, the station information closest to the next recorded boarding point in the current line needs to be searched first, and then judgment is carried out. Will eventually meet the thresholdThe two records are combined into a trip chain, and a basis is laid for subsequently deducing a trip destination point.
The detailed steps of the trip chain reconstruction are shown in fig. 4, specifically:
the method comprises the following steps: sorting all card swiping records according to the IC card number and the card swiping time, extracting a first card swiping record as a current research record, and judging;
step two: judging whether the current research record and the next record belong to the same card number, if so, entering a third step; if not, judging whether the current record is combined with the previous record into a trip chain, if not, regarding the current record as an independent trip chain, then regarding the next record as the current research record, and re-entering the step two;
step three: judging whether the card swiping type recorded in the current research is public transport or subway;
for public transport: calculating the distance between the last vehicle point of the next record and all stations of the current route, judging whether the minimum distance value is smaller than a threshold value, if not, taking the current research record as an independent trip chain, and entering the step four; if the distance between the current line station and the next recorded boarding point is smaller than the threshold value, acquiring a station with the minimum distance from the next recorded boarding point in the current line station, recording the station as the current line distance minimum station, searching a sampling point which is closest to the current line distance minimum station through a GPS data set of the vehicle, regarding the corresponding moment as the moment when the vehicle reaches the station, further calculating the difference value between the moment when the next recorded boarding point and the moment when the vehicle reaches the current line distance minimum station, judging whether the difference value is smaller than the threshold value or not, if not, taking the current research record as an independent trip chain, and entering a fourth step; otherwise, combining the current research record with the next record, marking the obtained current line distance minimum station as a get-off point of the current research record, marking as a transfer point, and entering the step four;
for a subway: directly calculating the time difference and the distance interval between the getting-on point of the next record and the getting-off point of the current research record, comparing the time difference and the distance interval with a time threshold and a distance threshold respectively, if the time difference and the distance interval are smaller than the threshold, merging the current research record and the next record, marking the getting-off point of the current record as a transfer point, entering the fourth step, and if the time difference and the distance interval are not smaller than the threshold, considering the current research record as an independent travel chain, and entering the fourth step;
step four: and judging whether the next record is the last record in the whole IC card data set, if the next record does not meet the conditions, regarding the next record as the current research record, returning to the step two, otherwise, further judging whether the current record and the next record are combined, if the current record and the next record are combined, directly ending the whole process, and if the current record and the next record are not combined, regarding the next record as an independent trip chain, and ending the whole process.
And a final get-off point derivation step:
the derivation of the bus stop of the city bus is mainly to judge the bus stop based on the general rule and characteristics of the travel of passengers of the city bus on the basis of the judgment of the bus stop, and is a key stage for deriving the OD matrix of the bus stop. According to the times of taking the bus by the passenger in one day, the trip can be divided into one trip and multiple trips.
The one-time trip is that the bus passenger only swipes the card data once on the day, the passenger may finish visiting friends or visiting relatives through one-time trip, and then live near a terminal station or realize return trip through other transportation modes, and the trip chain is formed by a single card swiping record corresponding to the situation that the passenger only swipes the card data once on the day and has no transfer behavior in the trip chain reconstruction step.
The trip many times means that the passenger is bus card swiping times more than twice this day, corresponds two kinds of situations this moment: one is that the card is swiped for a plurality of times due to transfer, and a plurality of corresponding card swiping records are merged to reconstruct the trip chain when the passenger has card swiping data for a plurality of times and has a transfer point in the trip chain reconstruction step; and in the other step, the closed public transportation trip chain corresponding to the data of multiple card swiping times of the passenger on the same day in the trip chain reconstruction step, such as commuting transportation, comes and goes between the family and the workplace, and for example, the public transportation mode is adopted for the occasional trip and the coming and going.
In conclusion, the get-off point is divided into three types according to the travel characteristics: a transfer point, a closed strong trip point and a closed weak trip point; the judgment mode and the derivation method of the transfer points are seen in a trip chain reconstruction step, a closed strong trip point and a closed weak trip point are used for representing a getting-off point of a single trip or multiple trips under a non-transfer point, wherein the closed strong trip point corresponds to a frequent trip of commuter traffic and represents a frequent trip place of a passenger, the frequent trip place can be obtained according to card swiping records of multiple days, and the closed weak trip point corresponds to a sporadic trip and can be obtained by analyzing the characteristics of the card swiping records before and after the card swiping records.
And subsequently, further deducing a final getting-off point of the trip chain by using the closed strong trip point and the closed weak trip point, wherein the steps are shown in fig. 5 and specifically described as follows:
the method comprises the following steps: extracting the reconstructed trip chain in the trip chain reconstruction step, and marking the getting-off point with transfer behavior as a transfer point;
step two: extracting the reconstructed single trip chain in sequence;
step three: extracting the last card swiping record aiming at the single trip chain, and directly extracting the single card swiping record if the passenger only has one card swiping data on the same day for one trip;
step four: the vehicle getting-off point is judged based on the closed strong trip point: extracting the vehicle-entering points in the card-swiping records of the same card number for multiple days, sequentially sorting the vehicle-entering points according to the occurrence times of the vehicle-entering points from large to small, selecting a plurality of vehicle-entering stations in front of the sorting as closed strong trip points, searching the station in the line in which the last card-swiping record is located, which is closest to the closed strong trip point, calculating the distance between the closed strong trip point and the station in the line closest to the closed strong trip point, selecting the station which meets the threshold value and is closest to the closed strong trip point as the final vehicle-leaving point of the trip chain, and entering step eight;
if the distances between the line station in the line recorded by the last card swiping and the plurality of closed forced travel points do not meet the threshold requirement, entering a fifth step;
step five: judging whether the next continuous trip chain record with the same card number exists, if so, entering the step six, and if not, entering the step seven;
step six: judging a get-off point based on the closed weak trip point: extracting a boarding point, namely a closed weak trip point, in the next continuous trip chain record, searching a line station which is closest to the closed weak trip point in a line where the current card swiping record is located, and calculating the distance between the closed weak trip point and the line station which is closest to the closed weak trip point; if the distance meets the threshold requirement, taking the route station closest to the closed weak trip point as a final departure point of the trip chain, and entering the step eight; if not, entering a seventh step;
step seven: the real get-off point cannot be accurately obtained due to the shortage of information resources, and the step is not operated;
step eight: and extracting the next trip chain, entering the step three until all trip chains are judged to be finished, and ending.
Generating an OD matrix of the passenger flow between stations:
the OD matrix between the urban public transport stations is a travel matrix between the urban residents and obtained by statistics according to travel purposes, namely a real travel origin-destination, wherein transfer points are not included. Importing the getting-on point of each trip chain extracted in the step and the final getting-off point of the trip chain based on the closed strong and weak trip points into an Excel data table, and obtaining an OD matrix of passenger flow between the integrated public transport stations covering buses and subways by using a data perspective function of Excel; however, the obtained inter-station traffic OD matrix cannot represent a real complete traffic distribution situation, and has two disadvantages. On one hand, due to incomplete partial information resources, data records of certain bus IC cards cannot be smoothly matched with bus get-off stations, and if the bus get-off stations do not belong to transfer points or do not meet the condition of closing strong and weak trip point characteristics; on the other hand, the passenger flow distribution derived based on the IC card data only represents the group who uses the IC card for public transportation travel, and the group who completes payment travel partially through paper money is not considered. Therefore, it is necessary to perform a sample expansion process to generate a passenger flow distribution closest to the real situation.
And (3) performing sample expansion processing on the inter-station passenger flow OD matrix: and the sample expansion of the OD matrix between the stations is carried out by setting two sample expansion coefficients from the two aspects based on the bus line layer.
Aiming at the condition that certain card swiping records in an IC card data set can not be smoothly matched with bus stop stations, a first type of sample expansion coefficient is adopted, the first type of sample expansion coefficient is based on IC card data for deducing an OD matrix of passenger flow between the stations, the card swiping record data volume of each line of a final getting-off point deduced by adopting the final getting-off point deducting step is calculated and matched with the line of the IC card data record, and the passenger flow volume of related lines is counted.
The expression is as follows:
Figure BDA0002050408810000171
in the formula (I), the compound is shown in the specification,
Figure BDA0002050408810000172
the first type sample expansion coefficient of the line i; t isiThe total amount of card swiping data of a line i in the IC card data set; siIdentifying the card swiping record of the line i through the vehicle number in the process of deducing the getting-off point, and calculating the total card swiping record of the line i of the final getting-off point deduced by adopting the step of deducing the final getting-off point;
for the group completing the payment trip through the paper money, adopting a second sample expansion coefficient to expand samples; and the second type of sample expansion coefficients are matrix sample expansion between stations on the line level based on various types of calculated line fare income under the condition that the trip characteristics of coin-freed passengers and card-swiping passengers are completely consistent. The second sample expansion coefficient expression is as follows:
Figure BDA0002050408810000181
in the formula (I), the compound is shown in the specification,
Figure BDA0002050408810000182
the second type sample expansion coefficient of the line i; u shapeiThe total number of all travel times of the line i by using paper money and IC cards for card swiping payment; miAnd (4) the total quantity of travel times corresponding to the banknote fare income of the line i.
Compared with the prior art, the multi-mode public transport passenger flow calculation method based on the big data technology provided by the invention at least has the following beneficial technical effects:
(1) adopting multi-mode combined public transport passenger flow distribution analysis: under the background of common development of current rail transit and ground buses, the multi-mode integrated combined public transportation travel mode of public transit and subway is more common. The method comprehensively utilizes bus and subway card swiping data, and by combining the bus and subway card swiping data and considering the bus and subway card swiping data, the origin-destination points of various travel modes such as single bus travel, single subway travel, bus + bus travel, bus + subway travel and the like can be accurately extracted, and the multi-mode combined public transport passenger flow distribution condition with more practical significance is obtained.
(2) A get-off point derivation method based on travel characteristics comprises the following steps: in the process of deducing the departure point, the travel characteristics are fully considered. Firstly, all card swiping records are analyzed based on the transfer behaviors of passengers, and a complete trip chain of a user is reconstructed. Then, based on the consideration of the purposes of single trip and multiple trips of the passenger, closed strong and weak trip points corresponding to the frequent trip and the accidental trip are provided, and the getting-off points of most trip chains can be deduced by using the strong and weak trip points.
(3) The passenger flow OD sample expanding method considering the practical factors comprises the following steps: the passenger flow distribution derived based on the IC card data is often less than the real situation, and the complete public transport passenger flow distribution can be obtained only by carrying out sample expansion processing. When the method is used for sample expansion of the OD, not only is the IC card data of the get-off point incapable of being obtained due to information loss considered, but also a paper money user group is considered. Based on the consideration of multiple realistic factors, the sample expansion result of the method is closer to the real situation.
The method provided by the invention innovatively combines subway IC card data on the basis of the bus IC card and GPS data, applies mass public transport and subway data, calculates the passenger flow of urban multi-mode public transport travel, performs fusion analysis, optimizes the derivation method of the get-off point, provides a new idea of matching the get-off point based on travel characteristics, and considers multiple factors to expand the result. The method can accurately deduce the passenger flow OD distribution condition of the multi-mode bus trip, is more suitable for the traffic environment in which the current bus and subway combined public transportation trip mode is gradually common, and can provide help for planning and optimizing the public transportation industry.

Claims (5)

1. A multi-mode bus passenger flow calculation method based on big data technology is characterized in that the method deduces the boarding station of a passenger based on an IC card data set, a GPS data set and a station line basic data set; analyzing the travel chain characteristics of a single passenger to reconstruct a complete travel chain by analyzing the travel chain characteristics of the passenger; based on the trip characteristics, a single card is used for recording non-centralized deduction of the corresponding trip point to obtain a final trip point of a trip chain; obtaining an OD matrix between integrated public transport stations covering buses and subways by combining the boarding point and the final disembarking point of the trip chain, and performing sample expansion processing on the OD matrix to obtain complete public transport passenger flow distribution;
the station line basic data set comprises a subway terminal data set, a subway station line data set, a bus line station data set and a station serial number data set;
the IC card data set includes: the card swiping time, the subway terminal number or the bus number, the IC card number and the card swiping type for identifying the subway and the bus; the GPS data set includes: GPS point sampling time, vehicle number, running line, instantaneous longitude and instantaneous latitude;
wherein:
and (3) getting-on station derivation: respectively deducing bus stations and subway stations according to the characteristics of buses and subways based on an IC card data set, a GPS data set and a station line basic data set;
and (3) reconstructing a trip chain: integrating card swiping records according to whether a transfer behavior exists in passenger travel, and reconstructing a passenger travel chain; the reconstructed trip chain comprises: the trip chain is formed by corresponding single card swiping records when the passenger only swipes the card once in the day and has no transfer behavior; when the passenger has a plurality of times of card swiping data and transfer points on the same day, combining the corresponding plurality of card swiping records with the reconstructed trip chain; the method comprises the following steps that a passenger has a closed public transportation trip chain corresponding to data of multiple card swiping times on the same day, wherein the closed public transportation trip chain comprises two types of commuting frequent trips and occasional trips; after sorting the passenger card swiping records, determining whether transfer behaviors exist or not by judging whether the distance interval and the time interval between the upper and lower bus points of two adjacent records meet a threshold value or not, and if the distance interval and the time interval are smaller than the threshold value, determining that the transfer behaviors exist; combining a plurality of records with transfer behaviors to be regarded as a trip chain, and directly regarding a single record without the transfer behaviors as the trip chain;
and (3) final get-off point derivation: according to the trip characteristics, divide into the point of getting off: a transfer point, a closed strong trip point and a closed weak trip point; the transfer point can be obtained after the trip chain is reconstructed; the closed strong trip point and the closed weak trip point are used for representing a departure point of a non-transfer point; the closed strong trip point corresponds to commuting type frequent trips, represents places where passengers frequently trip, and can be obtained according to card swiping records of multiple days; the closed weak trip point corresponds to an accidental trip, represents a place representing the accidental trip of a passenger and can be obtained by analyzing the characteristics of the front and rear card swiping records; further deducing and obtaining a final getting-off point of a trip chain according to the closed strong trip point and the closed weak trip point;
and (3) generating an OD matrix of the passenger flow between stations: importing the extracted boarding points of each trip chain and the extracted final alighting points of the trip chains into an Excel data table, and obtaining an OD matrix of passenger flow between the integrated public transport stations covering buses and subways by using a data perspective function;
and (3) performing sample expansion treatment on the inter-station passenger flow OD matrix: aiming at the condition that certain card swiping records in an IC card data set can not be smoothly matched with bus-off stations and aiming at the group completing payment travel through paper money, different coefficients are respectively adopted for sample expansion.
2. The big data technology-based multi-mode bus passenger flow estimation method according to claim 1, wherein in the getting-on station derivation step:
the derivation method of the subway boarding station comprises the following steps: the IC card data set records the number of a subway terminal during card swiping, the number of the subway terminal in the IC card data set and the number of the subway terminal in the subway terminal data set are matched through the number of the subway terminal, the subway terminal data set also comprises a station name corresponding to the number of the subway, and therefore a boarding station when taking the subway is obtained;
the derivation method of the bus getting-on station comprises the following steps: the method comprises three steps of vehicle number matching, time matching and nearest site searching; firstly, obtaining the serial number of a bus taken by a passenger through an IC card data set, then converting card swiping time in the IC card data set and GPS time in a GPS data set of the passenger taking the bus into minutes and comparing the minutes, searching sampling time which is the same as or closest to the card swiping time in the GPS data set, and finally determining a bus stop which is closest to the bus on an operation line based on position coordinates at the sampling time point, namely the bus getting-on stop when the passenger takes the bus.
3. The multi-mode bus passenger flow calculation method based on the big data technology as claimed in claim 1, wherein the step of reconstructing the travel chain specifically comprises:
the method comprises the following steps: sorting all card swiping records according to the IC card number and the card swiping time, extracting a first card swiping record as a current research record, and judging;
step two: judging whether the current research record and the next record belong to the same card number, if so, entering a third step; if not, judging whether the current record is combined with the previous record into a trip chain, if not, regarding the current record as an independent trip chain, then regarding the next record as the current research record, and re-entering the step two;
step three: judging whether the card swiping type recorded in the current research is public transport or subway;
for public transport: calculating the distance between the last vehicle point of the next record and all stations of the current route, judging whether the minimum distance value is smaller than a threshold value, if not, taking the current research record as an independent trip chain, and entering the step four; if the distance is smaller than the threshold value, acquiring a station with the minimum distance from the next recorded boarding point in the current line stations, and recording as the current line distance minimum station; searching a sampling point which is closest to the current line distance minimum station through a GPS data set of the vehicle, regarding the corresponding time as the time when the vehicle reaches the current line distance minimum station, further calculating the difference value between the time when the vehicle is recorded at the next point and the time when the vehicle reaches the current line distance minimum station, judging whether the difference value is smaller than a threshold value, if not, taking the current research record as an independent trip chain, and entering a fourth step; otherwise, combining the current research record with the next record, marking the obtained current line distance minimum station as a get-off point of the current research record, marking as a transfer point, and entering the step four;
for a subway: directly calculating the time difference and the distance interval between the getting-on point of the next record and the getting-off point of the current research record, comparing the time difference and the distance interval with a time threshold and a distance threshold respectively, if the time difference and the distance interval are smaller than the threshold, merging the current research record and the next record, marking the getting-off point of the current record as a transfer point, entering the fourth step, and if the time difference and the distance interval are not smaller than the threshold, considering the current research record as an independent travel chain, and entering the fourth step;
step four: and judging whether the next record is the last record in the whole IC card data set, if the next record does not meet the conditions, regarding the next record as the current research record, returning to the step two, otherwise, further judging whether the current record and the next record are combined, if the current record and the next record are combined, directly ending the whole process, and if the current record and the next record are not combined, regarding the next record as an independent trip chain, and ending the whole process.
4. The multi-mode bus passenger flow calculation method based on big data technology according to claim 1, characterized in that in the step of getting-off point derivation, the step of further deriving a final getting-off point of a travel chain according to the closed strong travel point and the closed weak travel point is specifically:
the method comprises the following steps: extracting the reconstructed trip chain in the trip chain reconstruction step, and marking the getting-off point with transfer behavior as a transfer point;
step two: extracting the reconstructed single trip chain in sequence;
step three: extracting the last card swiping record aiming at the single trip chain, and directly extracting the single card swiping record if the passenger only has one card swiping data on the same day for one trip;
step four: the vehicle getting-off point is judged based on the closed strong trip point: extracting the vehicle-entering points in the card-swiping records of the same card number for multiple days, sequentially sorting the vehicle-entering points according to the occurrence times of the vehicle-entering points from large to small, selecting a plurality of vehicle-entering stations in front of the sorting as closed strong trip points, searching the station in the line in which the last card-swiping record is located, which is closest to the closed strong trip point, calculating the distance between the closed strong trip point and the station in the line closest to the closed strong trip point, selecting the station which meets the threshold value and is closest to the closed strong trip point as the final vehicle-leaving point of the trip chain, and entering step eight;
if the distances between the line station in the line recorded by the last card swiping and the plurality of closed forced travel points do not meet the threshold requirement, entering a fifth step;
step five: judging whether the next continuous trip chain record with the same card number exists, if so, entering the step six, and if not, entering the step seven;
step six: judging a get-off point based on the closed weak trip point: extracting a boarding point, namely a closed weak trip point, in the next continuous trip chain record, searching a line station which is closest to the closed weak trip point in a line where the current card swiping record is located, and calculating the distance between the closed weak trip point and the line station which is closest to the closed weak trip point; if the distance meets the threshold requirement, taking the route station closest to the closed weak trip point as a final departure point of the trip chain, and entering the step eight; if not, entering a seventh step;
step seven: the real get-off point cannot be accurately obtained due to the shortage of information resources, and the step is not operated;
step eight: and extracting the next trip chain, entering the step three until all trip chains are judged to be finished, and ending.
5. The multi-mode bus passenger flow estimation method based on big data technology as claimed in claim 1, wherein the sample expansion processing of the inter-station OD matrix comprises:
aiming at the condition that certain card swiping records in an IC card data set cannot be smoothly matched with bus-off stops, a first sample expansion coefficient is adopted, and the expression is as follows:
Figure FDA0003027582870000061
in the formula (I), the compound is shown in the specification,
Figure FDA0003027582870000062
the first type sample expansion coefficient of the line i; t isiThe total amount of card swiping data of a line i in the IC card data set; siIdentifying the card swiping record of the line i through the vehicle number in the process of deducing the getting-off point, and calculating the total card swiping record of the line i of the final getting-off point deduced by adopting the step of deducing the final getting-off point;
for the group completing the payment trip through the paper money, adopting a second sample expansion coefficient to expand samples; the second sample expansion coefficient expression is as follows:
Figure FDA0003027582870000063
in the formula (I), the compound is shown in the specification,
Figure FDA0003027582870000064
the second type sample expansion coefficient of the line i; u shapeiThe total number of all travel times of the line i by using paper money and IC cards for card swiping payment; miTravel times corresponding to the banknote and fare income of the line iThe total amount of the number.
CN201910372322.1A 2019-05-06 2019-05-06 Multi-mode bus passenger flow calculation method based on big data technology Active CN110188923B (en)

Priority Applications (1)

Application Number Priority Date Filing Date Title
CN201910372322.1A CN110188923B (en) 2019-05-06 2019-05-06 Multi-mode bus passenger flow calculation method based on big data technology

Applications Claiming Priority (1)

Application Number Priority Date Filing Date Title
CN201910372322.1A CN110188923B (en) 2019-05-06 2019-05-06 Multi-mode bus passenger flow calculation method based on big data technology

Publications (2)

Publication Number Publication Date
CN110188923A CN110188923A (en) 2019-08-30
CN110188923B true CN110188923B (en) 2022-01-07

Family

ID=67715655

Family Applications (1)

Application Number Title Priority Date Filing Date
CN201910372322.1A Active CN110188923B (en) 2019-05-06 2019-05-06 Multi-mode bus passenger flow calculation method based on big data technology

Country Status (1)

Country Link
CN (1) CN110188923B (en)

Families Citing this family (6)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN110705848B (en) * 2019-09-18 2022-10-18 交通运输部公路科学研究所 Comprehensive traffic service evaluation method and device based on individual trip chain
CN111079875A (en) * 2019-12-17 2020-04-28 广州交通信息化建设投资营运有限公司 Public transport passenger flow monitoring method and device based on multi-source data and storage medium
CN111639973B (en) * 2020-06-02 2023-01-17 广州交信投科技股份有限公司 Public transport passenger flow OD derivation method and device based on multivariate fusion big data
CN111858806A (en) * 2020-07-09 2020-10-30 武汉译码当先科技有限公司 Passenger travel track detection method, device, equipment and storage medium
CN113537714B (en) * 2021-06-11 2023-11-24 华设设计集团股份有限公司 Old people public transportation preference scheme assessment method and system based on multi-source big data fusion analysis
CN115798217A (en) * 2023-02-06 2023-03-14 中国市政工程西南设计研究总院有限公司 Multi-mode traffic network super-path flow distribution method, device, equipment and medium

Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104766473A (en) * 2015-02-09 2015-07-08 北京工业大学 Traffic trip feature extraction method based on multi-mode public transport data matching
CN105320998A (en) * 2015-09-22 2016-02-10 中山大学 IC card swiping data based optimal bus travel route acquisition method
CN105654721A (en) * 2016-01-21 2016-06-08 哈尔滨工业大学 Method for utilizing public transportation IC cards and vehicle-mounted GPS data to calculate public transportation OD amount
CN105788260A (en) * 2016-04-13 2016-07-20 西南交通大学 Public transportation passenger OD calculation method based on intelligent public transportation system data

Family Cites Families (3)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN103793760B (en) * 2014-01-24 2017-12-15 同济大学 Passenger flow transfer allocation proportion optimization method inside multi-mode comprehensive transportation hub
CN104318758B (en) * 2014-11-05 2016-06-29 东南大学 Based on multi-level multimodal Public transport network planning method
CN108171974B (en) * 2017-12-27 2020-02-18 东南大学 Traffic travel mode discrimination method based on mobile phone triangulation data

Patent Citations (4)

* Cited by examiner, † Cited by third party
Publication number Priority date Publication date Assignee Title
CN104766473A (en) * 2015-02-09 2015-07-08 北京工业大学 Traffic trip feature extraction method based on multi-mode public transport data matching
CN105320998A (en) * 2015-09-22 2016-02-10 中山大学 IC card swiping data based optimal bus travel route acquisition method
CN105654721A (en) * 2016-01-21 2016-06-08 哈尔滨工业大学 Method for utilizing public transportation IC cards and vehicle-mounted GPS data to calculate public transportation OD amount
CN105788260A (en) * 2016-04-13 2016-07-20 西南交通大学 Public transportation passenger OD calculation method based on intelligent public transportation system data

Non-Patent Citations (2)

* Cited by examiner, † Cited by third party
Title
基于公交IC卡和GPS数据的居民公交出行OD矩阵推导与应用;吴祥国;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20120415;第C034-711页 *
基于多日公交IC卡数据与AVL数据的公交OD推算方法研究;钱易;《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》;20180315;第C034-1086页 *

Also Published As

Publication number Publication date
CN110188923A (en) 2019-08-30

Similar Documents

Publication Publication Date Title
CN110188923B (en) Multi-mode bus passenger flow calculation method based on big data technology
CN109035770B (en) Real-time analysis and prediction method for bus passenger capacity in big data environment
CN113256987B (en) Multi-source data fusion-based resident trip chain generation method and co-multiplication query method
CN111932867B (en) Multisource data-based bus IC card passenger getting-off station derivation method
CN108761509B (en) Automobile driving track and mileage prediction method based on historical data
CN111079875A (en) Public transport passenger flow monitoring method and device based on multi-source data and storage medium
CN109903553B (en) Multi-source data mining bus station identification and inspection method
CN105788260A (en) Public transportation passenger OD calculation method based on intelligent public transportation system data
CN108922178B (en) Public transport vehicle real-time full load rate calculation method based on public transport multi-source data
CN109102114B (en) Bus trip getting-off station estimation method based on data fusion
CN112511982B (en) Subway passenger track real-time tracing and restoring method with automatic trip semantic annotation
CN109637134B (en) Public transportation equipment matching method
CN111653096A (en) Urban trip mode identification method based on mobile phone signaling data
CN110853156B (en) Passenger OD identification method integrating bus GPS track and IC card data
CN105390013A (en) Method for predicting bus arrival time based on bus IC card
CN107590239B (en) Method for measuring connection radius of public bicycle at subway station based on IC card data
CN108364464A (en) A kind of public transit vehicle hourage modeling method based on probabilistic model
CN114446048A (en) Rail transit traveler full trip chain analysis method based on mobile phone signaling data
CN111046937A (en) Two-segment passenger crowd trip purpose analysis method fusing public transportation data and POI data
CN107578619B (en) Method for measuring public bicycle service range of subway station based on IC card data
Guo et al. Exploring potential travel demand of customized bus using smartcard data
CN113658433B (en) Method for extracting passenger flow characteristics based on bus card swiping and code scanning data
CN113344268B (en) Urban traffic trip data analysis method
CN108681741B (en) Subway commuting crowd information fusion method based on IC card and resident survey data
KR20120068580A (en) Trip pattern analysis system of the public transportation using the transportation card data and the trip pattern analysis methods of the same

Legal Events

Date Code Title Description
PB01 Publication
PB01 Publication
SE01 Entry into force of request for substantive examination
SE01 Entry into force of request for substantive examination
GR01 Patent grant
GR01 Patent grant