CN103065205A - Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system - Google Patents
Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system Download PDFInfo
- Publication number
- CN103065205A CN103065205A CN2012105750151A CN201210575015A CN103065205A CN 103065205 A CN103065205 A CN 103065205A CN 2012105750151 A CN2012105750151 A CN 2012105750151A CN 201210575015 A CN201210575015 A CN 201210575015A CN 103065205 A CN103065205 A CN 103065205A
- Authority
- CN
- China
- Prior art keywords
- passenger flow
- transport hub
- analysis
- passenger
- flow
- 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.)
- Pending
Links
Images
Landscapes
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention provides a three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system which is aimed at the characteristics of passenger flow of a transportation junction. The three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system comprises a multi-source data layer, a data base layer and a functional module layer, wherein the functional module layer comprises a three-dimensional geographic information system (GIS) basic function module, a real-time traffic status analysis and release module, a transportation junction real-time traffic circle analysis and release module, a transportation junction passenger flow time-space distribution analysis and release module and a transportation junction passenger flow statistics and prediction analysis and release module. The real-time traffic status analysis and release module, the transportation junction real-time traffic circle analysis and release module, the transportation junction passenger flow time-space distribution analysis and release module and the transportation junction passenger flow statistics and prediction analysis and release module are all connected with the three-dimensional GIS basic function module. The three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system can achieve time-space analysis and three-dimensional visualization display for multi-source real-time dynamic traffic information aiming at the transportation junction.
Description
Technical field
The present invention relates to geospatial information systems technology field, relate in particular to a kind of 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system.
Background technology
The transport hub lack of control is to integrated management and the analysis of multi-source dynamic information at present, shortage is furtherd investigate and is used spatial and temporal distributions and transport hub passenger flow short-term rule statistics and the prediction etc. of transport hub passenger flow, and the dynamic and visual of shortage transport hub passenger flow space-time analysis in the three-dimensional city scene expressed.
Summary of the invention
The present invention is for solving the problems of the technologies described above, a kind of 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system are provided, it is characterized in that, passenger flow feature for the transport hub, comprise the multi-source data layer that comprises data, comprise wide area information server layer and the functional module layer take described multi-source data layer and described database layer as the basis operation, wherein, described functional module layer comprises:
The three-dimension GIS basic function module is used for traffic basis scene is carried out data loading, management, analysis and visual, and transport hub passenger flow space-time analysis is carried out the Three-Dimensional Dynamic Visualization with predicting the outcome; Real-time road is analyzed release module, is used at the issue of three-dimensional city scene and analysis real-time traffic information; Transport hub real-time traffic circle is analyzed release module, expresses for the scope that can arrive the surrounding area take the transport hub as starting point in user's setting-up time is analyzed with three-dimensional visualization; Transport hub passenger flow Analysis on Spatial Temporal Distribution release module is used for the transport hub passenger flow of each mode of transportation is carried out trip start-stop analysis and the three-dimensional visualization of each time period and expresses; Transport hub passenger flow statistics and forecast analysis release module, be used for the transport hub volume of the flow of passengers of each mode of transportation is added up and at times short-term forecasting, described real-time road is analyzed release module, transport hub real-time traffic circle is analyzed release module, transport hub passenger flow Analysis on Spatial Temporal Distribution release module and transport hub passenger flow statistics and all is connected with described three-dimension GIS basic function module with release module with forecast analysis.
Preferably, in the passenger flow Analysis on Spatial Temporal Distribution release module of described transport hub, the step of transport hub metro passenger flow Analysis on Spatial Temporal Distribution issue comprises:
Input historical subway transportation card data, extract the effective subway record of swiping the card; Add up each subway station passenger flow relevant with the transport hub, be the passenger flow of transport hub comprising destination and origin, respectively with working day and weekend as two statistics classifications, the average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come from each subway station to the transport hub and transport hub are gone to each subway station; In the three-dimensional city scene, the up/down volume of the flow of passengers of each ground iron spot is carried out Visualization by D prism map.
Preferably, in the passenger flow Analysis on Spatial Temporal Distribution release module of described transport hub, the step of transport hub taxi passenger flow Analysis on Spatial Temporal Distribution issue comprises:
Input taxi GPS record data extract effective taxi GPS record; Extract the trip of taxi relevant with the transport hub by map match; The average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come to the transport hub from each traffic zone and transport hub are gone to each traffic zone; Passenger flow to each traffic zone and transport hub in the three-dimensional city scene is carried out Visualization by flow graph, this passenger origin figure is made of the straight-line segment that all connect beginning-of-line and terminal point, article one, the passenger origin line segment points to terminal point by starting point, all starting points in traffic zone and terminal point are by the focus point unified representation of this traffic zone, and the thickness of a passenger origin line segment is directly proportional with the passenger flow flow of this flow direction.
Preferably, in described transport hub passenger flow statistics and the forecast analysis release module, metro passenger flow statistics in transport hub may further comprise the steps with the forecast analysis issue:
Input subway transportation card data are obtained the relevant effective subway in transport hub and are gone out line item; Input subway line data are to the day volume of the flow of passengers, every day of transport hub subway station, passenger flow was carried out statistical study at times; The factor of analyzing influence metro passenger flow is set up at times metro passenger flow forecast model; Passenger flow data according to reality is verified described at times metro passenger flow forecast model; Window expression to adding up and predicting the outcome and carry out histogram and curve map in three-dimension GIS.
Preferably, in described transport hub passenger flow statistics and the forecast analysis release module, taxi passenger flow statistics in transport hub may further comprise the steps with the forecast analysis issue:
Input taxi GPS record data extract effective taxi GPS record; Extract the trip of taxi relevant with the transport hub by map match; To the taxi vehicle day volume of the flow of passengers, every day of transport hub, passenger flow was carried out statistical study at times; The factor of analyzing influence taxi passenger flow is set up at times taxi passenger flow forecast model; Taxi passenger status flow data according to reality is verified described at times taxi passenger flow forecast model.
3 D intelligent traffic hinge passenger flow space-time analysis of the present invention and prognoses system are by merging and the analysis multi-source traffic information, quantize city dweller's trip spatial and temporal distributions relevant with the transport hub, set up the at times passenger flow Short-term Forecasting Model of each mode of transportation, the quantification support of transport hub management and planning is provided; Can the real-time accessibility of transport hub be analyzed and issue based on real-time dynamic information, improve the mass information service level of transport hub; Carry out comprehensive integration management and three-dimensional visible fractional analysis by the three-dimensional digital city technology, for decision maker, supvr and citizen provide more intuitively acquisition of information platform.
Description of drawings
Fig. 1 is one embodiment of the invention 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system configuration diagram;
Fig. 2 is one embodiment of the invention transport hub real-time traffic circle analysis issue schematic flow sheet;
Fig. 3 is one embodiment of the invention transport hub passenger flow Analysis on Spatial Temporal Distribution issue schematic flow sheet;
Fig. 4 is one embodiment of the invention transport hub passenger flow statistics and prediction schematic flow sheet.
Embodiment
Come the present invention is described in further detail below in conjunction with accompanying drawing and specific embodiment.
As shown in Figure 1, be one embodiment of the invention 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system configuration diagram, described 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system comprise: the multi-source data layer that comprises data, comprise the wide area information server layer and take described multi-source data layer and the described database layer functional module layer as the basis operation, wherein, described functional module layer comprises: the three-dimension GIS basic function module, being used for that traffic basis scene is carried out data loads, management, analysis and visual, and transport hub passenger flow space-time analysis carried out the Three-Dimensional Dynamic Visualization with predicting the outcome, described three-dimension GIS basic function module is with terrain data, image data, the city three-dimensional modeling data, basis road vectors data have the three-dimensional scenic operation as traffic basis contextual data, three-dimensional indoor and outdoor roaming is browsed, three-dimensional measurement is analyzed, and three-dimensional scenic object editing function; Real-time road is analyzed release module, be used at the issue of three-dimensional city scene and analysis real-time traffic information, described real-time road is analyzed the current Vehicle Speed that release module receives each highway section of being issued by special department in real time, grade classification to the Vehicle Speed degree of carrying out that the road is clear, utilize different color to show different the road is clear degree, as with redness, yellow, green represents respectively to block up, jogging, unobstructed traffic, update status according to the real-time road condition information that receives, the real-time road data that three-dimensional scenic is expressed dynamically update, and can service time progress bar check the real-time road of any time, for further transport hub passenger flow space-time analysis and predicted application; Transport hub real-time traffic circle is analyzed release module, be used for analyzing each highway section real time running speed that release module provides according to road network and described real-time road, the scope that can arrive the surrounding area take the transport hub as starting point in user's setting-up time analyzed with three-dimensional visualization showed; Transport hub passenger flow Analysis on Spatial Temporal Distribution release module, be used for the transport hub passenger flow of each mode of transportation go on a journey start-stop analysis and issue, described transport hub passenger flow Analysis on Spatial Temporal Distribution release module can add up and in the three-dimensional city scene visual every day with every day each mode of transportation of different time sections the transport hub passenger flow in the information of different terminals; Transport hub passenger flow statistics and forecast analysis and release module, for the transport hub volume of the flow of passengers of each mode of transportation being added up and predicting, described transport hub passenger flow statistics and forecast analysis release module are by statistics magnanimity multi-source traffic data, obtain every day and every day different time sections the transport hub volume of the flow of passengers of each mode of transportation, and utilize volume of the flow of passengers Short-term Forecasting Model, the passenger flows such as subway, taxi, long-distance passenger transportation are carried out short-term forecasting, and issue every day and every day passenger flow statistics at times and histogram and the curve map of prediction; Described real-time road is analyzed release module, transport hub real-time traffic circle is analyzed release module, transport hub passenger flow Analysis on Spatial Temporal Distribution release module and transport hub passenger flow statistics and all is connected with described three-dimension GIS basic function module with release module with forecast analysis.
In the above-described embodiments, described multi-source data layer can comprise subway transportation card data, taxi GPS record data, bus card-reading data, long-distance passenger transportation Che Faban record data and mobile phone location data etc., and these data have that storage is large, speedup is fast, real-time processing requirements high; Described database layer comprises topographic database, three-dimensional modeling data storehouse, city, basic traffic database, real time traffic data storehouse and historical traffic database etc., and all databases all are unified in the SQL Server data base management system (DBMS) and carry out unified storage and management.
As shown in Figure 2, be one embodiment of the invention transport hub real-time traffic circle analysis issue schematic flow sheet, transport hub real-time traffic circle analysis issue is the basis take the City Vector road data as network analysis, the Real-time Road travel speed that real-time road is analyzed release module and provided is connected on the corresponding highway section of road network, set up urban road network with this, then the transport loop time radius that arranges according to the user (for example: 20 minutes, 40 minutes, 1 hour etc.), utilize shortest path first, carry out the analysis of road network service range take the transport hub as starting point, at last the transport hub coverage diagram that generates is issued in the three-dimensional city scene, the method for visualizing of this transport loop is the translucent irregular planar zone that is superimposed upon on the three-dimensional city map, and the transport loop of different time radius can use the planar zone stack of different colours simultaneously.
As shown in Figure 3, be one embodiment of the invention transport hub passenger flow Analysis on Spatial Temporal Distribution issue schematic flow sheet.Wherein, transport hub metro passenger flow Analysis on Spatial Temporal Distribution issue is as the basis take historical subway transportation card data, extract the effective subway record of swiping the card, comprise transportation card ID, website enters the station, the departures website, enter the station the time, the departures time, add up each subway station passenger flow relevant with the transport hub, be the passenger flow of transport hub comprising destination and origin, respectively working day and weekend to add up classifications as two, the average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come from each subway station to the transport hub and transport hub are gone to each subway station, and in the three-dimensional city scene, the up/down volume of the flow of passengers of each ground iron spot is carried out Visualization by D prism map.Transport hub taxi passenger flow Analysis on Spatial Temporal Distribution issue is as the basis take taxi GPS record data, extract effective taxi GPS record, comprise taxi ID, the longitude and latitude that records each time, time, whether carrying waits raw information, from raw information, extract and obtain one day carrying number of times of each taxi, starting point latitude and longitude coordinates and time and terminal point latitude and longitude coordinates and the time of each carrying, map match is carried out in terminal and the urban transportation residential quarter of each time carrying trip, delimit the map area of transport hub, the trip of trip beginning or end in the body of a map or chart of transport hub is considered as the trip of taxi relevant with the transport hub, each traffic zone passenger flow relevant with the transport hub in the statistics city, be the passenger flow of transport hub comprising destination and origin, respectively working day and weekend to add up classifications as two, the average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come to the transport hub from each traffic zone and transport hub are gone to each traffic zone, passenger flow to each traffic zone and transport hub in the three-dimensional city scene is carried out Visualization by flow graph, this passenger origin figure is made of the straight-line segment that all connect beginning-of-line and terminal point, article one, the passenger origin line segment points to terminal point by starting point, all starting points in traffic zone and terminal point are by the focus point unified representation of this traffic zone, and the thickness of a passenger origin line segment is directly proportional with the passenger flow flow of this flow direction.Transport hub long-distance passenger transportation passenger flow Analysis on Spatial Temporal Distribution issue is to send out class data as the basis take long-distance passenger transportation, extract effective long-distance passenger transportation record, comprise long-distance regular bus license plate number, the starting point of dispatching a car, time, the terminus, long-distance distance, admission fee, long-distance type, patronage, examine manned number etc., add up each long-distance website passenger flow relevant with the transport hub, respectively working day and weekend to add up classifications as two, average day upper volume of passenger traffic that statistics is come to the transport hub from each long-distance passenger transportation website and and the transport hub average day lower volume of passenger traffic of going to each long-distance passenger transportation website, and in the three-dimensional city scene, carry out up/down volume of the flow of passengers D prism map at each long-distance passenger transportation website and show.
As shown in Figure 4, be one embodiment of the invention transport hub passenger flow statistics and prediction schematic flow sheet.Transport hub passenger flow statistics and prediction are that (comprise subway transportation card data, GPS data from taxi, long-distance passenger transportation send out class data etc.) is the basis take multi-source traffic data source, extract the separately effective trip data relevant with the transport hub, the per day volume of the flow of passengers of the various modes of transportation of statistics transport hub and every day be the average volume of the flow of passengers at times, by the statistical study to historical passenger flow, set up the passenger flow Short-term Forecasting Model of various modes of transportation, passenger flow is predicted, and will be predicted the outcome and in three-dimension GIS, carry out chart and express.
Transport hub of the present invention metro passenger flow statistics may further comprise the steps with prediction:
Input subway transportation card data are obtained the effective subway record of swiping the card, and comprise transportation card ID, the website that enters the station, the website that sets off, enter the station the time departures time;
In the week that the transport hub subway is entered the station and sets off the per day volume of the flow of passengers, every day of every day at times passenger flow (for example, per 2 hours statistics once) add up;
Different statistical time ranges according to period-sky-week-moon-year are added up the transport hub subway volume of the flow of passengers out of the station, analyze the relation of the correlative factors such as the volume of the flow of passengers and working day, weekend, vacation trip, work and rest rule.In a short time, for example, one month to half a year, for metro passenger flow present regular and stable, adopt regressive prediction model that metro passenger flow is carried out short-term forecasting.At first choose certain normal subway of January day part data volume of the flow of passengers out of the station as modeling sample, and the data of choosing week one after the modeling sample time period or two weeks are as the checking sample; Then choose the factor that may affect metro passenger flow, for example, several and period in week, modeling sample is carried out the factor variance analysis, the impact that each factor of factor variance analysis verification by repeatedly combination changes the volume of the flow of passengers; Choose passenger flow is changed influential factor, the at times passenger flow out of the station in the week is set up respectively regression model, the period of volume of the flow of passengers no significant difference in the week is adopted identical regression model.
For example, pass through two-way analysis of variance, find week several with the period for affect set off two key factors of passenger flow of subway, and the departures passenger flow whole day day part of Monday to Thursday changes indifference, then different with Friday, Saturday, Sunday, then the at times departures passenger flow on Monday to Thursday, Friday, Saturday, Sunday is set up respectively regression model, at first 16 hours of metro operation were divided into 8 periods by 2 hours periods, so that the time segment variable become a classification independent variable with 8 types, thereby produce 7 dummy variables.These four regression models are expressed as follows:
(1) passenger flow that sets off at times Monday to Thursday:
Flow_out_Mon＝a
1t
1+a
2t
2+a
3t
3+a
4t
4+a
5t
5+a
6t
6+a
7t
7+a
8。
(2) passenger flow that sets off at times Friday:
Flow_out_Fri＝b
1t
1+b
2t
2+b
3t
3+b
4t
4+b
5t
5+b
6t
6+b
7t
7+b
8。
(3) passenger flow that sets off at times Saturday:
Flow_out_Sat＝c
1t
1+c
2t
2+c
3t
3+c
4t
4+c
5t
5+c
6t
6+c
7t
7+c
8。
(4) passenger flow that sets off at times Sunday:
Flow_out_Sun＝d
1t
1+d
2t
2+d
3t
3+d
4t
4+d
5t
5+d
6t
6+d
7t
7+d
8。
Wherein, t
1, t
2... t
7It is the dummy variable of 8 periods.Work as t
1=1, t
2=t
3=...=t
7=0 o'clock, dependent variable represented the departures volume of the flow of passengers of first period; Work as t
2=1, t
1=t
3=...=t
7=0 o'clock, dependent variable represented the departures volume of the flow of passengers of second period; The like; And work as t
1=t
2=t
3=...=t
7=0 o'clock, dependent variable represented the departures volume of the flow of passengers of the 8th period.a
i, b
i, c
i, d
iBe respectively independent variable parameter and the constant term of four models.
Accuracy rate for each independent predicted value is calculated with absolute percent error (APE): APE=100%*| predicted value-actual value |/actual value, and use the checking sample that described at times metro passenger flow forecast model is carried out error rate and calculate.
Transport hub of the present invention taxi passenger flow statistics may further comprise the steps with prediction:
Input taxi GPS record data, obtain the start-stop data of effective taxi, comprise the raw informations such as taxi ID, starting point longitude and latitude, terminal point longitude and latitude, the starting point moment, the terminal point moment, from raw information, extract the starting point latitude and longitude coordinates obtain one day carrying number of times of each taxi, each carrying and time and the information such as terminal point latitude and longitude coordinates and time and set up special database table and manage at SQL Server database.
Described taxi GPS record data are carried out the city map coupling, and the map area of delimiting the transport hub is considered as the trip of taxi relevant with the transport hub with the trip of trip beginning or end in the body of a map or chart of transport hub;
To the per day volume of the flow of passengers of taxi and every day at times passenger flow add up;
Choose day part taxi departures in normal month volume of the flow of passengers as modeling sample, then modeling sample is carried out the repeated two-way analysis of variance of several and period of week, the otherness that changes by the volume of the flow of passengers in one week of two-way analysis of variance checking of repeatedly combination; At times passenger flow out of the station in one week is set up respectively regression model, to the identical regression model of period employing of volume of the flow of passengers no significant difference in the week.
For example, by two-way analysis of variance, find week several with the period for affect two key factors of taxi passenger flow, and the passenger flow whole day on Monday to Sunday variation indifference is then set up regression model to the at times taxi passenger flow unification on Monday to Sunday.Wherein regression model was divided into 12 periods with one day 24 hours by 2 hours periods so that the time segment variable become a classification independent variable with 12 types, thereby produce 11 dummy variables.This regression model is expressed as follows:
Flow_out＝a
1t
1+a
2t
2+a
3t
3+a
4t
4+a
5t
5+a
6t
6+a
7t
7+
a
8t
8+a
9t
9+a
10t
10+a
11t
11+a
12。
Wherein, t
1, t
2... t
11It is the dummy variable of 11 periods.Work as t
1=1, t
2=t
3=...=t
11=0 o'clock, dependent variable represented the departures volume of the flow of passengers of first period; Work as t
2=1, t
1=t
3=...=t
11=0 o'clock, dependent variable represented the departures volume of the flow of passengers of second period; The like; And work as t
1=t
2=t
3=...=t
11=0 o'clock, dependent variable represented the departures volume of the flow of passengers of the 12nd period.a
iIndependent variable parameter and constant term for model.
Accuracy rate for each independent predicted value is calculated with APE, according to the checking sample described at times taxi passenger flow forecast model is carried out error rate and calculates.
Transport hub of the present invention long-distance passenger transportation passenger flow statistics and prediction may further comprise the steps:
Input long-distance passenger transportation Che Faban record data, the valid data information of obtaining comprises the information such as long-distance regular bus license plate number, the starting point of dispatching a car, time, terminus, long-distance distance, admission fee, long-distance type, patronage, the manned number of nuclear;
The per day volume of the flow of passengers that long-distance passenger transportation is pulled in and sets off and every day, passenger flow was added up at times; Choose day part long-distance passenger transportation departures in normal month volume of the flow of passengers as modeling sample, then modeling sample is carried out the repeated two-way analysis of variance of several and period of week, the otherness that changes by the volume of the flow of passengers in one week of two-way analysis of variance checking of repeatedly combination; At times passenger flow out of the station in one week is set up respectively regression model, to the identical regression model of period employing of volume of the flow of passengers no significant difference in the week.
For example, pass through two-way analysis of variance, find week several with the period for affecting two key factors of taxi passenger flow, and the passenger flow whole day on Monday to Sunday changes all variant, then the at times taxi passenger status flow point on Monday to Sunday is not set up regression model, will be divided into 16 periods (since end 6 o'clock to 22 o'clock every day, take each hour as a period) every day, so that the time segment variable become a classification independent variable with 16 types, thereby produce 15 dummy variables.These seven regression models are expressed as follows:
(1) Monday passenger flow at times:
Flow_Mon＝a
1t
1+a
2t
2+a
3t
3.......+a
15t
15+a
16。
(2) Tuesday passenger flow at times:
Flow_Tue＝b
1t
1+b
2t
2+b
3t
3.......+b
15t
15+b
16。
(3) Wednesday passenger flow at times:
Flow_Wed＝c
1t
1+c
2t
2+c
3t
3.......+c
15t
15+c
16。
(4) Thursday passenger flow at times:
Flow_Thu＝d
1t
1+d
2t
2+d
3t
3.......+d
15t
15+d
16。
(5) Friday passenger flow at times:
Flow_Fri＝e
1t
1+e
2t
2+e
3t
3.......+e
15t
15+e
16。
(6) Saturday passenger flow at times:
Flow_Sat＝f
1t
1+f
2t
2+f
3t
3.......+f
15t
15+f
16。
(7) Sunday passenger flow at times:
Flow_Sun＝g
1t
1+g
2t
2+g
3t
3.......+g
15t
15+g
16。
Wherein, t
1t
2... ..t
15It is the dummy variable of 16 periods.Work as t
1=1, t
2=t
3=...=t
15=0 o'clock, dependent variable represented the departures volume of the flow of passengers of first period; Work as t
2=1, t
1=t
3=...=t
15=0 o'clock, dependent variable represented the departures volume of the flow of passengers of second period; The like; And work as t
1=t
2=t
3=...=t
15=0 o'clock, dependent variable represented the departures volume of the flow of passengers of the 16 period.a
ib
ic
id
ie
if
ig
iBe respectively independent variable parameter and the constant term of seven models.
Accuracy rate for each independent predicted value is calculated with APE, according to the checking sample described at times long-distance passenger transportation Passenger flow forecast model is carried out error rate and calculates.
3 D intelligent traffic hinge passenger flow space-time analysis of the present invention and prognoses system are by merging and the analysis multi-source traffic information, quantize city dweller's trip spatial and temporal distributions relevant with the transport hub, set up the at times passenger flow Short-term Forecasting Model of each mode of transportation, the quantification support of transport hub management and planning is provided; Can the real-time accessibility of transport hub be analyzed and issue based on real-time dynamic information, improve the mass information service level of transport hub; Carry out comprehensive integration management and three-dimensional visible fractional analysis by the three-dimensional digital city technology, for decision maker, supvr and citizen provide more intuitively acquisition of information platform.
Be understandable that, for the person of ordinary skill of the art, can make other various corresponding changes and distortion by technical conceive according to the present invention, and all these change the protection domain that all should belong to claim of the present invention with distortion.
Claims (5)
1. a 3 D intelligent traffic hinge passenger flow space-time analysis and prognoses system, it is characterized in that, passenger flow feature for the transport hub, comprise the multi-source data layer that comprises data, comprise wide area information server layer and the functional module layer take described multi-source data layer and described database layer as the basis operation, wherein, described functional module layer comprises:
The three-dimension GIS basic function module is used for traffic basis scene is carried out data loading, management, analysis and three-dimensional visualization, and transport hub passenger flow space-time analysis is carried out the Three-Dimensional Dynamic Visualization with predicting the outcome;
Real-time road is analyzed release module, is used at the issue of three-dimensional city scene and analysis real-time traffic information;
Transport hub real-time traffic circle is analyzed release module, expresses for the scope that can arrive the surrounding area take the transport hub as starting point in user's setting-up time is analyzed with three-dimensional visualization;
Transport hub passenger flow Analysis on Spatial Temporal Distribution release module is used for the transport hub passenger flow of each mode of transportation is carried out trip start-stop analysis and the three-dimensional visualization of each time period and expresses;
Transport hub passenger flow statistics and forecast analysis release module are used for the transport hub volume of the flow of passengers of each mode of transportation is added up and at times short-term forecasting;
Described real-time road is analyzed release module, transport hub real-time traffic circle is analyzed release module, transport hub passenger flow Analysis on Spatial Temporal Distribution release module and transport hub passenger flow statistics and all is connected with described three-dimension GIS basic function module with release module with forecast analysis.
2. 3 D intelligent traffic hinge space-time analysis according to claim 1 and prognoses system is characterized in that: in the passenger flow Analysis on Spatial Temporal Distribution release module of described transport hub, the step of transport hub metro passenger flow Analysis on Spatial Temporal Distribution issue comprises:
Input historical subway transportation card data, extract the effective subway record of swiping the card;
Add up each subway station passenger flow relevant with the transport hub, be the passenger flow of transport hub comprising destination and origin, respectively with working day and weekend as two statistics classifications, the average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come from each subway station to the transport hub and transport hub are gone to each subway station;
In the three-dimensional city scene, the up/down volume of the flow of passengers of each ground iron spot is carried out Visualization by D prism map.
3. 3 D intelligent traffic hinge space-time analysis according to claim 1 and prognoses system is characterized in that: in the passenger flow Analysis on Spatial Temporal Distribution release module of described transport hub, the step of transport hub taxi passenger flow Analysis on Spatial Temporal Distribution issue comprises:
Input taxi GPS record data extract effective taxi GPS record;
Extract the trip of taxi relevant with the transport hub by map match;
The average day lower volume of passenger traffic that average day upper volume of passenger traffic that statistics is come to the transport hub from each traffic zone and transport hub are gone to each traffic zone;
Passenger flow to each traffic zone and transport hub in the three-dimensional city scene is carried out Visualization by flow graph, this passenger origin figure is made of the straight-line segment that all connect beginning-of-line and terminal point, article one, the passenger origin line segment points to terminal point by starting point, all starting points in traffic zone and terminal point are by the focus point unified representation of this traffic zone, and the thickness of a passenger origin line segment is directly proportional with the passenger flow flow of this flow direction.
4. 3 D intelligent traffic hinge passenger flow space-time analysis according to claim 1 and prognoses system is characterized in that, in described transport hub passenger flow statistics and the forecast analysis release module, metro passenger flow statistics in transport hub may further comprise the steps with the forecast analysis issue:
Input subway transportation card data are obtained the relevant effective subway in transport hub and are gone out line item;
Input subway line data are to the day volume of the flow of passengers, every day of transport hub subway station, passenger flow was carried out statistical study at times;
The factor of analyzing influence metro passenger flow is set up at times metro passenger flow forecast model;
Passenger flow data according to reality is verified described at times metro passenger flow forecast model;
Window expression to adding up and predicting the outcome and carry out histogram and curve map in three-dimension GIS.
5. 3 D intelligent traffic hinge passenger flow space-time analysis according to claim 1 and prognoses system, it is characterized in that: in described transport hub passenger flow statistics and the forecast analysis release module, taxi passenger flow statistics in transport hub may further comprise the steps with the forecast analysis issue:
Input taxi GPS record data extract effective taxi GPS record;
Extract the trip of taxi relevant with the transport hub by map match;
To the taxi vehicle day volume of the flow of passengers, every day of transport hub, passenger flow was carried out statistical study at times;
The factor of analyzing influence taxi passenger flow is set up at times taxi passenger flow forecast model;
Taxi passenger status flow data according to reality is verified described at times taxi passenger flow forecast model.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105750151A CN103065205A (en) | 2012-12-26 | 2012-12-26 | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN2012105750151A CN103065205A (en) | 2012-12-26 | 2012-12-26 | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN103065205A true CN103065205A (en) | 2013-04-24 |
Family
ID=48107827
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN2012105750151A Pending CN103065205A (en) | 2012-12-26 | 2012-12-26 | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103065205A (en) |
Cited By (24)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103473620A (en) * | 2013-09-26 | 2013-12-25 | 青岛海信网络科技股份有限公司 | Prediction method and system for multiple traffic means of comprehensive passenger traffic hub |
| CN103914744A (en) * | 2014-04-23 | 2014-07-09 | 北京市市政工程设计研究总院有限公司 | Method and device for predicting subway station underground commercial passenger flow |
| CN104239958A (en) * | 2013-06-19 | 2014-12-24 | 上海工程技术大学 | Short-time passenger flow forecasting method suitable for urban rail transit system |
| CN104573072A (en) * | 2015-01-26 | 2015-04-29 | 江苏欧索软件有限公司 | Three-dimensional geographic information sharing service system based on heterogeneous digital resource fusion |
| CN105095481A (en) * | 2015-08-13 | 2015-11-25 | 浙江工业大学 | Large-scale taxi OD data visual analysis method |
| CN105184728A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Construction method of customized regular passenger coach transportation demand thermodynamic diagram |
| CN105184409A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Customized bus planned route travel demand thermodynamic diagram construction method |
| CN105184410A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Construction method of customized freight demand thermodynamic diagram |
| CN105810002A (en) * | 2016-04-20 | 2016-07-27 | 浙江大学 | Self-optimizable efficient public transit system based on Internet of Things and neural network |
| CN105808912A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Method and system for visually analyzing traffic track data |
| CN106599241A (en) * | 2016-12-20 | 2017-04-26 | 北京超图软件股份有限公司 | Big data visual management method for GIS software |
| CN106650976A (en) * | 2015-10-29 | 2017-05-10 | 深圳市综合交通运行指挥中心 | Travel analysis and forecasting method and system, and travel analysis and forecasting method and system based on IC card |
| CN106933956A (en) * | 2017-01-22 | 2017-07-07 | 深圳市华成峰科技有限公司 | Data digging method and device |
| 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 |
| CN107688873A (en) * | 2017-08-29 | 2018-02-13 | 南京轨道交通***工程有限公司 | Metro passenger flow Forecasting Methodology based on big data analysis |
| CN108418902A (en) * | 2017-11-20 | 2018-08-17 | 北京万相融通科技股份有限公司 | A kind of railway combined transport hub integrated control system of wisdom |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN110188156A (en) * | 2019-06-04 | 2019-08-30 | 国家电网有限公司 | A kind of work transmission line three dimensional design achievement key message extracting method and system |
| CN110223514A (en) * | 2019-06-06 | 2019-09-10 | 北京交通发展研究院 | Urban transportation running state analysis method, apparatus and electronic equipment |
| CN110570004A (en) * | 2018-06-05 | 2019-12-13 | 上海申通地铁集团有限公司 | subway passenger flow prediction method and system |
| CN110751102A (en) * | 2019-10-22 | 2020-02-04 | 天津财经大学 | Kyojin Ji three-ground airport passenger flow correlation analysis method and device |
| CN110751325A (en) * | 2019-10-16 | 2020-02-04 | 中国民用航空总局第二研究所 | Suggestion generation method, traffic hub deployment method, device and storage medium |
| CN111627107A (en) * | 2020-05-09 | 2020-09-04 | 浙江浙大中控信息技术有限公司 | Rail transit line network passenger flow visual analysis method based on GIS |
| CN113468243A (en) * | 2021-07-02 | 2021-10-01 | 金冰峰 | Subway passenger flow analysis and prediction method and system |
-
2012
- 2012-12-26 CN CN2012105750151A patent/CN103065205A/en active Pending
Non-Patent Citations (1)
| Title |
|---|
| 张昕等: "基于实时数据的交通枢纽客流态势研究", 《第七届中国智能交通年会优秀论文集——智能交通技术》 * |
Cited By (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104239958A (en) * | 2013-06-19 | 2014-12-24 | 上海工程技术大学 | Short-time passenger flow forecasting method suitable for urban rail transit system |
| CN103473620B (en) * | 2013-09-26 | 2016-09-21 | 青岛海信网络科技股份有限公司 | Comprehensive passenger transport hub many modes of transportation Forecasting Methodology and system |
| CN103473620A (en) * | 2013-09-26 | 2013-12-25 | 青岛海信网络科技股份有限公司 | Prediction method and system for multiple traffic means of comprehensive passenger traffic hub |
| 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 |
| CN103914744B (en) * | 2014-04-23 | 2016-10-26 | 北京市市政工程设计研究总院有限公司 | A kind of subway station underground commerce passenger flow forecasting and device |
| CN103914744A (en) * | 2014-04-23 | 2014-07-09 | 北京市市政工程设计研究总院有限公司 | Method and device for predicting subway station underground commercial passenger flow |
| CN105808912B (en) * | 2014-12-31 | 2019-07-02 | 中国科学院深圳先进技术研究院 | A kind of visual analysis method, the system of traffic track data |
| CN105808912A (en) * | 2014-12-31 | 2016-07-27 | 中国科学院深圳先进技术研究院 | Method and system for visually analyzing traffic track data |
| CN104573072A (en) * | 2015-01-26 | 2015-04-29 | 江苏欧索软件有限公司 | Three-dimensional geographic information sharing service system based on heterogeneous digital resource fusion |
| CN105095481A (en) * | 2015-08-13 | 2015-11-25 | 浙江工业大学 | Large-scale taxi OD data visual analysis method |
| CN105095481B (en) * | 2015-08-13 | 2018-06-26 | 浙江工业大学 | Extensive taxi OD data visualization analysis methods |
| CN105184728A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Construction method of customized regular passenger coach transportation demand thermodynamic diagram |
| CN105184409A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Customized bus planned route travel demand thermodynamic diagram construction method |
| CN105184410A (en) * | 2015-09-15 | 2015-12-23 | 广州地理研究所 | Construction method of customized freight demand thermodynamic diagram |
| CN106650976A (en) * | 2015-10-29 | 2017-05-10 | 深圳市综合交通运行指挥中心 | Travel analysis and forecasting method and system, and travel analysis and forecasting method and system based on IC card |
| CN105810002A (en) * | 2016-04-20 | 2016-07-27 | 浙江大学 | Self-optimizable efficient public transit system based on Internet of Things and neural network |
| CN106599241A (en) * | 2016-12-20 | 2017-04-26 | 北京超图软件股份有限公司 | Big data visual management method for GIS software |
| CN106599241B (en) * | 2016-12-20 | 2020-06-30 | 北京超图软件股份有限公司 | Visual management method for big data in GIS software |
| CN106933956A (en) * | 2017-01-22 | 2017-07-07 | 深圳市华成峰科技有限公司 | Data digging method and device |
| CN106933956B (en) * | 2017-01-22 | 2020-12-01 | 深圳市华成峰科技有限公司 | Data mining method and device |
| CN107688873A (en) * | 2017-08-29 | 2018-02-13 | 南京轨道交通***工程有限公司 | Metro passenger flow Forecasting Methodology based on big data analysis |
| CN108418902A (en) * | 2017-11-20 | 2018-08-17 | 北京万相融通科技股份有限公司 | A kind of railway combined transport hub integrated control system of wisdom |
| CN108418902B (en) * | 2017-11-20 | 2024-04-05 | 北京万相融通科技股份有限公司 | Intelligent railway comprehensive transportation junction integrated control system |
| CN110570004A (en) * | 2018-06-05 | 2019-12-13 | 上海申通地铁集团有限公司 | subway passenger flow prediction method and system |
| CN109543883A (en) * | 2018-10-26 | 2019-03-29 | 上海城市交通设计院有限公司 | A kind of hinge flow space-time distribution prediction modeling method based on multisource data fusion |
| CN110188156A (en) * | 2019-06-04 | 2019-08-30 | 国家电网有限公司 | A kind of work transmission line three dimensional design achievement key message extracting method and system |
| CN110223514A (en) * | 2019-06-06 | 2019-09-10 | 北京交通发展研究院 | Urban transportation running state analysis method, apparatus and electronic equipment |
| CN110223514B (en) * | 2019-06-06 | 2020-05-19 | 北京交通发展研究院 | Urban traffic running state analysis method and device and electronic equipment |
| CN110751325A (en) * | 2019-10-16 | 2020-02-04 | 中国民用航空总局第二研究所 | Suggestion generation method, traffic hub deployment method, device and storage medium |
| CN110751102A (en) * | 2019-10-22 | 2020-02-04 | 天津财经大学 | Kyojin Ji three-ground airport passenger flow correlation analysis method and device |
| CN110751102B (en) * | 2019-10-22 | 2023-12-22 | 天津财经大学 | Beijing Ji three-place airport passenger flow correlation analysis method and device |
| CN111627107A (en) * | 2020-05-09 | 2020-09-04 | 浙江浙大中控信息技术有限公司 | Rail transit line network passenger flow visual analysis method based on GIS |
| CN113468243A (en) * | 2021-07-02 | 2021-10-01 | 金冰峰 | Subway passenger flow analysis and prediction method and system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103065205A (en) | Three-dimensional intelligent transportation junction passenger flow time-space analysis and prediction system | |
| Chen et al. | Development of indicators of opportunity-based accessibility | |
| Motta et al. | Personal mobility service system in urban areas: The IRMA project | |
| Yazici et al. | A big data driven model for taxi drivers' airport pick-up decisions in new york city | |
| Chen et al. | Data analytics approach for travel time reliability pattern analysis and prediction | |
| CN101694706A (en) | Modeling method of characteristics of population space-time dynamic moving based on multisource data fusion | |
| Pramanik | Carpooling solutions using machine learning tools | |
| CN109637134A (en) | A kind of public transport device matching process | |
| Zhou et al. | Monitoring transit-served areas with smartcard data: A Brisbane case study | |
| Sándor et al. | Role of integrated parking information system in traffic management | |
| Zhang et al. | Demand, supply, and performance of street-hail taxi | |
| Ozbay et al. | Big data and the calibration and validation of traffic simulation models | |
| Rezzouqi et al. | Analyzing the accuracy of historical average for urban traffic forecasting using *** maps | |
| Tettamanti et al. | Road traffic measurement and related data fusion methodology for traffic estimation | |
| Tian et al. | Identifying residential and workplace locations from transit smart card data | |
| Hadi et al. | Framework for multi-resolution analyses of advanced traffic management strategies. | |
| Vitale et al. | A smartphone based DSS platform for assessing transit service attributes | |
| Pavlyuk et al. | Spatiotemporal dynamics of public transport demand: a case study of Riga | |
| Salanova et al. | Use of probe data generated by taxis | |
| Barth et al. | Passenger density and flow analysis and city zones and bus stops classification for public bus service management | |
| Morency et al. | Using 5 parallel passive data streams to report on a wide range of mobility options | |
| Varga et al. | Overview of taxi database from viewpoint of usability for traffic model development: a case study for Budapest | |
| Esztergár-Kiss | Optimization of multimodal travel chains | |
| Bertini et al. | Integrating Geographic Information Systems and Intelligent Transportation Systems to Improve Incident Management and Life Safety. | |
| Chen et al. | Exploring Human Spatio-Temporal Travel Behavior Based on Cellular Network Data: A Case Study of Hangzhou, China. |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C12 | Rejection of a patent application after its publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20130424 |