CN108364464A - A kind of public transit vehicle hourage modeling method based on probabilistic model - Google Patents
A kind of public transit vehicle hourage modeling method based on probabilistic model Download PDFInfo
- Publication number
- CN108364464A CN108364464A CN201810107601.0A CN201810107601A CN108364464A CN 108364464 A CN108364464 A CN 108364464A CN 201810107601 A CN201810107601 A CN 201810107601A CN 108364464 A CN108364464 A CN 108364464A
- Authority
- CN
- China
- Prior art keywords
- public transit
- platform
- time
- transit vehicle
- hourage
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 238000009826 distribution Methods 0.000 claims abstract description 24
- 238000005516 engineering process Methods 0.000 abstract description 4
- 230000010365 information processing Effects 0.000 abstract description 2
- 238000010586 diagram Methods 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 239000000284 extract Substances 0.000 description 3
- 230000003993 interaction Effects 0.000 description 2
- 238000003915 air pollution Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000001680 brushing effect Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000000605 extraction Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 238000005192 partition Methods 0.000 description 1
- 230000008092 positive effect Effects 0.000 description 1
- 230000001737 promoting effect Effects 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
- G08G1/0129—Traffic data processing for creating historical data or processing based on historical data
-
- 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
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G06Q50/40—
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Abstract
The public transit vehicle hourage modeling method based on probabilistic model that the invention discloses a kind of, belongs to ITS Information processing technology field.The method of the present invention includes:The operation data of public transit vehicle is acquired and is handled;It is fitted using offset lognormal distributions road trip time between platform;The interbehavior for considering the multi-line public transport vehicle with platform is modeled as a fifo queue to being lined up into platform, is modeled to bus platform berthing time based on probabilistic model;According to each road trip time and each platform berthing time, the route hourage of public transit vehicle is obtained, and analyzes distribution, expectation, variance and the reliability of hourage.The method of the present invention is suitable for public transit vehicle predicting travel time, and prediction result is accurate;The present invention can analyze the reason of hourage fluctuation, to promote Level-of-Services of Public Transit.
Description
Technical field
The invention belongs to ITS Information processing technology field, specifically a kind of bus based on probabilistic model
Hourage modeling method.
Background technology
Currently, in face of continuous increased Urban traffic demand, congestion in road, air pollution and limited land resource,
Many cities start to carry out the trip theory in " public transport city ", and " public transport city ", which passes through, promotes urban public transport service water
It is flat, it encourages people to reduce private car trip, then selects urban public transport trip.Public transit vehicle trip time dependability is public
The key element of level of service altogether, on the one hand, trip time dependability is that traveler is attracted to select the important of bus trip
Factor, predicting travel time are also the important component of intelligent passenger service system, such as punctuality rate prediction, delay time at stop prediction
With arrival time prediction etc.;On the other hand, predicting travel time is the important indicator of bus operation, accurate predicting travel time
Public transport company can be helped to formulate counter-measure in advance, promote public transit system efficiency of operation, reduce operation cost.
In terms of predicting travel time, the prior art is principally dedicated to the pre- of private car trip time dependability and fluctuation
It surveys, such as active path planning, E.T.A estimation, analysis foundation are road section or path.However, public transit vehicle trip
Row time and private car hourage are dramatically different, and in addition to road trip time, public transit vehicle hourage is also by passenger
Garage is the influence of (i.e. platform berthing time), and when platform is stopped, public transit vehicle needs to be lined up on platform, waiting Passengen
It gets off and drives into major trunk roads from platform, these processes are all the important component of public transport hourage, and are related to same stand
The interbehavior of platform multi-line public transport vehicle.
In addition, the prior art mainly by OLS (common least square method), SVR (support vector regression), neural network and
The model predictions private car hourage such as deep learning, it is predicted value to obtain result;For public transit vehicle hourage is analyzed,
These Predicting Techniques cannot analyze the size and reason of the fluctuation of public transport hourage, cannot analyze the behavior of getting on the bus of passenger, cannot
Consider the interbehavior with multi-line public transport vehicle between platform.
Invention content
The purpose of the present invention is to overcome above-mentioned the deficiencies in the prior art, provides a kind of public transit vehicle trip based on probabilistic model
Row time modeling method, to analyze the reliability of the public transport hourage under different traffic and passenger demand state.
A kind of public transit vehicle hourage modeling method based on probabilistic model provided by the invention, is as follows:
Step 1, the operation data of all public transit vehicles of circuit to be studied is acquired, including:It is driven out to the time from inception point, reaches
Each intermediate platform time is driven out to each intermediate platform time, the time of reaching terminal and each platform and gets on the bus number;
Step 2, it is fitted using offset lognormal distributions road trip time between platform;
Step 3, the process that platform is entered to public transit vehicle models, which is:It is lined up into platform, waiting Passengen
It gets on or off the bus, drive into major trunk roads from platform;It is modeled as first in first out (FIFO) queue to being lined up into platform, it is contemplated that with station
The interbehavior of the multi-line public transport vehicle of platform;Passenger getting on/off is calculated according to passenger getting on/off number to take;Use normal distribution
Fitting public transit vehicle drives into the time of major trunk roads from platform.Public transit vehicle platform berthing time is obtained, public transit vehicle platform is stopped
Time is queuing timePassenger getting on/off time tbWith drive into the sum of major trunk roads time β.
Step 4, the road trip time and platform berthing time obtained according to step 2 and step 3, calculates public transit vehicle
Route hourage, and analyze distribution, expectation, variance and the reliability of hourage.
The route hourage T of public transit vehicle be all road trip times and all the sum of platform berthing times,
It is expressed as:
Wherein, IRFor all sections of circuit to be studied, SRFor all bus platforms of circuit to be studied, tiFor bus
Hourage on the i of section, tsFor public transit vehicle platform s berthing time.
Compared with the existing technology, the advantages and positive effects of the present invention are:
(1) different from private car travel time prediction method, the method for the present invention not only allows for road trip time, also examines
Public transit vehicle platform berthing time is considered, this makes more to be applicable in public transit vehicle predicting travel time.
(2) present invention models public transport hourage by probabilistic model, and section trip is analyzed using modelling method of probabilistic
The influence of row time and passenger loading behavior to hourage, with multi-line public transport vehicle interbehavior between platform, and the trip of obtaining
The probability analysis of row time, in addition to forecast function, additionally it is possible to which the reason of analyzing hourage fluctuation, analysis hourage is reliable
Property, this is most important to promoting Level-of-Services of Public Transit and efficiency of operation.
(3) present invention models Public Transit Bus Stopping platform process, analyzes the interaction of same platform multi-line public transport vehicle
Effect, this, which is other prediction techniques, to consider.
Description of the drawings
Fig. 1 is the flow diagram of the public transit vehicle hourage modeling method of the present invention;
Fig. 2 is that the method for the present invention is the schematic diagram that public transit vehicle platform stops modeling;
Fig. 3 is public bus network schematic diagram in embodiment;
Fig. 4 is models fitting result schematic diagram in embodiment.
Specific implementation mode
Below in conjunction with drawings and examples, the present invention is described in further detail.
The present invention provides a kind of public transit vehicle hourage modeling method based on probabilistic model, and flow is as shown in Figure 1, packet
Include following steps:
Step 1) data acquire and processing.Data used include bus IC card brushing card data and bus GPS data, to institute
It studies all operation public transit vehicles of circuit and extracts following information:It is driven out to the time from inception point, arrival each intermediate platform time, sails
Go out each intermediate platform time, the time of reaching terminal, each platform are got on the bus number.For the interaction for studying with platform multi-line public transport vehicle
Situation, it is also necessary to which, by the different circuit public transit vehicle operation states of all intermediate platforms, required extraction information is same as above.
Step 2) calculates road trip time between platform.First, the section trip between platform is distributed with offset lognormal
The row time is fitted, and lognormal distributions can be fitted the situation of road trip time distribution peaks Forward, and increased inclined
Shifting amount can portray public transit vehicle road-section average hourage.
It is assumed that road trip time obeys offset lognormal distributions between platform, road trip time can calculate between platform
For:
ti=λi+exp(μi+σizi) (1)
Wherein, tiIndicate hourage of the public transit vehicle on the i of section, i is positive integer;λiIndicate the unimpeded row in the section
The time is sailed, is distributions shift amount;exp(μi+σizi) indicate the part beyond unimpeded running time, lognormal distributions are obeyed,
Wherein μi、σiRespectively exceed the mean value and variance of running time, ziFor standardized normal distribution.According to above formula, section i trips can be obtained
The row time it is expected E (ti) and variance Var (ti) be respectively:
Step 3), which is lined up, enters platform time modeling.As shown in Fig. 2, when public transit vehicle drives into platform, it is understood that there may be its
He is circuit public transit vehicle upper visitor or lower visitor just in platform, needs that All other routes public transit vehicle on-board and off-board is waited for complete and sail at this time
When going out platform, which could enter platform, which can be described as a fifo queue.
If platform serial number s ∈ SR, SRFor the bus platform set of circuit to be studied, s is positive integer;If removing line to be studied
The collection of other all public bus networks for crossing platform s is combined into L outside roads, when the public transit vehicle of circuit to be studied drives into platform s
The Probability p of public transit vehicle from circuit l also in the queuelsObey bernoulli distribution as follows:
Wherein,For according to the empirical two circuits public transit vehicle collision probability of operation, MsIt is to be studied
The bus of circuit and circuit l are in the number that meets of platform s, NsThe number of platform s is crossed for the public transit vehicle of circuit to be studied,It is 1 for parameter,Bernoulli distribution.The time that then public transit vehicle is waited in lineFor:
Wherein tlsIn the boarding and alighting time of platform s and it is driven out to the sum of platform time for circuit l public transit vehicles.
Step 4) passenger getting on/off, which takes, to be calculated.It is assumed that public transit vehicle spends time α above and below everyone, then on public transit vehicle
Lower visitor's time will depend on the maximum number of upper visitor and lower visitor, therefore boarding and alighting time tbIt can be calculated as
WhereinThe number respectively got off and got on the bus.
Step 5) public transit vehicle drives into major trunk roads time match.According to previous research conclusion, present invention normal distribution
Fitting bus drives into the time β of major trunk roads, as follows:
Wherein μmIt is the average time that public transit vehicle drives into major trunk roads, σmFor the variance of the time.
Step 6) public transit vehicle platform berthing time summarizes.As shown in Fig. 2, public transit vehicle platform berthing time is when being lined up
Between, the passenger getting on/off time and the sum of drive into the major trunk roads time, same platform multi-line is considered in queuing time calculating process
The interbehavior of public transit vehicle, passenger getting on/off time consider passenger loading behavior, and public affairs are considered driving into major trunk roads part
Hand over the interbehavior of vehicle and major trunk roads vehicle, the total berthing time t of public transit vehiclesIt can calculate as follows:
The expectation of platform berthing time and variance are respectively
Step 7) public transit vehicle route hourage is fitted.Route hourage T is road trip time TLStop with platform
By time TSThe sum of, traditional private car travel time prediction method mainly considers road trip time, therefore cannot analyze public affairs
The platform of vehicle is handed over to stop behavior.
Wherein, IRBy research circuit all sections, SRBy research circuit all bus platforms.
Route hourage it is expected and variance is respectively
Wherein, ρijThe hourage related coefficient of section i and section j is indicated, if the velocity vector of section i and section j point
It Wei not XiAnd Xj, then ρijIt is represented by:
Embodiment
Illustrate the public transit vehicle hourage the present invention is based on probabilistic model with reference to an example as shown in Figure 3
Modeling method, it is specific as follows:
1), data acquire.As shown in figure 3,68 road row public bus network of the Hangzhou selection 2017.05.01 to 2017.05.31
As research object, 68 tunnels amount to 11 platforms, 11.73 kilometers of overall length.Extract 68 tunnels all IC card swipe the card record and GPS note
Record, it includes field that IC card, which is swiped the card and recorded,:Card number, charge time, circuit ID, vehicle-mounted machine ID, GPS data include following field:Vehicle
Carrier aircraft ID, the time, longitude, latitude, station identification, in-track platform mark are driven out to.It extracts simultaneously all by 68 road intermediate platforms
Public bus network data, data format is as above.
2) time leaving from station, is extracted and number of getting on the bus.Arrival time be calculated as the first time occur in-track platform mark when
Between;Time leaving from station is the time of mark leaving from station occur for the first time;Number of getting on the bus is that two continuous platforms reach in identified time section
Swipe the card record number.Other are same as above by the circuit extracting method of intermediate platform.
3), road trip time is fitted between platform.68 k-path partitions are 10 sections by 11 bus platforms, with offset
Lognormal fitting of distribution results are as shown in table 1 below:
1 road trip time of table
It is examined by Kolmogorov-Smirnov (KS), it is all to fit within 0.05 level significantly, illustrate present invention side
The feasibility of method.
4) queuing time that, enters the station is fitted.By taking the 10th platform " crossings Wen Hui " as an example, circuit 135,187,535,2,105,
84 and 90 all pass through the platform;When 68 tunnels reach the platform, the probability that All other routes are just being got on or off the bus in the platform waiting Passengen,
And the number of getting on the bus that is averaged of each circuit can count as shown in table 2 below:
Enter the station 2 platform of table " crossings Wen Hui " queuing time
It is assumed that getting on or off the bus, everyone takes 3.23 seconds, and 68 tunnels can be calculated as in the queuing time of the platform:3.23* (4.3%*
3.49+9.2%*3.58+2.0%*2.96+5.4%*2.67+4.2%*1.6+3.6%*1.7+4.4 %*2.77)=6.24s.
5), pick-up time is fitted per capita.Present invention least square regression OLS fitting boarding and alighting time and get on the bus number it
Between relationship.Gained relational expression is y=3.23x+7.21, R2=0.346, regression coefficient is horizontal notable 0.05.
6) major trunk roads, are driven into and take fitting.Major trunk roads are driven into normal distribution fitting to take, and obtain following relational expression
β~N (9.74,1.552) (12)
7), platform berthing time calculates.Platform berthing time is queuing time, passenger getting on/off time and drives into major trunk roads
The sum of time.Result of calculation is as shown in table 3 below:
The platform berthing time of 3 68 road vehicles of table
8), route hourage is estimated.Route hourage is the sum of road trip time and platform berthing time.
Therefore the route hourage of 68 road car is desired for 1333.61+216.72=1550.33s, the route of 68 road car
The variance of hourage is 264.39+79.99=344.38s.It is sampled by bootstrap, route hourage can be obtained
Distribution, Fig. 4 shows the route hourage of fitting and true route hourage.It can be seen from the figure that utilizing this
The route hourage of inventive method fitting and difference of true route hourage are smaller, therefore, can utilize present invention side
Method relatively accurately analyzes the reliability of public transport hourage under different traffic and passenger demand state, public for being promoted
Level of service and efficiency of operation altogether.
Claims (8)
1. a kind of public transit vehicle hourage modeling method based on probabilistic model, which is characterized in that include the following steps:
Step 1, the operation data of all public transit vehicles of circuit to be studied is acquired, including:From inception point be driven out to the time, reach it is each in
Between the platform time, be driven out to each intermediate platform time, the time of reaching terminal and each platform and get on the bus number;
Step 2, it is fitted using offset lognormal distributions road trip time between platform;
Step 3, the process that platform is entered to public transit vehicle models, which is:It is lined up into above and below platform, waiting Passengen
Vehicle drives into major trunk roads from platform;It is modeled as a fifo queue calculating bus queuing time, root to being lined up into platform
According to passenger getting on/off number calculate the passenger getting on/off time, with normal distribution be fitted public transit vehicle from platform drive into major trunk roads when
Between;Public transit vehicle platform berthing time is obtained, public transit vehicle platform berthing time is queuing timePassenger getting on/off time tb
With drive into the sum of major trunk roads time β;
Step 4, the route hourage of public transit vehicle is obtained, and analyzes distribution, expectation, variance and the reliability of hourage;
Wherein, the route hourage T of public transit vehicle be all road trip times and all the sum of platform berthing times,
It is expressed as:IRFor all sections of circuit to be studied, SRFor all bus platforms of circuit to be studied, ti
For hourage of the public transit vehicle on the i of section, tsFor public transit vehicle platform s berthing time.
2. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1, feature exist
In in the step 1, the operation data of the public transit vehicle of the different circuits of all intermediate platforms is passed through in also acquisition.
3. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1, feature exist
In, in the step 2, hourage t of the public transit vehicle on the i of sectioniIt calculates as follows:
ti=λi+exp(μi+σizi);
Wherein, λiIt indicates the unimpeded running time in the section, is distributions shift amount;exp(μi+σizi) indicate beyond it is unimpeded when driving
Between part, obey lognormal distribution, wherein μi、σiRespectively exceed the mean value and variance of running time, ziJust for standard
State is distributed;
Obtain the expectation E (t of section i houragesi) and variance Var (ti) be respectively:
4. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1, feature exist
In in the step 3, calculating public transit vehicle queuing time, method is as follows:
If to the bus platform s of circuit to be studied, other public bus network collection for entering the platform are combined into L in addition to circuit to be studieds,
The Probability p of public transit vehicle also in the queue when the public transit vehicle of circuit to be studied drives into platform s from circuit llsFor:
Wherein,For according to the public transit vehicle collision probability for runing empirical circuit to be studied and circuit l, Ms
It is the bus of circuit to be studied and circuit l in the number that meets of platform s, NsPublic transit vehicle for circuit to be studied crosses platform
The number of s,It is 1 for parameter,Bernoulli distribution;
The time that then public transit vehicle is lined upIt is expressed as:
Wherein, tlsFor circuit l public transit vehicle platform s boarding and alighting time and be driven out to the sum of platform time.
5. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1 or 4, feature
It is, in the step 3, the method for calculating the passenger getting on/off time is as follows:
Everyone is arranged, and public transit vehicle spends the time for α up and down, then public transit vehicle boarding and alighting time depends on upper objective and lower visitor's
Passenger getting on/off is taken t by maximum numberbFor:
Wherein,Respectively in the number of platform s got off and got on the bus.
6. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1 or 4, feature
It is, in the step 3, public transit vehicle drives into the time β of major trunk roads from platform, is fitted with normal distribution, indicates as follows:
Wherein, μm、σmIt is average time and the time variance that public transit vehicle drives into major trunk roads respectively.
7. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1 or 4, feature
It is, in the step 3, public transit vehicle platform berthing time tsIt is as follows:
The expectation of platform berthing time and variance difference are as follows:
8. a kind of public transit vehicle hourage modeling method based on probabilistic model according to claim 1 or 4, feature
It is, in the step 4,
Route hourage it is expected that E (T) is:
Route hourage variance Var (T) is:
Wherein, ρijThe related coefficient for indicating section i and section j, if the velocity vector of section i and section j are respectively XiAnd Xj, then
ρijIt is represented by:
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810107601.0A CN108364464B (en) | 2018-02-02 | 2018-02-02 | Probability model-based public transport vehicle travel time modeling method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810107601.0A CN108364464B (en) | 2018-02-02 | 2018-02-02 | Probability model-based public transport vehicle travel time modeling method |
Publications (2)
Publication Number | Publication Date |
---|---|
CN108364464A true CN108364464A (en) | 2018-08-03 |
CN108364464B CN108364464B (en) | 2020-10-16 |
Family
ID=63004400
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810107601.0A Active CN108364464B (en) | 2018-02-02 | 2018-02-02 | Probability model-based public transport vehicle travel time modeling method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108364464B (en) |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109637143A (en) * | 2019-01-22 | 2019-04-16 | 江苏智通交通科技有限公司 | Improved Travel Time Reliability analysis method |
CN112990694A (en) * | 2021-03-11 | 2021-06-18 | 平安科技(深圳)有限公司 | Bus stop traffic capacity analysis method, device, equipment and storage medium |
CN113053095A (en) * | 2021-03-27 | 2021-06-29 | 李文祥 | Network taxi booking system and method with low vacant seat rate |
CN113470366A (en) * | 2021-09-01 | 2021-10-01 | 南通华豪巨电子科技有限公司 | Intelligent bus stop time prediction method and system based on big data |
CN115798211A (en) * | 2022-11-21 | 2023-03-14 | 长安大学 | Control method, system, equipment and medium for preventing internet public transport from being disconnected and mixed |
CN116704763A (en) * | 2023-06-13 | 2023-09-05 | 大连海事大学 | Intelligent bus team dynamic formation method considering bus operation scheme |
Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578267A (en) * | 2012-07-18 | 2014-02-12 | 北京掌城科技有限公司 | Bus arrival predication method and system based on bus GPS data |
CN104200648A (en) * | 2014-08-21 | 2014-12-10 | 四川大学 | Road section average travelling time calculation method based on electronic license plate |
CN105390013A (en) * | 2015-11-18 | 2016-03-09 | 北京工业大学 | Method for predicting bus arrival time based on bus IC card |
CN106504516A (en) * | 2016-10-24 | 2017-03-15 | 东南大学 | One kind is based on the informationalized multi-form bus dynamic dispatching method in bus station |
CN106781506A (en) * | 2017-02-21 | 2017-05-31 | 济南全通信息科技有限公司 | The real time execution level evaluation method of urban public traffic network on a large scale based on bus GPS data |
CN106845768A (en) * | 2016-12-16 | 2017-06-13 | 东南大学 | Bus hourage model building method based on survival analysis parameter distribution |
-
2018
- 2018-02-02 CN CN201810107601.0A patent/CN108364464B/en active Active
Patent Citations (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN103578267A (en) * | 2012-07-18 | 2014-02-12 | 北京掌城科技有限公司 | Bus arrival predication method and system based on bus GPS data |
CN104200648A (en) * | 2014-08-21 | 2014-12-10 | 四川大学 | Road section average travelling time calculation method based on electronic license plate |
CN105390013A (en) * | 2015-11-18 | 2016-03-09 | 北京工业大学 | Method for predicting bus arrival time based on bus IC card |
CN106504516A (en) * | 2016-10-24 | 2017-03-15 | 东南大学 | One kind is based on the informationalized multi-form bus dynamic dispatching method in bus station |
CN106845768A (en) * | 2016-12-16 | 2017-06-13 | 东南大学 | Bus hourage model building method based on survival analysis parameter distribution |
CN106781506A (en) * | 2017-02-21 | 2017-05-31 | 济南全通信息科技有限公司 | The real time execution level evaluation method of urban public traffic network on a large scale based on bus GPS data |
Non-Patent Citations (1)
Title |
---|
计晓昕: "公交车到站时间预测模型与实证研究", 《中国优秀硕士学位论文全文数据库 工程科技Ⅱ辑》 * |
Cited By (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109637143A (en) * | 2019-01-22 | 2019-04-16 | 江苏智通交通科技有限公司 | Improved Travel Time Reliability analysis method |
WO2020151294A1 (en) * | 2019-01-22 | 2020-07-30 | 江苏智通交通科技有限公司 | Improved method for analyzing travel time reliability |
CN109637143B (en) * | 2019-01-22 | 2021-06-11 | 江苏智通交通科技有限公司 | Improved travel time reliability analysis method |
CN112990694A (en) * | 2021-03-11 | 2021-06-18 | 平安科技(深圳)有限公司 | Bus stop traffic capacity analysis method, device, equipment and storage medium |
CN113053095A (en) * | 2021-03-27 | 2021-06-29 | 李文祥 | Network taxi booking system and method with low vacant seat rate |
CN113470366A (en) * | 2021-09-01 | 2021-10-01 | 南通华豪巨电子科技有限公司 | Intelligent bus stop time prediction method and system based on big data |
CN113470366B (en) * | 2021-09-01 | 2021-11-16 | 南通华豪巨电子科技有限公司 | Intelligent bus stop time prediction method and system based on big data |
CN115798211A (en) * | 2022-11-21 | 2023-03-14 | 长安大学 | Control method, system, equipment and medium for preventing internet public transport from being disconnected and mixed |
CN115798211B (en) * | 2022-11-21 | 2023-09-22 | 长安大学 | Control method, system, equipment and medium for preventing network bus from being separated and mixed |
CN116704763A (en) * | 2023-06-13 | 2023-09-05 | 大连海事大学 | Intelligent bus team dynamic formation method considering bus operation scheme |
CN116704763B (en) * | 2023-06-13 | 2023-12-05 | 大连海事大学 | Intelligent bus team dynamic formation method considering bus operation scheme |
Also Published As
Publication number | Publication date |
---|---|
CN108364464B (en) | 2020-10-16 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108364464A (en) | A kind of public transit vehicle hourage modeling method based on probabilistic model | |
WO2021159865A1 (en) | Data calibration-based bus route prediction method and system | |
WO2021159866A1 (en) | Bus route prediction method and system based on facial recognition | |
CN107563566B (en) | Inter-bus-station operation time interval prediction method based on support vector machine | |
CN105788260A (en) | Public transportation passenger OD calculation method based on intelligent public transportation system data | |
CN110299011A (en) | A kind of traffic flow forecasting method of the highway arbitrary cross-section based on charge data | |
Li et al. | Public bus arrival time prediction based on traffic information management system | |
Gong et al. | Hybrid dynamic prediction model of bus arrival time based on weighted of historical and real-time GPS data | |
CN102324128A (en) | Method for predicting OD (Origin-Destination) passenger flow among bus stations on basis of IC (Integrated Circuit)-card record and device | |
CN110188923B (en) | Multi-mode bus passenger flow calculation method based on big data technology | |
CN106379379B (en) | A kind of Forecasting Methodology of urban track traffic passenger getting on/off time | |
CN104750963A (en) | Intersection delay time estimation method and device | |
CN112036757A (en) | Parking transfer parking lot site selection method based on mobile phone signaling and floating car data | |
CN110766940A (en) | Method for evaluating running condition of road signalized intersection | |
Shviatsova et al. | The Smart Urban Transport System | |
CN116090785B (en) | Custom bus planning method for two stages of large-scale movable loose scene | |
CN105070060B (en) | A kind of urban road traffic state method of discrimination based on public transport vehicle-mounted gps data | |
CN103748432B (en) | Image processing apparatus, image procossing managing device, terminal, processing means and image processing method | |
Kostakos | Using Bluetooth to capture passenger trips on public transport buses | |
CN114971085B (en) | Method and system for predicting accessibility of bus station and storage medium | |
CN111339159B (en) | Analysis mining method for one-ticket public transport data | |
JP3932383B2 (en) | Traveling time prediction device | |
CN111931968B (en) | Method for optimizing public bicycle station layout by using mobile phone GPS data | |
Erdei et al. | Analysis of flexibility on the FTS | |
CN113723761B (en) | Multi-dimensional urban public transportation operation service reliability evaluation method based on operation data |
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 |