CN103310651B - A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology - Google Patents
A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology Download PDFInfo
- Publication number
- CN103310651B CN103310651B CN201310199229.8A CN201310199229A CN103310651B CN 103310651 B CN103310651 B CN 103310651B CN 201310199229 A CN201310199229 A CN 201310199229A CN 103310651 B CN103310651 B CN 103310651B
- Authority
- CN
- China
- Prior art keywords
- point
- gps
- real
- time
- road
- 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
Links
- 238000000034 method Methods 0.000 title claims abstract description 44
- 230000008569 process Effects 0.000 claims description 12
- 238000005070 sampling Methods 0.000 claims description 10
- 230000008878 coupling Effects 0.000 claims description 7
- 238000010168 coupling process Methods 0.000 claims description 7
- 238000005859 coupling reaction Methods 0.000 claims description 7
- 230000002159 abnormal effect Effects 0.000 claims description 2
- 230000002776 aggregation Effects 0.000 claims description 2
- 238000004220 aggregation Methods 0.000 claims description 2
- 230000008707 rearrangement Effects 0.000 claims description 2
- 230000008859 change Effects 0.000 abstract description 7
- 238000012545 processing Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 abstract description 3
- 230000013011 mating Effects 0.000 abstract 1
- 238000011160 research Methods 0.000 description 4
- 238000001914 filtration Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 230000003247 decreasing effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 238000007619 statistical method Methods 0.000 description 2
- 238000000714 time series forecasting Methods 0.000 description 2
- 238000011144 upstream manufacturing Methods 0.000 description 2
- PCTMTFRHKVHKIS-BMFZQQSSSA-N (1s,3r,4e,6e,8e,10e,12e,14e,16e,18s,19r,20r,21s,25r,27r,30r,31r,33s,35r,37s,38r)-3-[(2r,3s,4s,5s,6r)-4-amino-3,5-dihydroxy-6-methyloxan-2-yl]oxy-19,25,27,30,31,33,35,37-octahydroxy-18,20,21-trimethyl-23-oxo-22,39-dioxabicyclo[33.3.1]nonatriaconta-4,6,8,10 Chemical compound C1C=C2C[C@@H](OS(O)(=O)=O)CC[C@]2(C)[C@@H]2[C@@H]1[C@@H]1CC[C@H]([C@H](C)CCCC(C)C)[C@@]1(C)CC2.O[C@H]1[C@@H](N)[C@H](O)[C@@H](C)O[C@H]1O[C@H]1/C=C/C=C/C=C/C=C/C=C/C=C/C=C/[C@H](C)[C@@H](O)[C@@H](C)[C@H](C)OC(=O)C[C@H](O)C[C@H](O)CC[C@@H](O)[C@H](O)C[C@H](O)C[C@](O)(C[C@H](O)[C@H]2C(O)=O)O[C@H]2C1 PCTMTFRHKVHKIS-BMFZQQSSSA-N 0.000 description 1
- 238000013459 approach Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000003455 independent Effects 0.000 description 1
- 230000007246 mechanism Effects 0.000 description 1
- 238000000611 regression analysis Methods 0.000 description 1
- 230000001373 regressive effect Effects 0.000 description 1
- 230000008439 repair process Effects 0.000 description 1
- 238000004088 simulation Methods 0.000 description 1
- 238000012706 support-vector machine Methods 0.000 description 1
- 238000012360 testing method Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Abstract
The invention discloses a kind of public transport based on real-time road condition information to arrive at a station Forecasting Methodology, belong to intelligent transport technology, comprise: pre-service is carried out to public bus network data, according to pretreated public bus network data, by the bus GPS Point matching of Real-time Collection on public bus network; Bus traveling behavior is on the line judged, carries out arriving at a station prediction based on the public transport of real-time road condition information according to judged result.Public transport provided by the invention arrives at a station Forecasting Methodology by mating based on the GPS fast path of sampled point, reduce the complexity of GPS anchor point and line matching, improve distance processing speed of arriving at a station, the real-time matching for extensive gps data provides a kind of simple and effective way.The present invention adopts and to arrive at a station forecast model based on the public transport of real-time road condition information, can carry out dynamic public transport prediction, have good real-time and accuracy according to the traffic conditions of real-time change.
Description
Technical field
The invention belongs to technical field of intelligent traffic, particularly a kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology.
Background technology
Along with the continuous intensification of urbanization, modernization, motorization degree, vehicle guaranteeding organic quantity increases fast, and citizens' activities demand presents variation, personalized feature, and urban traffic pressure increases day by day.Domestic and international Development of large city experience shows, solve urban transport problems, and the traffic problems of especially super-huge international city, must give full play to the vital role of public transport.The service of public transport arrival time is one of key service improving public's road traffic simulation power.By providing real-time vehicle to arrive at a station information, user can be made better to arrange the public transport stroke of oneself, reducing the stand-by period.Therefore, real-time public transport arrival time forecasting techniques has become the focus of research at intelligent transportation field.But because traffic conditions is complicated and changeable and road conditions unstable, the prediction of arriving at a station of public transport accurately in real time remains a difficult point.In prediction is arrived at a station in public transport, carry out much research both at home and abroad at present, mainly contain statistical analysis method, Kalman filtering method, machine learning method, historical data Similarity Model etc.
Statistical analysis method mainly comprises regretional analysis and time series forecasting.Regretional analysis is the method being undertaken predicting by analyzing cause-effect relationship between things and influence degree, as analyzed the correlativity of the factor such as number, weather of public transport arrival time and line construction, passenger getting on/off, intermediate stations, build regression equation, according to the change of these independents variable at prediction period, the dependent variable bus running time is predicted.The method requires that these influence factors are independently, and this strictly limits the application of regression analysis.Time series forecasting is that the accuracy of its prediction depends on predicted journey time Changing Pattern and the matching degree of historical law, has certain limitation by finding that the Changing Pattern in research object past infers the method for its following value.
Kalman filtering is a kind of high efficiency regressive filter, can from one group comprise noise to the observation sequence of object space, to current location and in the future position estimate.Kalman filtering is a kind of method of prediction Short-Term Traffic Flow, has good robustness, can make effective reaction to external environment condition.But its working time only within prediction following one or two time period is effective, when predict distance or time overall very long time, precision of prediction is lower.
Machine learning techniques is all widely used in a lot of fields, be applied at present public transport arrive at a station prediction mainly contain the technology such as artificial neural network and support vector machine.The method obtains forecast model mainly through carrying out training study to mass historical data, can reach certain precision of prediction.But the method needs training and testing widely, thus find out correct model structure and parameter, implementation complexity is higher, is difficult to the training and the performance prediction that realize real-time online simultaneously.
Be based upon under traffic circulation has the prerequisite of the regularity of circulation change, by analyzing historical data, with the journey time that the journey time mean prediction of history phase same time bus is current based on the Forecasting Methodology of historical data Similarity Model.The electronic stop plate display arrival time of current most cities is predicted based on this naive model.On this basis, also there is the further city bus arrival time forecasting mechanism proposed based on road conditions similarity of research, propose polynary group of traffic information, and traffic information polynary group of similarity calculation method, predict according to similar history road conditions.This method, completely based on historical data, does not consider the transport information of real-time change, real-time and accuracy poor.
Summary of the invention
In view of this, the object of the present invention is to provide a kind of public transport based on real-time road condition information to arrive at a station Forecasting Methodology, for improving accuracy and the real-time of prediction, reducing complexity.
The invention provides a kind of public transport based on real-time road condition information to arrive at a station Forecasting Methodology, comprising:
Pre-service is carried out to public bus network data, according to pretreated public bus network data, by the bus GPS Point matching of Real-time Collection on public bus network; Bus traveling behavior is on the line judged, carries out arriving at a station prediction based on the public transport of real-time road condition information according to judged result.
Public transport provided by the invention arrives at a station Forecasting Methodology at pretreatment stage, is generated and serializing process by track data, obtains public transport basic data form based on sampled point and irrelevant with map; And mated by the GPS fast path based on sampled point, reduce the complexity of GPS anchor point and line matching, improve distance processing speed of arriving at a station, the real-time matching for extensive gps data provides a kind of simple and effective way.The present invention adopts and to arrive at a station forecast model based on the public transport of real-time road condition information, can carry out dynamic public transport prediction, have good real-time and accuracy according to the traffic conditions of real-time change.
Accompanying drawing explanation
Fig. 1 to arrive at a station Forecasting Methodology process flow diagram for the public transport based on real-time road condition information that the embodiment of the present invention provides;
Fig. 2 is the principle schematic of circuit serializing in the embodiment of the present invention;
Fig. 3 is the principle schematic projected to by website in the embodiment of the present invention on the chain of road;
Fig. 4 be in the embodiment of the present invention by bus GPS Point matching to the principle schematic on public bus network;
Fig. 5 is the principle schematic calculating current traffic information in the embodiment of the present invention;
Fig. 6 is the principle schematic predicting public transport arrival time in the embodiment of the present invention.
Embodiment
For making the object, technical solutions and advantages of the present invention clearly, below in conjunction with accompanying drawing, the present invention is described in further detail.
The public transport that the embodiment of the present invention provides arrives at a station Forecasting Methodology at pretreatment stage, is generated and serializing process by track data, obtains public transport basic data form based on sampled point and irrelevant with map; And mated by the GPS fast path based on sampled point, reduce the complexity of GPS anchor point and line matching, improve distance processing speed of arriving at a station, the real-time matching for extensive gps data provides a kind of simple and effective way.The present embodiment adopts and to arrive at a station forecast model based on the public transport of real-time road condition information, can carry out dynamic public transport prediction, have good real-time and accuracy according to the traffic conditions of real-time change.
Fig. 1 to arrive at a station Forecasting Methodology process flow diagram for the public transport based on real-time road condition information that the embodiment of the present invention provides, comprising:
Step 101, pre-service is carried out to public bus network data.Data prediction comprises generation and the public bus network serializing of public bus network data:
The generation of step 1011, track data.
Due to the raw data (data that public transit system provides of public transit system access, comprise line number, site location, gps data etc.) lack track data, for meeting the demand of prediction of arriving at a station, need on the basis of raw data, according to existing road base map, in conjunction with public transport operation GPS historical data, describe according to GPS track or add road chain, road chain divides according to crossing usually, and all roads chain constitutes the running orbit of this circuit, and road first-in-chain(FIC) tail point is set to sampled point.
Considering that there is deviation original site positional information and actual anchor point position, in order to improve the accuracy rate of prediction further, needing, according to GPS convergence point, to correct site location, site location is adapted to coupling GPS convergence point.
Step 1012, line sequence.Track data needs to carry out serializing pretreatment work after generating, and the step comprise open circuit chain in reparation, road chain sorts, website being added sampled point, increase sampled point, finally exports the public transport basic data based on sampled point, as shown in Figure 2.
1, in repairing, open circuit chain refers to that the circuit to generating checks, judges whether circuit has the situation of interruption, automatically adds the road chain interrupted, and forms the path of complete only existence end points from beginning to end.First, check that whether a sampled point quantity circuit occurred once is more than two, in this way, then represent that circuit has and interrupt or have bifurcated; Then, breakpoint pairing between two, searches the road chain of tail point headed by these 2 in the line, repairs disrupted circuit.Article one, complete circuit is connected to form by a lot of roads chain head and the tail, and the Liang Ge road chain be connected can exist a common tie point.According to this principle, on a circuit, the sampled point (chain two ends, road are sampled point) of all roads chain, except circuit head and the tail, other sampled points at least should occur twice, only just there will be once at the head and the tail sampled point of circuit.If therefore when a circuit occurring the quantity of sampled point is once more than two, then illustrate that circuit has and interrupt or have bifurcated.
2, the sequence of road chain refer to pick out vehicle can initial from circuit be correct direction to all transitable direction of circuit ending, connect all roads chain discharge order of a circuit, so that derive circuit sampled point according to the head and the tail of road chain.When road chain sorts, if there is the situation that circuit both direction all cannot sort, illustrate that circuit Road chain direction is wrong, need to carry out adjusting rear rearrangement.
3, for ease of follow-up prediction, need website to add on the chain of road as sampled point, due on the chain of website Bu road, therefore need website to be projected on a nearest road chain.
As shown in Figure 3, ABCD is three road chains on a circuit, and S is website position, S
1and S
2for website is in the projection on chain of not going the same way, d
1and d
2for website is to the distance of road chain.When adding sampled point, comparison d
1and d
2, select to add in approach chain, as Fig. 3, d from the subpoint close to the chain of road as sampled point
1< d
2, then S is added
1as sampled point.
4, because part road chain sampled point is rare, causing during coupling and have relatively large deviation, in order to improve the precision of GPS Point matching, then needing to add sampled point on the chain of road.The principle of adding sampled point is: when a road chain there being two sampled point spacings be greater than 15m, then add a little between two sampled points.
Suppose that A, B are sampled point adjacent on the chain of road, and distance d
aB> 15, then need to add n=[d at point-to-point transmission
aB/ 15] individual sampled point S
1, S
2... S
n, and meet
Increase after sampled point, need calculating sampling Dian Dao road first-in-chain(FIC) back range from and to the distance of the next stop, as the property store of sampled point.
Finally export the public transport basic data be made up of circuit and station data, sampling number certificate, road chain data, website and affiliated road chain data.
Step 102, according to pretreated public bus network data, by the bus GPS Point matching of Real-time Collection on public bus network.
First, according to line number and the circuit up-downgoing of the bus GPS point of Real-time Collection, obtain all sampled points of this circuit sort by longitude size after list; Secondly, adopt binary chop, from list, find out all sampled points of before and after distance current bus GPS point longitude 100 meters; Finally, the distance of the sampled point found out being carried out again to point-to-point calculates, and calculates the distance of bus GPS point to sampled point, takes out nearest sampled point for coupling sampled point, as shown in Figure 4 (wherein, × be sampled point).
After finding out the sampled point that bus GPS point mates, can not determine its be before sampled point or after, when carrying out the next stop and judging, need to judge the front and back of GPS point at the corresponding sampled point of website.As shown in Figure 4, S
2for the sampled point of GPS Point matching, pick out S
2former and later two sampled points S
1and S
3composition line segment S
1s
2and S
2s
3, GPS spot projection is asked bee-line to two line segments, judges that GPS is before sampled point or rear.
Step 103, bus traveling behavior on the line to be judged.Mainly be divided into two stages: up-downgoing judges and assemble to stop to judge.
1, up-downgoing judges
Public bus network is divided into uplink and downgoing line, judges the traffic direction that can obtain Current vehicle, thus obtain the GPS match point on correct up and down line by up-downgoing, and next stop information.
Suppose T
2for the timestamp of current bus GPS point, T
1for the last time receives the timestamp of same car GPS point, only have and work as T
2> T
1time, be considered as normal GPS information.Suppose S
nowfor in uplink, according to the sampled point that Current GPS Point matching arrives, S
prefor in uplink, according to the sampled point that last GPS Point matching arrives; X
nowfor in downgoing line, according to the sampled point that Current GPS Point matching arrives, X
prefor in downgoing line, according to the sampled point that last GPS Point matching arrives.
Then increase progressively when meeting upstream sampling point sequence number, i.e. S
presequence number be less than S
now, and descending sampled point sequence number is successively decreased or constant, i.e. X
presequence number be more than or equal to X
now, be considered as up; Increase progressively when meeting descending sampled point sequence number, i.e. X
presequence number be less than X
now, and upstream sampling point sequence number is successively decreased or constant, i.e. S
presequence number be more than or equal to S
now, be considered as descending.
2, assemble stop to judge
When public bus network occurring assemble stop, Water demand special data Producing reason, no longer arrives at a station to the vehicle being parked in the special area such as bus terminus, parking lot and predicts issue.
First, analyze according to history GPS abnormal aggregation situation, and the gathering situation such as bus terminus, parking lot is marked; Secondly, judge that the bus GPS point of Real-time Collection is whether in convergence point, and motionless for a long time, be if so, then labeled as and assemble dwell flag accordingly, no longer carry out prediction issue of arriving at a station.
Step 104, carry out arriving at a station prediction based on the public transport of real-time road condition information.
Step 1041, calculate current traffic information according to bus GPS data, comprise Current vehicle travelling speed and road chain speed.
Current vehicle travelling speed is defined as the vehicle average velocity of current 3 minutes (current time pushes away forward 3 minutes).As shown in Figure 5, after reception gps data, through oversampled points coupling, the sampled point matched is put into vehicle lateral speed queue (queue length is 9, is about 3 minutes).When calculating vehicle present speed, first element in queue is taken out, and remove inactive elements (the sampled point sequence number as a rear gps time is less than last gps time, a rear GPS mates is less than the elements such as last GPS sampled point sequence number), if the element 1 ~ 2 in transverse velocity queue in Fig. 5 (a) is inactive elements, do not include calculating in.For sampled point effective in queue, calculate the distance dis of its process, and elapsed time T
e-T
s(T
sthe time of first effective sampling points, T
ethe time of last effective sampling points), thus calculate the average velocity of vehicle in 3 minutes, i.e. vehicle present speed.Then now the current travelling speed of vehicle i' is:
Road chain speed is defined as the average velocity of nearest n' the car through a road chain.For a longitudinal velocity queue set up by circuit Shang Meitiao road chain; When obtaining Current vehicle travelling speed, extracting the road chain list of this vehicle process, and Current vehicle travelling speed being added in the longitudinal velocity queue of each road chain of its process.As shown in Fig. 5 (b), in the longitudinal velocity queue of road chain, store the speed of the public transit vehicle of nearest 4 these road chains of process.After the Current vehicle travelling speed calculating certain car, this velocity amplitude is joined in the longitudinal velocity queue of road chain.Suppose to store n' in the longitudinal velocity queue of road chain recently through the car speed of this road chain, then chain speed in road is:
Step 1042, based on real-time road condition information prediction public transport arrival time.Specifically comprise:
By the GPS spot projection of bus to be predicted to sampled point, obtain the current sampling point distance distance of the next stop and the road chain information at interval; By n road chain in the middle of supposing, each road chain length is L
i, and the distance of the positional distance road last-of-chain of Current GPS point is L (i=1...n)
now, then the distance of the Current GPS point distance next stop is:
As shown in Figure 6, Lian Wei road, the road chain 1 at bus distance interval, the next stop to be predicted and road chain 2, then the distance arriving the next stop is L
now+ L
1+ L
2.The road chain speed of each road chain is known, is v
i(i=1...n), v
nowfor the speed of bus current place road chain, then the time prediction of arriving the next stop is:
The present invention's beneficial effect is compared with prior art: at pretreatment stage, is generated and serializing process, obtain based on sampled point by track data, with the public transport basic data form that map is irrelevant; Mated by the GPS fast path based on sampled point, reduce the complexity of GPS anchor point and line matching, improve distance processing speed of arriving at a station, the real-time matching for extensive gps data provides a kind of simple and effective way.Adopt and to arrive at a station forecast model based on the public transport of real-time road condition information, dynamic public transport prediction can be carried out according to the traffic conditions of real-time change, there is good real-time and accuracy.
In a word, the foregoing is only preferred embodiment of the present invention, be not intended to limit protection scope of the present invention.
Claims (8)
1. to arrive at a station a Forecasting Methodology based on the public transport of real-time road condition information, it is characterized in that, comprising:
Pre-service is carried out to public bus network data, according to pretreated public bus network data, by the bus GPS Point matching of Real-time Collection on public bus network; Bus traveling behavior is on the line judged, carries out arriving at a station prediction based on the public transport of real-time road condition information according to judged result;
Described pretreated step specifically comprises generation and the public bus network serializing of public bus network data;
The generation of described public bus network data specifically comprises:
On the raw data basis of public transit system access, according to existing road base map, in conjunction with public transport operation GPS historical data, describe according to GPS track or add road chain, described road chain divides according to crossing, and all roads chain constitutes the running orbit of this circuit, and road first-in-chain(FIC) tail point is set to sampled point;
The generation of described public bus network data also comprises further:
According to GPS convergence point, site location is corrected, site location is adapted to coupling GPS convergence point;
Described public bus network serializing specifically comprises:
Check that whether a sampled point quantity circuit occurred once is more than two, if so, then carry out breakpoint pairing between two, search the road chain adding tail point headed by these 2 in the line, disrupted circuit is repaired;
Connect all roads chain discharge order of a circuit according to the head and the tail of road chain, when road chain sorts, if there is the situation that circuit both direction all cannot sort, then circuit Road chain direction is wrong, carries out adjusting rear rearrangement;
Website is projected on a nearest road chain, thus website is added on this road chain as sampled point;
When a road chain there being two sampled point spacings be greater than 15m, then between two sampled points, add sampled point.
2. the public transport based on real-time road condition information according to claim 1 is arrived at a station Forecasting Methodology, and it is characterized in that, the described bus GPS Point matching by Real-time Collection specifically comprises to the step on public bus network:
According to line number and the circuit up-downgoing of the bus GPS point of Real-time Collection, obtain all sampled points of this circuit sort by longitude size after list; All sampled points of before and after distance current bus GPS point longitude 100 meters are found out from described list; The distance of the sampled point found out being carried out again to point-to-point calculates, and calculates the distance of bus GPS point to each sampled point, takes out nearest sampled point for coupling sampled point;
According to the projector distance of bus GPS point, judge bus GPS point before mated sampled point or after.
3. the public transport based on real-time road condition information according to claim 2 is arrived at a station Forecasting Methodology, it is characterized in that, the described step judged bus traveling behavior on the line specifically comprises up-downgoing and judges and assemble to stop to judge.
4. the public transport based on real-time road condition information according to claim 3 is arrived at a station Forecasting Methodology, it is characterized in that, described up-downgoing judges specifically to comprise:
Suppose T
2for the timestamp of current bus GPS point, T
1for the timestamp of same the car GPS point that the last time receives, only have and work as T
2> T
1time, be considered as normal GPS information; Suppose S
nowfor in uplink, according to the sampled point that Current GPS Point matching arrives, S
prefor in uplink, according to the sampled point that last GPS Point matching arrives; X
nowfor in downgoing line, according to the sampled point that current bus GPS Point matching arrives, X
prefor in downgoing line, according to the sampled point that last GPS Point matching arrives, then when meeting S
presequence number be less than S
now, and X
presequence number be more than or equal to X
now, for up; When meeting X
presequence number be less than X
now, and S
presequence number be more than or equal to S
now, for descending.
5. the public transport based on real-time road condition information according to claim 4 is arrived at a station Forecasting Methodology, it is characterized in that, described gathering stops and judges specifically to comprise:
Analyze according to history GPS abnormal aggregation situation, and the gathering situation in bus terminus, parking lot is marked; Judge that the bus GPS point of Real-time Collection is whether in convergence point, and motionless for a long time, be if so, then labeled as and assemble dwell flag accordingly, prediction of no longer carrying out arriving at a station is issued.
6. the public transport based on real-time road condition information according to claim 5 is arrived at a station Forecasting Methodology, it is characterized in that, the described public transport based on real-time road condition information prediction of arriving at a station specifically comprises:
Obtain current traffic information according to bus GPS data, comprise Current vehicle travelling speed and road chain speed, according to described road chain speed and road chain length prediction public transport arrival time.
7. the public transport based on real-time road condition information according to claim 6 is arrived at a station Forecasting Methodology, it is characterized in that, the described step obtaining current traffic information according to bus GPS data specifically comprises:
After often receiving a gps data, through oversampled points coupling, the sampled point matched is put into vehicle lateral speed queue; When calculating Current vehicle travelling speed, taking out element in described queue, and removing inactive elements, for sampled point effective in queue, calculating the distance dis of its process, and elapsed time T
e-T
s, T
sthe time of first effective sampling points, T
ebe the time of last effective sampling points, then now the Current vehicle travelling speed of vehicle i' is:
For a longitudinal velocity queue set up by circuit Shang Meitiao road chain; When obtaining Current vehicle travelling speed, extracting the road chain list of this vehicle process, and Current vehicle travelling speed being added in the longitudinal velocity queue of each road chain of this vehicle process; After the Current vehicle travelling speed calculating certain car, this velocity amplitude is joined in the longitudinal velocity queue of road chain; Suppose to store n' in the longitudinal velocity queue of road chain recently through the car speed of this road chain, then chain speed in road is:
wherein, i represents the label of road chain.
8. the public transport based on real-time road condition information according to claim 7 is arrived at a station Forecasting Methodology, it is characterized in that, the described step according to road chain speed and road chain length prediction public transport arrival time specifically comprises:
By the GPS spot projection of bus to be predicted to sampled point, obtain the current sampling point distance distance of the next stop and the road chain information at interval; By n road chain in the middle of supposing, each road chain length is L
i, and the distance of the positional distance road last-of-chain of current bus GPS point is L
now, then the distance of the current bus GPS point distance next stop is:
The road chain speed of each road chain is v
i, v
nowfor the speed of bus current place road chain, then the time prediction of arriving the next stop is:
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310199229.8A CN103310651B (en) | 2013-05-24 | 2013-05-24 | A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201310199229.8A CN103310651B (en) | 2013-05-24 | 2013-05-24 | A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN103310651A CN103310651A (en) | 2013-09-18 |
| CN103310651B true CN103310651B (en) | 2016-03-02 |
Family
ID=49135818
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201310199229.8A Active CN103310651B (en) | 2013-05-24 | 2013-05-24 | A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN103310651B (en) |
Families Citing this family (33)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| TWI569226B (en) * | 2014-02-12 | 2017-02-01 | Chunghwa Telecom Co Ltd | Logistics Delivery Arrival Time Estimation System and Method with Notification Function |
| US10699496B2 (en) | 2014-03-05 | 2020-06-30 | Huawei Device Co., Ltd. | Method for processing data on internet of vehicles, server, and terminal |
| CN105096639B (en) * | 2014-05-23 | 2017-08-11 | 中国电信股份有限公司 | Methods, devices and systems for predicting public transport arrival time |
| CN104064024B (en) * | 2014-06-23 | 2016-04-06 | 银江股份有限公司 | A kind of public transit vehicle arrival time Forecasting Methodology based on historical data |
| CN104252795B (en) * | 2014-09-23 | 2016-08-17 | 深圳市谷米科技有限公司 | Bus arrival time Forecasting Methodology |
| CN104502933B (en) * | 2014-12-26 | 2018-11-13 | 贵州中科汉天下信息技术有限公司 | A kind of bus GPS positioning system and its method |
| CN104616527A (en) * | 2015-02-04 | 2015-05-13 | 上海市政工程设计研究总院（集团）有限公司 | Bus station-arrival information automatic-publishing system and information publishing method thereof |
| CN106156074B (en) * | 2015-03-31 | 2021-07-16 | 联想(北京)有限公司 | Information processing method and electronic equipment |
| CN104807469B (en) * | 2015-04-01 | 2018-02-13 | 贵州智通天下信息技术有限公司 | A kind of method that bus traffic route shows correction on map |
| CN106199669B (en) * | 2015-05-06 | 2018-10-23 | 北京千方城市信息科技有限公司 | A kind of method and device for analyzing public transit vehicle operational process based on GPS track |
| CN106291597B (en) * | 2015-05-26 | 2019-01-08 | 深圳市腾讯计算机系统有限公司 | The monitoring method and device of bus running state |
| CN105590452B (en) * | 2015-06-09 | 2018-09-18 | 上海博协软件有限公司 | Automatically generate the method and its device of electronic road form |
| CN105632222B (en) * | 2015-10-14 | 2018-04-17 | 上海博协软件有限公司 | Forecast the method and its system of arrival time |
| CN106251642B (en) * | 2016-09-18 | 2018-10-26 | 北京航空航天大学 | A kind of public transport road chain speed calculation method based on real-time bus GPS data |
| CN106652534B (en) * | 2016-12-14 | 2019-08-16 | 北京工业大学 | A method of prediction bus arrival time |
| CN106710218A (en) * | 2017-03-09 | 2017-05-24 | 北京公共交通控股（集团）有限公司 | Method for predicting arrival time of bus |
| CN108196280B (en) * | 2017-11-15 | 2022-01-14 | 北京通途永久科技有限公司 | Method for deducing bus route through GPS |
| CN107945560A (en) * | 2017-12-21 | 2018-04-20 | 大连海事大学 | A kind of public transport smart electronics stop sign information display control method and system |
| CN108802776B (en) * | 2018-07-02 | 2021-03-02 | 武汉蓝泰源信息技术有限公司 | Bus GPS (global positioning system) deviation rectifying method based on abnormal point elimination and track compression algorithm |
| CN109033424B (en) * | 2018-08-10 | 2021-03-26 | 北京航天控制仪器研究所 | Method for accurately extracting bus running path based on bus operation track |
| CN109359682B (en) * | 2018-10-11 | 2019-08-30 | 北京市交通信息中心 | A kind of Shuttle Bus candidate's website screening technique based on F-DBSCAN iteration cluster |
| CN109920248B (en) * | 2019-03-05 | 2021-09-17 | 南通大学 | Bus arrival time prediction method based on GRU neural network |
| CN111161531A (en) * | 2019-03-29 | 2020-05-15 | 江西善行智能设备制造有限公司 | Method for judging forward route, forward route and station passing based on bus-mounted terminal |
| CN112801326A (en) * | 2019-11-13 | 2021-05-14 | 武汉微品致远信息科技有限公司 | Bus arrival prediction service platform |
| CN113382361B (en) * | 2020-03-09 | 2022-11-15 | 上海擎感智能科技有限公司 | Route segmentation based test driving monitoring method, system, medium and equipment |
| CN111523560B (en) * | 2020-03-18 | 2023-07-25 | 第四范式（北京）技术有限公司 | Method, device and system for training number prediction model of arrival trucks |
| CN111968398B (en) * | 2020-07-14 | 2022-07-29 | 深圳市综合交通运行指挥中心 | Method, device, terminal and medium for determining running state of public transport means |
| CN112268563B (en) * | 2020-10-23 | 2022-03-04 | 重庆越致科技有限公司 | Method and device for detecting traffic state and track of pedestrian on track |
| CN112396865A (en) * | 2020-11-18 | 2021-02-23 | 南京智慧交通信息股份有限公司 | Real-time bus arrival prediction method based on line track |
| CN112991722B (en) * | 2021-02-03 | 2022-07-19 | 浙江中控信息产业股份有限公司 | High-frequency gps (gps) point bus real-time intersection prediction method and system |
| CN113077648A (en) * | 2021-02-03 | 2021-07-06 | 浙江浙大中控信息技术有限公司 | Method and system for predicting real-time station of public transport vehicle |
| CN115188215B (en) * | 2022-06-21 | 2023-10-31 | 青岛海信网络科技股份有限公司 | Electronic equipment and prediction method of bus running duration between stations |
| CN115311871B (en) * | 2022-08-12 | 2023-09-05 | 深圳市能信安科技股份有限公司 | Method, device, system, equipment and storage medium for judging vehicle running direction |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4799162A (en) * | 1985-10-25 | 1989-01-17 | Mitsubishi Denki Kabushiki Kaisha | Route bus service controlling system |
| CN1963847A (en) * | 2005-11-07 | 2007-05-16 | 同济大学 | Method for forecasting reaching station of bus |
| CN102074124A (en) * | 2011-01-27 | 2011-05-25 | 山东大学 | Dynamic bus arrival time prediction method based on support vector machine (SVM) and H-infinity filtering |
| CN102157075A (en) * | 2011-03-15 | 2011-08-17 | 上海交通大学 | Method for predicting bus arrivals |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020069017A1 (en) * | 1995-08-14 | 2002-06-06 | Schmier Kenneth J. | Public transit vehicle arrival information system |
-
2013
- 2013-05-24 CN CN201310199229.8A patent/CN103310651B/en active Active
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US4799162A (en) * | 1985-10-25 | 1989-01-17 | Mitsubishi Denki Kabushiki Kaisha | Route bus service controlling system |
| CN1963847A (en) * | 2005-11-07 | 2007-05-16 | 同济大学 | Method for forecasting reaching station of bus |
| CN102074124A (en) * | 2011-01-27 | 2011-05-25 | 山东大学 | Dynamic bus arrival time prediction method based on support vector machine (SVM) and H-infinity filtering |
| CN102157075A (en) * | 2011-03-15 | 2011-08-17 | 上海交通大学 | Method for predicting bus arrivals |
Non-Patent Citations (1)
| Title |
|---|
| 基于GPS的公交车辆到达时间预测技术研究;罗虹;《中国优秀硕士学位论文全文数据库 工程科技II辑》;20071215(第6期);正文第3-5章 * |
Also Published As
| Publication number | Publication date |
|---|---|
| CN103310651A (en) | 2013-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN103310651B (en) | A kind of public transport based on real-time road condition information is arrived at a station Forecasting Methodology | |
| CN103177561B (en) | Method for generating bus real-time traffic status | |
| CN104064028B (en) | Based on public transport arrival time Forecasting Methodology and the system of multiple information data | |
| CN105046956B (en) | Traffic flow simulating and predicting method based on turning probability | |
| CN104134349B (en) | A kind of public transport road conditions disposal system based on traffic multisource data fusion and method | |
| CN102081859B (en) | Control method of bus arrival time prediction model | |
| CN109816977B (en) | Data-driven intersection signal control evaluation system | |
| CN102087788B (en) | Method for estimating traffic state parameter based on confidence of speed of float car | |
| CN103871239B (en) | Based on public transport operation condition discrimination method and the application system of taxi and public transport gps data | |
| CN105261212B (en) | A kind of trip space-time analysis method based on GPS data from taxi map match | |
| CN104464310A (en) | Signal collaborative optimization control method and system of multiple intersections of urban region | |
| CN101615340A (en) | Real-time information processing method in the bus dynamic dispatching | |
| CN106710218A (en) | Method for predicting arrival time of bus | |
| CN104778834A (en) | Urban road traffic jam judging method based on vehicle GPS data | |
| CN102855760A (en) | On-line queuing length detection method based on floating vehicle data | |
| CN105868861A (en) | Bus passenger flow evolution analysis method based on time-space data fusion | |
| CN110491158A (en) | A kind of bus arrival time prediction technique and system based on multivariate data fusion | |
| CN101853573A (en) | City expressway short-time traffic information predicting system and method | |
| CN104318770A (en) | Method for detecting traffic jam state of expressway in real time based on mobile phone data | |
| CN101944288A (en) | Method for setting stop stations of urban bus line | |
| CN106251642A (en) | A kind of public transport road based on real-time bus gps data chain speed calculation method | |
| CN104766475A (en) | Urban traffic bottleneck mining method | |
| CN101128051A (en) | Update method of mobile object location based on traffic network and GPS | |
| CN102930718A (en) | Intermittent flow path section travel time estimation method based on floating car data and coil flow fusion | |
| CN106097717A (en) | The signalized intersections average transit time method of estimation merged based on two class floating car datas |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| C14 | Grant of patent or utility model | ||
| GR01 | Patent grant |