CN105243848A - Real-time road condition prediction method and system - Google Patents
Real-time road condition prediction method and system Download PDFInfo
- Publication number
- CN105243848A CN105243848A CN201510760673.1A CN201510760673A CN105243848A CN 105243848 A CN105243848 A CN 105243848A CN 201510760673 A CN201510760673 A CN 201510760673A CN 105243848 A CN105243848 A CN 105243848A
- Authority
- CN
- China
- Prior art keywords
- road
- matrix
- shunting
- present road
- current
- 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
Landscapes
- Traffic Control Systems (AREA)
Abstract
The invention provides a real-time road condition prediction method and a real-time road condition prediction system. The real-time road condition prediction method comprises the steps of calling road topological structure information and acquiring a vehicle driving speed of a current road at a current moment through a road server, acquiring passing rate, a diverging flow direction matrix and a diverging matrix of the current road in sequence, and iterating the passing rate of the current road at the current moment and the diverging matrix of the current road on the basis of Markov process to obtain passing rate of a prediction road at a predetermined moment. Since the passing rate of the current road at the current moment equals a ratio of the vehicle driving speed of the current road at the current moment to a speed limit of the current road, and the speed limit of each road can be obtained directly through the road topological structure information, the vehicle driving speed of the prediction road at the predetermined moment can be derived through a back-stepping process just by acquiring the passing rate of the prediction road at the predetermined moment, the real-time road condition of the prediction road is obtained directly, the prediction precision is increased, and the real-time road condition prediction method and the real-time road condition prediction system have the advantage of universality.
Description
Technical field
The present invention relates to technical field of transportation, particularly a kind of Forecasting Methodology of real-time road and system.
Background technology
Along with the raising of people's living standard, steering vehicle trip has become one of main mode of transportation of people, if driver can obtain the traffic information of road in the process of steering vehicle, then contribute to driver and plan driving path, be about to arrive the traffic information of road when arriving if can get further, driver just more reasonably can plan driving path according to predicting the outcome, and so just can improve the utilization factor of road and effectively preventing blocks up.
At present, road condition predicting mainly contains following three kinds of modes:
One, if China Patent No. is 201110438175.7 disclose a kind of traffic condition predictions system and method merging multiple traffic data, it is mainly based on historical data, the data of data on flows and this three types of speed data, and according to corresponding weight Modling model, then according to the load conditions of the model prediction road established.
Two, if China Patent No. is the 200910265617.5 road condition predicting method and systems disclosing based on time-space relationship, it is mainly based on the data of historical data, spacial influence degree, this three types of real-time road data, and highlight the cyberspace relation of road, according to above three kinds of data types, set up corresponding weight model, road conditions are predicted.
Three, if China Patent No. is 201310155684.8 disclose a kind of traffic congestion prompt system based on collective intelligence network, this system excavates module, microblogging traffic hot spot excavation module and road conditions law forecasting module composition by webpage traffic hot spot, towards intelligent perception network, in conjunction with traditional transport information source, excavation based on data activating technology and prediction are carried out to urban transportation focus.
Finding through research, all there is respective shortcoming in above-mentioned three kinds of road condition predicting modes:
First kind of way, needs a large amount of personnel to participate in, at substantial financial resource and material resource; Speed data obtains real time data by Floating Car amount technology, and data on flows can gather real-time data on flows by coil; The data type needed is many, just needs a large amount of collecting works; Second point is that the foundation of model is partially complicated, has a certain impact to the accuracy of calculating and model.The second way also exists the problem identical with first kind of way equally, and spacial influence degree considers the impact in a certain scope simultaneously, but road conditions also exist butterfly effect, and the scope likely affected can feed through to other scopes.The third mode mainly to be excavated on webpage and traffic hot spot data on microblogging, if a certain region does not belong to hot spot region on webpage or microblogging, so would not produce road conditions, more impossible have road condition predicting.
Summary of the invention
The object of the present invention is to provide a kind of Forecasting Methodology and system of real-time road, use the Forecasting Methodology of real-time road in prior art to there is the problem that modeling copies, precision is low to solve.
For solving the problems of the technologies described above, the invention provides a kind of Forecasting Methodology of real-time road, the Forecasting Methodology of described real-time road comprises:
Road service device calls road topology structural information and obtains the Vehicle Speed of current time present road;
Calculate the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road;
The shunting obtaining present road according to road topology structural information flows to matrix, and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection;
The shunting matrix of matrix computations present road is flowed to according to described shunting;
Based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtain the current rate of predetermined instant predicted link.
Optionally, in the Forecasting Methodology of described real-time road, the shunting matrix calculating present road adopts following formula:
A＝qE+(1-q)P(n)，
Wherein, A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road.
Optionally, in the Forecasting Methodology of described real-time road, the current rate obtaining predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and the current rate of predicted link when R (n+1) represents that predetermined instant is subsequent time, A represents the shunting matrix of present road.
Optionally, in the Forecasting Methodology of described real-time road, it is 0 or 1 that described shunting flows to entry of a matrix element, and when there is connection between two different roads, described shunting flows to entry of a matrix element and gets 1; When there is not connection between two different roads, described shunting flows to entry of a matrix element and gets 0.
Optionally, in the Forecasting Methodology of described real-time road, described road topology structural information comprises: the type classification of the speed limit of all roads, the numbering of road and road.
Optionally, in the Forecasting Methodology of described real-time road, the Vehicle Speed of described current time present road equals the mean value of current time all Vehicle Speed on present road.
Optionally, in the Forecasting Methodology of described real-time road, the span of the current rate of current time present road and the current rate of predetermined instant predicted link is [0,1].
The present invention also provides a kind of prognoses system of real-time road, and the prognoses system of described real-time road comprises:
Road service device, for calling road topology structural information and obtaining the Vehicle Speed of current time present road;
Current rate acquisition module, for calculating the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road;
Shunting matrix acquisition module, the shunting obtaining present road according to described road topology structural information flows to matrix, and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection;
Shunting matrix computations module, calculates the shunting matrix of present road according to described shunting matrix acquisition module;
Prediction module, based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtains the current rate of predetermined instant predicted link.
Optionally, in the prognoses system of described real-time road, the shunting matrix that described shunting matrix computations module calculates present road adopts following formula:
A＝qE+(1-q)P(n)，
Wherein, A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road.
Optionally, in the prognoses system of described real-time road, the current rate that described prediction module obtains predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and the current rate of predicted link when R (n+1) represents that predetermined instant is subsequent time, A represents the shunting matrix of present road.
In the Forecasting Methodology and system of real-time road provided by the present invention, first call road topology structural information by road service device and obtain the Vehicle Speed of current time present road, obtain the current rate of present road successively, flow to matrix and shunting matrix, afterwards based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtain the current rate of predetermined instant predicted link.Current rate due to current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road, and the speed limit of every bar road directly obtains by road topology structural information, therefore the current rate obtaining predetermined instant predicted link is only needed instead can to push away Vehicle Speed in predetermined instant predicted link, obtain the real-time road of predicted link comparatively intuitively, improve the precision of prediction, there is universality.
Accompanying drawing explanation
Fig. 1 is the process flow diagram of the Forecasting Methodology of real-time road in one embodiment of the invention;
Fig. 2 is the schematic diagram of the prognoses system of real-time road in one embodiment of the invention.
In Fig. 2, road service device 10; Current rate acquisition module 11; Shunting matrix acquisition module 12; Shunting matrix computations module 13; Prediction module 14.
Embodiment
Below in conjunction with the drawings and specific embodiments, the Forecasting Methodology of the real-time road that the present invention proposes and system are described in further detail.According to the following describes and claims, advantages and features of the invention will be clearer.It should be noted that, accompanying drawing all adopts the form that simplifies very much and all uses non-ratio accurately, only in order to object that is convenient, the aid illustration embodiment of the present invention lucidly.
Please refer to Fig. 1, it is the process flow diagram of the Forecasting Methodology of real-time road in one embodiment of the invention.As shown in Figure 1, the Forecasting Methodology of described real-time road comprises the steps:
First, perform step S1, road service device calls road topology structural information and obtains the Vehicle Speed of current time present road; Wherein, described road topology structural information comprises: the information such as the type classification of the speed limit of road, the numbering of road and road, can be stored in road service device for topology information, so that user implements when carrying out road condition predicting to call relevant information.For the speed limit of road, if do not record the speed limit data of road in the middle of topology information, then according to the different speed limit data of the dissimilar grade determination road of road.
Then, perform step S2, calculate the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road; Wherein, the Vehicle Speed of described current time present road equals the mean value of current time all Vehicle Speed on present road;
Here it should be noted that the numerical value of the Vehicle Speed of present road is the data that can change in the moment, and the speed limit of present road has defined according to the type level of road, therefore, the speed limit of road and time, it doesn't matter.
Concrete, the Vehicle Speed obtain manner of road is as follows:
Road service device obtains the related data of driving vehicle, mainly comprises: the satellite location data of driving vehicle, the speed data of vehicle and driving vehicle deflection data; Road service device is according to the road at the driving vehicle place, deflection data location of the satellite location data of driving vehicle and driving vehicle; Road service device obtains the travel speed of all driving vehicles of same path, according to the average velocity of the speed of all driving vehicles at the same path Vehicle Speed as this road.
Further, the current rate of current time present road and the current rate span of predetermined instant predicted link are [0,1].Current rate value is more close to 1, and illustrate that the Vehicle Speed of current time present road is more close to the speed limit of present road, that is this road is more unimpeded.Current rate value is more close to 0, and illustrate that the Vehicle Speed of current time present road is more lower than the speed limit of present road, namely this road rate is more bad, and this road more blocks up.Certainly, in fact, the speed that vehicle travels very likely exceedes the speed limit of road, but is small probability event after all, now current rate value is taken as 1.
Then, perform step S3, the shunting obtaining present road according to road topology structural information flows to matrix P (n), and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection; P (n)=(r
ij), r here
ijrepresent the annexation be numbered between the road of i and the road being numbered j, r
ijvalue is 0 or 1, when the road being numbered i with exist between the road being numbered j be connected time, described shunting flows to entry of a matrix element and gets 1; When the road being numbered i with do not exist between the road being numbered j be connected time, described shunting flows to entry of a matrix element and gets 0.
Then, perform step S4, flow to the shunting matrix of matrix computations present road according to described shunting; Wherein, the shunting matrix calculating present road adopts following formula:
A＝qE+(1-q)P(n)，
A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road, and in the present embodiment, q is 0.8.
It is that road divides flow path direction that shunting in step S3 flows to matrix sign, and the shunting matrix in step S4 characterizes the distributing strategy of road,
The distributing strategy of road is embodied in two aspects, first aspect, and to which local shunting, how second aspect, shunt; Wherein, be shunt according to the annexation of road for first aspect, the current rate value on every bar road can only be diverted on the down hop road that is connected with high road, and distributing strategy can only occur between interconnective road.For second aspect, determine the ratio problems of the shunting to next road exactly, according to step S4, shunt ratio shunts according to the proportionate relationship of current rate value.First, obtain next roads all of this road, then, obtain the current rate value of next roads all, the last proportionate relationship according to current rate value is shunted.
Then, perform step S5, based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtain the current rate of predetermined instant predicted link.Wherein, the current rate obtaining predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and R (n+1) represents that predetermined instant is the current rate of subsequent time predicted link, and A represents the shunting matrix of present road.
During predicting road conditions of the present invention, what adopt is prediction mode based on Markovian process, why road conditions are regarded as Markovian process, because for road conditions, the road conditions of subsequent time only depend on the road conditions of current time, and be that it doesn't matter with road conditions before, and this exactly constitutes Markovian process.What serve as the state-transition matrix in Markovian process in the technical scheme of the application is the shunting matrix of driving vehicle, and the initial value in Markovian process is exactly the current rate score of current time present road; Iteration result is exactly that the subsequent time of prediction is (if current for the n moment, then subsequent time is the n+1 moment) the current rate score of road, if predict that the lower lower moment is (if current for the n moment, then the lower lower moment is the n+2 moment) the numerical value of road, only need many iteration once just can calculate.Here the current rate score of the current rate score of the predicted link of so-called subsequent time or the predetermined road in lower lower moment is the current rate of predetermined instant predicted link.That is, want the road conditions predicting following a certain moment road, can to calculate through the iteration of corresponding number of times based on the shunting matrix of the current rate of current time present road and vehicle and know.Therefore, as long as the current rate calculating certain road of predetermined instant can know the road conditions of predicted link when predetermined instant, the program is comparatively directly perceived, and reliability is strong.
Accordingly, the present embodiment additionally provides a kind of prognoses system of real-time road, describes the prognoses system of real-time road described in the present embodiment below with reference to Fig. 2 in detail.
Road service device 10, for calling road topology structural information and obtaining the Vehicle Speed of current time present road;
Current rate acquisition module 11, for calculating the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road;
Shunting matrix acquisition module 12, the shunting obtaining present road according to described road topology structural information flows to matrix, and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection; Wherein, the shunting matrix that described shunting matrix computations module 12 calculates present road adopts following formula:
A＝qE+(1-q)P(n)，
Wherein, A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road.
Shunting matrix computations module 13, calculates the shunting matrix A of present road according to described shunting matrix acquisition module 12;
Prediction module 14, based on the current rate R (n) of Markov process by current time (being originally embodied as the n moment) present road and the shunting matrix A iteration of present road, obtain the current rate of predetermined instant (being originally embodied as the n+1 moment) predicted link.Wherein, the current rate of described prediction module acquisition predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and R (n+1) represents that predetermined instant is the current rate of subsequent time predicted link, and A represents the shunting matrix of present road, and n represents the n moment, specifically refers to time point.
Preferably, the prognoses system of real-time road also comprises road condition predicting and shows subsystem, for providing interface to the external world, provides service by the mode of interface to external system.
To sum up, in the Forecasting Methodology and system of real-time road provided by the present invention, first call road topology structural information by road service device and obtain the Vehicle Speed of current time present road, obtain the current rate of present road successively, flow to matrix and shunting matrix, afterwards based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtain the current rate of predetermined instant predicted link.Current rate due to current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road, and the speed limit of every bar road directly obtains by road topology structural information, therefore the current rate obtaining predetermined instant predicted link is only needed instead can to push away Vehicle Speed in predetermined instant predicted link, obtain the real-time road of predicted link comparatively intuitively, improve the precision of prediction, there is universality.
Foregoing description is only the description to present pre-ferred embodiments, any restriction not to the scope of the invention, and any change that the those of ordinary skill in field of the present invention does according to above-mentioned disclosure, modification, all belong to the protection domain of claims.
Claims (10)
1. a Forecasting Methodology for real-time road, is characterized in that, comprising:
Road service device calls road topology structural information and obtains the Vehicle Speed of current time present road;
Calculate the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road;
The shunting obtaining present road according to road topology structural information flows to matrix, and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection;
The shunting matrix of matrix computations present road is flowed to according to described shunting;
Based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtain the current rate of predetermined instant predicted link.
2. the Forecasting Methodology of real-time road as claimed in claim 1, is characterized in that, the shunting matrix calculating present road adopts following formula:
A＝qE+(1-q)P(n)，
Wherein, A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road.
3. the Forecasting Methodology of real-time road as claimed in claim 2, is characterized in that, the current rate obtaining predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and the current rate of predicted link when R (n+1) represents that predetermined instant is subsequent time, A represents the shunting matrix of present road.
4. the Forecasting Methodology of real-time road as claimed in claim 1, it is characterized in that, it is 0 or 1 that described shunting flows to entry of a matrix element, and when there is connection between two different roads, described shunting flows to entry of a matrix element and gets 1; When there is not connection between two different roads, described shunting flows to entry of a matrix element and gets 0.
5. the Forecasting Methodology of real-time road as claimed in claim 1, it is characterized in that, described road topology structural information comprises: the type classification of the speed limit of all roads, the numbering of road and road.
6. the Forecasting Methodology of real-time road as claimed in claim 1, it is characterized in that, the Vehicle Speed of described current time present road equals the mean value of current time all Vehicle Speed on present road.
7. the Forecasting Methodology of real-time road as claimed in claim 1, it is characterized in that, the span of the current rate of current time present road and the current rate of predetermined instant predicted link is [0,1].
8. a prognoses system for real-time road, is characterized in that, comprising:
Road service device, for calling road topology structural information and obtaining the Vehicle Speed of current time present road;
Current rate acquisition module, for calculating the current rate of current time present road according to the Vehicle Speed of described road topology structural information and current time present road, the current rate of described current time present road equals the ratio of the Vehicle Speed of current time present road and the speed limit of present road;
Shunting matrix acquisition module, the shunting obtaining present road according to described road topology structural information flows to matrix, and the described shunting each element flowed in matrix characterizes between two different roads whether there is connection;
Shunting matrix computations module, calculates the shunting matrix of present road according to described shunting matrix acquisition module;
Prediction module, based on the current rate of Markov process by current time present road and the shunting matrix iteration of present road, obtains the current rate of predetermined instant predicted link.
9. the prognoses system of real-time road as claimed in claim 8, is characterized in that, the shunting matrix that described shunting matrix computations module calculates present road adopts following formula:
A＝qE+(1-q)P(n)，
Wherein, A represents the shunting matrix of present road, E representation unit matrix, and P (n) represents that the shunting of present road flows to matrix, and q represents that vehicle can stay the probability on present road.
10. the prognoses system of real-time road as claimed in claim 9, is characterized in that, the current rate that described prediction module obtains predetermined instant predicted link adopts following formula:
R(n+1)＝AR(n)，
Wherein, R (n) represents the current rate of current time present road, and the current rate of predicted link when R (n+1) represents that predetermined instant is subsequent time, A represents the shunting matrix of present road.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510760673.1A CN105243848A (en) | 2015-11-10 | 2015-11-10 | Real-time road condition prediction method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510760673.1A CN105243848A (en) | 2015-11-10 | 2015-11-10 | Real-time road condition prediction method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN105243848A true CN105243848A (en) | 2016-01-13 |
Family
ID=55041474
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510760673.1A Pending CN105243848A (en) | 2015-11-10 | 2015-11-10 | Real-time road condition prediction method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105243848A (en) |
Cited By (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106557814A (en) * | 2016-11-15 | 2017-04-05 | 成都通甲优博科技有限责任公司 | A kind of road vehicle density assessment method and device |
| CN108074008A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of method and device in predicted congestion section |
| CN110969275A (en) * | 2018-09-30 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Traffic flow prediction method and device, readable storage medium and electronic device |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020082767A1 (en) * | 1999-03-08 | 2002-06-27 | Telquest, Ltd. | Method and system for mapping traffic congestion |
| CN101694743A (en) * | 2009-08-25 | 2010-04-14 | 北京世纪高通科技有限公司 | Method and device for predicting road conditions |
| CN102110365A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Road condition prediction method and road condition prediction system based on space-time relationship |
| CN104616498A (en) * | 2015-02-02 | 2015-05-13 | 同济大学 | Markov chain and neural network based traffic congestion state combined prediction method |
| CN104732761A (en) * | 2015-02-06 | 2015-06-24 | 上海语镜汽车信息技术有限公司 | Road traffic condition predicting method based on real-time calculation and paying attention to roads |
-
2015
- 2015-11-10 CN CN201510760673.1A patent/CN105243848A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20020082767A1 (en) * | 1999-03-08 | 2002-06-27 | Telquest, Ltd. | Method and system for mapping traffic congestion |
| CN101694743A (en) * | 2009-08-25 | 2010-04-14 | 北京世纪高通科技有限公司 | Method and device for predicting road conditions |
| CN102110365A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Road condition prediction method and road condition prediction system based on space-time relationship |
| CN104616498A (en) * | 2015-02-02 | 2015-05-13 | 同济大学 | Markov chain and neural network based traffic congestion state combined prediction method |
| CN104732761A (en) * | 2015-02-06 | 2015-06-24 | 上海语镜汽车信息技术有限公司 | Road traffic condition predicting method based on real-time calculation and paying attention to roads |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106557814A (en) * | 2016-11-15 | 2017-04-05 | 成都通甲优博科技有限责任公司 | A kind of road vehicle density assessment method and device |
| CN108074008A (en) * | 2016-11-18 | 2018-05-25 | 腾讯科技（深圳）有限公司 | A kind of method and device in predicted congestion section |
| CN108074008B (en) * | 2016-11-18 | 2022-01-07 | 腾讯科技（深圳）有限公司 | Method and device for predicting congested road section |
| CN110969275A (en) * | 2018-09-30 | 2020-04-07 | 杭州海康威视数字技术股份有限公司 | Traffic flow prediction method and device, readable storage medium and electronic device |
| CN110969275B (en) * | 2018-09-30 | 2024-01-23 | 杭州海康威视数字技术股份有限公司 | Traffic flow prediction method and device, readable storage medium and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US10581634B2 (en) | Providing dynamic routing alternatives based on determined traffic conditions | |
| CN107945507B (en) | Travel time prediction method and device | |
| US10563994B2 (en) | Safe routing for navigation systems | |
| Liu et al. | Dynamic shared autonomous taxi system considering on-time arrival reliability | |
| CN109612488B (en) | Big data micro-service-based mixed travel mode path planning system and method | |
| US20150179064A1 (en) | Traffic-Volume Prediction Device and Method | |
| CN103295414A (en) | Bus arrival time forecasting method based on mass historical GPS (global position system) trajectory data | |
| CN103745611A (en) | Method, apparatus and system for traffic route planning | |
| CN108106622A (en) | A kind of riding route method and system for planning | |
| CN105303854A (en) | Travel route data processing method and device | |
| Karmakar et al. | A smart priority-based traffic control system for emergency vehicles | |
| KR20140028801A (en) | Prediction of urban congestion using its based data | |
| CN106197442A (en) | Air navigation aid and equipment | |
| Cao et al. | Bilevel generalized least squares estimation of dynamic origin–destination matrix for urban network with probe vehicle data | |
| CN104484514A (en) | Flexible bus route design method capable of evading jammed road segments | |
| CN113066285A (en) | Road condition information determining method and device, electronic equipment and storage medium | |
| Yang et al. | Effects of left-turn waiting areas on capacity and level of service of signalized intersections | |
| CN107957267B (en) | Method and device for determining navigation path prompt information | |
| CN105243848A (en) | Real-time road condition prediction method and system | |
| KR101123967B1 (en) | Traffic congestion prediction system, prediction method and recording medium thereof | |
| CN102750826A (en) | Identification method of driver response behaviors under group induction information | |
| Jian Daniel et al. | Research and analysis on causality and spatial-temporal evolution of urban traffic congestions—a case study on Shenzhen of China | |
| Liang et al. | An Overlapping Phase Approach to Optimize Bus Signal Priority Control under Two‐Way Signal Coordination on Urban Arterials | |
| CN105303838A (en) | Method and device for determining traffic flow | |
| Marve | Traffic Congestion Minimization Study for Hingna Area of Nagpur City, MS. India |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| WD01 | Invention patent application deemed withdrawn after publication |
Application publication date: 20160113 |
|
| WD01 | Invention patent application deemed withdrawn after publication |