CN108022425A - Traffic movement prediction method, device and computer equipment - Google Patents
Traffic movement prediction method, device and computer equipment Download PDFInfo
- Publication number
- CN108022425A CN108022425A CN201711396601.9A CN201711396601A CN108022425A CN 108022425 A CN108022425 A CN 108022425A CN 201711396601 A CN201711396601 A CN 201711396601A CN 108022425 A CN108022425 A CN 108022425A
- Authority
- CN
- China
- Prior art keywords
- congestion information
- lattice
- set cell
- congestion
- cell
- 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
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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/18—Complex mathematical operations for evaluating statistical data, e.g. average values, frequency distributions, probability functions, regression analysis
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Mathematical Physics (AREA)
- Computational Mathematics (AREA)
- Strategic Management (AREA)
- Human Resources & Organizations (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Operations Research (AREA)
- Chemical & Material Sciences (AREA)
- Pure & Applied Mathematics (AREA)
- Analytical Chemistry (AREA)
- Software Systems (AREA)
- Evolutionary Biology (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Algebra (AREA)
- Development Economics (AREA)
- Probability & Statistics with Applications (AREA)
- Game Theory and Decision Science (AREA)
- Databases & Information Systems (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Quality & Reliability (AREA)
- Tourism & Hospitality (AREA)
- General Business, Economics & Management (AREA)
- Traffic Control Systems (AREA)
Abstract
The present invention proposes a kind of traffic movement prediction method, device and computer equipment, wherein, method includes：For the congestion information of N number of period before Set cell acquisition current slot, the first congestion information of current slot is predicted according to the congestion information of N number of period, determine the corresponding object time scope of current slot, obtain the history congestion information in the range of the object time, the second congestion information in current slot is obtained according to history congestion information, the each adjacent cells lattice adjacent with Set cell are obtained within the previous period to the influence value of Set cell, the 3rd congestion information of current slot is obtained according to influence value, obtain the similar units lattice of Set cell, and obtain the 4th congestion information in current slot using similar units lattice, at least two in the four of acquisition congestion informations obtain the target congestion information of Set cell.By this method, computation complexity can be reduced, improves universality.
Description
Technical field
The present invention relates to technical field of transportation, more particularly to a kind of traffic movement prediction method, device and computer equipment.
Background technology
With the development and the raising of people's living standard quality of social economy, the quantity of private car is more and more, thus
The Urban Traffic Jam Based brought is also increasingly severe.Therefore, it is predicted for the region of traffic congestion may occur, and
The traffic in Shi Faxian regions is simultaneously shunted, to lifting urban service ability, improve people go out line efficiency have it is important
Meaning.
Existing city traffic road condition Forecasting Methodology, usually only considers the information of specific road section in city, and only considers
The periphery situation of target road section, lacks universality, and limitation is larger.In addition, existing method normally only considers speed to congestion
Influence, analyzed when being predicted by section, computation complexity is high.
The content of the invention
It is contemplated that solve at least some of the technical problems in related technologies.
For this reason, first purpose of the present invention is to propose a kind of traffic movement prediction method, by the way that urban area is drawn
It is divided into multiple cells, considers that many factors are predicted the congestion of Set cell, to reduce computation complexity,
Universality is improved, solves prior art complexity height, the technical problem of universality difference.
Second object of the present invention is to propose a kind of traffic condition predicting device.
Third object of the present invention is to propose a kind of computer equipment.
Fourth object of the present invention is to propose a kind of non-transitorycomputer readable storage medium.
The 5th purpose of the present invention is to propose a kind of computer program product.
In order to achieve the above object, first aspect present invention embodiment proposes a kind of traffic movement prediction method, including：
For any one Set cell in city, during N number of before obtaining the Set cell current slot
Between section congestion information, according to the congestion information of N number of period, predict the first congestion letter of the current slot
Breath；Wherein, N is integer and N >=1；
Determine the object time scope corresponding to the current slot, obtain the Set cell in the target
Between in the range of history congestion information, and according to the history congestion information, second obtained in the current slot gathers around
Stifled information；
The each adjacent cells lattice adjacent with the Set cell are obtained within the previous period to the target list
The influence value of first lattice, the 3rd congestion information of the current slot is obtained according to the influence value；
Inquiry obtains the similar units lattice similar to the Set cell from the city, utilizes the similar units
Lattice obtain the 4th congestion information in the current slot；
According to first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information, obtain
The target congestion information of the Set cell；Wherein, the target congestion information is used to characterize the Set cell in institute
State the congestion status of current slot.
It is described according to N number of period as another optional implementation of first aspect present invention embodiment
The congestion information, predict the first congestion information of the current slot, including：
Using default linear model, the congestion information of N number of period is weighted, is obtained described
First congestion information.
It is described to obtain the first congestion letter as another optional implementation of first aspect present invention embodiment
After breath, further include：
Calculate the variance between the history congestion information in the current slot and first congestion information；
When the variance is not up to minimum, then the weight in the linear model is adjusted, retrieved described
First congestion information, until variance minimum, using corresponding first congestion information during variance minimum as final
First congestion information.
It is described to be believed according to the history congestion as another optional implementation of first aspect present invention embodiment
Breath, obtains the second congestion information in the current slot, including：
According to the time range belonging to the current slot, inquiry obtains and the matched history of the time range
Congestion information；
Obtain the current factor for influencing traffic congestion state；
Acquisition and the matched adjustment amount of the factor, are adjusted the history congestion information using the adjustment amount,
Obtain second congestion information.
It is described to determine the current slot as another optional implementation of first aspect present invention embodiment
After corresponding object time scope, further include：
For each time range, the congestion letter before being under the jurisdiction of the Set cell in the time range is obtained
Breath；
Statistical analysis is carried out to the congestion information before described, obtains the history congestion information of the time range.
As another optional implementation of first aspect present invention embodiment, the acquisition and the object element
The adjacent each adjacent cells lattice of lattice within the previous period to the influence value of the Set cell, according to the influence value
The 3rd congestion information of the current slot is obtained, including：
For any one border of the Set cell, determine to share the institute on the border with the Set cell
State adjacent cells lattice；Wherein, a border corresponds to the adjacent cells lattice；
Obtain in the previous period and enter the adjacent cells lattice from the Set cell by the border
The first vehicle number and the first average speed, according to first vehicle number and first average speed, obtain described adjacent
First sub- influence value of the cell to the border；Obtain in the previous period from described in adjacent cells lattice process
Border enters the second vehicle number and the second average speed of the Set cell, according to second vehicle number and described second
Average speed, obtains second sub- influence value of the adjacent cells lattice to the border；
Obtain in the previous period from the adjacent cells lattice by the adjacent cells lattice another border into
Enter the 3rd vehicle number and the 3rd average speed of the adjacent cells lattice of the adjacent cells lattice, according to the 3rd vehicle number and institute
The 3rd average speed is stated, obtains threeth sub- influence value of the adjacent cells lattice to the border；Wherein, the adjacent cells lattice
Another border be the border parallel with the border of the Set cell；
Obtain in the previous period from the Set cell by the Set cell another border into
Enter the 4th vehicle number and the 4th average speed of another adjacent cells lattice, be averaged according to the 4th vehicle number and the described 4th
Speed, obtains fourth sub- influence value of the adjacent cells lattice to the border；Wherein, another border of the Set cell
It is the border parallel with the border of the Set cell；Another described adjacent cells lattice are total to the Set cell
Enjoy another border；
According to the described first sub- influence value, the second sub- influence value, the 3rd sub- influence value and the 4th sub- influence value, obtain
The influence value of the single adjacent cells lattice；
The influence value of each adjacent cells lattice is weighted, obtains the 3rd congestion information.
It is described to be influenced according to the described first son as another optional implementation of first aspect present invention embodiment
Value, the second sub- influence value, the 3rd sub- influence value and the 4th sub- influence value, obtain the shadow of the single adjacent cells lattice
Value is rung, specific formula for calculation is as follows：
Wherein, the C represents the influence value, the F1~F4Represent that the described first sub- influence value, the second son influence respectively
Value, the 3rd sub- influence value and the 4th sub- influence value, the α and β are constant, and the η is adjustment amount.
As another optional implementation of first aspect present invention embodiment, described inquired about from the city is obtained
The similar units lattice similar to the Set cell are taken, including：
From the remaining cell in addition to the Set cell in the city, identify and the Set cell
Cell with similar congestion status conversion trend is as candidate unit lattice；
The similarity between the Set cell and each candidate unit lattice is calculated, according to the similarity from all
The similar units lattice are extracted in candidate unit lattice.
It is described to calculate the Set cell as another optional implementation of first aspect present invention embodiment
With the similarity between each candidate unit lattice, including：
Using the congestion information of N number of period of the Set cell, and each candidate unit lattice
The congestion information of N number of period, forms a matrix；
Calculate the average value of each element value in the matrix；
According to the average value and the matrix, calculate similar between the Set cell and each candidate unit lattice
Degree.
As another optional implementation of first aspect present invention embodiment, it is described according to the similarity from institute
The similar units lattice are extracted in some candidate unit lattice, including：
The similarity is chosen beyond the candidate unit lattice of default first threshold as the similar units lattice.
It is described to utilize the similar units lattice as another optional implementation of first aspect present invention embodiment
The 4th congestion information in the current slot is obtained, including：
For each similar units lattice, using the congestion information of N number of period of the similar units lattice, in advance
Survey first congestion information of current slot described in the similar units lattice；
Utilize first congestion information of the similar units lattice similarity corresponding with the similar units lattice
It is multiplied, obtains the first numerical value of the similar units lattice；
First numerical value of each similar units lattice is added to obtain second value, each similar units lattice are corresponding described
Similarity is added to obtain third value, and the second value and the third value are done ratio, obtains the described 4th and gathers around
Stifled information.
It is described to utilize the similar units lattice as another optional implementation of first aspect present invention embodiment
The 4th congestion information in the current slot is obtained, including：
For each similar units lattice, history congestion letter of the similar units lattice in the range of the object time is obtained
Breath；
Utilize the history congestion information of the similar units lattice similarity corresponding with the similar units lattice
It is multiplied, obtains the 4th numerical value of the similar units lattice；
4th numerical value of each similar units lattice is added to obtain the 5th numerical value, each similar units lattice are corresponding described
Similarity is added to obtain the 6th numerical value, and the 5th numerical value and the 6th numerical value are done ratio, obtains the described 4th and gathers around
Stifled information.
It is described to be directed to any one in city as another optional implementation of first aspect present invention embodiment
Cell, before the congestion information for obtaining N number of period before the Set cell current slot, further includes：
Cell division is carried out to the city.
It is described to obtain the Set cell as another optional implementation of first aspect present invention embodiment
Target congestion information after, further include：
Obtain current location and the driving path of current vehicle；Wherein, the driving path is according to the current vehicle
Departure place and destination cook up；
According to the current location and the driving path, judge whether the current vehicle arrives at；
If it is judged that being no, then the first module that the current vehicle does not travel is extracted from the driving path
Lattice；
Obtain the target congestion information of the first module lattice；
According to the target congestion information of the first module lattice, predict that the current vehicle is driven to where destination
First module lattice when required traveling duration.
It is described according to the first module lattice as another optional implementation of first aspect present invention embodiment
The target congestion information, predict the current vehicle drive to destination where first module lattice when required traveling
Duration, including：
For each first module lattice, Vehicle Speed corresponding with the target congestion information is obtained；
According to the Vehicle Speed and the current vehicle in the road length of the first module lattice, determine described
Running time of the current vehicle in the first module lattice；
The running time of all first module lattice is added, obtains the traveling duration.
The traffic movement prediction method of the embodiment of the present invention, by for any one Set cell in city, obtaining
The congestion information of N number of period before Set cell current slot, is predicted current according to the congestion information of N number of period
The first congestion information of period, determines the object time scope corresponding to current slot, obtains in the range of the object time
History congestion information, and the second congestion information in current slot, acquisition and object element are obtained according to history congestion information
The adjacent each adjacent cells lattice of lattice, to the influence value of Set cell, obtain current within the previous period according to influence value
The 3rd congestion information of period, obtains the similar units lattice of Set cell, and obtains current time using similar units lattice
The 4th congestion information in section, believes according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion
Breath obtains the target congestion information of Set cell.By multiple from time, space, target area itself and similar area etc.
Aspect predicts the congestion of target area, makes the factor that considers during prediction traffic more comprehensive, it is possible to increase pervasive
Property, computation complexity is reduced, solves prior art complexity height, the technical problem of universality difference.
In order to achieve the above object, second aspect of the present invention embodiment proposes a kind of traffic situation prediction apparatus, including：
Time congestion prediction module, for for any one Set cell in city, obtaining the Set cell
The congestion information of N number of period before current slot, according to the congestion information of N number of period, described in prediction
First congestion information of current slot；Wherein, N is integer and N >=1；
Steric congestion prediction module, for determining the object time scope corresponding to the current slot, described in acquisition
History congestion information of the Set cell in the range of the object time, and according to the history congestion information, obtain institute
State the second congestion information in current slot；
Local correlations prediction module, for obtaining each adjacent cells lattice adjacent with the Set cell previous
To the influence value of the Set cell in a period, the 3rd congestion of the current slot is obtained according to the influence value
Information；
Holistic correlation prediction module, for from the city inquiry obtain it is similar to the Set cell similar
Cell, the 4th congestion information in the current slot is obtained using the similar units lattice；
Acquisition module, for according to first congestion information, the second congestion information, the 3rd congestion information and the 4th congestion
Information, obtains the target congestion information of the Set cell；Wherein, the target congestion information is used to characterize the target list
Congestion status of first lattice in the current slot.
The traffic condition predicting device of the embodiment of the present invention, by for any one Set cell in city, obtaining
The congestion information of N number of period before Set cell current slot, is predicted current according to the congestion information of N number of period
The first congestion information of period, determines the object time scope corresponding to current slot, obtains in the range of the object time
History congestion information, and the second congestion information in current slot, acquisition and object element are obtained according to history congestion information
The adjacent each adjacent cells lattice of lattice, to the influence value of Set cell, obtain current within the previous period according to influence value
The 3rd congestion information of period, obtains the similar units lattice of Set cell, and obtains current time using similar units lattice
The 4th congestion information in section, believes according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion
Breath obtains the target congestion information of Set cell.By multiple from time, space, target area itself and similar area etc.
Aspect predicts the congestion of target area, makes the factor that considers during prediction traffic more comprehensive, it is possible to increase pervasive
Property, computation complexity is reduced, solves prior art complexity height, the technical problem of universality difference.
In order to achieve the above object, third aspect present invention embodiment proposes a kind of computer equipment, including：Processor and deposit
Reservoir；Wherein, the processor is held by reading the executable program code stored in the memory to run with described
The corresponding program of line program code, for realizing the traffic movement prediction method as described in first aspect embodiment.
To achieve these goals, fourth aspect present invention embodiment proposes a kind of computer-readable storage of non-transitory
Medium, is stored thereon with computer program, and the traffic as described in first aspect embodiment is realized when which is executed by processor
Condition predicting method.
To achieve these goals, fifth aspect present invention embodiment proposes a kind of computer program product, when described
When instruction in computer program product is performed by processor, the traffic condition predictions side as described in first aspect embodiment is realized
Method.
The additional aspect of the present invention and advantage will be set forth in part in the description, and will partly become from the following description
Obtain substantially, or recognized by the practice of the present invention.
Brief description of the drawings
Of the invention above-mentioned and/or additional aspect and advantage will become from the following description of the accompanying drawings of embodiments
Substantially and it is readily appreciated that, wherein：
The flow diagram for the traffic movement prediction method that Fig. 1 is provided by the embodiment of the present invention one；
The flow diagram for the traffic movement prediction method that Fig. 2 is provided by the embodiment of the present invention two；
Fig. 3 is that cell divides schematic diagram in city；
Fig. 4 is the flow diagram for the traffic movement prediction method that the embodiment of the present invention three provides；
Fig. 5 is the flow diagram for the traffic movement prediction method that the embodiment of the present invention four provides；
Fig. 6 is influence schematic diagram of the adjacent cells lattice to Set cell；
Fig. 7 is the flow diagram for the traffic movement prediction method that the embodiment of the present invention five provides；
Schematic diagrames of the Fig. 8 (a) based on section analysis traffic；
Fig. 8 (b) is the schematic diagram based on unit case analysis traffic；
Fig. 9 is the structure diagram for the traffic condition predicting device that the embodiment of the present invention one provides；
Figure 10 is the structure diagram of traffic condition predicting device provided by Embodiment 2 of the present invention；
Figure 11 is the structure diagram for the traffic condition predicting device that the embodiment of the present invention three provides；
Figure 12 is the structure diagram for the traffic condition predicting device that the embodiment of the present invention four provides；
Figure 13 is the structure diagram for the traffic condition predicting device that the embodiment of the present invention five provides；And
Figure 14 is the structure diagram for the computer equipment that one embodiment of the invention proposes.
Embodiment
The embodiment of the present invention is described below in detail, the example of the embodiment is shown in the drawings, wherein from beginning to end
Same or similar label represents same or similar element or has the function of same or like element.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to for explaining the present invention, and is not considered as limiting the invention.
Below with reference to the accompanying drawings the traffic movement prediction method, device and computer equipment of the embodiment of the present invention are described.
The flow diagram for the traffic movement prediction method that Fig. 1 is provided by the embodiment of the present invention one.
As shown in Figure 1, the traffic movement prediction method comprises the following steps：
Step 101, for any one Set cell in city, the N before Set cell current slot is obtained
The congestion information of a period, according to the congestion information of N number of period, predicts the first congestion information of current slot；Wherein,
N is integer and N >=1.
In actual life, in addition to some abnormal conditions, such as great traffic accident, the traffic control etc. of burst, a ground
The change of the traffic route in area is often relatively more slow, and the change of a regional traffic behavior has some omens,
It is such as more and more crowded or more and more smooth.So as in the present embodiment, when can be according to one before current slot
Between section or traffic information in multiple periods estimate the traffic information of current slot.
Therefore, in the present embodiment, when needing the traffic information to city to be predicted, cell first is carried out to city and is drawn
Point, then using any one cell in all cells in city as Set cell, in the Set cell
The congestion status in portion is analyzed according to follow-up step.
First, the congestion information of N number of period before acquisition Set cell current slot.And then utilize acquisition
The top n period congestion information, predict the congestion information of current slot, and be used as the first congestion information.
Step 102, determine the object time scope corresponding to current slot, obtain Set cell in object time model
Interior history congestion information is enclosed, and according to history congestion information, obtains the second congestion information in current slot.
Wherein, object time scope is the time range identical with current slot in each cycle in the preceding n cycle,
A cycle is one day, and n is the positive integer not less than 1.Such as, it is assumed that current slot is morning 7:00~8:00, then target
Time range can be the morning 7 of the previous day:00~8:00 or the last week in every morning 7:00~8:00.
In some specific periods, the traffic information of the same area often changes less, and Set cell is in a rank
The traffic information in same time period in section is more similar, such as, at peak period in the morning, afternoon and evening, same section is in daily phase
With being congestion status in the period.Therefore, for same region, the history traffic information of same time period should for prediction
The traffic information of region current slot has higher referring to property.
So as to, in the present embodiment, object time model that can first according to corresponding to current slot determines current slot
Enclose, and obtain history congestion information of the Set cell in the range of the object time, and then, obtained and worked as according to history congestion information
Congestion information in the preceding period, and it is used as the second congestion information.
In the present embodiment, history that can be using the corresponding congestion status of object time the previous day scope as current slot
Congestion information.Alternatively, the corresponding congestion status of object time scope more days continuous is counted, the target that will be counted
History congestion information of the congestion status of time range as current slot.
Step 103, each adjacent cells lattice adjacent with Set cell are obtained within the previous period to target list
The influence value of first lattice, the 3rd congestion information of current slot is obtained according to influence value.
In the cell of city division, in addition to the cell of boundary, each cell in city incity has four phases
Adjacent urban units lattice, wagon flow flows in or out to object element between Set cell and adjacent four urban units lattice
There is also large effect for the traffic information of lattice.For example if four adjacent urban units lattice enter Set cell
Wagon flow is more than the wagon flow that Set cell flows out, and average speed slows down, this must cause target cities cell than before
Period congestion, it is on the contrary then can become unimpeded.
So as to which in the present embodiment, each adjacent cells lattice adjacent with Set cell can be obtained in the previous time
To the influence value of Set cell in section, the congestion information of current slot is obtained according to influence value, and is believed as the 3rd congestion
Breath.
It should be noted that for each cell of boundary, also there are four adjacent cells, simply this four lists
Include the cell of adjacent cities in first lattice, the traffic information of the cell of boundary is also by four adjacent around cells
Wagon flow situation influence.Therefore, can also be according to four adjacent units when Set cell is the cell of boundary
Lattice obtain the congestion information of current slot within the previous period to the influence value of Set cell.Alternatively, due to city
The vehicle flowrate of boundary is usually smaller, and therefore, the urban units lattice of boundary, which can directly be ignored, not to be considered.
Herein it should be noted that obtaining the specific implementation process of the 3rd congestion information of current slot according to influence value
It will provide in subsequent content, to avoid repeating, be not described in detail herein.
Step 104, inquiry obtains the similar units lattice similar to Set cell from city, is obtained using similar units lattice
Take the 4th congestion information in current slot.
In a city, although there is no directly contact between some regions, wagon flow will not be in a short period of time
Far another place is flowed to from a place, but there may be larger similitude, example between these different regions
The park of such as festivals or holidays, the commercial square at weekend, the court of weekend evenings.These regions are not geographically correlation
Connection, but have many similarities from the point of view of their property and content, whereupon it may be inferred that, the traffic behavior in these regions
There is also the degree of some related (positive correlations), so that, can be global by traveling through in the present embodiment, divided from city
All cells in inquiry obtain similar units lattice similar to Set cell, utilize similar units lattice acquisition current time
4th congestion information of Set cell in section.
Under normal circumstances, congestion status can for example include unimpeded, substantially unimpeded, slight congestion, moderate congestion and serious
Five grades of congestion.Congestion status depends on congestion information, and congestion information is the centrifugal pump of one, can be with table by the centrifugal pump
Levy out congestion status.
In the present embodiment, the speed of collector unit lattice simultaneously calculates average speed, according in average speed and cell
Vehicle density, obtains congestion information, shown in the calculation formula such as formula (1) of congestion information.
Wherein, DensitygridRepresent the vehicle density of cell, VelocitygirdRepresent the average speed in cell,
ξ is for normalized value, PgridRepresent congestion information.
In the present embodiment, congestion information can be normalized to by normalization between (0~1).In advance to (0~1) area
Between divided, such as according to 0.2 interval carry out interval division, formed (0~0.2), [0.2~0.4), [0.4~
0.6), [0.6~0.8) and [0.8~1.0) 5 segments, wherein, (0~0.2) represent it is unimpeded, [0.2~04) represent basic
Unimpeded, [0.4~06) the slight congestion of expression, [0.6~0.8) congestion of expression moderate, [0.8~1.0) represent heavy congestion.Also
It is to say, each segment can correspond to a congestion status.
Step 105, according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information,
Obtain the target congestion information of Set cell.
Wherein, target congestion information is used to characterize congestion status of the Set cell in current slot.
In the present embodiment, the first congestion information in Set cell current slot, the second congestion information, are obtained
After three congestion informations and the 4th congestion information, can according at least two congestion informations in four congestion informations of acquisition into
Row weighted calculation, the target congestion information using result of calculation as Set cell.Such as with according under four kinds of influence factors when
The congestion information of preceding period, exemplified by target congestion information is calculated by the way of the weighted sum, target congestion information can
To be calculated by equation below (2).
Si,t=α * Y+ β * Si,t,n+γ*Ci+μ*Sg,t+θ(2)
Wherein, Y be Set cell the first congestion information, Si,t,nFor the second of i-th of cell (Set cell)
Congestion information, CiFor the 3rd congestion information of i-th of cell, Sg,tFor the 4th congestion information of Set cell；α, β, γ and
μ is respectively weight of first congestion information to the 4th congestion information, and θ is constant, can be preset, for congestion information into
Row adjustment.
For example, the corresponding centrifugal pump of target congestion information calculated is 0.7, then target congestion information pair can be determined
The congestion status answered is moderate congestion.And when the target congestion information calculated is 0.3, determine that target congestion information is corresponding
Congestion status is substantially unimpeded.
The traffic movement prediction method of the present embodiment, by for any one Set cell in city, obtaining target
The congestion information of N number of period before cell current slot, current time is predicted according to the congestion information of N number of period
First congestion information of section, determines the object time scope corresponding to current slot, obtains the history in the range of the object time
Congestion information, and the second congestion information in current slot is obtained according to history congestion information, obtain and Set cell phase
Adjacent each adjacent cells lattice, to the influence value of Set cell, current time are obtained according to influence value within the previous period
3rd congestion information of section, obtains the similar units lattice of Set cell, and is obtained using similar units lattice in current slot
The 4th congestion information, obtained according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information
Take the target congestion information of Set cell.By from many aspects such as time, space, target area itself and similar areas
To predict the congestion of target area, make the factor that considers during prediction traffic more comprehensive, it is possible to increase universality, drop
Low computation complexity, solves prior art complexity height, the technical problem of universality difference.
The flow diagram for the traffic movement prediction method that Fig. 2 is provided by the embodiment of the present invention two.
As shown in Fig. 2, the traffic movement prediction method comprises the following steps：
Step 201, cell division is carried out to city.
In the present embodiment, for the city for needing progress road condition predicting, the longitude and latitude boundary value in the city can be obtained, it is sharp
A rectangle is established with the boundary value of acquisition, and mesh generation is carried out in rectangle inside, which is divided into several sizes
Cell equal, specification is consistent.As shown in the black rectangle frame in Fig. 3, black rectangle frame in Fig. 3 is its that divided
In a cell.
Step 202, for any one Set cell in city, the N before Set cell current slot is obtained
The congestion information of a period, according to the congestion information of N number of period, predicts the first congestion information of current slot；Wherein,
N is integer and N >=1.
The congestion in one region or it is unimpeded gradually form, for example the flow speeds in the region are slower and slower, because
This, can be according to the congestion information of N number of continuous period before Set cell current slot come pre- in the present embodiment
Survey the congestion information of current slot.
Specifically, when predicting the first congestion information of current slot according to the congestion information of N number of period, can utilize
Default linear model, is weighted the congestion information of N number of period, obtains the first congestion information.
Before using linear model linearly calculate, the window value of linear regression can be first set, window value is with obtaining
The number of the period taken is identical, i.e., window value is N.Assuming that to predict the congestion information of k-th of period, then need to obtain it
Preceding kth-N, k-N-1, k-N-2 ..., the congestion information of k-1 period.Using the congestion information of top n period as defeated
Enter, input into pre-set linear model, the first congestion information of current slot can be obtained.
Assuming that the first congestion information of the current slot of Set cell is denoted as Y, the top n adjacent with current slot
The congestion information of period is denoted as Y respectively1, Y2..., YN-1, YN, then the first congestion information can use formula (3) represent.
Wherein, wiRepresent i-th of congestion information YiWeight.According to actual conditions, the time more closed on current slot
Influence of the congestion information of section to the congestion information of current slot is bigger, therefore, can be with initial setting up wiIt is incremental for one
Sequence, YNWeighted value it is maximum, Y1Weighted value it is minimum.
Further, in a kind of possible implementation of the embodiment of the present invention, the first congestion of acquisition can also be believed
Breath optimizes.Specifically, the variance between the history congestion information in current slot and the first congestion information can be calculated,
When variance is not up to minimum, then the weight in linear model is adjusted, retrieves the first congestion information, recalculate
The variance between history congestion information in new the first congestion information and current slot, until variance reaches default minimum
Value, using corresponding first congestion information during variance minimum as the first final congestion information.
When obtaining N number of history congestion information, each history congestion information and the first congestion information can be calculated respectively
Between variance, and N number of variance to obtaining sum, if variance summation result be not up to default minimum value, to linear
Weight in model is adjusted, until the result of variance summation reaches minimum value, by N number of variance summed result it is minimum when correspond to
The first congestion information as the first final congestion information.
The first congestion information of acquisition is optimized by the history congestion information according to current slot, can be made pre-
The first congestion information measured relatively meets real road condition, improves the accuracy of the first congestion information prediction.
Step 203, determine the object time scope corresponding to current slot, obtain Set cell in object time model
Interior history congestion information is enclosed, and according to history congestion information, obtains the second congestion information in current slot.
Step 204, each adjacent cells lattice adjacent with Set cell are obtained within the previous period to target list
The influence value of first lattice, the 3rd congestion information of current slot is obtained according to influence value.
Step 205, inquiry obtains the similar units lattice similar to Set cell from city, is obtained using similar units lattice
Take the 4th congestion information in current slot.
Step 206, according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information,
Obtain the target congestion information of Set cell.
Wherein, target congestion information is used to characterize congestion status of the Set cell in current slot.
It should be noted that the description in the present embodiment to step 203- steps 206, it is right in previous embodiment to may refer to
The description of step 102- steps 105, details are not described herein again.
Step 207, current location and the driving path of current vehicle are obtained.
In the present embodiment, can according to installed in current vehicle automobile data recorder, GPS navigator, smart machine terminal
The current location of current vehicle is obtained Deng device.Further, the departure place inputted according to user on the devices such as navigator
And destination, it can recommend to exercise path to user, user can travel according to the paths wherein recommended.
Step 208, according to the current location of current vehicle and the driving path of current vehicle, judge whether current vehicle arrives
Up to destination.
, can be to the position of vehicle into line trace in vehicle travel process.If the current location of current vehicle is not located
In destination, it is determined that current vehicle also travels on driving path, does not arrive at also, then performs step 209；If work as
The current location of vehicle in front is in destination, it is determined that current vehicle has arrived at destination, terminates.
Step 209, the first module lattice that current vehicle does not travel are extracted from driving path.
Wherein, first module lattice can be that current vehicle is not run over every in all cells where driving path
One cell.For example driving path includes five cells, the direction from starting point to destination, the volume of each cell
Number it is respectively 1,2,3,4 and 5, the Set cell that current vehicle is currently located is the cell that numbering is 3, then first module lattice
The cell that the cell and numbering for being 4 for numbering are 5.
In the present embodiment, after the driving path for obtaining current vehicle, according to the run routing information of acquisition, it can obtain
The cell that driving path is passed through, and the cell according to where current vehicle are taken, can extract and work as from driving path
The first module lattice that vehicle in front does not travel.
Step 210, the target congestion information of first module lattice is obtained.
After first module lattice are determined, for each first module lattice, it can use and foregoing acquisition Set cell
The identical method of target congestion information, obtain the target congestion informations of first module lattice.
Step 211, according to the target congestion information of first module lattice, prediction current vehicle drives to the where destination
Required traveling duration during one cell.
In the present embodiment, after the target congestion information for obtaining first module lattice, gathered around according to the target of first module lattice
Stifled information, can predict current vehicle drive to destination where first module lattice when required traveling duration.
Specifically, each first module lattice can be directed to, obtain Vehicle Speed corresponding with target congestion information, than
Such as, the average speed under different congestion status and the corresponding congestion status can be prestored, and stores target congestion
The correspondence of information and congestion status, after the target congestion information of first module lattice is obtained, by inquiring about corresponding close
System, it may be determined that the congestion status of first module lattice, and then first module lattice are determined when being under the congestion status, first module
The average speed of vehicle in lattice, the speed can be used as the corresponding Vehicle Speed of target congestion information.Travelled according to vehicle
Speed and current vehicle determine running time of the current vehicle in first module lattice in the road length of first module lattice, will
The running time of all first module lattice is added, and obtains traveling duration.
The traffic movement prediction method of the present embodiment, by the way that (the second congestion is believed from time (the first congestion information), space
Breath), many aspects such as adjacent area (the 3rd congestion information) and similar area (the 4th congestion information) predict target area
Congestion, makes the factor that considers during prediction traffic more comprehensive, it is possible to increase universality, reduces computation complexity.It is logical
The driving path for obtaining current vehicle is crossed, the first module lattice that current vehicle does not travel are extracted from driving path, obtains first
The target congestion information of cell, according to where the target congestion information of first module lattice predicts that current vehicle drives to destination
First module lattice when required traveling duration, the time that user arrives at can be predicted, facilitate user according to
The arrangement of time schedule arrived at, lifts user experience.
In order to more clearly describe in above-described embodiment according to second in history congestion information acquisition current slot
The specific implementation process of congestion information, the embodiment of the present invention propose another traffic movement prediction method, and Fig. 4 is real for the present invention
The flow diagram of the traffic movement prediction method of the offer of example three is provided.
As shown in figure 4, on the basis of embodiment as shown in Figure 1, step 102 may comprise steps of：
Step 301, the time range according to belonging to current slot, inquiry obtain and the matched history congestion of time range
Information.
In the present embodiment, 24 hours of one day can be divided into multiple time ranges with one day for a cycle, than
Such as, the duration of two hours is included with a time range, 12 time ranges were divided into by one day；Alternatively, with a time
Scope includes the duration of three hours, and 8 time ranges etc. were divided into by one day.In the traffic information progress to Set cell
During prediction, time range that can first according to belonging to current slot determines current slot, further according to belonging to current slot
Time range, inquiry obtain with the matched history congestion information of time range.
Wherein, inquire about acquisition can be with the matched history congestion information of time range before in a cycle (one day)
The history congestion information of the time range or in several cycles before the time range history congestion information carry out
The history congestion information obtained after statistical analysis.
Before only obtaining during the history congestion information of a cycle, time in a cycle before can directly acquiring
The history congestion information of scope.For example the time range belonging to current slot is 7:00~9:00, then it can obtain the previous day
In 7:00~9:In 00 this time range, the congestion information of Set cell is as the history congestion information for inquiring about acquisition.
Before acquisition during the history congestion information in several cycles, it can be obtained for the time range in each cycle
The congestion information before the Set cell being under the jurisdiction of in the time range is taken, statistical analysis is carried out to congestion information before,
Obtain the history congestion information of the time range.Such as, it is assumed that the history congestion information in first three cycle of acquisition, current time
Time range belonging to section is 7:00~9:00, then in first three day of acquisition current slot, 7 in every day:00~9:00 this
In the range of one time, the congestion information of Set cell, and statistical analysis is carried out to three congestion informations of acquisition, for example pass through
The mode averaged, the history congestion information that gained average is obtained as inquiry.
Step 302, the current factor for influencing traffic congestion state is obtained.
Wherein, the factor for influencing traffic congestion state can be the one or more in weather, traffic control, red-letter day etc..
In the present embodiment, Set cell can be obtained in current slot, influence weather, the section of traffic congestion state
The factors such as day.
Step 303, acquisition and the matched adjustment amount of factor, are adjusted history congestion information using adjustment amount, obtain
Second congestion information.
Different influence factors may be different to the degree of influence of urban traffic conditions, in the present embodiment, can be directed to not
Same influence factor, by analyzing influence of the influence factor to congestion information in congestion information before, obtains difference
The corresponding degree of influence of influence factor；Alternatively, can also rule of thumb it be pre-set for different influence factors corresponding
Degree of influence.So as to after the current factor for influencing traffic congestion state is got, obtain and the matched influence of factor
Dynamics is adjusted history congestion information as adjustment amount, and using adjustment amount, obtains the second congestion information.Set cell
It can be represented in the second congestion information of current slot by formula (4).
Si,t,n=Wi,t+Ti,t,n(4)
Wherein, Si,t,nRepresent congestion information of i-th of cell in n-th day t-th period, i.e. the second congestion information；
Wi,tRepresent history congestion information of i-th of cell in the time range belonging to t-th of period；Ti,t,nRepresent i-th of list
The adjustment amount of first lattice impacted factor in n-th day t-th of period.
The traffic movement prediction method of the present embodiment, by the inquiry of time range according to belonging to current slot obtain with
The matched history congestion information of time range, obtains the current factor for influencing traffic congestion state, obtains and the matched tune of factor
Whole amount, is adjusted history congestion information using adjustment amount to obtain the second congestion information.By considering going through for same time period
The influence of history congestion information and traffic congestion state influence factor, it is possible to increase the authenticity and standard of the second congestion information of acquisition
True property.
In order to more clearly describe to obtain current slot according to the influence value of adjacent cells lattice in above-described embodiment
The specific implementation process of 3rd congestion information, the embodiment of the present invention propose another traffic movement prediction method, and Fig. 5 is this hair
The flow diagram for the traffic movement prediction method that bright example IV provides.
As shown in figure 5, on the basis of embodiment as shown in Figure 1, step 103 may comprise steps of：
Step 401, for any one border of Set cell, the adjacent list with Set cell Border is determined
First lattice；Wherein, a border corresponds to an adjacent cells lattice.
One city is divided into multiple cells, and using side as boundary between cell, each cell has four edges,
The each edge of each cell corresponds to an adjacent cells lattice, the adjacent cells of the cell at least a line of marginal position
Lattice are another cell in city.Therefore, in the present embodiment, for any one border of Set cell, it may be determined that
With the adjacent cells lattice of Set cell Border.
Step 402, the first car for entering adjacent cells lattice in the previous period by border from Set cell is obtained
Number and the first average speed, according to the first vehicle number and the first average speed, obtain first son of the adjacent cells lattice to border
Influence value；Obtain the second vehicle number and second for entering Set cell in the previous period by border from adjacent cell
Average speed, according to the second vehicle number and the second average speed, obtains second sub- influence value of the adjacent cells lattice to border.
Each cell in city has four borders, and the wagon flow of corresponding four direction, there is a fixed number in each direction
The vehicle and mean flow rate of amount, therefore, for same cell, there is respective jam situation, can distinguish in each direction
Obtain each borderline jam situation.
For each border of Set cell, wagon flow can flow into Set cell from adjacent cell through border,
Adjacent cells lattice can be flowed into from Set cell through border.Wagon flow enters adjacent cells lattice from Set cell, to target list
The traffic of first lattice plays the role of unimpeded；Wagon flow enters Set cell, the traffic to Set cell from adjacent cell
Situation plays the role of congestion.
In the present embodiment, for any one border of Set cell, it can obtain in the previous period from target
Cell enters the first vehicle number and the first average speed of adjacent cells lattice by border, and according to the first vehicle number and first
Average speed obtains first sub- influence value of the adjacent cells lattice to border, and the first sub- influence value is properly termed as escape power.Meanwhile obtain
The second vehicle number and the second average speed for entering Set cell in the previous period by border from adjacent cell are taken,
And second sub- influence value of the adjacent cells lattice to border, the second sub- influence value are obtained according to the second vehicle number and the second average speed
It is properly termed as driving force.
Fig. 6 is influence schematic diagram of the adjacent cells lattice to Set cell.In Fig. 6, A is Set cell, B1, B2, B3
With four adjacent cells lattice that B4 is Set cell.For the border shared between Set cell A and adjacent cells lattice B1
For, F1 represents the first sub- influence value in Fig. 6, and F2 is the second sub- influence value.
Step 403, obtain in the previous period and enter phase from adjacent cell by another border of adjacent cells lattice
The 3rd vehicle number and the 3rd average speed of the adjacent cells lattice of adjacent cell, according to the 3rd vehicle number and the 3rd average speed,
Obtain threeth sub- influence value of the adjacent cells lattice to border；Wherein, another border of adjacent cells lattice is and Set cell
The parallel border in border.
In addition to there is the first sub- influence value and the second sub- influence value that directly affect to Set cell, adjacent cells
Between lattice and the adjacent cells lattice of adjacent cells lattice wagon flow flow in and out to the traffic of Set cell there is also
Influence indirectly.
Therefore, in the present embodiment, can also obtain parallel with adjacent cells lattice and Set cell Border adjacent
The influence value on the another side bound pair border of cell.Specifically, it can obtain in the previous period and pass through from adjacent cell
Another border of adjacent cells lattice enters the 3rd vehicle number and the 3rd average speed of the adjacent cells lattice of adjacent cells lattice, and root
Threeth sub- influence value of the adjacent cells lattice to border is obtained according to the 3rd vehicle number and the 3rd average speed.
By taking Fig. 6 as an example, the border that cell B1 and cell D2 are shared is another border of adjacent cells lattice B1, Fig. 6
In F3 i.e. represent the 3rd sub- influence value.
Step 404, obtain in the previous period and enter separately from Set cell by another border of Set cell
The 4th vehicle number and the 4th average speed of one adjacent cells lattice, according to the 4th vehicle number and the 4th average speed, obtain phase
Fourth sub- influence value of the adjacent cell to border.
Wherein, another border of Set cell is the border parallel with the border of Set cell；Another adjacent list
First lattice share another border with Set cell.
By taking Fig. 6 as an example, when currently definite adjacent cells lattice are B1, another border of Set cell is object element
The border shared between lattice A and adjacent cells lattice B4, obtains in the previous period and passes through Set cell from Set cell
Another border enter another adjacent cells lattice the 4th vehicle number and the 4th average speed, that is, obtain previous time period in from
Set cell A enters the 4th of adjacent cells to B4 by the border shared between Set cell A and adjacent cells lattice B4
Vehicle number and the 4th average speed, the adjacent cells lattice obtained according to the 4th vehicle number and the 4th average speed are to the 4th of border
Sub- influence value is the F4 in Fig. 6.
In the present embodiment, the 3rd sub- influence value and the 4th sub- influence value are properly termed as tractive force, and adjacent cells lattice with
Set cell the parallel boundary of Border escape power, to the first sub- influence value and the second sub- influence value play driving or
The effect of prevention, influences the traffic of Set cell indirectly.For the first sub- influence value, if the 3rd sub- influence value
The flow speeds of expression faster, then play driving effect to the first sub- influence value, are conducive to alleviate the congestion feelings of Set cell
Condition；If the flow speeds that the 3rd sub- influence value represents are slower, interception is played to the first sub- influence value, is unfavorable for target
Cell it is unimpeded.
Step 405, according to the first sub- influence value, the second sub- influence value, the 3rd sub- influence value and the 4th sub- influence value, obtain
The influence value of single adjacent cells lattice.
For each border of Set cell, adjacent cells lattice are obtained to the first sub- influence value on the border,
After two sub- influence values, the 3rd sub- influence value and the 4th sub- influence value, according to the first sub- influence value, the second sub- influence value, the 3rd
Sub- influence value and the 4th sub- influence value, can obtain influence value of the single adjacent cells lattice to Set cell.
Specifically, single adjacent cells lattice can use formula (5) to represent as follows the influence value of Set cell.
Wherein, C represents influence value, F1~F4The first sub- influence value, the second sub- influence value, the 3rd sub- influence value are represented respectively
With the 4th sub- influence value, α and β are constant, and η is adjustment amount, represent influence of the other factors to influence value.
Step 406, the influence value of each adjacent cells lattice is weighted, obtains the 3rd congestion information.
Set cell has four adjacent adjacent cells lattice, is obtained for each adjacent cells lattice to Set cell
After influence value, the influence value of each adjacent cells lattice can be weighted, obtain the 3rd congestion information.
By taking Fig. 6 as an example, the 3rd congestion information of Set cell A (uses CARepresent) it can be calculated by equation below (6)
Obtain.
CA=λ1·CB1→A+λ2·CB2→A+λ3·CB3→A+λ4·CB4→A(6)
Wherein, λi(i=1,2,3,4) represents the weight of the influence value of each adjacent cells lattice, CB1→ARepresent adjacent cells
Lattice B1 is to the influence value of Set cell A, CB2→ARepresent adjacent cells lattice B2 to the influence value of Set cell A, CB3→ARepresent
Adjacent cells lattice B3 is to the influence value of Set cell A, CB4→ARepresent influence values of the adjacent cells lattice B4 to Set cell A.
The traffic movement prediction method of the present embodiment, by obtaining influence of each adjacent cells lattice to Set cell
Value, the influence value of each adjacent cells lattice is weighted to obtain the 3rd congestion information, it is contemplated that adjacent area is to target
The influence of region transportation situation, makes traffic condition predictions more comprehensive.
In order to more clearly in description above-described embodiment from city inquiry obtain it is similar to Set cell similar
Cell, the specific implementation process of the 4th congestion information in current slot is obtained using similar units lattice, and the present invention is implemented
Example proposes another traffic movement prediction method, and Fig. 7 is the stream for the traffic movement prediction method that the embodiment of the present invention five provides
Journey schematic diagram.
As shown in fig. 7, on the basis of embodiment as shown in Figure 1, step 104 may comprise steps of：
Step 501, from the remaining cell in addition to Set cell in city, identify has with Set cell
The cell of similar congestion status conversion trend is as candidate unit lattice.
Wherein, on similar congestion status conversion trend refers to two cells in identical continuous time section at the same time
Rise or decline at the same time, overall change curve keeps basically identical.
Specifically, the congestion status sequence in nearest several continuous time sections of Set cell is obtained, forms a mesh
Mark the congestion status sequence of cell.Obtain the congestion status sequence in nearest several continuous time sections of remaining cell, shape
Into the congestion status sequence of remaining cell, two congestion status sequences are compared, if in two congestion status sequences
The congestion information of expression congestion status keep identical variation tendency, then can determine that Set cell is with remaining cell
Similar congestion status.That is, ascendant trend is presented in the congestion status of Set cell in nearest continuous time section,
Then ascendant trend is also presented in the congestion status of remaining cell；The congestion status of Set cell in nearest continuous time section
Downward trend is presented, then the congestion status change of downward trend, i.e. Set cell is also presented in the congestion status of remaining cell
Congestion status change with remaining cell is kept substantially consistent.
In the present embodiment, it can identify and target in all cells from the city in addition to Set cell
The congestion status of cell converts the similar cell of trend as candidate unit lattice.
Step 502, the similarity between Set cell and each candidate unit lattice is calculated, according to similarity from all
Similar units lattice are extracted in candidate unit lattice.
Congestion status conversion trend according to two cells is similar not can determine that the two cells be it is similar, than
Such as, the time series of the congestion status of a cell is { 0,0,0,0,0,0,1 }, the congestion status of another cell when
Between sequence be { 5,5,5,5,5,5,6 }, although the change of the time series of the congestion status of the two cells is all more steady,
But congestion level difference is larger.Therefore, in the present embodiment, candidate unit lattice can be screened, by calculating object element
Similarity between lattice and each candidate unit lattice, similar units lattice are extracted according to similarity from all candidate unit lattice.
Specifically, the congestion information of N number of period of Set cell, and the N of each candidate unit lattice can be utilized
The congestion information of a period, forms a matrix, as shown in formula (7).
Wherein, gridi+a(a=0,1 ..., m) represents cell numbering, tj-b(b=0,1 ..., N) represent N number of period
And the numbering of current slot,Represent that numbering is gridi+aCell in numbering be tj-bPeriod in gather around
Stifled information.
Then, average value is obtained according to the exploitation of all elements in matrix, and according to average value and matrix, calculates mesh
Mark the similarity between cell and each candidate unit lattice.Similarity between two cells can be counted by formula (8)
Obtain.
Wherein, i represents i-th of candidate unit lattice, and g represents Set cell, Di,gRepresent i and g two cells it
Between similarity, U represent form matrix,The average value of each element value, R in representing matrixu,iRepresent that cell i exists
Corresponding value, R in matrixu,gRepresent Set cell g corresponding values in a matrix.
Finally, select similarity beyond the candidate unit lattice of default first threshold as similar units lattice.Wherein, first
Threshold value is set in advance.
Step 503, the 4th congestion information in current slot is obtained using similar units lattice.
As a kind of possible implementation, the 4th congestion information in current slot is being obtained using similar units lattice
When, each similar units lattice can be directed to, using the congestion information of N number of period of similar units lattice, predict similar units lattice
First congestion information of current slot；Utilize the first congestion information of similar units lattice similarity corresponding with similar units lattice
It is multiplied, obtains the first numerical value of similar units lattice；First numerical value of each similar units lattice is added to obtain second value, will be every
The corresponding similarity of a similar units lattice is added to obtain third value, and second value and third value are done ratio, obtains
4th congestion information.
The process of above-mentioned the 4th congestion information of acquisition can use formula (9) to represent.
Wherein, Sg,tRepresent fourth congestion informations of the Set cell g in current slot t；Si,tRepresent i-th of similar list
First lattice are in the first congestion information of current slot t, the number of the total similar units lattice of m expressions, Di,gRepresent i-th of similar list
Similarity between first lattice and Set cell g.
As a kind of possible implementation, the 4th congestion information in current slot is being obtained using similar units lattice
When, each similar units lattice can be directed to, obtain history congestion information of the similar units lattice in the range of the object time；Utilize phase
It is multiplied like the history congestion information similarity corresponding with similar units lattice of cell, obtains the 4th numerical value of similar units lattice；
4th numerical value of each similar units lattice is added to obtain the 5th numerical value, the corresponding similarity of each similar units lattice is added
Ratio is done to the 6th numerical value, and by the 5th numerical value and the 6th numerical value, obtains the 4th congestion information.
The traffic movement prediction method of the present embodiment, candidate unit is identified by the conversion trend according to congestion
Lattice, the similar units lattice of Set cell are extracted by calculating similarity from candidate unit lattice, are obtained using similar units lattice
The 4th congestion information in current slot is taken, can consider surrounding enviroment from the global influence factor for considering congestion information
Influence, Consideration is more comprehensive.
Schematic diagrames of the Fig. 8 (a) based on section analysis traffic, Fig. 8 (b) is showing based on unit case analysis traffic
It is intended to.From Fig. 8 (a) as can be seen that based on section analysis traffic when, vehicle needed from A to B by 5 roads, 4
Road junction.When from Fig. 8 (b) as can be seen that being based on unit case analysis traffic, vehicle only passes through 3 cells from A to B.Cause
This, compared to the analysis method based on section, the traffic movement prediction method computation complexity based on cell reduces, prediction effect
Rate improves.
In order to realize above-described embodiment, the present invention also proposes a kind of traffic condition predicting device.
Fig. 9 is the structure diagram for the traffic condition predicting device that the embodiment of the present invention one provides.
As shown in figure 9, the traffic condition predicting device 90 includes：Time congestion prediction module 910, steric congestion prediction mould
Block 920, local correlations prediction module 930, holistic correlation prediction module 940, and acquisition module 950.Wherein,
Time congestion prediction module 910, for for any one Set cell in city, obtaining Set cell and working as
The congestion information of N number of period before the preceding period, according to the congestion information of N number of period, predicts the of current slot
One congestion information；Wherein, N is integer and N >=1.
Specifically, time congestion prediction module 910 can utilize default linear model, the congestion letter to N number of period
Breath is weighted, and obtains the first congestion information.
Further, in a kind of possible implementation of the embodiment of the present invention, time congestion prediction module 910 obtains the
After one congestion information, the variance between the history congestion information in current slot and the first congestion information can also be calculated；
When variance is not up to minimum, then the weight in linear model is adjusted, the first congestion information is retrieved, until variance
Minimum, using corresponding first congestion information during variance minimum as the first final congestion information.
The first congestion information of acquisition is optimized by the history congestion information according to current slot, can be made pre-
The first congestion information measured relatively meets real road condition, improves the accuracy of the first congestion information prediction.
Steric congestion prediction module 920, for determining the object time scope corresponding to current slot, obtains target list
History congestion information of first lattice in the range of the object time, and according to history congestion information, obtains the in current slot
Two congestion informations.
Local correlations prediction module 930, for obtaining each adjacent cells lattice adjacent with Set cell previous
To the influence value of Set cell in a period, according to the 3rd congestion information of influence value acquisition current slot.
Holistic correlation prediction module 940, the similar units similar to Set cell for the inquiry acquisition from city
Lattice, the 4th congestion information in current slot is obtained using similar units lattice.
Acquisition module 950, for being gathered around according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th
Stifled information, obtains the target congestion information of Set cell；Wherein, target congestion information is used to characterize Set cell current
The congestion status of period.
Further, in a kind of possible implementation of the embodiment of the present invention, as shown in Figure 10, as shown in Figure 9 real
On the basis of applying example, which further includes：
Division module 900, for carrying out cell division to city.
Duration prediction module 960, for obtaining the driving path of current vehicle, current vehicle is extracted not from driving path
The first module lattice of traveling, obtain the target congestion information of first module lattice, according to the target congestion information of first module lattice, in advance
Required traveling duration when surveying the first module lattice where current vehicle drives to destination.
Specifically, duration prediction module 960 is predicting current vehicle traveling according to the target congestion information of first module lattice
During to first module lattice where destination during required traveling duration, can be directed to each first module lattice, acquisition and mesh
Mark the corresponding Vehicle Speed of congestion information；Grown according to Vehicle Speed and current vehicle in the traveling of first module lattice
Degree, determines running time of the current vehicle in first module lattice；The running time of all first module lattice is added, is obtained
Travel duration.
By obtaining the driving path of current vehicle, the first module that current vehicle does not travel is extracted from driving path
Lattice, obtain the target congestion information of first module lattice, and current vehicle traveling is predicted according to the target congestion information of first module lattice
Required traveling duration, can be predicted the time that user arrives at during to first module lattice where destination,
User is facilitated to lift user experience according to the arrangement of time schedule arrived at.
Further, in a kind of possible implementation of the embodiment of the present invention, as shown in figure 11, as shown in Figure 9 real
On the basis of applying example, steric congestion prediction module 920 can include：
Acquiring unit 921 is inquired about, for the time range according to belonging to current slot, inquiry obtains and time range
The history congestion information matched somebody with somebody.
Alternatively, before only obtaining during the history congestion information of a cycle (1 day), inquiry acquiring unit 921 can be with
The history congestion information of the interior time range of a cycle before directly acquiring.
Alternatively, before acquisition during the history congestion information in several cycles, inquiry acquiring unit 921 can be directed to each
The time range in cycle, obtain and be under the jurisdiction of congestion information before the Set cell in the time range, to before
Congestion information carries out statistical analysis, obtains the history congestion information of the time range.
Acquisition factor unit 922, for obtaining the current factor for influencing traffic congestion state.
Adjustment unit 923, for acquisition and the matched adjustment amount of factor, adjusts history congestion information using adjustment amount
It is whole, obtain the second congestion information.
By considering the history congestion information of same time period and the influence of traffic congestion state influence factor, it is possible to increase
The authenticity and accuracy of the second congestion information obtained.
Further, in a kind of possible implementation of the embodiment of the present invention, as shown in figure 12, as shown in Figure 9 real
On the basis of applying example, local correlations prediction module 930 can include：
Determination unit 931, for any one border for Set cell, determines and Set cell Border
Adjacent cells lattice；Wherein, a border corresponds to an adjacent cells lattice.
Obtaining son influences value cell 932, enters phase from Set cell by border for obtaining in the previous period
The first vehicle number and the first average speed of adjacent cell, according to the first vehicle number and the first average speed, obtain adjacent cells
First sub- influence value of the lattice to border；Obtain in the previous period and enter Set cell from adjacent cell by border
Second vehicle number and the second average speed, according to the second vehicle number and the second average speed, obtain adjacent cells lattice to border
Second sub- influence value；Obtain in the previous period and enter adjacent list from adjacent cell by another border of adjacent cells lattice
The 3rd vehicle number and the 3rd average speed of the adjacent cells lattice of first lattice, according to the 3rd vehicle number and the 3rd average speed, obtain
Threeth sub- influence value of the adjacent cells lattice to border；Wherein, another border of adjacent cells lattice is the border with Set cell
Parallel border；And obtain in the previous period and enter separately from Set cell by another border of Set cell
The 4th vehicle number and the 4th average speed of one adjacent cells lattice, according to the 4th vehicle number and the 4th average speed, obtain phase
Fourth sub- influence value of the adjacent cell to border；Wherein, another border of Set cell is put down with the border of Set cell
Capable border；Another adjacent cells lattice shares another border with Set cell.
Influence value computing unit 933, for according to the first sub- influence value, the second sub- influence value, the 3rd sub- influence value and
Four sub- influence values, obtain the influence value of single adjacent cells lattice.
Specifically, the shadow of single adjacent cells lattice can be calculated in influence value computing unit 933 according to above-mentioned formula (5)
Ring value.
Weighted calculation module 934, for the influence value of each adjacent cells lattice to be weighted, obtains the 3rd congestion
Information.
Further, in a kind of possible implementation of the embodiment of the present invention, as shown in figure 13, as shown in Figure 9 real
On the basis of applying example, holistic correlation prediction module 940 can include：
Recognition unit 941, for from the remaining cell in addition to Set cell in city, identifying and target list
First lattice have the cell of similar congestion status conversion trend as candidate unit lattice.
Extraction module 942, for calculating the similarity between Set cell and each candidate unit lattice, according to similarity
Similar units lattice are extracted from all candidate unit lattice.
Specifically, extraction module 942 is when calculating the similarity between Set cell and each candidate unit lattice, can be with
First with the congestion information of N number of period of Set cell, and the congestion letter of N number of period of each candidate unit lattice
Cease, one matrix of composition, the average value of each element value, according to average value and matrix, calculates object element in calculating matrix
Similarity between lattice and each candidate unit lattice.And then extraction module 942 can choose similarity and exceed default first threshold
The candidate unit lattice of value are as similar units lattice.
Acquiring unit 943, for obtaining the 4th congestion information in current slot using similar units lattice.
As a kind of possible implementation, acquiring unit 943 can be directed to each similar units lattice, utilize similar units
The congestion information of N number of period of lattice, predicts the first congestion information of similar units lattice current slot；Utilize similar units lattice
Corresponding with the similar units lattice similarity of the first congestion information be multiplied, obtain the first numerical value of similar units lattice；By each phase
It is added to obtain second value like the first numerical value of cell, the corresponding similarity of each similar units lattice is added to obtain the 3rd number
Value, and second value and third value are done into ratio, obtain the 4th congestion information.
As a kind of possible implementation, acquiring unit 943 can be directed to each similar units lattice, obtain similar units
History congestion information of the lattice in the range of the object time；It is corresponding with similar units lattice using the history congestion information of similar units lattice
Similarity be multiplied, obtain the 4th numerical value of similar units lattice；4th numerical value of each similar units lattice is added to obtain the 5th
Numerical value, the corresponding similarity of each similar units lattice is added to obtain the 6th numerical value, and the 5th numerical value is done with the 6th numerical value
Ratio, obtains the 4th congestion information.
It should be noted that the foregoing explanation to traffic movement prediction method embodiment is also applied for the embodiment
Traffic condition predicting device, its realization principle is similar, and details are not described herein again.
The traffic condition predicting device of the present embodiment, by for any one Set cell in city, obtaining target
The congestion information of N number of period before cell current slot, current time is predicted according to the congestion information of N number of period
First congestion information of section, determines the object time scope corresponding to current slot, obtains the history in the range of the object time
Congestion information, and the second congestion information in current slot is obtained according to history congestion information, obtain and Set cell phase
Adjacent each adjacent cells lattice, to the influence value of Set cell, current time are obtained according to influence value within the previous period
3rd congestion information of section, obtains the similar units lattice of Set cell, and is obtained using similar units lattice in current slot
The 4th congestion information, obtained according to the first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information
Take the target congestion information of Set cell.By from many aspects such as time, space, target area itself and similar areas
To predict the congestion of target area, make the factor that considers during prediction traffic more comprehensive, it is possible to increase universality, drop
Low computation complexity, solves prior art complexity height, the technical problem of universality difference.
In order to realize above-described embodiment, the present invention also proposes a kind of computer equipment.
Figure 14 is the structure diagram for the computer equipment that one embodiment of the invention proposes.As shown in figure 14, the computer
Equipment 140 includes：Processor 141 and memory 142.Wherein, what processor 141 was stored by reading in memory 142 holds
Line program code runs program corresponding with executable program code, for realizing the traffic described in previous embodiment
Forecasting Methodology.
In order to realize above-described embodiment, the present invention also proposes a kind of non-transitorycomputer readable storage medium, deposits thereon
Computer program is contained, traffic movement prediction method as in the foregoing embodiment is realized when which is executed by processor.
In order to realize above-described embodiment, the present invention also proposes a kind of computer program product, when in computer program product
Instruction traffic movement prediction method as in the foregoing embodiment is realized when being performed by processor.
In the description of this specification, reference term " one embodiment ", " some embodiments ", " example ", " specifically show
The description of example " or " some examples " etc. means specific features, structure, material or the spy for combining the embodiment or example description
Point is contained at least one embodiment of the present invention or example.In the present specification, schematic expression of the above terms is not
It must be directed to identical embodiment or example.Moreover, particular features, structures, materials, or characteristics described can be in office
Combined in an appropriate manner in one or more embodiments or example.In addition, without conflicting with each other, the skill of this area
Art personnel can be tied the different embodiments or example described in this specification and different embodiments or exemplary feature
Close and combine.
In addition, term " first ", " second " are only used for description purpose, and it is not intended that instruction or hint relative importance
Or the implicit quantity for indicating indicated technical characteristic.Thus, define " first ", the feature of " second " can be expressed or
Implicitly include at least one this feature.In the description of the present invention, " multiple " are meant that at least two, such as two, three
It is a etc., unless otherwise specifically defined.
Any process or method described otherwise above description in flow chart or herein is construed as, and represents to include
Module, fragment or the portion of the code of the executable instruction of one or more the step of being used for realization custom logic function or process
Point, and the scope of the preferred embodiment of the present invention includes other realization, wherein can not press shown or discuss suitable
Sequence, including according to involved function by it is basic at the same time in the way of or in the opposite order, carry out perform function, this should be of the invention
Embodiment person of ordinary skill in the field understood.
Expression or logic and/or step described otherwise above herein in flow charts, for example, being considered use
In the order list for the executable instruction for realizing logic function, may be embodied in any computer-readable medium, for
Instruction execution system, device or equipment (such as computer based system including the system of processor or other can be held from instruction
The system of row system, device or equipment instruction fetch and execute instruction) use, or combine these instruction execution systems, device or set
It is standby and use.For the purpose of this specification, " computer-readable medium " can any can be included, store, communicate, propagate or pass
Defeated program is for instruction execution system, device or equipment or the dress used with reference to these instruction execution systems, device or equipment
Put.The more specifically example (non-exhaustive list) of computer-readable medium includes following：Electricity with one or more wiring
Connecting portion (electronic device), portable computer diskette box (magnetic device), random access memory (RAM), read-only storage
(ROM), erasable edit read-only storage (EPROM or flash memory), fiber device, and portable optic disk is read-only deposits
Reservoir (CDROM).In addition, computer-readable medium can even is that the paper that can print described program on it or other are suitable
Medium, because can be for example by carrying out optical scanner to paper or other media, then into edlin, interpretation or if necessary with it
His suitable method is handled electronically to obtain described program, is then stored in computer storage.
It should be appreciated that each several part of the present invention can be realized with hardware, software, firmware or combinations thereof.Above-mentioned
In embodiment, software that multiple steps or method can be performed in memory and by suitable instruction execution system with storage
Or firmware is realized.Such as, if realized with hardware with another embodiment, following skill well known in the art can be used
Any one of art or their combination are realized：With the logic gates for realizing logic function to data-signal from
Logic circuit is dissipated, the application-specific integrated circuit with suitable combinational logic gate circuit, programmable gate array (PGA), scene can compile
Journey gate array (FPGA) etc..
Those skilled in the art are appreciated that to realize all or part of step that above-described embodiment method carries
Suddenly it is that relevant hardware can be instructed to complete by program, the program can be stored in a kind of computer-readable storage medium
In matter, the program upon execution, including one or a combination set of the step of embodiment of the method.
In addition, each functional unit in each embodiment of the present invention can be integrated in a processing module, can also
That unit is individually physically present, can also two or more units be integrated in a module.Above-mentioned integrated mould
Block can both be realized in the form of hardware, can also be realized in the form of software function module.The integrated module is such as
Fruit is realized in the form of software function module and as independent production marketing or in use, can also be stored in a computer
In read/write memory medium.
Storage medium mentioned above can be read-only storage, disk or CD etc..Although have been shown and retouch above
The embodiment of the present invention is stated, it is to be understood that above-described embodiment is exemplary, it is impossible to be interpreted as the limit to the present invention
System, those of ordinary skill in the art can be changed above-described embodiment, change, replace and become within the scope of the invention
Type.
Claims (10)
- A kind of 1. traffic movement prediction method, it is characterised in that including：For any one Set cell in city, N number of period before the Set cell current slot is obtained Congestion information, according to the congestion information of N number of period, predict the first congestion information of the current slot； Wherein, N is integer and N >=1；Determine the object time scope corresponding to the current slot, obtain the Set cell in the object time model Interior history congestion information is enclosed, and according to the history congestion information, obtains the second congestion letter in the current slot Breath；The each adjacent cells lattice adjacent with the Set cell are obtained within the previous period to the Set cell Influence value, the 3rd congestion information of the current slot is obtained according to the influence value；Inquiry obtains the similar units lattice similar to the Set cell from the city, is obtained using the similar units lattice Take the 4th congestion information in the current slot；According to first congestion information, the second congestion information, the 3rd congestion information and/or the 4th congestion information, described in acquisition The target congestion information of Set cell；Wherein, the target congestion information is worked as characterizing the Set cell described The congestion status of preceding period.
- 2. according to the method described in claim 1, it is characterized in that, the congestion information according to N number of period, Predict the first congestion information of the current slot, including：Using default linear model, the congestion information of N number of period is weighted, obtains described first Congestion information.
- 3. according to the method described in claim 2, it is characterized in that, it is described obtain first congestion information after, further include：Calculate the variance between the history congestion information in the current slot and first congestion information；When the variance is not up to minimum, then the weight in the linear model is adjusted, retrieves described first Congestion information, until variance minimum, using corresponding first congestion information during variance minimum as final institute State the first congestion information.
- 4. according to the method described in claim 1, it is characterized in that, described according to the history congestion information, acquisition is described to work as The second congestion information in the preceding period, including：According to the time range belonging to the current slot, inquiry obtains and the matched history congestion of the time range Information；Obtain the current factor for influencing traffic congestion state；Acquisition and the matched adjustment amount of the factor, are adjusted the history congestion information using the adjustment amount, obtain Second congestion information.
- 5. according to the method described in claim 4, it is characterized in that, it is described determine the current slot corresponding to target when Between after scope, further include：For each time range, the congestion information being under the jurisdiction of before the Set cell in the time range is obtained；Statistical analysis is carried out to the congestion information before described, obtains the history congestion information of the time range.
- 6. according to the method described in claim 1, it is characterized in that, described obtain each phase adjacent with the Set cell Adjacent cell within the previous period to the influence value of the Set cell, when obtaining described current according to the influence value Between section the 3rd congestion information, including：For any one border of the Set cell, determine to share the phase on the border with the Set cell Adjacent cell；Wherein, a border corresponds to the adjacent cells lattice；Obtain and enter the of the adjacent cells lattice in the previous period by the border from the Set cell One vehicle number and the first average speed, according to first vehicle number and first average speed, obtain the adjacent cells First sub- influence value of the lattice to the border；Obtain in the previous period and pass through the border from the adjacent cells lattice Into the second vehicle number and the second average speed of the Set cell, it is averaged according to second vehicle number and described second Speed, obtains second sub- influence value of the adjacent cells lattice to the border；Obtain in the previous period and enter institute from the adjacent cells lattice by another border of the adjacent cells lattice The 3rd vehicle number and the 3rd average speed of the adjacent cells lattice of adjacent cells lattice are stated, according to the 3rd vehicle number and described Three average speeds, obtain threeth sub- influence value of the adjacent cells lattice to the border；Wherein, the adjacent cells lattice is another One border is the border parallel with the border of the Set cell；Obtain in the previous period and enter separately from the Set cell by another border of the Set cell The 4th vehicle number and the 4th average speed of one adjacent cells lattice, according to the 4th vehicle number and the 4th average car Speed, obtains fourth sub- influence value of the adjacent cells lattice to the border；Wherein, another border of the Set cell is The border parallel with the border of the Set cell；Another described adjacent cells lattice are shared with the Set cell Another border；According to the described first sub- influence value, the second sub- influence value, the 3rd sub- influence value and the 4th sub- influence value, obtain single The influence value of the adjacent cells lattice；The influence value of each adjacent cells lattice is weighted, obtains the 3rd congestion information.
- 7. according to the method described in claim 6, it is characterized in that, described influence according to the described first sub- influence value, the second son Value, the 3rd sub- influence value and the 4th sub- influence value, obtain the influence value of the single adjacent cells lattice, specific to calculate Formula is as follows：<mrow> <mi>C</mi> <mo>=</mo> <mfrac> <mi>&alpha;</mi> <msup> <mi>e</mi> <mrow> <msub> <mi>F</mi> <mn>4</mn> </msub> <mo>-</mo> <msub> <mi>F</mi> <mn>2</mn> </msub> </mrow> </msup> </mfrac> <mo>&CenterDot;</mo> <msub> <mi>F</mi> <mn>2</mn> </msub> <mo>-</mo> <mfrac> <mi>&beta;</mi> <msup> <mi>e</mi> <mrow> <mi>F</mi> <mn>3</mn> <mo>-</mo> <msub> <mi>F</mi> <mn>1</mn> </msub> </mrow> </msup> </mfrac> <mo>&CenterDot;</mo> <msub> <mi>F</mi> <mn>1</mn> </msub> <mo>+</mo> <mi>&eta;</mi> <mo>;</mo> </mrow>Wherein, the C represents the influence value, the F1~F4Represent respectively the described first sub- influence value, the second sub- influence value, 3rd sub- influence value and the 4th sub- influence value, the α and β are constant, and the η is adjustment amount.
- 8. according to the method described in claim 1, it is characterized in that, the inquiry from the city obtains and the target list The similar similar units lattice of first lattice, including：From the remaining cell in addition to the Set cell in the city, identify has with the Set cell The cell of similar congestion status conversion trend is as candidate unit lattice；The similarity between the Set cell and each candidate unit lattice is calculated, according to the similarity from all candidates The similar units lattice are extracted in cell.
- 9. according to the method described in claim 8, it is characterized in that, described calculate the Set cell and each candidate unit Similarity between lattice, including：Using the congestion information of N number of period of the Set cell, and the N of each candidate unit lattice The congestion information of a period, forms a matrix；Calculate the average value of each element value in the matrix；According to the average value and the matrix, the similarity between the Set cell and each candidate unit lattice is calculated.
- A kind of 10. traffic condition predicting device, it is characterised in that including：Time congestion prediction module, for for any one Set cell in city, it is current to obtain the Set cell The congestion information of N number of period before period, according to the congestion information of N number of period, is predicted described current The first congestion information of period；Wherein, N is integer and N >=1；Steric congestion prediction module, for determining the object time scope corresponding to the current slot, obtains the target History congestion information of the cell in the range of the object time, and according to the history congestion information, obtain described work as The second congestion information in the preceding period；Local correlations prediction module, for obtaining each adjacent cells lattice adjacent with the Set cell when previous Between in section to the influence value of the Set cell, the 3rd congestion that the current slot is obtained according to the influence value is believed Breath；Holistic correlation prediction module, the similar units similar to the Set cell for the inquiry acquisition from the city Lattice, the 4th congestion information in the current slot is obtained using the similar units lattice；Acquisition module, for being believed according to first congestion information, the second congestion information, the 3rd congestion information and the 4th congestion Breath, obtains the target congestion information of the Set cell；Wherein, the target congestion information is used to characterize the object element Congestion status of the lattice in the current slot.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396601.9A CN108022425B (en) | 2017-12-21 | 2017-12-21 | Traffic condition prediction method and device and computer equipment |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201711396601.9A CN108022425B (en) | 2017-12-21 | 2017-12-21 | Traffic condition prediction method and device and computer equipment |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108022425A true CN108022425A (en) | 2018-05-11 |
| CN108022425B CN108022425B (en) | 2020-05-05 |
Family
ID=62074463
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201711396601.9A Active CN108022425B (en) | 2017-12-21 | 2017-12-21 | Traffic condition prediction method and device and computer equipment |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108022425B (en) |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875667A (en) * | 2018-06-27 | 2018-11-23 | 北京字节跳动网络技术有限公司 | target identification method, device, terminal device and storage medium |
| CN110738373A (en) * | 2019-10-15 | 2020-01-31 | 中国城市规划设计研究院 | land traffic generation and distribution prediction method and system |
| CN111341099A (en) * | 2020-02-27 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111341098A (en) * | 2020-02-18 | 2020-06-26 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN112071061A (en) * | 2020-09-11 | 2020-12-11 | 谢能丹 | Vehicle service system based on cloud computing and data analysis |
| CN112927508A (en) * | 2021-02-05 | 2021-06-08 | 北京交通大学 | Traffic accident space-time influence range estimation method considering multiple congestion levels |
| CN113570867A (en) * | 2021-09-26 | 2021-10-29 | 西南交通大学 | Urban traffic state prediction method, device, equipment and readable storage medium |
| CN113643535A (en) * | 2021-08-02 | 2021-11-12 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102636177A (en) * | 2012-04-01 | 2012-08-15 | 北京百度网讯科技有限公司 | Navigation path programming method and device as well as navigation system |
| CN103134495A (en) * | 2012-12-25 | 2013-06-05 | 上海博泰悦臻电子设备制造有限公司 | Generating method of navigation information, navigation device and vehicle-mounted terminal |
| KR20150072471A (en) * | 2013-12-19 | 2015-06-30 | 건국대학교 산학협력단 | Traffic flow prediction system using spatiotemporal stochastic model |
| CN106652441A (en) * | 2015-11-02 | 2017-05-10 | 杭州师范大学 | Urban road traffic condition prediction method based on spatial-temporal data |
| CN106971547A (en) * | 2017-05-18 | 2017-07-21 | 福州大学 | A kind of Short-time Traffic Flow Forecasting Methods for considering temporal correlation |
| CN106991510A (en) * | 2017-05-31 | 2017-07-28 | 福建江夏学院 | A kind of method based on the traffic accident of spatial-temporal distribution characteristic predicted city |
| CN107045788A (en) * | 2017-06-28 | 2017-08-15 | 北京数行健科技有限公司 | Traffic Forecasting Methodology and device |
-
2017
- 2017-12-21 CN CN201711396601.9A patent/CN108022425B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102636177A (en) * | 2012-04-01 | 2012-08-15 | 北京百度网讯科技有限公司 | Navigation path programming method and device as well as navigation system |
| CN103134495A (en) * | 2012-12-25 | 2013-06-05 | 上海博泰悦臻电子设备制造有限公司 | Generating method of navigation information, navigation device and vehicle-mounted terminal |
| KR20150072471A (en) * | 2013-12-19 | 2015-06-30 | 건국대학교 산학협력단 | Traffic flow prediction system using spatiotemporal stochastic model |
| CN106652441A (en) * | 2015-11-02 | 2017-05-10 | 杭州师范大学 | Urban road traffic condition prediction method based on spatial-temporal data |
| CN106971547A (en) * | 2017-05-18 | 2017-07-21 | 福州大学 | A kind of Short-time Traffic Flow Forecasting Methods for considering temporal correlation |
| CN106991510A (en) * | 2017-05-31 | 2017-07-28 | 福建江夏学院 | A kind of method based on the traffic accident of spatial-temporal distribution characteristic predicted city |
| CN107045788A (en) * | 2017-06-28 | 2017-08-15 | 北京数行健科技有限公司 | Traffic Forecasting Methodology and device |
Non-Patent Citations (5)
| Title |
|---|
| 丁闪闪: "基于时空关联和BP_Adaboost的短时交通参数预测", 《公路交通科技》 * |
| 夏英: "智能交通系统中的时空数据分析关键技术研究", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 张婧: "城市道路交通拥堵判别、疏导与仿真", 《中国博士学位论文全文数据库工程科技Ⅱ辑》 * |
| 邱世崇: "基于时空特性的城市道路短时交通流预测研究", 《中国优秀硕士学位论文全文数据库工程科技Ⅱ辑》 * |
| 隋亚刚: "《城市道路交通流预测预报系统研究与应用》", 31 December 2009, 中国铁道出版社 * |
Cited By (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108875667B (en) * | 2018-06-27 | 2021-03-02 | 北京字节跳动网络技术有限公司 | Target identification method and device, terminal equipment and storage medium |
| CN108875667A (en) * | 2018-06-27 | 2018-11-23 | 北京字节跳动网络技术有限公司 | target identification method, device, terminal device and storage medium |
| CN110738373A (en) * | 2019-10-15 | 2020-01-31 | 中国城市规划设计研究院 | land traffic generation and distribution prediction method and system |
| CN111341098A (en) * | 2020-02-18 | 2020-06-26 | 北京中旖新能源有限公司 | Congestion state prediction method and device |
| CN111341099B (en) * | 2020-02-27 | 2022-05-10 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN111341099A (en) * | 2020-02-27 | 2020-06-26 | 阿里巴巴集团控股有限公司 | Data processing method and device and electronic equipment |
| CN112071061A (en) * | 2020-09-11 | 2020-12-11 | 谢能丹 | Vehicle service system based on cloud computing and data analysis |
| CN112071061B (en) * | 2020-09-11 | 2021-10-15 | 武汉云上融媒科技有限公司 | Vehicle service system based on cloud computing and data analysis |
| CN112927508A (en) * | 2021-02-05 | 2021-06-08 | 北京交通大学 | Traffic accident space-time influence range estimation method considering multiple congestion levels |
| CN113643535A (en) * | 2021-08-02 | 2021-11-12 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
| CN113643535B (en) * | 2021-08-02 | 2023-02-21 | 宝方云科技(浙江)有限公司 | Road traffic prediction method, device, equipment and medium based on smart city |
| CN113570867B (en) * | 2021-09-26 | 2021-12-07 | 西南交通大学 | Urban traffic state prediction method, device, equipment and readable storage medium |
| CN113570867A (en) * | 2021-09-26 | 2021-10-29 | 西南交通大学 | Urban traffic state prediction method, device, equipment and readable storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108022425B (en) | 2020-05-05 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108022425A (en) | Traffic movement prediction method, device and computer equipment | |
| CN108985475B (en) | Network taxi appointment and taxi calling demand prediction method based on deep neural network | |
| CN105185115B (en) | A kind of traffic forecast method and forecasting system | |
| CN110555990B (en) | Effective parking space-time resource prediction method based on LSTM neural network | |
| CN110956807B (en) | Highway flow prediction method based on combination of multi-source data and sliding window | |
| CN104021672B (en) | A kind of method and apparatus obtaining traffic congestion index | |
| CN113313303A (en) | Urban area road network traffic flow prediction method and system based on hybrid deep learning model | |
| CN108776852A (en) | Without stake vehicle dispatching method and system | |
| CN107919014B (en) | Taxi running route optimization method for multiple passenger mileage | |
| CN109559512A (en) | A kind of regional traffic flow prediction technique and device | |
| CN110390349A (en) | Bus passenger flow volume based on XGBoost model predicts modeling method | |
| CN103956050A (en) | Road network running evaluation method based on vehicle travel data | |
| CN110288205B (en) | Traffic influence evaluation method and device | |
| Schneider et al. | Development and application of volume model for pedestrian intersections in San Francisco, California | |
| CN110264706A (en) | A kind of unloaded taxi auxiliary system excavated based on big data | |
| CN113177657A (en) | Rail transit passenger flow prediction method and device | |
| CN114328675A (en) | Bus travel time prediction method based on double-attention machine system and bidirectional double-layer LSTM | |
| CN116798218A (en) | Urban low-carbon traffic big data detection method based on digital twinning | |
| CN106295868A (en) | Traffic trip data processing method and device | |
| CN110490365B (en) | Method for predicting network car booking order quantity based on multi-source data fusion | |
| CN111862583B (en) | Traffic flow prediction method and device | |
| CN111985731B (en) | Method and system for predicting number of people at urban public transport station | |
| CN116451867A (en) | Subway short-time passenger flow prediction method based on space-time travel path calibration | |
| CN110164133A (en) | Festivals or holidays freeway network traffic efficiency appraisal procedure, electronic equipment, medium | |
| Wang et al. | A deep prediction model of traffic flow considering precipitation impact |
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 |