CN105139656B - A kind of road condition Forecasting Methodology and device - Google Patents
A kind of road condition Forecasting Methodology and device Download PDFInfo
- Publication number
- CN105139656B CN105139656B CN201510629427.2A CN201510629427A CN105139656B CN 105139656 B CN105139656 B CN 105139656B CN 201510629427 A CN201510629427 A CN 201510629427A CN 105139656 B CN105139656 B CN 105139656B
- Authority
- CN
- China
- Prior art keywords
- road
- predicted
- state
- mrow
- msub
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Abstract
The embodiment of the invention discloses a kind of road condition Forecasting Methodology and device.This method includes：Associated road state array is determined according to road to be predicted, the matrix value of the associated road state array is the road that setpoint distance relation is met with the road to be predicted, the state value within the setting historical juncture；Probabilistic relation between the state to be predicted and associated road state array inscribed according to the road to be predicted when to be predicted, calculates the state to be predicted.The present invention implements the technical scheme provided, and by the state to be predicted inscribed according to road to be predicted when to be predicted, the probabilistic relation between the associated road state array of road to be predicted predicts the state of road to be predicted, improves the accuracy rate of road prediction.
Description
Technical field
The embodiment of the present invention belongs to technical field of data processing, is related to a kind of road condition Forecasting Methodology and device.
Background technology
Accurately, timely telecommunication flow information is most important to the successful application of intelligent transportation system.It can help road
User makes more preferable trip decision-making, alleviates traffic congestion, reduces carbon emission, and improve traffic circulation efficiency.Nowadays, traffic
Data become increasingly abundant, and we have come into the traffic big data epoch.Effectively carried out more accurately and timely using traffic big data
Traffic flow forecasting, manager can be helped to make more preferable traffic control scheme, the trip decision-making for the person that is traffic trip is carried
For providing powerful support for.
Existing traffic stream calculation is mainly calculated current load conditions, it is therefore intended that can accurately be reacted
Current road condition.Existing traffic flow forecasting method is mainly carried out using the road conditions such as periodicity of historical time framework repeatability
The prediction of future period road conditions.
Existing traffic flow forecasting method is only simply considered that road conditions are the repetitions of time, it is believed that road conditions have the time cycle
Property, it is difficult Accurate Prediction road conditions in the case of slightly complexity excessively simply, it is impossible to solve the road condition predicting of actual complex well
Problem, i.e. at present for the still no preferable solution of prediction of following road conditions.
The content of the invention
The purpose of the embodiment of the present invention is to propose a kind of road condition Forecasting Methodology and device, to improve road condition prediction
The degree of accuracy.
On the one hand, the embodiments of the invention provide a kind of road condition Forecasting Methodology, including：
Associated road state array is determined according to road to be predicted, the matrix value of the associated road state array is to be treated with described
Predicted link meets the road of setpoint distance relation, the state value within the setting historical juncture, and the associated road state array is：
Sm,n, wherein, the matrix value r of each matrix doti,jFor the road for being i with road distance to be predicted, before current time at j
The state value at quarter；
It is general between the state to be predicted and associated road state array inscribed according to the road to be predicted when to be predicted
Rate relation, calculates the state to be predicted.
On the other hand, the embodiments of the invention provide a kind of road condition prediction meanss, including：
Association status array element, for determining associated road state array, the associated road state according to road to be predicted
The matrix value of battle array is the road that setpoint distance relation is met with the road to be predicted, is setting the state value in the historical juncture,
The associated road state array is：Sm,n, wherein, the matrix value r of each matrix doti,jFor the road for being i with road distance to be predicted
Road, the state value at j moment before current time；
States prediction unit, for the state to be predicted inscribed according to the road to be predicted when to be predicted with associating
Probabilistic relation between line state battle array, calculates the state to be predicted.
Road condition Forecasting Methodology provided in an embodiment of the present invention and device, by treating pre- according to the road to be predicted
Probabilistic relation between the state to be predicted and associated road state array inscribed during survey, calculates the shape to be predicted of road to be predicted
State, because the factor for combining time and space is predicted, therefore improves the degree of accuracy of road condition prediction.
Brief description of the drawings
Fig. 1 a are a kind of schematic flow sheet for road condition Forecasting Methodology that the embodiment of the present invention one is provided；
Fig. 1 b are a kind of road condition prediction that the embodiment of the present invention one is provided；
Fig. 1 c are a kind of road condition prediction that the embodiment of the present invention one is provided；
Fig. 2 is a kind of schematic flow sheet for road condition Forecasting Methodology that the embodiment of the present invention two is provided；
Fig. 3 a are a kind of schematic flow sheet for road condition Forecasting Methodology that the embodiment of the present invention three is provided；
Fig. 3 b are the road schematic diagram that the embodiment of the present invention three is provided；
Fig. 4 is a kind of schematic flow sheet for road condition Forecasting Methodology that the embodiment of the present invention four is provided；
Fig. 5 is a kind of structural representation for road condition prediction meanss that the embodiment of the present invention five is provided.
Embodiment
The present invention is described in further detail with reference to the accompanying drawings and examples.It is understood that this place is retouched
The specific embodiment stated is used only for explaining the present invention, rather than limitation of the invention.It also should be noted that, in order to just
Part related to the present invention rather than entire infrastructure are illustrate only in description, accompanying drawing.
Embodiment one
Fig. 1 a are a kind of schematic flow sheet for road condition Forecasting Methodology that the embodiment of the present invention one is provided.The present embodiment can
The situation of the road condition such as predicting traffic flow or passage time is wanted suitable for user.This method can be by road condition prediction meanss
Perform.Referring to Fig. 1 a, the road condition Forecasting Methodology that the present embodiment is provided specifically includes as follows：
S11, determine associated road state array according to road to be predicted, the matrix value of the associated road state array for institute
The road that road to be predicted meets setpoint distance relation is stated, the state value within the setting historical juncture.
Exemplary, the associated road state array can be：Sm,n, wherein, the matrix value r of each matrix doti,jFor with
Road distance to be predicted is i road, the state value at j moment before current time.M be according to prediction need set with
Maximum distance between road to be predicted, n is that the earliest moment between the moment to be predicted of setting is needed according to prediction, and i is small
In or equal to m, j is less than or equal to n.
In transportation network, road is connected with each other.With reference to Fig. 1 b and Fig. 1 c, the line with arrow represents road and road side
To circle represents the tie point between road, and wherein road is logical concept, and a logical road can include one or more
Physical road.Transportation network meets tie point flow Conservation Relationship, i.e. tie point and does not produce the magnitude of traffic flow, flows into the friendship of tie point
Through-current capacity is equal to the magnitude of traffic flow of outflow tie point, uses finRepresent the inflow flow of tie point, foutRepresent the flowing out stream of tie point
Amount, then following equation is set up：
fin=fout
The traffic flow situation of every road is related to the traffic flow situation of the associated road of the road, in these connections
In road, flow to the road traffic flow, also have from the road flow out the magnitude of traffic flow, wherein, associated road can be with
The road has the road of common connecting point.The present embodiment predicts the road in future using magnitude of traffic flow conservation and road annexation
Line state.
It is 2, two connected by double bounce by the distance between two road for jumping connection with reference to Fig. 1 b and Fig. 1 c
The distance between road is 3, by that analogy, and the distance between road is calculated with hop count.The unit at moment can be setting value, example
Such as 1 minute, 10 minutes.Road like state value can be represented using the centrifugal pump such as congestion, slow, unobstructed, can also use average row
Enter velocity amplitude to represent.
Between S12, the state to be predicted inscribed according to the road to be predicted when to be predicted and associated road state array
Probabilistic relation, calculate the state to be predicted.
State to be predicted and associated road state array exemplary, inscribed according to the road to be predicted when to be predicted
Between probabilistic relation, calculating the state to be predicted can specifically include：
1) desired value of state value to be predicted is calculated according to equation below based on the probabilistic relation, as described to be predicted
State value：
In state value consecutive hours, the desired value of state value to be predicted is obtained by integration according to above-mentioned formula, in state value
Summed when discrete according to discrete point and obtain the desired value of state value to be predicted.
2) according to the probabilistic relation, the state value corresponding to most probable value is chosen according to equation below, it is pre- as treating
Survey state value：
Wherein, P (Rk/Sm,n) it is state R to be predictedkWith associated road state array Sm,nBetween probabilistic relation,To treat
Predicted state value.Each moment road to be predicted and each state array have a probabilistic relation, probability be expressed as curve or from
Scattered data point, transverse axis is the state value of moment road to be predicted, and the longitudinal axis is probable value；Probabilistic relation can pass through historical data
Count to determine.
Exemplary, state value to be predicted can be to be worth traffic flow value to be predicted or passage time to be predicted, i.e. pass through
The traffic flow value of the association status battle array of road to be predicted can predict the traffic flow value of road to be predicted, pass through road to be predicted
Association status battle array passage time value can predict road to be predicted passage time be worth.
The road condition Forecasting Methodology that the present embodiment is provided, by determining associated road state array according to road to be predicted,
And the probabilistic relation between the state to be predicted and associated road state array inscribed according to the road to be predicted when to be predicted,
The state value of road to be predicted is calculated, because probabilistic relation has considered time and two, space dimension, compared to existing
Road Forecasting Methodology only considers that time cycle property improves the degree of accuracy of road condition prediction.
Embodiment two
The present embodiment provides a kind of new road condition Forecasting Methodology on the basis of above-described embodiment.Fig. 2 is this hair
A kind of schematic flow sheet for road condition Forecasting Methodology that bright embodiment two is provided.The road like provided referring to Fig. 2, the present embodiment
State Forecasting Methodology specifically includes as follows：
S21, determine associated road state array according to road to be predicted, the matrix value of the associated road state array for institute
The road that road to be predicted meets setpoint distance relation is stated, the state value within the setting historical juncture.
On space structure, state between road influence relation is different with the change of distance, according to distance by closely and
Remote order, the set expression that one road l of distance distance is less than or equal to m road is Lm,
Lm={ li},distance(l,li)≤m
In time structure, road liThe traffic flow modes at current time are li,0, the friendship before the moment at current time j
Open position is li,j.On time and two, space dimension, distance is less than or equal to apart from threshold values m, and the time is not more than time threshold values
The collection of the traffic flow modes of n road is combined into Sm,n, referred to as traffic flow spatio-temporal state matrix, abbreviation state array,
Sm,n={ li,j},distance(l,li)≤m and j≤n
The associated road matrix S when different with time threshold values n apart from threshold values mm,nIt is different, i.e. a road correspondence to be predicted
At least two associated road matrixes,WithAny one state array at least two state array is represented respectively.
Between S22, the state to be predicted inscribed according to the road to be predicted when to be predicted and associated road state array
Probabilistic relation, determine the state value to be predicted of associated road, and by the state value to be predicted of determination, be used as associated road state
The predicted state value of battle array.
Specifically, the state R to be predicted inscribed according to road to be predicted when to be predictedkWith associated road state array
Between probabilistic relationDetermine associated road state arrayPredicted state value, existed according to road to be predicted
The state R to be predicted inscribed when to be predictedkWith associated road state arrayBetween probabilistic relationIt is determined that
Associated road state arrayPredicted state value, i.e. it is determined that the predicted state value of each associated road state array.
S23, at least two associated road state array according to the road to be predicted, therefrom determine that matrix distance is met and set
The associated road state array of provisioning request.
Exemplary, at least two associated road state array of the road to be predicted can be：With the road to be predicted
Not meeting in the same time for road sets road distance m, at least two associated road state array of setting historical juncture n.
Exemplary, the distance between state array is calculated using equation below：
WithAny one state array at least two state array is represented respectively,
Im,n=(wi,j), i ∈ [0, m], j ∈ [0, n], wi,jRepresent with predicted link apart from the road for i away from current j
The weighing factor of traffic flow modes before moment to future transportation stream mode.
It is exemplary, state value to be predicted be in traffic flow value to be predicted, influence matrix weighted value according to the road of road
Road grade, road direction, road shape, and/or site of road are determined.Following traffic conditions and its own of one road
Flow it is relevant, it is also relevant with the traffic conditions of its related other road, impacted degree to apart from related, distance
Nearer influence is bigger, relatively small apart from remote influence, and the relation on this road space structure also determines that traffic flow is empty
Between on relation, spatial relationship on this flow can be for doing the volume forecasting of road.The magnitude of traffic flow of road not only by
The influence of road and traffic flow spatial relationship, interval time nearer traffic related also to the time change of road network traffic conditions
Relation between stream mode is closer, and the relation between the remote traffic flow modes of interval time is relatively weak.This traffic flow shape
Dependency relation of the state in the time may also be used for doing the volume forecasting of road.
The predicted state value corresponding to associated road state array that S24, acquisition are determined.
Obtain the predicting traffic flow value that matrix distance meets each associated road state array of sets requirement.
S25, the predicted state value according to the associated road state array of determination, determine the shape to be predicted of the road to be predicted
State value.
Specifically, treating for the road to be predicted can be determined using KNN (k-Nearest Neighbor, neighbouring) algorithm
Predicting traffic flow value, the thinking of KNN algorithms is to choose the most traffic flow shape of quantity corresponding to K nearest state array
State, is used as the predicting traffic flow value of road to be predicted.Specifically, will occur in each predicting traffic flow value determined in S24
The most predicting traffic flow amount of number of times as road to be predicted predicting traffic flow amount.
In addition, additionally providing the state value to be predicted that a kind of improved mode determines road to be predicted：It is adjacent have chosen K
State array after, the traffic flow modes value of prediction, the vector that weight coefficient is constituted referred to as shape are calculated in the way of linear weighted function
State composite vector.
In the present embodiment, influence matrix and state composite vector can be obtained using the method for machine learning, here not
Which kind of machine learning method is limitation use.Also, the exponent number m of space correlation and the exponent number n of time correlation can be according to actual need
Selected, exponent number is bigger, and prediction is more accurate, but complexity increase between this degree of accuracy and complexity, it is necessary to be weighed.
The road condition Forecasting Methodology that the present embodiment is provided, passes through the selection matrix from least two associated road state array
Distance meets the associated road state array of sets requirement, and determines the predicted state value of each associated road state array of selection, with
The predicted state value of road to be predicted is determined according to each predicted state value determined afterwards, the accurate of road condition prediction is improved
Degree.
Embodiment three
The present embodiment provides a kind of new road condition Forecasting Methodology on the basis of above-described embodiment, in the present embodiment
In state value to be predicted be passage time to be predicted.Fig. 3 a are a kind of road condition Forecasting Methodology that the embodiment of the present invention three is provided
Schematic flow sheet.Referring to Fig. 3 a, the road condition Forecasting Methodology that the present embodiment is provided specifically includes as follows：
S31, determine associated road state array according to road to be predicted, the matrix value of the associated road state array for institute
The road that road to be predicted meets setpoint distance relation is stated, the passage time value within the setting historical juncture.
S32, the passage time to be predicted inscribed according to the road to be predicted when to be predicted and associated road state array
Between probabilistic relation, calculate passage time to be predicted.
Exemplary, the passage time prediction for target road can include：By the target road according to tie point
It is segmented；The passage time of every section of road of piecewise prediction, next section of road is used as using the terminal of road clearance time the last period
Initial time be predicted, the time point eventually arrived at.Passage time prediction for target road specifically can also
Including：Using the target road as road to be predicted, whole section of prediction is carried out.
Exemplary, before prediction passage time, it can also include：Chosen according to the distance with road starting point and treat pre-
The m of the associated road state array of survey road, n values, wherein, the m nearer apart from starting point, n values are smaller, the m more remote apart from starting point, n
Value is bigger.
Specifically, the estimation of path passage time can have two ways, segmentation estimation and overall estimation.As shown in Figure 3 b,
Top half estimates that the latter half is overall estimation for segmentation.Segmentation method of estimation can be entered to the whole path of target road
Row segmentation, its passage time is estimated to different sections, when making in this way, using initial time as zero, and every section to be estimated
Moment is above all sums for being segmented passage times, and each section of parameter can be selected each.During using overall estimation, to target track
The passage time in the whole path on road carries out overall estimation.Distance of the selection of Spatial dimensionality dependent on prediction time, path is remote
Dimension needed for the transit time at end is bigger than path near-end, and the size of univers parameter is radial to distal end by near-end, specific ginseng
Number selection can be using linear radial or non-linear radial.
The road condition Forecasting Methodology that the present embodiment is provided, by determining associated road state array according to road to be predicted,
And the probabilistic relation between the state to be predicted and associated road state array inscribed according to the road to be predicted when to be predicted,
The passage time value of road to be predicted is calculated, because probabilistic relation has considered time and two, space dimension, compared to existing
Some road Forecasting Methodologies only consider that time cycle property improves the degree of accuracy of road condition prediction.
Example IV
The present embodiment provides a kind of new road condition Forecasting Methodology on the basis of above-described embodiment three.Fig. 4 is this
A kind of schematic flow sheet for road condition Forecasting Methodology that inventive embodiments four are provided.The road provided referring to Fig. 4, the present embodiment
Trend prediction method specifically includes as follows：
S41, determine associated road state array according to road to be predicted, the matrix value of the associated road state array for institute
The road that road to be predicted meets setpoint distance relation is stated, the passage time value within the setting historical juncture.
On space structure, state between road influence relation is different with the change of distance, according to distance by closely and
Remote order, the set expression that one road l of distance distance is less than or equal to m road is Lm,
Lm={ li},distance(l,li)≤m
In time structure, road liThe traffic flow modes at current time are li,0, the friendship before the moment at current time j
Open position is li,j.On time and two, space dimension, distance is less than or equal to apart from threshold values m, and the time is not more than time threshold values
The collection of the traffic flow modes of n road is combined into Sm,n, referred to as traffic flow spatio-temporal state matrix, abbreviation state array,
Sm,n={ li,j},distance(l,li)≤m and j≤n
One at least two associated road matrix of road correspondence to be predicted,WithAt least two shapes are represented respectively
Any one state array in state battle array.
Under certain m and n, the passage time R of the road at road k-th of moment of futurekWith room and time distance
Relation Between Traffic Flow in the range of m and n can be expressed as P (R with probabilityk/Sm,n), referred to as passage time probability.
S42, the passage time to be predicted inscribed according to the road to be predicted when to be predicted and associated road state array
Between probabilistic relation, determine the passage time value to be predicted of associated road, and the passage time to be predicted of determination is worth, as
The prediction passage time value of associated road state array.
It is exemplary, the passage time to be predicted inscribed according to the road to be predicted when to be predicted and associated road shape
Probabilistic relation between state battle array, the calculating passage time to be predicted can specifically include：
1) desired value of passage time value to be predicted is calculated according to equation below based on the probabilistic relation, is treated as described
Predict passage time value：
2) according to the probabilistic relation, the passage time value corresponding to most probable value is chosen according to equation below, as
Passage time value to be predicted：
Wherein, P (Rk/Sm,n) it is state R to be predictedkWith associated road state array Sm,nBetween probabilistic relation,To treat
Predicted state value.
S43, at least two associated road state array according to the road to be predicted, therefrom determine that matrix distance is met and set
The associated road state array of provisioning request.
Exemplary, at least two associated road state array of the road to be predicted can be：With the road to be predicted
Not meeting in the same time for road sets road distance m, at least two associated road state array of setting historical juncture n.
Exemplary, the distance between state array is calculated using equation below：
WithAny one state array at least two state array is represented respectively,
Im,n=(wi,j), i ∈ [0, m], j ∈ [0, n], wi,jRepresent with predicted link apart from the road for i away from current j
The weighing factor of traffic flow modes before moment to future transportation stream mode.
S44, the prediction passage time obtained corresponding to the associated road state array determined are worth.
S45, it is worth according to the prediction passage time of the associated road state array of determination, determine the road to be predicted treats pre-
Survey passage time value.
S46, according to individual drive correction factor obtained passage time to be predicted is modified.
Road arrival time is equal to initial time and adds path passage time, and predicting road clearance time can predict
The arrival time of road.After collection routes passage time is obtained, set passage time can be entered according to personal correction factor
Row amendment, and then obtain individual path passage time or arrival time, to the preparation method of personal correction factor without limiting.
This arrival time method of estimation be based on space-time restriction relation, can be according to different occasions, to complexity
With the different demands of the degree of accuracy, using flexible embodiment：
1) simple application.The model that typical road connects shape, such as linearly connected relational model, fourth can be built
Font link model, cross link model, annular link model waits the link model of other real roads.These models are only
The position of road is stood on, when estimating road clearance time, from the corresponding link model of road.
2) the slightly application of complexity.In addition to road connection shape, by category of roads, the factor such as road direction is taken into account,
Build the space-time restriction model of the composite factors such as connection shape, road type.This embodiment is also independent from the position of road,
When estimating road clearance time, from the corresponding link model of road.
3) what site of road was related implements in full mode.Space-time restriction model is built to every road, road is set up related
Model library, implement towards road personalized model.This embodiment is capable of the details of accurate response diverse location road
Sex differernce, reaches the effect accurately estimated.The arrival time method of estimation that the present embodiment is proposed may apply to navigation, road conditions sense
Know, share-car etc. reaches the various applications of time correlation.
The technical scheme that the present embodiment is provided, estimates the rendezvous value of arrival time, obtains the set in path first
Arrival time is estimated, is then adjusted according to the correction factor of individual, obtains the arrival time estimation of individual.The set in path
Arrival time and individual arrival time are above independent in application.This method has been considered in transportation network, and road is mutual
Connection, the relation of travel situations of the vehicle on road both between personal driving habit, it is also considered that travel situations and road
Relation between the traffic on road, improves the degree of accuracy of road clearance time prediction.
Embodiment five
Fig. 5 is a kind of structural representation of the interworking unit for many system of account that the embodiment of the present invention five is provided.This implementation
Example is applicable to the situation that user wants the road condition such as predicting traffic flow or passage time.Referring to Fig. 5, road condition prediction
The concrete structure of device is as follows：
Association status array element 51, for determining associated road state array, the associated road shape according to road to be predicted
The matrix value of state battle array is the road that setpoint distance relation is met with the road to be predicted, the state within the setting historical juncture
Value；
States prediction unit 52, for the state to be predicted inscribed according to the road to be predicted when to be predicted with associating
Probabilistic relation between road condition battle array, calculates the state to be predicted.
Exemplary, the associated road state array is：
Sm,n, wherein, the matrix value r of each matrix doti,jFor the road for being i with road distance to be predicted, in current time
The state value at j moment before.
It is exemplary, the states prediction unit 52 specifically for：
The desired value of state value to be predicted is calculated according to equation below based on the probabilistic relation, the shape to be predicted is used as
State value：
Or, according to the probabilistic relation, the state value corresponding to most probable value is chosen according to equation below, as treating
Predicted state value：
Wherein, P (Rk/Sm,n) it is state R to be predictedkWith associated road state array Sm,nBetween probabilistic relation,To treat
Predicted state value.
Exemplary, the states prediction unit 52 includes：
Predicted state value subelement, for by the state value to be predicted of determination, being used as the prediction shape of associated road state array
State value；
Association status frame subelement, at least two associated road state array according to the road to be predicted, therefrom
Determine that matrix distance meets the associated road state array of sets requirement；
Association status value subelement, for obtaining the predicted state value corresponding to the associated road state array determined；
Status predication subelement, for the predicted state value of the associated road state array according to determination, it is determined that described treat pre-
Survey the state value to be predicted of road.
Exemplary, at least two associated road state array of the road to be predicted are：
Road distance m, at least two passes of setting historical juncture n are set with not meeting in the same time for the road to be predicted
Join road condition battle array.
Exemplary, the distance between state array is calculated using equation below：
WithAny one state array at least two state array is represented respectively,
Im,n=(wi,j), i ∈ [0, m], j ∈ [0, n], wi,jRepresent with predicted link apart from the road for i away from current j
The weighing factor of traffic flow modes before moment to future transportation stream mode.
Exemplary, weighted value is according to the category of roads of road, road direction, road shape, and/or road in influence matrix
Road position is determined.
Exemplary, state value to be predicted is to be worth traffic flow value to be predicted or passage time to be predicted.
Exemplary, when state value to be predicted is passage time to be predicted, the states prediction unit is for target track
Road passage time prediction specifically for：
The target road is segmented according to tie point；
The passage time of every section of road of piecewise prediction, using the terminal of road clearance time the last period as next section of road
Initial time is predicted, the time point eventually arrived at.
Exemplary, when state value to be predicted is passage time to be predicted, the states prediction unit is for target track
Road passage time prediction specifically for：
Using the target road as road to be predicted, whole section of prediction is carried out.
Exemplary, the device also includes：
Parameter chooses unit, for before prediction passage time, being chosen according to the distance with road starting point to be predicted
The m of the associated road state array of road, n values, wherein, the m nearer apart from starting point, n values are smaller, the m more remote apart from starting point, n values
It is bigger.
Exemplary, correction factor is driven according to individual obtained passage time to be predicted is modified.
Above-mentioned road condition prediction meanss can perform the road condition Forecasting Methodology that any embodiment of the present invention is provided, tool
The standby corresponding functional module of execution method and beneficial effect.Not ins and outs of detailed description in the present embodiment, reference can be made to this
The road condition Forecasting Methodology that invention any embodiment is provided.
Note, above are only presently preferred embodiments of the present invention and institute's application technology principle.It will be appreciated by those skilled in the art that
The invention is not restricted to specific embodiment described here, can carry out for a person skilled in the art it is various it is obvious change,
Readjust and substitute without departing from protection scope of the present invention.Therefore, although the present invention is carried out by above example
It is described in further detail, but the present invention is not limited only to above example, without departing from the inventive concept, also
Other more equivalent embodiments can be included, and the scope of the present invention is determined by scope of the appended claims.
Claims (22)
1. a kind of road condition Forecasting Methodology, it is characterised in that including：
Associated road state array is determined according to road to be predicted, the matrix value of the associated road state array be with it is described to be predicted
Road meets the road of setpoint distance relation, the state value within the setting historical juncture, and the associated road state array is：Sm,n,
Wherein, the matrix value r of each matrix doti,jFor the road for being i with road distance to be predicted, j moment before current time
State value, m is that the maximum distance between road to be predicted of setting is needed according to prediction, and n is to need what is set according to prediction
The earliest moment between the moment to be predicted；
Probability between the state to be predicted and associated road state array inscribed according to the road to be predicted when to be predicted is closed
System, calculates the state to be predicted.
2. according to the method described in claim 1, it is characterised in that is inscribed according to the road to be predicted when to be predicted treats
Probabilistic relation between predicted state and associated road state array, calculates the state to be predicted, including：
The desired value of state value to be predicted is calculated according to equation below based on the probabilistic relation, the state to be predicted is used as
Value：
<mrow>
<mover>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>^</mo>
</mover>
<mo>=</mo>
<mo>&Integral;</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>&CenterDot;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>/</mo>
<msub>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>dR</mi>
<mi>k</mi>
</msub>
<mo>;</mo>
</mrow>
Or, according to the probabilistic relation, the state value corresponding to most probable value is chosen according to equation below, as to be predicted
State value：
<mrow>
<mover>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>^</mo>
</mover>
<mo>=</mo>
<munder>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
</munder>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>/</mo>
<msub>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
</mrow>
Wherein, P (Rk/SM, n) it is state R to be predictedkWith associated road state array Sm,nBetween probabilistic relation,For shape to be predicted
State value.
3. method according to claim 2, it is characterised in that is inscribed according to the road to be predicted when to be predicted treats
Probabilistic relation between predicted state and associated road state array, calculates the state to be predicted, including：
By the state value to be predicted of determination, the predicted state value of associated road state array is used as；
According at least two associated road state array of the road to be predicted, therefrom determine that matrix distance meets sets requirement
Associated road state array；
Obtain the predicted state value corresponding to the associated road state array determined；
According to the predicted state value of the associated road state array of determination, the state value to be predicted of the road to be predicted is determined.
4. method according to claim 3, it is characterised in that at least two associated road states of the road to be predicted
Battle array be：
With the road to be predicted setting road distance m is not met in the same time, set at least two of historical juncture n and associate
Line state battle array.
5. method according to claim 3, it is characterised in that the distance between state array is calculated using equation below：
<mrow>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<msubsup>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<msub>
<mi>I</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>|</mo>
<mo>|</mo>
</mrow>
WithAny one state array at least two state array is represented respectively,
Im,n=(wi,j), i ∈ [0, m], j ∈ [0, n], wi,jRepresent with predicted link apart from the road for i away from the current j moment
Weighing factor of the preceding traffic flow modes to future transportation stream mode.
6. method according to claim 5, it is characterised in that in influence matrix weighted value according to the category of roads of road,
Road direction, road shape, and/or site of road are determined.
7. according to the method described in claim 1, it is characterised in that state value to be predicted is traffic flow value to be predicted or treats pre-
Survey passage time value.
8. method according to claim 7, it is characterised in that right when state value to be predicted is passage time to be predicted
Include in the passage time prediction of target road：
The target road is segmented according to tie point；
The passage time of every section of road of piecewise prediction, the starting of next section of road is used as using the terminal of road clearance time the last period
Time is predicted, the time point eventually arrived at.
9. method according to claim 7, it is characterised in that right when state value to be predicted is passage time to be predicted
Specifically included in the passage time prediction of target road：
Using the target road as road to be predicted, whole section of prediction is carried out.
10. method according to claim 8 or claim 9, it is characterised in that before prediction passage time, in addition to：
Choose the m of the associated road state array of road to be predicted according to the distance with road starting point, n values, wherein, apart from starting point
Nearer m, n value are smaller, and the m more remote apart from starting point, n values are bigger.
11. method according to claim 7, it is characterised in that correction factor is driven according to individual to be predicted to what is obtained
Passage time is modified.
12. a kind of road condition prediction meanss, it is characterised in that including：
Association status array element, for determining associated road state array according to road to be predicted, the associated road state array
Matrix value is the road that setpoint distance relation is met with the road to be predicted, and the state value within the setting historical juncture is described
Associated road state array is：Sm,n, wherein, the matrix value r of each matrix doti,jFor the road for being i with road distance to be predicted,
The state value at j moment before current time, m is that the maximum distance between road to be predicted of setting, n are needed according to prediction
For the earliest moment between the moment to be predicted for needing to set according to prediction；
States prediction unit, for state to be predicted and the associated road shape inscribed according to the road to be predicted when to be predicted
Probabilistic relation between state battle array, calculates the state to be predicted.
13. device according to claim 12, it is characterised in that the states prediction unit specifically for：
The desired value of state value to be predicted is calculated according to equation below based on the probabilistic relation, the state to be predicted is used as
Value：
<mrow>
<mover>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>^</mo>
</mover>
<mo>=</mo>
<mo>&Integral;</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>&CenterDot;</mo>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>/</mo>
<msub>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<msub>
<mi>dR</mi>
<mi>k</mi>
</msub>
<mo>;</mo>
</mrow>
Or, according to the probabilistic relation, the state value corresponding to most probable value is chosen according to equation below, as to be predicted
State value：
<mrow>
<mover>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>^</mo>
</mover>
<mo>=</mo>
<munder>
<mrow>
<mi>m</mi>
<mi>a</mi>
<mi>x</mi>
</mrow>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
</munder>
<mi>P</mi>
<mrow>
<mo>(</mo>
<msub>
<mi>R</mi>
<mi>k</mi>
</msub>
<mo>/</mo>
<msub>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>)</mo>
</mrow>
<mo>,</mo>
</mrow>
Wherein, P (Rk/Sm,n) it is state R to be predictedkWith associated road state array Sm,nBetween probabilistic relation,To be to be predicted
State value.
14. device according to claim 13, it is characterised in that the states prediction unit includes：
Predicted state value subelement, for by the state value to be predicted of determination, being used as the predicted state value of associated road state array；
Association status frame subelement, at least two associated road state array according to the road to be predicted, is therefrom determined
Matrix distance meets the associated road state array of sets requirement；
Association status value subelement, for obtaining the predicted state value corresponding to the associated road state array determined；
Status predication subelement, for the predicted state value of the associated road state array according to determination, determines the road to be predicted
The state value to be predicted on road.
15. device according to claim 14, it is characterised in that at least two associated road shapes of the road to be predicted
State battle array be：
With the road to be predicted setting road distance m is not met in the same time, set at least two of historical juncture n and associate
Line state battle array.
16. device according to claim 14, it is characterised in that the distance between state array is calculated using equation below：
<mrow>
<mo>|</mo>
<mo>|</mo>
<mrow>
<mo>(</mo>
<msubsup>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mn>1</mn>
</msubsup>
<mo>-</mo>
<msubsup>
<mi>S</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
<mn>2</mn>
</msubsup>
<mo>)</mo>
</mrow>
<mo>&CenterDot;</mo>
<msub>
<mi>I</mi>
<mrow>
<mi>m</mi>
<mo>,</mo>
<mi>n</mi>
</mrow>
</msub>
<mo>|</mo>
<mo>|</mo>
</mrow>
WithAny one state array at least two state array is represented respectively,
Im,n=(wi,j), i ∈ [0, m], j ∈ [0, n], wi,jRepresent with predicted link apart from the road for i away from the current j moment
Weighing factor of the preceding traffic flow modes to future transportation stream mode.
17. device according to claim 16, it is characterised in that weighted value is according to road of road etc. in influence matrix
Level, road direction, road shape, and/or site of road are determined.
18. device according to claim 12, it is characterised in that state value to be predicted is traffic flow value to be predicted or treated
Predict passage time value.
19. device according to claim 18, it is characterised in that when state value to be predicted is passage time to be predicted,
The states prediction unit for target road passage time prediction specifically for：
The target road is segmented according to tie point；
The passage time of every section of road of piecewise prediction, the starting of next section of road is used as using the terminal of road clearance time the last period
Time is predicted, the time point eventually arrived at.
20. device according to claim 18, it is characterised in that when state value to be predicted is passage time to be predicted,
The states prediction unit for target road passage time prediction specifically for：
Using the target road as road to be predicted, whole section of prediction is carried out.
21. the device according to claim 19 or 20, it is characterised in that also include：
Parameter chooses unit, for before prediction passage time, road to be predicted to be chosen according to the distance with road starting point
Associated road state array m, n values, wherein, the m nearer apart from starting point, n values are smaller, and the m more remote apart from starting point, n values are bigger.
22. device according to claim 18, it is characterised in that correction factor is driven according to individual to be predicted to what is obtained
Passage time is modified.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629427.2A CN105139656B (en) | 2015-09-28 | 2015-09-28 | A kind of road condition Forecasting Methodology and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201510629427.2A CN105139656B (en) | 2015-09-28 | 2015-09-28 | A kind of road condition Forecasting Methodology and device |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN105139656A CN105139656A (en) | 2015-12-09 |
| CN105139656B true CN105139656B (en) | 2017-09-29 |
Family
ID=54724983
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201510629427.2A Active CN105139656B (en) | 2015-09-28 | 2015-09-28 | A kind of road condition Forecasting Methodology and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN105139656B (en) |
Families Citing this family (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548625B (en) * | 2016-12-07 | 2019-02-26 | 山东易构软件技术股份有限公司 | A kind of urban highway traffic situation combination forecasting method |
| CN108986453A (en) * | 2018-06-15 | 2018-12-11 | 华南师范大学 | A kind of traffic movement prediction method based on contextual information, system and device |
| CN109300309A (en) * | 2018-10-29 | 2019-02-01 | 讯飞智元信息科技有限公司 | Road condition predicting method and device |
| CN109448381A (en) * | 2018-12-19 | 2019-03-08 | 安徽江淮汽车集团股份有限公司 | A kind of traffic prediction technique based on car networking big data |
| KR102457803B1 (en) | 2019-03-28 | 2022-10-20 | 베이징 바이두 넷컴 사이언스 앤 테크놀로지 코., 엘티디. | Road condition prediction method, device, device and computer storage medium |
| CN110751828B (en) * | 2019-09-10 | 2020-10-20 | 平安国际智慧城市科技股份有限公司 | Road congestion measuring method and device, computer equipment and storage medium |
| CN111091231B (en) * | 2019-11-25 | 2022-04-15 | 珠海格力电器股份有限公司 | Prediction model training method, time prediction method, training device and terminal |
| CN111653088B (en) * | 2020-04-21 | 2022-02-01 | 长安大学 | Vehicle driving quantity prediction model construction method, prediction method and system |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1069405A2 (en) * | 1999-07-14 | 2001-01-17 | Kabushiki Kaisha Equos Research | Navigation method and system |
| DE10057796A1 (en) * | 2000-11-22 | 2002-05-23 | Daimler Chrysler Ag | Vehicle-specific dynamic traffic forecasting method by finding best-match load curve from historical load curves |
| CN101123038A (en) * | 2007-07-11 | 2008-02-13 | 山东省计算中心 | A dynamic information collection method for associated road segments of intersection |
| CN102110365A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Road condition prediction method and road condition prediction system based on space-time relationship |
| CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
| CN104408915A (en) * | 2014-11-05 | 2015-03-11 | 青岛海信网络科技股份有限公司 | Traffic state parameter estimation method and system |
| CN104809879A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway road traffic state estimation method based on dynamic Bayesian network |
| CN104933858A (en) * | 2015-05-14 | 2015-09-23 | 浙江工业大学 | Space traffic characteristic Kernel-KNN matching road traffic state obtain method |
-
2015
- 2015-09-28 CN CN201510629427.2A patent/CN105139656B/en active Active
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| EP1069405A2 (en) * | 1999-07-14 | 2001-01-17 | Kabushiki Kaisha Equos Research | Navigation method and system |
| DE10057796A1 (en) * | 2000-11-22 | 2002-05-23 | Daimler Chrysler Ag | Vehicle-specific dynamic traffic forecasting method by finding best-match load curve from historical load curves |
| CN101123038A (en) * | 2007-07-11 | 2008-02-13 | 山东省计算中心 | A dynamic information collection method for associated road segments of intersection |
| CN102110365A (en) * | 2009-12-28 | 2011-06-29 | 日电（中国）有限公司 | Road condition prediction method and road condition prediction system based on space-time relationship |
| CN104157139A (en) * | 2014-08-05 | 2014-11-19 | 中山大学 | Prediction method and visualization method of traffic jam |
| CN104408915A (en) * | 2014-11-05 | 2015-03-11 | 青岛海信网络科技股份有限公司 | Traffic state parameter estimation method and system |
| CN104809879A (en) * | 2015-05-14 | 2015-07-29 | 重庆大学 | Expressway road traffic state estimation method based on dynamic Bayesian network |
| CN104933858A (en) * | 2015-05-14 | 2015-09-23 | 浙江工业大学 | Space traffic characteristic Kernel-KNN matching road traffic state obtain method |
Also Published As
| Publication number | Publication date |
|---|---|
| CN105139656A (en) | 2015-12-09 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105139656B (en) | A kind of road condition Forecasting Methodology and device | |
| Zhao et al. | A novel generation-adversarial-network-based vehicle trajectory prediction method for intelligent vehicular networks | |
| CN102868972B (en) | Based on the Internet of Things faulty sensors node positioning method improving Q learning algorithm | |
| Jin et al. | A group-based traffic signal control with adaptive learning ability | |
| CN103903430B (en) | Dynamic fusion type travel time predicting method with multi-source and isomorphic data adopted | |
| Sedki et al. | Hybrid particle swarm optimization and differential evolution for optimal design of water distribution systems | |
| Babazadeh et al. | Application of particle swarm optimization to transportation network design problem | |
| Yao et al. | Parallel hyper-heuristic algorithm for multi-objective route planning in a smart city | |
| CN107967803A (en) | Traffic congestion Forecasting Methodology based on multi-source data and variable-weight combined forecasting model | |
| CN102521989B (en) | Dynamic-data-driven highway-exit flow-quantity predicting method | |
| CN102207928B (en) | Reinforcement learning-based multi-Agent sewage treatment decision support system | |
| CN110415516A (en) | Urban traffic flow prediction technique and medium based on figure convolutional neural networks | |
| CN104020665A (en) | Minimum saltus trajectory optimization method of mechanical arm based on multi-objective particle swarm optimization algorithm | |
| Zhao et al. | Dynamic path planning of emergency vehicles based on travel time prediction | |
| CN103968841A (en) | Improved fireflyalgorithm based AUV (autonomous underwater vehicle) three-dimensional track planning method | |
| CN101866143A (en) | Road traffic service level prediction method based on space-time characteristic aggregation | |
| Li et al. | Backpressure control with estimated queue lengths for urban network traffic | |
| CN105246097A (en) | Lifetime optimization method of mobile Sink-based wireless sensor network | |
| Tanyimboh et al. | Multiobjective evolutionary optimization of water distribution systems: Exploiting diversity with infeasible solutions | |
| CN104537446A (en) | Bilevel vehicle routing optimization method with fuzzy random time window | |
| Marsetič et al. | Road artery traffic light optimization with use of the reinforcement learning | |
| JPH07129882A (en) | Road traffic signal control optimizing device and road traffic control system using the same | |
| TWI623920B (en) | Speed prediction method | |
| CN113516277A (en) | Network connection intelligent traffic path planning method based on dynamic pricing of road network | |
| CN108364491A (en) | Driver information based reminding method based on vehicle flowrate prediction |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| C06 | Publication | ||
| PB01 | Publication | ||
| C10 | Entry into substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |