CN104766475A - Urban traffic bottleneck mining method - Google Patents

Abstract

An urban traffic bottleneck mining method includes the following steps that firstly, microwave data and floating car data are cleaned, wherein data interpolation is carried out to solve the data missing problem of the microwave data and the floating car data; secondly, road segment traffic states are estimated by taking set time quanta as time granularity; thirdly, the total occurrence probability of traffic congestion of each road segment in the set time quanta within a statistical cycle is calculated; fourthly, the balance degree of traffic congestion occurring at each day within the statistical cycle is calculated; fifthly, the upper bound of the balance degrees of traffic congestion within the statistical cycle is worked out; sixthly, the normalization balance degree of traffic congestion within the statistical cycle is worked out; seventhly, the severity of traffic bottlenecks is figured out. The urban traffic bottleneck mining method has good reliability.

Description

A kind of urban transportation bottleneck method for digging

Technical field

Patent of the present invention belongs to intelligent transportation field, is specifically related to a kind of traffic bottlenecks method for digging of Corpus--based Method.

Background technology

Along with the increase continuously and healthily of city vehicle, urban traffic blocking constantly aggravates, and its main cause is the speedup of speedup much larger than road construction of vehicle, result in the situation that supply falls short of demand.Urban traffic blocking causes the Trip Costs of the public to increase, and causes exhaust emissions too much due to trip delay, and be degrading living environment further, consequence is serious.In order to relax urban traffic blocking and optimize limited path resource configuration, then the value that the data analyzed and utilize traffic sensor to collect contain carry out effective traffic organization is important means, is the Main Basis that vehicle supervision department formulates rational traffic management measure.

Traffic police road surface is on duty is one not only tradition but also effective traffic organization method with commander, is the important means alleviating traffic congestion.But, which section should be paid close attention on earth, but lack the calculating means of quantification.Traffic bottlenecks section is often there is in urban road network, these bottleneck roads in certain hour section current demand much larger than the handling capacity in section, show as blocking up of the normal property sent out, find and locate the fixed point duties prediction scheme that these sections can facilitate the formulation of traffic police personnel to optimize.

The method of traditional location traffic bottlenecks is by experience, with impression.This method is comparatively original, has following shortcoming: the discovery for traffic bottlenecks is comprehensive not; Be not easy Timeliness coverage and increase bottleneck newly; Be not easy to find the bottleneck sequence under combination condition, such as traffic police personnel wish to know in advance which section belongs to traffic bottlenecks under little rainy day, evening peak, festivals or holidays three combination conditions.Therefore, the order of severity that quantification expresses traffic bottlenecks has very large necessity, and the formulation for traffic police's duties prediction scheme has important reference value.

The traffic bottlenecks of published in recent years excavate paper as: document " Discovering TrafficBottlenecks in an Urban Network by Spatiotemporal Data Mining onLocation-Based Services " utilizes location-based taxi data etc., propose a kind of three stage space-time traffic bottlenecks mining models, by research space-time cluster and communication mode of blocking up, establish a kind of space-time traffic bottlenecks prediction model of complexity; Document " Urban trafficcongestion propagation and bottleneck identification " proposes a kind of identification based on unit TRANSFER MODEL fine-grained space-time traffic bottlenecks mining model.Patent 201410172412.3 proposes a kind of traffic bottlenecks recognition methods based on Floating Car gps data or enquiry data, identifies traffic bottlenecks by the occurrence frequency that blocks up in section.

Summary of the invention

In order to the deficiency that the reliability overcoming existing urban transportation bottleneck excavation mode is poor, the invention provides the urban transportation bottleneck method for digging that a kind of reliability is good.

The technical solution adopted for the present invention to solve the technical problems is:

A kind of urban transportation bottleneck method for digging, comprises the steps:

Step 1: cleaning microwave and floating car data: the shortage of data problem existed for microwave data and floating car data, carries out data interpolation;

Step 2: with setting-up time section for time granularity estimates road section traffic volume state

The traffic behavior in the section that 2.1 Floating Car cover is estimated

If section L has c automobile to pass by setting-up time section, its instantaneous velocity is respectively v ₁, v ₂... v _c, then the section travel speed V in setting-up time section this section interior _lbe expressed as:

$V_L=\underset{i=1}{\overset{c}{\mathrm{\Σ}}}{v}_i/c$

Then work as V _lduring≤threshold value T, the traffic behavior of section L is estimated as and blocks up;

The traffic behavior in the section that 2.2 Floating Car and microwave radar cover jointly is estimated

If section L there is microwave radar sensor, the section speed measuring the setting-up time section returned is v _m, then the section travel speed V in setting-up time section this section interior _lbe expressed as:

$V_L=(v_m+\underset{i=1}{\overset{c}{\mathrm{\Σ}}}{v}_i/c)/2$

In like manner, V is worked as _lduring≤threshold value T, the traffic behavior of section L is estimated as and blocks up;

The section that 2.3 microwave radars cover

K nearest neighbor sorting technique is adopted to estimate the section that microwave radar covers;

Step 3: the overall probability that in the counting statistics cycle, the setting-up time section traffic congestion in every bar section occurs

If measurement period is N days, be divided into the time slot of setting-up time section every day, make morning peak comprise the time slot of n setting-up time section, if in the morning peak of N days, total m setting-up time section generation traffic congestion, in measurement period, in N days morning peak time periods, setting-up time section block up occur probability P _tbe expressed as:

P _t＝m/(N*n)

Step 4: in the counting statistics cycle, traffic congestion is at the equilibrium degree of every day

Make C _ito represent in measurement period in i-th day that setting-up time section is blocked up the number of times occurred, then at i-th day, the accounting that setting-up time section is blocked up in measurement period is: p _i=C _i/ m; Making U express traffic congestion in measurement period, at the equilibrium degree of every day, adopts information entropy to express equilibrium degree:

$U=-\underset{i}{\mathrm{\Σ}}{p}_i\log p_i$

Step 5: the upper bound of traffic congestion equilibrium degree in the counting statistics cycle

If in measurement period N days, the number of times that the setting-up time section jam situation of every day occurs is identical, then the accounting of every day is 1/N, and setting-up time section traffic congestion equilibrium degree is in this case maximum, maximum informational entropy U _maxbe expressed as:

U _max＝logN

Step 6: the normalization equilibrium degree of traffic congestion in the counting statistics cycle

Definition normalization equilibrium degree U _nfor the setting-up time section traffic congestion information entropy of reality is divided by maximum informational entropy, that is:

$U_n=\frac{U}{U_{\max }}=\frac{-\underset{i}{\mathrm{\Σ}}{p}_i\log p_i}{\log N}$

U _nspan (0,1] between;

Step 7: the severity calculating traffic bottlenecks

The severity model of traffic bottlenecks is defined as:

Y _j＝αP _t+(1-α)U _n，

Wherein, Y _jrepresent the bottleneck order of severity in jth bar section, α is a parameter between (0,1).

Further, described method for digging also comprises the steps: step 8: the traffic bottlenecks severity in all sections of descending sort, distributes reference rationally for duties.

Further again, in described step 1, microwave data cleaning way: first the threshold value that the flow collected, speed and occupation rate value and point duty department draw according to historical data is compared, data beyond threshold range are defined as misdata, for the data not meeting Threshold, substitute misdata by threshold value; Obtain misdata according to decision rule, for the data not meeting traffic flow theory, adopt the average method of historical data to revise.

In described step 1, floating car data cleaning way: when the Floating Car speed in a certain section a certain moment is 0, if three moment Floating Car speed before this moment of this section are not all 0, three moment speed averages before we adopt this moment of this section are revised; If the Floating Car speed in three moment before this moment of this section is 0, then the Floating Car speed average of history same period is utilized to revise.

In described step 2.3, the mode based on video playback marks the traffic behavior of a collection of microwave radar sample, and the sample set after mark is called template samples collection, and its form is as follows:

Flow velocity

Flow

Lane occupancy ratio

Whether block up

For a section sample S (V to be sorted _s, F _s, O _s), wherein, V _srepresent the vehicle mean flow rate on the S of section in 5 minutes, F _srepresent its average discharge, O _srepresent its Ratio of driveway occupancy time; First try to achieve the Euclidean distance of S to all template samples, select the minimum K of a distance S section template samples, then choose the traffic behavior of S according to the traffic state information of template samples in a vote.

In the present invention, gather floating car data and microwave radar data, the traffic bottlenecks computation model proposed not only considers the frequency blocking up and occur, and take into account the harmony of probability distribution, contribute to the sporadic traffic bottlenecks filtered because road occupying of repairing the roads, great social activities and other special circumstances cause.

Beneficial effect of the present invention is mainly manifested in: reliability is good.

Accompanying drawing explanation

Fig. 1 is the process flow diagram of urban transportation bottleneck method for digging.

Embodiment

Below in conjunction with accompanying drawing, the invention will be further described.

With reference to Fig. 1, a kind of urban transportation bottleneck method for digging, comprises the steps:

Step 1: cleaning microwave and floating car data

Due to mechanical fault or the communication issue of microwave detection equipment, data there will be error message, so need to clean microwave data before data analysis; For the shortage of data problem that microwave data and floating car data exist, carry out data interpolation.

1.1 microwave data cleanings

First the threshold value that the flow collected, speed and occupation rate value and point duty department draw according to historical data is compared, data beyond threshold range are defined as misdata, below for Hangzhou road traffic flow data, give concrete misdata decision rule example, as shown in table 1.

Table 1

The decision rule drawn according to traffic flow theory is as shown in table 2.

Table 2

After obtaining misdata according to decision rule, need to revise misdata, for the data not meeting Threshold, substitute misdata by threshold value, for the data not meeting traffic flow theory, adopt the average method of historical data to revise.

1.2 floating car data cleanings

When Floating Car speed is 0, we think that Floating Car is slack, cannot reflect the operation conditions of road in this case, and therefore we need the data to Floating Car speed is 0 to clean.Cleaning rule is as follows:

When the Floating Car speed in a certain section a certain moment is 0, if three moment Floating Car speed before this moment of this section are not all 0, three moment speed averages before we adopt this moment of this section are revised; If the Floating Car speed in three moment before this moment of this section is 0, then the Floating Car speed average of the history same period (the history data of month of synchronization) is utilized to revise.

Step 2: with setting-up time section (5 minutes) for time granularity estimates road section traffic volume state

Traffic state estimation method designed by the present invention is carried out based on Floating Car and microwave radar two kinds of data sources, and traffic behavior to be estimated is divided into two classes of blocking up and do not block up, and below divides three kinds of situations to set forth.

2.1 only Floating Car cover section traffic behavior estimate

If section L had c automobile to pass by 5 minutes, its instantaneous velocity is respectively v ₁, v ₂... v _c, then the section travel speed V in this section in 5 minutes _lbe expressed as:

$V_L=\underset{i=1}{\overset{c}{\mathrm{\Σ}}}{v}_i/c$

Then work as V _lduring <=T, the traffic behavior of section L is estimated as and blocks up.For major trunk roads, subsidiary road and branch road, T gets 15km/h; For through street, T gets 25km/h.

The traffic behavior in the section that 2.2 Floating Car and microwave radar cover jointly is estimated

If section L there is microwave radar sensor, measuring the 5 minutes section speed returned is v _m, then the section travel speed V in this section in 5 minutes _lbe expressed as:

$V_L=(v_m+\underset{i=1}{\overset{c}{\mathrm{\&Sigma;}}}{v}_i/c)/2$

In like manner, V is worked as _lduring <=T, the traffic behavior of section L is estimated as and blocks up.For major trunk roads, subsidiary road and branch road, T gets 15km/h; For through street, T gets 25km/h.

2.3 only microwave radar cover section

The present invention adopts k nearest neighbor sorting technique to estimate the section only having microwave radar to cover.First mark the traffic behavior of a collection of microwave radar sample based on the mode of video playback, the sample set after mark is called template samples collection, and its form is as follows:

Flow velocity

Flow

Lane occupancy ratio

Whether block up

For a section sample S (V to be sorted _s, F _s, O _s), wherein, V _srepresent the vehicle mean flow rate on the S of section in 5 minutes, F _srepresent its average discharge, O _srepresent its Ratio of driveway occupancy time.First try to achieve the Euclidean distance (all sample should by dimension normalization) of S to all template samples, select the minimum K of a distance S section template samples, then choose the traffic behavior of S according to the traffic state information of template samples in a vote.

Attention: microwave radar sensor belongs to section sensor, section section speed can not represent section overall speed well, therefore when differentiating traffic behavior, adopts threshold value calculation method to lack rationality.

Step 3: the overall probability that in the counting statistics cycle, 5 minutes traffic congestions in every bar section occur

If measurement period is N days, 288 5 minutes grooves can be divided into every day.Make morning peak be 7:30-9:00 totally 1 hour 30 points, comprise 18 5 minutes grooves altogether.If in the morning peak of N days, total m there is traffic congestion in 5 minutes.So, in measurement period, in N days morning peak time periods, the probability P occurred of blocking up for 5 minutes _tcan be expressed as:

P _t＝m/(N*18)

Step 4: in the counting statistics cycle, traffic congestion is at the equilibrium degree of every day

Make C _irepresent in measurement period the number of times occurred that blocks up in i-th day 5 minutes, then at i-th day, the accounting of blocking up in measurement period for 5 minutes is: p _i=C _i/ m.Traffic congestion is at the equilibrium degree of every day to make U express in measurement period, and the present invention adopts information entropy to express equilibrium degree:

$U=-\underset{i}{\mathrm{\&Sigma;}}{p}_i\log p_i$

Roughly, U value is larger, represents that the possibility that 5 minutes traffic congestion situations are distributed in each sky in measurement period is larger.Also may be interpreted as: a larger U value explanation 5 minutes jam situations are not concentrate the indivedual skies occurred in measurement period, but 5 minutes jam situations appear at a lot of skies in measurement period.In theory, the latter more meets the often key concept that property is blocked up that traffic bottlenecks contain.

Step 5: the upper bound of traffic congestion equilibrium degree in the counting statistics cycle

If in measurement period N days, the number of times that 5 minutes jam situations of every day occur is identical, then the accounting of every day is 1/N.In this case 5 minutes traffic congestion equilibrium degrees are maximum.Can be expressed as:

U _max＝logN

Step 6: the normalization equilibrium degree of traffic congestion in the counting statistics cycle

Definition normalization equilibrium degree U _nfor 5 minutes traffic congestion information entropys of reality are divided by maximum informational entropy, that is:

$U_n=\frac{U}{U_{\max }}=\frac{-\underset{i}{\mathrm{\&Sigma;}}{p}_i\log p_i}{\log N}$

Be not difficult to find, U _nspan (0,1] between.

Step 7: the severity calculating traffic bottlenecks

Build the assessment models of traffic congestion bottleneck, both 5 minutes probability that block up in a section in measurement period should have been considered, these should be avoided again to block up is not concentrate on a few sky, and the latter may cause due to the reason such as road occupying, occasion of repairing the roads, and does not belong to normal and issues the category that blocks up.Therefore, the severity model of traffic bottlenecks is defined as by the present invention:

Y _j＝αP _t+(1-α)U _n，

Wherein, Y _jrepresent the bottleneck order of severity in jth bar section.α is a parameter between (0,1), and its value is the closer to 0, then above-mentioned expression more focuses on the balance of distribution of traffic congestion in measurement period; Its value is the closer to 1, then whether the severity metrics of traffic bottlenecks to get over the emphasis probability that totally blocks up for 5 minutes high.Can find out from here why propose the concept of normalization equilibrium degree, be in order to probability P of totally blocking up 5 minutes _tunified under identical yardstick with normalization equilibrium degree, thus be conducive to building information fusion expression formula Y _j=α P _t+ (1-α) U _n.

Step 8: the traffic bottlenecks severity in all sections of descending sort, distributes reference rationally for duties.

Committed step of the present invention is set forth by two examples, embodiment 1 sets forth the computing method of traffic bottlenecks severity, especially set forth the validity of balance of distribution when portraying traffic bottlenecks severity of blocking up, embodiment 2 sets forth the traffic behavior how utilizing k nearest neighbor classification method to differentiate microwave radar monitoring section.

Embodiment 1: set measurement period as 20 days, the morning peak time period is from 7:30 to 9:00.Section A, due to the occasion impact near in first 5 days, causes the morning peak of the first 5 days duration that blocks up longer, and the duration that blocks up of the morning peak in its 20 days is respectively:

[60,65,65,65,70,5,0,5,0,10,5,0,5,5,10,0,0,0,5,5]，

The time of blocking up in section B each sky in measurement period is respectively:

[20,15,15,20,30,25,15,10,15,20,20,15,15,20,20,15,25,15,20,20]。

Ask section A and section B bottleneck severity separately.

Attention: the section A causing the duration that blocks up longer due to occasion, from concept, should not regard traffic bottlenecks as, does not belong to the normal property sent out and blocks up, do not have generality.On the contrary, the morning peak of section B almost every day all can not block up 10 minutes to 30 minutes not etc., and can regard a normal property of sending out as and block up, in theory, its bottleneck severity should higher than section A.The following bottleneck severity assessing section A and B according to traffic bottlenecks severity computing method proposed by the invention, sees and whether meets expection.

In step 3,5 minutes traffic congestion overall probability in measurement period.

Always the block up duration of section A in measurement period is: 380 minutes, and its probability that totally blocks up for 5 minutes is:

380/(90*20)＝38/180

Always the block up duration of section B in measurement period is: 370, and its probability that totally blocks up for 5 minutes is:

370/(90*20)＝37/180

In step 4, in the counting statistics cycle traffic congestion at the probability distribution equilibrium degree of every day for section A or section B, with the duration that blocks up of every day divided by the available probability distribution of blocking up of the duration that blocks up that A or B is total, consider the numerical problem in follow-up Logarithmic calculation, namely the input of logarithmic function can not be 0, the duration that always blocks up is added a small constant 0.00002, the duration that blocks up of every day is added 0.000001 simultaneously.So obtain the probability distribution p that blocks up of the every day of section A in measurement period _i(1=<i<=20):

[0.157 0.171 0.171 0.171 0.184 0.013 2.63e-09 0.013 2.63e-090.026

0.013 2.63e-09 0.013 0.013 0.026 2.63e-09 2.63e-09 2.63e-090.013 0.013]

And the probability distribution q that blocks up of the every day of section A in measurement period _i(1=<i<=20):

[0.054 0.040 0.040 0.054 0.081 0.067 0.040 0.027 0.0400.054

0.054 0.040 0.040 0.054 0.054 0.040 0.067 0.040 0.054 0.054]

Adopt the logarithmic function being the end with 2, the equilibrium degree that blocks up that can obtain section A is:

$U_A=-\underset{i}{\mathrm{\&Sigma;}}{p}_i\log p_i=3.029$

Adopt the logarithmic function being the end with 2, the equilibrium degree that blocks up that can obtain section A is:

$U_B=-\underset{i}{\mathrm{\&Sigma;}}{q}_i\log q_i=4.2802$

Step 5: the maximum probability distributing equilibrium degree (adopt with 2 be the end logarithmic function) of 5 minutes traffic congestions in the counting statistics cycle:

U _max＝logN＝log(20)＝4.3219

Step 6: the normalization equilibrium degree of 5 minutes traffic congestions in the counting statistics cycle

5 minutes probability distribution normalization equilibrium degrees of section A:

U _n ^A＝3.029/4.3219＝0.7

5 minutes probability distribution normalization equilibrium degrees of section B:

U _n ^B＝4.2802/4.3219＝0.9903

Step 7: the severity calculating traffic bottlenecks:

Make parameter alpha=0.8, represent that bottleneck severity is focused on totally blocking up for 5 minutes the size of probability, but contemplate the harmony of the probability distribution of blocking up of every day.For section A, can obtain its bottleneck severity is:

$Y_A=0.8*{P_t}^A+(1-0.8)U_n^A=0.3091$

For section B, can obtain its bottleneck severity is:

$Y_B=0.8*{P_t}^B+(1-0.8)U_n^B=0.3625$

So far, we see that section B is more likely be evaluated as traffic bottlenecks than section A, meet concept expection, the bottleneck severity of the regular section B blocked up is greater than the bottleneck severity of the sporadic section A blocked up, and illustrates that traffic bottlenecks mining model proposed by the invention is effective.

Embodiment 2: the traffic behavior based on microwave data and k nearest neighbor algorithm is estimated.Be provided with template samples storehouse, trunk section as shown in the table, section speed, flow and lane occupancy ratio wherein in 5 minutes are recorded by microwave remote sensor, and whether section blocks up is marked by video playback and obtains:

Sample sequence number	Speed (km/h)	Flow ()	Lane occupancy ratio (%)	Whether block up
					1	19	10	60	Be
2	22	23	52	Be
					3	40	87	20	No
4	64	92	12	No
					5	15	16	46	Be

Table 3

If the profile data that the upper microwave radar in certain trunk section to be sorted records: speed is 24km/h, and flow is 27, and lane occupancy ratio is 70%, k nearest neighbour method is adopted to estimate the traffic behavior in this section.Make V represent velocity vector, then its normalization mode is:

(x-min (V))/(max (V)-min (V)), wherein, max function and min the function minimum and maximal value respectively in return vector V, x represents and treats normalized velocity amplitude.The normalization mode of flow and lane occupancy ratio is similar.Can obtain normalized speed, flow and lane occupancy ratio is as calculated table 4:

Sample sequence number	Speed	Flow	Lane occupancy ratio
				1	0.08	0	0.83
2	0.14	0.16	0.69
				3	0.51	0.94	0.14
4	1	1	0
				5	0	0.07	0.59
Section to be sorted	0.18	0.21	1

Table 4

Further, section to be sorted can be tried to achieve and be respectively table 5 to the Euclidean distance of 5 samples:

Table 5

If get k=4, then the most similar to section to be sorted template samples is respectively 1,2,4,5, wherein have 3 tickets block up and 1 ticket do not block up, therefore, section to be sorted should be estimated as and block up.

Claims (5)

1. a urban transportation bottleneck method for digging, is characterized in that: described method for digging comprises the steps:

Step 1: cleaning microwave and floating car data: the shortage of data problem existed for microwave data and floating car data, carries out data interpolation;

Step 2: with setting-up time section for time granularity estimates road section traffic volume state

The traffic behavior in the section that 2.1 Floating Car cover is estimated

If section L has c automobile to pass by setting-up time section, its instantaneous velocity is respectively v ₁, v ₂... v _c, then the section travel speed V in setting-up time section this section interior _lbe expressed as:

Then work as V _lduring≤threshold value T, the traffic behavior of section L is estimated as and blocks up;

The traffic behavior in the section that 2.2 Floating Car and microwave radar cover jointly is estimated

If section L there is microwave radar sensor, the section speed measuring the setting-up time section returned is v _m, then the section travel speed V in setting-up time section this section interior _lbe expressed as:

In like manner, V is worked as _lduring≤threshold value T, the traffic behavior of section L is estimated as and blocks up;

The section that 2.3 microwave radars cover

K nearest neighbor sorting technique is adopted to estimate the section that microwave radar covers;

Step 3: the overall probability that in the counting statistics cycle, the setting-up time section traffic congestion in every bar section occurs

If measurement period is N days, be divided into the time slot of setting-up time section every day, morning peak is made to comprise the time slot of n setting-up time section, if in the morning peak of N days, total m setting-up time section generation traffic congestion, in measurement period, in N days morning peak time periods, setting-up time section block up occur probability P _tbe expressed as:

P _t＝m/(N*n)

Step 4: in the counting statistics cycle, traffic congestion is at the equilibrium degree of every day

Make C _ito represent in measurement period in i-th day that setting-up time section is blocked up the number of times occurred, then at i-th day, the accounting that setting-up time section is blocked up in measurement period is: p _i=C _i/ m; Making U express traffic congestion in measurement period, at the equilibrium degree of every day, adopts information entropy to express equilibrium degree:

Step 5: the upper bound of traffic congestion equilibrium degree in the counting statistics cycle

If in measurement period N days, the number of times that the setting-up time section jam situation of every day occurs is identical, then the accounting of every day is 1/N, and setting-up time section traffic congestion equilibrium degree is in this case maximum, maximum informational entropy U _maxbe expressed as:

U _max＝logN

Step 6: the normalization equilibrium degree of traffic congestion in the counting statistics cycle

Definition normalization equilibrium degree U _nfor the setting-up time section traffic congestion information entropy of reality is divided by maximum informational entropy, that is:

U _nspan (0,1] between;

Step 7: the severity calculating traffic bottlenecks

The severity model of traffic bottlenecks is defined as:

Y _j＝αP _t+(1-α)U _n，

Wherein, Y _jrepresent the bottleneck order of severity in jth bar section, α is a parameter between (0,1).

2. a kind of urban transportation bottleneck method for digging as claimed in claim 1, is characterized in that: described method for digging also comprises the steps: step 8: the traffic bottlenecks severity in all sections of descending sort, distributes reference rationally for duties.

3. a kind of urban transportation bottleneck method for digging as claimed in claim 1 or 2, it is characterized in that: in described step 1, microwave data cleaning way: first the threshold value that the flow collected, speed and occupation rate value and point duty department draw according to historical data is compared, data beyond threshold range are defined as misdata, for the data not meeting Threshold, substitute misdata by threshold value; Obtain misdata according to decision rule, for the data not meeting traffic flow theory, adopt the average method of historical data to revise.

4. a kind of urban transportation bottleneck method for digging as claimed in claim 1 or 2, it is characterized in that: in described step 1, floating car data cleaning way: when the Floating Car speed in a certain section a certain moment is 0, if three moment Floating Car speed before this moment of this section are not all 0, three moment speed averages before this moment of this section are adopted to revise; If the Floating Car speed in three moment before this moment of this section is 0, then the Floating Car speed average of history same period is utilized to revise.

5. a kind of urban transportation bottleneck method for digging as claimed in claim 1 or 2, it is characterized in that: in described step 2.3, mode based on video playback marks the traffic behavior of a collection of microwave radar sample, and the sample set after mark is called template samples collection, and its form is as follows:

Flow velocity Flow Lane occupancy ratio Whether block up

For a section sample S (V to be sorted _s, F _s, O _s), wherein, V _srepresent the vehicle mean flow rate on the S of section in 5 minutes, F _srepresent its average discharge, O _srepresent its Ratio of driveway occupancy time; First try to achieve the Euclidean distance of S to all template samples, select the minimum K of a distance S section template samples, then choose the traffic behavior of S according to the traffic state information of template samples in a vote.