CN110517481A - Vehicle flowrate prediction technique, medium, equipment and device - Google Patents
Vehicle flowrate prediction technique, medium, equipment and device Download PDFInfo
- Publication number
- CN110517481A CN110517481A CN201910684640.1A CN201910684640A CN110517481A CN 110517481 A CN110517481 A CN 110517481A CN 201910684640 A CN201910684640 A CN 201910684640A CN 110517481 A CN110517481 A CN 110517481A
- Authority
- CN
- China
- Prior art keywords
- vehicle flowrate
- information
- weather conditions
- initial data
- conditions information
- 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.)
- Withdrawn
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
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
Landscapes
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Traffic Control Systems (AREA)
Abstract
The invention discloses a kind of vehicle flowrate prediction technique, medium, equipment and devices, including obtain vehicle flowrate initial data, wherein vehicle flowrate initial data includes the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；The related coefficient between weather conditions information and information of vehicle flowrate is calculated, and filters out weather conditions information and information of vehicle flowrate that related coefficient is greater than predetermined coefficient threshold value；Training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；The building that forecasting traffic flow model is carried out according to the classifier of training sample data collection, depth confidence network and support vector regression, predicts vehicle flowrate with will pass through forecasting traffic flow model；Accurate Prediction is carried out to vehicle flowrate to realize, improves the property of can refer to of final vehicle flowrate prediction result.
Description
Technical field
The present invention relates to technical field of information processing, in particular to a kind of vehicle flowrate prediction technique, medium, equipment and dress
It sets.
Background technique
Vehicle flowrate prediction, is a kind of method predicted the vehicle flowrate that will be generated, and vehicle flowrate is predicted for the public
The work such as traffic trip, public transport scheduling have very high directive significance.
However, in existing vehicle flowrate prediction mode, it is more that vehicle flowrate is only carried out according to the historical data of traffic flow
Prediction is not bound with the prediction that weather conditions carry out vehicle flowrate, causes final vehicle flowrate prediction result not accurate enough, influence wagon flow
Measure the property of can refer to of prediction result.
Summary of the invention
The present invention is directed to solve one of the technical problem in above-mentioned technology at least to a certain extent.For this purpose, of the invention
One purpose is to propose a kind of vehicle flowrate prediction technique, can be realized and carry out Accurate Prediction to vehicle flowrate, improve final wagon flow
Measure the property of can refer to of prediction result.
Second object of the present invention is to propose a kind of computer readable storage medium.
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 vehicle flowrate prediction meanss.
In order to achieve the above objectives, first aspect present invention embodiment proposes a kind of vehicle flowrate prediction technique, including following
Step: vehicle flowrate initial data is obtained, wherein vehicle flowrate initial data includes weather conditions information and corresponding weather conditions information
Information of vehicle flowrate；The related coefficient between weather conditions information and information of vehicle flowrate is calculated, and filters out related coefficient and is greater than
The weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value；According to the weather conditions information and information of vehicle flowrate structure filtered out
Build training sample data collection；It is handed over according to the classifier of training sample data collection, depth confidence network and support vector regression
The building of through-flow prediction model predicts vehicle flowrate with will pass through forecasting traffic flow model.
Vehicle flowrate prediction technique according to an embodiment of the present invention, firstly, obtaining vehicle flowrate initial data, wherein vehicle flowrate
Initial data includes the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；Then, weather conditions information is calculated
Related coefficient between information of vehicle flowrate, and filter out weather conditions information and vehicle that related coefficient is greater than predetermined coefficient threshold value
Flow information；Then, training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；Then, root
The building of forecasting traffic flow model is carried out according to the classifier of training sample data collection, depth confidence network and support vector regression,
Vehicle flowrate is predicted with will pass through forecasting traffic flow model；Accurate Prediction is carried out to vehicle flowrate to realize, is improved final
The property of can refer to of vehicle flowrate prediction result.
In addition, the vehicle flowrate prediction technique proposed according to that above embodiment of the present invention can also have following additional technology
Feature:
Optionally, the related coefficient between the weather conditions information and the information of vehicle flowrate is counted according to the following formula
It calculates:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw,
yt) indicate related coefficient between weather conditions information and information of vehicle flowrate.
Optionally, it is carried out according to the classifier of the training sample data collection, depth confidence network and support vector regression
The building of forecasting traffic flow model, comprising:
The training of depth confidence network is carried out using the training sample data collection as input, and obtains the depth confidence
First vehicle flowrate predicted value of network output；
The classifier of the support vector regression is trained according to the first vehicle flowrate predicted value；
Forecasting traffic flow is carried out according to the classifier of the depth confidence network after training and the support vector regression after training
The building of model.
Optionally, the vehicle flowrate initial data further includes the temporal information of the corresponding weather conditions information, wherein In
After acquisition vehicle flowrate initial data, further includes:
The vehicle flowrate initial data is divided into working day vehicle flowrate initial data, festivals or holidays according to the temporal information
Vehicle flowrate initial data and weekend vehicle flowrate initial data, so as to false according to the working day vehicle flowrate initial data, the section
Day vehicle flowrate initial data and the weekend vehicle flowrate initial data carry out the building of corresponding traffic flow prediction model, to generate work
Make day forecasting traffic flow model, festivals or holidays forecasting traffic flow model and weekend forecasting traffic flow model.
Optionally, after obtaining vehicle flowrate initial data, also the vehicle flowrate initial data is pre-processed,
In, the pretreated step includes:
According to average algorithm to the weather conditions information and information of vehicle flowrate lacked in the vehicle flowrate initial data into
Row completion, and denoising is carried out to the vehicle flowrate initial data after completion according to low-pass filtering algorithm, and according to normalization
The vehicle flowrate initial data after denoising is normalized in algorithm.
Optionally, when being lacked in the vehicle flowrate initial data there are weather conditions information and information of vehicle flowrate, according to
With the average value of the weather conditions information of missing and the weather conditions information of information of vehicle flowrate adjacent moment and information of vehicle flowrate into
The completion of row missing data, wherein the weather conditions information of the adjacent moment and the average value of information of vehicle flowrate are according to following
Formula calculates:
Wherein, x indicates weather conditions information and information of vehicle flowrate,Indicate the weather conditions information and wagon flow of adjacent moment
The average value of information is measured, t indicates the moment locating for the weather conditions information lacked and information of vehicle flowrate, and n indicates the day of adjacent moment
The quantity of gas condition information and information of vehicle flowrate.
In order to achieve the above objectives, second aspect of the present invention embodiment proposes a kind of computer readable storage medium, thereon
It is stored with vehicle flowrate Prediction program, such as above-mentioned vehicle flowrate prediction side is realized when which is executed by processor
Method.
Computer readable storage medium according to an embodiment of the present invention, by storing vehicle flowrate Prediction program, such wagon flow
Amount Prediction program realizes such as above-mentioned vehicle flowrate prediction technique when being executed by processor；Vehicle flowrate is carried out accurately to realize
Prediction, improves the property of can refer to of final vehicle flowrate prediction result.
In order to achieve the above objectives, third aspect present invention embodiment proposes a kind of computer equipment, including memory, place
The computer program managing device and storage on a memory and can running on a processor, when the processor executes described program,
Realize such as above-mentioned vehicle flowrate prediction technique.
Computer equipment according to an embodiment of the present invention executes above-mentioned vehicle flowrate Prediction program by processor, thus real
Accurate Prediction now is carried out to vehicle flowrate, improves the property of can refer to of final vehicle flowrate prediction result.
In order to achieve the above objectives, fourth aspect of embodiment of the present invention embodiment proposes a kind of vehicle flowrate prediction meanss, packet
It includes: module is obtained, for obtaining vehicle flowrate initial data, wherein vehicle flowrate initial data includes weather conditions information and correspondence
The information of vehicle flowrate of weather conditions information；Computing module, for calculating the correlation between weather conditions information and information of vehicle flowrate
Coefficient, and filter out weather conditions information and information of vehicle flowrate that related coefficient is greater than predetermined coefficient threshold value；Module is constructed, is used for
Training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；Training module, for according to training
The classifier of sample data set, depth confidence network and support vector regression carries out the building of forecasting traffic flow model；Predict mould
Block, for being predicted by forecasting traffic flow model vehicle flowrate.
Vehicle flowrate prediction meanss according to an embodiment of the present invention, setting obtain module and obtain to vehicle flowrate initial data
It takes, wherein vehicle flowrate initial data includes the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；It is getting
After vehicle flowrate initial data, the meter of the related coefficient between weather conditions information and information of vehicle flowrate is carried out by computing module
It calculates, and filters out weather conditions information and information of vehicle flowrate that related coefficient is greater than predetermined coefficient threshold value；To construct module root
Training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；Training module is set according to training sample
The classifier of data set, depth confidence network and support vector regression carries out the building of forecasting traffic flow model；To predict mould
Block predicts vehicle flowrate by the forecasting traffic flow model that training obtains；Accurate Prediction is carried out to vehicle flowrate to realize,
Improve the property of can refer to of final vehicle flowrate prediction result.
In addition, the vehicle flowrate prediction meanss proposed according to that above embodiment of the present invention can also have following additional technology
Feature:
Optionally, the related coefficient between the weather conditions information and the information of vehicle flowrate is counted according to the following formula
It calculates:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw,
yt) indicate related coefficient between weather conditions information and information of vehicle flowrate.
Detailed description of the invention
Fig. 1 is the flow diagram according to the vehicle flowrate prediction technique of the embodiment of the present invention；
Fig. 2 is the structural schematic diagram according to the forecasting traffic flow model of the embodiment of the present invention；
Fig. 3 is the flow diagram according to the vehicle flowrate prediction technique of another embodiment of the present invention；
Fig. 4 is the flow diagram according to the vehicle flowrate prediction technique of further embodiment of this invention；
Fig. 5 is the block diagram according to the vehicle flowrate prediction meanss of the embodiment of the present invention.
Specific embodiment
The embodiment of the present invention is described below in detail, examples of the embodiments are shown in the accompanying drawings, wherein from beginning to end
Same or similar label indicates same or similar element or element with the same or similar functions.Below with reference to attached
The embodiment of figure description is exemplary, it is intended to is used to explain the present invention, and is not considered as limiting the invention.
Existing vehicle flowrate prediction mode prediction gained vehicle flowrate result is not accurate enough, and the property of can refer to is lower, according to this hair
The vehicle flowrate prediction technique that bright embodiment proposes, firstly, obtaining vehicle flowrate initial data, wherein vehicle flowrate initial data includes
The information of vehicle flowrate of weather conditions information and corresponding weather conditions information；Then, weather conditions information and information of vehicle flowrate are calculated
Between related coefficient, and filter out related coefficient be greater than predetermined coefficient threshold value weather conditions information and information of vehicle flowrate；So
Afterwards, training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；Then, according to number of training
The building of forecasting traffic flow model is carried out, according to the classifier of collection, depth confidence network and support vector regression will pass through traffic
Stream prediction model predicts vehicle flowrate；Accurate Prediction is carried out to vehicle flowrate to realize, improves final vehicle flowrate prediction knot
The property of can refer to of fruit.
In order to better understand the above technical scheme, the exemplary reality that the present invention will be described in more detail below with reference to accompanying drawings
Apply example.Although showing exemplary embodiment of the present invention in attached drawing, it being understood, however, that may be realized in various forms this hair
It is bright and should not be limited by the embodiments set forth herein.It is to be able to thoroughly understand this on the contrary, providing these embodiments
Invention, and the scope of the present invention can be fully disclosed to those skilled in the art.
In order to better understand the above technical scheme, in conjunction with appended figures and specific embodiments to upper
Technical solution is stated to be described in detail.
Fig. 1 is the flow diagram of the vehicle flowrate prediction technique proposed according to the embodiment of the present invention, as shown in Figure 1, the vehicle
Method for predicting the following steps are included:
S101 obtains vehicle flowrate initial data.
That is, being obtained to vehicle flowrate initial data, for example, it is corresponding to obtain each time point obtained according to statistics
Vehicle flowrate data.
Wherein, the information that vehicle flowrate initial data may include can there are many, for example, vehicle flowrate initial data can wrap
Include the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；Alternatively, vehicle flowrate initial data includes temporal information
And the corresponding information of vehicle flowrate of temporal information, here, not being defined to the specifying information of vehicle flowrate initial data.
S102 calculates the related coefficient between weather conditions information and information of vehicle flowrate, and filters out related coefficient and be greater than
The weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value.
That is, calculating the related coefficient between weather conditions information and corresponding information of vehicle flowrate, to divide
The degree of correlation between weather conditions information and corresponding information of vehicle flowrate is analysed, and filters out related coefficient greater than predetermined coefficient threshold value
Weather conditions information and information of vehicle flowrate.
Wherein, the calculation of the related coefficient between weather conditions information and information of vehicle flowrate can there are many.
As an example, the related coefficient between weather conditions information and information of vehicle flowrate is counted according to the following formula
It calculates:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw,
yt) indicate related coefficient between weather conditions information and information of vehicle flowrate.
S103 constructs training sample data collection according to the weather conditions information and information of vehicle flowrate filtered out.
That is, after filtering out the higher weather conditions information of the degree of correlation and corresponding information of vehicle flowrate, according to
The data filtered out are trained the building of sample data set, so that the subsequent training sample data collection completed according to building carries out
The training of depth confidence network model.
S104 carries out traffic flow according to the classifier of training sample data collection, depth confidence network and support vector regression
The building of prediction model predicts vehicle flowrate with will pass through forecasting traffic flow model.
That is, after the building of training sample data collection is completed, using support vector regression as depth confidence net
The classifier of network training pattern, and according to the training sample data collection, the classifier of depth confidence network and support vector regression
The training of forecasting traffic flow model is carried out, to pass through forecasting traffic flow model after the completion of forecasting traffic flow model training
Vehicle flowrate is predicted.
As an example, the training of depth confidence network is carried out using training sample data collection as input, and obtains depth
Spend the first vehicle flowrate predicted value of confidence network output；According to the first vehicle flowrate predicted value to the classifier of support vector regression into
Row training；Forecasting traffic flow mould is carried out according to the classifier of the depth confidence network after training and the support vector regression after training
The building of type.
As another example, Fig. 2 is a kind of structural schematic diagram of forecasting traffic flow model of the embodiment of the present invention, is such as schemed
Shown in 2, wherein DBN (depth confidence network) includes three layers of hidden layer and one layer of visible layer, also, the number of iterations of DBN is set
The kernel function being set in 100, SVR (classifier of support vector regression) selects RBF, and the number of iterations is set as 10000, punishment
The factor is set as 0.01, and after the generation of training sample data collection, training sample data collection is input to DBN (depth confidence net
Network) in visible layer, to pass through unsupervised pre-training, net that successively greedy initialization RBM (the limited graceful machine of Bohr thatch) obtains
Then the first vehicle flowrate predicted value that depth confidence network exports, is input to top to complete the training of depth confidence network by network
The SVR (classifier of support vector regression) of layer, to be trained to SVR, finally, the DBN-SVR that training is completed is as friendship
Through-flow prediction model.
In conclusion vehicle flowrate prediction technique according to an embodiment of the present invention, firstly, vehicle flowrate initial data is obtained,
In, vehicle flowrate initial data includes the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；Then, weather is calculated
Related coefficient between condition information and information of vehicle flowrate, and filter out the weather conditions that related coefficient is greater than predetermined coefficient threshold value
Information and information of vehicle flowrate；Then, training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；
Then, forecasting traffic flow model is carried out according to the classifier of training sample data collection, depth confidence network and support vector regression
Building, vehicle flowrate is predicted with will pass through forecasting traffic flow model；Accurate Prediction is carried out to vehicle flowrate to realize, is mentioned
The property of can refer to of high final vehicle flowrate prediction result.
In some embodiments, as shown in figure 3, in order to improve the embodiment of the present invention proposition vehicle flowrate prediction technique for
The forecasting accuracy of vehicle flowrate, and shorten the training time of model, the vehicle flowrate prediction technique that another embodiment of the present invention proposes
The following steps are included:
S201 obtains vehicle flowrate initial data.
S202 believes the weather conditions information and vehicle flowrate lacked in the vehicle flowrate initial data according to average algorithm
Breath carries out completion.
That is, in the vehicle flowrate initial data got, it is understood that there may be part weather conditions information and vehicle flowrate letter
The missing of breath, that is, the data got are incomplete, at this point, carrying out the benefit of data to the part of missing according to average algorithm
Entirely, to improve data integrity.
As an example, when being lacked in vehicle flowrate initial data there are weather conditions information and information of vehicle flowrate, root
According to the weather conditions information of weather conditions information and information of vehicle flowrate adjacent moment with missing and the average value of information of vehicle flowrate
Carry out the completion of missing data, wherein the weather conditions information of adjacent moment and the average value of information of vehicle flowrate are according to following public affairs
Formula calculates:
Wherein, x indicates weather conditions information and information of vehicle flowrate,Indicate the weather conditions information and wagon flow of adjacent moment
The average value of information is measured, t indicates the moment locating for the weather conditions information lacked and information of vehicle flowrate, and n indicates the day of adjacent moment
The quantity of gas condition information and information of vehicle flowrate.
S203 carries out denoising to the vehicle flowrate initial data after completion according to low-pass filtering algorithm.
In other words, the exceptional value in the vehicle flowrate initial data after completion is carried out at denoising using the method for low-pass filtering
Reason.
S204 is normalized the vehicle flowrate initial data after denoising according to normalization algorithm.
That is, the vehicle flowrate initial data after denoising is normalized according to normalization algorithm, with
It improves the accuracy of prediction result and shortens the training time of model.
As an example, the vehicle flowrate initial data after denoising is normalized, by all data
It normalizes between [0,1], also, the normalization of data is calculated according to the following formula:
Wherein, x indicates vehicle flowrate initial data, and y indicates the data after normalization, xminIt indicates in vehicle flowrate initial data
Minimum value, xmaxIndicate the maximum value in vehicle flowrate initial data.
To the vehicle flowrate initial data after denoising be normalized by above-mentioned formula, to improve final vehicle
The accuracy of volume forecasting result, meanwhile, shorten the training time of subsequent forecasting traffic flow model.
S205 calculates the related coefficient between weather conditions information and information of vehicle flowrate, and filters out related coefficient and be greater than
The weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value.
S206 constructs training sample data collection according to the weather conditions information and information of vehicle flowrate filtered out.
S207 carries out traffic flow according to the classifier of training sample data collection, depth confidence network and support vector regression
The building of prediction model predicts vehicle flowrate with will pass through forecasting traffic flow model.
It is consistent about the correlation step description in vehicle flowrate prediction technique in above-mentioned steps S205-S207 and Fig. 1, herein not
It repeats.
In conclusion vehicle flowrate prediction technique according to an embodiment of the present invention, firstly, obtaining vehicle flowrate initial data；It connects
, the weather conditions information and information of vehicle flowrate that lack in the vehicle flowrate initial data are mended according to average algorithm
Entirely；Then, denoising is carried out to the vehicle flowrate initial data after completion according to low-pass filtering algorithm；Then, according to normalization
The vehicle flowrate initial data after denoising is normalized in algorithm；Then, weather conditions information and vehicle flowrate are calculated
Related coefficient between information, and filter out weather conditions information and vehicle flowrate letter of the related coefficient greater than predetermined coefficient threshold value
Breath；Then, training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；Then, according to training
The classifier of sample data set, depth confidence network and support vector regression carries out the building of forecasting traffic flow model, to lead to
Forecasting traffic flow model is crossed to predict vehicle flowrate；Thus, it is possible to while realization to vehicle flowrate progress Accurate Prediction, into one
Step improves the accuracy of final vehicle flowrate prediction, also, saves the training time of forecasting traffic flow model.
In some embodiments, related between finally formed forecasting traffic flow model and date type in order to establish
Property, with further increase vehicle flowrate prediction accuracy, as shown in figure 4, the vehicle flowrate prediction technique the following steps are included:
S301 obtains vehicle flowrate initial data.
Wherein, vehicle flowrate initial data may include weather conditions information and corresponding weather conditions information temporal information and
Information of vehicle flowrate.
Vehicle flowrate initial data is divided into working day vehicle flowrate initial data, festivals or holidays vehicle according to temporal information by S302
Flow initial data and weekend vehicle flowrate initial data.
That is, further being drawn according to the type of period each in temporal information to vehicle flowrate initial data
Point, vehicle flowrate initial data is divided into working day vehicle flowrate initial data, festivals or holidays vehicle flowrate initial data and all last buses
Flow initial data is trained so as to subsequent according to different vehicle flowrate initial data, to generate corresponding each date type
Model, thus, establish the corresponding relationship between finally formed forecasting traffic flow model and date type.
S303 calculates separately a day vehicle flowrate initial data, festivals or holidays vehicle flowrate initial data and weekend vehicle flowrate original number
According to the related coefficient between middle weather conditions information and information of vehicle flowrate, and related coefficient is filtered out greater than predetermined coefficient threshold value
Weather conditions information and information of vehicle flowrate.
S304 according to the weather conditions information and information of vehicle flowrate construction work day training sample data collection filtered out, is saved
Holiday training sample data collection and weekend training sample data collection.
That is, the data to different date types are further screened, to generate corresponding different date types
Training sample data collection.
S305, according to day training sample data collection, festivals or holidays training sample data collection and weekend training sample data collection, depth
The classifier of degree confidence network and support vector regression carries out working day forecasting traffic flow model, festivals or holidays forecasting traffic flow respectively
The building of model and weekend forecasting traffic flow model, will pass through working day forecasting traffic flow model, festivals or holidays forecasting traffic flow
Model and weekend forecasting traffic flow model predict vehicle flowrate.
That is, after the training sample data collection corresponding to different date types generates, according to not same date class
The training sample data collection of type carries out the training of corresponding forecasting traffic flow model, with building maths modec type and forecasting traffic flow mould
Corresponding relationship between type.
In conclusion vehicle flowrate prediction technique according to an embodiment of the present invention connects firstly, obtaining vehicle flowrate initial data
, vehicle flowrate initial data is divided by working day vehicle flowrate initial data, festivals or holidays vehicle flowrate original number according to temporal information
According to weekend vehicle flowrate initial data；Then, a day vehicle flowrate initial data, festivals or holidays vehicle flowrate initial data and week are calculated separately
Related coefficient in last bus flow initial data between weather conditions information and information of vehicle flowrate, and filter out related coefficient and be greater than
The weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value；Then, according to the weather conditions information and vehicle flowrate filtered out
Information architecture working day training sample data collection, festivals or holidays training sample data collection and weekend training sample data collection；Then, root
According to day training sample data collection, festivals or holidays training sample data collection and weekend training sample data collection, depth confidence network and branch
The classifier for holding vector regression carries out working day forecasting traffic flow model, festivals or holidays forecasting traffic flow model and weekend traffic respectively
The building of prediction model is flowed, will pass through working day forecasting traffic flow model, festivals or holidays forecasting traffic flow model and weekend traffic
Prediction model is flowed to predict vehicle flowrate, thus, allow finally formed forecasting traffic flow model according to not same date
Type carries out the prediction of vehicle flowrate, meanwhile, prediction result is related to weather conditions, further increases final vehicle flowrate prediction result
Accuracy and the property of can refer to.
In order to realize above-described embodiment, the embodiment of the present invention also proposed a kind of computer readable storage medium, deposit thereon
Vehicle flowrate Prediction program is contained, such as above-mentioned vehicle flowrate prediction technique is realized when which is executed by processor.
Computer readable storage medium according to an embodiment of the present invention, by storing vehicle flowrate Prediction program, such wagon flow
Amount Prediction program realizes such as above-mentioned vehicle flowrate prediction technique when being executed by processor；Vehicle flowrate is carried out accurately to realize
Prediction, improves the property of can refer to of final vehicle flowrate prediction result.
In order to realize above-described embodiment, the embodiment of the present invention also proposed a kind of computer equipment, including memory, processing
Device and storage on a memory and the computer program that can run on a processor, when the processor executes described program, reality
Now such as above-mentioned vehicle flowrate prediction technique.
Computer equipment according to an embodiment of the present invention executes above-mentioned vehicle flowrate Prediction program by processor, thus real
Accurate Prediction now is carried out to vehicle flowrate, improves the property of can refer to of final vehicle flowrate prediction result.
In order to realize above-described embodiment, as shown in figure 5, the embodiment of the present invention also proposed a kind of vehicle flowrate prediction meanss,
The vehicle flowrate prediction meanss include: to obtain module 10, computing module 20, building module 30, training module 40 and prediction module 50.
Wherein, module 10 is obtained for obtaining vehicle flowrate initial data, wherein vehicle flowrate initial data includes weather conditions
The information of vehicle flowrate of information and corresponding weather conditions information；
Computing module 20 is used to calculate the related coefficient between weather conditions information and information of vehicle flowrate, and filters out correlation
Coefficient is greater than the weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value；
Building module 30 is used for according to weather conditions information and information of vehicle flowrate the building training sample data collection filtered out；
Training module 40 be used for according to the classifier of training sample data collection, depth confidence network and support vector regression into
The building of row forecasting traffic flow model；
Prediction module 50 is for predicting vehicle flowrate by forecasting traffic flow model.
In some embodiments, the related coefficient between weather conditions information and information of vehicle flowrate is counted according to the following formula
It calculates:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw,
yt) indicate related coefficient between weather conditions information and information of vehicle flowrate.
It should be noted that the above-mentioned description as described in vehicle flowrate prediction technique in Fig. 1 is equally applicable to vehicle flowrate prediction
Device, herein without repeating.
In conclusion vehicle flowrate prediction meanss according to an embodiment of the present invention, setting obtains module to vehicle flowrate original number
According to being obtained, wherein vehicle flowrate initial data includes the information of vehicle flowrate of weather conditions information and corresponding weather conditions information；
After getting vehicle flowrate initial data, the correlation between weather conditions information and information of vehicle flowrate is carried out by computing module
The calculating of coefficient, and filter out weather conditions information and information of vehicle flowrate that related coefficient is greater than predetermined coefficient threshold value；So as to structure
Modeling root tuber is according to weather conditions information and information of vehicle flowrate the building training sample data collection filtered out；Be arranged training module according to
The classifier of training sample data collection, depth confidence network and support vector regression carries out the building of forecasting traffic flow model；With
Just prediction module predicts vehicle flowrate by the forecasting traffic flow model that training obtains；Standard is carried out to vehicle flowrate to realize
Really prediction, improves the property of can refer to of final vehicle flowrate prediction result.
It should be understood by those skilled in the art that, the embodiment of the present invention can provide as method, system or computer program
Product.Therefore, complete hardware embodiment, complete software embodiment or reality combining software and hardware aspects can be used in the present invention
Apply the form of example.Moreover, it wherein includes the computer of computer usable program code that the present invention, which can be used in one or more,
The computer program implemented in usable storage medium (including but not limited to magnetic disk storage, CD-ROM, optical memory etc.) produces
The form of product.
The present invention be referring to according to the method for the embodiment of the present invention, the process of equipment (system) and computer program product
Figure and/or block diagram describe.It should be understood that every one stream in flowchart and/or the block diagram can be realized by computer program instructions
The combination of process and/or box in journey and/or box and flowchart and/or the block diagram.It can provide these computer programs
Instruct the processor of general purpose computer, special purpose computer, Embedded Processor or other programmable data processing devices to produce
A raw machine, so that being generated by the instruction that computer or the processor of other programmable data processing devices execute for real
The device for the function of being specified in present one or more flows of the flowchart and/or one or more blocks of the block diagram.
These computer program instructions, which may also be stored in, is able to guide computer or other programmable data processing devices with spy
Determine in the computer-readable memory that mode works, so that it includes referring to that instruction stored in the computer readable memory, which generates,
Enable the manufacture of device, the command device realize in one box of one or more flows of the flowchart and/or block diagram or
The function of being specified in multiple boxes.
These computer program instructions also can be loaded onto a computer or other programmable data processing device, so that counting
Series of operation steps are executed on calculation machine or other programmable devices to generate computer implemented processing, thus in computer or
The instruction executed on other programmable devices is provided for realizing in one or more flows of the flowchart and/or block diagram one
The step of function of being specified in a box or multiple boxes.
It should be noted that in the claims, any reference symbol between parentheses should not be configured to power
The limitation that benefit requires.Word "comprising" does not exclude the presence of component or step not listed in the claims.Before component
Word "a" or "an" does not exclude the presence of multiple such components.The present invention can be by means of including several different components
It hardware and is realized by means of properly programmed computer.In the unit claims listing several devices, these are filled
Several in setting, which can be, to be embodied by the same item of hardware.The use of word first, second, and third is not
Indicate any sequence.These words can be construed to title.
Although preferred embodiments of the present invention have been described, it is created once a person skilled in the art knows basic
Property concept, then additional changes and modifications may be made to these embodiments.So it includes excellent that the following claims are intended to be interpreted as
It selects embodiment and falls into all change and modification of the scope of the invention.
Obviously, various changes and modifications can be made to the invention without departing from essence of the invention by those skilled in the art
Mind and range.In this way, if these modifications and changes of the present invention belongs to the range of the claims in the present invention and its equivalent technologies
Within, then the present invention is also intended to include these modifications and variations.
In the description of the present invention, it is to be understood that, term " first ", " second " are used for description purposes only, and cannot
It is interpreted as indication or suggestion relative importance or implicitly indicates the quantity of indicated technical characteristic.Define as a result, " the
One ", the feature of " second " can explicitly or implicitly include one or more of the features.In the description of the present invention,
The meaning of " plurality " is two or more, unless otherwise specifically defined.
In the present invention unless specifically defined or limited otherwise, term " installation ", " connected ", " connection ", " fixation " etc.
Term shall be understood in a broad sense, for example, it may be being fixedly connected, may be a detachable connection, or integral；It can be mechanical connect
It connects, is also possible to be electrically connected；It can be directly connected, can also can be in two elements indirectly connected through an intermediary
The interaction relationship of the connection in portion or two elements.It for the ordinary skill in the art, can be according to specific feelings
Condition understands the concrete meaning of above-mentioned term in the present invention.
In the present invention unless specifically defined or limited otherwise, fisrt feature in the second feature " on " or " down " can be with
It is that the first and second features directly contact or the first and second features pass through intermediary mediate contact.Moreover, fisrt feature exists
Second feature " on ", " top " and " above " but fisrt feature be directly above or diagonally above the second feature, or be merely representative of
First feature horizontal height is higher than second feature.Fisrt feature can be under the second feature " below ", " below " and " below "
One feature is directly under or diagonally below the second feature, or is merely representative of first feature horizontal height less than second feature.
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 spy described in conjunction with this embodiment or example
Point is included at least one embodiment or example of the invention.In the present specification, schematic expression of the above terms are not
It is interpreted as that identical embodiment or example must be directed to.Moreover, particular features, structures, materials, or characteristics described
It may be combined in any suitable manner in any one or more of the embodiments or examples.In addition, without conflicting with each other, this
The technical staff in field can be by the spy of different embodiments or examples described in this specification and different embodiments or examples
Sign is combined.
Although the embodiments of the present invention has been shown and described above, it is to be understood that above-described embodiment is example
Property, it is not considered as limiting the invention, those skilled in the art within the scope of the invention can be to above-mentioned
Embodiment is changed, modifies, replacement and variant.
Claims (10)
1. a kind of vehicle flowrate prediction technique, which comprises the following steps:
Obtain vehicle flowrate initial data, wherein the vehicle flowrate initial data includes weather conditions information and the corresponding weather
The information of vehicle flowrate of condition information；
The related coefficient between the weather conditions information and the information of vehicle flowrate is calculated, and it is big to filter out the related coefficient
In the weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value；
Training sample data collection is constructed according to the weather conditions information and information of vehicle flowrate filtered out；
Forecasting traffic flow mould is carried out according to the classifier of the training sample data collection, depth confidence network and support vector regression
The building of type predicts vehicle flowrate with will pass through the forecasting traffic flow model.
2. vehicle flowrate prediction technique as described in claim 1, which is characterized in that the weather conditions information and the vehicle flowrate
Related coefficient between information calculates according to the following formula:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw, yt) table
Show the related coefficient between weather conditions information and information of vehicle flowrate.
3. vehicle flowrate prediction technique as described in claim 1, which is characterized in that according to the training sample data collection, depth
The building of the classifier of confidence network and support vector regression progress forecasting traffic flow model, comprising:
The training of depth confidence network is carried out using the training sample data collection as input, and obtains the depth confidence network
First vehicle flowrate predicted value of output；
The classifier of the support vector regression is trained according to the first vehicle flowrate predicted value；
Forecasting traffic flow model is carried out according to the classifier of the depth confidence network after training and the support vector regression after training
Building.
4. vehicle flowrate prediction technique as described in claim 1, which is characterized in that the vehicle flowrate initial data further includes corresponding to
The temporal information of the weather conditions information, wherein after obtaining vehicle flowrate initial data, further includes:
The vehicle flowrate initial data is divided into working day vehicle flowrate initial data, festivals or holidays wagon flow according to the temporal information
Initial data and weekend vehicle flowrate initial data are measured, so as to according to the working day vehicle flowrate initial data, the festivals or holidays vehicle
Flow initial data and the weekend vehicle flowrate initial data carry out the building of corresponding traffic flow prediction model, to generate working day
Forecasting traffic flow model, festivals or holidays forecasting traffic flow model and weekend forecasting traffic flow model.
5. such as vehicle flowrate prediction technique of any of claims 1-4, which is characterized in that obtaining vehicle flowrate original number
According to later, also the vehicle flowrate initial data is pre-processed, wherein the pretreated step includes:
The weather conditions information and information of vehicle flowrate that lack in the vehicle flowrate initial data are mended according to average algorithm
Entirely, and according to low-pass filtering algorithm to the vehicle flowrate initial data after completion denoising is carried out, and according to normalization algorithm
Vehicle flowrate initial data after denoising is normalized.
6. vehicle flowrate prediction technique as claimed in claim 5, which is characterized in that when there are days in the vehicle flowrate initial data
When gas condition information and information of vehicle flowrate lack, according to the day of weather conditions information and information of vehicle flowrate adjacent moment with missing
The completion of the average value of gas condition information and information of vehicle flowrate progress missing data, wherein the weather conditions of the adjacent moment
The average value of information and information of vehicle flowrate calculates according to the following formula:
Wherein, x indicates weather conditions information and information of vehicle flowrate,Indicate the weather conditions information and vehicle flowrate letter of adjacent moment
The average value of breath, t indicate the moment locating for the weather conditions information lacked and information of vehicle flowrate, and n indicates that the day of adjacent moment is vaporous
The quantity of condition information and information of vehicle flowrate.
7. a kind of computer readable storage medium, which is characterized in that be stored thereon with vehicle flowrate Prediction program, vehicle flowrate prediction
Such as vehicle flowrate prediction technique of any of claims 1-6 is realized when program is executed by processor.
8. a kind of computer equipment including memory, processor and stores the meter that can be run on a memory and on a processor
Calculation machine program, which is characterized in that when the processor executes described program, realize as of any of claims 1-6
Vehicle flowrate prediction technique.
9. a kind of vehicle flowrate prediction meanss characterized by comprising
Obtain module, for obtaining vehicle flowrate initial data, wherein the vehicle flowrate initial data include weather conditions information and
The information of vehicle flowrate of the corresponding weather conditions information；
Computing module for calculating the related coefficient between the weather conditions information and the information of vehicle flowrate, and filters out
The related coefficient is greater than the weather conditions information and information of vehicle flowrate of predetermined coefficient threshold value；
Module is constructed, for according to weather conditions information and information of vehicle flowrate the building training sample data collection filtered out；
Training module, for according to the classifier of the training sample data collection, depth confidence network and support vector regression into
The building of row forecasting traffic flow model；
Prediction module, for being predicted by the forecasting traffic flow model vehicle flowrate.
10. vehicle flowrate prediction meanss as claimed in claim 9, which is characterized in that the weather conditions information and the wagon flow
Related coefficient between amount information calculates according to the following formula:
Wherein, n indicates the quantity of weather conditions information, xwIndicate weather conditions information, ytIndicate information of vehicle flowrate, r (xw, yt) table
Show the related coefficient between weather conditions information and information of vehicle flowrate.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910684640.1A CN110517481A (en) | 2019-07-26 | 2019-07-26 | Vehicle flowrate prediction technique, medium, equipment and device |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910684640.1A CN110517481A (en) | 2019-07-26 | 2019-07-26 | Vehicle flowrate prediction technique, medium, equipment and device |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110517481A true CN110517481A (en) | 2019-11-29 |
Family
ID=68623695
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910684640.1A Withdrawn CN110517481A (en) | 2019-07-26 | 2019-07-26 | Vehicle flowrate prediction technique, medium, equipment and device |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110517481A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956341A (en) * | 2019-12-31 | 2020-04-03 | 京东城市(北京)数字科技有限公司 | Parking lot flow prediction method and device, electronic equipment and storage medium |
| CN111882878A (en) * | 2020-09-02 | 2020-11-03 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN112102610A (en) * | 2020-07-27 | 2020-12-18 | 清华大学深圳国际研究生院 | Traffic flow prediction method |
| CN113096398A (en) * | 2021-04-01 | 2021-07-09 | 付鑫 | Comprehensive traffic data mining method for multi-source data fusion |
| CN114005275A (en) * | 2021-10-25 | 2022-02-01 | 浙江交投高速公路运营管理有限公司 | Highway vehicle congestion judging method based on multi-data source fusion |
| CN116311930A (en) * | 2023-03-15 | 2023-06-23 | 河北省交通规划设计研究院有限公司 | Traffic flow state data time gathering method and system |
| CN118155423A (en) * | 2024-05-08 | 2024-06-07 | 四川智能交通系统管理有限责任公司 | Holiday long-term traffic situation prediction method and device based on time sequence model |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120087339A (en) * | 2011-01-21 | 2012-08-07 | (주)이노필리아 | Method for Providing Weather and Traffic Information |
| CN102693627A (en) * | 2011-03-23 | 2012-09-26 | 电装It研究所 | Traffic flow estimating apparatus, traffic flow estimating method and program |
| CN107945534A (en) * | 2017-12-13 | 2018-04-20 | 浙江大学城市学院 | A kind of special bus method for predicting based on GMDH neutral nets |
| CN109191846A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司温州供电公司 | A kind of traffic trip method for predicting |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
-
2019
- 2019-07-26 CN CN201910684640.1A patent/CN110517481A/en not_active Withdrawn
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| KR20120087339A (en) * | 2011-01-21 | 2012-08-07 | (주)이노필리아 | Method for Providing Weather and Traffic Information |
| CN102693627A (en) * | 2011-03-23 | 2012-09-26 | 电装It研究所 | Traffic flow estimating apparatus, traffic flow estimating method and program |
| CN107945534A (en) * | 2017-12-13 | 2018-04-20 | 浙江大学城市学院 | A kind of special bus method for predicting based on GMDH neutral nets |
| CN109191846A (en) * | 2018-10-12 | 2019-01-11 | 国网浙江省电力有限公司温州供电公司 | A kind of traffic trip method for predicting |
| CN109859469A (en) * | 2019-02-15 | 2019-06-07 | 重庆邮电大学 | A kind of vehicle flowrate prediction technique based on integrated LSTM neural network |
Non-Patent Citations (1)
| Title |
|---|
| 李星: "融合天气因素的短时交通流深度预测方法", 《中国优秀硕士学位论文全文数据库》 * |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110956341A (en) * | 2019-12-31 | 2020-04-03 | 京东城市(北京)数字科技有限公司 | Parking lot flow prediction method and device, electronic equipment and storage medium |
| CN110956341B (en) * | 2019-12-31 | 2023-06-27 | 京东城市(北京)数字科技有限公司 | Parking lot flow prediction method and device, electronic equipment and storage medium |
| CN112102610A (en) * | 2020-07-27 | 2020-12-18 | 清华大学深圳国际研究生院 | Traffic flow prediction method |
| CN111882878A (en) * | 2020-09-02 | 2020-11-03 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN111882878B (en) * | 2020-09-02 | 2021-07-02 | 烟台大学 | Method for maximizing traffic capacity of key roads based on traffic flow prediction |
| CN113096398A (en) * | 2021-04-01 | 2021-07-09 | 付鑫 | Comprehensive traffic data mining method for multi-source data fusion |
| CN114005275A (en) * | 2021-10-25 | 2022-02-01 | 浙江交投高速公路运营管理有限公司 | Highway vehicle congestion judging method based on multi-data source fusion |
| CN114005275B (en) * | 2021-10-25 | 2023-03-14 | 浙江交投高速公路运营管理有限公司 | Highway vehicle congestion judging method based on multi-data source fusion |
| CN116311930A (en) * | 2023-03-15 | 2023-06-23 | 河北省交通规划设计研究院有限公司 | Traffic flow state data time gathering method and system |
| CN118155423A (en) * | 2024-05-08 | 2024-06-07 | 四川智能交通系统管理有限责任公司 | Holiday long-term traffic situation prediction method and device based on time sequence model |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110517481A (en) | Vehicle flowrate prediction technique, medium, equipment and device | |
| CN110517492B (en) | Traffic path recommendation method, system and device based on parallel ensemble learning | |
| CN108492555A (en) | A kind of city road net traffic state evaluation method and device | |
| CN108664893A (en) | A kind of method for detecting human face and storage medium | |
| CN108257675A (en) | Chronic obstructive pulmonary disease onset risk Forecasting Methodology, server and computer readable storage medium | |
| CN103514506B (en) | For the method and system of automatic event analysis | |
| Zheng et al. | A stochastic simulation-based optimization method for equitable and efficient network-wide signal timing under uncertainties | |
| CN109242135A (en) | A kind of model method for running, device and service server | |
| CN107679985A (en) | Feature of risk screening, description message forming method, device and electronic equipment | |
| CN108389631A (en) | Varicella morbidity method for early warning, server and computer readable storage medium | |
| CN110689070B (en) | Training method and device of business prediction model | |
| CN109360413A (en) | A kind of vehicle dispatching method and system | |
| CN110084438A (en) | Prediction technique and device, the logistics system and computer-readable medium of order | |
| CN110335067A (en) | A kind of transaction prediction model construction method and device | |
| CN107977748B (en) | Multivariable distorted time sequence prediction method | |
| CN109741177A (en) | Appraisal procedure, device and the intelligent terminal of user credit | |
| CN110287332A (en) | Method and device for selecting simulation model in cloud environment | |
| Pomante | System-level design space exploration for dedicated heterogeneous multi-processor systems | |
| CN106469332A (en) | A kind of data processing method and device | |
| CN109583978A (en) | The method, device and equipment of invoice enterprise is write out falsely in a kind of identification | |
| CN110147388A (en) | A kind of method and device of data processing | |
| CN110166945A (en) | Terminal passenger traffic volume dynamic prediction method, device, medium and equipment | |
| CN110309947A (en) | Complete vehicle logistics order forecast method and device, logistics system and computer-readable medium | |
| CN109992408A (en) | A kind of resource allocation methods, device, electronic equipment and storage medium | |
| CN108805333A (en) | The batch operation operation of core banking system takes prediction technique and device |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191129 |