CN110232820A - A kind of method for building up and device of road condition predicting model - Google Patents
A kind of method for building up and device of road condition predicting model Download PDFInfo
- Publication number
- CN110232820A CN110232820A CN201910419771.7A CN201910419771A CN110232820A CN 110232820 A CN110232820 A CN 110232820A CN 201910419771 A CN201910419771 A CN 201910419771A CN 110232820 A CN110232820 A CN 110232820A
- Authority
- CN
- China
- Prior art keywords
- road
- predicted
- chain
- characteristic
- road chain
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/045—Combinations of networks
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- 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
Abstract
The application provides the method for building up and device of a kind of road condition predicting model, is related to urban highway traffic technical field, and more accurate road condition predicting may be implemented.This method comprises: determining different time points corresponding characteristic vector of the road chain to be predicted in the first preset time period, the characteristic vector is used to reflect the feature of the road chain to be predicted；The corresponding true road conditions value of the characteristic vector is determined from default telecommunication flow information library；Road condition predicting model is established according to the characteristic vector and the true road conditions value, the road condition predicting model is used to determine the road conditions of the road chain to be predicted.
Description
Technical field
This application involves urban highway traffic technical field more particularly to a kind of method for building up and dress of road condition predicting model
It sets.
Background technique
With being increasing for vehicle, urban road increasingly congestion causes many inconvenience, therefore realizes that road condition predicting is
The vital task of modern intelligent transportation, accurate road condition predicting can not only provide for urban traffic control person administers determining for congestion
Plan foundation can also go on a journey for people and provide layout of roads and navigation.
The road condition predicting of the prior art be using the road condition predicting model based on travel pattern, travel pattern refer to according to when
Between attribute road conditions are clustered, gone to search affiliated class cluster according to time attribute, then map out corresponding travel pattern.So
And, on the one hand, due to causing many because being known as of road condition change, the road condition predicting model based on travel pattern is to influence factor
Consider not comprehensive enough.On the other hand, the prior art needs the road conditions attribute for belonging to same class cluster carrying out equalization, makes data not
It can be good at showing individual difference, lead to that finally truth cannot be reacted well when carrying out road condition predicting.
Summary of the invention
The application provides the method for building up and device of a kind of road condition predicting model, and it is pre- that more accurate road conditions may be implemented
It surveys.
In order to achieve the above objectives, the application adopts the following technical scheme that
In a first aspect, the application provides a kind of method for building up of road condition predicting model, this method comprises:
Determine the corresponding characteristic vector of different time points of the road chain to be predicted in the first preset time period, institute
Characteristic vector is stated for reflecting the feature of the road chain to be predicted；The characteristic is determined from default telecommunication flow information library
According to the corresponding true road conditions value of vector；Road condition predicting mould is established according to the characteristic vector and the true road conditions value
Type, the road condition predicting model are used to determine the road conditions of the road chain to be predicted.
Second aspect, what the application provided a kind of road condition predicting model establishes device, which includes determination unit, is used for
Determine the corresponding characteristic vector of different time points of the road chain to be predicted in the first preset time period, the characteristic
It is used to reflect the feature of the road chain to be predicted according to vector；The determination unit is also used to from default telecommunication flow information library really
Determine the corresponding true road conditions value of the characteristic vector；Unit is established, for according to the characteristic vector and described
True road conditions value establishes road condition predicting model, and the road condition predicting model is used to determine the road conditions of the road chain to be predicted.
The third aspect, the application provide a kind of computer readable storage medium, are stored in computer readable storage medium
Instruction, when computer executes the instruction, which, which executes in above-mentioned first aspect and its various optional implementations, appoints
Method described in one of meaning.
Fourth aspect, the application provides a kind of computer program product comprising instruction, when the computer program product
When running on computers so that the computer execute in above-mentioned first aspect and its various optional implementations it is any it
Method described in one.
5th aspect, provide a kind of road condition predicting model establishes device, comprising: processor and communication interface, it is described logical
Believe interface and processor coupling, the processor is for running computer program or instruction, to execute above-mentioned first aspect
The method.
This application provides the method for building up and device of a kind of road condition predicting model, reflect that road chain to be predicted is special by determining
The characteristic vector of sign further determines the corresponding true road conditions of this feature data vector according to default telecommunication flow information library
Value, finally establishes road condition predicting model according to this feature data vector and true road conditions value.The road condition predicting model is using special
Data vector and corresponding true road conditions value are levied as training data, individual difference can not only be shown, additionally it is possible to make road
Condition prediction becomes more accurate, has broken the bottleneck of traditional road condition predicting accuracy rate.
Detailed description of the invention
Fig. 1 is the flow diagram one of the method for building road condition predicting model provided by the embodiments of the present application；
Fig. 2 is the flow diagram two of the method for building road condition predicting model provided by the embodiments of the present application；
Fig. 3 is the schematic diagram of road chain to be predicted and upstream and downstream road chain provided by the embodiments of the present application；
Fig. 4 is the flow diagram three of the method for building road condition predicting model provided by the embodiments of the present application；
Fig. 5 is the structural schematic diagram of neural network model provided by the embodiments of the present application；
Fig. 6 is the structural schematic diagram one of the device of building road condition predicting model provided by the embodiments of the present application；
Fig. 7 is the structural schematic diagram two of the device of building road condition predicting model provided by the embodiments of the present application.
Specific embodiment
The method for building up to road condition predicting model provided by the embodiments of the present application and device carry out detailed with reference to the accompanying drawing
Ground description.
In the description of the present application, unless otherwise indicated, "/" indicates the meaning of "or", for example, A/B can indicate A or B.
"and/or" herein is only a kind of incidence relation for describing affiliated partner, indicates may exist three kinds of relationships, for example, A
And/or B, can indicate: individualism A exists simultaneously A and B, these three situations of individualism B.In addition, "at least one" is
Refer to one or more, " multiple " refer to two or more.
In addition, the term " includes " being previously mentioned in the description of the present application and " having " and their any deformation, it is intended that
It is to cover and non-exclusive includes.Such as the process, method, system, product or equipment for containing a series of steps or units do not have
It is defined in listed step or unit, but optionally further comprising the step of other are not listed or unit, or optionally
It further include the other step or units intrinsic for these process, methods, product or equipment.
It should be noted that in the embodiment of the present application, " illustrative " or " such as " etc. words make example, example for indicating
Card or explanation.Be described as in the embodiment of the present application " illustrative " or " such as " any embodiment or design scheme do not answer
It is interpreted than other embodiments or design scheme more preferably or more advantage.Specifically, " illustrative " or " example are used
Such as " word is intended to that related notion is presented in specific ways.
Technical solution provided by the embodiments of the present application can be applied to road condition predicting system, be mainly used for the short-term pre- of road conditions
It surveys, in the prior art, the prediction of road conditions is gone to define generally according to time attribute, such as early evening peak, festivals or holidays etc. are all
Be defined as road congestion period, although however this prediction technique realize process it is simple, it is excessively unilateral, accuracy rate compared with
It is low.Whether the factor for influencing road conditions is varied, such as have burst accident etc. all can be to current on weather, road attribute, road
Road conditions have an impact.
The embodiment of the present application is melted by establishing the predictions of road condition predicting model realization road conditions according to the characteristics of road chain to be predicted
It closes many-sided influence factor and carries out data acquisition and processing (DAP), form the training set of road condition predicting model in conjunction with true road conditions value,
Training set is input in neural network model and is iterated training, finally obtains road condition predicting model.The embodiment of the present application causes
Power is mentioned in solving the problems, such as that current road conditions short-term forecast accuracy rate is lower for urban road network planning, urban traffic control and control
For foundation.
The embodiment of the present application provides a kind of method for building up of road condition predicting model, and the executing subject of this method is arbitrarily to have
The terminal device of data processing function, the terminal device can be computer, and the embodiment of the present application is not limited in any way this.Ginseng
Fig. 1 is examined, this method may include step S101-S103:
S101, determine different time points corresponding characteristic of the road chain to be predicted in the first preset time period to
Amount.
Road network refer in city scope by different function, grade, position road, by certain density and it is appropriate in the form of
The network architecture of composition.Road chain refers to the road segment segment in road net data between two points of arbitrary neighborhood.
It should be understood that different time points correspond at least one characteristic vector in the embodiment of the present application.
For example, 1 character pair data vector 1 of time point, the corresponding characteristic vector 2 of time point 2.
The embodiment of the present application Zhong Yi road chain is basic unit, it is first determined road chain to be predicted is in the first preset time period
The corresponding characteristic vector of different time points, this feature data vector are used to reflect the feature of road chain to be predicted, these
Feature can have an impact the road conditions of road chain to be predicted.This feature data vector may include a variety of dimensions, such as the time,
Space, speed and other in addition to time, space, speed can describe the dimension of the feature of road chain to be predicted.
It is for determining data acquisition range that the first preset time period, which is arranged, which can be one
Month, different time points refer to multiple time points in this one month, can be any point-in-time in one month, determining time
Point is more, and collected training set is bigger, and the accuracy of road condition predicting model is also higher.Illustratively, one can be determined
Daily all integral point moment are the different time points in the first preset time period in month.
S102, the corresponding true road conditions value of this feature data vector is determined from default telecommunication flow information library.
It should be understood that S102 is specifically that each time point is corresponding in the corresponding characteristic vector of different time points in order to determine
Characteristic vector true road conditions value.
It include the much information of road chain in default telecommunication flow information library, which includes the attribute for describing road chain feature
The history true road conditions value of information and the corresponding characterization road chain road conditions of different time points, attribute information refer to characterization road chain feature
Attribute set, the lane quantity etc. for being included such as road chain grade, road chain.Road chain with same or similar attribute set can be with
It is confirmed as same road chain.
The true road conditions value can be speed or congestion levels, or other can indicate the numerical value of road conditions.Speed
Refer in real road traffic, passes through the average speeds of certain road chain section in the unit time.Congestion levels refer to root
According to road conditions divide multiple grades, for example, the average speeds of the road Ruo Moutiao chain section are very fast, it is determined that the road chain it is crowded
Grade is lower, and the average speeds of the road Ruo Moutiao chain section are slower, it is determined that the congestion levels of the road chain are higher, this is crowded etc.
Grade can be divided according to speed, can also have other division modes, it is not limited here.
The characteristic vector of road chain to be predicted in different time points is determined by S101, first according to road chain to be predicted
Attribute information determination include corresponding all true road conditions values of the road chain to be predicted in default telecommunication flow information library, then
Corresponding true road conditions under dimension by characterizing the time in characteristic vector determines the road chain to be predicted in different time points
Value.
Illustratively, it presets in telecommunication flow information library comprising tri- road chains of A, B, C with different attribute information, every road
Chain has all corresponded to the true road conditions value under multiple and different time points, this can be determined to pre- according to the attribute information of road chain to be predicted
The true road conditions value of the road Ce Lulianwei chain A, road chain A corresponding true road conditions value, that is, road to be predicted chain, such as 8 points of correspondences of Monday
True road conditions value x, 9 points of Monday corresponding true road conditions value y therefore can be true according to the time dimension in characteristic vector
Determine the corresponding true road conditions value of this feature data vector.
It should be noted that can first be sieved according to attribute information to the true road conditions value in default telecommunication flow information library
Choosing, can also first screen the true road conditions value in default telecommunication flow information library according to time point, in the embodiment of the present application
It does not limit this.
S103, road condition predicting model is established according to this feature data vector and the true road conditions value.
The corresponding true road conditions value of characteristic vector, a characteristic vector and this feature has been determined by S102
An element in the corresponding true road conditions value, that is, training set of data vector, establishes road conditions by the training set that multiple elements form
Prediction model, the road condition predicting model are used to determine the road conditions of the road chain to be predicted.
This application provides the method for building up and device of a kind of road condition predicting model, reflect that road chain to be predicted is special by determining
The characteristic vector of sign further determines the corresponding true road conditions of this feature data vector according to default telecommunication flow information library
Value, finally establishes road condition predicting model according to this feature data vector and true road conditions value.The road condition predicting model is using special
Data vector and corresponding true road conditions value are levied as training data, individual difference can not only be shown, additionally it is possible to make road
Condition prediction becomes more accurate, has broken the bottleneck of traditional road condition predicting accuracy rate.
In the alternatively possible embodiment of the application, with reference to Fig. 2, determine road chain to be predicted in the first preset time period
The corresponding characteristic vector of interior different time points includes S201-S202, specifically, including:
S201, road chain to be predicted corresponding characteristic in different time points is determined.
This feature data may include temporal characteristics data, velocity characteristic data, space characteristics data and remove time spy
Levy other surface data other than data, velocity characteristic data, space characteristics data.
Temporal characteristics data of the road chain to be predicted in the first preset time period are for reflecting different time road to be predicted
The traffic information of chain.The temporal characteristics data can be Zhou Tezheng, such as Monday, Friday, or festivals or holidays feature, in this way
It is no for festivals or holidays and to belong to which etc. festivals or holidays, it can also be hour feature or minute grade feature, such as belong in 24 hours
Which or specific to which minute belonged to hour.Illustratively, which includes Wednesday, non-festivals or holidays, 9 points of the morning
30 points.
The velocity characteristic data of road chain to be predicted are for reflecting at least one the road chain to connect with the road chain to be predicted
Influence of the velocity characteristic to the road conditions of road chain to be predicted.It may include more in the range of chain upstream and downstream preset length in road to be predicted
A road chain.
Illustratively, with reference to Fig. 3, in each 1 km of upstream and downstream of road chain to be predicted, the upstream of the road chain to be predicted includes
Road chain 1 and road chain 2, downstream include road chain 3, and the road chain for being included by upstream and downstream carries out the equidistant cutting of preset quantity, such as
100 equal parts, the road Ji Jiang chain 1 and road chain 2 carry out 100 equal parts, road chain 3 are carried out 100 equal parts, according to default telecommunication flow information library point
Do not obtain the speed (speed) of this pavement branch sections such as 200, available speed1-speed200 totally 200 velocity amplitudes, this 200
Speed, that is, road to be predicted chain velocity characteristic data.
The space characteristics data of road chain to be predicted are used to reflect the road chain feature of road chain to be predicted to the road chain to be predicted
The influence of road conditions.Road chain feature refers to the build-in attribute of the road chain to be predicted.Illustratively, chain feature in road may include road chain etc.
Grade, road chain length, road chain width, the road chain gradient, any one or more in the chain curvature of road.
The surface data of road chain to be predicted are for reflecting except temporal characteristics data, velocity characteristic data, space are special
Levy influence of the characteristic other than data to the road conditions of road chain to be predicted.Illustratively, the surface number of road chain to be predicted
According to may include weather characteristics (including precipitation, temperature, rain and snow weather, haze index etc.), traffic accident whether occurs etc., to
Whether prediction road chain and at least one the road chain to connect with the road chain to be predicted restrict driving.
S202, characteristic is pre-processed, obtains the corresponding characteristic vector of different time points.
The S201 characteristic determined is pre-processed, pretreatment is to guarantee the integrality of characteristic and accurate
Property, reject the influence of accidentalia.Illustratively, it may include the parsing to this feature data, screen, fill up, Ke Yixian
This feature data are parsed, the screening of data is then carried out according to parsing result and are filled up, it can also be first to this feature number
According to being screened to reduce data volume, then the characteristic after screening is parsed and filled up again, the embodiment of the present application pair
Pretreated sequence is without limitation.
It will be converted into the corresponding characteristic vector of different time points by pretreated characteristic, it is exemplary
, if some temporal characteristics data includes Wednesday, non-festivals or holidays, at 9 points in the morning 30 minutes, which can be converted into
Time arrow including Zhou Tezheng, festivals or holidays feature, hour feature totally three dimensions.If the upstream and downstream road chain of road chain to be predicted is total
Cutting is 200 equal parts, then velocity characteristic data can be converted into the velocity vector including 200 dimensions.It can similarly obtain, space is special
Sign data can be converted into the sky including road chain grade, road chain length, road chain width, the road chain gradient, road chain curvature totally 5 dimensions
Between vector, surface data can be converted into including weather, accident, the external vector for 3 dimensions of restricting driving totally.Therefore characteristic
According to vector include the time arrow of 3 dimensions, the velocity vector of 200 dimensions, 5 dimensions space vector and 3 dimensions
External vector amounts to 211 dimensions.
In the alternatively possible embodiment of the application, with reference to Fig. 4, characteristic is determined from default telecommunication flow information library
According to vector, corresponding true road conditions value includes S301-S203 in different time points, specifically, including:
S301, at least one time tag is determined according to characteristic vector.
Characteristic vector includes time arrow, can determine one according to the time arrow and the second preset time period
At least one time tag of characteristic vector, and have between adjacent time label at least one time tag and preset
Time interval.
The embodiment of the present application demarcates characteristic vector with history road condition data, such as a road chain has 9:00-
The history road condition data of mono- hour of 10:00, then can be used to generate the corresponding spy of 9:30 with preceding half an hour (9:00-9:30)
Data vector is levied, uses the road conditions feature of half an hour after (9:30-10:00) as the calibration value of characteristic vector.
Illustratively, the second preset time period is 30 minutes, at least one time tag is 6 time tags, i.e., default
Time interval is five minutes, it is assumed that the time arrow of this feature data vector is at 9 points in the morning 30 minutes, then is with the time point
Point, it is spaced points that 5 minutes futures, 10 minutes, 15 minutes, 20 minutes, 25 minutes, 30 minutes, which can be set,.Demarcate the morning 9: 35
Point, 40 minutes at 9 points in mornings, 45 minutes at 9 points in mornings, 50 minutes at 9 points in mornings, 10 points of 55 minutes at 9 points in mornings, the morning 00 minute total T5、T10、T15、
T20、T25、T30Six time tags.
S302, determine that at least one time tag is corresponding true in different time points from default telecommunication flow information library
Road conditions value.
At least one time tag of this feature data vector can be determined not by inquiring default telecommunication flow information library
The corresponding true road conditions value with time point.Determine T5、T10、T15、T20、T25、T30Six time tags 35 minutes at 9 points in mornings, on
40 minutes 9 points of noons, 45 minutes at 9 points in mornings, 50 minutes at 9 points in mornings, 10 points of 55 minutes at 9 points in mornings, the morning 00 minute corresponding true road conditions
Value Y5、Y10、Y15、Y20、Y25、Y30。
S303, by least one time tag in different time points corresponding true road conditions value be determined as this feature data to
Measure corresponding true road conditions value in different time points.
At least one time tag corresponding true road conditions value in different time points, an available characteristic has been determined
According to vector corresponding true road conditions value in different time points, finally by the calibration of characteristic vector and this feature data vector
It is worth corresponding true road conditions value and is input in deep learning model and is trained.
Optionally, 7 layers of convolutional neural networks model realization road conditions short-term forecast, the nerve net are selected in the embodiment of the present application
Network model is formed by 7 layers, including 2 convolutional layers, 2 pond layers, 3 full articulamentums, with reference to Fig. 5, specifically:
First layer is convolutional layer:
The input of this layer is exactly original image pixels 252*6*1.First convolutional layer filter size is 5*5, depth
It is 6, is filled without using full 0, step-length 1.
The second layer is pond layer:
The input of this layer is the output of first layer.For 2*2, long and wide step-length is this layer of filter size used
2。
Third layer is convolutional layer:
This layer of input is the output of the second layer, and the filter size used is 5*5, and depth is that 16. layers do not use full 0
Filling, step-length 1.
4th layer is pond layer:
The input of this layer is the output of first layer.For 2*2, long and wide step-length is this layer of filter size used
2。
Layer 5 is full articulamentum:
If upper one layer of output matrix dimension is z port number of m row n column, the filter size connected entirely of this layer is
(m*n*z) * 1024, bias term b dimension is 1024.
Layer 6 is full articulamentum:
If upper one layer of output matrix dimension is z port number of m row n column, the dimension of the filter w connected entirely of this layer
For (m*n*z) * 512, bias term b dimension is 512.
Layer 7 is full articulamentum:
If upper one layer of output matrix dimension is z port number of m row n column, the filter size connected entirely of this layer is
(m*n*z) * 6, bias term b dimension is 6.
Optionally, road conditions prediction model can be evaluated and tested by way of calculating relative error, i.e. relative errorWherein xiFor true road conditions value, x is predicted value.By way of setting threshold value, sentence
Break the road condition predicting model prediction result it is whether accurate.
A kind of possible structure for establishing device that Fig. 6 shows road condition predicting model involved in above-described embodiment is shown
It is intended to.The device 400 includes determination unit 401, specific:
The determination unit 401 is used for:
Determine the corresponding characteristic vector of different time points of the road chain to be predicted in the first preset time period, it should
Characteristic vector is used to reflect the feature of the road chain to be predicted.
Optionally, which is also used to:
The corresponding true road conditions value of this feature data vector is determined from default telecommunication flow information library.
Optionally, the device 400 further include:
Unit 402 is established, it, should for establishing road condition predicting model according to this feature data vector and the true road conditions value
Road condition predicting model is used to determine the road conditions of the road chain to be predicted.
Optionally, the determination unit 401, is specifically used for:
Determine the road chain to be predicted in the corresponding characteristic of the different time points；This feature data are located in advance
Reason, obtains the corresponding characteristic vector of the different time points.
Optionally, this feature data include:
The temporal characteristics data of the road chain to be predicted in first preset time period, the temporal characteristics data are for reflecting
The traffic information of the different time road chain to be predicted.
The velocity characteristic data of the road chain to be predicted, which, which is used to reflect, connects with the road chain to be predicted
Influence of the velocity characteristic of at least one road chain to the road conditions of the road chain to be predicted.
The space characteristics data of the road chain to be predicted, the space characteristics data are used to reflect that the road chain of the road chain to be predicted to be special
Levy the influence to the road conditions of the road chain to be predicted.
The surface data of the road chain to be predicted, the surface data are for reflecting except the temporal characteristics data, being somebody's turn to do
The influence of characteristic other than velocity characteristic data, the space characteristics data to the road conditions of the road chain to be predicted.
Optionally, the determination unit, is specifically also used to:
At least one time tag is determined according to this feature data vector；This is determined at least from default telecommunication flow information library
One time tag is in the corresponding true road conditions value of the different time points；By at least one time tag in the different time points
Corresponding true road conditions value is determined as this feature data vector in the corresponding true road conditions value of the different time points.
Optionally, which is determined by the second preset time period and the time arrow, and this at least one
There is between adjacent time label prefixed time interval in a time tag.
Fig. 7 shows another possible structure for establishing device of road condition predicting model involved in above-described embodiment
Schematic diagram.The device 500 includes: processor 502.Processor 502 is for carrying out control management, example to the movement of the device 500
Such as, it executes above-mentioned determination unit 401, establish the step of unit 402 executes, and/or for executing techniques described herein
Other processes.
Above-mentioned processor 502 can be realization or execute to combine and various illustratively patrols described in present disclosure
Collect box, module and circuit.The processor can be central processing unit, general processor, digital signal processor, dedicated integrated
Circuit, field programmable gate array or other programmable logic device, transistor logic, hardware component or it is any
Combination.It, which may be implemented or executes, combines various illustrative logic blocks, module and electricity described in present disclosure
Road.The processor be also possible to realize computing function combination, such as comprising one or more microprocessors combine, DSP and
The combination etc. of microprocessor.
Optionally, which can also include communication interface 503, memory 501 and bus 504, communication interface 503
For supporting the communication of device 500 Yu other network entities.Memory 501 is used to store the program code sum number of the device 500
According to.
Wherein, memory 501 can be the memory in device 500, which may include volatile memory, example
Such as random access memory；The memory also may include nonvolatile memory, such as read-only memory, flash memory,
Hard disk or solid state hard disk；The memory can also include the combination of the memory of mentioned kind.
Bus 504 can be expanding the industrial standard structure (Extended Industry Standard
Architecture, EISA) bus etc..Bus 504 can be divided into address bus, data/address bus, control bus etc..For convenient for table
Show, only indicated with a thick line in Fig. 7, it is not intended that an only bus or a type of bus.
Through the above description of the embodiments, it is apparent to those skilled in the art that, for description
It is convenienct and succinct, only the example of the division of the above functional modules, in practical application, can according to need and will be upper
It states function distribution to be completed by different functional modules, i.e., the internal structure of device is divided into different functional modules, to complete
All or part of function described above.The specific work process of the system, apparatus, and unit of foregoing description, before can referring to
The corresponding process in embodiment of the method is stated, details are not described herein.
The embodiment of the present application provides a kind of computer program product comprising instruction, when the computer program product is being counted
When being run on calculation machine, so that the computer executes the method for constructing road condition predicting model described in above method embodiment.
The embodiment of the present application also provides a kind of computer readable storage medium, and finger is stored in computer readable storage medium
It enables, when the network equipment executes the instruction, which executes network in method flow shown in above method embodiment and set
The standby each step executed.
Wherein, computer readable storage medium, such as electricity, magnetic, optical, electromagnetic, infrared ray can be but not limited to or partly led
System, device or the device of body, or any above combination.The more specific example of computer readable storage medium is (non-poor
The list of act) it include: the electrical connection with one or more conducting wires, portable computer diskette, hard disk, random access memory
(Random Access Memory, RAM), read-only memory (Read-Only Memory, ROM), erasable type may be programmed read-only
It is memory (Erasable Programmable Read Only Memory, EPROM), register, hard disk, optical fiber, portable
Compact disc read-only memory (Compact Disc Read-Only Memory, CD-ROM), light storage device, magnetic memory
The computer readable storage medium of part or above-mentioned any appropriate combination or any other form well known in the art.
A kind of illustrative storage medium is coupled to processor, to enable a processor to from the read information, and can be to
Information is written in the storage medium.Certainly, storage medium is also possible to the component part of processor.Pocessor and storage media can be with
In application-specific IC (Application Specific Integrated Circuit, ASIC).In the application
In embodiment, computer readable storage medium can be any tangible medium for including or store program, which can be referred to
Enable execution system, device or device use or in connection.
The above, the only specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any
Change or replacement within the technical scope of the present application should all be covered within the scope of protection of this application.Therefore, this Shen
Protection scope please should be subject to the protection scope in claims.
Claims (13)
1. a kind of method for building up of road condition predicting model characterized by comprising
Determine the corresponding characteristic vector of different time points of the road chain to be predicted in the first preset time period, the spy
Sign data vector is used to reflect the feature of the road chain to be predicted；
The corresponding true road conditions value of the characteristic vector is determined from default telecommunication flow information library；
Road condition predicting model is established according to the characteristic vector and the true road conditions value, the road condition predicting model is used
In the road conditions for determining the road chain to be predicted.
2. the method according to claim 1, wherein determination road chain to be predicted is in the first preset time period
The corresponding characteristic vector of different time points include:
Determine the road chain to be predicted in the corresponding characteristic of the different time points；
The characteristic is pre-processed, the corresponding characteristic vector of the different time points is obtained.
3. according to the method described in claim 2, it is characterized in that, the characteristic includes:
Temporal characteristics data of the road chain to be predicted in first preset time period, the temporal characteristics data are for anti-
Reflect the traffic information of road chain to be predicted described in different time；
The velocity characteristic data of the road chain to be predicted, the velocity characteristic data connect for reflecting with the road chain to be predicted
At least one road chain influence of the velocity characteristic to the road conditions of the road chain to be predicted；
The space characteristics data of the road chain to be predicted, the space characteristics data are used to reflect the road chain of the road chain to be predicted
Influence of the feature to the road conditions of the road chain to be predicted；
The surface data of the road chain to be predicted, the surface data for reflect except the temporal characteristics data,
The influence of characteristic other than the velocity characteristic data, the space characteristics data to the road conditions of the road chain to be predicted.
4. the method according to claim 1, wherein described determine the feature from default telecommunication flow information library
Data vector includes: in the corresponding true road conditions value of the different time points
At least one time tag is determined according to the characteristic vector；
Determine at least one described time tag on the corresponding true road of the different time points from default telecommunication flow information library
Condition value；
At least one described time tag is determined as the characteristic in the corresponding true road conditions value of the different time points
Vector is in the corresponding true road conditions value of the different time points.
5. according to the method described in claim 4, it is characterized in that, at least one described time tag is by the second preset time period
It is determined with the time arrow, and there is between adjacent time label prefixed time interval at least one described time tag.
6. a kind of road condition predicting model establishes device characterized by comprising
Determination unit, for determining different time points corresponding characteristic of the road chain to be predicted in the first preset time period
According to vector, the characteristic vector is used to reflect the feature of the road chain to be predicted；
The determination unit is also used to determine the corresponding true road conditions of the characteristic vector from default telecommunication flow information library
Value；
Unit is established, it is described for establishing road condition predicting model according to the characteristic vector and the true road conditions value
Road condition predicting model is used to determine the road conditions of the road chain to be predicted.
7. device according to claim 6, which is characterized in that the determination unit is specifically used for:
Determine the road chain to be predicted in the corresponding characteristic of the different time points；
The characteristic is pre-processed, the corresponding characteristic vector of the different time points is obtained.
8. device according to claim 7, which is characterized in that the characteristic includes:
Temporal characteristics data of the road chain to be predicted in first preset time period, the temporal characteristics data are for anti-
Reflect the traffic information of road chain to be predicted described in different time；
The velocity characteristic data of the road chain to be predicted, the velocity characteristic data connect for reflecting with the road chain to be predicted
At least one road chain influence of the velocity characteristic to the road conditions of the road chain to be predicted；
The space characteristics data of the road chain to be predicted, the space characteristics data are used to reflect the road chain of the road chain to be predicted
Influence of the feature to the road conditions of the road chain to be predicted；
The surface data of the road chain to be predicted, the surface data for reflect except the temporal characteristics data,
The influence of characteristic other than the velocity characteristic data, the space characteristics data to the road conditions of the road chain to be predicted.
9. device according to claim 6, which is characterized in that the determination unit is specifically also used to:
At least one time tag is determined according to the characteristic vector；
Determine at least one described time tag on the corresponding true road of the different time points from default telecommunication flow information library
Condition value；
At least one described time tag is determined as the characteristic in the corresponding true road conditions value of the different time points
Vector is in the corresponding true road conditions value of the different time points.
10. device according to claim 9, which is characterized in that at least one described time tag is by the second preset time
Section and the time arrow determine, and at least one described time tag between adjacent time label have preset time between
Every.
11. a kind of road condition predicting model establishes device, which is characterized in that described device includes: processor and communication interface, institute
Communication interface and processor coupling are stated, the processor is for running computer program or instruction, to realize as right is wanted
Method described in one of asking 1-5 any.
12. a kind of computer readable storage medium, it is stored with instruction in computer readable storage medium, is referred to when computer executes this
When enabling, the computer execute it is one of any in the claims 1-5 described in method.
13. a kind of computer program product comprising instruction, when the computer program product is run on computers, the meter
Calculation machine execute it is one of any in the claims 1-5 described in method.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419771.7A CN110232820A (en) | 2019-05-20 | 2019-05-20 | A kind of method for building up and device of road condition predicting model |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910419771.7A CN110232820A (en) | 2019-05-20 | 2019-05-20 | A kind of method for building up and device of road condition predicting model |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110232820A true CN110232820A (en) | 2019-09-13 |
Family
ID=67860785
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910419771.7A Pending CN110232820A (en) | 2019-05-20 | 2019-05-20 | A kind of method for building up and device of road condition predicting model |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110232820A (en) |
Cited By (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889558A (en) * | 2019-11-29 | 2020-03-17 | 北京世纪高通科技有限公司 | Road condition prediction method and device |
| CN111862590A (en) * | 2020-05-13 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Road condition prediction method, road condition prediction device and storage medium |
| CN111959495A (en) * | 2020-06-29 | 2020-11-20 | 北京百度网讯科技有限公司 | Vehicle control method and device and vehicle |
| CN111986490A (en) * | 2020-09-18 | 2020-11-24 | 北京百度网讯科技有限公司 | Road condition prediction method and device, electronic equipment and storage medium |
| CN112651550A (en) * | 2020-12-21 | 2021-04-13 | 北京世纪高通科技有限公司 | Road condition prediction method and device and readable storage medium |
| CN112669594A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device, equipment and storage medium for predicting traffic road conditions |
| CN115457766A (en) * | 2022-08-31 | 2022-12-09 | 华迪计算机集团有限公司 | Method and system for predicting road congestion state |
Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894809A (en) * | 2014-12-25 | 2016-08-24 | 杭州远眺科技有限公司 | Sectional type urban road traffic state estimation method |
| CN106228808A (en) * | 2016-08-05 | 2016-12-14 | 北京航空航天大学 | City expressway travel time prediction method based on Floating Car space-time grid data |
| CN106935027A (en) * | 2015-12-30 | 2017-07-07 | 沈阳美行科技有限公司 | A kind of traffic information predicting method and device based on running data |
| CN107038478A (en) * | 2017-04-20 | 2017-08-11 | 百度在线网络技术（北京）有限公司 | Road condition predicting method and device, computer equipment and computer-readable recording medium |
| CN107045788A (en) * | 2017-06-28 | 2017-08-15 | 北京数行健科技有限公司 | Traffic Forecasting Methodology and device |
| CN107103754A (en) * | 2017-05-10 | 2017-08-29 | 华南师范大学 | A kind of road traffic condition Forecasting Methodology and system |
| CN107195177A (en) * | 2016-03-09 | 2017-09-22 | 中国科学院深圳先进技术研究院 | Based on Forecasting Methodology of the distributed memory Computational frame to city traffic road condition |
| CN107886718A (en) * | 2017-11-01 | 2018-04-06 | 沈阳世纪高通科技有限公司 | A kind of road condition analyzing method, apparatus and network system |
| CN109300309A (en) * | 2018-10-29 | 2019-02-01 | 讯飞智元信息科技有限公司 | Road condition predicting method and device |
| CN109410565A (en) * | 2017-08-15 | 2019-03-01 | 高德信息技术有限公司 | A kind of dynamic traffic event prediction method and device |
| CN109686092A (en) * | 2019-01-23 | 2019-04-26 | 北京航空航天大学 | A kind of access appraisal procedure of transportation network |
| KR101974495B1 (en) * | 2018-08-21 | 2019-05-03 | 한국과학기술정보연구원 | Apparatus for predicting traffic information, method thereof and recoding medium for predicting traffic information |
-
2019
- 2019-05-20 CN CN201910419771.7A patent/CN110232820A/en active Pending
Patent Citations (12)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105894809A (en) * | 2014-12-25 | 2016-08-24 | 杭州远眺科技有限公司 | Sectional type urban road traffic state estimation method |
| CN106935027A (en) * | 2015-12-30 | 2017-07-07 | 沈阳美行科技有限公司 | A kind of traffic information predicting method and device based on running data |
| CN107195177A (en) * | 2016-03-09 | 2017-09-22 | 中国科学院深圳先进技术研究院 | Based on Forecasting Methodology of the distributed memory Computational frame to city traffic road condition |
| CN106228808A (en) * | 2016-08-05 | 2016-12-14 | 北京航空航天大学 | City expressway travel time prediction method based on Floating Car space-time grid data |
| CN107038478A (en) * | 2017-04-20 | 2017-08-11 | 百度在线网络技术（北京）有限公司 | Road condition predicting method and device, computer equipment and computer-readable recording medium |
| CN107103754A (en) * | 2017-05-10 | 2017-08-29 | 华南师范大学 | A kind of road traffic condition Forecasting Methodology and system |
| CN107045788A (en) * | 2017-06-28 | 2017-08-15 | 北京数行健科技有限公司 | Traffic Forecasting Methodology and device |
| CN109410565A (en) * | 2017-08-15 | 2019-03-01 | 高德信息技术有限公司 | A kind of dynamic traffic event prediction method and device |
| CN107886718A (en) * | 2017-11-01 | 2018-04-06 | 沈阳世纪高通科技有限公司 | A kind of road condition analyzing method, apparatus and network system |
| KR101974495B1 (en) * | 2018-08-21 | 2019-05-03 | 한국과학기술정보연구원 | Apparatus for predicting traffic information, method thereof and recoding medium for predicting traffic information |
| CN109300309A (en) * | 2018-10-29 | 2019-02-01 | 讯飞智元信息科技有限公司 | Road condition predicting method and device |
| CN109686092A (en) * | 2019-01-23 | 2019-04-26 | 北京航空航天大学 | A kind of access appraisal procedure of transportation network |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889558A (en) * | 2019-11-29 | 2020-03-17 | 北京世纪高通科技有限公司 | Road condition prediction method and device |
| CN110889558B (en) * | 2019-11-29 | 2023-06-06 | 北京世纪高通科技有限公司 | Road condition prediction method and device |
| CN111862590A (en) * | 2020-05-13 | 2020-10-30 | 北京嘀嘀无限科技发展有限公司 | Road condition prediction method, road condition prediction device and storage medium |
| CN111959495A (en) * | 2020-06-29 | 2020-11-20 | 北京百度网讯科技有限公司 | Vehicle control method and device and vehicle |
| CN111959495B (en) * | 2020-06-29 | 2021-11-12 | 阿波罗智能技术(北京)有限公司 | Vehicle control method and device and vehicle |
| CN111986490A (en) * | 2020-09-18 | 2020-11-24 | 北京百度网讯科技有限公司 | Road condition prediction method and device, electronic equipment and storage medium |
| CN112669594A (en) * | 2020-12-11 | 2021-04-16 | 国汽(北京)智能网联汽车研究院有限公司 | Method, device, equipment and storage medium for predicting traffic road conditions |
| CN112651550A (en) * | 2020-12-21 | 2021-04-13 | 北京世纪高通科技有限公司 | Road condition prediction method and device and readable storage medium |
| CN115457766A (en) * | 2022-08-31 | 2022-12-09 | 华迪计算机集团有限公司 | Method and system for predicting road congestion state |
| CN115457766B (en) * | 2022-08-31 | 2023-08-08 | 华迪计算机集团有限公司 | Method and system for predicting road congestion state |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110232820A (en) | A kind of method for building up and device of road condition predicting model | |
| CN107038478B (en) | Road condition prediction method and device, computer equipment and readable medium | |
| CN112700072B (en) | Traffic condition prediction method, electronic device, and storage medium | |
| CN110264711A (en) | A kind of traffic accident method of determining probability and device | |
| EP3929805A1 (en) | Method and apparatus for identifying traffic accident, device and computer storage medium | |
| CN111144648B (en) | People flow prediction device and method | |
| CN107389085B (en) | Method and device for determining road traffic attributes, computer and storage medium | |
| CN110782120B (en) | Method, system, equipment and medium for evaluating traffic flow model | |
| CN110132293B (en) | Route recommendation method and device | |
| US20130090905A1 (en) | Traffic Sensor Management | |
| CN106504534B (en) | A kind of method, apparatus and user equipment for predicting road conditions | |
| CN112257954A (en) | Method, device and system for predicting risk level of segmented road and storage medium | |
| CN110956807A (en) | Highway flow prediction method based on combination of multi-source data and sliding window | |
| CN110889558A (en) | Road condition prediction method and device | |
| Wei et al. | An improved road network partition algorithm for parallel microscopic traffic simulation | |
| CN111914940A (en) | Shared vehicle station clustering method, system, device and storage medium | |
| CN114373309A (en) | Method and device for calculating traffic flow of service area, terminal equipment and medium | |
| CN114596709A (en) | Data processing method, device, equipment and storage medium | |
| CN112651550A (en) | Road condition prediction method and device and readable storage medium | |
| CN115359663B (en) | Mountain road disaster section disaster-resistant toughness calculation method and device and electronic equipment | |
| CN110986992A (en) | Navigation method and device for unmanned vending vehicle, electronic equipment and storage medium | |
| CN110264725A (en) | The determination method and device of link flow | |
| Li et al. | Vehicle departure pattern and queue length prediction at an isolated intersection with automatic vehicle identity detection | |
| CN115563522A (en) | Traffic data clustering method, device, equipment and medium | |
| CN113298309A (en) | Method, device and terminal for predicting traffic congestion state |
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 | ||
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190913 |