CN108805312A - A kind of determination method and device of adjacent bayonet - Google Patents
A kind of determination method and device of adjacent bayonet Download PDFInfo
- Publication number
- CN108805312A CN108805312A CN201710281279.9A CN201710281279A CN108805312A CN 108805312 A CN108805312 A CN 108805312A CN 201710281279 A CN201710281279 A CN 201710281279A CN 108805312 A CN108805312 A CN 108805312A
- Authority
- CN
- China
- Prior art keywords
- bayonet
- attribute information
- algorithm
- information
- association
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
- G06Q10/047—Optimisation of routes or paths, e.g. travelling salesman problem
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
Abstract
The embodiment of the invention discloses a kind of determination method and devices of adjacent bayonet, determine the corresponding driving trace of each car plate, according to the driving trace and the first attribute information of each bayonet obtained in advance, establish bayonet consecutive phantom；When it needs to be determined that whether two bayonets are adjacent, the second attribute information of the two bayonets is matched with the model established, when successful match, determines that the two bayonets are adjacent bayonet.It can be seen that this programme can determine whether two bayonets are adjacent, without the degree of association being to determine between two bayonets, the accuracy for determining adjacent bayonet is improved.
Description
Technical field
Technical field of data processing of the present invention, more particularly to a kind of determination method and device of adjacent bayonet.
Background technology
Currently, vehicle is more and more, traffic block port is also more and more in road, and traffic also becomes increasingly complex.Multiple
In miscellaneous traffic, it usually needs determine adjacent bayonet, to facilitate vehicle to carry out Path selection, or facilitate dependent part
Sorting-out in statistics etc. of the door to traffic data.
In existing scheme, it is already possible to determine the degree of association between each bayonet, but the degree of association can only react each bayonet
Between may adjacent probability, whether adjacent can not accurately react bayonet.
Invention content
The embodiment of the present invention is designed to provide a kind of determination method and device of adjacent bayonet, improves and determines adjacent card
The accuracy of mouth.
In order to achieve the above objectives, the embodiment of the invention discloses a kind of determination methods of adjacent bayonet, including：
Vehicle record is crossed according to pre-stored, determines the corresponding driving trace of each car plate；Wherein, described cross in vehicle record is wrapped
Containing license board information, bayonet information, temporal information；
According to identified driving trace and the first attribute information of each bayonet obtained in advance, the adjacent mould of bayonet is established
Type；
Obtain the second attribute information of two bayonets for including in bayonet group to be determined and the bayonet group；Described second belongs to
There are correspondences with first attribute information for property information；
Second attribute information is matched with the bayonet consecutive phantom, when successful match, determines described two
A bayonet is adjacent bayonet.
Optionally, the first attribute information of driving trace determined by the basis and each bayonet obtained in advance is established
The step of bayonet consecutive phantom, may include：
Using association rule algorithm, in identified each driving trace, extraction association bayonet set, each association card
Mouth set includes two bayonets；
Determine each number for being associated with two bayonets that bayonet set includes and appearing in same driving trace；
According to the number, the corresponding relating attribute information of each association bayonet set is determined；
Using feature extraction algorithm and/or feature selecting algorithm, first attribute information and the relating attribute are determined
The corresponding target signature data of information；
Using sorting algorithm, classify to the target signature data, according to classification results, establishes the adjacent mould of bayonet
Type.
Optionally, described to utilize feature extraction algorithm and/or feature selecting algorithm, determine first attribute information and institute
The step of stating relating attribute information corresponding target signature data may include：
The corresponding static attribute information of each association bayonet set is extracted from first attribute information；
Using feature extraction algorithm and/or feature selecting algorithm, the static attribute information and the relating attribute are determined
The corresponding target signature data of information.
Optionally, described to utilize feature extraction algorithm and feature selecting algorithm, determine the static attribute information and described
The step of relating attribute information corresponding target signature data, may include：
Using feature extraction algorithm, dimension-reduction treatment is carried out to the static attribute information and the relating attribute information；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
Optionally, described to utilize sorting algorithm, classify to the target signature data, according to classification results, establishes
The step of bayonet consecutive phantom, may include：
According to the number, the corresponding abnormal attribute information of each association bayonet set is determined；
The corresponding Regional Property information of each association bayonet set is extracted from first attribute information；
Using sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to the target signature number
According to classifying, according to classification results, bayonet consecutive phantom is established.
Optionally, described to utilize sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to described
Target signature data are classified, and according to classification results, the step of establishing bayonet consecutive phantom, may include：
The target signature data are divided into training set and test set；
The training set is carried out in conjunction with the abnormal attribute information and the Regional Property information using sorting algorithm
Training, obtains training pattern；
The training pattern is tested using the test set, according to test result, the training pattern is carried out
Adjustment；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
In order to achieve the above objectives, the embodiment of the invention also discloses a kind of determining devices of adjacent bayonet, including：
Determining module determines the corresponding driving trace of each car plate for crossing vehicle record according to pre-stored；Wherein, institute
It stated in vehicle record comprising license board information, bayonet information, temporal information；
Module is established, for the first attribute information according to identified driving trace and each bayonet obtained in advance, is built
Vertical bayonet consecutive phantom；
Acquisition module, the second attribute for obtaining two bayonets for including in bayonet group to be determined and the bayonet group are believed
Breath；There are correspondences with first attribute information for second attribute information；
Matching module works as successful match for matching second attribute information with the bayonet consecutive phantom
When, determine that described two bayonets are adjacent bayonet.
Optionally, described to establish module, may include：
Extracting sub-module, for utilizing association rule algorithm, in identified each driving trace, extraction association bayonet
Set, each bayonet set that is associated with includes two bayonets；
First determination sub-module, for determining that two bayonets that each association bayonet set includes appear in same traveling
The number of track；
Second determination sub-module, for according to the number, determining the corresponding relating attribute letter of each association bayonet set
Breath；
Third determination sub-module determines first attribute for utilizing feature extraction algorithm and/or feature selecting algorithm
Information and the corresponding target signature data of the relating attribute information；
Setting up submodule classifies to the target signature data for utilizing sorting algorithm, according to classification results,
Establish bayonet consecutive phantom.
Optionally, the third determination sub-module may include：
First extraction unit belongs to for extracting the corresponding static state of each association bayonet set from first attribute information
Property information；
First determination unit determines the static attribute letter for utilizing feature extraction algorithm and/or feature selecting algorithm
Breath and the corresponding target signature data of the relating attribute information.
Optionally, first determination unit, specifically can be used for：
Using feature extraction algorithm, dimension-reduction treatment is carried out to the static attribute information and the relating attribute information；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
Optionally, the setting up submodule may include：
Second determination unit, for according to the number, determining the corresponding abnormal attribute information of each association bayonet set；
Second extraction unit belongs to for extracting the corresponding region of each association bayonet set from first attribute information
Property information；
Unit is established, for utilizing sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to institute
It states target signature data to classify, according to classification results, establishes bayonet consecutive phantom.
Optionally, described to establish unit, specifically it can be used for：
The target signature data are divided into training set and test set；
The training set is carried out in conjunction with the abnormal attribute information and the Regional Property information using sorting algorithm
Training, obtains training pattern；
The training pattern is tested using the test set, according to test result, the training pattern is carried out
Adjustment；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
It using the embodiment of the present invention, determines the corresponding driving trace of each car plate, obtains according to the driving trace and in advance
First attribute information of each bayonet, establishes bayonet consecutive phantom；When it needs to be determined that whether two bayonets are adjacent, the two are blocked
Second attribute information of mouth is matched with the model established, and when successful match, determines that the two bayonets are adjacent bayonet.
It can be seen that this programme can determine whether two bayonets are adjacent, without the degree of association being to determine between two bayonets, determination is improved
The accuracy of adjacent bayonet.
Certainly, it implements any of the products of the present invention or method must be not necessarily required to reach all the above excellent simultaneously
Point.
Description of the drawings
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Obtain other attached drawings according to these attached drawings.
Fig. 1 is a kind of flow diagram of the determination method of adjacent bayonet provided in an embodiment of the present invention；
Fig. 2 is the flow diagram provided in an embodiment of the present invention for establishing bayonet consecutive phantom；
Fig. 3 is a kind of structural schematic diagram of the determining device of adjacent bayonet provided in an embodiment of the present invention.
Specific implementation mode
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, those of ordinary skill in the art are obtained every other without creative efforts
Embodiment shall fall within the protection scope of the present invention.
In order to solve the above-mentioned technical problem, an embodiment of the present invention provides a kind of determination method and device of adjacent bayonet,
Various electronic equipments are can be applied to, are not limited specifically.
A kind of determination method of adjacent bayonet provided in an embodiment of the present invention is described in detail first below.
Fig. 1 is a kind of flow diagram of the determination method of adjacent bayonet provided in an embodiment of the present invention, including：
S101：Vehicle record is crossed according to pre-stored, determines the corresponding driving trace of each car plate.Wherein, described to cross vehicle note
Include license board information, bayonet information, temporal information in record.
For example, pre-stored vehicle record of crossing includes following content：
1, car plate-capital A00000, bayonet identify -0067, by 1 day 9 December 2016 time：40；
2, car plate-capital A00000, bayonet identify -0065, by 1 day 9 December 2016 time：00；
3, car plate-capital A00000, bayonet identify -0076, by 1 day 10 December 2016 time：20；
4, car plate-capital A00000, bayonet identify -0082, by 1 day 11 December 2016 time：30；
……
It crosses in vehicle record comprising license board information, bayonet information, temporal information, therefore, can be determined according to vehicle record is crossed
The corresponding driving trace of each car plate.For example, according to the above, the corresponding traveling rail of car plate " capital A00000 " can be determined
Mark：Bayonet identifies " 0065 "-bayonet mark " 0067 "-bayonet mark " 0076 "-bayonet mark " 0082 ".
S102：According to identified driving trace and the first attribute information of each bayonet obtained in advance, bayonet phase is established
Adjacent model.
As an implementation, this step can be with as shown in Fig. 2, include：
S201：Using association rule algorithm, in identified each driving trace, extraction association bayonet set, each
It includes two bayonets to be associated with bayonet set；
S202：Determine each number for being associated with two bayonets that bayonet set includes and appearing in same driving trace；
S203：According to the number, the corresponding relating attribute information of each association bayonet set is determined；
S204：Using feature extraction algorithm and/or feature selecting algorithm, first attribute information and the association are determined
The corresponding target signature data of attribute information；
S205：Using sorting algorithm, classify to the target signature data, according to classification results, establishes bayonet phase
Adjacent model.
There are many association rule algorithms, such as Apriori algorithm, frequent pattern tree (fp tree) FP-tree algorithms or FPGrowth
Etc..Using association rule algorithm, relevant bayonet can be identified in each driving trace.It is tied according to identification
Fruit, extraction association bayonet set, each bayonet set that is associated with includes two bayonets.
Lift a simply example, it is assumed that all not only included to be identified as the bayonet of " 0076 " but also comprising mark in a plurality of driving trace
For the bayonet of " 0082 ", then the two bayonets can form an association bayonet set.
Assuming that extracting following association bayonet set：{0076—0082},{0100—0105},{0210—0215},
{0300—0303}。
Determine each number for being associated with two bayonets that bayonet set includes and appearing in same driving trace.It needs to illustrate
, it includes temporal information to cross in vehicle record, and the driving trace determined can also correspond to temporal information, accordingly, it is determined that going out this
After number, it can be directed to each association bayonet set, two bayonets for including in further statistical correlation bayonet set are default
The sum of the number of same driving trace is appeared in period.
The preset time period can be one day, one week, one month etc., not limit specifically.Alternatively, can also statistical correlation
Two bayonets for including in bayonet set maximum times within a preset period of time, minimum number, number average value, number side
Difference, number are very poor etc., do not limit specifically.It can " the sum of number, maximum times, minimum number, number be average by these
Value, number variance, number are very poor " etc. data be determined as being associated with the corresponding relating attribute information of bayonet set.
In the present embodiment, the various data that attribute information includes are known as characteristic, that is to say, that above-mentioned relating attribute
The various data " the sum of number, maximum times, minimum number, number average value, number variance, number are very poor " that information includes,
It can be known as characteristic.
For example, two bayonets in { 0076-0082 } on December 11,5 days-2016 December in 2016 (one week it
It is interior) in appear in the number of same driving trace daily and be respectively：100,96,72,112,106,89,98.
It is 100+96+72+112+106+89+98=that the sum of the number of { 0076-0082 } within this week, which can be counted,
673；Can also count { 0076-0082 } within this week daily in maximum times be 112, minimum number 72, number it is average
Value is 96, and the characteristics such as other variances, very poor will not enumerate.
Using feature extraction algorithm and/or feature selecting algorithm, first attribute information and the relating attribute are determined
The corresponding target signature data of information may include：
The corresponding static attribute information of each association bayonet set is extracted from first attribute information；
Using feature extraction algorithm and/or feature selecting algorithm, the static attribute information and the relating attribute are determined
The corresponding target signature data of information.
May include the static attribute information of bayonet, static attribute letter in first attribute information of each bayonet obtained in advance
Breath may include：The corresponding track quantity of bayonet, the corresponding direction quantity of bayonet, threshold speed (the speed limit situation of bayonet setting
Under), bayonet headend equipment number, region where road type, bayonet where bayonet etc..
In the present embodiment, the corresponding static attribute information of association bayonet set can be understood as two bayonets in set
Static attribute information.In addition, according to being described above, in the present embodiment, the various data that attribute information includes are known as characteristic
According to, that is to say, that the various data that above-mentioned static attribute information includes can also be known as characteristic.
As an implementation, feature extraction algorithm can be utilized, determines static attribute information and relating attribute information
Corresponding target signature data.
There are many feature extraction algorithms, for example, main element analysis (PCA, Principal Component Analysis),
The methods of the mapping algorithms, factorial analysis such as cluster.It will be understood by those skilled in the art that static attribute information and relating attribute letter
Include various features data in breath, can there are problems that multicollinearity；Therefore, feature extraction algorithm can be utilized, to static state
Attribute information and relating attribute information carry out dimension-reduction treatment；Then, then from after dimensionality reduction static attribute information and relating attribute letter
Target signature data are determined in breath.
As another embodiment, feature selecting algorithm can be utilized, determines static attribute information and relating attribute letter
Cease corresponding target signature data.
For example, scoring sequence, root can be carried out to each characteristic in static attribute information and relating attribute information
According to ranking results, selection target characteristic.Can also utilize method of gradual regression (Stepwise regression) or other
Algorithm obtains the preferable target signature data of effect by repetition test.
As another embodiment, feature extraction algorithm and feature selecting algorithm can be utilized, determines the static category
Property information and the corresponding target signature data of the relating attribute information.
Specifically, feature extraction algorithm can be utilized, the static attribute information and the relating attribute information are carried out
Dimension-reduction treatment；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
Present embodiment combination above two embodiment determines candidate feature data first with feature extraction algorithm, then
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
Using sorting algorithm, classify to the target signature data, according to classification results, establishes the adjacent mould of bayonet
Type may include：
According to the number, the corresponding abnormal attribute information of each association bayonet set is determined；
The corresponding Regional Property information of each association bayonet set is extracted from first attribute information；
Using sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to the target signature number
According to classifying, according to classification results, bayonet consecutive phantom is established.
The abnormal attribute information may include：It crosses train number number upper quartile day, cross day and quantile, day under train number number cross vehicle
It's day pastes the number of days accounting, etc. that train number number is 0 number of days that number is 0.
According to being described above, in the present embodiment, the various data that attribute information includes are known as characteristic, that is,
It says, the various data that above-mentioned abnormal attribute information includes can also be known as characteristic.
Continue above-mentioned example, two bayonets in { 0076-0082 } are on December 11,5 days-2016 December in 2016
The number for appearing in same driving trace in (within one week) daily is respectively：100,96,72,112,106,89,98.Then
May include in { 0076-0082 } corresponding abnormal attribute information：Day train number number upper quartile is crossed to be 89, cross train number number day
Lower quantile 106, the characteristics such as to cross the number of days accounting that the number of days that train number number is 0 is 0, to cross train number number day be 0 day be 0 ....
It can also include the Regional Property information of bayonet, Regional Property in first attribute information of each bayonet obtained in advance
Information may include：Road name etc. where region name, bayonet where bayonet latitude and longitude information, bayonet.
According to being described above, in the present embodiment, the various data that attribute information includes are known as characteristic, that is,
It says, the various data that above-mentioned Regional Property information includes can also be known as characteristic.
There are many sorting algorithms, such as xgboost algorithms, SVM (Support Vector Machine, support vector machines)
Algorithm etc., does not limit specifically.
Using sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to the target signature number
According to classifying, according to classification results, bayonet consecutive phantom is established, specific modeling process may include：
Target signature data are divided into training set and test set；
Training set is trained, is trained in conjunction with abnormal attribute information and Regional Property information using sorting algorithm
Model；
Training pattern is tested using test set, according to test result, training pattern is adjusted；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
In the above process, the indexs such as accuracy rate, the recall rate of test set test training pattern can be utilized, are referred to based on these
Mark, the parameter of adjusting training model, to achieve the effect that optimize training pattern.Training pattern after can optimizing and revising determines
For bayonet consecutive phantom, training pattern can also further be adjusted, obtain bayonet consecutive phantom.
It will be understood by those skilled in the art that when being trained to training set, abnormal attribute information is combined, it can be to avoid
Some accidentalia are influenced caused by modeling process.Such as during the Spring Festival, vehicle significantly reduces in a line city, the mistake of bayonet
Train number number also significantly reduces, and bayonet consecutive phantom is established according to the car data of crossing during the Spring Festival, inevitable inaccurate.It is tied in this programme
It closes abnormal attribute information and establishes bayonet consecutive phantom, improve the accuracy of modeling.
In addition, using above-mentioned sorting algorithm, target signature data, abnormal attribute information and Regional Property letter can also be adjusted
The weight of breath further improves the accuracy of modeling.
S103：Obtain the second attribute information of two bayonets for including in bayonet group to be determined and the bayonet group.It is described
There are correspondences with first attribute information for second attribute information.
S104：Second attribute information is matched with the bayonet consecutive phantom, when successful match, determines institute
It is adjacent bayonet to state two bayonets.
According to content above, bayonet consecutive phantom is had been set up.When it needs to be determined that whether two bayonets are adjacent, execute
S103,S104.Assuming that it needs to be determined that whether bayonet 0023 is adjacent with bayonet 0036, then bayonet group to be determined is exactly { 0023-
0036 }, the second attribute information of bayonet 0023 and bayonet 0036 is obtained.
Second attribute information may include relating attribute information or static attribute information etc., in the second attribute information
Characteristic can be less than the characteristic in the first attribute information, but the second attribute information should be opposite with the first attribute information
It answers.For example, if containing bayonet headend equipment number in the first attribute information, and region name where bayonet is not included
Claim, then also should include that bayonet headend equipment is numbered in the second attribute information, cannot only include region name where bayonet.This leader
Technical staff is appreciated that bayonet consecutive phantom is built according to the first attribute information, and the second attribute information is adjacent with the bayonet
Model is matched, and therefore, the first attribute information is corresponding with the second attribute information, and matching result is just significant.
Using embodiment illustrated in fig. 1 of the present invention, the corresponding driving trace of each car plate is determined, according to the driving trace and in advance
First attribute information of each bayonet obtained, establishes bayonet consecutive phantom；When it needs to be determined that whether two bayonets are adjacent, by this
Second attribute information of two bayonets is matched with the model established, and when successful match, determines that the two bayonets are phase
Adjacent bayonet.It can be seen that this programme can determine whether two bayonets are adjacent, without the degree of association being to determine between two bayonets, carry
The high accuracy for determining adjacent bayonet.
Corresponding with above-described embodiment, the embodiment of the present invention also provides a kind of determining device of adjacent bayonet.
Fig. 3 is a kind of structural schematic diagram of the determining device of adjacent bayonet provided in an embodiment of the present invention, including：
Determining module 301 determines the corresponding driving trace of each car plate for crossing vehicle record according to pre-stored；Wherein,
It is described to cross in vehicle record comprising license board information, bayonet information, temporal information；
Module 302 is established, for the first attribute information according to identified driving trace and each bayonet obtained in advance,
Establish bayonet consecutive phantom；
Acquisition module 303, second for obtaining two bayonets for including in bayonet group to be determined and the bayonet group belongs to
Property information；There are correspondences with first attribute information for second attribute information；
Matching module 304, for second attribute information to be matched with the bayonet consecutive phantom, when matching at
When work(, determine that described two bayonets are adjacent bayonet.
In the present embodiment, module 302 is established, may include：Extracting sub-module, the first determination sub-module, second determine son
Module, third determination sub-module and setting up submodule (not shown), wherein
Extracting sub-module, for utilizing association rule algorithm, in identified each driving trace, extraction association bayonet
Set, each bayonet set that is associated with includes two bayonets；
First determination sub-module, for determining that two bayonets that each association bayonet set includes appear in same traveling
The number of track；
Second determination sub-module, for according to the number, determining the corresponding relating attribute letter of each association bayonet set
Breath；
Third determination sub-module determines first attribute for utilizing feature extraction algorithm and/or feature selecting algorithm
Information and the corresponding target signature data of the relating attribute information；
Setting up submodule classifies to the target signature data for utilizing sorting algorithm, according to classification results,
Establish bayonet consecutive phantom.
In the present embodiment, the third determination sub-module may include：
First extraction unit belongs to for extracting the corresponding static state of each association bayonet set from first attribute information
Property information；
First determination unit determines the static attribute letter for utilizing feature extraction algorithm and/or feature selecting algorithm
Breath and the corresponding target signature data of the relating attribute information.
In the present embodiment, first determination unit specifically can be used for：
Using feature extraction algorithm, dimension-reduction treatment is carried out to the static attribute information and the relating attribute information；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
In the present embodiment, the setting up submodule may include：
Second determination unit, for according to the number, determining the corresponding abnormal attribute information of each association bayonet set；
Second extraction unit belongs to for extracting the corresponding region of each association bayonet set from first attribute information
Property information；
Unit is established, for utilizing sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to institute
It states target signature data to classify, according to classification results, establishes bayonet consecutive phantom.
It is described to establish unit in the present embodiment, specifically it can be used for：
The target signature data are divided into training set and test set；
The training set is carried out in conjunction with the abnormal attribute information and the Regional Property information using sorting algorithm
Training, obtains training pattern；
The training pattern is tested using the test set, according to test result, the training pattern is carried out
Adjustment；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
Using embodiment illustrated in fig. 3 of the present invention, the corresponding driving trace of each car plate is determined, according to the driving trace and in advance
First attribute information of each bayonet obtained, establishes bayonet consecutive phantom；When it needs to be determined that whether two bayonets are adjacent, by this
Second attribute information of two bayonets is matched with the model established, and when successful match, determines that the two bayonets are phase
Adjacent bayonet.It can be seen that this programme can determine whether two bayonets are adjacent, without the degree of association being to determine between two bayonets, carry
The high accuracy for determining adjacent bayonet.
It should be noted that herein, relational terms such as first and second and the like are used merely to a reality
Body or operation are distinguished with another entity or operation, are deposited without necessarily requiring or implying between these entities or operation
In any actual relationship or order or sequence.Moreover, the terms "include", "comprise" or its any other variant are intended to
Non-exclusive inclusion, so that the process, method, article or equipment including a series of elements is not only wanted including those
Element, but also include other elements that are not explicitly listed, or further include for this process, method, article or equipment
Intrinsic element.In the absence of more restrictions, the element limited by sentence "including a ...", it is not excluded that
There is also other identical elements in process, method, article or equipment including the element.
Each embodiment in this specification is all made of relevant mode and describes, identical similar portion between each embodiment
Point just to refer each other, and each embodiment focuses on the differences from other embodiments.Especially for device reality
For applying example, since it is substantially similar to the method embodiment, so description is fairly simple, related place is referring to embodiment of the method
Part explanation.
One of ordinary skill in the art will appreciate that all or part of step in realization above method embodiment is can
It is completed with instructing relevant hardware by program, the program can be stored in computer read/write memory medium,
The storage medium designated herein obtained, such as：ROM/RAM, magnetic disc, CD etc..
The foregoing is merely illustrative of the preferred embodiments of the present invention, is not intended to limit the scope of the present invention.It is all
Any modification, equivalent replacement, improvement and so within the spirit and principles in the present invention, are all contained in protection scope of the present invention
It is interior.
Claims (12)
1. a kind of determination method of adjacent bayonet, which is characterized in that including：
Vehicle record is crossed according to pre-stored, determines the corresponding driving trace of each car plate；Wherein, described cross in vehicle record includes vehicle
Board information, bayonet information, temporal information；
According to identified driving trace and the first attribute information of each bayonet obtained in advance, bayonet consecutive phantom is established；
Obtain the second attribute information of two bayonets for including in bayonet group to be determined and the bayonet group；The second attribute letter
There are correspondences with first attribute information for breath；
Second attribute information is matched with the bayonet consecutive phantom, when successful match, determines described two cards
Mouth is adjacent bayonet.
2. according to the method described in claim 1, it is characterized in that, driving trace determined by the basis and obtaining in advance
First attribute information of each bayonet, the step of establishing bayonet consecutive phantom, including：
Using association rule algorithm, in identified each driving trace, extraction association bayonet set is each to be associated with bayonet collection
It includes two bayonets to close；
Determine each number for being associated with two bayonets that bayonet set includes and appearing in same driving trace；
According to the number, the corresponding relating attribute information of each association bayonet set is determined；
Using feature extraction algorithm and/or feature selecting algorithm, first attribute information and the relating attribute information are determined
Corresponding target signature data；
Using sorting algorithm, classify to the target signature data, according to classification results, establishes bayonet consecutive phantom.
3. according to the method described in claim 2, it is characterized in that, described calculated using feature extraction algorithm and/or feature selecting
Method, the step of determining first attribute information and the relating attribute information corresponding target signature data, including：
The corresponding static attribute information of each association bayonet set is extracted from first attribute information；
Using feature extraction algorithm and/or feature selecting algorithm, the static attribute information and the relating attribute information are determined
Corresponding target signature data.
4. according to the method described in claim 3, it is characterized in that, it is described utilize feature extraction algorithm and feature selecting algorithm,
The step of determining the static attribute information and the relating attribute information corresponding target signature data, including：
Using feature extraction algorithm, dimension-reduction treatment is carried out to the static attribute information and the relating attribute information；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
5. according to the method described in claim 4, it is characterized in that, described utilize sorting algorithm, to the target signature data
Classify, according to classification results, the step of establishing bayonet consecutive phantom, including：
According to the number, the corresponding abnormal attribute information of each association bayonet set is determined；
The corresponding Regional Property information of each association bayonet set is extracted from first attribute information；
Using sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to the target signature data into
Row classification, according to classification results, establishes bayonet consecutive phantom.
6. according to the method described in claim 5, it is characterized in that, described utilize sorting algorithm, in conjunction with abnormal attribute letter
Breath and the Regional Property information, classify to the target signature data, according to classification results, establish bayonet consecutive phantom
The step of, including：
The target signature data are divided into training set and test set；
The training set is trained in conjunction with the abnormal attribute information and the Regional Property information using sorting algorithm,
Obtain training pattern；
The training pattern is tested using the test set, according to test result, the training pattern is adjusted；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
7. a kind of determining device of adjacent bayonet, which is characterized in that including：
Determining module determines the corresponding driving trace of each car plate for crossing vehicle record according to pre-stored；Wherein, the mistake
Include license board information, bayonet information, temporal information in vehicle record；
Module is established, for the first attribute information according to identified driving trace and each bayonet obtained in advance, establishes card
Mouth consecutive phantom；
Acquisition module, the second attribute information for obtaining two bayonets for including in bayonet group to be determined and the bayonet group；
There are correspondences with first attribute information for second attribute information；
Matching module, for matching second attribute information with the bayonet consecutive phantom, when successful match, really
Fixed described two bayonets are adjacent bayonet.
8. device according to claim 7, which is characterized in that it is described to establish module, including：
Extracting sub-module, for utilizing association rule algorithm, in identified each driving trace, extraction association bayonet collection
It closes, each bayonet set that is associated with includes two bayonets；
First determination sub-module, for determining that two bayonets that each association bayonet set includes appear in same driving trace
Number；
Second determination sub-module, for according to the number, determining the corresponding relating attribute information of each association bayonet set；
Third determination sub-module determines first attribute information for utilizing feature extraction algorithm and/or feature selecting algorithm
And the corresponding target signature data of the relating attribute information；
Setting up submodule is classified to the target signature data, according to classification results, is established for utilizing sorting algorithm
Bayonet consecutive phantom.
9. device according to claim 8, which is characterized in that the third determination sub-module, including：
First extraction unit, for extracting the corresponding static attribute letter of each association bayonet set from first attribute information
Breath；
First determination unit, for utilize feature extraction algorithm and/or feature selecting algorithm, determine the static attribute information and
The corresponding target signature data of the relating attribute information.
10. device according to claim 9, which is characterized in that first determination unit is specifically used for：
Using feature extraction algorithm, dimension-reduction treatment is carried out to the static attribute information and the relating attribute information；
From after dimension-reduction treatment static attribute information and relating attribute information in, determine candidate feature data；
Using feature selecting algorithm, the selection target characteristic from candidate feature data.
11. device according to claim 10, which is characterized in that the setting up submodule, including：
Second determination unit, for according to the number, determining the corresponding abnormal attribute information of each association bayonet set；
Second extraction unit, for extracting the corresponding Regional Property letter of each association bayonet set from first attribute information
Breath；
Unit is established, for utilizing sorting algorithm, in conjunction with the abnormal attribute information and the Regional Property information, to the mesh
Mark characteristic is classified, and according to classification results, establishes bayonet consecutive phantom.
12. according to the devices described in claim 11, which is characterized in that it is described to establish unit, it is specifically used for：
The target signature data are divided into training set and test set；
The training set is trained in conjunction with the abnormal attribute information and the Regional Property information using sorting algorithm,
Obtain training pattern；
The training pattern is tested using the test set, according to test result, the training pattern is adjusted；
According to the training pattern after adjustment, bayonet consecutive phantom is established.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281279.9A CN108805312B (en) | 2017-04-26 | 2017-04-26 | Method and device for determining adjacent bayonets |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710281279.9A CN108805312B (en) | 2017-04-26 | 2017-04-26 | Method and device for determining adjacent bayonets |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN108805312A true CN108805312A (en) | 2018-11-13 |
| CN108805312B CN108805312B (en) | 2020-09-18 |
Family
ID=64068835
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710281279.9A Active CN108805312B (en) | 2017-04-26 | 2017-04-26 | Method and device for determining adjacent bayonets |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108805312B (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584553A (en) * | 2018-11-29 | 2019-04-05 | 中电海康集团有限公司 | A kind of section degree of association missing complementing method based on space time information |
| CN111161120A (en) * | 2019-12-20 | 2020-05-15 | 华为技术有限公司 | Bayonet position determining method and bayonet management device |
| CN111369790A (en) * | 2019-10-16 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle passing record correction method, device, equipment and storage medium |
| CN112013865A (en) * | 2020-08-28 | 2020-12-01 | 北京百度网讯科技有限公司 | Method, system, electronic device and medium for determining traffic gate |
| CN116386336A (en) * | 2023-05-29 | 2023-07-04 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103366566A (en) * | 2013-06-25 | 2013-10-23 | 中国科学院信息工程研究所 | Running track prediction method aiming at specific vehicle potential group |
| US20140247159A1 (en) * | 2011-06-27 | 2014-09-04 | Stc, Inc. | Signal Light Priority System Utilizing Estimated Time of Arrival |
| CN104537210A (en) * | 2014-12-09 | 2015-04-22 | 深圳市华仁达技术有限公司 | Automatic-search fake plate time threshold value configuration algorithm based on adjacent gates |
| CN104732765A (en) * | 2015-03-30 | 2015-06-24 | 杭州电子科技大学 | Real-time urban road saturability monitoring method based on checkpoint data |
| CN104916129A (en) * | 2015-05-05 | 2015-09-16 | 杭州电子科技大学 | Method for calculating real-time traffic speed of road based on large-scale data about vehicles passing through gates |
-
2017
- 2017-04-26 CN CN201710281279.9A patent/CN108805312B/en active Active
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20140247159A1 (en) * | 2011-06-27 | 2014-09-04 | Stc, Inc. | Signal Light Priority System Utilizing Estimated Time of Arrival |
| CN103366566A (en) * | 2013-06-25 | 2013-10-23 | 中国科学院信息工程研究所 | Running track prediction method aiming at specific vehicle potential group |
| CN104537210A (en) * | 2014-12-09 | 2015-04-22 | 深圳市华仁达技术有限公司 | Automatic-search fake plate time threshold value configuration algorithm based on adjacent gates |
| CN104732765A (en) * | 2015-03-30 | 2015-06-24 | 杭州电子科技大学 | Real-time urban road saturability monitoring method based on checkpoint data |
| CN104916129A (en) * | 2015-05-05 | 2015-09-16 | 杭州电子科技大学 | Method for calculating real-time traffic speed of road based on large-scale data about vehicles passing through gates |
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584553A (en) * | 2018-11-29 | 2019-04-05 | 中电海康集团有限公司 | A kind of section degree of association missing complementing method based on space time information |
| CN111369790A (en) * | 2019-10-16 | 2020-07-03 | 杭州海康威视系统技术有限公司 | Vehicle passing record correction method, device, equipment and storage medium |
| CN111369790B (en) * | 2019-10-16 | 2021-11-09 | 杭州海康威视系统技术有限公司 | Vehicle passing record correction method, device, equipment and storage medium |
| CN111161120A (en) * | 2019-12-20 | 2020-05-15 | 华为技术有限公司 | Bayonet position determining method and bayonet management device |
| CN112013865A (en) * | 2020-08-28 | 2020-12-01 | 北京百度网讯科技有限公司 | Method, system, electronic device and medium for determining traffic gate |
| CN112013865B (en) * | 2020-08-28 | 2022-08-30 | 北京百度网讯科技有限公司 | Method, system, electronic device and medium for determining traffic gate |
| CN116386336A (en) * | 2023-05-29 | 2023-07-04 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
| CN116386336B (en) * | 2023-05-29 | 2023-08-08 | 四川国蓝中天环境科技集团有限公司 | Road network traffic flow robust calculation method and system based on bayonet license plate data |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108805312B (en) | 2020-09-18 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805312A (en) | A kind of determination method and device of adjacent bayonet | |
| CN108765131A (en) | Credit authorization method, apparatus, terminal and readable storage medium storing program for executing based on micro- expression | |
| CN108764710A (en) | Evaluation Method of Teaching Quality and device | |
| CN109800320A (en) | A kind of image processing method, equipment and computer readable storage medium | |
| CN107133265A (en) | A kind of method and device of identification behavior abnormal user | |
| CN107862862B (en) | Vehicle behavior analysis method and device | |
| CN106653001A (en) | Baby crying identifying method and system | |
| CN104850663A (en) | System and method for inputting and analyzing test scores | |
| CN104252627A (en) | SVM (support vector machine) classifier training sample acquiring method, training method and training system | |
| CN108731691A (en) | The determination method and apparatus of the yaw point of navigation equipment | |
| CN106874943A (en) | Business object sorting technique and system | |
| CN109509087A (en) | Intelligentized loan checking method, device, equipment and medium | |
| CN110059952A (en) | Vehicle insurance methods of risk assessment, device, equipment and storage medium | |
| CN109697447A (en) | Disaggregated model construction device, method and electronic equipment based on random forest | |
| CN109710240A (en) | Flow chart decomposition method and system | |
| CN108304852A (en) | The determination method, apparatus and storage medium of road section type, electronic device | |
| US20180053072A1 (en) | Verification device, verification method, and verification program | |
| CN109874104A (en) | User location localization method, device, equipment and medium | |
| CN108182444A (en) | The method and device of video quality diagnosis based on scene classification | |
| CN106777350A (en) | It is a kind of based on bayonet socket data scheming to search drawing method and device | |
| CN101299762A (en) | Identification authentication method and apparatus | |
| CN111414930B (en) | Deep learning model training method and device, electronic equipment and storage medium | |
| CN102339341B (en) | Method for automatically controlling extraction precision of parasitic parameters during physical layout simulation | |
| CN107194352A (en) | A kind of pedestrian counting method of video monitoring, apparatus and system | |
| CN110309737A (en) | A kind of information processing method applied to cigarette sales counter, apparatus and system |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant |