CN108805312B - Method and device for determining adjacent bayonets - Google Patents
Method and device for determining adjacent bayonets Download PDFInfo
- Publication number
- CN108805312B CN108805312B CN201710281279.9A CN201710281279A CN108805312B CN 108805312 B CN108805312 B CN 108805312B CN 201710281279 A CN201710281279 A CN 201710281279A CN 108805312 B CN108805312 B CN 108805312B
- Authority
- CN
- China
- Prior art keywords
- attribute information
- bayonet
- determining
- bayonets
- algorithm
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
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 method and a device for determining adjacent gates, which are used for determining a driving track corresponding to each license plate and establishing a gate adjacent model according to the driving track and first attribute information of each gate acquired in advance; and when the two bayonets are required to be determined to be adjacent, matching the second attribute information of the two bayonets with the established model, and when the matching is successful, determining that the two bayonets are adjacent. Therefore, the scheme can determine whether the two bayonets are adjacent instead of determining the association degree between the two bayonets, and the accuracy of determining the adjacent bayonets is improved.
Description
Technical Field
The invention belongs to the technical field of data processing, and particularly relates to a method and a device for determining adjacent bayonets.
Background
At present, vehicles are more and more, traffic bayonets are more and more in roads, and traffic conditions are more and more complicated. In a complex traffic condition, it is usually necessary to determine adjacent gates to facilitate the route selection of vehicles or the statistical arrangement of traffic data by related departments.
In the existing scheme, the association degree between bayonets can be determined, but the association degree can only reflect the probability that bayonets are possibly adjacent, and cannot accurately reflect whether bayonets are adjacent or not.
Disclosure of Invention
The embodiment of the invention aims to provide a method and a device for determining adjacent bayonets, which can improve the accuracy of determining the adjacent bayonets.
In order to achieve the above object, an embodiment of the present invention discloses a method for determining adjacent bayonets, including:
determining a driving track corresponding to each license plate according to a pre-stored vehicle passing record; the vehicle passing record comprises license plate information, checkpoint information and time information;
establishing a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet;
acquiring a bayonet group to be determined and second attribute information of two bayonets contained in the bayonet group; the second attribute information and the first attribute information have a corresponding relation;
and matching the second attribute information with the bayonet adjacent models, and determining that the two bayonets are adjacent bayonets when the matching is successful.
Optionally, the step of establishing a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet may include:
extracting association bayonet sets in each determined driving track by using an association rule algorithm, wherein each association bayonet set comprises two bayonets;
determining the times of two bayonets contained in each associated bayonet set appearing in the same driving track;
determining the associated attribute information corresponding to each associated bayonet set according to the times;
determining the first attribute information and target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm;
and classifying the target characteristic data by using a classification algorithm, and establishing a bayonet adjacent model according to a classification result.
Optionally, the step of determining the first attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm may include:
extracting static attribute information corresponding to each associated bayonet set from the first attribute information;
and determining the static attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm.
Optionally, the step of determining the static attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and a feature selection algorithm may include:
performing dimension reduction processing on the static attribute information and the associated attribute information by using a feature extraction algorithm;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
Optionally, the step of classifying the target feature data by using a classification algorithm and establishing a bayonet adjacent model according to a classification result may include:
determining abnormal attribute information corresponding to each associated bayonet set according to the times;
extracting region attribute information corresponding to each associated bayonet set from the first attribute information;
and classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
Optionally, the step of classifying the target feature data by using a classification algorithm in combination with the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result may include:
dividing the target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to a test result;
and establishing a bayonet adjacent model according to the adjusted training model.
In order to achieve the above object, an embodiment of the present invention further discloses a device for determining adjacent bayonets, including:
the determining module is used for determining the corresponding driving track of each license plate according to the pre-stored vehicle passing record; the vehicle passing record comprises license plate information, checkpoint information and time information;
the building module is used for building a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet;
the acquisition module is used for acquiring a bayonet group to be determined and second attribute information of two bayonets contained in the bayonet group; the second attribute information and the first attribute information have a corresponding relation;
and the matching module is used for matching the second attribute information with the bayonet adjacent model, and when the matching is successful, the two bayonets are determined to be adjacent bayonets.
Optionally, the establishing module may include:
the extraction submodule is used for extracting association bayonet sets in each determined driving track by utilizing an association rule algorithm, and each association bayonet set comprises two bayonets;
the first determining submodule is used for determining the times of two checkpoints contained in each associated checkpoint set appearing in the same driving track;
the second determining submodule is used for determining the associated attribute information corresponding to each associated bayonet set according to the times;
a third determining submodule, configured to determine, by using a feature extraction algorithm and/or a feature selection algorithm, target feature data corresponding to the first attribute information and the associated attribute information;
and the establishing submodule is used for classifying the target characteristic data by utilizing a classification algorithm and establishing a bayonet adjacent model according to a classification result.
Optionally, the third determining sub-module may include:
a first extracting unit, configured to extract static attribute information corresponding to each associated bayonet set from the first attribute information;
and the first determining unit is used for determining the static attribute information and the target feature data corresponding to the associated attribute information by utilizing a feature extraction algorithm and/or a feature selection algorithm.
Optionally, the first determining unit may be specifically configured to:
performing dimension reduction processing on the static attribute information and the associated attribute information by using a feature extraction algorithm;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
Optionally, the establishing sub-module may include:
the second determining unit is used for determining the abnormal attribute information corresponding to each associated bayonet set according to the times;
a second extracting unit, configured to extract region attribute information corresponding to each associated bayonet set from the first attribute information;
and the establishing unit is used for classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
Optionally, the establishing unit may be specifically configured to:
dividing the target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to a test result;
and establishing a bayonet adjacent model according to the adjusted training model.
By applying the embodiment of the invention, the driving track corresponding to each license plate is determined, and the bayonet adjacent model is established according to the driving track and the pre-acquired first attribute information of each bayonet; and when the two bayonets are required to be determined to be adjacent, matching the second attribute information of the two bayonets with the established model, and when the matching is successful, determining that the two bayonets are adjacent. Therefore, the scheme can determine whether the two bayonets are adjacent instead of determining the association degree between the two bayonets, and the accuracy of determining the adjacent bayonets is improved.
Of course, it is not necessary for any product or method of practicing the invention to achieve all of the above-described advantages at the same time.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below, it is obvious that the drawings in the following description are only some embodiments of the present invention, and for those skilled in the art, other drawings can be obtained according to the drawings without creative efforts.
Fig. 1 is a schematic flowchart of a method for determining adjacent gates according to an embodiment of the present invention;
fig. 2 is a schematic flow chart of establishing a bayonet adjacent model according to an embodiment of the present invention;
fig. 3 is a schematic structural diagram of a device for determining adjacent bayonets according to an embodiment of the present invention.
Detailed Description
The technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention, and it is obvious that the described embodiments are only a part of the embodiments of the present invention, and not all of the embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
In order to solve the foregoing technical problems, embodiments of the present invention provide a method and an apparatus for determining adjacent bayonets, which can be applied to various electronic devices, and are not limited specifically.
First, a method for determining adjacent bayonets provided in an embodiment of the present invention is described in detail below.
Fig. 1 is a schematic flow chart of a method for determining an adjacent bayonet according to an embodiment of the present invention, including:
s101: and determining the corresponding driving track of each license plate according to the pre-stored vehicle passing record. The vehicle passing record comprises license plate information, checkpoint information and time information.
For example, the pre-stored vehicle passing record includes the following contents:
1. license plate-Jing A00000, bayonet mark-0067, elapsed time 2016, 12 months, 1 days 9: 40;
2. license plate-Jing A00000, bayonet mark-0065, elapsed time 2016, 12 months, 1 day 9: 00;
3. license plate-Jing A00000, bayonet mark-0076, elapsed time 2016, 12 months, 1 day 10: 20;
4. license plate-Jing A00000, bayonet identification-0082, elapsed time 2016, 12 months, 1 day 11: 30, of a nitrogen-containing gas;
……
the vehicle passing record comprises license plate information, checkpoint information and time information, so that the driving track corresponding to each license plate can be determined according to the vehicle passing record. For example, according to the above contents, the driving trajectory corresponding to the license plate "jing a 00000" can be determined: bayonet identification "0065" -bayonet identification "0067" -bayonet identification "0076" -bayonet identification "0082".
S102: and establishing a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet.
As an embodiment, this step may be as shown in fig. 2, and includes:
s201: extracting association bayonet sets in each determined driving track by using an association rule algorithm, wherein each association bayonet set comprises two bayonets;
s202: determining the times of two bayonets contained in each associated bayonet set appearing in the same driving track;
s203: determining the associated attribute information corresponding to each associated bayonet set according to the times;
s204: determining the first attribute information and target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm;
s205: and classifying the target characteristic data by using a classification algorithm, and establishing a bayonet adjacent model according to a classification result.
There are many association rule algorithms, such as Apriori algorithm, frequent pattern tree FP-tree algorithm or FPGrowth, etc. By utilizing the association rule algorithm, the gate with the association relation can be identified in each driving track. And extracting associated bayonet sets according to the recognition result, wherein each associated bayonet set comprises two bayonets.
For a simple example, assuming that a plurality of driving trajectories include both a bayonet labeled "0076" and a bayonet labeled "0082", the two bayonets may form an associated bayonet set.
Assume that the following set of associated checkpoints is extracted: { 0076-0082 }, { 0100-0105 }, { 0210-0215 }, and { 0300-0303 }.
And determining the times of the two bayonets contained in each associated bayonet set appearing in the same driving track. It should be noted that the vehicle passing record includes time information, and the determined travel track may also correspond to the time information, so after the number of times is determined, for each associated bayonet set, the sum of the number of times that two bayonets included in the associated bayonet set appear in the same travel track within a preset time period may be further counted.
The preset time period may be one day, one week, one month, etc., and is not particularly limited. Or, the maximum number, the minimum number, the average number, the variance of the number, the extreme difference of the number, and the like of the two checkpoints included in the associated checkpoint set in a preset time period may be counted, which is not limited specifically. These data such as "the sum of times, the maximum times, the minimum times, the average of times, the variance of times, the range of times" can be determined as the associated attribute information corresponding to the associated bayonet set.
In the present embodiment, various data included in the attribute information is referred to as feature data, that is, various data included in the related attribute information, such as "sum of times, maximum times, minimum times, average of times, variance of times, and range of times" may be referred to as feature data.
For example, the number of times that two checkpoints in { 0076-0082 } appear in the same driving track every day in 2016 (within one week) 12 and 5 days in 2016 (12 and 11 days in 2016 (one week)) is respectively: 100. 96, 72, 112, 106, 89, 98.
The sum of the times of { 0076-0082 } in the week is 100+96+72+112+106+89+98 as 673; it can also be counted that { 0076-0082 } in this week the maximum number is 112, the minimum number is 72, the average number is 96, and the other variance, range and other characteristic data are not listed.
Determining the first attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm, which may include:
extracting static attribute information corresponding to each associated bayonet set from the first attribute information;
and determining the static attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm.
The pre-acquired first attribute information of each card port may include static attribute information of the card port, and the static attribute information may include: the number of lanes corresponding to the bayonets, the number of directions corresponding to the bayonets, a speed threshold set by the bayonets (under the condition of speed limitation), the serial number of equipment at the front ends of the bayonets, the types of roads where the bayonets are located, the regions where the bayonets are located and the like.
In this embodiment, the static attribute information corresponding to the associated bayonet set may be understood as the static attribute information of two bayonets in the set. In addition, according to the above description, in the present embodiment, various data included in the attribute information is referred to as feature data, that is, various data included in the above-described static attribute information may also be referred to as feature data.
As an implementation manner, the target feature data corresponding to the static attribute information and the associated attribute information may be determined by using a feature extraction algorithm.
There are various feature extraction algorithms, such as a Principal Component Analysis (PCA), a clustering and other mapping algorithm, a factor Analysis and other methods. Those skilled in the art can understand that the static attribute information and the associated attribute information contain various feature data, and a problem of multiple collinearity exists; therefore, the static attribute information and the associated attribute information can be subjected to dimension reduction by using a feature extraction algorithm; and then, determining target characteristic data from the static attribute information and the associated attribute information after dimension reduction.
As another implementation, the target feature data corresponding to the static attribute information and the associated attribute information may be determined by using a feature selection algorithm.
For example, the scoring order may be performed on each feature data in the static attribute information and the associated attribute information, and the target feature data may be selected according to the ranking result. Or a Stepwise regression method (Stepwise regression) or other algorithms may be used to obtain target feature data with better effect through trial and error.
As another implementation, a feature extraction algorithm and a feature selection algorithm may be used to determine the static attribute information and the target feature data corresponding to the associated attribute information.
Specifically, a feature extraction algorithm may be used to perform dimension reduction processing on the static attribute information and the associated attribute information;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
In the present embodiment, in combination with the above two embodiments, the feature extraction algorithm is used to determine candidate feature data, and then the feature selection algorithm is used to select target feature data from the candidate feature data.
Classifying the target characteristic data by using a classification algorithm, and establishing a bayonet adjacent model according to a classification result, wherein the method comprises the following steps:
determining abnormal attribute information corresponding to each associated bayonet set according to the times;
extracting region attribute information corresponding to each associated bayonet set from the first attribute information;
and classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
The abnormality attribute information may include: quartiles on number of vehicle passes daily, deciles under number of vehicle passes daily, days with number of vehicle passes daily of 0, and the like.
According to the above description, in the present embodiment, various data included in the attribute information is referred to as feature data, that is, various data included in the above-described abnormality attribute information may also be referred to as feature data.
Continuing with the above example, the number of times that two checkpoints in { 0076-0082 } appear in the same driving trajectory every day in 2016 (12/5/2016) -12/11/2016 (within one week) is: 100. 96, 72, 112, 106, 89, 98. Then, the exception attribute information corresponding to { 0076-0082 } may include: the upper quartile of the number of the passing days is 89, the lower quartile of the number of the passing days is 106, the number of the passing days is 0, the proportion of the number of the passing days is 0, and the ratio of the number of the passing days is 0 … ….
The first attribute information of each bayonet acquired in advance may further include region attribute information of the bayonet, and the region attribute information may include: the longitude and latitude information of the bayonet, the name of the region where the bayonet is located, the name of the road where the bayonet is located and the like.
In the above description, in the present embodiment, various data included in the attribute information is referred to as feature data, that is, various data included in the region attribute information may be referred to as feature data.
There are various classification algorithms, such as an xgboost algorithm, an SVM (Support Vector Machine) algorithm, and the like, and the classification algorithm is not limited specifically.
Classifying the target feature data by using a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result, wherein the specific modeling process can comprise the following steps:
dividing target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to the test result;
and establishing a bayonet adjacent model according to the adjusted training model.
In the process, the test set can be used for testing indexes such as accuracy and recall rate of the training model, and parameters of the training model are adjusted based on the indexes so as to achieve the effect of optimizing the training model. The training model after optimization and adjustment can be determined as a bayonet adjacent model, and the training model can be further adjusted to obtain the bayonet adjacent model.
As can be understood by those skilled in the art, when the training set is trained, the abnormal attribute information is combined, so that the influence of some accidental factors on the modeling process can be avoided. For example, in the spring festival, vehicles in a first-line city are obviously reduced, the vehicle passing times of the gate are also obviously reduced, and the gate adjacent model is established according to the vehicle passing data in the spring festival, so that the accuracy is inevitably inaccurate. According to the scheme, the bayonet adjacent model is established by combining the abnormal attribute information, so that the modeling accuracy is improved.
In addition, by utilizing the classification algorithm, the weights of the target characteristic data, the abnormal attribute information and the region attribute information can be adjusted, and the modeling accuracy is further improved.
S103: and acquiring a bayonet group to be determined and second attribute information of two bayonets contained in the bayonet group. The second attribute information and the first attribute information have a corresponding relationship.
S104: and matching the second attribute information with the bayonet adjacent models, and determining that the two bayonets are adjacent bayonets when the matching is successful.
From the above, a bayonet neighbor model has been established. And executing S103 and S104 when the two bayonets are adjacent to each other. If it is required to determine whether the bayonet 0023 and the bayonet 0036 are adjacent, the group of bayonets to be determined is { 0023-0036 }, and second attribute information of the bayonet 0023 and the bayonet 0036 is obtained.
The second attribute information may include associated attribute information, static attribute information, or the like, and the feature data in the second attribute information may be less than the feature data in the first attribute information, but the second attribute information should correspond to the first attribute information. For example, if the first attribute information includes the card front-end device number but does not include the name of the area where the card is located, the second attribute information should also include the card front-end device number and cannot include only the name of the area where the card is located. Those skilled in the art can understand that the bayonet adjacent model is constructed according to the first attribute information, and the second attribute information is matched with the bayonet adjacent model, so that the first attribute information corresponds to the second attribute information, and the matching result is meaningful.
By applying the embodiment shown in fig. 1 of the invention, the driving track corresponding to each license plate is determined, and a bayonet adjacent model is established according to the driving track and the pre-acquired first attribute information of each bayonet; and when the two bayonets are required to be determined to be adjacent, matching the second attribute information of the two bayonets with the established model, and when the matching is successful, determining that the two bayonets are adjacent. Therefore, the scheme can determine whether the two bayonets are adjacent instead of determining the association degree between the two bayonets, and the accuracy of determining the adjacent bayonets is improved.
Corresponding to the above embodiments, the embodiments of the present invention further provide a device for determining adjacent bayonets.
Fig. 3 is a schematic structural diagram of a device for determining adjacent bayonets, provided in an embodiment of the present invention, including:
the determining module 301 is configured to determine a driving track corresponding to each license plate according to a pre-stored vehicle passing record; the vehicle passing record comprises license plate information, checkpoint information and time information;
the establishing module 302 is configured to establish a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet;
an obtaining module 303, configured to obtain a bayonet group to be determined and second attribute information of two bayonets included in the bayonet group; the second attribute information and the first attribute information have a corresponding relation;
a matching module 304, configured to match the second attribute information with the bayonet adjacent model, and when matching is successful, determine that the two bayonets are adjacent bayonets.
In this embodiment, the establishing module 302 may include: an extraction sub-module, a first determination sub-module, a second determination sub-module, a third determination sub-module, and a creation sub-module (not shown in the figure), wherein,
the extraction submodule is used for extracting association bayonet sets in each determined driving track by utilizing an association rule algorithm, and each association bayonet set comprises two bayonets;
the first determining submodule is used for determining the times of two checkpoints contained in each associated checkpoint set appearing in the same driving track;
the second determining submodule is used for determining the associated attribute information corresponding to each associated bayonet set according to the times;
a third determining submodule, configured to determine, by using a feature extraction algorithm and/or a feature selection algorithm, target feature data corresponding to the first attribute information and the associated attribute information;
and the establishing submodule is used for classifying the target characteristic data by utilizing a classification algorithm and establishing a bayonet adjacent model according to a classification result.
In this embodiment, the third determining sub-module may include:
a first extracting unit, configured to extract static attribute information corresponding to each associated bayonet set from the first attribute information;
and the first determining unit is used for determining the static attribute information and the target feature data corresponding to the associated attribute information by utilizing a feature extraction algorithm and/or a feature selection algorithm.
In this embodiment, the first determining unit may be specifically configured to:
performing dimension reduction processing on the static attribute information and the associated attribute information by using a feature extraction algorithm;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
In this embodiment, the establishing sub-module may include:
the second determining unit is used for determining the abnormal attribute information corresponding to each associated bayonet set according to the times;
a second extracting unit, configured to extract region attribute information corresponding to each associated bayonet set from the first attribute information;
and the establishing unit is used for classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
In this embodiment, the establishing unit may be specifically configured to:
dividing the target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to a test result;
and establishing a bayonet adjacent model according to the adjusted training model.
By applying the embodiment shown in fig. 3 of the invention, the driving track corresponding to each license plate is determined, and a bayonet adjacent model is established according to the driving track and the pre-acquired first attribute information of each bayonet; and when the two bayonets are required to be determined to be adjacent, matching the second attribute information of the two bayonets with the established model, and when the matching is successful, determining that the two bayonets are adjacent. Therefore, the scheme can determine whether the two bayonets are adjacent instead of determining the association degree between the two bayonets, and the accuracy of determining the adjacent bayonets is improved.
It is noted that, herein, relational terms such as first and second, and the like may be used solely to distinguish one entity or action from another entity or action without necessarily requiring or implying any actual such relationship or order between such entities or actions. Also, the terms "comprises," "comprising," or any other variation thereof, are intended to cover a non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements does not include only those elements but may include other elements not expressly listed or inherent to such process, method, article, or apparatus. Without further limitation, an element defined by the phrase "comprising an … …" does not exclude the presence of other identical elements in a process, method, article, or apparatus that comprises the element.
All the embodiments in the present specification are described in a related manner, and the same and similar parts among the embodiments may be referred to each other, and each embodiment focuses on the differences from the other embodiments. In particular, as for the apparatus embodiment, since it is substantially similar to the method embodiment, the description is relatively simple, and for the relevant points, reference may be made to the partial description of the method embodiment.
Those skilled in the art will appreciate that all or part of the steps in the above method embodiments may be implemented by a program to instruct relevant hardware to perform the steps, and the program may be stored in a computer-readable storage medium, which is referred to herein as a storage medium, such as: ROM/RAM, magnetic disk, optical disk, etc.
The above description is only for the preferred embodiment of the present invention, and is not intended to limit the scope of the present invention. Any modification, equivalent replacement, or improvement made within the spirit and principle of the present invention shall fall within the protection scope of the present invention.
Claims (10)
1. A method of determining adjacent bayonets, comprising:
determining a driving track corresponding to each license plate according to a pre-stored vehicle passing record; the vehicle passing record comprises license plate information, checkpoint information and time information;
establishing a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet;
acquiring a bayonet group to be determined and second attribute information of two bayonets contained in the bayonet group; the second attribute information and the first attribute information have a corresponding relation;
matching the second attribute information with the bayonet adjacent models, and determining the two bayonets as adjacent bayonets when the matching is successful;
the step of establishing a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet comprises the following steps:
extracting association bayonet sets in each determined driving track by using an association rule algorithm, wherein each association bayonet set comprises two bayonets;
determining the times of two bayonets contained in each associated bayonet set appearing in the same driving track;
determining the associated attribute information corresponding to each associated bayonet set according to the times;
determining the first attribute information and target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm;
and classifying the target characteristic data by using a classification algorithm, and establishing a bayonet adjacent model according to a classification result.
2. The method according to claim 1, wherein the step of determining the target feature data corresponding to the first attribute information and the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm comprises:
extracting static attribute information corresponding to each associated bayonet set from the first attribute information;
and determining the static attribute information and the target feature data corresponding to the associated attribute information by using a feature extraction algorithm and/or a feature selection algorithm.
3. The method according to claim 2, wherein the step of determining the target feature data corresponding to the static attribute information and the associated attribute information by using a feature extraction algorithm and a feature selection algorithm comprises:
performing dimension reduction processing on the static attribute information and the associated attribute information by using a feature extraction algorithm;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
4. The method according to claim 3, wherein the step of classifying the target feature data by using a classification algorithm and establishing a bayonet adjacent model according to the classification result comprises:
determining abnormal attribute information corresponding to each associated bayonet set according to the times;
extracting region attribute information corresponding to each associated bayonet set from the first attribute information;
and classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
5. The method according to claim 4, wherein the step of classifying the target feature data by using a classification algorithm in combination with the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result includes:
dividing the target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to a test result;
and establishing a bayonet adjacent model according to the adjusted training model.
6. An apparatus for determining adjacent bayonets, comprising:
the determining module is used for determining the corresponding driving track of each license plate according to the pre-stored vehicle passing record; the vehicle passing record comprises license plate information, checkpoint information and time information;
the building module is used for building a bayonet adjacent model according to the determined driving track and the pre-acquired first attribute information of each bayonet;
the acquisition module is used for acquiring a bayonet group to be determined and second attribute information of two bayonets contained in the bayonet group; the second attribute information and the first attribute information have a corresponding relation;
the matching module is used for matching the second attribute information with the bayonet adjacent models, and when the matching is successful, the two bayonets are determined to be adjacent bayonets;
wherein the establishing module comprises:
the extraction submodule is used for extracting association bayonet sets in each determined driving track by utilizing an association rule algorithm, and each association bayonet set comprises two bayonets;
the first determining submodule is used for determining the times of two checkpoints contained in each associated checkpoint set appearing in the same driving track;
the second determining submodule is used for determining the associated attribute information corresponding to each associated bayonet set according to the times;
a third determining submodule, configured to determine, by using a feature extraction algorithm and/or a feature selection algorithm, target feature data corresponding to the first attribute information and the associated attribute information;
and the establishing submodule is used for classifying the target characteristic data by utilizing a classification algorithm and establishing a bayonet adjacent model according to a classification result.
7. The apparatus of claim 6, wherein the third determining submodule comprises:
a first extracting unit, configured to extract static attribute information corresponding to each associated bayonet set from the first attribute information;
and the first determining unit is used for determining the static attribute information and the target feature data corresponding to the associated attribute information by utilizing a feature extraction algorithm and/or a feature selection algorithm.
8. The apparatus according to claim 7, wherein the first determining unit is specifically configured to:
performing dimension reduction processing on the static attribute information and the associated attribute information by using a feature extraction algorithm;
determining candidate feature data from the static attribute information and the associated attribute information after the dimension reduction processing;
and selecting target characteristic data from the candidate characteristic data by utilizing a characteristic selection algorithm.
9. The apparatus of claim 8, wherein the build submodule comprises:
the second determining unit is used for determining the abnormal attribute information corresponding to each associated bayonet set according to the times;
a second extracting unit, configured to extract region attribute information corresponding to each associated bayonet set from the first attribute information;
and the establishing unit is used for classifying the target characteristic data by utilizing a classification algorithm and combining the abnormal attribute information and the region attribute information, and establishing a bayonet adjacent model according to a classification result.
10. The apparatus according to claim 9, wherein the establishing unit is specifically configured to:
dividing the target characteristic data into a training set and a test set;
training the training set by using a classification algorithm and combining the abnormal attribute information and the region attribute information to obtain a training model;
testing the training model by using the test set, and adjusting the training model according to a test result;
and establishing a bayonet adjacent model according to the adjusted training model.
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 CN108805312A (en) | 2018-11-13 |
| CN108805312B true 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) |
Families Citing this family (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584553B (en) * | 2018-11-29 | 2020-09-22 | 浙江海康智联科技有限公司 | Road section relevance missing completion method based on space-time information |
| 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 |
| CN111161120B (en) * | 2019-12-20 | 2023-06-20 | 华为技术有限公司 | Bayonet position determining method and bayonet management device |
| 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 |
| 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 |
Citations (4)
| 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 |
| 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 |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US8878695B2 (en) * | 2011-06-27 | 2014-11-04 | Stc, Inc. | Signal light priority system utilizing estimated time of arrival |
-
2017
- 2017-04-26 CN CN201710281279.9A patent/CN108805312B/en active Active
Patent Citations (4)
| 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 |
| 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 |
Also Published As
| Publication number | Publication date |
|---|---|
| CN108805312A (en) | 2018-11-13 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108805312B (en) | Method and device for determining adjacent bayonets | |
| CN108073923B (en) | License plate correction method and device | |
| Miao et al. | A semi-automatic method for road centerline extraction from VHR images | |
| CN107862862B (en) | Vehicle behavior analysis method and device | |
| US20130132166A1 (en) | Smart toll network for improving performance of vehicle identification systems | |
| CN111126224A (en) | Vehicle detection method and classification recognition model training method | |
| CN106156767A (en) | Driving license effect duration extraction method, server and terminal | |
| CN106126751A (en) | A kind of sorting technique with time availability and device | |
| CN104156734A (en) | Fully-autonomous on-line study method based on random fern classifier | |
| Meedech et al. | Prediction of student dropout using personal profile and data mining approach | |
| CN103617429A (en) | Sorting method and system for active learning | |
| CN110502982A (en) | The method, apparatus and computer equipment of barrier in a kind of detection highway | |
| CN110728198B (en) | Image processing method and device, electronic equipment and readable storage medium | |
| CN104615986A (en) | Method for utilizing multiple detectors to conduct pedestrian detection on video images of scene change | |
| CN111400533B (en) | Image screening method, device, electronic equipment and storage medium | |
| CN104199840A (en) | Intelligent placename recognition technology based on statistical model | |
| CN104063713A (en) | Semi-autonomous on-line studying method based on random fern classifier | |
| CN106843941A (en) | Information processing method, device and computer equipment | |
| AU2017261601A1 (en) | Intelligent automatic license plate recognition for electronic tolling environments | |
| CN106023159A (en) | Disease spot image segmentation method and system for greenhouse vegetable leaf | |
| CN110866734A (en) | Intelligent recruitment method and system based on deep learning | |
| CN111210321B (en) | Risk early warning method and system based on contract management | |
| US9953238B2 (en) | Image processing method and system for extracting distorted circular image elements | |
| CN104978569A (en) | Sparse representation based incremental face recognition method | |
| CN111325255B (en) | Specific crowd delineating method and device, electronic equipment and storage medium |
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 |