CN116935625B - Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles - Google Patents
Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles Download PDFInfo
- Publication number
- CN116935625B CN116935625B CN202310650657.1A CN202310650657A CN116935625B CN 116935625 B CN116935625 B CN 116935625B CN 202310650657 A CN202310650657 A CN 202310650657A CN 116935625 B CN116935625 B CN 116935625B
- Authority
- CN
- China
- Prior art keywords
- illegal
- provincial
- vehicle
- data
- inter
- 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
- 230000006399 behavior Effects 0.000 title claims abstract description 116
- 238000001514 detection method Methods 0.000 title claims abstract description 17
- 238000000034 method Methods 0.000 claims abstract description 49
- 238000012549 training Methods 0.000 claims abstract description 49
- 238000012795 verification Methods 0.000 claims abstract description 18
- 238000012545 processing Methods 0.000 claims abstract description 17
- 238000013480 data collection Methods 0.000 claims abstract description 4
- 238000005457 optimization Methods 0.000 claims abstract description 4
- 230000008569 process Effects 0.000 claims description 19
- 238000002790 cross-validation Methods 0.000 claims description 14
- 238000007619 statistical method Methods 0.000 claims description 13
- 238000009826 distribution Methods 0.000 claims description 11
- 239000013598 vector Substances 0.000 claims description 10
- 230000009471 action Effects 0.000 claims description 9
- 238000010200 validation analysis Methods 0.000 claims description 9
- 238000012544 monitoring process Methods 0.000 claims description 8
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000011156 evaluation Methods 0.000 claims description 6
- 230000006870 function Effects 0.000 claims description 6
- 238000007781 pre-processing Methods 0.000 claims description 5
- 238000004458 analytical method Methods 0.000 claims description 4
- 230000003542 behavioural effect Effects 0.000 claims description 3
- 238000004422 calculation algorithm Methods 0.000 claims description 3
- 238000007621 cluster analysis Methods 0.000 claims description 3
- 238000013135 deep learning Methods 0.000 claims description 3
- 230000010354 integration Effects 0.000 claims description 3
- 238000012417 linear regression Methods 0.000 claims description 3
- 238000007477 logistic regression Methods 0.000 claims description 3
- 239000000463 material Substances 0.000 claims description 3
- 238000002360 preparation method Methods 0.000 claims description 3
- 238000007637 random forest analysis Methods 0.000 claims description 3
- 238000012216 screening Methods 0.000 claims description 3
- 238000012706 support-vector machine Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 3
- 238000006243 chemical reaction Methods 0.000 claims description 2
- 238000004140 cleaning Methods 0.000 claims description 2
- 230000000694 effects Effects 0.000 description 11
- 238000005516 engineering process Methods 0.000 description 4
- 238000000605 extraction Methods 0.000 description 4
- 230000009286 beneficial effect Effects 0.000 description 3
- 238000007418 data mining Methods 0.000 description 3
- 238000010586 diagram Methods 0.000 description 3
- 238000007689 inspection Methods 0.000 description 3
- 230000004075 alteration Effects 0.000 description 1
- 238000010276 construction Methods 0.000 description 1
- 238000007405 data analysis Methods 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000035945 sensitivity Effects 0.000 description 1
- 238000005728 strengthening Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0125—Traffic data processing
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/24—Querying
- G06F16/245—Query processing
- G06F16/2458—Special types of queries, e.g. statistical queries, fuzzy queries or distributed queries
- G06F16/2462—Approximate or statistical queries
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/211—Selection of the most significant subset of features
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/213—Feature extraction, e.g. by transforming the feature space; Summarisation; Mappings, e.g. subspace methods
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
- G06F18/2148—Generating training patterns; Bootstrap methods, e.g. bagging or boosting characterised by the process organisation or structure, e.g. boosting cascade
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24323—Tree-organised classifiers
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/27—Regression, e.g. linear or logistic regression
-
- 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
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/26—Government or public services
-
- Y—GENERAL TAGGING OF NEW TECHNOLOGICAL DEVELOPMENTS; GENERAL TAGGING OF CROSS-SECTIONAL TECHNOLOGIES SPANNING OVER SEVERAL SECTIONS OF THE IPC; TECHNICAL SUBJECTS COVERED BY FORMER USPC CROSS-REFERENCE ART COLLECTIONS [XRACs] AND DIGESTS
- Y02—TECHNOLOGIES OR APPLICATIONS FOR MITIGATION OR ADAPTATION AGAINST CLIMATE CHANGE
- Y02T—CLIMATE CHANGE MITIGATION TECHNOLOGIES RELATED TO TRANSPORTATION
- Y02T10/00—Road transport of goods or passengers
- Y02T10/10—Internal combustion engine [ICE] based vehicles
- Y02T10/40—Engine management systems
Abstract
The invention provides an intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic operation vehicles, which comprises the steps of firstly, data collection and pretreatment; step two, extracting and processing the characteristics of the preprocessed data; step three, constructing a gradient lifting tree model, and performing model training; step four, model verification and optimization; fifthly, identifying illegal behaviors of illegal inter-provincial passenger transport operation vehicles; and step six, collecting and processing illegal behavior evidence. The method realizes automatic identification and early warning of illegal behaviors of illegal inter-provincial passenger traffic vehicles.
Description
Technical Field
The invention belongs to the field of traffic management and big data analysis, in particular to an intelligent detection method for illegal behaviors of illegal provincial passenger traffic management vehicles based on ETC data and historical administrative punishment case information, which belongs to the field of digital modeling of highway infrastructure, and particularly relates to an intelligent detection method for illegal behaviors of illegal provincial passenger traffic management vehicles.
Background
The prior illegal behavior recognition technology of illegal inter-provincial passenger traffic vehicles (without obtaining road passenger traffic operation permission and without conducting road passenger traffic operation) mainly relies on manual inspection and monitoring video snapshot. These methods have certain limitations such as high labor cost, limited accuracy, insufficient real-time performance, etc. In addition, the prior art has limited capability for processing and analyzing large-scale vehicle data, and is difficult to meet the real-time monitoring and preventing requirements for illegal behaviors of illegal inter-provincial passenger traffic vehicles.
Aiming at the defects of the prior art, the invention provides an intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles. The method is based on data mining and machine learning technologies and is an illegal behavior identification method of illegal provincial passenger traffic operation vehicles. The method utilizes rich ETC traffic data, historical administrative punishment case information and other data sources, and realizes automatic identification and early warning of illegal behaviors of illegal inter-provincial passenger traffic vehicles through steps of feature extraction and processing, model training and verification and the like.
Disclosure of Invention
The invention provides an intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles. The method utilizes rich ETC traffic data, historical administrative punishment case information and other data sources, and realizes automatic identification and early warning of illegal behaviors of illegal inter-provincial passenger traffic vehicles through steps of feature extraction and processing, model training and verification and the like.
In order to solve the technical problems, the invention provides an intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles, which comprises the following steps:
step one, data collection and pretreatment; collecting data, and preprocessing the collected data;
step two, extracting and processing the characteristics of the preprocessed data;
step three, constructing a gradient lifting tree model, and performing model training;
step four, model verification and optimization;
the method comprises the steps of evaluating the performance of a gradient lifting tree machine learning model by applying a k-fold cross validation method; optimizing the super parameters of the gradient lifting tree model by using a grid search method, and finding out the optimal parameter combination;
fifthly, identifying illegal behaviors of illegal inter-provincial passenger transport operation vehicles;
predicting a new vehicle feature vector by using the trained gradient lifting tree model to obtain a prediction result; setting a threshold value, and judging that the vehicle has illegal behaviors of the inter-provincial black passenger transport vehicle when the prediction result exceeds the threshold value;
step six, collecting and processing illegal behavior evidence;
the method comprises the steps of capturing traffic data and monitoring video of the vehicle and collecting the data; when illegal behaviors are found, notifying a traffic management department or a company to which the vehicle belongs to take measures; and carrying out statistical analysis on the illegal behaviors.
Optionally, the first step includes,
1.1 The method comprises the steps of periodically or real-timely collecting related data from each data source, wherein the related data comprise historical administrative penalty case information, ETC traffic data and vehicle information, and the ETC traffic data comprise date and time, a high-speed entrance, a high-speed exit and high-speed portal longitude and latitude;
1.2 Preprocessing the collected data, including data cleaning, data integration and missing value processing.
Optionally, the second step includes,
2.1 Key features are extracted from the preprocessed data and are classified into the following categories:
a. travel track characteristics: according to the longitude and latitude data of the high-speed portal, calculating the running track of the vehicle on the expressway, and carrying out cluster analysis;
b. travel time characteristics: calculating the driving time of each vehicle on the expressway and the driving time duty ratio in a specific time period;
c. travel speed characteristics: calculating the skewness and kurtosis of the average speed, the highest speed, the lowest speed and the speed distribution of the vehicle;
d. high-speed access information features: analyzing high-speed inlet and outlet data of each vehicle, and counting frequency, conversion frequency and time interval;
e. historical illicit behavioral characteristics: counting the historical illegal action times, illegal type distribution and illegal action occurrence time and place of each vehicle;
f. temporal and spatial characteristics: extracting the passing characteristics of vehicles in different time periods and geographic positions;
2.2 Characteristic weight setting, namely using LASO regression as a characteristic selection algorithm, wherein the LASO regression is an extension of linear regression, and regularization terms are added into a loss function, so that the LASO regression can perform characteristic selection in a fitting process; by optimizing regularization parameters of LASSO regression, a proper parameter value is found, so that the model only maintains the characteristics with larger influence on target variables, and further, characteristic screening is realized;
the loss function is as follows:
，
wherein,nis the number of samples, representing the number of vehicles;pis the number of features, representing the number of extracted vehicle travel features;y i is the firstiTarget variable of each sample, representing the firstiWhether the vehicle is illegal or not, wheni=0 indicates illegal behavior of the illegal passenger traffic vehicle without province,i=1 represents illegal behavior of an illegal inter-provincial passenger traffic vehicle;
x ij is the firstiSample numberjAnd the characteristic is represented by the firstiVehicle NojA plurality of travel characteristics;
β j is the firstjRegression coefficient of each feature, representing the firstjThe influence of individual characteristics on illegal behaviors of illegal inter-provincial passenger transport operation vehicles;
αis a regularization parameter used to control the complexity of the model and the degree of feature selection;
2.3 Determining a target, wherein in the process of selecting the characteristics, the target is to screen out the characteristics which have the most influence on the illegal behavior identification of the illegal inter-provincial passenger traffic operation vehicles; using known illegal inter-provincial passenger traffic vehicle illegal behavior data as training data, wherein the illegal behavior data comprises characteristics and corresponding labels; for LASSO regression, a target variable is set to be a two-class variable, 0 represents illegal behaviors of illegal passenger traffic management vehicles without province, 1 represents illegal behaviors of illegal passenger traffic management vehicles with province, and the characteristics correspond to the characteristics extracted in the step two;
2.4 After performing feature selection by using LASSO regression, the obtained model parameters, namely regression coefficients, are used as feature weights; the feature weight reflects the relative importance of each feature in illegal behavior identification of illegal inter-provincial passenger traffic vehicles; the feature weights are distributed according to regression coefficients of features in LASSO regression; for the characteristic with larger regression coefficient, the method is considered to have larger influence on the illegal behavior identification of the illegal inter-provincial passenger traffic operation vehicle.
Optionally, the third step comprises,
3.1 Data preparation: using known illegal inter-provincial passenger traffic vehicle illegal behavior data as a training set, and matching the screened feature vectors with corresponding labels to determine whether the feature vectors are illegal inter-provincial passenger traffic vehicle illegal behaviors or not; dividing the data set into a training set and a verification set so as to evaluate the performance of the model in the training process;
3.2 Model initialization: selecting a gradient lifting tree model as a classifier, and setting initial parameters according to the characteristics of the problems, wherein the parameters comprise the number of trees, the maximum depth of the trees and the learning rate;
3.3 Characteristic weight: according to the feature weights obtained in the step two, weighting each feature in the training process of the gradient lifting tree model;
3.4 Model training: training the gradient lifting tree model by using a training set; during the training process, the performance of the model on the validation set is monitored and the training error and validation error for each iteration are recorded.
Optionally, the fourth step comprises,
4.1 Applying k-fold cross validation: evaluating the performance of the gradient lifting tree model by using a k-fold cross validation method; k-fold cross validation allows comprehensive assessment of models without sacrificing data set size, thereby improving the recognition accuracy of illegal inter-provincial passenger traffic vehicles;
4.1.1 dividing known illegal inter-provincial passenger traffic vehicle illegal behavior data into k subsets;
4.1.2 In k iterations, selecting one subset as a verification set each time, and the rest subsets as training sets, and training the gradient lifting tree model by using the training sets;
4.1.3 Evaluating the performance of the model on a verification set, and recording performance indexes such as accuracy, recall rate, F1 score and the like; this process is repeated k times so that each subset is used as a validation set;
4.1.4 Calculating the average performance index of k iterations as an evaluation result of the gradient lifting tree model;
4.2 Applying a grid search: optimizing the super parameters of the gradient lifting tree model by using a grid searching method; grid search operation systematically traverses all possible super-parameter combinations to find the optimal parameter combination, thereby improving the prediction precision and stability of the model;
4.2.1 Determining a super-parameter search space of the gradient lifting tree model; setting a series of possible value ranges so as to traverse the parameter combinations in the grid search process;
4.2.2 For each hyper-parameter combination, evaluating model performance using the k-fold cross-validation in step 4.1; calculating the average performance index of k iterations as an evaluation result of the current super-parameter combination;
4.2.3 traversing all the super-parameter combinations to find the super-parameter combination with optimal performance;
4.2.4 training the gradient lifting tree model by using the optimal super-parameter combination and utilizing the whole known illegal inter-provincial passenger traffic vehicle illegal behavior data set; the model has higher accuracy and generalization capability.
Optionally, the fifth step comprises,
5.1 Model prediction: predicting a new vehicle feature vector by using the trained gradient lifting tree model to obtain a prediction result; the prediction result is the probability that each sample belongs to illegal behaviors of illegal provincial passenger traffic management vehicles;
5.2 Threshold setting: setting a threshold value, and judging that illegal behaviors of illegal inter-provincial passenger traffic operation vehicles exist in the vehicles when the prediction result exceeds the threshold value; and setting a threshold value according to the performance of the model on the training set and the verification set and adjusting the actual requirement of illegal behavior of the illegal inter-provincial passenger traffic operation vehicle.
Optionally, the step six includes,
6.1 Evidence collection: after judging that the illegal inter-provincial passenger traffic operation illegal behaviors exist in the vehicle, carrying out snapshot and evidence collection of the illegal behaviors based on ETC traffic data and surrounding monitoring videos of the vehicle;
6.2 Evidence arrangement: ETC entrance and exit data, ETC portal traffic data, historical administrative punishment case information and the like of the vehicle are extracted and used as evidence materials of illegal provincial passenger traffic operation illegal behaviors; the evidence is sorted and classified, so that convenience is provided for subsequent punishment and analysis;
6.3 Illegal action notification: when the illegal inter-provincial passenger traffic operation illegal behaviors of the vehicles are found, immediately informing a traffic management department or a company to which the vehicles belong to take corresponding measures;
6.4 Statistical analysis: and carrying out statistical analysis on the illegal behaviors, and optimizing a traffic management strategy according to the statistical analysis result.
Optionally, the gradient lifting tree model in the third step may be replaced by one or a combination of several of random forest, logistic regression, support vector machine and deep learning.
Through the method, the invention has the following technical effects:
(1) Accuracy rate is improved: the invention utilizes LASSO regression to select the characteristics with larger influence on the illegal behavior identification of illegal inter-provincial passenger traffic vehicles, and improves the prediction accuracy of the model. Meanwhile, classification is carried out by utilizing a gradient lifting tree (GBT) model, so that the recognition accuracy of illegal behaviors of illegal inter-provincial passenger traffic vehicles is further improved.
(2) Real-time enhancement: by collecting and processing each data source in real time, the invention can identify potential illegal inter-provincial passenger traffic vehicle illegal behaviors in real time, provide real-time early warning information for traffic management departments, and improve the impact strength on the illegal inter-provincial passenger traffic vehicle illegal behaviors.
(3) The labor cost is reduced: the invention realizes the automatic identification of illegal behaviors of illegal inter-provincial passenger traffic operation vehicles, reduces the requirement of manual inspection and reduces the labor cost.
(4) Providing decision support: the invention carries out statistical analysis on the illegal behaviors, including the types of the illegal behaviors, time distribution, geographical position distribution and the like, provides decision support for traffic management departments, is beneficial to optimizing traffic management strategies and improves treatment effects.
(5) Scalability: the data mining and machine learning technology adopted by the invention has good expandability, and can integrate new data sources and features according to requirements, thereby further improving the illegal behavior recognition effect of illegal passenger traffic vehicles.
Drawings
In order to make the technical problems solved by the present invention, the technical means adopted and the technical effects achieved more clear, specific embodiments of the present invention will be described in detail below with reference to the accompanying drawings. It should be noted, however, that the drawings described below are merely illustrative of exemplary embodiments of the present invention and that other embodiments of the drawings may be derived from these drawings by those skilled in the art without undue effort.
FIG. 1 is an overall flow chart of an intelligent detection method for illegal behaviors of an illegal mass transit vehicle according to the present invention;
FIG. 2 is a flow chart of the feature extraction and processing procedure in the second step of the present invention;
FIG. 3 is a flow chart of a machine learning model of the present invention;
Detailed Description
For a clearer understanding of the technical features, objects, and effects of the present invention, exemplary embodiments of the present invention will now be described more fully with reference to the accompanying drawings. While the exemplary embodiments may be embodied in many specific forms, the present invention should not be construed as limited to the embodiments set forth herein. Rather, these exemplary embodiments are provided so that this disclosure will be thorough and complete, and will fully convey the concept of the invention to those skilled in the art.
The structures, capabilities, effects, or other features described in a particular embodiment may be incorporated in one or more other embodiments in any suitable manner without departing from the spirit of the present invention.
In describing particular embodiments, specific details of construction, performance, effects, or other features are set forth in order to provide a thorough understanding of the embodiments by those skilled in the art. It is not excluded, however, that one skilled in the art may implement the present invention in a particular situation in a solution that does not include the structures, properties, effects, or other characteristics described above.
The flow diagrams in the figures are merely exemplary flow illustrations and do not represent that all of the elements, operations, and steps in the flow diagrams must be included in the aspects of the invention, nor that the steps must be performed in the order shown in the figures. For example, some of the operations/steps in the flowcharts may be broken down, some of the operations/steps may be combined or partially combined, and so forth. The order of execution shown in the flowcharts may be changed according to actual situations without departing from the gist of the present invention.
The block diagrams in the figures generally represent functional entities and do not necessarily correspond to physically separate entities. That is, the functional entities may be implemented in software, or in one or more hardware modules or integrated circuits, or in different networks and/or processor devices and/or microcontroller devices.
The same reference numerals in the drawings denote the same or similar elements, components or portions, and thus repeated descriptions of the same or similar elements, components or portions may be omitted hereinafter. It will be further understood that, although the terms first, second, third, etc. may be used herein to describe various devices, elements, components or portions, these devices, elements, components or portions should not be limited by these terms. That is, these phrases are merely intended to distinguish one from the other. For example, a first device may also be referred to as a second device without departing from the spirit of the invention. Furthermore, the term "and/or," "and/or" is meant to include all combinations of any one or more of the items listed.
The invention provides an intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles (road passenger traffic operation permission is not obtained and road passenger traffic operation is not performed by unauthorized persons), which is shown in fig. 1-2 and comprises the following steps:
step one, data collection and preprocessing
1.1 Related data including historical administrative penalty case information, ETC traffic data (including date and time, high speed entry, high speed exit, high speed portal latitude and longitude, etc.), and vehicle information, etc. are collected periodically or in real time from various data sources.
1.2 The collected data is preprocessed, including data cleansing, data integration, and missing value processing, for subsequent analysis.
Step two, feature extraction and processing
2.1 Key features are extracted from the preprocessed data and are classified into the following categories:
a. travel track characteristics: and calculating the running track of the vehicle on the expressway according to the longitude and latitude data of the high-speed portal, and performing cluster analysis.
b. Travel time characteristics: and calculating the driving time of each vehicle on the expressway and the driving time duty ratio in a specific time period.
c. Travel speed characteristics: the average speed, highest speed, lowest speed, and skewness and kurtosis of the speed profile of the vehicle are calculated.
d. High-speed access information features: the high speed ingress and egress data for each vehicle is analyzed, and the frequency, switching frequency and time interval are counted.
e. Historical illicit behavioral characteristics: and counting the historical illegal action times, illegal type distribution and the time and place of illegal action occurrence of each vehicle.
f. Temporal and spatial characteristics: the traffic characteristics of the vehicle in different time periods and geographic positions are extracted.
2.2 Feature weight setting, LASSO regression (Least Absolute Shrinkage and Selection Operator) was used as the feature selection algorithm. LASSO regression is an extension of linear regression, which adds regularization terms (L1 regularization) to the loss function, which enables feature selection during fitting. By optimizing regularization parameters of LASSO regression, a proper parameter value is found, so that the model only maintains the characteristics with larger influence on the target variable, and the characteristic screening is realized.
The loss function is as follows:
，
nis the number of samples, representing the number of vehicles;pis the number of features, representing the number of extracted vehicle travel features;y i is the firstiTarget variable of each sample, representing the firstiWhether the vehicle is illegal act of illegal provincial passenger operation vehicle (0 represents illegal act of illegal provincial passenger operation vehicle, 1 represents illegal act of illegal provincial passenger operation vehicle);
x ij is the firstiSample numberjAnd the characteristic is represented by the firstiVehicle NojA plurality of travel characteristics;
β j is the firstjRegression coefficient of each feature, representing the firstjThe influence of individual characteristics on illegal behaviors of illegal inter-provincial passenger transport operation vehicles;
αis a regularization parameter used to control the complexity of the model and the degree of feature selection.
2.3 In the process of feature selection, the method aims to screen out the features which have the most influence on illegal behavior identification of illegal inter-provincial passenger traffic vehicles. Known illegal inter-provincial passenger vehicle offence data (including features and corresponding tags) are used as training data. For LASSO regression, a target variable is set with a two-class variable (0 represents illegal behavior of illegal passenger traffic management vehicles without province, 1 represents illegal behavior of illegal passenger traffic management vehicles without province), and the characteristics correspond to the characteristics extracted in the step two.
2.4 After feature selection using LASSO regression, the obtained model parameters (regression coefficients) are used as feature weights. These weights reflect the relative importance of the various features in the identification of illegal behaviors of illegally provincial passenger traffic vehicles. Feature weights may be assigned according to regression coefficients of features in LASSO regression. For the characteristic with larger regression coefficient, the method is considered to have larger influence on the illegal behavior identification of the illegal inter-provincial passenger traffic operation vehicle.
As shown in fig. 3, the machine learning model flow specifically includes:
step three, training a gradient lifting tree (GBT) model
3.1 Data preparation: using known illegal inter-provincial passenger traffic vehicle illegal behavior data as a training set, and matching the screened feature vector with a corresponding tag (whether the illegal inter-provincial passenger traffic vehicle illegal behavior is or not). The data set is divided into a training set and a validation set to evaluate model performance during the training process.
3.2 Model initialization: GBT is selected as a classifier, and initial parameters are set according to the characteristics of the problem. These parameters include the number of trees, the maximum depth of the tree, the learning rate, etc.
3.3 Characteristic weight: and (3) weighting each feature in the GBT model training process according to the feature weight obtained in the step two. This helps to increase the sensitivity of the model to important features, thereby increasing prediction accuracy.
3.4 Model training: the GBT model is trained using a training set. During the training process, the performance of the model on the validation set is monitored and the training error and validation error for each iteration are recorded.
The gradient lifting tree model in the third step can be replaced by one or a combination of a plurality of random forests, logistic regression, support vector machines and deep learning. Other models are selected, and the effect of intelligent detection of illegal behaviors of illegal inter-provincial passenger traffic vehicles can be achieved.
Step four, model verification and optimization
4.1 Applying k-fold cross validation: the performance of the GBT model was evaluated using a k-fold cross-validation method. k-fold cross-validation allows for comprehensive assessment of models without sacrificing data set size, thereby improving the accuracy of unauthorized road passenger vehicle identification without gaining road passenger permission.
4.1.1 dividing known illegal inter-provincial passenger vehicle offence data (including features and corresponding tags) into k subsets.
4.1.2 In k iterations, one subset is selected at a time as the validation set and the remaining subsets are selected as training sets. The GBT model is trained using a training set.
4.1.3 And evaluating the performance of the model on the verification set, and recording performance indexes such as accuracy, recall rate, F1 score and the like. This process is repeated k times so that each subset is used as a validation set.
4.1.4 And calculating the average performance index of k iterations as an evaluation result of the GBT model.
4.2 Applying a grid search: and optimizing the super parameters of the GBT model by using a grid search method. Grid searching can help systematically traverse all possible hyper-parameter combinations to find the best parameter combination, thereby improving the prediction accuracy and stability of the model.
4.2.1 A hyper-parametric search space of the GBT model is determined, such as the number of trees, the depth of the trees, the learning rate, etc. A series of possible value ranges are set to traverse these parameter combinations during the grid search.
4.2.2 For each hyper-parameter combination, model performance was assessed using k-fold cross-validation in step 4.1. And calculating the average performance index of k iterations to be used as an evaluation result of the current super-parameter combination.
And 4.2.3 traversing all the super-parameter combinations to find the super-parameter combination with the optimal performance.
4.2.4 training the GBT model by using the optimal super-parameter combination and utilizing the whole known illegal inter-provincial passenger traffic vehicle illegal behavior data set. This will allow a model with higher accuracy and generalization capability.
Step five, illegal behavior identification of illegal inter-provincial passenger transport operation vehicles
5.1 Model prediction: and predicting the new vehicle feature vector by using the trained GBT model to obtain a prediction result. The prediction result is the probability that each sample belongs to illegal behaviors of illegal provincial passenger traffic management vehicles.
5.2 Threshold setting: setting a threshold value, and judging that the vehicle has illegal behaviors of illegally provincial passenger traffic operation vehicles when the prediction result exceeds the threshold value. The threshold value can be set according to the performance of the model on the training set and the verification set, and the actual requirements of illegal behaviors of illegal inter-provincial passenger traffic vehicles can be adjusted.
Step six, collecting and processing illegal behavior evidence
6.1 Evidence collection: after the illegal inter-provincial passenger traffic operation illegal behaviors of the vehicle are judged, snapshot and evidence collection of the illegal behaviors are carried out based on ETC traffic data and surrounding monitoring videos of the vehicle.
6.2 Evidence arrangement: ETC entrance and exit data, ETC portal traffic data, historical administrative penalty case information and the like of the vehicle are extracted and used as evidence materials of illegal provincial passenger traffic operation illegal behaviors. The evidence is sorted and categorized to facilitate subsequent penalties and analysis.
6.3 Illegal action notification: when the illegal province passenger traffic operation illegal behavior exists in the vehicle, the traffic management department or the company to which the vehicle belongs is immediately informed to take corresponding measures such as fine and the like.
6.4 Statistical analysis: and carrying out statistical analysis on the illegal behaviors, including the types, time distribution, geographical position distribution and the like of the illegal behaviors, and providing decision support for traffic management departments. According to the statistical analysis result, optimizing the traffic management strategy, such as strengthening the patrol intensity of certain areas or time periods, and improving the hit intensity of illegal provincial passenger traffic operation illegal behaviors.
In summary, the intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles can achieve the following beneficial effects:
(1) Accuracy rate is improved: the invention utilizes LASSO regression to select the characteristics with larger influence on the illegal behavior identification of illegal inter-provincial passenger traffic vehicles, and improves the prediction accuracy of the model. Meanwhile, classification is carried out by utilizing a gradient lifting tree (GBT) model, so that the recognition accuracy of illegal behaviors of illegal inter-provincial passenger traffic vehicles is further improved.
(2) Real-time enhancement: by collecting and processing each data source in real time, the invention can identify potential illegal inter-provincial passenger traffic vehicle illegal behaviors in real time, provide real-time early warning information for traffic management departments, and improve the impact strength on the illegal inter-provincial passenger traffic vehicle illegal behaviors.
(3) The labor cost is reduced: the invention realizes the automatic identification of illegal behaviors of illegal inter-provincial passenger traffic operation vehicles, reduces the requirement of manual inspection and reduces the labor cost.
(4) Providing decision support: the invention carries out statistical analysis on the illegal behaviors, including the types of the illegal behaviors, time distribution, geographical position distribution and the like, provides decision support for traffic management departments, is beneficial to optimizing traffic management strategies and improves treatment effects.
(5) Scalability: the data mining and machine learning technology adopted by the invention has good expandability, and can integrate new data sources and features according to requirements, thereby further improving the illegal behavior recognition effect of illegal passenger traffic vehicles.
The foregoing description and drawings are merely illustrative of the present invention and are not intended to limit the scope of the invention, as it is understood by those skilled in the art that the description as a whole is given for clarity. Any equivalent alterations, modifications and combinations thereof will be effected by those skilled in the art without departing from the spirit and principles of this invention, and it is intended to be within the scope of the invention.
Claims (5)
1. An intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles is characterized by comprising the following steps:
step one, data collection and pretreatment; collecting data, and preprocessing the collected data;
step two, extracting and processing the characteristics of the preprocessed data;
step three, constructing a gradient lifting tree model, and performing model training;
step four, model verification and optimization;
the method comprises the steps of evaluating the performance of a gradient lifting tree machine learning model by applying a k-fold cross validation method; optimizing the super parameters of the gradient lifting tree model by using a grid search method, and finding out the optimal parameter combination;
fifthly, identifying illegal behaviors of illegal inter-provincial passenger transport operation vehicles;
predicting a new vehicle feature vector by using the trained gradient lifting tree model to obtain a prediction result; setting a threshold value, and judging that the vehicle has illegal behaviors of the inter-provincial black passenger transport vehicle when the prediction result exceeds the threshold value;
step six, collecting and processing illegal behavior evidence;
the method comprises the steps of capturing traffic data and monitoring video of the vehicle and collecting the data; when illegal behaviors are found, notifying a traffic management department or a company to which the vehicle belongs to take measures; carrying out statistical analysis on illegal behaviors;
wherein, the second step comprises the steps of,
2.1 Key features are extracted from the preprocessed data and are classified into the following categories:
a. travel track characteristics: according to the longitude and latitude data of the high-speed portal, calculating the running track of the vehicle on the expressway, and carrying out cluster analysis;
b. travel time characteristics: calculating the driving time of each vehicle on the expressway and the driving time duty ratio in a specific time period;
c. travel speed characteristics: calculating the skewness and kurtosis of the average speed, the highest speed, the lowest speed and the speed distribution of the vehicle;
d. high-speed access information features: analyzing high-speed inlet and outlet data of each vehicle, and counting frequency, conversion frequency and time interval;
e. historical illicit behavioral characteristics: counting the historical illegal action times, illegal type distribution and illegal action occurrence time and place of each vehicle;
f. temporal and spatial characteristics: extracting the passing characteristics of vehicles in different time periods and geographic positions;
2.2 Characteristic weight setting, namely using LASO regression as a characteristic selection algorithm, wherein the LASO regression is an extension of linear regression, and regularization terms are added into a loss function, so that the LASO regression can perform characteristic selection in a fitting process; by optimizing regularization parameters of LASSO regression, a proper parameter value is found, so that the model only maintains the characteristics with larger influence on target variables, and further, characteristic screening is realized;
the loss function is as follows:
；
wherein,nis the number of samples, representing the number of vehicles;pis the number of features representing the extracted vehicle travelThe number of features;y i is the firstiTarget variable of each sample, representing the firstiWhether the vehicle is illegal or not, wheni=0 indicates illegal behavior of the illegal passenger traffic vehicle without province,i=1 represents illegal behavior of an illegal inter-provincial passenger traffic vehicle;
x ij is the firstiSample numberjAnd the characteristic is represented by the firstiVehicle NojA plurality of travel characteristics;
β j is the firstjRegression coefficient of each feature, representing the firstjThe influence of individual characteristics on illegal behaviors of illegal inter-provincial passenger transport operation vehicles;
αis a regularization parameter used to control the complexity of the model and the degree of feature selection;
2.3 Determining a target, wherein in the process of selecting the characteristics, the target is to screen out the characteristics which have the most influence on the illegal behavior identification of the illegal inter-provincial passenger traffic operation vehicles; using known illegal inter-provincial passenger traffic vehicle illegal behavior data as training data, wherein the illegal behavior data comprises characteristics and corresponding labels; for LASSO regression, a target variable is set to be a two-class variable, 0 represents illegal behaviors of illegal passenger traffic management vehicles without province, 1 represents illegal behaviors of illegal passenger traffic management vehicles with province, and the characteristics correspond to the characteristics extracted in the step two;
2.4 After performing feature selection by using LASSO regression, the obtained model parameters, namely regression coefficients, are used as feature weights; the feature weight reflects the relative importance of each feature in illegal behavior identification of illegal inter-provincial passenger traffic vehicles; the feature weights are distributed according to regression coefficients of features in LASSO regression; for the characteristic with larger regression coefficient, the characteristic is considered to have larger influence on illegal behavior identification of illegal inter-provincial passenger traffic vehicles;
wherein the third step comprises the steps of,
3.1 Data preparation: using known illegal inter-provincial passenger traffic vehicle illegal behavior data as a training set, and matching the screened feature vectors with corresponding labels to determine whether the feature vectors are illegal inter-provincial passenger traffic vehicle illegal behaviors or not; dividing the data set into a training set and a verification set so as to evaluate the performance of the model in the training process;
3.2 Model initialization: selecting a gradient lifting tree model as a classifier, and setting initial parameters according to the characteristics of the problems, wherein the parameters comprise the number of trees, the maximum depth of the trees and the learning rate;
3.3 Characteristic weight: according to the feature weights obtained in the step two, weighting each feature in the training process of the gradient lifting tree model;
3.4 Model training: training the gradient lifting tree model by using a training set; in the training process, monitoring the performance of the model on the verification set, and recording the training error and the verification error of each iteration;
wherein, the fourth step comprises the following steps,
4.1 Applying k-fold cross validation: evaluating the performance of the gradient lifting tree model by using a k-fold cross validation method; k-fold cross validation allows comprehensive assessment of models without sacrificing data set size, thereby improving the recognition accuracy of illegal inter-provincial passenger traffic vehicles;
4.1.1 dividing known illegal inter-provincial passenger traffic vehicle illegal behavior data into k subsets;
4.1.2 In k iterations, selecting one subset as a verification set each time, and the rest subsets as training sets, and training the gradient lifting tree model by using the training sets;
4.1.3 Evaluating the performance of the model on a verification set, and recording the performance indexes of accuracy, recall rate and F1 fraction; this process is repeated k times so that each subset is used as a validation set;
4.1.4 Calculating the average performance index of k iterations as an evaluation result of the gradient lifting tree model;
4.2 Applying a grid search: optimizing the super parameters of the gradient lifting tree model by using a grid searching method; grid search operation systematically traverses all possible super-parameter combinations to find the optimal parameter combination, thereby improving the prediction precision and stability of the model;
4.2.1 Determining a super-parameter search space of the gradient lifting tree model; setting a series of possible value ranges so as to traverse the parameter combinations in the grid search process;
4.2.2 For each hyper-parameter combination, evaluating model performance using the k-fold cross-validation in step 4.1; calculating the average performance index of k iterations as an evaluation result of the current super-parameter combination;
4.2.3 traversing all the super-parameter combinations to find the super-parameter combination with optimal performance;
4.2.4 training the gradient lifting tree model by using the optimal super-parameter combination and utilizing the whole known illegal inter-provincial passenger traffic vehicle illegal behavior data set; the model has higher accuracy and generalization capability.
2. An intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles according to claim 1, wherein the method further comprises:
the first step comprises the steps of,
1.1 The method comprises the steps of periodically or real-timely collecting related data from each data source, wherein the related data comprise historical administrative penalty case information, ETC traffic data and vehicle information, and the ETC traffic data comprise date and time, a high-speed entrance, a high-speed exit and high-speed portal longitude and latitude;
1.2 Preprocessing the collected data, including data cleaning, data integration and missing value processing.
3. An intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles according to claim 1, wherein the method further comprises:
the fifth step comprises the steps of,
5.1 Model prediction: predicting a new vehicle feature vector by using the trained gradient lifting tree model to obtain a prediction result; the prediction result is the probability that each sample belongs to illegal behaviors of illegal provincial passenger traffic management vehicles;
5.2 Threshold setting: setting a threshold value, and judging that illegal behaviors of illegal inter-provincial passenger traffic operation vehicles exist in the vehicles when the prediction result exceeds the threshold value; and setting a threshold value according to the performance of the model on the training set and the verification set and adjusting the actual requirement of illegal behavior of the illegal inter-provincial passenger traffic operation vehicle.
4. An intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles according to claim 1, wherein the method further comprises:
the sixth step comprises the steps of,
6.1 Evidence collection: after judging that the illegal inter-provincial passenger traffic operation illegal behaviors exist in the vehicle, carrying out snapshot and evidence collection of the illegal behaviors based on ETC traffic data and surrounding monitoring videos of the vehicle;
6.2 Evidence arrangement: ETC entrance and exit data, ETC portal traffic data and historical administrative punishment case information of the vehicle are extracted and used as evidence materials of illegal provincial passenger traffic operation illegal behaviors; the evidence is sorted and classified, so that convenience is provided for subsequent punishment and analysis;
6.3 Illegal action notification: when the illegal inter-provincial passenger traffic operation illegal behaviors of the vehicles are found, immediately informing a traffic management department or a company to which the vehicles belong to take corresponding measures;
6.4 Statistical analysis: and carrying out statistical analysis on the illegal behaviors, and optimizing a traffic management strategy according to the statistical analysis result.
5. The intelligent detection method for illegal behaviors of illegal inter-provincial passenger traffic vehicles according to claim 1, wherein,
the gradient lifting tree model in the third step can be replaced by one or a combination of a plurality of random forests, logistic regression, support vector machines and deep learning.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310650657.1A CN116935625B (en) | 2023-06-05 | 2023-06-05 | Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202310650657.1A CN116935625B (en) | 2023-06-05 | 2023-06-05 | Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN116935625A CN116935625A (en) | 2023-10-24 |
| CN116935625B true CN116935625B (en) | 2024-03-22 |
Family
ID=88383372
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202310650657.1A Active CN116935625B (en) | 2023-06-05 | 2023-06-05 | Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN116935625B (en) |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10740716B1 (en) * | 2019-08-27 | 2020-08-11 | I Transport, Llc | Methods and systems for coordinating physical transport of an object utilizing artificial intelligence |
| CN113689720A (en) * | 2021-07-14 | 2021-11-23 | 东南大学 | Automatic intersection traffic decision method based on convolutional neural network |
| CN114241777A (en) * | 2022-01-06 | 2022-03-25 | 交通运输部路网监测与应急处置中心 | Multi-source heterogeneous networking road condition monitoring early warning system and method |
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN114912641A (en) * | 2022-06-14 | 2022-08-16 | 山东高速集团有限公司 | Road network bridge and tunnel maintenance decision and intelligent inspection system based on BIM |
| CN115328982A (en) * | 2022-07-27 | 2022-11-11 | 公安部道路交通安全研究中心 | Digital management and service system for electric bicycle |
| CN116013084A (en) * | 2023-01-16 | 2023-04-25 | 公安部道路交通安全研究中心 | Traffic management and control scene determining method and device, electronic equipment and storage medium |
Family Cites Families (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20220277831A1 (en) * | 2021-03-01 | 2022-09-01 | Kpn Innovations, Llc. | System and method for generating an addiction nourishment program |
-
2023
- 2023-06-05 CN CN202310650657.1A patent/CN116935625B/en active Active
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US10740716B1 (en) * | 2019-08-27 | 2020-08-11 | I Transport, Llc | Methods and systems for coordinating physical transport of an object utilizing artificial intelligence |
| CN113689720A (en) * | 2021-07-14 | 2021-11-23 | 东南大学 | Automatic intersection traffic decision method based on convolutional neural network |
| CN114241777A (en) * | 2022-01-06 | 2022-03-25 | 交通运输部路网监测与应急处置中心 | Multi-source heterogeneous networking road condition monitoring early warning system and method |
| CN114363316A (en) * | 2022-01-28 | 2022-04-15 | 交通运输部路网监测与应急处置中心 | Intelligent networking monitoring and supervision system for cross-regional road infrastructure |
| CN114912641A (en) * | 2022-06-14 | 2022-08-16 | 山东高速集团有限公司 | Road network bridge and tunnel maintenance decision and intelligent inspection system based on BIM |
| CN115328982A (en) * | 2022-07-27 | 2022-11-11 | 公安部道路交通安全研究中心 | Digital management and service system for electric bicycle |
| CN116013084A (en) * | 2023-01-16 | 2023-04-25 | 公安部道路交通安全研究中心 | Traffic management and control scene determining method and device, electronic equipment and storage medium |
Also Published As
| Publication number | Publication date |
|---|---|
| CN116935625A (en) | 2023-10-24 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN105303197B (en) | A kind of vehicle follow the bus safety automation appraisal procedure based on machine learning | |
| CN110097755B (en) | Highway traffic flow state identification method based on deep neural network | |
| CN111462488B (en) | Intersection safety risk assessment method based on deep convolutional neural network and intersection behavior characteristic model | |
| CN112085947A (en) | Traffic jam prediction method based on deep learning and fuzzy clustering | |
| CN109410588B (en) | Traffic accident evolution analysis method based on traffic big data | |
| CN104750800A (en) | Motor vehicle clustering method based on travel time characteristic | |
| CN116504076A (en) | Expressway traffic flow prediction method based on ETC portal data | |
| CN108009690A (en) | A kind of routine bus system optimized based on modularity steals group's automatic testing method | |
| Elyassami et al. | Road crashes analysis and prediction using gradient boosted and random forest trees | |
| Chen et al. | Pattern recognition using clustering algorithm for scenario definition in traffic simulation-based decision support systems | |
| CN112560915A (en) | Urban expressway traffic state identification method based on machine learning | |
| Xue et al. | Multi long-short term memory models for short term traffic flow prediction | |
| Shi et al. | Automatic clustering for unsupervised risk diagnosis of vehicle driving for smart road | |
| CN116935625B (en) | Intelligent detection method for illegal behaviors of illegal inter-provincial passenger transport operation vehicles | |
| David et al. | Crime Forecasting using Interpretable Regression Techniques | |
| Huang | Svm-based real-time identification model of dangerous traffic stream state | |
| Li | A deep learning approach for real-time crash risk prediction at urban arterials | |
| Munasinghe et al. | Machine Learning based criminal short listing using Modus Operandi features | |
| CN116386339B (en) | Intelligent detection method for illegal running behavior of inter-provincial passenger transport not according to line | |
| Wu et al. | Research on the method of handling missing ETC transaction data | |
| CN117095364B (en) | Urban environment early warning method and system based on AI intelligent garbage recognition | |
| Feng et al. | Risk analysis of road traffic accidents based on improved data mining method | |
| CN117473435B (en) | Method for detecting false abnormal information of sudden public health event based on space-time characteristics | |
| Yu et al. | An expressway congestion detection algorithm based on etc data mining | |
| Nemas et al. | PUBLISHED PROJECT REPORT PPR 863 |
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 |