CN109035763A - Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method - Google Patents
Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method Download PDFInfo
- Publication number
- CN109035763A CN109035763A CN201810706364.XA CN201810706364A CN109035763A CN 109035763 A CN109035763 A CN 109035763A CN 201810706364 A CN201810706364 A CN 201810706364A CN 109035763 A CN109035763 A CN 109035763A
- Authority
- CN
- China
- Prior art keywords
- accident
- attribute
- decision tree
- pattern
- variable
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/01—Detecting movement of traffic to be counted or controlled
- G08G1/0104—Measuring and analyzing of parameters relative to traffic conditions
- G08G1/0137—Measuring and analyzing of parameters relative to traffic conditions for specific applications
Landscapes
- Chemical & Material Sciences (AREA)
- Analytical Chemistry (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Traffic Control Systems (AREA)
Abstract
The expressway traffic accident primary and secondary based on C4.5 that the invention discloses a kind of is because of analysis and accident pattern judgment method, include the following steps: 1, collect N traffic accidents record, the attribute informations, accident pattern such as road conditions, driver conditions, vehicle condition when occurring including accident；2, attribute information is subjected to symbolism；Sample set is constructed by attribute variable and accident pattern；3, the attribute variable of n times accident forms attribute set { ViAs input, accident pattern set { CiAs output, decision tree is constructed using C4.5 algorithm, the terminal node of decision tree is accident pattern, and intermediate node is attribute；4, accident secondary factors sequence is obtained according to established decision tree.This method comprehensively considers the road people-Che-- environmental index relevant to accident, can precisely analyze road traffic accident primary and secondary because, judge it is certain under the conditions of the accident pattern that is most likely to occur, take safeguard procedures that there is directive significance highway traffic control department.
Description
Technical field
The invention belongs to highway traffic safety management study fields, and in particular to a kind of traffic accident based on data mining
Primary and secondary is because of judgment method and accident pattern judgment method.
Background technique
Highway is the convenient way for being suitble to middle-long distance trip, while being also the most trip mode of insecurity factor.
China is every year because personal injury brought by traffic accident and property loss situation are all extremely serious, and traffic accident problem is always
It is the Important Problems of field of traffic scientific research.
Foreign scholar is more early to the traffic accident analysis development based on data mining, and diversification is presented in research method
Trend.For example, gray model and regression model can be utilized for the prediction of traffic accident, decision-tree model, which can be applicable to, probes into thing
Therefore primary and secondary reason and severity of injuries influence factor, Bayesian model can be used to probe into what single factor test influenced accident
Degree, clustering and association rule algorithm can be used to probe into being associated with, etc. between traffic accident correlative factor.
The factor for influencing expressway traffic accident is numerous, and traffic control can be assisted by carrying out classification and importance ranking to Accident-causing
Department formulates the reasonable precautionary measures and more accurate decision.Primary and secondary is carried out because analysis can quantify often to accident in causation analysis
A factor specifies the Influencing Mechanism of different accident patterns to the influence degree of accident, is conducive to analysis personnel and catches principal contradiction.
Decision tree C4.5 algorithm is to probe into primary and secondary because of a kind of common sorting algorithm, and this method arithmetic speed is fast, is suitable for processing magnanimity
Accident information, the representation method of arborescence meet the mode of thinking of people and more intuitive.Therefore, it is visited using decision tree C4.5 algorithm
Study carefully influence accident primary and secondary because method have very strong practicability and operability.
It since the expressway construction in China is later, collects accident information and even lacks unified standard, to carry out data
Analysis, accident information are generally required by a large amount of pretreatment works.The analysis of traffic accident is mainly also stopped at present in China
Stay in the statistical analysis stage.Accident is analyzed using data mining algorithm, height is required to data and method itself, at present also
There is no the big scale of construction to promote.How all-sidedly and accurately collecting information and carrying out analysis to information by scientific method is that China is current
Two important issues in traffic accident analysis field.
Summary of the invention
Goal of the invention: aiming at the problems existing in the prior art, the invention discloses a kind of highways based on C4.5
For accident primary and secondary because of analysis method and accident pattern judgment method, this method comprehensively considers the road people-Che-- environment relevant to accident
Index, can precisely analyze road traffic accident primary and secondary because, judge it is certain under the conditions of the accident pattern that is most likely to occur, to highway
Traffic management department takes safeguard procedures to have directive significance.
Technical solution: the present invention adopts the following technical scheme:
One aspect of the present invention discloses a kind of expressway traffic accident primary and secondary based on C4.5 and walks because of analysis method, including as follows
It is rapid:
(A1) N traffic accidents record, road conditions, driver when occurring including accident each time are collected
The attribute informations such as situation, vehicle condition, accident pattern；
(A2) attribute information is subjected to symbolism, the value of each attribute of symbolically；If obtaining m of each accident
Attribute constitutes the Type C of attribute variable V, each accident, constructs sample set T={ T1,T2,…,TN}；Wherein i-th accident TiTable
It is shown as Ti=[Vi,Ci], ViFor accident TiAttribute variable, CiFor TiAccident pattern, i=1 ..., N；The attribute of accident
Variable V is expressed as V=[v1,v2,…,vm], vjFor j-th of attribute, j=1 ..., m；
(A3) attribute variable of n times accident forms attribute set { ViAs input, accident pattern set { CiAs defeated
Out, decision tree is constructed using C4.5 algorithm, the terminal node of the decision tree is accident pattern, and intermediate node is attribute；
(A4) accident secondary factors sequence is obtained according to step (A3) established decision tree, from positioned at the upper of the decision tree
Layer arrives lower layer, and attribute is sequentially reduced the influence degree of accident, and the influence power of same layer attribute is essentially identical.
Attribute information carries out symbolism, discretization, symbolically discrete type including continuous type attribute in step (A2)
Continuous type attribute after attribute and discretization.
Further include in step (A3) be arranged node minimum instance number it is small to cut off instance number after the completion of constructing decision tree
In the terminal node of preset minimum instance number.
Another aspect of the present invention discloses a kind of expressway traffic accident type judgement method based on C4.5, including walks as follows
It is rapid:
(B1) N traffic accidents record, road conditions, driver when occurring including accident each time are collected
The attribute informations such as situation, vehicle condition, accident pattern；
(B2) attribute information is subjected to symbolism, the value of each attribute of symbolically；If obtaining m of each accident
Attribute constitutes the Type C of attribute variable V, each accident, constructs sample set T={ T1,T2,…,TN}；Wherein i-th accident TiTable
It is shown as Ti=[Vi,Ci], ViFor accident TiAttribute variable, CiFor TiAccident pattern, i=1 ..., N；The attribute of accident
Variable V is expressed as V=[v1,v2,…,vm], vjFor j-th of attribute, j=1 ..., m；
(B3) attribute variable of n times accident forms attribute set { ViAs input, accident pattern set { CiAs defeated
Out, decision tree is constructed using C4.5 algorithm, the terminal node of the decision tree is accident pattern, and intermediate node is attribute；
(B4) attributes such as current road conditions, driver conditions, vehicle condition, value and step according to each attribute are obtained
(B3) decision tree constructed in, obtains the accident pattern under current attribute.
Attribute information carries out symbolism, discretization, symbolically discrete type including continuous type attribute in step (B2)
Continuous type attribute after attribute and discretization.
Further include in step (B3) be arranged node minimum instance number it is small to cut off instance number after the completion of constructing decision tree
In the terminal node of preset minimum instance number.
The utility model has the advantages that the traffic accident primary and secondary disclosed by the invention based on C4.5 is because of analysis compared with existing analytical technology
Method and accident pattern judgment method have the advantage that 1, consider data diversification, and multivariate model compares single data element
Judge more accurate；2, with decision tree C4.5 algorithm rather than traditional analysis.Traditional analysis processing multivariable be
It is slow to analyze speed, and is difficult to handle continuous variable.3, disaggregated model can intuitively disclose the master for influencing accident pattern distribution
It is secondary because there is certain directive significance to the decision of highway traffic safety administrative department.
Detailed description of the invention
Fig. 1 is expressway traffic accident primary and secondary disclosed by the invention because of analysis flow chart diagram；
Fig. 2 is that 117~K127 of beautiful temperature high speed K studies section position view in example；
Fig. 3 is the decision tree diagram that example generates；
Fig. 4 is the various condition patterns for causing rear-end collision.
Specific embodiment
To make the object, technical solutions and advantages of the present invention clearer, with reference to the accompanying drawing to specific reality of the invention
Case is applied to explain.
The present embodiment elaborates the expressway traffic accident master disclosed in this invention based on C4.5 by taking beautiful temperature high speed as an example
It is secondary because of analysis method, process is as shown in Figure 1.
Step 1, beautiful temperature high speed are domestic positioned at Zhejiang Province, connect Lishui and Wenzhou.Li Wen high speed mileage open to traffic 116km, bridge
Tunnel mileage accounting is known as " Qiao Sui club " up to 90% or more, by industry traffic specialists.Research section model selected by this example
It encloses for K117~K134, overall length 17km, as shown in Figure 2.Research section have passed through in order the tunnel of the hilllock Tong Ling 2, the tunnel Yu Zhuan,
Sea fern bridge, DaLiangshan tunnel, Yangshan Tunnel and bright and beautiful water tunnel, complex geographical environment.It is 2006 to 2013, left through counting
Accident 243, which occurs, for line rises, and accident 389, which occurs, for right line rises.According to " Lishui area under one's jurisdiction accident over the years summarizes " file, research road is filtered out
632 accident records in section collect the information such as road conditions, driver conditions, the vehicle condition when accident occurs, and every time
Accident volume type, road condition information therein are obtained by " Jin Liwen high speed route design drawing "；
Initial data has mixed and disorderly, imperfect, fuzzy characteristic, after removing tuple missing and cryptic data group,
The valid data for retaining 65%, finally obtain 411 accident records.
1 attribute variable of table
Step 2, building accident sample set, attribute variable is as shown in table 1, include accident occur when road conditions, drive
The person's of sailing situation, vehicle condition and whether there is cart to participate in, whether the factors such as extreme terrain, accident record reason item；It is wherein bent
Rate radius and depth displacement absolute value are continuous variable, are first carried out discretization, then the value after symbolically discretization；
Accident pattern, which is divided into, hits solids, knocks into the back, overturns, scraping, catching fire, other, as shown in table 2, wherein straight linear
Radius of curvature with 12000 meters substitute.
Table 2
Step 3, the attribute set for forming 411 incident attributes variables are as input, and accident pattern is as output, application
C4.5 algorithm constructs decision tree；
Decision tree is constructed using data mining software weka in the present embodiment, by handle well to output and input data defeated
Enter weka software, trade-off decision tree C4.5 sorting algorithm.Model overfitting in order to prevent carries out cut operator to model.If
The minimum instance number for setting node cuts off the terminal section that instance number is less than preset minimum instance number after the completion of constructing decision tree
Point, setting minimum node number is 4 in the present embodiment.Obtained tree graph is as shown in figure 3, the terminal node of decision tree is accident class
Type, intermediate node are attribute.First digit is correct classification in terminal node bracket, and second digit is mistake classification.Example
Hit solid as accident pattern caused by slippery when wet is all judged as by first branch of model, wherein have 44 it is correct, 10
A mistake.Verified, which reaches 82.24%, has higher reliability.
Intermediate node, i.e., the significance level for sequentially representing each attribute up and down of oval node, the accident in top layer
Record reason item is primary factor, including fatigue driving, slippery when wet, vehicle body spacing are too small, driver's operation is out of control, vehicle condition not
Good, massif trickles down object, drives over the speed limit；Radius of curvature in the second layer and whether have cart to participate in be the second key factor, the
Two layers it is below whether the factors such as extreme terrain, elevation, time accident pattern is influenced it is little.
It can intuitively find out which kind of accident pattern be easy to cause in some cases from tree graph.By taking rear-end collision as an example, with
It is rear-end collision that the accident pattern occurred is easiest in the case of lower 6 kinds, as shown in Figure 4.
(1) reason: spacing is too small；
(2) reason: hypervelocity → radius of curvature≤4000；
(3) reason: hypervelocity → radius of curvature > 4000 → elevation absolute value > 13.6；
(4) it reason: operates out of control → cart and participates in: nothing → landform: tunnel exit；
(5) reason: out of control → landform is operated: in tunnel → radius of curvature :≤1000；
(6) reason: operate out of control → cart and participate in: have → radius of curvature: > 850 → period: daytime → elevation is absolute
Value :≤5.
Claims (6)
1. the expressway traffic accident primary and secondary based on C4.5 is because of analysis method, which comprises the steps of:
(A1) N traffic accidents record, road conditions, driver's feelings when occurring including accident each time are collected
The attribute informations such as condition, vehicle condition, accident pattern；
(A2) attribute information is subjected to symbolism, the value of each attribute of symbolically；If obtaining m attribute of each accident
The Type C of attribute variable V, each accident are constituted, sample set T={ T is constructed1,T2,…,TN}；Wherein i-th accident TiIt is expressed as
Ti=[Vi,Ci], ViFor accident TiAttribute variable, CiFor TiAccident pattern, i=1 ..., N；The attribute variable V of accident
It is expressed as V=[v1,v2,…,vm], vjFor j-th of attribute, j=1 ..., m；
(A3) attribute variable of n times accident forms attribute set { ViAs input, accident pattern set { CiAs output, it answers
Decision tree is constructed with C4.5 algorithm, the terminal node of the decision tree is accident pattern, and intermediate node is attribute；
(A4) accident secondary factors sequence is obtained according to step (A3) established decision tree, from be located at the upper layer of the decision tree to
Lower layer, attribute are sequentially reduced the influence degree of accident, and the influence power of same layer attribute is essentially identical.
2. the expressway traffic accident primary and secondary according to claim 1 based on C4.5 is because of analysis method, which is characterized in that step
(A2) attribute information carries out symbolism, discretization, symbolically discrete type attribute and discretization including continuous type attribute in
Continuous type attribute afterwards.
3. the expressway traffic accident primary and secondary according to claim 1 based on C4.5 is because of analysis method, which is characterized in that step
(A3) further include the minimum instance number that node is set in, after the completion of constructing decision tree, cut off instance number less than preset minimum
The terminal node of instance number.
4. the expressway traffic accident type judgement method based on C4.5, which comprises the steps of:
(B1) N traffic accidents record, road conditions, driver's feelings when occurring including accident each time are collected
The attribute informations such as condition, vehicle condition, accident pattern；
(B2) attribute information is subjected to symbolism, the value of each attribute of symbolically；If obtaining m attribute of each accident
The Type C of attribute variable V, each accident are constituted, sample set T={ T is constructed1,T2,…,TN}；Wherein i-th accident TiIt is expressed as
Ti=[Vi,Ci], ViFor accident TiAttribute variable, CiFor TiAccident pattern, i=1 ..., N；The attribute variable V of accident
It is expressed as V=[v1,v2,…,vm], vjFor j-th of attribute, j=1 ..., m；
(B3) attribute variable of n times accident forms attribute set { ViAs input, accident pattern set { CiAs output, it answers
Decision tree is constructed with C4.5 algorithm, the terminal node of the decision tree is accident pattern, and intermediate node is attribute；
(B4) attributes such as current road conditions, driver conditions, vehicle condition, value and step (B3) according to each attribute are obtained
The decision tree of middle building obtains the accident pattern under current attribute.
5. the expressway traffic accident type judgement method according to claim 4 based on C4.5, which is characterized in that step
(B2) attribute information carries out symbolism, discretization, symbolically discrete type attribute and discretization including continuous type attribute in
Continuous type attribute afterwards.
6. the expressway traffic accident type judgement method according to claim 4 based on C4.5, which is characterized in that step
(B3) further include the minimum instance number that node is set in, after the completion of constructing decision tree, cut off instance number less than preset minimum
The terminal node of instance number.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810706364.XA CN109035763A (en) | 2018-07-02 | 2018-07-02 | Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810706364.XA CN109035763A (en) | 2018-07-02 | 2018-07-02 | Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109035763A true CN109035763A (en) | 2018-12-18 |
Family
ID=65522148
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810706364.XA Pending CN109035763A (en) | 2018-07-02 | 2018-07-02 | Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109035763A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036709A (en) * | 2020-08-12 | 2020-12-04 | 东南大学 | Random forest based rainfall weather expressway secondary accident cause analysis method |
| CN113033471A (en) * | 2021-04-15 | 2021-06-25 | 北京百度网讯科技有限公司 | Traffic abnormality detection method, apparatus, device, storage medium, and program product |
| CN114613130A (en) * | 2022-02-18 | 2022-06-10 | 北京理工大学 | Driving credibility analysis method in traffic and delivery system |
| CN116720142A (en) * | 2023-06-08 | 2023-09-08 | 中国汽车工程研究院股份有限公司 | Accident unknown information quick reconstruction method under limited evidence |
Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1652120A (en) * | 2005-02-24 | 2005-08-10 | 上海交通大学 | Plasticity forming technique regulation obtaining method based on numerical value simulation and policy-making tree algorithm |
| CN102289933A (en) * | 2011-08-08 | 2011-12-21 | 上海电科智能系统股份有限公司 | Method for predicting grades of spatial effect ranges of traffic event effects on city expressways |
| CN105335752A (en) * | 2015-09-18 | 2016-02-17 | 国网山东省电力公司菏泽供电公司 | Principal component analysis multivariable decision-making tree-based connection manner identification method |
| CN106126328A (en) * | 2016-06-24 | 2016-11-16 | 同济大学 | A kind of traffic metadata management method based on event classification and system |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
| CN106650807A (en) * | 2016-12-20 | 2017-05-10 | 东南大学 | Method for predicting and evaluating concrete strength deterioration under ocean environment |
| CN107516287A (en) * | 2017-08-23 | 2017-12-26 | 中南大学 | Traffic accidents reason analysis method |
| CN107742256A (en) * | 2017-09-18 | 2018-02-27 | 中国农业大学 | A kind of network puppet public opinion identification method based on decision making of combinatorial optimization tree |
-
2018
- 2018-07-02 CN CN201810706364.XA patent/CN109035763A/en active Pending
Patent Citations (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN1652120A (en) * | 2005-02-24 | 2005-08-10 | 上海交通大学 | Plasticity forming technique regulation obtaining method based on numerical value simulation and policy-making tree algorithm |
| CN102289933A (en) * | 2011-08-08 | 2011-12-21 | 上海电科智能系统股份有限公司 | Method for predicting grades of spatial effect ranges of traffic event effects on city expressways |
| CN105335752A (en) * | 2015-09-18 | 2016-02-17 | 国网山东省电力公司菏泽供电公司 | Principal component analysis multivariable decision-making tree-based connection manner identification method |
| CN106126328A (en) * | 2016-06-24 | 2016-11-16 | 同济大学 | A kind of traffic metadata management method based on event classification and system |
| CN106228499A (en) * | 2016-07-06 | 2016-12-14 | 东南大学 | A kind of cargo security evaluation model based on people's bus or train route goods multi-risk System source |
| CN106650807A (en) * | 2016-12-20 | 2017-05-10 | 东南大学 | Method for predicting and evaluating concrete strength deterioration under ocean environment |
| CN107516287A (en) * | 2017-08-23 | 2017-12-26 | 中南大学 | Traffic accidents reason analysis method |
| CN107742256A (en) * | 2017-09-18 | 2018-02-27 | 中国农业大学 | A kind of network puppet public opinion identification method based on decision making of combinatorial optimization tree |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112036709A (en) * | 2020-08-12 | 2020-12-04 | 东南大学 | Random forest based rainfall weather expressway secondary accident cause analysis method |
| CN113033471A (en) * | 2021-04-15 | 2021-06-25 | 北京百度网讯科技有限公司 | Traffic abnormality detection method, apparatus, device, storage medium, and program product |
| CN114613130A (en) * | 2022-02-18 | 2022-06-10 | 北京理工大学 | Driving credibility analysis method in traffic and delivery system |
| CN116720142A (en) * | 2023-06-08 | 2023-09-08 | 中国汽车工程研究院股份有限公司 | Accident unknown information quick reconstruction method under limited evidence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109035763A (en) | Expressway traffic accident primary and secondary based on C4.5 is because of analysis and accident pattern judgment method | |
| CN103971523B (en) | A kind of mountain road traffic safety dynamic early-warning system | |
| Han et al. | Intelligent decision model of road maintenance based on improved weight random forest algorithm | |
| CN109993223A (en) | Pavement Condition prediction technique, storage medium, electronic equipment | |
| CN105405293B (en) | A kind of road travel time short term prediction method and system | |
| CN109754110A (en) | A kind of method for early warning and system of traction converter failure | |
| CN109243178A (en) | Town way Traffic Safety Analysis and evaluation method under the conditions of a kind of bad climate | |
| CN108682149A (en) | The linear causation analysis method in highway accident stain section based on binary logistic regression | |
| CN112396320A (en) | Tunnel collapse risk assessment method based on ISM and fuzzy Bayesian network | |
| CN105374209A (en) | Urban region road network running state characteristic information extraction method | |
| Wang et al. | Open-pit mine truck fuel consumption pattern and application based on multi-dimensional features and XGBoost | |
| CN108447265A (en) | Road traffic accident stain section discrimination method based on TOPSIS methods | |
| CN110288144A (en) | A kind of deep basal pit security assessment method based on utility theory and D-S evidential reasoning | |
| CN115148019A (en) | Early warning method and system based on holiday congestion prediction algorithm | |
| CN107871183A (en) | Permafrost Area highway distress Forecasting Methodology based on uncertain Clouds theory | |
| CN106384507A (en) | Travel time real-time estimation method based on sparse detector | |
| Cao et al. | Quantification of the impact of traffic incidents on speed reduction: A causal inference based approach | |
| CN115938124A (en) | Urban rail transit emergency influence prediction method, system and product | |
| He et al. | Visualization and analysis of mapping knowledge domain of heterogeneous traffic flow | |
| CN103383819B (en) | Based on the desert road vehicle travel speed prediction computing system of driver's cognitive features | |
| CN105912775B (en) | The multi-modal modeling method of bridge dynamic weighing system vehicle axle weight data | |
| CN116681330A (en) | Road tunnel electromechanical system running state classification and comprehensive evaluation method | |
| CN109255956A (en) | A kind of charge station's magnitude of traffic flow method for detecting abnormality | |
| Xie et al. | Modeling lane-specific breakdown probabilities at freeway diverge sections | |
| Huang | Svm-based real-time identification model of dangerous traffic stream state |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181218 |
|
| RJ01 | Rejection of invention patent application after publication |