CN116913105A - Short-time traffic flow prediction method based on cyclic nerve gray model - Google Patents
Short-time traffic flow prediction method based on cyclic nerve gray model Download PDFInfo
- Publication number
- CN116913105A CN116913105A CN202310916418.6A CN202310916418A CN116913105A CN 116913105 A CN116913105 A CN 116913105A CN 202310916418 A CN202310916418 A CN 202310916418A CN 116913105 A CN116913105 A CN 116913105A
- Authority
- CN
- China
- Prior art keywords
- sequence
- traffic flow
- main
- road section
- gray
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 27
- 125000004122 cyclic group Chemical group 0.000 title claims abstract description 21
- 210000005036 nerve Anatomy 0.000 title claims abstract description 16
- 238000004088 simulation Methods 0.000 claims abstract description 7
- 238000012549 training Methods 0.000 claims description 12
- 230000002087 whitening effect Effects 0.000 claims description 12
- 238000009825 accumulation Methods 0.000 claims description 3
- 230000000694 effects Effects 0.000 claims description 3
- 230000001537 neural effect Effects 0.000 claims description 3
- 238000012545 processing Methods 0.000 claims description 3
- 238000012163 sequencing technique Methods 0.000 claims description 3
- 238000013528 artificial neural network Methods 0.000 claims description 2
- 238000011161 development Methods 0.000 claims description 2
- 230000006870 function Effects 0.000 description 11
- 238000001514 detection method Methods 0.000 description 2
- 239000000284 extract Substances 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000010485 coping Effects 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000006698 induction Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 239000002699 waste material Substances 0.000 description 1
Classifications
-
- G—PHYSICS
- G08—SIGNALLING
- G08G—TRAFFIC CONTROL SYSTEMS
- G08G1/00—Traffic control systems for road vehicles
- G08G1/065—Traffic control systems for road vehicles by counting the vehicles in a section of the road or in a parking area, i.e. comparing incoming count with outgoing count
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/11—Complex mathematical operations for solving equations, e.g. nonlinear equations, general mathematical optimization problems
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
- G06N3/044—Recurrent networks, e.g. Hopfield networks
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- 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
- 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
-
- 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 relates to a short-time traffic flow prediction method based on a cyclic nerve gray model, and belongs to the technical field of intelligent traffic. The method comprises the following steps: s1: collecting the traffic flow of a certain main road section and a branch of the main road section; analyzing gray association degree of the main road section and the branch road traffic flow by using the gray association degree, and selecting the main road section as a main sequence and the branch road with larger association degree as an influence sequence; s2: establishing a cyclic nerve gray model by using a main sequence and an influence sequence; s3: and determining the optimal simulation and the number of predictions, and predicting the traffic flow of the main road section by using an optimal scheme. The prediction method can effectively improve the prediction precision of short-time traffic flow.
Description
Technical Field
The invention belongs to the technical field of intelligent traffic, and relates to a short-time traffic flow prediction method based on a cyclic nerve gray model.
Background
Short-time traffic flow prediction is always a popular research field in an intelligent traffic system, real-time accurate traffic flow prediction is a precondition and key of traffic control and traffic induction, and has important significance for relieving urban traffic jams and avoiding social resource waste.
At present, a plurality of methods for modeling and predicting short-time traffic flow are provided, and common models are as follows: the system comprises a historical average model, a time sequence model, a Kalman filtering model, a neural network model and the like, wherein the historical average model is simple in principle, high in operation efficiency, suitable for road sections with small fluctuation range of traffic flow, low in prediction accuracy and poor in capability of coping with sudden traffic conditions; for a road section with small fluctuation amplitude of traffic flow, the time sequence model has good real-time performance and stability, can meet the prediction requirement, but the prediction accuracy is too dependent on the number of samples; the Kalman filtering model has high prediction accuracy on steady state traffic flow, but the prediction accuracy depends on the linear characteristics of the traffic flow, and is suitable for linear non-real-time online traffic flow prediction; the neural network model has strong self-adaptive learning capability, good instantaneity, higher prediction accuracy and slow convergence speed, and is suitable for complex, changeable and nonlinear traffic flow prediction. However, most of these models only consider the nonlinear characteristics of traffic flow, and traffic flow has many characteristics, and if only one characteristic is considered, the prediction accuracy is limited. In addition, the main link traffic increases due to the merging of the branch link traffic into the main link, but there is less effort to comprehensively consider the branch link traffic for predicting the main link traffic.
Disclosure of Invention
Therefore, the invention aims to provide a short-time traffic flow prediction method based on a cyclic nerve gray model, which extracts data features of a traffic flow main sequence and an influence sequence by using a gray differential dynamic multivariable prediction model, then stores the extracted data features of each step by using a hidden state of a cyclic nerve network, and comprehensively considers nonlinearity and non-stationarity of traffic flow data by iterating the features of time sequence and time sequence of deep mining data, thereby effectively improving the prediction precision of short-time traffic flow.
In order to achieve the above purpose, the present invention provides the following technical solutions:
a short-time traffic flow prediction method based on a cyclic nerve gray model specifically comprises the following steps:
s1: collecting the traffic flow of a certain main road section and a branch of the main road section; analyzing gray association degree of the main road section and the branch road traffic flow by using the gray association degree, and selecting the main road section as a main sequence and the branch road with larger association degree as an influence sequence;
s2: establishing a cyclic nerve gray model by using a main sequence and an influence sequence;
s3: and determining the optimal simulation and the number of predictions, and predicting the traffic flow of the main road section by using an optimal scheme.
In step S2, a cyclic neural gray model is established, specifically, the hidden state of the cyclic neural network is used to store the data features of the traffic flow main sequence and the influencing sequence extracted in each step, and the time sequence features of the data are mined through iteration depth.
Further, the step S2 specifically includes the following steps:
s21: data processing;
for the main sequence y (0) (t) and influencing sequencesPerforming first-order accumulation to obtain y (1)(t) and />m represents the number of branches;
s22: determining a whitening equation form of the univariate gray model according to the influence sequence, and solving an iteration formula by using an Euler method;
sequencing ofThe whitening equation of +.>Reduce it to-> wherein ,/>The Euler method of the differential equation is solved as +.>Wherein l represents step size, < >>Represents the gray effect amount, w, of the ith influencing sequence i =[b i0 ,b i1 ,θ i ]Parameters representing the reduced whitening equation, +.>Solution of whitening equation, f i (x i (1) (t),t,θ i ) The right side function of a whitening equation of a general gray model is represented, and n represents the number of traffic flow observation points of a main road section and a branch road section;
s23: will beWhitening equation solution of (1) take g into i (x i (1) (t),t,w i ) Is calculated to obtain
S24: will beIs brought into the following
Wherein a represents the development coefficient of the main sequence, and c represents a constant;
simplifying to obtainSolving the equation by Euler's method, the solution of which is expressed as
wherein ,predicted value representing the main sequence,/->Represents the value of the function G at time t-1, w= [ a, b ] i0 ,θ i ,c]Parameters representing the function G;
s25: initializing first layer training parameters and inputting training dataInitial state->And step length l, and will be given by
Is set as a hidden layer function,setting the first layer RNN as an output layer function;
s26: initializing a second layer training parameter, setting a step length l, taking the first layer output as a second layer input, and initializing a state initial 2= [ y ] (1) (1)]And will be of the formula
Setting a hidden state function, wherein the hidden state is used as output to construct a second layer RNN;
s27: calculating a mean square error between the output sequence of the second layer RNN and the original sequence as a loss function, and accordingly counter-propagating the propagation training parameters;
s28: predicting by using a trained model, and subtracting the predicted sequence.
Further, the step S3 specifically includes the following steps:
s31: determining the value of the step length l;
s32: selecting main sequences with different lengths, predicting values with different lengths by using the cyclic nerve gray model established in the step S2, calculating average simulation errors and average prediction errors of each combination, and selecting the combination with the minimum error as an optimal scheme;
s33: and predicting a predicted value of the influence sequence by using a single-variable gray prediction model, and then predicting the main sequence by using the optimal scheme in the step S32.
The invention has the beneficial effects that: the invention uses a cyclic nerve gray model prediction, extracts data characteristics of a traffic flow main sequence and an influence sequence by using a gray differential dynamic multivariable model, then stores the extracted data characteristics of each step by using a hidden state of a cyclic nerve network, and mines the characteristics of time sequence and time sequence of data through iteration depth. The method not only can deeply mine the data characteristics of the traffic flow, but also shows high accuracy and reliability on short-time traffic flow prediction.
Additional advantages, objects, and features of the invention will be set forth in part in the description which follows and in part will become apparent to those having ordinary skill in the art upon examination of the following or may be learned from practice of the invention. The objects and other advantages of the invention may be realized and obtained by means of the instrumentalities and combinations particularly pointed out in the specification.
Drawings
For the purpose of making the objects, technical solutions and advantages of the present invention more apparent, the present invention will be described in the following preferred detail with reference to the accompanying drawings, in which:
FIG. 1 is a diagram of a cyclic neural gray model network of the present invention.
Detailed Description
Other advantages and effects of the present invention will become apparent to those skilled in the art from the following disclosure, which describes the embodiments of the present invention with reference to specific examples. The invention may be practiced or carried out in other embodiments that depart from the specific details, and the details of the present description may be modified or varied from the spirit and scope of the present invention. It should be noted that the illustrations provided in the following embodiments merely illustrate the basic idea of the present invention by way of illustration, and the following embodiments and features in the embodiments may be combined with each other without conflict.
Referring to fig. 1, the present invention provides a short-time traffic flow prediction method, as shown in fig. 1, specifically including the following steps:
s1: and taking out the traffic flow data of the history records of the main road section and the branch road section according to the appointed time interval.
The traffic flow data recorded in the history is derived from a traffic data acquisition system and can be acquired through means of coil detection, video detection and the like. The obtained historical traffic flow data is the number of vehicles passing through a specific observation point or road section within a certain time interval. The specified time interval may be specified according to the predicted need (e.g., 15 minutes). Obtaining the sequences of n observation points of the traffic flow of the main road section and the branch road section, which are Y respectively (0) =(y (0) (1),y (0) (2),…,y (0) (n))、X i (0) =(x i (0) (1),x i (0) (2),…,x i (0) (n)) (i=1, 2, …, m), wherein m represents a branchThe number of ways.
S2: the grey correlation degree is calculated for the traffic flow sequence of the main road section and the branch road section, and for xi epsilon (0, 1), Y (0) And (3) withGray association degree->The method comprises the following steps:
and selecting the sequence with larger grey correlation degree as the influencing sequence.
S3: the method comprises the following main steps of establishing a cyclic nerve gray model by using a main sequence and an influence sequence:
s31: and (5) data processing. For the main sequence y (0) (t) and influencing sequencesPerforming first-order accumulation to obtain y (1)(t) and />
S32: and determining a whitening equation form of the univariate gray model according to the influence sequence, and solving an iteration formula by using an Euler method. Sequencing ofThe whitening equation of +.>Reduce it to-> wherein />The Euler method of the differential equation is solved as +.>
S33: will beWhitening equation solution of (1) take g into i (x i (1) (t),t,w i ) Is calculated to obtain
S34: will beIs brought into the following
Simplifying to obtainSolving the equation by Euler's method, the solution of which is expressed as
S35: initializing a first layer training parameter, inputting training data X, initial state initial1 and step length l, and taking the following formula
Is set as a hidden layer function,set as output layer function, build first layer RNN.
S36: initializing second layer training parameters, setting step length l, taking first layer output as second layer input, initializing state, and taking the following formula
Setting as hidden layer function, hidden state as output builds the second layer RNN.
S37: and taking the mean square error of the output sequence of the second layer RNN and the original sequence as a loss function, thereby counter-propagating the propagation training parameters.
S38: predicting by using a trained model, and subtracting the predicted sequence.
S4: determining the optimal simulation and prediction number, and predicting the traffic flow of the road section by using an optimal scheme, wherein the method mainly comprises the following steps of:
s31: and determining the value of the step length l.
S32: and selecting main sequences with different lengths for predicting values with different lengths, calculating average simulation errors and average prediction errors of each combination, and selecting the combination with the minimum error as an optimal scheme.
S33: predicting a predicted value of the influence sequence by using a single-variable gray prediction model, and then predicting the main sequence by using an optimal scheme of Step 2.
Finally, it is noted that the above embodiments are only for illustrating the technical solution of the present invention and not for limiting the same, and although the present invention has been described in detail with reference to the preferred embodiments, it should be understood by those skilled in the art that modifications and equivalents may be made thereto without departing from the spirit and scope of the present invention, which is intended to be covered by the claims of the present invention.
Claims (4)
1. The short-time traffic flow prediction method based on the cyclic nerve gray model is characterized by comprising the following steps of:
s1: collecting the traffic flow of a certain main road section and a branch of the main road section; analyzing gray association degree of the main road section and the branch road traffic flow by using the gray association degree, and selecting the main road section as a main sequence and the branch road with high association degree as an influence sequence;
s2: establishing a cyclic nerve gray model by using a main sequence and an influence sequence;
s3: and determining the optimal simulation and the number of predictions, and predicting the traffic flow of the main road section by using an optimal scheme.
2. The short-term traffic flow prediction method according to claim 1, wherein in step S2, a cyclic neural gray model is established, specifically, the hidden state of the cyclic neural network is used to store the data characteristics of the traffic flow main sequence and the influencing sequence extracted in each step, and the time sequence characteristics of the data are mined through iteration depth.
3. The short-term traffic flow prediction method according to claim 1 or 2, characterized in that step S2 specifically comprises the steps of:
s21: data processing;
for the main sequence y (0) (t) and influencing sequencesPerforming first-order accumulation to obtain y (1)(t) and />m represents the number of branches;
s22: determining a whitening equation form of the univariate gray model according to the influence sequence, and solving an iteration formula by using an Euler method;
sequencing ofThe whitening equation of +.>Reduce it to-> wherein ,/>The Euler method of the differential equation is solved as +.>Wherein l represents step size, < >>Represents the gray effect amount, w, of the ith influencing sequence i =[b i0 ,b i1 ,θ i ]Parameters representing the reduced whitening equation, +.>Solution of whitening equation, f i (x i (1) (t),t,θ i ) The right side function of a whitening equation of a general gray model is represented, and n represents the number of traffic flow observation points of a main road section and a branch road section;
s23: will beWhitening equation solution of (1) take g into i (x i (1) (t),t,w i ) Is calculated to obtain
S24: will beIs brought into the following
Wherein a represents the development coefficient of the main sequence, and c represents a constant;
simplifying to obtainSolving the equation by Euler's method, the solution of which is expressed as
wherein ,predicted value representing the main sequence,/->Represents the value of the function G at time t-1, w= [ a, b ] i0 ,θ i ,c]Parameters representing the function G;
s25: initializing first layer training parameters and inputting training dataInitial state->And step length l, and will be given by
Is set as a hidden layer function,setting the first layer RNN as an output layer function;
s26: initializing a second layer training parameter, setting a step length l, taking the first layer output as a second layer input, and initializing a state initial 2= [ y ] (1) (1)]And is combined withWill be as follows
Setting a hidden state function, wherein the hidden state is used as output to construct a second layer RNN;
s27: calculating a mean square error between the output sequence of the second layer RNN and the original sequence as a loss function, and accordingly counter-propagating the propagation training parameters;
s28: predicting by using a trained model, and subtracting the predicted sequence.
4. The short-term traffic flow prediction method according to claim 1, wherein the step S3 specifically comprises the steps of:
s31: determining the value of the step length l;
s32: selecting main sequences with different lengths, predicting values with different lengths by using the cyclic nerve gray model established in the step S2, calculating average simulation errors and average prediction errors of each combination, and selecting the combination with the minimum error as an optimal scheme;
s33: and predicting a predicted value of the influence sequence by using a single-variable gray prediction model, and then predicting the main sequence by using the optimal scheme in the step S32.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310916418.6A CN116913105B (en) | 2023-07-24 | 2023-07-24 | Short-time traffic flow prediction method based on cyclic nerve gray model |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202310916418.6A CN116913105B (en) | 2023-07-24 | 2023-07-24 | Short-time traffic flow prediction method based on cyclic nerve gray model |
Publications (2)
Publication Number | Publication Date |
---|---|
CN116913105A true CN116913105A (en) | 2023-10-20 |
CN116913105B CN116913105B (en) | 2024-03-19 |
Family
ID=88364484
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202310916418.6A Active CN116913105B (en) | 2023-07-24 | 2023-07-24 | Short-time traffic flow prediction method based on cyclic nerve gray model |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN116913105B (en) |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110161261A1 (en) * | 2009-12-28 | 2011-06-30 | Nec(China) Co., Ltd. | Method and system for traffic prediction based on space-time relation |
CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
CN106448151A (en) * | 2016-07-07 | 2017-02-22 | 河南理工大学 | Short-time traffic flow prediction method |
CN110414719A (en) * | 2019-07-05 | 2019-11-05 | 电子科技大学 | A kind of vehicle flowrate prediction technique based on Multi-variable Grey Model time series |
US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
-
2023
- 2023-07-24 CN CN202310916418.6A patent/CN116913105B/en active Active
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20110161261A1 (en) * | 2009-12-28 | 2011-06-30 | Nec(China) Co., Ltd. | Method and system for traffic prediction based on space-time relation |
CN103730006A (en) * | 2014-01-26 | 2014-04-16 | 吉林大学 | Short-time traffic flow combined forecasting method |
CN106448151A (en) * | 2016-07-07 | 2017-02-22 | 河南理工大学 | Short-time traffic flow prediction method |
CN110414719A (en) * | 2019-07-05 | 2019-11-05 | 电子科技大学 | A kind of vehicle flowrate prediction technique based on Multi-variable Grey Model time series |
US20210209939A1 (en) * | 2020-12-08 | 2021-07-08 | Harbin Engineering University | Large-scale real-time traffic flow prediction method based on fuzzy logic and deep LSTM |
Non-Patent Citations (1)
Title |
---|
段辉明: "灰色微分动态多变量预测模型及其应用", 《系统工程理论与实践》, vol. 42, no. 5, 25 May 2022 (2022-05-25), pages 1402 - 1412 * |
Also Published As
Publication number | Publication date |
---|---|
CN116913105B (en) | 2024-03-19 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN110110419B (en) | TBM tunneling parameter prediction method based on multi-target learning | |
CN111967688B (en) | Power load prediction method based on Kalman filter and convolutional neural network | |
CN109214581B (en) | Railway line wind speed prediction method considering wind direction and confidence interval | |
Matheson | The economic value of analysis and computation | |
Huang et al. | An integrated neural-fuzzy-genetic-algorithm using hyper-surface membership functions to predict permeability in petroleum reservoirs | |
CN109426672B (en) | Oil reservoir injection-production parameter optimization method based on uncertain geological model | |
CN106250988A (en) | Relevance vector regression Incremental Learning Algorithm based on sample properties and system | |
CN111127246A (en) | Intelligent prediction method for transmission line engineering cost | |
CN111027673B (en) | Subway passenger flow prediction method | |
CN108595803A (en) | Shale gas well liquid loading pressure prediction method based on recurrent neural network | |
CN112633328A (en) | Dense oil reservoir transformation effect evaluation method based on deep learning | |
CN111160659A (en) | Power load prediction method considering temperature fuzzification | |
CN114169645A (en) | Short-term load prediction method for smart power grid | |
CN116244647A (en) | Unmanned aerial vehicle cluster running state estimation method | |
CN116913105B (en) | Short-time traffic flow prediction method based on cyclic nerve gray model | |
CN105654053A (en) | Improved constrained EKF algorithm-based dynamic oscillation signal parameter identification method | |
Hu et al. | Adaptive environmental sampling for underwater vehicles based on ant colony optimization algorithm | |
Tahmasebi et al. | Comparison of optimized neural network with fuzzy logic for ore grade estimation | |
CN116821586A (en) | Landslide displacement prediction method based on attention mechanism and bidirectional gating circulating unit | |
CN104598741A (en) | Lane saturation predication model | |
CN114862007A (en) | Short-period gas production rate prediction method and system for carbonate gas well | |
CN113255963A (en) | Road surface use performance prediction method based on road element splitting and deep learning model LSTM | |
CN108171381A (en) | A kind of blast furnace CO utilization rates chaos weighing first order local prediction method and system | |
CN114418164A (en) | Intelligent optimization type selection method for shield tunneling equipment based on knowledge management | |
CN113890633A (en) | Underwater acoustic communication system self-adaptive selection method based on deep neural network |
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 |