CN111813830B - Industrial time sequence data retrieval method based on rail transit industrial Internet - Google Patents
Industrial time sequence data retrieval method based on rail transit industrial Internet Download PDFInfo
- Publication number
- CN111813830B CN111813830B CN202010632977.0A CN202010632977A CN111813830B CN 111813830 B CN111813830 B CN 111813830B CN 202010632977 A CN202010632977 A CN 202010632977A CN 111813830 B CN111813830 B CN 111813830B
- Authority
- CN
- China
- Prior art keywords
- data
- data set
- time sequence
- rail transit
- industrial
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Active
Links
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- 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
- G06F16/2477—Temporal data queries
-
- 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
- G06F17/00—Digital computing or data processing equipment or methods, specially adapted for specific functions
- G06F17/10—Complex mathematical operations
- G06F17/16—Matrix or vector computation, e.g. matrix-matrix or matrix-vector multiplication, matrix factorization
-
- 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
- G06N3/045—Combinations of 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
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Mathematical Physics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Software Systems (AREA)
- General Engineering & Computer Science (AREA)
- Computational Linguistics (AREA)
- Probability & Statistics with Applications (AREA)
- Computing Systems (AREA)
- Databases & Information Systems (AREA)
- Computational Mathematics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Mathematical Analysis (AREA)
- Mathematical Optimization (AREA)
- Pure & Applied Mathematics (AREA)
- Molecular Biology (AREA)
- Health & Medical Sciences (AREA)
- Fuzzy Systems (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Algebra (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The application discloses an industrial time sequence data retrieval method based on a rail transit industrial internet, which comprises the following steps: step 1, acquiring a time sequence data set in a train running process in a rail transit system, and carrying out pictorial transformation on the time sequence data set to generate a picture data set; step 2, constructing a convolutional neural network model, training the convolutional neural network model by using a historical data set in a rail transit system, and performing feature extraction on data in the picture data set by using the trained convolutional neural network model to generate a feature vector; and 3, calculating the similarity between the characteristic vector and the data in the historical data set, and recording the data with the highest similarity as retrieval data of the data in the time sequence data set. Through the technical scheme in the application, the time sequence data in the rail transit system are subjected to imaging, so that the data coverage which can be analyzed is more complete, and the effectiveness and the accuracy of rail transit time sequence data retrieval are improved.
Description
Technical Field
The application relates to the technical field of rail transit information data processing, in particular to an industrial time sequence data retrieval method based on a rail transit industrial internet.
Background
In recent years, industrial internet has emerged worldwide, featuring a new and significant engineering technology and industrial application featuring an all-round and deep integration of internet and new-generation information technology with industrial systems.
The rail transit industrial internet platform is a key carrier for implementing landing and ecological construction of an industrial internet in the rail transit industry, wherein time sequence data in industrial data accounts for the majority, and the data are stored on an industrial internet cloud platform. When data retrieval is carried out on the rail transit industrial internet platform, the characteristics of rail transit data need to be fully considered, namely, the data dimension is high, the data volume is large, and the time sequence is strong.
The research on the data retrieval technology of the rail transit industry internet platform is the key for exerting the data value of the industry. The data retrieval aims at better discovering knowledge and experience hidden in data in the industry, improving the query efficiency of people in data expansion, shortening the query time in mass data, enabling practitioners to access required and interested data more quickly, and covering various related categories such as train operation data, train maintenance data, equipment manufacturing data, electric service state data and the like in the rail transit field.
In the prior art, linear matching is generally performed on the feature vectors of the data, and distance measurement is linearly performed on the feature vectors in the industrial internet cloud platform to obtain the most similar data, so that data retrieval is completed. With the increase of data volume, data retrieval is changed from small-scale retrieval to large-scale data retrieval, and when a large amount of industrial time sequence data are contained on an industrial internet cloud platform, the queried features are compared with the features of all data in a database one by one, so that unacceptable time cost is brought.
Disclosure of Invention
The purpose of this application lies in: the time sequence data in the rail transit system is subjected to imaging, so that the data coverage which can be analyzed is more complete, and the effectiveness and the accuracy of rail transit time sequence data retrieval are improved.
The technical scheme of the application is as follows: the method for retrieving the industrial time series data based on the rail transit industrial Internet comprises the following steps:
step 1, acquiring a time sequence data set in a train running process in a rail transit system, and performing pictorial transformation on the time sequence data set to generate a picture data set;
step 2, constructing a convolutional neural network model, training the convolutional neural network model by using a historical data set in the rail transit system, and performing feature extraction on data in the picture data set by using the trained convolutional neural network model to generate a feature vector, wherein the historical data set is generated by performing pictorial transformation on historical time sequence data;
and 3, calculating the similarity between the feature vector and the data in the historical data set, and recording the data with the highest similarity as the retrieval data of the data in the time sequence data set.
In any one of the above technical solutions, further, in step 1, performing a pictorial transformation on the time series data set specifically includes:
step 11, performing normalization processing on the data in the time sequence data set, and replacing the data with a trigonometric function to generate a trigonometric function sequence, wherein a calculation formula of the trigonometric function sequence is as follows:
X={x 1 ,…,x i ,…,x n }
wherein i =1,2, \8230;, n,for the ith time series data x i Corresponding normalization value(s), in conjunction with a corresponding normalization value>Φ i Is the normalized value->Corresponding ith trigonometric function data in the trigonometric function sequence, wherein X is the time sequence data set, and n is the length of the time sequence data set X;
step 12, performing matrix transformation calculation according to the trigonometric function sequence to generate an image transformation matrix;
and step 13, performing color mapping according to the image transformation matrix to generate the picture data set.
In any one of the above technical solutions, further, the calculation formula of the image transformation matrix is:
wherein I is an n-order identity matrix, GASF is the image transformation matrix,is an intermediate matrix.
In any one of the above technical solutions, further, the time series data set includes train operation speed data, gear data, and train sensor characteristic data.
In any of the above technical solutions, further, the calculation formula of the similarity is:
wherein A is a feature vector, B is a historical data set, r (A, B) is the similarity between the feature vector A and the historical data set B,is an average of the data in the feature vector A>Is the average of the data in the historical data set B.
The beneficial effect of this application is:
according to the technical scheme, the time sequence data in the running process of the train in the rail transit system are subjected to picture transformation, particularly the time sequence data detected by a sensor of industrial equipment are used as the input of a convolutional neural network model, and therefore data retrieval is facilitated. By carrying out picture change on the time sequence data, the data coverage area during retrieval and analysis is enlarged, so that the data retrieval method in the application has good universality.
According to the data retrieval method, the convolutional neural network model is constructed, and the time sequence data after the picture is retrieved in the industry database by the convolutional neural network model, so that the data retrieval method has strong adaptability, the characteristic extraction of the time sequence data can be rapidly completed under complex environmental information, and the effectiveness and accuracy of data retrieval and the usability and efficiency of the rail transit time sequence data retrieval are greatly improved.
Drawings
The advantages of the above and/or additional aspects of the present application will become apparent and readily appreciated from the following description of the embodiments, taken in conjunction with the accompanying drawings of which:
FIG. 1 is a schematic flow chart diagram of an industrial time series data retrieval method based on a rail transit industrial Internet according to one embodiment of the present application;
FIG. 2 is a schematic flow diagram of a data-graphing process according to one embodiment of the application;
FIG. 3 is a schematic diagram of constructing a convolutional neural network model according to one embodiment of the present application.
Detailed Description
In order that the above objects, features and advantages of the present application can be more clearly understood, the present application will be described in further detail with reference to the accompanying drawings and detailed description. It should be noted that the embodiments and features of the embodiments of the present application may be combined with each other without conflict.
In the following description, numerous specific details are set forth in order to provide a thorough understanding of the present application, however, the present application may be practiced in other ways than those described herein, and therefore the scope of the present application is not limited by the specific embodiments disclosed below.
As shown in fig. 1, the embodiment provides an industrial time series data retrieval method based on a rail transit industrial internet, and the method includes:
step 1, acquiring a time sequence data set in a train running process in a rail transit system, and performing pictorial transformation on the time sequence data set to generate a picture data set, wherein the time sequence data set comprises a plurality of time sequence data, the time sequence data can be train running speed data, gear data and train sensor characteristic data, and the train sensor characteristic data can be pantograph data and voltage data.
Specifically, in the embodiment, the audio and video information acquired by the industrial camera and the track traffic concentration data acquired by the track traffic sensor are used as a time sequence data set, and track traffic time sequence data retrieval is performed on texture features, color features, motion features, transformation features, track traffic concentration data and the like of track traffic in the time sequence data set. Such as travel speed data, gear data, train line data, etc., of the automatic driving data.
Further, in step 1, performing a pictorial transformation on the time series data set, specifically including:
step 11, normalizing the data in the time sequence data set, and replacing the data with a trigonometric function to generate a trigonometric function sequence, wherein the calculation formula of the trigonometric function sequence is as follows:
X={x 1 ,…,x i ,…,x n }
wherein i =1,2, \8230, n,for the ith time series data x i Corresponding normalization value->Φ i Is a normalized value>The ith trigonometric function data in the corresponding trigonometric function sequence, X is time sequence data, and n is the length of the time sequence data X;
in particular, as shown in figure 2, setting the acquired time sequence data as X = { X = 1 ,…,x i ,…,x n The method comprises the steps of (1) }, i =1,2, \ 8230;, n is the length of time sequence data X, and the time sequence data X is compressed to [ -1,1 ] by using a normalization processing method for data in the time sequence data set]The normalized calculation formula is:
in the formula (I), the compound is shown in the specification,for the ith time series data x i The corresponding normalization values, max (X) and min (X), are the maximum data and minimum data, respectively, in the time series data set.
Due to the ith time series data x i Normalized valueTherefore, instead of using trigonometric functions, a sequence of trigonometric functions is generated, namely:
the trigonometric function relationship shows that: phi i ∈[0,π]And sin (phi) i )≥0。
Step 12, performing matrix transformation calculation according to the trigonometric function sequence to generate an image transformation matrix;
further, the calculation formula of the image transformation matrix is as follows:
wherein I is an n-order identity matrix having a length equal to that of the time-series data X, GASF is an image transformation matrix,is an intermediate matrix.
And step 13, performing color mapping according to the image transformation matrix to generate a picture data set.
Specifically, when performing color mapping, one of the existing tab20c method and the rainbow method may be adopted, and the rainbow method is taken as an example in the embodiment for description.
The rainbow color mapping is a frequently used color mapping diagram, namely, data in a certain range and colors in a certain range are corresponding, different colors represent different sizes of the data, and the diagram is very visual and clear when displayed, and subsequent convolutional neural network feature extraction is easy to perform.
Step 2, constructing a convolutional neural network model, training the convolutional neural network model by utilizing a historical data set in a rail transit system, and performing feature extraction on data in a picture data set by utilizing the trained convolutional neural network model to generate a feature vector, wherein the historical data set is generated by performing picture transformation on historical time sequence data, and the historical data can be obtained from data in an industry database;
specifically, the process of generating the historical data set from the historical time series data through the pictorial transformation is similar to the process of generating the picture data set, and is not repeated here.
As shown in fig. 3, a historical data set is used as an input of a convolutional neural network model, calculation is performed layer by layer from an input layer through forward propagation, local features after various data integration and classification in a rail transit system are obtained through convolution operation of convolutional layers which are alternately arranged and feature integration and classification of pooling layers, and local features obtained in the early stage are integrated and classified through full connection layers to form global features of data retrieval.
And after the training of the convolutional neural network model is finished, taking the picture data set as input and bringing the picture data set into the trained convolutional neural network model, repeating the operation process, performing feature extraction on the data in the picture data set to generate feature vectors, and taking the feature vectors as the retrieval basis of the data in the picture data set.
And 3, calculating the similarity between the characteristic vector and the data in the historical data set, and recording the data with the highest similarity as retrieval data of the data in the time sequence data set.
Specifically, in this embodiment, the similarity between the data in the historical data set and the input data (the data in the picture data set) is calculated through a convolutional neural network model, and the data with the highest similarity is used as the search data to complete the whole search process, where the calculation formula of the similarity is:
wherein A is a feature vector, B is a history data set, and r (A, B) is a feature vectorThe similarity between a and the historical data set B,is the average of the data in the feature vector A, <' >>The average value of the data in the historical data set B is obtained, wherein the feature vector A and the historical data set B have the same dimension, are n dimensions, and have the same length as the time series data X.
Further, in order to ensure the training effect of the convolutional neural network model, when the convolutional neural network model is trained by using the historical data set in the rail transit system, the method further comprises the following steps: completing the historical data set, specifically comprising:
when the historical data is judged to have missing data, carrying out missing judgment on the historical data in the preset interval at the missing data according to the preset interval, if the historical data in the preset interval has missing, adjusting the preset interval, and carrying out the missing judgment again according to the adjusted preset interval; if the data is not missing, calculating the average value of the historical data in the preset interval, recording the average value as filling data, and performing completion processing on the missing data by using the filling data, wherein the method for judging the data missing can be realized by adopting the prior art, and the details are not repeated here.
The technical scheme of the present application is described in detail above with reference to the accompanying drawings, and the present application provides an industrial time series data retrieval method based on a rail transit industry internet, which includes: step 1, acquiring a time sequence data set in a train running process in a rail transit system, and carrying out pictorial transformation on the time sequence data set to generate a picture data set; step 2, constructing a convolutional neural network model, training the convolutional neural network model by using a historical data set in the rail transit system, and performing feature extraction on data in the picture data set by using the trained convolutional neural network model to generate a feature vector; and 3, calculating the similarity between the characteristic vector and the data in the historical data set, and recording the data with the highest similarity as retrieval data of the data in the time sequence data set. Through the technical scheme in the application, the time sequence data in the rail transit system are subjected to imaging, so that the data coverage which can be analyzed is more complete, and the effectiveness and the accuracy of rail transit time sequence data retrieval are improved.
The steps in the present application may be sequentially adjusted, combined, and subtracted according to actual requirements.
The units in the device can be merged, divided and deleted according to actual requirements.
Although the present application has been disclosed in detail with reference to the accompanying drawings, it is to be understood that such description is merely illustrative and is not intended to limit the application of the present application. The scope of the present application is defined by the appended claims and may include various modifications, adaptations, and equivalents of the invention without departing from the scope and spirit of the application.
Claims (3)
1. An industrial time sequence data retrieval method based on a rail transit industrial internet is characterized by comprising the following steps:
step 1, acquiring a time sequence data set in a train running process in a rail transit system, and carrying out pictorial transformation on the time sequence data set to generate a picture data set;
in step 1, performing a pictorial transformation on the time series data set specifically includes:
step 11, performing normalization processing on the data in the time sequence data set, and replacing the data with a trigonometric function to generate a trigonometric function sequence, wherein a calculation formula of the trigonometric function sequence is as follows:
X={x 1 ,…,x i ,…,x n }
wherein i =1,2, \8230;, n,for the ith time series data x i Corresponding normalization value->Φ i Is the normalized value->The ith trigonometric function data in the corresponding trigonometric function sequence, X is the time sequence data set, and n is the length of the time sequence data set X;
step 12, performing matrix transformation calculation according to the trigonometric function sequence to generate an image transformation matrix;
step 13, performing color mapping according to the image transformation matrix to generate the picture data set;
step 2, constructing a convolutional neural network model, training the convolutional neural network model by using a historical data set in the rail transit system, and performing feature extraction on data in the picture data set by using the trained convolutional neural network model to generate a feature vector, wherein the historical data set is generated by performing pictorial transformation on historical time sequence data;
and 3, calculating the similarity between the feature vector and the data in the historical data set, and recording the data with the highest similarity as the retrieval data of the data in the time sequence data set.
2. The industrial time series data retrieval method based on the rail transit industrial internet as claimed in claim 1, wherein the calculation formula of the image transformation matrix is as follows:
3. The industrial time series data retrieval method based on the rail transit industrial internet as claimed in any one of claims 1 to 2, wherein the time series data set includes train operation speed data, gear data, train sensor characteristic data.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010632977.0A CN111813830B (en) | 2020-07-02 | 2020-07-02 | Industrial time sequence data retrieval method based on rail transit industrial Internet |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010632977.0A CN111813830B (en) | 2020-07-02 | 2020-07-02 | Industrial time sequence data retrieval method based on rail transit industrial Internet |
Publications (2)
Publication Number | Publication Date |
---|---|
CN111813830A CN111813830A (en) | 2020-10-23 |
CN111813830B true CN111813830B (en) | 2023-03-28 |
Family
ID=72856098
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010632977.0A Active CN111813830B (en) | 2020-07-02 | 2020-07-02 | Industrial time sequence data retrieval method based on rail transit industrial Internet |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN111813830B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114218164A (en) * | 2021-12-17 | 2022-03-22 | 微梦创科网络科技(中国)有限公司 | Data anomaly detection method and system based on time sequence vector retrieval |
Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107122809A (en) * | 2017-04-24 | 2017-09-01 | 北京工业大学 | Neural network characteristics learning method based on image own coding |
CN107330127A (en) * | 2017-07-21 | 2017-11-07 | 湘潭大学 | A kind of Similar Text detection method retrieved based on textual image |
JP2018089142A (en) * | 2016-12-05 | 2018-06-14 | 学校法人同志社 | Method for estimating human's brain activity state from brain function imaging data |
CN109754126A (en) * | 2019-01-30 | 2019-05-14 | 银江股份有限公司 | Short-time Traffic Flow Forecasting Methods based on temporal correlation and convolutional neural networks |
CN110309867A (en) * | 2019-06-21 | 2019-10-08 | 北京工商大学 | A kind of Mixed gas identification method based on convolutional neural networks |
CN110503104A (en) * | 2019-08-29 | 2019-11-26 | 桂林电子科技大学 | A kind of remaining parking stall quantitative forecasting technique in short-term based on convolutional neural networks |
CN110599556A (en) * | 2019-09-05 | 2019-12-20 | 河海大学常州校区 | Method for converting time sequence into image based on improved recursive graph |
-
2020
- 2020-07-02 CN CN202010632977.0A patent/CN111813830B/en active Active
Patent Citations (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP2018089142A (en) * | 2016-12-05 | 2018-06-14 | 学校法人同志社 | Method for estimating human's brain activity state from brain function imaging data |
CN107122809A (en) * | 2017-04-24 | 2017-09-01 | 北京工业大学 | Neural network characteristics learning method based on image own coding |
CN107330127A (en) * | 2017-07-21 | 2017-11-07 | 湘潭大学 | A kind of Similar Text detection method retrieved based on textual image |
CN109754126A (en) * | 2019-01-30 | 2019-05-14 | 银江股份有限公司 | Short-time Traffic Flow Forecasting Methods based on temporal correlation and convolutional neural networks |
CN110309867A (en) * | 2019-06-21 | 2019-10-08 | 北京工商大学 | A kind of Mixed gas identification method based on convolutional neural networks |
CN110503104A (en) * | 2019-08-29 | 2019-11-26 | 桂林电子科技大学 | A kind of remaining parking stall quantitative forecasting technique in short-term based on convolutional neural networks |
CN110599556A (en) * | 2019-09-05 | 2019-12-20 | 河海大学常州校区 | Method for converting time sequence into image based on improved recursive graph |
Also Published As
Publication number | Publication date |
---|---|
CN111813830A (en) | 2020-10-23 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109241349B (en) | Monitoring video multi-target classification retrieval method and system based on deep learning | |
CN108197326B (en) | Vehicle retrieval method and device, electronic equipment and storage medium | |
CN112069868A (en) | Unmanned aerial vehicle real-time vehicle detection method based on convolutional neural network | |
CN112163447B (en) | Multi-task real-time gesture detection and recognition method based on Attention and Squeezenet | |
CN117496384B (en) | Unmanned aerial vehicle image object detection method | |
CN106844636A (en) | A kind of unstructured data processing method based on deep learning | |
CN114005078B (en) | Vehicle weight identification method based on double-relation attention mechanism | |
CN114022697A (en) | Vehicle re-identification method and system based on multitask learning and knowledge distillation | |
CN112836346B (en) | Motor fault diagnosis method based on CN and PCA, electronic equipment and medium | |
CN111079748A (en) | Method for detecting oil throwing fault of rolling bearing of railway wagon | |
CN111813830B (en) | Industrial time sequence data retrieval method based on rail transit industrial Internet | |
Saveliev et al. | Method for automated generation of road accident scene sketch based on data from mobile device camera | |
CN114743128B (en) | Multi-mode northeast tiger re-identification method and device based on heterogeneous neural network | |
CN115937540A (en) | Image Matching Method Based on Transformer Encoder | |
CN112668662B (en) | Outdoor mountain forest environment target detection method based on improved YOLOv3 network | |
CN111178370B (en) | Vehicle searching method and related device | |
CN117037085A (en) | Vehicle identification and quantity statistics monitoring method based on improved YOLOv5 | |
CN116070985B (en) | Dangerous chemical vehicle loading and unloading process identification method | |
CN115984634B (en) | Image detection method, apparatus, device, storage medium, and program product | |
CN116468784A (en) | Visual position identification method, system and device based on attention compression coding feature | |
CN110750876A (en) | Bearing data model training and using method | |
CN111061774B (en) | Search result accuracy judging method and device, electronic equipment and storage medium | |
CN115661097A (en) | Object surface defect detection method and system | |
CN114722704A (en) | Wheel wear prediction network model training method and device | |
CN114706902A (en) | Speed reducer data sharing method based on knowledge graph |
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 |