CN113225300B - Big data analysis method based on image - Google Patents
Big data analysis method based on image Download PDFInfo
- Publication number
- CN113225300B CN113225300B CN202010948080.9A CN202010948080A CN113225300B CN 113225300 B CN113225300 B CN 113225300B CN 202010948080 A CN202010948080 A CN 202010948080A CN 113225300 B CN113225300 B CN 113225300B
- Authority
- CN
- China
- Prior art keywords
- image
- feature
- images
- pictures
- utilizing
- 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
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/51—Indexing; Data structures therefor; Storage structures
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/55—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/50—Information retrieval; Database structures therefor; File system structures therefor of still image data
- G06F16/58—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually
- G06F16/583—Retrieval characterised by using metadata, e.g. metadata not derived from the content or metadata generated manually using metadata automatically derived from the content
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/951—Indexing; Web crawling techniques
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/23—Clustering techniques
- G06F18/232—Non-hierarchical techniques
- G06F18/2321—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions
- G06F18/23213—Non-hierarchical techniques using statistics or function optimisation, e.g. modelling of probability density functions with fixed number of clusters, e.g. K-means clustering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/28—Quantising the image, e.g. histogram thresholding for discrimination between background and foreground patterns
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/20—Image preprocessing
- G06V10/30—Noise filtering
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V10/00—Arrangements for image or video recognition or understanding
- G06V10/40—Extraction of image or video features
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/02—Network architectures or network communication protocols for network security for separating internal from external traffic, e.g. firewalls
- H04L63/0227—Filtering policies
-
- H—ELECTRICITY
- H04—ELECTRIC COMMUNICATION TECHNIQUE
- H04L—TRANSMISSION OF DIGITAL INFORMATION, e.g. TELEGRAPHIC COMMUNICATION
- H04L63/00—Network architectures or network communication protocols for network security
- H04L63/14—Network architectures or network communication protocols for network security for detecting or protecting against malicious traffic
- H04L63/1441—Countermeasures against malicious traffic
- H04L63/145—Countermeasures against malicious traffic the attack involving the propagation of malware through the network, e.g. viruses, trojans or worms
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Computer Security & Cryptography (AREA)
- Databases & Information Systems (AREA)
- Computer Networks & Wireless Communication (AREA)
- Multimedia (AREA)
- Signal Processing (AREA)
- Computing Systems (AREA)
- Computer Hardware Design (AREA)
- Library & Information Science (AREA)
- General Health & Medical Sciences (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Evolutionary Biology (AREA)
- Virology (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Health & Medical Sciences (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Probability & Statistics with Applications (AREA)
- Evolutionary Computation (AREA)
- Software Systems (AREA)
- Image Analysis (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention relates to the technical field of image analysis, in particular to a big data analysis method based on an image, which comprises the following steps of 1, image acquisition: step 2, image preprocessing: step 3, feature extraction: step 4, establishing an image feature index: and 5, matching image features. The invention has novel design and sophisticated method, converts the high-dimensional image recognition problem into the recognition problem of the feature expression vector by utilizing the PCA algorithm, greatly reduces the complexity of calculation, reduces the recognition error caused by redundant information, improves the recognition precision and the working efficiency, simultaneously reduces the required storage space, saves the cost of storage equipment, and can output the image with high similarity to low similarity by image feature matching, thereby improving the recognition degree.
Description
Technical Field
The invention relates to the technical field of image analysis, in particular to a big data analysis method based on an image.
Background
Since the 20 th century 60 s, there have been many research achievements in image analysis, and image analysis techniques for specific problems and applications gradually developed toward establishing general theories. The image analysis is closely related to the research content of image processing, computer graphics and the like, and is mutually crossed and overlapped. However, image processing mainly studies image transmission, storage, enhancement and restoration, computer graphics mainly studies a point, line, plane and volume representation method and a visual information display method, image analysis focuses on a description method for constructing images, and more particularly, symbols represent various images, rather than computing the images themselves, and reasoning is performed by using various related knowledge. Image analysis is also germane to research on human vision, where research on certain recognizable modules in human vision mechanisms may contribute to improved computer vision capabilities.
However, the conventional image analysis method is simple, and the image dimension is large, so that the storage space is excessively occupied, the storage cost is increased, the analysis time is also increased, and the working efficiency is influenced to a certain extent. Accordingly, one skilled in the art provides an image-based big data analysis method to solve the problems set forth in the background art described above.
Disclosure of Invention
The present invention is directed to a method for analyzing big data based on an image, so as to solve the problems mentioned in the background art.
In order to achieve the purpose, the invention provides the following technical scheme: an image-based big data analysis method, comprising the steps of:
step 1, image acquisition: collecting related images and pictures in the internet through a web crawler according to the specified keywords;
the collected images and pictures are used for isolating trojan and network attacks and searching and killing trojan and network attacks through a network firewall and antivirus software;
step 2, image preprocessing: carrying out background difference and filtering denoising on the collected images and pictures, and further finishing reduction and amplification conversion so as to obtain fixed-size images and picture samples;
carrying out gray processing on fixed-size images and picture samples, and enhancing the images by a median filtering and morphological method to ensure that main texture features of the images and the pictures are clear and distinguishable;
processing the images and pictures by utilizing a histogram equalization technology to enable the images and pictures to meet uniform mean values and variances so as to obtain standard images and pictures;
step 3, feature extraction: establishing a Gaussian pyramid of the image, partitioning the image to enable the image to present a hierarchical pyramid structure, further respectively counting the characteristics of each block of substructure, and splicing into complete characteristics after all structural characteristics are counted;
carrying out dimension processing on the image and the picture by utilizing a PCA algorithm, and storing the processed image and the picture into a gallery;
carrying out feature set discretization processing by using a K-means clustering method, and converting features after discretization processing into neighborhood characteristics;
step 4, establishing an image feature index: rapidly retrieving the image characteristics by using an inverted index technology;
step 5, image feature matching: setting a retrieval feature, after quantization, determining an index entry Wi in reverse retrieval corresponding to the feature to be retrieved, further taking a series of related index features corresponding to the index entry Wi as candidate matching results, and defining a matching function between two image feature vectors X and Y as follows: fq (x, y) = σ q (x), q (y).
As a further aspect of the invention: the specific sub-steps of the dimension reduction processing are as follows:
s1, aiming at the existing data set P = (P1, PZ \8230; pn) through a formulaCalculating an average value;
s2, subtracting the mean value from the original data to obtain Pi '= Pi-m, and then obtaining the Pi' = Pi-m through a formulaCalculating a covariance matrix;
S3, calculating eigenvalues E1 and E2 of a covariance matrix, 823060, 8230Em and eigenvectors EV1 and EV2, 82308230, EVm, further arranging the eigenvalues from large to small to obtain E1', E2' \8230, em 'and corresponding eigenvectors EV1', EV2 '\8230, 8230and EVm';
s4, selecting the first 32 data according to the size of the characteristic value, reducing the original data from the original 128 dimensions to the new 32 dimensions, and finishing the dimension reduction processing on the original data;
as a further scheme of the invention: the feature vector represents the distribution direction of the original data, and the greater the feature value corresponding to the feature vector, the more important the feature vector is.
As a further aspect of the invention: the method for discretizing the feature set comprises the following substeps of:
a1, extracting a large number of feature sets from a gallery, discretizing the feature sets by utilizing K-means clustering, wherein a clustering mark is an index value of an image or a picture, and dividing the feature sets into K discrete clusters;
a2, dividing each feature into the clusters closest to the feature by utilizing an iterative mode, wherein a single connection method is adopted in the inter-class distance measurement, and for any two clusters Ci and Cj, the calculation formula of the single connection method is as follows:
dist(ci,cj)=min{dist(xi,xj)|xi∈ci,xj∈cj}。
as a further aspect of the invention: the number of K values in A1 is 10000.
As a further scheme of the invention: in step 5, q is a quantization function, and the feature vector is mapped to the cluster center closest to the feature vector.
Compared with the prior art, the invention has the beneficial effects that: the invention has novel design and sophisticated method, converts the high-dimensional image recognition problem into the recognition problem of the feature expression vector by utilizing the PCA algorithm, greatly reduces the complexity of calculation, reduces the recognition error caused by redundant information, improves the recognition precision and the working efficiency, simultaneously reduces the required storage space, saves the cost of storage equipment, and can output the image with high similarity to low similarity by image feature matching, thereby improving the recognition degree.
Drawings
FIG. 1 is a step diagram of a method for image-based big data analysis.
Detailed Description
Referring to fig. 1, in an embodiment of the present invention, an image-based big data analysis method includes the following steps:
step 1, image acquisition: collecting related images and pictures in the internet through a web crawler according to the specified keywords;
the collected images and pictures are used for isolating trojan and network attacks and searching and killing trojan and network attacks through a network firewall and antivirus software;
step 2, image preprocessing: carrying out background difference and filtering denoising on the collected images and pictures, and further finishing reduction and amplification conversion so as to obtain fixed-size images and picture samples;
carrying out gray processing on fixed-size images and picture samples, and enhancing the images by a median filtering and morphological method to ensure that main texture features of the images and the pictures are clear and distinguishable;
processing the images and pictures by using a histogram equalization technology to enable the images and pictures to meet uniform mean values and variances, and further obtaining standard images and pictures;
step 3, feature extraction: establishing a Gaussian pyramid of the image, carrying out blocking processing on the image to enable the image to present a hierarchical pyramid structure, further respectively counting the characteristics of each block of substructure, and splicing into complete characteristics after all structural characteristics are counted;
carrying out dimension processing on the image and the picture by utilizing a PCA algorithm, and storing the processed image and the picture into a gallery;
carrying out feature set discretization by using a K-means clustering method, and converting the discretized features into neighborhood characteristics;
step 4, establishing an image feature index: rapidly retrieving the image characteristics by using an inverted index technology;
step 5, image feature matching: setting a retrieval feature, after quantization, determining an index item Wi in reverse retrieval corresponding to the feature to be retrieved, further taking a series of related index features corresponding to the index item Wi as candidate matching results, and defining a matching function between two image feature vectors X and Y as follows: fq (x, y) = σ q (x), q (y).
Further, the dimension reduction processing has the following specific sub-steps:
s1, aiming at the existing data set P = (P1, PZ \8230; pn) through a formulaCalculating an average value;
s2, subtracting the mean value from the original data to obtain Pi '= Pi-m, and then obtaining the Pi' = Pi-m through a formulaCalculating a covariance matrix;
s3, calculating eigenvalues E1 and E2 of a covariance matrix, 823060, 8230Em and eigenvectors EV1 and EV2, 82308230, EVm, further arranging the eigenvalues from large to small to obtain E1', E2' \8230, em 'and corresponding eigenvectors EV1', EV2 '\8230, 8230and EVm';
s4, selecting the first 32 data according to the size of the characteristic value, reducing the original data from the original 128 dimensions to the new 32 dimensions, and finishing the dimension reduction processing on the original data;
further, the feature vector represents the distribution direction of the original data, and the larger the feature value corresponding to the feature vector is, the more important the feature vector is.
Further, the method for discretizing the feature set comprises the following substeps:
a1, extracting a large number of feature sets from a gallery, discretizing the feature sets by utilizing K-means clustering, wherein a clustering mark is an index value of an image or a picture, and dividing the feature sets into K discrete clusters;
a2, dividing each feature into the clusters closest to the feature by utilizing an iterative mode, wherein a single connection method is adopted in the inter-class distance measurement, and for any two clusters Ci and Cj, the calculation formula of the single connection method is as follows:
dist(ci,cj)=min{dist(xi,xj)|xi∈ci,xj∈cj}。
furthermore, the K value in A1 is 10000.
Further, q in step 5 is a quantization function, and the feature vector is mapped to the cluster center closest to the feature vector.
Comparative example:
selecting a same keyword, and analyzing corresponding images by using the method and the traditional method to finally obtain the following data:
occupancy rate of storage space | Match rate | Time improvement rate | |
Tradition of | 5% | 78% | 15% |
This application | 0.7% | 92% | 43% |
In summary, the following steps: the invention has novel design and sophisticated method, converts the high-dimensional image recognition problem into the recognition problem of the feature expression vector by utilizing the PCA algorithm, greatly reduces the complexity of calculation, reduces the recognition error caused by redundant information, improves the recognition precision and the working efficiency, simultaneously reduces the required storage space, saves the cost of storage equipment, and can output the image with high similarity to low similarity by image feature matching, thereby improving the recognition degree.
The above description is only for the preferred embodiment of the present invention, but the scope of the present invention is not limited thereto, and any person skilled in the art should be considered to be within the technical scope of the present invention, and the technical solutions and the inventive concepts thereof according to the present invention are equivalent to or changed within the technical scope of the present invention.
Claims (5)
1. An image-based big data analysis method is characterized by comprising the following steps:
step 1, image acquisition: collecting related images and pictures in the Internet through a web crawler according to the specified keywords;
the collected images and pictures are isolated and checked and killed by Trojan and network attacks through a network firewall and antivirus software;
step 2, image preprocessing: carrying out background difference and filtering denoising on the collected images and pictures, and further finishing reduction and amplification conversion so as to obtain fixed-size images and picture samples;
carrying out gray processing on images and picture samples with fixed sizes, and enhancing the images by a median filtering and morphological method to ensure that main texture features of the images and the pictures are clear and distinguishable;
processing the images and pictures by utilizing a histogram equalization technology to enable the images and pictures to meet uniform mean values and variances so as to obtain standard images and pictures;
step 3, feature extraction: establishing a Gaussian pyramid of the image, partitioning the image to enable the image to present a hierarchical pyramid structure, further respectively counting the characteristics of each block of substructure, and splicing into complete characteristics after all structural characteristics are counted;
carrying out dimensionality reduction on the image and the picture by utilizing a PCA algorithm, and storing the processed image and the picture into a gallery;
carrying out feature set discretization processing by using a K-means clustering method, and converting the discretized features into neighborhood features;
step 4, establishing an image feature index: rapidly retrieving image features by utilizing an inverted index technology;
step 5, image feature matching: setting a retrieval feature, after quantization, determining an index entry Wi in reverse retrieval corresponding to the feature to be retrieved, further taking a series of related index features corresponding to the index entry Wi as candidate matching results, and defining a matching function between two image feature vectors x and y as follows:;
the feature set discretization processing method comprises the following substeps:
a1, extracting a large number of feature sets from a gallery, discretizing the feature sets by utilizing K-means clustering, wherein a clustering mark is an index value of an image or a picture, and dividing the feature sets into K discrete clusters;
2. an image-based big data analysis method according to claim 1, wherein the dimension reduction process comprises the following specific sub-steps:
s1, aiming at the existing data set P = (P1, P2 \8230; pn), the formula is adoptedCalculating an average value;
s2, subtracting the mean value from the original data to obtainThen by the formulaCalculating a covariance matrix;
s3, calculating eigenvalues E1, E2 \8230ofthe covariance matrix, \8230Emand eigenvectors EV1, EV2 \8230, 8230and EVm, and further arranging the eigenvalues in sequence from large to small to obtainAnd corresponding feature vectors;
S4, selecting the first 32 data according to the size of the characteristic value, reducing the original data from the original 128 dimensions to the new 32 dimensions, and finishing the dimension reduction processing of the original data.
3. The method of claim 2, wherein the eigenvector represents the distribution direction of the original data, and the larger the eigenvalue corresponding to the eigenvector is, the more important the eigenvector is.
4. The image-based big data analysis method of claim 1, wherein the number of K values in A1 is 10000.
5. The method of claim 1, wherein q in step 5 is a quantization function, and the feature vector is mapped to the nearest cluster center.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010948080.9A CN113225300B (en) | 2020-09-10 | 2020-09-10 | Big data analysis method based on image |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN202010948080.9A CN113225300B (en) | 2020-09-10 | 2020-09-10 | Big data analysis method based on image |
Publications (2)
Publication Number | Publication Date |
---|---|
CN113225300A CN113225300A (en) | 2021-08-06 |
CN113225300B true CN113225300B (en) | 2022-12-27 |
Family
ID=77086003
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN202010948080.9A Active CN113225300B (en) | 2020-09-10 | 2020-09-10 | Big data analysis method based on image |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN113225300B (en) |
Families Citing this family (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN114595350B (en) * | 2021-12-08 | 2024-04-26 | 拓尔思信息技术股份有限公司 | Billion-level image quick searching method |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778281A (en) * | 2015-05-06 | 2015-07-15 | 苏州搜客信息技术有限公司 | Image index parallel construction method based on community analysis |
CN106355202A (en) * | 2016-08-31 | 2017-01-25 | 广州精点计算机科技有限公司 | Image feature extraction method based on K-means clustering |
CN109919208A (en) * | 2019-02-25 | 2019-06-21 | 中电海康集团有限公司 | A kind of appearance images similarity comparison method and system |
CN110717530A (en) * | 2019-09-27 | 2020-01-21 | 中国中医科学院 | Automatic rechecking method for traditional Chinese medicine decoction piece dispensing based on image recognition technology |
Family Cites Families (1)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP2284796A4 (en) * | 2008-04-28 | 2012-10-31 | Univ Osaka Prefect Public Corp | Method for creating image database for object recognition, processing device, and processing program |
-
2020
- 2020-09-10 CN CN202010948080.9A patent/CN113225300B/en active Active
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104778281A (en) * | 2015-05-06 | 2015-07-15 | 苏州搜客信息技术有限公司 | Image index parallel construction method based on community analysis |
CN106355202A (en) * | 2016-08-31 | 2017-01-25 | 广州精点计算机科技有限公司 | Image feature extraction method based on K-means clustering |
CN109919208A (en) * | 2019-02-25 | 2019-06-21 | 中电海康集团有限公司 | A kind of appearance images similarity comparison method and system |
CN110717530A (en) * | 2019-09-27 | 2020-01-21 | 中国中医科学院 | Automatic rechecking method for traditional Chinese medicine decoction piece dispensing based on image recognition technology |
Also Published As
Publication number | Publication date |
---|---|
CN113225300A (en) | 2021-08-06 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Sahbi et al. | Context-dependent kernels for object classification | |
Shen et al. | Non-negative matrix factorization clustering on multiple manifolds | |
Xie et al. | Texture classification via patch-based sparse texton learning | |
CN111340103B (en) | Feature layer fusion method and device based on graph embedding typical correlation analysis | |
CN110751027B (en) | Pedestrian re-identification method based on deep multi-instance learning | |
CN104966090B (en) | Realize the system and method that the vision word towards image understanding is generated and evaluated | |
Mishra et al. | Image mining in the context of content based image retrieval: a perspective | |
CN111400528A (en) | Image compression method, device, server and storage medium | |
Sundara Vadivel et al. | An efficient CBIR system based on color histogram, edge, and texture features | |
Ahmad et al. | Describing colors, textures and shapes for content based image retrieval-a survey | |
Jin et al. | Content-based image retrieval based on shape similarity calculation | |
CN109934852B (en) | Video description method based on object attribute relation graph | |
Liu et al. | Improving image retrieval by integrating shape and texture features | |
Khalaf et al. | Robust partitioning and indexing for iris biometric database based on local features | |
CN113592030B (en) | Image retrieval method and system based on complex value singular spectrum analysis | |
CN113225300B (en) | Big data analysis method based on image | |
CN103942572A (en) | Method and device for extracting facial expression features based on bidirectional compressed data space dimension reduction | |
Chatbri et al. | Sketch-based image retrieval by size-adaptive and noise-robust feature description | |
Priya et al. | Optimized content based image retrieval system based on multiple feature fusion algorithm | |
CN109978066B (en) | Rapid spectral clustering method based on multi-scale data structure | |
CN115131854A (en) | Global subspace face image clustering method based on fuzzy clustering | |
Fu et al. | Pedestrian detection by feature selected self-similarity features | |
Rajpoot et al. | Unsupervised learning of shape manifolds | |
Tuyet et al. | Adaptive content-based medical image retrieval based on local features extraction in shearlet domain | |
Ahmed et al. | Multimode image clustering using optimal image descriptor |
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 |