CN112613500A - Campus dynamic scoring system based on deep learning - Google Patents
Campus dynamic scoring system based on deep learning Download PDFInfo
- Publication number
- CN112613500A CN112613500A CN202011517003.4A CN202011517003A CN112613500A CN 112613500 A CN112613500 A CN 112613500A CN 202011517003 A CN202011517003 A CN 202011517003A CN 112613500 A CN112613500 A CN 112613500A
- Authority
- CN
- China
- Prior art keywords
- module
- image
- controller
- answer
- recognition model
- 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
- 238000013135 deep learning Methods 0.000 title claims abstract description 21
- 238000007781 pre-processing Methods 0.000 claims abstract description 16
- 238000012360 testing method Methods 0.000 claims abstract description 10
- 238000012549 training Methods 0.000 claims description 24
- 238000003062 neural network model Methods 0.000 claims description 10
- 238000012163 sequencing technique Methods 0.000 claims description 10
- 238000010276 construction Methods 0.000 claims description 6
- 239000011159 matrix material Substances 0.000 claims description 6
- 238000000034 method Methods 0.000 claims description 6
- 230000011218 segmentation Effects 0.000 claims description 6
- 238000012937 correction Methods 0.000 claims description 3
- 238000011161 development Methods 0.000 claims description 3
- 230000018109 developmental process Effects 0.000 claims description 3
- 238000003708 edge detection Methods 0.000 claims description 3
- 239000000284 extract Substances 0.000 claims description 3
- 238000000605 extraction Methods 0.000 claims description 3
- 230000007547 defect Effects 0.000 abstract description 3
- 238000004458 analytical method Methods 0.000 description 1
- 238000013473 artificial intelligence Methods 0.000 description 1
- 238000013528 artificial neural network Methods 0.000 description 1
- 210000004556 brain Anatomy 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 238000001914 filtration Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000003672 processing method Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- 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
- G06V10/22—Image preprocessing by selection of a specific region containing or referencing a pattern; Locating or processing of specific regions to guide the detection or recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F40/00—Handling natural language data
- G06F40/30—Semantic analysis
-
- 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
-
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
-
- 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
- G06V10/26—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion
- G06V10/267—Segmentation of patterns in the image field; Cutting or merging of image elements to establish the pattern region, e.g. clustering-based techniques; Detection of occlusion by performing operations on regions, e.g. growing, shrinking or watersheds
Abstract
The invention relates to a paper marking system, in particular to a campus dynamic paper marking system based on deep learning, which comprises a controller, wherein the controller is connected with a scanning image receiving module used for receiving a scanning image of an answer sheet, the controller is connected with an image preprocessing module used for preprocessing the scanning image, the image preprocessing module is connected with a test paper information identification module used for identifying and reading answer person information from the preprocessed image, the controller is connected with an answer area identification module used for identifying an answer area in the image, the controller is connected with an image cutting module used for cutting the image according to the identification result of the answer area, and the controller is connected with an image sorting module used for sorting the cut images according to the original answer sequence; the technical scheme provided by the invention can effectively overcome the defects that the prior art is only suitable for the answer sheet of the fixed plate type and the marking is not accurate enough.
Description
Technical Field
The invention relates to an examination paper marking system, in particular to a campus dynamic examination paper marking system based on deep learning.
Background
With the rapid development of computers and artificial intelligence, the development of the computer-based intelligent education system is greatly improved in work and life, and the field of education is particularly prominent. The traditional paper marking mode has a plurality of problems, on one hand, great workload is formed for teachers, and even lesson preparation time of the teachers is shortened; on the other hand, the reading and writing of the subjective questions has strong subjectivity, and the reading and writing errors can be caused by long-time continuous reading and writing according to the analysis of the working quality and the working duration of the human brain.
The traditional electronic marking paper mainly aims at objective questions, and adopts a processing method of reading data of a filling-up answer sheet and comparing the data with standard answers, so that the marking speed is effectively improved.
However, for subjective questions, the conventional examination paper reading system can only read the answer sheet defined by the system itself, but cannot be compatible with other types of answer sheets. In addition, the conventional examination paper marking system for subjective questions is low in identification accuracy, so that the difference between the result of the examination paper marking system and the result of manual examination paper marking is large, and the examination paper marking is not accurate enough.
Disclosure of Invention
Technical problem to be solved
Aiming at the defects in the prior art, the invention provides a campus dynamic scoring system based on deep learning, which can effectively overcome the defects that the prior art is only suitable for fixed plate type answer sheets and scoring is not accurate enough.
(II) technical scheme
In order to achieve the purpose, the invention is realized by the following technical scheme:
a campus dynamic marking system based on deep learning comprises a controller, wherein the controller is connected with a scanning image receiving module used for receiving scanning images of answer sheets, the controller is connected with an image preprocessing module used for preprocessing the scanning images, the image preprocessing module is connected with a test paper information identification module used for identifying and reading information of answer persons from the preprocessed images, the controller is connected with an answer area identification module used for identifying answer areas in the images, the controller is connected with an image cutting module used for cutting the images according to the identification results of the answer areas, and the controller is connected with an image sorting module used for sorting the cut images according to the original answer order;
the controller is respectively connected with a character recognition model building module and a semantic recognition model building module, the character recognition model building module is connected with a character recognition model training module for training a character recognition model, and the semantic recognition model building module is connected with a semantic recognition model training module for training the semantic recognition model;
the controller is connected with an answer semantic storage module used for storing standard answer semantics, the controller is connected with a grading and summarizing module used for inputting the cut pictures into a character recognition model and a semantic recognition model and grading according to semantic recognition results, the controller is connected with a score sequencing module used for sequencing grading scores, and the controller is connected with a data display module used for displaying score sequencing.
Preferably, the image preprocessing module processes the scanned image based on a correction algorithm of deep learning to obtain a de-noised and enhanced test paper image, and then performs edge detection to find and record all edge contours in the scanned image.
Preferably, the answer area identification module searches for a closed frame with the largest area from all edge profiles, extracts the closed frame from the scanned image, and cuts a sub-closed frame in the closed frame to form a cut picture.
Preferably, the character recognition module constructed by the character recognition model construction module performs character recognition on the cut picture, and includes:
acquiring a cut picture containing characters to be recognized; inputting the cutting picture into a trained neural network model for feature extraction to obtain a feature map; and recognizing the literal characters in the feature map through a neural network model.
Preferably, the character recognition model training module collects a large number of closed frame images containing character characters and corresponding character recognition results, and inputs the constructed character recognition model for training.
Preferably, the semantic recognition of the character recognition result by the semantic recognition model constructed by the semantic recognition model construction module includes:
deleting nonsense words and stop words in the character recognition result, and performing word segmentation on the reserved characters; and encoding the character after word segmentation into a vector matrix, and inputting the vector matrix into a trained neural network model for semantic recognition.
Preferably, the semantic recognition model training module collects a large number of keywords containing the relevant knowledge points of the test paper and the characters in the problem solving process, and inputs the constructed semantic recognition model for training.
Preferably, when the semantic recognition model carries out semantic recognition on the character recognition result, the standard answer semantics are taken as a reference; and when the semantic recognition result is closer to the standard answer semantics, the score of the score summarizing module is higher.
Preferably, the scoring summarization module weights the scoring result of each cut picture according to the corresponding weight of the original answer sequence, calculates the scoring score, and packages the scoring score and sends the scoring score to the score ordering module.
Preferably, the data display module displays the score variation of each student in different time periods in the form of a dynamic line graph.
(III) advantageous effects
Compared with the prior art, the campus dynamic marking system based on deep learning provided by the invention can be compatible with various plate-type answer sheets, so that the cost brought by replacing the answer sheets can be reduced, and character recognition and semantic recognition can be performed through the neural network model, so that the character semantics on the answer sheets can be accurately and effectively presumed, the difference between the character semantics and manual marking is reduced, and the marking result is more accurate.
Drawings
In order to more clearly illustrate the embodiments of the present invention or the technical solutions in the prior art, the drawings used in the description of the embodiments or the prior art will be briefly described below. It is obvious that the drawings in the following description are only some embodiments of the invention, and that for a person skilled in the art, other drawings can be derived from them without inventive effort.
FIG. 1 is a schematic diagram of the system of the present invention.
Detailed Description
In order to make the objects, technical solutions and advantages of the embodiments of the present invention clearer, the technical solutions in the embodiments of the present invention will be clearly and completely described below with reference to the drawings in the embodiments of the present invention. It is to be understood that the embodiments described are only a few embodiments of the present invention, and not all embodiments. All other embodiments, which can be derived by a person skilled in the art from the embodiments given herein without making any creative effort, shall fall within the protection scope of the present invention.
A campus dynamic paper marking system based on deep learning is disclosed, as shown in figure 1, and comprises a controller, wherein the controller is connected with a scanning image receiving module for receiving a scanning image of an answer sheet, the controller is connected with an image preprocessing module for preprocessing the scanning image, the image preprocessing module is connected with a test paper information identification module for identifying and reading information of an answer person from a preprocessed image, the controller is connected with an answer area identification module for identifying an answer area in the image, the controller is connected with an image cutting module for cutting the image according to an answer area identification result, and the controller is connected with a picture sorting module for sorting cut pictures according to an original answer sequence.
The image preprocessing module processes the scanned image based on a correction algorithm of deep learning to obtain a de-noised and enhanced test paper image, and then carries out edge detection to find out and record all edge contours in the scanned image.
The answer area identification module searches for the closed frame with the largest area from all edge profiles, extracts the closed frame from the scanned image, and cuts the sub-closed frames in the closed frame to form a cut picture.
Through the image preprocessing module, the positions of the closed frame body and the sub-closed frame body can be accurately identified by the answer area identification module, all answer contents contained in the cutting picture are guaranteed, and the situation that the answer contents are missed due to inaccurate cutting positions is prevented.
The technical scheme is suitable for all different plate-type answer sheets containing the closed frame body and the sub-closed frame body, and the answer sheets can be identified no matter how the shapes and the positions of the closed frame body and the sub-closed frame body are.
The controller is respectively connected with the character recognition model building module and the semantic recognition model building module, the character recognition model building module is connected with the character recognition model training module for training the character recognition model, and the semantic recognition model building module is connected with the semantic recognition model training module for training the semantic recognition model.
The character recognition model constructed by the character recognition model construction module performs character recognition on the cut picture, and comprises the following steps: acquiring a cut picture containing characters to be recognized; inputting the cutting picture into a trained neural network model for feature extraction to obtain a feature map; and recognizing the literal characters in the feature map through a neural network model.
The character recognition model training module collects a large number of closed frame images containing character characters and corresponding character recognition results, and inputs the constructed character recognition model for training.
The semantic recognition module constructed by the semantic recognition module construction module carries out semantic recognition on the character recognition result, and the semantic recognition comprises the following steps: deleting nonsense words and stop words in the character recognition result, and performing word segmentation on the reserved characters; and encoding the character after word segmentation into a vector matrix, and inputting the vector matrix into a trained neural network model for semantic recognition.
The semantic recognition model training module collects a large number of keywords containing the relevant knowledge points of the test paper and character characters in the problem solving process, and inputs the constructed semantic recognition model for training.
In the technical scheme, the character recognition model is a model trained based on an HCCR-GoogLeNet neural network, the model has layer-by-layer flexible convolution kernel filtering, and a large number of characteristic graphs with the same size are obtained through convolution and combination of different scales.
The controller is connected with an answer semantic storage module used for storing standard answer semantics, the controller is connected with a grading and summarizing module used for inputting the cut pictures into the character recognition model and the semantic recognition model and grading according to semantic recognition results, the controller is connected with a score sequencing module used for sequencing grading scores, and the controller is connected with a data display module used for displaying score sequencing.
When the semantic recognition model carries out semantic recognition on the character recognition result, the standard answer semantics are taken as reference; and when the semantic recognition result is closer to the standard answer semantics, the score of the score summarizing module is higher. And the grading and summarizing module weights the grading result of each cut picture according to the corresponding weight of the original answer sequence, calculates the grading score and packs the grading score to be sent to the score sequencing module.
The data display module displays the score change of each student in different time periods in a dynamic line graph mode, so that teachers and students can feel the score change condition more intuitively.
The above examples are only intended to illustrate the technical solution of the present invention, but not to limit it; although the present invention has been described in detail with reference to the foregoing embodiments, it will be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not depart from the spirit and scope of the corresponding technical solutions.
Claims (10)
1. The utility model provides a campus developments scoring system based on deep learning which characterized in that: the image cutting device comprises a controller, wherein the controller is connected with a scanning image receiving module used for receiving a scanning image of an answer sheet, the controller is connected with an image preprocessing module used for preprocessing the scanning image, the image preprocessing module is connected with a test paper information identification module used for identifying and reading answer person information from the preprocessed image, the controller is connected with an answer area identification module used for identifying an answer area in the image, the controller is connected with an image cutting module used for cutting the image according to an answer area identification result, and the controller is connected with a picture sorting module used for sorting the cut pictures according to an original answer sequence;
the controller is respectively connected with a character recognition model building module and a semantic recognition model building module, the character recognition model building module is connected with a character recognition model training module for training a character recognition model, and the semantic recognition model building module is connected with a semantic recognition model training module for training the semantic recognition model;
the controller is connected with an answer semantic storage module used for storing standard answer semantics, the controller is connected with a grading and summarizing module used for inputting the cut pictures into a character recognition model and a semantic recognition model and grading according to semantic recognition results, the controller is connected with a score sequencing module used for sequencing grading scores, and the controller is connected with a data display module used for displaying score sequencing.
2. The deep learning based campus dynamic scoring system of claim 1, wherein: the image preprocessing module processes the scanned image based on a correction algorithm of deep learning to obtain a de-noised and enhanced test paper image, and then carries out edge detection to find out and record all edge contours in the scanned image.
3. The deep learning based campus dynamic scoring system of claim 2, wherein: the answer area identification module searches for a closed frame with the largest area from all edge profiles, extracts the closed frame from the scanned image, and cuts the sub-closed frames in the closed frame to form a cut picture.
4. The deep learning based campus dynamic scoring system of claim 3, wherein: the character recognition model constructed by the character recognition model construction module performs character recognition on the cut picture, and comprises the following steps:
acquiring a cut picture containing characters to be recognized; inputting the cutting picture into a trained neural network model for feature extraction to obtain a feature map; and recognizing the literal characters in the feature map through a neural network model.
5. The deep learning based campus dynamic scoring system of claim 4, wherein: the character recognition model training module collects a large number of closed frame images containing character characters and corresponding character recognition results, and inputs the constructed character recognition model for training.
6. The deep learning based campus dynamic scoring system of claim 4, wherein: the semantic recognition module constructed by the semantic recognition module construction module carries out semantic recognition on the character recognition result, and the semantic recognition comprises the following steps:
deleting nonsense words and stop words in the character recognition result, and performing word segmentation on the reserved characters; and encoding the character after word segmentation into a vector matrix, and inputting the vector matrix into a trained neural network model for semantic recognition.
7. The deep learning based campus dynamic scoring system of claim 6, wherein: the semantic recognition model training module collects a large number of keywords containing the relevant knowledge points of the test paper and character characters in the problem solving process, and inputs the constructed semantic recognition model for training.
8. The deep learning based campus dynamic scoring system of claim 6, wherein: when the semantic recognition model carries out semantic recognition on the character recognition result, the standard answer semantics are taken as reference; and when the semantic recognition result is closer to the standard answer semantics, the score of the score summarizing module is higher.
9. The deep learning based campus dynamic scoring system of claim 8, wherein: the grading summarizing module weights the grading result of each cut picture according to the corresponding weight of the original answer sequence, calculates the grading score and packs the grading score to be sent to the score sorting module.
10. The deep learning based campus dynamic scoring system of claim 9, wherein: and the data display module displays the score change of each student in different time periods in a dynamic line graph mode.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011517003.4A CN112613500A (en) | 2020-12-21 | 2020-12-21 | Campus dynamic scoring system based on deep learning |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202011517003.4A CN112613500A (en) | 2020-12-21 | 2020-12-21 | Campus dynamic scoring system based on deep learning |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112613500A true CN112613500A (en) | 2021-04-06 |
Family
ID=75244491
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202011517003.4A Pending CN112613500A (en) | 2020-12-21 | 2020-12-21 | Campus dynamic scoring system based on deep learning |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112613500A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580429A (en) * | 2022-01-26 | 2022-06-03 | 云捷计算机软件(江苏)有限责任公司 | Artificial intelligence-based language and image understanding integrated service system |
Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
| CN108734153A (en) * | 2018-07-18 | 2018-11-02 | 深圳迪普乐宁科技有限公司 | A kind of method and system of efficient computer marking |
| CN108764074A (en) * | 2018-05-14 | 2018-11-06 | 山东师范大学 | Subjective item intelligently reading method, system and storage medium based on deep learning |
| CN109117738A (en) * | 2018-07-19 | 2019-01-01 | 江苏黄金屋教育发展股份有限公司 | Method to go over files based on artificial intelligence |
| CN109740436A (en) * | 2018-12-03 | 2019-05-10 | 李卫强 | A kind of intelligence marking system |
| CN110110585A (en) * | 2019-03-15 | 2019-08-09 | 西安电子科技大学 | Intelligently reading realization method and system based on deep learning, computer program |
| CN110689018A (en) * | 2019-09-24 | 2020-01-14 | 华南理工大学 | Intelligent marking system and processing method thereof |
-
2020
- 2020-12-21 CN CN202011517003.4A patent/CN112613500A/en active Pending
Patent Citations (7)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104268603A (en) * | 2014-09-16 | 2015-01-07 | 科大讯飞股份有限公司 | Intelligent marking method and system for text objective questions |
| CN108764074A (en) * | 2018-05-14 | 2018-11-06 | 山东师范大学 | Subjective item intelligently reading method, system and storage medium based on deep learning |
| CN108734153A (en) * | 2018-07-18 | 2018-11-02 | 深圳迪普乐宁科技有限公司 | A kind of method and system of efficient computer marking |
| CN109117738A (en) * | 2018-07-19 | 2019-01-01 | 江苏黄金屋教育发展股份有限公司 | Method to go over files based on artificial intelligence |
| CN109740436A (en) * | 2018-12-03 | 2019-05-10 | 李卫强 | A kind of intelligence marking system |
| CN110110585A (en) * | 2019-03-15 | 2019-08-09 | 西安电子科技大学 | Intelligently reading realization method and system based on deep learning, computer program |
| CN110689018A (en) * | 2019-09-24 | 2020-01-14 | 华南理工大学 | Intelligent marking system and processing method thereof |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN114580429A (en) * | 2022-01-26 | 2022-06-03 | 云捷计算机软件(江苏)有限责任公司 | Artificial intelligence-based language and image understanding integrated service system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| US11790641B2 (en) | Answer evaluation method, answer evaluation system, electronic device, and medium | |
| CN108932508B (en) | Method and system for intelligently identifying and correcting subjects | |
| WO2020259060A1 (en) | Test paper information extraction method and system, and computer-readable storage medium | |
| CN110008933B (en) | Universal intelligent marking system and method | |
| CN107506762B (en) | Score automatic input method based on image analysis | |
| CN111597908A (en) | Test paper correcting method and test paper correcting device | |
| CN111753767A (en) | Method and device for automatically correcting operation, electronic equipment and storage medium | |
| CN108388895B (en) | Machine learning-based automatic processing method for test paper answer sheet | |
| CN112115736B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| CN106599887B (en) | Paper answer region recognition and examination question read and appraise method, system | |
| CN109242856A (en) | A kind of papery operation electronization reads and makes comments method and device | |
| CN110689018A (en) | Intelligent marking system and processing method thereof | |
| CN112507758A (en) | Answer sheet character string identification method, answer sheet character string identification device, terminal and computer storage medium | |
| CN110837793A (en) | Intelligent recognition handwriting mathematical formula reading and amending system | |
| CN112446259A (en) | Image processing method, device, terminal and computer readable storage medium | |
| CN112116840B (en) | Job correction method and system based on image recognition and intelligent terminal | |
| CN108428073A (en) | A kind of intelligent evaluation system for teachers ' teaching quality | |
| CN107066939A (en) | A kind of paper cutting process method of online paper-marking system | |
| CN110826872A (en) | Method, system and device for generating examination result analysis report | |
| CN112613500A (en) | Campus dynamic scoring system based on deep learning | |
| CN107067399A (en) | A kind of paper image segmentation processing method | |
| CN108681713A (en) | A kind of system for teaching quality evaluation for teachers | |
| CN112926571A (en) | Formula picture recognition and question judgment system based on deep learning | |
| CN109993153B (en) | Artificial intelligence system of going over examination papers based on edge calculation | |
| CN110705610A (en) | Evaluation system and method based on handwriting detection and temporary writing capability |
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: 20210406 |
|
| RJ01 | Rejection of invention patent application after publication |