CN109271973A - Medicine text OCR method and system - Google Patents
Medicine text OCR method and system Download PDFInfo
- Publication number
- CN109271973A CN109271973A CN201811330262.9A CN201811330262A CN109271973A CN 109271973 A CN109271973 A CN 109271973A CN 201811330262 A CN201811330262 A CN 201811330262A CN 109271973 A CN109271973 A CN 109271973A
- Authority
- CN
- China
- Prior art keywords
- text
- ocr
- medicine
- text file
- identifier
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/40—Document-oriented image-based pattern recognition
- G06V30/41—Analysis of document content
- G06V30/413—Classification of content, e.g. text, photographs or tables
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V30/00—Character recognition; Recognising digital ink; Document-oriented image-based pattern recognition
- G06V30/10—Character recognition
- G06V30/14—Image acquisition
- G06V30/148—Segmentation of character regions
- G06V30/153—Segmentation of character regions using recognition of characters or words
Landscapes
- Engineering & Computer Science (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Multimedia (AREA)
- Theoretical Computer Science (AREA)
- Artificial Intelligence (AREA)
- Medical Treatment And Welfare Office Work (AREA)
Abstract
This disclosure relates to which optical character identification and medical domain, disclose a kind of medicine text OCR method and system.The medicine text OCR method includes: that medicine textual image is tentatively identified as text file；Classify according to text type predetermined to text file, determines text type belonging to text file；Text file is accurately identified by dedicated OCR identifier corresponding with text type belonging to text file.The present disclosure proposes a kind of medicine text OCR schemes, image content is identified by using general purpose O CR identifier, thus the image content after preliminary identification is distributed on different dedicated OCR identifiers and is accurately identified, so as to improve the effect of medical files OCR identification.
Description
Technical field
This disclosure relates to optical character identification and medical domain, and in particular to a kind of medicine text OCR method and system.
Background technique
It with the presence of many files is, in order to extract information therein, to need people in a manner of scanned copy in medical system
Work typing, or use machine recognition.The development of optical character identification (OCR, Optical Character Recognition)
There is the time of decades, the OCR system that has had system that much can be practical at present, but can actually use in medical system
It unites still seldom.
In the technical solution of the prior art, there are mainly two types of processing modes for optical character identification (OCR), one is being based on
The identifying system of individual character segmentation, the second is the identifying system based on symbol string, the identifying system based on character string uses depth mostly
Spend learning model.
The shortcomings that prior art: many symbols are had in medicine text, different from the regular of Chinese character, the size of various symbols
It changes greatly, discrimination is lower.
Therefore, it is necessary to a kind of new medicine text OCR methods.
Above- mentioned information are only used for reinforcing the understanding to the background of the disclosure, therefore it disclosed in the background technology part
It may include the information not constituted to the prior art known to persons of ordinary skill in the art.
Summary of the invention
The disclosure discloses a kind of medicine text OCR method and system, can accurately identify to medicine text, thus bright
The aobvious effect for improving medicine text OCR identification.
Other characteristics and advantages of the disclosure will be apparent from by the following detailed description, or partially by the disclosure
Practice and acquistion.
According to the disclosure in a first aspect, disclosing a kind of medicine text OCR method characterized by comprising
Medicine textual image is tentatively identified as text file；
Classify according to text type predetermined to text file, determines text type belonging to text file；
Text file is accurately known by dedicated OCR identifier corresponding with text type belonging to text file
Not.
According to an example embodiment of the disclosure, wherein being tentatively identified by the progress of general purpose O CR identifier.
According to an example embodiment of the disclosure, wherein being known by common corpus and the dedicated corpus of medicine to general purpose O CR
Other device carries out model training.
According to an example embodiment of the disclosure, wherein being classified by text classifier to text file.
According to an example embodiment of the disclosure, wherein text type predetermined includes: checklist, medical image
Report, medical history or inspection report.
According to an example embodiment of the disclosure, the identification frame that wherein OCR is combined using CNN, bilayer LSTM and CTC
Structure.
According to the second aspect of the disclosure, a kind of medicine text OCR system is disclosed characterized by comprising
General purpose O CR identifier, for medicine textual image to be tentatively identified as text file；
Text classifier determines text file for classifying according to text type predetermined to text file
Affiliated text type；And
Dedicated OCR identifier, accurately identifies text file for the text type according to belonging to text file.
According to an example embodiment of the disclosure, wherein being known by common corpus and the dedicated corpus of medicine to general purpose O CR
Other device carries out model training.
According to an example embodiment of the disclosure, wherein text type predetermined includes: checklist, medical image
Report, medical history or inspection report.
According to an example embodiment of the disclosure, the identification frame that wherein OCR is combined using CNN, bilayer LSTM and CTC
Structure.
According to some embodiments of the disclosure, image content is identified by using general purpose O CR identifier, thus preliminary
Image content after identification is distributed on different dedicated OCR identifiers and is accurately identified, so as to improve medical files OCR
The effect of identification.
According to some embodiments of the disclosure, due to the vocabulary very little that dedicated OCR identifier needs, training data
Type is more concentrated, therefore recognition effect is substantially better than general purpose O CR.
It should be understood that the above general description and the following detailed description are merely exemplary, it is not intended to limit
The disclosure.
Detailed description of the invention
Its example embodiment is described in detail by referring to accompanying drawing, above and other target, feature and the advantage of the disclosure will
It becomes more fully apparent.Drawings discussed below is only some embodiments of the present disclosure, for the ordinary skill of this field
For personnel, without creative efforts, it is also possible to obtain other drawings based on these drawings.
Fig. 1 shows the medicine text OCR method flow diagram according to one example embodiment of the disclosure.
Fig. 2 shows the medicine text OCR system block diagrams according to one example embodiment of the disclosure.
Specific embodiment
Example embodiment is described more fully with reference to the drawings.However, example embodiment can be with a variety of shapes
Formula is implemented, and is not understood as limited to example set forth herein；On the contrary, thesing embodiments are provided so that the description of the disclosure
Will be more full and complete, and the design of example embodiment is comprehensively communicated to those skilled in the art.Attached drawing is only
The schematic illustrations of the disclosure are not necessarily drawn to scale.Identical appended drawing reference indicates same or similar portion in figure
Point, thus repetition thereof will be omitted.
In addition, described feature, structure or characteristic can be incorporated in one or more implementations in any suitable manner
In mode.In the following description, many details are provided to provide and fully understand to embodiment of the present disclosure.So
And it will be appreciated by persons skilled in the art that one in the specific detail can be omitted with technical solution of the disclosure
Or more, or can be using other methods, constituent element, step etc..In other cases, it is not shown in detail or describes known knot
Structure, method, realization or operation are to avoid a presumptuous guest usurps the role of the host and all aspects of this disclosure is made to thicken.
Some block diagrams shown in the drawings are functional entitys, not necessarily must be with physically or logically independent entity phase
It is corresponding.These functional entitys can be realized using software form, or in one or more hardware modules or integrated circuit in fact
These existing functional entitys, or these functions reality is realized in heterogeneous networks and/or processor device and/or microcontroller device
Body.
The purpose of the disclosure is to disclose a kind of medicine text OCR method and system.The medicine text OCR method includes:
Medicine textual image is tentatively identified as text file；Classify according to text type predetermined to text file, really
Determine text type belonging to text file；By dedicated OCR identifier corresponding with text type belonging to text file to text
This document is accurately identified.The present disclosure proposes a kind of medicine text OCR methods, are identified by using general purpose O CR identifier
Thus image content is distributed to the image content after preliminary identification on different dedicated OCR identifiers and is accurately identified, from
And improve the effect of medical files OCR identification.Simultaneously as the vocabulary very little that dedicated OCR identifier needs, training data
Type more concentrate, therefore recognition effect is substantially better than general purpose O CR.
It is specifically described below with reference to medicine text OCR method and system of the Fig. 1-2 to the disclosure, wherein Fig. 1 is shown
According to the medicine text OCR method flow diagram of one example embodiment of the disclosure；Fig. 2 shows according to one example embodiment party of the disclosure
The medicine text OCR system block diagram of formula.
Combine Fig. 1-2 that the medicine text OCR method of the disclosure is specifically described first, wherein Fig. 1 is shown according to this
The medicine text OCR method flow diagram of one example embodiment is disclosed；Fig. 2 shows the doctors according to one example embodiment of the disclosure
Learn text OCR system block diagram.
Briefly introduce the medicine text OCR method of the disclosure on the whole first: medicine textual scan part usually has
There are stringenter function distinguishing, such as checklist, medical image is reported, medical history, inspection report etc., each file has
Oneself corresponding vocabulary can construct different words by the statistics to massive medical text for different files by type
Remittance table and corpus, the specific identification model of training.On general frame, text passes through a general identifier first, uses
Come to text classification, further according to the specific identifier of category assignment.Specifically, the medicine text optical character of the disclosure identifies
Scheme trains a general purpose O CR identifier first, using two, corpus source in terms of, one is common language, from mutually
Networking, the second is the dedicated corpus of medicine, derives from true medicine text.For the medicine text that needs identify, according to text class
Type is classified, and one text classifier of training, the input of text classifier is the output of general purpose O CR, text classifier it is defeated
It is then predefined text type out.And each text type, all train a dedicated OCR identifier.It does so
Benefit be that the vocabulary very little that dedicated OCR identifier needs, the type of training data is more concentrated, recognition effect is therefore obvious
Better than general purpose O CR.The basic structure of OCR is CNN (Convolutional Neural Network, convolutional neural networks)+bis-
(Long Short-Term Memory, shot and long term memory network are a kind of time recurrent neural networks, are suitable for locating layer LSTM
Relatively long critical event is spaced and postponed in reason and predicted time sequence)+CTC (Connectionist temporal
Classification, it can be understood as timing class classification neural network based connects in RNN (Recurrent Neural
Network, Recognition with Recurrent Neural Network) network the last layer for used in Sequence Learning).
It is described in detail with reference to the accompanying drawing.
Fig. 1 shows a kind of flow chart of medicine text OCR method according to one illustrative embodiments of the disclosure.
As shown in Figure 1, medicine textual image is tentatively identified as text file in S102.Have in medical system very much
File is existed in the way of scanned copy (such as by papery case history or the scanning of ct, x mating plate as picture), in order to extract letter therein
Breath needs manual entry, or uses machine recognition.
According to an example embodiment of the disclosure, wherein being tentatively identified by general purpose O CR identifier 1 (such as institute in Fig. 2
Show) it carries out.
According to an example embodiment of the disclosure, wherein being known by common corpus and the dedicated corpus of medicine to general purpose O CR
Other device carries out model training.Corpus used in one general purpose O CR identifier of training can be with two, source aspect, one is common
Language derives from internet, the second is the dedicated corpus of medicine, derives from true medicine text.
In S104, classify according to text type predetermined to text file, determines text belonging to text file
This type.
According to an example embodiment of the disclosure, wherein by text classifier 2 (as shown in Figure 2) to text file
Classify.
Specifically, the medicine text (picture) identified for needs, classifies according to text type, one text of training
This classifier, the input of text classifier are the output of general purpose O CR identifier, and the output of text classifier is then that predefined is good
Text type.
According to an example embodiment of the disclosure, wherein text type predetermined includes: checklist, medical image
Report, medical history or inspection report.
In S106, pass through dedicated OCR identifier 3 (as shown in Figure 2) corresponding with text type belonging to text file
Text file is accurately identified.
Pass through S104, it is determined that text type belonging to text file.On this basis, further according to text text in S106
Text type belonging to part accurately identifies text file using dedicated OCR identifier corresponding with text type.
That is, for each text type (such as checklist, medical image report, medical history, inspection report etc.
Deng), all train a dedicated OCR identifier.The advantage of doing so is that the vocabulary very little that dedicated OCR identifier needs, instruction
The type for practicing data is more concentrated, therefore recognition effect is substantially better than general purpose O CR.
According to an example embodiment of the disclosure, wherein OCR (algorithm) is combined using CNN, bilayer LSTM and CTC
Technical Architecture.Wherein, CNN is the abbreviation of Convolutional Neural Network, i.e. convolutional neural networks；The double-deck LSTM
In LSTM be Long Short-Term Memory abbreviation, i.e. shot and long term memory network is a kind of time recurrent neural net
Network is suitable for being spaced and postpone relatively long critical event in processing and predicted time sequence；And CTC is
The abbreviation of Connectionist temporal classification, it is possible to understand that for timing class neural network based point
Class connects the last layer in RNN (Recurrent Neural Network, Recognition with Recurrent Neural Network) network for Sequence Learning institute
With).
Fig. 2 shows the medicine text OCR system block diagrams according to disclosure example embodiment.
The medicine text OCR system of the disclosure can be used for the equipment such as PC, work station or server.
As shown in Fig. 2, medicine text OCR system may include general purpose O CR identifier 1, text classifier 2 and dedicated OCR
Identifier 3.
General purpose O CR identifier 1, for medicine textual image to be tentatively identified as text file.
According to an example embodiment of the disclosure, wherein being known by common corpus and the dedicated corpus of medicine to general purpose O CR
Other device carries out model training.Corpus used in one general purpose O CR identifier of training can be with two, source aspect, one is common
Language derives from internet, the second is the dedicated corpus of medicine, derives from true medicine text.
Text classifier 2 determines text file for classifying according to text type predetermined to text file
Affiliated text type.
Specifically, the medicine text (picture) identified for needs, classifies according to text type, one text of training
This classifier 2, the input of text classifier 2 are the output of general purpose O CR identifier 1, and the output of text classifier is then fixed in advance
The good text type of justice.
According to an example embodiment of the disclosure, wherein text type predetermined includes: checklist, medical image
Report, medical history or inspection report.
Dedicated OCR identifier 3, accurately identifies text file for the text type according to belonging to text file.
That is, for each text type (such as checklist, medical image report, medical history, inspection report etc.
Deng), all train a dedicated OCR identifier 3.The advantage of doing so is that the vocabulary very little that dedicated OCR identifier needs,
The type of training data is more concentrated, therefore recognition effect is substantially better than general purpose O CR.
According to an example embodiment of the disclosure, wherein OCR (algorithm) is combined using CNN, bilayer LSTM and CTC
Technical Architecture.Wherein, CNN is the abbreviation of Convolutional Neural Network, i.e. convolutional neural networks；The double-deck LSTM
In LSTM be Long Short-Term Memory abbreviation, i.e. shot and long term memory network is a kind of time recurrent neural net
Network is suitable for being spaced and postpone relatively long critical event in processing and predicted time sequence；And CTC is
The abbreviation of Connectionist temporal classification, it is possible to understand that for timing class neural network based point
Class connects the last layer in RNN (Recurrent Neural Network, Recognition with Recurrent Neural Network) network for Sequence Learning institute
With).
By above detailed description, those skilled in the art it can be readily appreciated that according to the method for the embodiment of the present disclosure and
System has one or more of the following advantages.
According to some embodiments of the disclosure, image content is identified by using general purpose O CR identifier, thus preliminary
Image content after identification is distributed on different dedicated OCR identifiers and is accurately identified, so as to improve medical files OCR
The effect of identification.
According to some embodiments of the disclosure, due to the vocabulary very little that dedicated OCR identifier needs, training data
Type is more concentrated, therefore recognition effect is substantially better than general purpose O CR.
Those skilled in the art after considering the specification and implementing the invention disclosed here, will readily occur to its of the disclosure
Its embodiment.This application is intended to cover any variations, uses, or adaptations of the disclosure, these modifications, purposes or
Person's adaptive change follows the general principles of this disclosure and including the undocumented common knowledge in the art of the disclosure
Or conventional techniques.The description and examples are only to be considered as illustrative, and the true scope and spirit of the disclosure are by following
Claim is pointed out.
It should be understood that the present disclosure is not limited to the precise structures that have been described above and shown in the drawings, and
And various modifications and changes may be made without departing from the scope thereof.The scope of the present disclosure is only limited by the accompanying claims.
Claims (10)
1. a kind of medicine text OCR method characterized by comprising
Medicine textual image is tentatively identified as text file；
Classify according to text type predetermined to text file, determines text type belonging to text file；
Text file is accurately identified by dedicated OCR identifier corresponding with text type belonging to text file.
2. the method as described in claim 1, wherein being tentatively identified by the progress of general purpose O CR identifier.
3. method according to claim 2, wherein being carried out by common corpus and the dedicated corpus of medicine to general purpose O CR identifier
Model training.
4. the method as described in claim 1, wherein being classified by text classifier to text file.
5. method as described in claim 1 or 4, wherein text type predetermined includes: checklist, medical image report
Announcement, medical history or inspection report.
6. the method as described in claim 1, the identification framework that wherein OCR is combined using CNN, bilayer LSTM and CTC.
7. a kind of medicine text OCR system characterized by comprising
General purpose O CR identifier, for medicine textual image to be tentatively identified as text file；
Text classifier determines belonging to text file for classifying according to text type predetermined to text file
Text type；And
Dedicated OCR identifier, accurately identifies text file for the text type according to belonging to text file.
8. system as claimed in claim 7, wherein being carried out by common corpus and the dedicated corpus of medicine to general purpose O CR identifier
Model training.
9. system as claimed in claim 7, wherein text type predetermined includes: checklist, medical image report, disease
History or inspection report.
10. system as claimed in claim 7, the identification framework that wherein OCR is combined using CNN, bilayer LSTM and CTC.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811330262.9A CN109271973A (en) | 2018-11-09 | 2018-11-09 | Medicine text OCR method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811330262.9A CN109271973A (en) | 2018-11-09 | 2018-11-09 | Medicine text OCR method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109271973A true CN109271973A (en) | 2019-01-25 |
Family
ID=65191961
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811330262.9A Pending CN109271973A (en) | 2018-11-09 | 2018-11-09 | Medicine text OCR method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109271973A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110889412A (en) * | 2019-11-01 | 2020-03-17 | 泰康保险集团股份有限公司 | Medical long text positioning and classifying method and device in physical examination report |
| CN111768820A (en) * | 2020-06-04 | 2020-10-13 | 上海森亿医疗科技有限公司 | Paper medical record digitization and target detection model training method, device and storage medium |
| CN112016553A (en) * | 2019-05-28 | 2020-12-01 | 创新先进技术有限公司 | Optical Character Recognition (OCR) system, automatic OCR correction system, method |
| CN112381089A (en) * | 2020-11-20 | 2021-02-19 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7233697B2 (en) * | 2001-03-30 | 2007-06-19 | Kabushiki Kaisha Toshiba | Character recognition device and a method therefor |
| CN104408678A (en) * | 2014-10-31 | 2015-03-11 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record system for personal use |
| CN105046289A (en) * | 2015-08-07 | 2015-11-11 | 北京旷视科技有限公司 | Text field type identification method and text field type identification system |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
| CN108564992A (en) * | 2018-04-16 | 2018-09-21 | 深圳零壹云医科技有限公司 | A kind of electronic health record method for sorting and system |
-
2018
- 2018-11-09 CN CN201811330262.9A patent/CN109271973A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US7233697B2 (en) * | 2001-03-30 | 2007-06-19 | Kabushiki Kaisha Toshiba | Character recognition device and a method therefor |
| CN104408678A (en) * | 2014-10-31 | 2015-03-11 | 中国科学院苏州生物医学工程技术研究所 | Electronic medical record system for personal use |
| CN105046289A (en) * | 2015-08-07 | 2015-11-11 | 北京旷视科技有限公司 | Text field type identification method and text field type identification system |
| CN108229463A (en) * | 2018-02-07 | 2018-06-29 | 众安信息技术服务有限公司 | Character recognition method based on image |
| CN108564992A (en) * | 2018-04-16 | 2018-09-21 | 深圳零壹云医科技有限公司 | A kind of electronic health record method for sorting and system |
Non-Patent Citations (1)
| Title |
|---|
| 李琴等: "医学文本图像字符识别校正技术研究与应用", 《医学信息学杂志》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112016553A (en) * | 2019-05-28 | 2020-12-01 | 创新先进技术有限公司 | Optical Character Recognition (OCR) system, automatic OCR correction system, method |
| CN112016553B (en) * | 2019-05-28 | 2022-01-25 | 创新先进技术有限公司 | Optical Character Recognition (OCR) system, automatic OCR correction system, method |
| CN110889412A (en) * | 2019-11-01 | 2020-03-17 | 泰康保险集团股份有限公司 | Medical long text positioning and classifying method and device in physical examination report |
| CN111768820A (en) * | 2020-06-04 | 2020-10-13 | 上海森亿医疗科技有限公司 | Paper medical record digitization and target detection model training method, device and storage medium |
| CN112381089A (en) * | 2020-11-20 | 2021-02-19 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
| CN112381089B (en) * | 2020-11-20 | 2024-06-07 | 山西同方知网数字出版技术有限公司 | Self-feedback text separation method and system in complex environment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109271973A (en) | Medicine text OCR method and system | |
| CN103577818B (en) | A kind of method and apparatus of pictograph identification | |
| CN109993160A (en) | A kind of image flame detection and text and location recognition method and system | |
| CN109214303A (en) | A kind of multithreading dynamic human face based on cloud API is registered method | |
| Zhao et al. | Two-stage segmentation of unconstrained handwritten Chinese characters | |
| CN109670494B (en) | Text detection method and system with recognition confidence | |
| Saini et al. | A review of bot protection using CAPTCHA for web security | |
| JP2020184109A (en) | Learning model generation device, character recognition device, learning model generation method, character recognition method, and program | |
| CN104123550A (en) | Cloud computing-based text scanning identification method | |
| JPWO2010092952A1 (en) | Pattern recognition device | |
| CN109460551A (en) | Signing messages extracting method and device | |
| CN107145514B (en) | Chinese sentence pattern classification method based on decision tree and SVM mixed model | |
| CN108171243B (en) | Medical image information identification method and system based on deep neural network | |
| CN112508011A (en) | OCR (optical character recognition) method and device based on neural network | |
| CN106650664A (en) | Collection system and method for college and university enrollment book data | |
| CN113408535A (en) | OCR error correction method based on Chinese character level characteristics and language model | |
| Hong | Degraded text recognition using visual and linguistic context | |
| Nandanwar et al. | A new method for detecting altered text in document images | |
| Saiful et al. | Real-time sign language detection using cnn | |
| CN114419636A (en) | Text recognition method, device, equipment and storage medium | |
| US9665786B2 (en) | Confirming automatically recognized handwritten answers | |
| US10127469B2 (en) | Leveraging digital images of user information in a social network | |
| Ovodov | Optical Braille recognition using object detection neural network | |
| Ifhaam et al. | Sinhala handwritten postal address recognition for postal sorting | |
| Feild | Improving text recognition in images of natural scenes |
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: 20190125 |
|
| RJ01 | Rejection of invention patent application after publication |