CN109132744A - Elevator based on deep learning regulates and controls method and system - Google Patents
Elevator based on deep learning regulates and controls method and system Download PDFInfo
- Publication number
- CN109132744A CN109132744A CN201810997851.6A CN201810997851A CN109132744A CN 109132744 A CN109132744 A CN 109132744A CN 201810997851 A CN201810997851 A CN 201810997851A CN 109132744 A CN109132744 A CN 109132744A
- Authority
- CN
- China
- Prior art keywords
- elevator
- deep learning
- elevator cage
- space accounting
- regulates
- 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
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/24—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration
- B66B1/2408—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration where the allocation of a call to an elevator car is of importance, i.e. by means of a supervisory or group controller
- B66B1/2416—For single car elevator systems
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B1/00—Control systems of elevators in general
- B66B1/24—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration
- B66B1/28—Control systems with regulation, i.e. with retroactive action, for influencing travelling speed, acceleration, or deceleration electrical
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/20—Details of the evaluation method for the allocation of a call to an elevator car
- B66B2201/215—Transportation capacity
-
- B—PERFORMING OPERATIONS; TRANSPORTING
- B66—HOISTING; LIFTING; HAULING
- B66B—ELEVATORS; ESCALATORS OR MOVING WALKWAYS
- B66B2201/00—Aspects of control systems of elevators
- B66B2201/40—Details of the change of control mode
- B66B2201/403—Details of the change of control mode by real-time traffic data
Abstract
The elevator that the invention discloses a kind of based on deep learning regulates and controls method and system, and method is the following steps are included: S1: with predetermined amount of time being segmentation unit to generate plurality of pictures by collected real-time video after carrying out real time video collection in elevator cage.S2: plurality of pictures is normalized.S3: blocking identification is carried out to the object in elevator cage by the picture after normalized, and judges the space accounting in elevator cage, to judge whether to stop according to space accounting when elevator receives docked request.Its system are as follows: image acquisition device to video be sent to intelligent processor, intelligent processor judges the space accounting in elevator cage according to the video received and sends result to electric life controller, when electric life controller receives the docked request of elevator docked request button, electric life controller judges whether to stop according to space accounting, present invention saves riding times, improve the seating efficiency of personnel.
Description
Technical field
The present invention relates to machine vision and field of intelligent control technology, in particular to a kind of based on deep learning
Elevator regulates and controls method and system.
Background technique
The popularization degree of elevator is higher and higher, and cab formula elevator is more and more in large-scale office building, residential building and store.But
It is that crowd has expired in the periods cab such as next peak period, since every layer of someone presses, even if passenger can not be superior later,
Elevator is still stopped at every layer, is greatly reduced operational efficiency and is caused the time waste of passenger.
Summary of the invention
The present invention is directed to solve above-mentioned technical problem to a certain extent.
In view of this, the present invention provides a kind of, the elevator based on deep learning regulates and controls method and system, should be based on depth
The elevator regulation method and system of study have saved riding time, improve the seating efficiency of personnel.
In order to solve the above-mentioned technical problem, first aspect present invention provides a kind of elevator regulation side based on deep learning
Method and system, comprising the following steps:
S1: in elevator cage carry out real time video collection after, by collected real-time video with predetermined amount of time be point
Unit is cut to generate plurality of pictures；S2: plurality of pictures is normalized；S3: pass through the picture pair after normalized
Object in elevator cage carries out blocking identification, and judges the space accounting in elevator cage, to receive stop in elevator
When request, judge whether to stop according to space accounting.
Further, further comprising the steps of before S1: the operational mode of elevator being set to intelligent mode as needed.
Further, in step s3, judge to further include step when the space accounting in elevator cage:
S31: inductive learning is carried out to plurality of pictures and establishes training set, to given data set yi∈{C1,C2,K,CN}
The pairing of N number of classification is carried out, N (N-1)/2 two classification C are generatediAnd Cj, CiWith CjIt is set as positive sample and negative sample, is passed through
Training process makes positive sample: anti-sample >=1:2.
Further, in step S3, judge to further include step when the space accounting in elevator cage: S32: to multiple figures
Edge contour identification in every two-value grayscale image in piece generates multiple modules by the cutting of profile, by modules
Parallel individually training.
Further, in step S3, judge to further include step when the space accounting in elevator cage: S33: training process
In using predict error as training complete whether evaluation criterion, in training error excess, iterate training, guidance prediction
Error exports current learning outcome when reaching standard.
Further, in step S3, judge to further include step when the space accounting in elevator cage: S34: this study
Output as a result, in training next time as study input, by back-propagation algorithm, making to learn output error every time will be constant
Or become smaller.
Further, in step S2, plurality of pictures is normalized by classifier, the study of classifier is based on tree
Certain kind of berries group realizes that raspberry pie supports 8 GPIO mouthfuls of communications, meets the real-time input free of discontinuities of front end signal and rear end control circuit dynamic
State control.
The second aspect of the present invention provides a kind of elevator regulator control system based on deep learning, comprising: image collector
It sets, described image acquisition device is located in elevator cage, for carrying out real time video collection in the elevator cage；At intelligence
Device is managed, the intelligent processor is connect with described image acquisition device；Elevator docked request button, the elevator docked request are pressed
Button is connect with the electric life controller, and wherein the collected video of described image acquisition device is sent to the intelligent processor,
The intelligent processor judges the space accounting in the elevator cage according to the video received and sends result to
The electric life controller, when the electric life controller receives the docked request of the elevator docked request button, the electricity
Terraced controller judges whether to stop according to the space accounting.
Further, described image acquisition device is camera.
Further, the intelligent processor is raspberry pie, and the raspberry pie supports 8 GPIO mouthfuls of communications.
The technical effects of the invention are that: after carrying out real time video collection in elevator cage, plurality of pictures is carried out
The normalized of series of standards converts.Blocking is carried out to the object in elevator cage by the picture after normalized
Identification, and judge the space accounting in elevator cage, under the premise of elevator receives docked request, when the space of elevator cage accounts for
When than being less than scheduled value, cab is stopped, and when the space accounting of elevator cage is greater than scheduled value, cab is without stopping
It leans on, under the premise of elevator connects and do not receive docked request, elevator is operated normally, and has been saved riding time, has been improved multiplying for personnel
Sit efficiency.
Detailed description of the invention
Fig. 1 is a kind of flow chart of elevator regulation method based on deep learning according to the present invention.
Fig. 2 is a kind of flow chart of elevator regulator control system based on deep learning according to the present invention.
Fig. 3 is the training structure figure of classifier according to the present invention.
Wherein, 1- image collecting device；2- intelligent processor；3- elevator docked request button；4- electric life controller.
Specific embodiment
The present invention will be further explained below with reference to the attached drawings and specific examples, so that those skilled in the art can be with
It better understands the present invention and can be practiced, but illustrated embodiment is not as a limitation of the invention.
As shown in figures 1 and 3, a kind of elevator based on deep learning regulates and controls method, comprising the following steps:
S1: in elevator cage carry out real time video collection after, by collected real-time video with predetermined amount of time be point
Unit is cut to generate plurality of pictures；S2: plurality of pictures is normalized；S3: pass through the picture pair after normalized
Object in elevator cage carries out blocking identification, and judges the space accounting in elevator cage, to receive stop in elevator
When request, judge whether to stop according to space accounting.
It according to a particular embodiment of the invention, will be collected real-time after to real time video collection is carried out in elevator cage
Video is segmentation unit to generate plurality of pictures with predetermined amount of time.Plurality of pictures is subjected to a series of normalized change
It changes, is allowed to be transformed to fixed standard form, and be normalized to 96 × 96 pixels.By the picture after normalized to elevator
Object in cab carries out blocking identification, and judges the space accounting in elevator cage, before elevator receives docked request
It puts, when the space accounting of elevator cage is less than scheduled value, cab is stopped, when the space accounting of elevator cage is greater than
When scheduled value, cab is without stopping, and under the premise of elevator connects and do not receive docked request, elevator is operated normally, and saves
Riding time improves the seating efficiency of personnel.
According to a particular embodiment of the invention, further comprising the steps of before S1: as needed by the operational mode of elevator
It is set to intelligent mode, avoids passing through and is manually monitored, saved manpower and material resources, improve work efficiency.
It according to a particular embodiment of the invention, in step s3, further include one when judging the space accounting in elevator cage
Lower step:
S31: inductive learning is carried out to plurality of pictures and establishes training set, to given data set yi∈{C1,C2,K,CN}
The pairing of N number of classification is carried out, N (N-1)/2 two classification C are generatediAnd Cj, CiWith CjIt is set as positive sample and negative sample, is passed through
Training process makes positive sample: anti-sample >=1:2.
It according to a particular embodiment of the invention, further include when judging the space accounting in elevator cage in step S3
Step: S32: identifying the edge contour in the two-value grayscale image of every in plurality of pictures, is generated by the cutting of profile more
A module individually trains modules parallel, and during independent training, the region of object features is extracted in module,
And these features are analyzed, and analysis precision is improved.
In concrete application, the standard for extracting object features is overweight figure, normal type, inclined ectomorphic type and adult, youngster
Virgin, baby.There is same learning process for objects such as specific articles, such as chest, vehicle.
It according to a particular embodiment of the invention, further include when judging the space accounting in elevator cage in step S3
Step: S33: evaluation criterion whether in training process to predict that error is completed as training, in training error excess, repeatedly
Repetitive exercise, guidance prediction error export current learning outcome when reaching standard.
It according to a particular embodiment of the invention, further include when judging the space accounting in elevator cage in step S3
Step: S34: what this learnt to export learns to input as a result, being used as in training next time, by back-propagation algorithm, makes every time
Study output error will be constant or become smaller.
Divide according to a particular embodiment of the invention, plurality of pictures is normalized by classifier, classifier
Study realizes that raspberry pie supports 8 GPIO mouthfuls of communications based on raspberry pie, makes front end signal input free of discontinuities in real time and rear end control
Circuit meets dynamic and controls.
As shown in Fig. 2, a kind of elevator regulator control system based on deep learning, comprising:
Image collecting device 1, image collecting device 1 are located in elevator cage, for being regarded in real time in elevator cage
Frequency acquires；Intelligent processor 2, intelligent processor 2 are connect with image collecting device 1；Electric life controller 4, electric life controller 4 and intelligence
It can the connection of processor 2；Elevator docked request button 3, elevator docked request button 3 are connect with electric life controller 4, wherein
The collected video of image collecting device 1 is sent to intelligent processor 2, and intelligent processor 2 is according to the view received
Frequency judges the space accounting in elevator cage and sends result to electric life controller 4, receives elevator in electric life controller 4 and stops
When by the docked request of request button 3, electric life controller 4 judges whether to stop according to space accounting.
According to a particular embodiment of the invention, image collecting device 1 will carry out real time video collection in elevator cage, and will
The video of acquisition is sent to intelligent processor 2, and intelligent processor 2 judges that the space in elevator cage accounts for according to the video received
Than and send result to electric life controller 4, receive the docked request of elevator docked request button 3 in electric life controller 4
Under the premise of, when the space accounting of elevator cage is less than scheduled value, cab is stopped, when the space accounting of elevator cage is big
When scheduled value, cab is without stopping, and when the space accounting of elevator cage is greater than scheduled value, cab is without stopping
It leans on, under the premise of elevator connects and do not receive docked request, elevator is operated normally.
The control circuit of electric life controller 4 is divided into two parts, and what is taken is the logical relation of "AND".
The scheduled value preferably 90% of space accounting, when crowd density in carriage or space accounting reach 90%, i.e.,
Make current floor someone press elevator to cancel automatically, remains next group.
As shown in Fig. 2, image collecting device 1 is camera.
According to a particular embodiment of the invention, image collecting device 1 is camera, is carried out by camera to video real-time
Online acquisition and transmission, to obtain the image of high definition exquisiteness, the preferred CCD industry camera of camera, CCD industry camera is fitted
Answer the requirement of industrial complex environment, the work of energy long-time stable.
CCD industry camera sends image information to intelligent processor 2 by USB3.0.
As shown in Fig. 2, intelligent processor 2 is raspberry pie, raspberry pie supports 8 GPIO mouthfuls of communications.
According to a particular embodiment of the invention, raspberry pie is fast to the recognition speed of video, stable, and space accounting is small,
Raspberry pie supports 8 GPIO mouthfuls of communications, realizes that the real-time input free of discontinuities of front end signal and rear end control circuit meet dynamic control.
Embodiment described above is only to absolutely prove preferred embodiment that is of the invention and being lifted, protection model of the invention
It encloses without being limited thereto.Those skilled in the art's made equivalent substitute or transformation on the basis of the present invention, in the present invention
Protection scope within.Protection scope of the present invention is subject to claims.
Claims (10)
1. a kind of elevator based on deep learning regulates and controls method, which comprises the following steps:
S1: after carrying out real time video collection in elevator cage, collected real-time video is single for segmentation with predetermined amount of time
Position is to generate plurality of pictures；
S2: plurality of pictures is normalized；
S3: blocking identification is carried out to the object in elevator cage by the picture after normalized, and judges elevator cage
Interior space accounting, to judge whether to stop according to space accounting when elevator receives docked request.
2. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that also wrapped before step S1
It includes following steps: the operational mode of elevator being set to intelligent mode as needed.
3. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that in step s3, sentence
Further include step when space accounting in disconnected elevator cage:
S31: inductive learning is carried out to plurality of pictures and establishes training set, to given data set yi∈{C1,C2,K,CNCarry out N
The pairing of a classification generates N (N-1)/2 two classification CiAnd Cj, CiWith CjIt is set as positive sample and negative sample, passes through training
Process makes positive sample: anti-sample >=1:2.
4. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that in step S3, judgement
It further include step when space accounting in elevator cage: S32: to the side in the two-value grayscale image of every in plurality of pictures
Edge outline identification generates multiple modules by the cutting of profile, modules is individually trained parallel.
5. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that in step S3, judgement
It further include step when space accounting in elevator cage: S33: whether in training process to predict that error is completed as training
Evaluation criterion, in training error excess, iterate training, output current study knot when guidance prediction error reaches standard
Fruit.
6. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that in step S3, judgement
Further include step when space accounting in elevator cage: S34: this study output as a result, the conduct in training next time
Study input, by back-propagation algorithm, making to learn every time output error will be constant or become smaller.
7. the elevator according to claim 1 based on deep learning regulates and controls method, which is characterized in that, will be more in step S2
Picture is normalized by classifier, and the study of classifier realizes that raspberry pie supports 8 GPIO mouthfuls based on raspberry pie
Communication controls front end signal input free of discontinuities in real time and rear end control circuit satisfaction dynamic.
8. a kind of elevator regulator control system based on deep learning characterized by comprising
Image collecting device, described image acquisition device are located in elevator cage, for real-time to carrying out in the elevator cage
Video acquisition；
Intelligent processor, the intelligent processor are connect with described image acquisition device；
Electric life controller, the electric life controller are connect with the intelligent processor；
Elevator docked request button, the elevator docked request button are connect with the electric life controller, and wherein described image is adopted
The collected video of acquisition means is sent to the intelligent processor, and the intelligent processor judges according to the video received
Space accounting in the elevator cage simultaneously sends result to the electric life controller, receives institute in the electric life controller
When stating the docked request of elevator docked request button, the electric life controller judges whether to stop according to the space accounting.
9. the elevator regulator control system according to claim 8 based on deep learning, which is characterized in that described image acquisition dress
It is set to camera.
10. the elevator regulator control system according to claim 8 based on deep learning, which is characterized in that the Intelligent treatment
Device is raspberry pie, and the raspberry pie supports 8 GPIO mouthfuls of communications.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810997851.6A CN109132744A (en) | 2018-08-29 | 2018-08-29 | Elevator based on deep learning regulates and controls method and system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810997851.6A CN109132744A (en) | 2018-08-29 | 2018-08-29 | Elevator based on deep learning regulates and controls method and system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109132744A true CN109132744A (en) | 2019-01-04 |
Family
ID=64829300
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810997851.6A Pending CN109132744A (en) | 2018-08-29 | 2018-08-29 | Elevator based on deep learning regulates and controls method and system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109132744A (en) |
Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB695682A (en) * | 1951-01-17 | 1953-08-12 | Westinghouse Electric Int Co | Improvements in or relating to elevator control systems, embodying alternating current motors |
| CN1931697A (en) * | 2006-09-29 | 2007-03-21 | 浙江工业大学 | Intelligent dispatcher for group controlled lifts based on image recognizing technology |
| CN101139057A (en) * | 2007-09-06 | 2008-03-12 | 北京中星微电子有限公司 | Function lift control method and system using video monitoring apparatus |
| CN102821272A (en) * | 2012-08-16 | 2012-12-12 | 安徽中科智能高技术有限责任公司 | Video monitoring system with elevator invalid request signal removing function |
| CN204280935U (en) * | 2014-11-12 | 2015-04-22 | 成都英力拓信息技术有限公司 | A kind of elevator with Internet of Things safety detection scan function |
| CN104724557A (en) * | 2015-02-15 | 2015-06-24 | 英华达（上海）科技有限公司 | Elevator load carrying judgment system and method thereof |
| CN105712151A (en) * | 2016-04-27 | 2016-06-29 | 上海卓易科技股份有限公司 | Elevator operation method and system |
| CN105760835A (en) * | 2016-02-17 | 2016-07-13 | 天津中科智能识别产业技术研究院有限公司 | Gait segmentation and gait recognition integrated method based on deep learning |
| CN105819289A (en) * | 2016-03-31 | 2016-08-03 | 乐视控股（北京）有限公司 | Elevator control device and method |
| CN106586738A (en) * | 2017-01-24 | 2017-04-26 | 沈阳建筑大学 | Multi-car elevator dispatching method based on visual inspection |
| CN106980873A (en) * | 2017-03-09 | 2017-07-25 | 南京理工大学 | Fancy carp screening technique and device based on deep learning |
| CN107832768A (en) * | 2017-11-23 | 2018-03-23 | 盐城线尚天使科技企业孵化器有限公司 | Efficient method to go over files and marking system based on deep learning |
| CN108217352A (en) * | 2018-01-19 | 2018-06-29 | 深圳禾思众成科技有限公司 | A kind of intelligent elevator dispatches system |
-
2018
- 2018-08-29 CN CN201810997851.6A patent/CN109132744A/en active Pending
Patent Citations (13)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| GB695682A (en) * | 1951-01-17 | 1953-08-12 | Westinghouse Electric Int Co | Improvements in or relating to elevator control systems, embodying alternating current motors |
| CN1931697A (en) * | 2006-09-29 | 2007-03-21 | 浙江工业大学 | Intelligent dispatcher for group controlled lifts based on image recognizing technology |
| CN101139057A (en) * | 2007-09-06 | 2008-03-12 | 北京中星微电子有限公司 | Function lift control method and system using video monitoring apparatus |
| CN102821272A (en) * | 2012-08-16 | 2012-12-12 | 安徽中科智能高技术有限责任公司 | Video monitoring system with elevator invalid request signal removing function |
| CN204280935U (en) * | 2014-11-12 | 2015-04-22 | 成都英力拓信息技术有限公司 | A kind of elevator with Internet of Things safety detection scan function |
| CN104724557A (en) * | 2015-02-15 | 2015-06-24 | 英华达（上海）科技有限公司 | Elevator load carrying judgment system and method thereof |
| CN105760835A (en) * | 2016-02-17 | 2016-07-13 | 天津中科智能识别产业技术研究院有限公司 | Gait segmentation and gait recognition integrated method based on deep learning |
| CN105819289A (en) * | 2016-03-31 | 2016-08-03 | 乐视控股（北京）有限公司 | Elevator control device and method |
| CN105712151A (en) * | 2016-04-27 | 2016-06-29 | 上海卓易科技股份有限公司 | Elevator operation method and system |
| CN106586738A (en) * | 2017-01-24 | 2017-04-26 | 沈阳建筑大学 | Multi-car elevator dispatching method based on visual inspection |
| CN106980873A (en) * | 2017-03-09 | 2017-07-25 | 南京理工大学 | Fancy carp screening technique and device based on deep learning |
| CN107832768A (en) * | 2017-11-23 | 2018-03-23 | 盐城线尚天使科技企业孵化器有限公司 | Efficient method to go over files and marking system based on deep learning |
| CN108217352A (en) * | 2018-01-19 | 2018-06-29 | 深圳禾思众成科技有限公司 | A kind of intelligent elevator dispatches system |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107729872A (en) | Facial expression recognition method and device based on deep learning | |
| CN107133612A (en) | Based on image procossing and the intelligent ward of speech recognition technology and its operation method | |
| CN109919243A (en) | A kind of scrap iron and steel type automatic identifying method and device based on CNN | |
| CN104063686B (en) | Crop leaf diseases image interactive diagnostic system and method | |
| CN109064304A (en) | Finance reimbursement bill automated processing system and method | |
| CN111862065B (en) | Power transmission line diagnosis method and system based on multitask deep convolutional neural network | |
| CN113408087B (en) | Substation inspection method based on cloud side system and video intelligent analysis | |
| CN104751186A (en) | Iris image quality classification method based on BP (back propagation) network and wavelet transformation | |
| CN107644218A (en) | The method of work of crowded region behavioural analysis judgement is realized based on image collecting function | |
| CN106503275A (en) | The tone color collocation method of chat robots and device | |
| CN113688825A (en) | AI intelligent garbage recognition and classification system and method | |
| CN113145492A (en) | Visual grading method and grading production line for pear appearance quality | |
| CN109726777A (en) | PCB appearance detection system and detection method Internet-based | |
| CN115511367A (en) | Intelligent quality management system of production line | |
| CN108664886A (en) | A kind of fast face recognition method adapting to substation's disengaging monitoring demand | |
| CN107526440A (en) | The intelligent electric appliance control method and system of gesture identification based on decision tree classification | |
| CN114378002A (en) | Hericium erinaceus grading system and grading method based on machine vision | |
| CN117088015A (en) | Intelligent garbage disposal method, system and storage medium | |
| CN116443682B (en) | Intelligent elevator control system | |
| CN109132744A (en) | Elevator based on deep learning regulates and controls method and system | |
| CN116128879B (en) | Lightweight transmission line defect detection method and device | |
| CN111160428A (en) | Automatic vegetable identification method based on CNN-SVM algorithm | |
| CN209777324U (en) | assembled garbage sorting device | |
| WO2022241597A1 (en) | Ai intelligent garbage identification and classification system and method | |
| CN112818740A (en) | Psychological quality dimension evaluation method and device for intelligent interview |
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 | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190104 |