CN106971203A - Personal identification method based on characteristic on foot - Google Patents
Personal identification method based on characteristic on foot Download PDFInfo
- Publication number
- CN106971203A CN106971203A CN201710205410.3A CN201710205410A CN106971203A CN 106971203 A CN106971203 A CN 106971203A CN 201710205410 A CN201710205410 A CN 201710205410A CN 106971203 A CN106971203 A CN 106971203A
- Authority
- CN
- China
- Prior art keywords
- section
- foot
- characteristic
- personal identification
- identification method
- 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.)
- Granted
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/243—Classification techniques relating to the number of classes
- G06F18/24317—Piecewise classification, i.e. whereby each classification requires several discriminant rules
-
- G—PHYSICS
- G01—MEASURING; TESTING
- G01P—MEASURING LINEAR OR ANGULAR SPEED, ACCELERATION, DECELERATION, OR SHOCK; INDICATING PRESENCE, ABSENCE, OR DIRECTION, OF MOVEMENT
- G01P15/00—Measuring acceleration; Measuring deceleration; Measuring shock, i.e. sudden change of acceleration
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Bioinformatics & Computational Biology (AREA)
- General Engineering & Computer Science (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Life Sciences & Earth Sciences (AREA)
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
- Telephone Function (AREA)
Abstract
The invention discloses a kind of personal identification method based on characteristic on foot, including step:3-axis acceleration data to collection are segmented, by one section of continuous movement decomposition into the regular length of Time Continuous data slot;Feature is calculated in time domain and frequency domain respectively to each data slot;Each section of feature is classified with the good grader of training in advance;The recognition result of the continuous data slot of certain amount is collected, identification result is drawn.Circuit-switched data can be walked by the smart mobile phone collection carried with, extract the feature for classification, then the circuit-switched data of walking of collection is classified using the grader trained, so as to recognize the identity of currently used person.The cost of equipment is effectively saved, while having reached good recognition effect again.
Description
Technical field
The invention belongs to identity identification technical field, more particularly to a kind of walking for sensor collection based on smart mobile phone
The method that circuit-switched data carries out identification.
Background technology
Application of the various intelligence systems in life is more and more universal.Identification is frequently necessary in intelligence system to carry
For personalized service.Identification is that mainly have personal identification by some in a very stubborn problem, conventional method
The things of feature differentiates, such as the identity article such as certificate, key, or username and password etc identity
Knowledge.But traditional authentication identifying method have the disadvantage it is quite obvious:Identity article is easily lost or is forged, identity
Mark knowledge is easily forgotten or is stolen.It can in addition contain the biological characteristic such as face characteristic using everyone in itself, fingerprint etc.
Deng with regard to good effect can be reached.But requirement of this kind of method to technology and equipment is too high.
Automatically recognize the physical activity of the mankind, commonly referred to as User Activity identification (HAR, Human Activity
Recognition) technology, is an important research direction in man-machine interaction and general fit calculation field, its object is to automatic
Obtain the information on User Activity and be supplied to the service or application of correlation, allow them to more active and aid in exactly
User completes their target.Traditional User Activity identification technology mainly uses the method based on computer vision, such skill
Art is analyzed rest image or video by image processing method, so as to extract the activity of user and to the class of activity
Do not judged.Although such technology has been obtained for extensive research, it remains more obvious defect:
1st, such technology depends on external equipment, therefore is limited in using scope and has deployed image capture device
In (such as camera) and the region that can be observed by these equipment.
2nd, by the transmissive information of image institute is enriched very much, have the other information in addition to User Activity and be compromised
Risk, therefore there is also more serious privacy concern for such technology.
3rd, because image procossing and video processing technique require higher to network transmission bandwidth and computing capability, in existing skill
It is difficult to accomplish processing, therefore also limit application of such technology in real-time system in real time under the conditions of art.
In the last few years, as Intelligent mobile equipment (such as smart mobile phone, wearable device) and related sensor are (as action is passed
Sensor, skin electric transducer) etc. technology develop rapidly, the emphasis of User Activity identification technology research just regarded from based on computer
The method of feel turns to the recognition methods based on other sensors on the Intelligent mobile equipment that user carries with.The present invention is therefore
.
The content of the invention
For above-mentioned technical problem, the present invention seeks to:There is provided a kind of identity based on characteristic on foot
Recognition methods, can walk circuit-switched data by the smart mobile phone collection carried with, extract the feature for classification, then utilize
The grader trained is classified to the circuit-switched data of walking of collection, so as to recognize the identity of currently used person.It is effectively saved and sets
Standby cost, while having reached good recognition effect again.
The technical scheme is that:
A kind of personal identification method based on characteristic on foot, comprises the following steps:
S01:3-axis acceleration data to collection are segmented, by one section of continuous movement decomposition consolidating into Time Continuous
The data slot of measured length;
S02:Feature is calculated in time domain and frequency domain respectively to each data slot;
S03:Each section of feature is classified with the good grader of training in advance;
S04:The recognition result of the continuous data slot of certain amount is collected, identification result is drawn.
It is preferred that, with vertical direction x-axis in the step S01, left and right directions is y-axis, and fore-and-aft direction is that z-axis sets up right angle
Coordinate system, 3-axis acceleration data include x-axis acceleration information, y-axis acceleration information and z-axis acceleration information.
It is preferred that, the feature calculated in the time domain in the step S02 include maximum, minimum value, average, amplitude,
Root, standard deviation, zero-crossing rate and kurtosis, the feature calculated in a frequency domain include peak frequency, second largest frequency and spectrum slope.
It is preferred that, the calculation formula of the root mean square is:
Wherein, i represents i-th section, aikK-th of sample point in section is represented, N represents sample number total in section.
It is preferred that, the calculation formula of the zero-crossing rate is:
Wherein, i represents i-th section, aikK-th of sample point in section is represented, N represents sample number total in section, IR < 0It is
One target function:
It is preferred that, the calculation formula of the kurtosis is:
Wherein, i represents i-th section, aikK-th of sample point in section is represented,It is the average of all sample points, N tables
Show sample number total in section.
It is preferred that, the calculation formula of the spectrum slope is:
Wherein, i represents i-th section, ai(k) it is frequency f as i-th section of k-th of frequency componenti(k) corresponding width
Degree, N represents sample number total in section.
It is preferred that, the 3-axis acceleration data to collection before data sectional are pre-processed, and are removed straight in data
Flow component.
It is preferred that, in the step S04, if the data slot more than half is identified as non-user, that is, sentence
It is set to no, is alarmed;Otherwise, it is determined that being yes.
It is preferred that, also include before the step S01, pass through the 3-axis acceleration sensor collection three built in smart mobile phone
Axle acceleration data, when judging that user walks, carries out step S01.
Compared with prior art, it is an advantage of the invention that:
1. practicality:This method utilizes the 3-axis acceleration sensor gathered data built in commercial ready-made smart mobile phone,
Without extra special installation, the cost of equipment is effectively saved.
2. reliability:This method trains grader using mankind's activity recognition methods (HAR), then utilizes point trained
Class device is classified to the data of currently used person, so as to recognize the identity of currently used person.As long as training set is enough, identification
Error very little.Differentiate that decision-making technique can be such that accuracy further improves finally by the identity in this method.
3. convenience:The foundation that this method is used for differentiating user identity is that walking for user is accustomed to.Custom is different from foot
Key, identity card etc. is conventionally used to the foundation of identification, and in the absence of loss, situation about forgetting occurs.
4. flexibility:The scope of application of this method is larger, waits bad weather reliably to use overcast and rainy.
Brief description of the drawings
Below in conjunction with the accompanying drawings and embodiment the invention will be further described:
Fig. 1 is flow chart of the method for the present invention;
Fig. 2 is smart mobile phone and its coordinate system with acceleration transducer
Fig. 3 is the schematic diagram for the data that 3-axis acceleration sensor of the present invention is gathered;
Fig. 4 is the accuracy of 5 kinds of graders of the present invention;
Fig. 5 is the used time of 5 kinds of graders of the present invention.
Embodiment
Such scheme is described further below in conjunction with specific embodiment.It should be understood that these embodiments are to be used to illustrate
The present invention and be not limited to limit the scope of the present invention.The implementation condition used in embodiment can be done according to the condition of specific producer
Further adjustment, unreceipted implementation condition is usually the condition in normal experiment.
Embodiment:
As shown in figure 1, the present embodiment, which is based on away circuit-switched data, carries out identification.This method is main by data acquisition, data
Feature extraction, multi-categorizer training and daily routines recognize that four parts are constituted.Specifically include following steps:
S01:3-axis acceleration data to collection are segmented, by one section of continuous movement decomposition consolidating into Time Continuous
The data slot of measured length;
S02:Feature is calculated in time domain and frequency domain respectively to each data slot;
S03:Each section of feature is classified with the good grader of training in advance;
S04:The recognition result of the continuous data slot of certain amount is collected, identification result is drawn.
3-axis acceleration data are gathered by the 3-axis acceleration sensor built in smart mobile phone in the present embodiment, when
It can also be so acquired for the intelligent terminal of other built-in 3-axis acceleration sensors.Specific implementation step is as follows:
(1) collection of data is the first step of the present invention.Analyzed and tested to collect raw acceleration data, I
Develop application program in an Android platform.The application program about 15 3-axis accelerations of generation per second are counted
According to record, and it can also be continued to run with backstage.Then 16 different heights, the volunteer of body weight are recruited to walk collection number
According to.As shown in Fig. 2 with vertical direction x-axis, left and right directions is y-axis, fore-and-aft direction is that z-axis sets up rectangular coordinate system, and three axles accelerate
Degrees of data includes x-axis acceleration information, y-axis acceleration information and z-axis acceleration information, and the data of collection are as shown in Figure 3.Aspiration
Person smoothly goes ahead, it is allowed to 90 degree of turnings, but does not allow the touch turn of jerk and 180 degree.There is 1 people to be selected in 16 people
For the owner of positive sample, i.e. mobile phone, remaining 15 people is negative sample.
(2) data collected are pre-processed, eliminates DC component.Then we utilize time-based cunning
Dynamic window is segmented to it, and between adjacent window apertures overlapping 40% section.Thus by one section of original number after pretreated
The section equal according to several window sizes are divided into, establishes data set.Data set is divided into training set and two parts of test set,
Wherein training set includes the people of positive sample 1,627, the people of negative sample 11,850.Test set includes the people of positive sample 1,327, bears sample
This 4 people, 319.The data of wherein positive sample are not on the sample in a gatherer process, and the data of negative sample do not have phase
The data of same people.
(3) feature extraction is carried out for each sample in step (2), in the time domain, calculates following characteristics:It is maximum
Value, minimum value, average, amplitude, root mean square, standard deviation, zero-crossing rate and kurtosis.Including x, y, 3 components of z-axis, in addition,
Due to x, y, z3 axles may have relation in synchronization, so introducingIt is used as the 4th component.Each point
Amount have above except ZCR 7 features (Consistently greater than 0, so ZCR is always 0, it is nonsensical).So
31 features are had in the time domain.
(4) for the feature extraction in step (2), in a frequency domain, following characteristics are calculated:Peak frequency, second largest frequency
With spectrum slope (Spectral Slope).Including x, y, 3 components of z-axis, withoutSo in frequency domain
In have 9 features.
(5) using unified training characteristics training grader, SVM (Support Vector be trained in this example
), Machine Random Forest, Naive Bayes, Logistic and MLP (Multi-layer perceptron
Neural networks) Various Classifiers on Regional.Each data slot in test set is divided with the grader trained again
Class, so as to recognize the identity of each section, the result as shown in figure 4, wherein SVM, Random Forest, Logistic and MLP
Accuracy rate all near 98%.Wherein MLP recognition capability is optimal, has reached 98.1132%, next to that SVM
97.7987%, and Random Forest and Logistic accuracy rate are 97.6415%.Although but MLP identification is accurate
Property it is optimal, but the time that its training pattern is consumed is also several more more than other, as shown in Figure 5.
(6) to continuous 20 time-based section, it is identified labeled as { s1, s2 ..., s20 }, if wherein had super
More than half sections are identified as non-user, that is, are determined as no, and alarm are sent, otherwise, it is determined that being yes.Due to step (5)
In more than 95% has been reached to the recognition accuracy of section, then by the identity identification in this step, discrimination almost connects
Nearly 100%.
To sum up, if certain user carries the mobile phone installed and employ the software of the present invention, when the first of hand-set from stolen
Between, mobile phone will recognise that stolen possibility, and send alarm.So as to reach the purpose of protection user's property.
The foregoing examples are merely illustrative of the technical concept and features of the invention, its object is to allow the person skilled in the art to be
Present disclosure can be understood and implemented according to this, it is not intended to limit the scope of the present invention.It is all smart according to the present invention
Equivalent transformation or modification that refreshing essence is done, should all be included within the scope of the present invention.
Claims (10)
1. a kind of personal identification method based on characteristic on foot, it is characterised in that comprise the following steps:
S01:3-axis acceleration data to collection are segmented, and one section of continuous movement decomposition is grown into the fixed of Time Continuous
The data slot of degree;
S02:Feature is calculated in time domain and frequency domain respectively to each data slot;
S03:Each section of feature is classified with the good grader of training in advance;
S04:The recognition result of the continuous data slot of certain amount is collected, identification result is drawn.
2. the personal identification method according to claim 1 based on characteristic on foot, it is characterised in that the step
With vertical direction x-axis in S01, left and right directions is y-axis, and fore-and-aft direction is that z-axis sets up rectangular coordinate system, 3-axis acceleration packet
Include x-axis acceleration information, y-axis acceleration information and z-axis acceleration information.
3. the personal identification method according to claim 1 based on characteristic on foot, it is characterised in that the step
The feature calculated in the time domain in S02 includes maximum, minimum value, average, amplitude, root mean square, standard deviation, zero-crossing rate and peak
Degree, the feature calculated in a frequency domain includes peak frequency, second largest frequency and spectrum slope.
4. the personal identification method according to claim 3 based on characteristic on foot, it is characterised in that the root mean square
Calculation formula be:
Wherein, i represents i-th section, aikK-th of sample point in section is represented, N represents sample number total in section.
5. the personal identification method according to claim 3 based on characteristic on foot, it is characterised in that the zero-crossing rate
Calculation formula be:
Wherein, i represents i-th section, aikK-th of sample point in section is represented, N represents sample number total in section, IR < 0It is a finger
Scalar functions:
6. the personal identification method according to claim 3 based on characteristic on foot, it is characterised in that the kurtosis
Calculation formula is:
Wherein, i represents i-th section, aikK-th of sample point in section is represented,It is the average of all sample points, N represents section
In total sample number.
7. the personal identification method according to claim 3 based on characteristic on foot, it is characterised in that the frequency spectrum is oblique
The calculation formula of rate is:
Wherein, i represents i-th section, ai(k) it is frequency f as i-th section of k-th of frequency componenti(k) respective amplitude, N
Represent sample number total in section.
8. the personal identification method according to claim 1 based on characteristic on foot, it is characterised in that in data sectional
The 3-axis acceleration data to collection are pre-processed before, remove the DC component in data.
9. the personal identification method according to claim 1 based on characteristic on foot, it is characterised in that the step
In S04, if the data slot more than half is identified as non-user, that is, it is determined as no, is alarmed;Otherwise, sentence
Being set to is.
10. the personal identification method according to claim 1 based on characteristic on foot, it is characterised in that the step
Also include before S01,3-axis acceleration data are gathered by the 3-axis acceleration sensor built in smart mobile phone, judge that user walks
Lu Shi, carries out step S01.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205410.3A CN106971203B (en) | 2017-03-31 | 2017-03-31 | Identity recognition method based on walking characteristic data |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710205410.3A CN106971203B (en) | 2017-03-31 | 2017-03-31 | Identity recognition method based on walking characteristic data |
Publications (2)
Publication Number | Publication Date |
---|---|
CN106971203A true CN106971203A (en) | 2017-07-21 |
CN106971203B CN106971203B (en) | 2020-06-09 |
Family
ID=59336563
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710205410.3A Expired - Fee Related CN106971203B (en) | 2017-03-31 | 2017-03-31 | Identity recognition method based on walking characteristic data |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106971203B (en) |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108537014A (en) * | 2018-04-04 | 2018-09-14 | 深圳大学 | A kind of method for authenticating user identity and system based on mobile device |
CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
CN108737623A (en) * | 2018-05-31 | 2018-11-02 | 南京航空航天大学 | The method for identifying ID of position and carrying mode is carried based on smart mobile phone |
CN108965585A (en) * | 2018-06-22 | 2018-12-07 | 成都博宇科技有限公司 | A kind of method for identifying ID based on intelligent mobile phone sensor |
Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101695445A (en) * | 2009-10-29 | 2010-04-21 | 浙江大学 | Acceleration transducer-based gait identification method |
WO2012171967A2 (en) * | 2011-06-17 | 2012-12-20 | Myotest Sa | An athletic performance monitoring device |
CN103150036A (en) * | 2013-02-06 | 2013-06-12 | 宋子健 | Information acquisition system and method, man-machine interaction system and method, and shoes |
CN103886341A (en) * | 2014-03-19 | 2014-06-25 | 国家电网公司 | Gait behavior recognition method based on feature combination |
WO2014191803A1 (en) * | 2013-05-27 | 2014-12-04 | Tata Consultancy Services Limited | Acceleration-based step activity detection and classification on mobile devices |
CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
CN105212941A (en) * | 2015-08-25 | 2016-01-06 | 武汉理工大学 | A kind of human body active state recognition methods and system |
CN105279411A (en) * | 2015-09-22 | 2016-01-27 | 电子科技大学 | Gait bio-feature based mobile device identity recognition method |
CN105528613A (en) * | 2015-11-30 | 2016-04-27 | 南京邮电大学 | Behavior identification method based on GPS speed and acceleration data of smart phone |
CN106454723A (en) * | 2016-09-09 | 2017-02-22 | 常州大学 | Mobile phone accelerometer based child custody method |
-
2017
- 2017-03-31 CN CN201710205410.3A patent/CN106971203B/en not_active Expired - Fee Related
Patent Citations (10)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN101695445A (en) * | 2009-10-29 | 2010-04-21 | 浙江大学 | Acceleration transducer-based gait identification method |
WO2012171967A2 (en) * | 2011-06-17 | 2012-12-20 | Myotest Sa | An athletic performance monitoring device |
CN103150036A (en) * | 2013-02-06 | 2013-06-12 | 宋子健 | Information acquisition system and method, man-machine interaction system and method, and shoes |
WO2014191803A1 (en) * | 2013-05-27 | 2014-12-04 | Tata Consultancy Services Limited | Acceleration-based step activity detection and classification on mobile devices |
CN103886341A (en) * | 2014-03-19 | 2014-06-25 | 国家电网公司 | Gait behavior recognition method based on feature combination |
CN104268577A (en) * | 2014-06-27 | 2015-01-07 | 大连理工大学 | Human body behavior identification method based on inertial sensor |
CN105212941A (en) * | 2015-08-25 | 2016-01-06 | 武汉理工大学 | A kind of human body active state recognition methods and system |
CN105279411A (en) * | 2015-09-22 | 2016-01-27 | 电子科技大学 | Gait bio-feature based mobile device identity recognition method |
CN105528613A (en) * | 2015-11-30 | 2016-04-27 | 南京邮电大学 | Behavior identification method based on GPS speed and acceleration data of smart phone |
CN106454723A (en) * | 2016-09-09 | 2017-02-22 | 常州大学 | Mobile phone accelerometer based child custody method |
Non-Patent Citations (3)
Title |
---|
HAYLEY HUNG ET AL: ""Classifying social actions with a single accelerometer"", 《PROCEEDINGS OF THE 2013 ACM INTERNATIONAL JOINT CONFERENCE ON PERVASIVE AND UBIQUITOUS》 * |
徐川龙: ""基于三维加速度传感器的人体行为识别"", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
李勇谋: ""基于智能手机的活动识别和身份识别技术研究"", 《中国优秀硕士学位论文全文数据库-信息科技辑》 * |
Cited By (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108537014A (en) * | 2018-04-04 | 2018-09-14 | 深圳大学 | A kind of method for authenticating user identity and system based on mobile device |
CN108710788A (en) * | 2018-05-22 | 2018-10-26 | 上海众人网络安全技术有限公司 | A kind of safety certifying method, device, terminal and storage medium |
CN108737623A (en) * | 2018-05-31 | 2018-11-02 | 南京航空航天大学 | The method for identifying ID of position and carrying mode is carried based on smart mobile phone |
CN108965585A (en) * | 2018-06-22 | 2018-12-07 | 成都博宇科技有限公司 | A kind of method for identifying ID based on intelligent mobile phone sensor |
Also Published As
Publication number | Publication date |
---|---|
CN106971203B (en) | 2020-06-09 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN101558996B (en) | Gait recognition method based on orthogonal projection three-dimensional reconstruction of human motion structure | |
Mubashir et al. | A survey on fall detection: Principles and approaches | |
CN106971203A (en) | Personal identification method based on characteristic on foot | |
CN107016346A (en) | gait identification method and system | |
Kao et al. | Development of a portable activity detector for daily activity recognition | |
CN103093234B (en) | Based on the personal identification method of ground reaction force during walking | |
Nickel et al. | Classification of acceleration data for biometric gait recognition on mobile devices | |
CN107831907A (en) | Identity identifying method and device based on Gait Recognition | |
CN106156564B (en) | Driver identification method based on smart phone | |
CN202257856U (en) | Driver fatigue-driving monitoring device | |
CN101620673A (en) | Robust face detecting and tracking method | |
CN111178155B (en) | Gait feature extraction and gait recognition method based on inertial sensor | |
CN103049741A (en) | Foot-to-ground acting force-based gait feature extraction method and gait identification system | |
Zylius | Investigation of route-independent aggressive and safe driving features obtained from accelerometer signals | |
CN105138967B (en) | Biopsy method and device based on human eye area active state | |
Xiao et al. | Daily human physical activity recognition based on kernel discriminant analysis and extreme learning machine | |
CN111505632A (en) | Ultra-wideband radar action attitude identification method based on power spectrum and Doppler characteristics | |
CN108629167A (en) | A kind of more smart machine identity identifying methods of combination wearable device | |
CN108958482B (en) | Similarity action recognition device and method based on convolutional neural network | |
He | Activity recognition from accelerometer signals based on wavelet-ar model | |
CN108245172A (en) | It is a kind of not by the human posture recognition method of position constraint | |
Hestbek et al. | Biometric gait recognition for mobile devices using wavelet transform and support vector machines | |
CN107169334B (en) | The user authen method based on straight punch motion detection for hand wearable device | |
CN107103219B (en) | Gait-based wearable device user identification method and system | |
CN114155614A (en) | Method and system for identifying anti-violation behaviors in operation site |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
GR01 | Patent grant | ||
GR01 | Patent grant | ||
CF01 | Termination of patent right due to non-payment of annual fee | ||
CF01 | Termination of patent right due to non-payment of annual fee |
Granted publication date: 20200609 Termination date: 20210331 |