CN110226932A - The plantar pressure feature extracting method of human body daily behavior movement - Google Patents
The plantar pressure feature extracting method of human body daily behavior movement Download PDFInfo
- Publication number
- CN110226932A CN110226932A CN201811606326.3A CN201811606326A CN110226932A CN 110226932 A CN110226932 A CN 110226932A CN 201811606326 A CN201811606326 A CN 201811606326A CN 110226932 A CN110226932 A CN 110226932A
- Authority
- CN
- China
- Prior art keywords
- model
- pressure
- plantar pressure
- aic
- human body
- 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
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/1036—Measuring load distribution, e.g. podologic studies
- A61B5/1038—Measuring plantar pressure during gait
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1116—Determining posture transitions
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/112—Gait analysis
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/103—Detecting, measuring or recording devices for testing the shape, pattern, colour, size or movement of the body or parts thereof, for diagnostic purposes
- A61B5/11—Measuring movement of the entire body or parts thereof, e.g. head or hand tremor, mobility of a limb
- A61B5/1123—Discriminating type of movement, e.g. walking or running
-
- A—HUMAN NECESSITIES
- A61—MEDICAL OR VETERINARY SCIENCE; HYGIENE
- A61B—DIAGNOSIS; SURGERY; IDENTIFICATION
- A61B5/00—Measuring for diagnostic purposes; Identification of persons
- A61B5/68—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient
- A61B5/6801—Arrangements of detecting, measuring or recording means, e.g. sensors, in relation to patient specially adapted to be attached to or worn on the body surface
- A61B5/6802—Sensor mounted on worn items
- A61B5/6804—Garments; Clothes
- A61B5/6807—Footwear
Abstract
The invention discloses a kind of plantar pressure feature extracting methods of human body daily behavior movement.The present invention acquires first metatarsal bone, second metatarsal bone and the respective pressure signal of heel area by pressure insole, calculate pressure ratio, the pressure of each sensor and gross pressure are normalized, extract the fisrt feature sub-vector and second feature sub-vector of plantar pressure by overall pressure ratio.According under the various motor patterns of human body, the current value of plantar pressure sensor is all related to past value, constructs the AR model of plantar pressure signal, acquires model coefficient.Different daily behaviors are acted with the AIC calculating for carrying out vola AR model by testing, the value and dimension of comprehensive AIC propose tradeoff confidence level, and making order corresponding to the confidence level highest of tradeoff is most suitable order.The AR model coefficient of plantar pressure sensor is configured to third feature vector.The present invention determines the order of plantar pressure AR model by AIC criterion and tradeoff confidence level, there is good effect.
Description
Technical field
The invention belongs to feature extraction fields, are related to a kind of plantar pressure feature extraction side of human body daily behavior movement
Method.
Background technique
Plantar pressure refers to active force and reaction between vola and ground that Human Sole generates when being contacted with ground
Power, distribution situation disclose the details of foot movement, are of great significance, are widely used in human gait's analysis
The fields such as identification, motion tracking, action recognition.
Plantar pressure situation is initially the research in morbid state, this is because pressure distribution and the various foots of foot
Pathology have clinical correlation.Scanning and the pressure distribution in analysis vola are most important, this will be helpful to biomethanics after operation
Balance control, the identification research such as gait deviations or attitude disorders of assessment, orthoses design and improvement patient.Chen et al.
Pressure insole is made, the pattern-recognition moved using discrete touch power distribution signal, insole includes that foot is wearable
Interface and four FSR pressure sensors.Achkar etc. is devising the instrument comprising pressure sensor and inertial sensor later
Shoe system is for the elderly's daily routines and fall monitoring and diagnosis.Maximum value, minimum are generally comprised to the processing of plantar pressure
Value, average value and standard variance etc..Xia Yi acquires the vola pressure of walking process using its pressure measurement plate voluntarily developed
Power characterizes the distribution of pressure using space-time HOG feature, is used for Gait Recognition.Its data tested belongs to vola scanning
For image class as a result, its discrimination is reached for 93.5%, false alert rate 5.2% is accurate to feature through plantar nervous arch pair
The division of different footmarks.Chen passes through the gross pressure to discrete plantar pressure model, the related coefficient of several paths and three ranks
Autoregressive coefficient identifies gait movement, obtains considerable recognition effect.Plantar pressure refers to that Human Sole connects with ground
A kind of force signals generated when touching, size and distribution can reflect human leg, sufficient structure, function and entire body gesture
The information such as control are of great significance to human gait's analysis, are widely used in clinical diagnosis, the measurement of illness degree, postoperative treatment
The fields such as effect evaluation and action recognition.
Summary of the invention
In view of the deficiencies of the prior art, the present invention proposes a kind of plantar pressure features of human body daily behavior movement to mention
Take method.Firstly, it is each to acquire first metatarsal bone, second metatarsal bone and heel area by pressure insole according to plantar nervous arch figure
From pressure signal, calculate pressure ratio, overall pressure ratio normalizes the pressure of each sensor and gross pressure, extracts plantar pressure
Fisrt feature sub-vector and second feature sub-vector.According under the various motor patterns of human body, plantar pressure sensor
Current value is all related to past value, constructs the AR model of plantar pressure signal, acquires model coefficient.By experiment to not on the same day
The AIC that normal behavior act carries out vola AR model is calculated, and the value and dimension of comprehensive AIC propose tradeoff confidence level, make tradeoff
Order corresponding to confidence level highest is most suitable order.The AR model coefficient of plantar pressure sensor is configured to third
Characteristic vector.The present invention determines the order of plantar pressure AR model by AIC criterion and tradeoff confidence level, there is good effect
Fruit.
In order to achieve the goal above, the method for the present invention mainly comprises the steps that
Step (1), in first metatarsal bone, second metatarsal bone, heel area places plantar pressure sensor respectively, acquires human body
The plantar pressure signal of daily behavior；The movement of human body daily behavior includes: station, on seat or sits on level ground, squat, lie；
It walks, go upstairs, go downstairs, run in level land；Stand-seat, seat-stand, stand-seat level ground, sit level ground-and stand, stand
It squats, crouching-is stood, sat-lie, lie-and sits；- falling, downstairs-is walked-falls, upstairs to fall, race-tumble.
Step (2) sets FiThe respectively pressure size of 3 pressure sensors in vola, i=1,2,3, FstIt is total when to stand
Whether pressure, the weight that can characterize human body are undertaken by foot entirely；The pressure of each sensor and gross pressure are normalized, foot is extracted
The fisrt feature sub-vector F1 and second feature sub-vector F2 of bottom pressure, the extraction formula of characteristic vector F1, F2 are as follows:
Step (3) according under the various motor patterns of human body, the current value of plantar pressure sensor all with past value phase
It closes, constructs the AR model of plantar pressure signal, acquire model coefficient η1,η2,…ηP, it is specific as follows:
If XiFor plantar pressure signal sequence, then the AR model of plantar pressure signal sequence is as follows:
Xi-η1Xi-1-η2Xi-2-...-ηpXi-p=Ci (2)
Wherein, P is the order of AR model, CiFor error coefficient, ηpAs AR coefficient；
AR model can describe the signal relation of each rank by error equation, and the error equation of P rank AR model is as follows:
Cp+1=Xpη1+Xp-1η2+...+X1ηp-Xp+1
Cp+2=Xp+1η1+Xpη2+...+X2ηp-Xp+2
……
CN=Xn-1η1+Xn-1η2+...+Xn-pηp-Xn (3)
Matrix form is written as by formula (3) is various:
C=X η-Y (4)
Wherein C=[CP+1,CP+2,…Cn]T, η=[η1,η2,…ηP]T,Y=
[XP+1,XP+2,…Xn]T；The then least square solution of η are as follows: η=(XTX)-1XTY；
Step (4) acts the AIC calculating for carrying out vola AR model by experiment to different daily behaviors；It is specific as follows:
P rank AR model residual variance unbiased esti-mator is as follows:
Wherein,
The AIC of AR model:
AIC=NLog ση 2+2p (6)
By experiment different daily behaviors are acted with the AIC calculating for carrying out vola AR model according to formula (6)；
The value and dimension p of the comprehensive AIC of step (5), proposes tradeoff confidence level Cre:
In formula, AICnorTo normalize AIC value, p is order, that is, intrinsic dimensionality of AR model, and k is dimension weighted index；Make
The confidence level Cre of tradeoff is higher, corresponding order PCAs most suitable order；
AR model coefficient of the step (6) 3 plantar pressure sensors It is configured to third feature vector F 3=[η1,η2,η3]。
The present invention has a characteristic that compared with the feature extraction algorithm of existing many plantar pressure signals
Feature extracting method based on plantar pressure, AR model frequency resolution with higher, for the data of short section
Record, remains to generate reasonable Power estimation.The selection of model order has a significant impact to Power estimation characteristic, and order is too low, can make
Power estimation resolving power is low, cannot get ideal result, and order is excessively high, can not only increase calculation amount, can also generate on Power estimation
False details, the present invention are determined the order of AR model by AIC criterion and tradeoff confidence level Cre, there is good effect.
Detailed description of the invention
Fig. 1 is implementation flow chart of the invention；
Fig. 2 is part gait and tumble plantar pressure signal figure
Fig. 3 is the static overall pressure ratio in part；
Fig. 4 is tradeoff confidence level grayscale image.
Specific embodiment
Elaborate with reference to the accompanying drawing to the embodiment of the present invention: the present embodiment is being with technical solution of the present invention
Under the premise of implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
As shown in Figure 1, the present embodiment includes the following steps:
Step 1, in first metatarsal bone, second metatarsal bone, heel area places plantar pressure sensor, acquisition vola pressure respectively
Force signal.
Step 2, if Fi(i=1,2,3) is respectively the pressure size of 3 pressure sensors in vola, FstWhen to stand
Whether gross pressure, the weight that can characterize human body are undertaken by foot entirely.The pressure of each sensor and gross pressure are normalized, extracted
The fisrt feature sub-vector F1 and second feature sub-vector F2 of plantar pressure.
Step 3, according under the various motor patterns of human body, the current value of plantar pressure sensor all with past value phase
It closes, constructs the AR model of plantar pressure signal, acquire model coefficient η1,η2,…ηP。
Step 4 acts the AIC (Akaike for carrying out vola AR model to different daily behaviors by testing
Information Criterio) it calculates.
Step 5, the value and dimension p of comprehensive AIC propose tradeoff confidence level.Keep the confidence level of tradeoff higher, it is corresponding
Order is most suitable order.
Step 6, the AR model coefficient of 3 plantar pressure sensors It is configured to third feature vector F 3=[η1,η2,η3]。
As shown in Fig. 2, the sub-vector F2 that vola overall pressure ratio is formed can more intuitively identify contact feelings of the step with ground
Condition, and then distinguish static, movement major class of gait etc., the overall pressure ratio schematic diagram that Fig. 3 is 10 groups of stations, sits, lies, according to respective
The size of value can identify whether static movement has support behavior with threshold method easily.
When AIC (min) gets minimum value, that is, reach most suitable order.The suitable order that general AIC is calculated will not
It is excessively high, but get most suitable order value to measure the relationship of order and AIC value, the present invention by AR order be limited to 1 rank~
Between 12 ranks.It include tumble movement for different ADLs, the AIC for respectively carrying out vola AR model is calculated, and by respective AIC
Value is recorded in table 1, and the value of overstriking is the smallest value of AIC in the movement in table.
AIC value of 1 ADLs of table from tumble under different AR orders
Although the value of AIC is smaller, the feature extraction effect that identified order reaches, selected order is higher,
The dimension of input signal can be caused to increase, bring certain complexity to subsequent processing, it is evident that Cre is bigger, the order
It is more suitable.Fig. 4 is the tradeoff confidence level of each data calculated with above formula, and it is shorthand that wherein ordinate, which is number respectively,
Various ADLs, abscissa indicate the order of AR.For every data line, color more superficial show tradeoff confidence level more
Height, then the feature extraction effect that the order that abscissa indicates reaches might as well.From the point of view of every a line, light areas is concentrated mainly on
Order is 1~5, thus this embodiment of the invention selects order 3 as the parameter of AR model.
Claims (2)
1. the plantar pressure feature extracting method of human body daily behavior movement, which is characterized in that this method comprises the following steps:
Step (1), in first metatarsal bone, second metatarsal bone, heel area places plantar pressure sensor respectively, acquires the daily row of human body
For plantar pressure signal；
Step (2) sets FiThe respectively pressure size of 3 pressure sensors in vola, i=1,2,3, FstGross pressure when to stand,
Whether the weight that human body can be characterized is undertaken by foot entirely；The pressure of each sensor and gross pressure are normalized, plantar pressure is extracted
Fisrt feature sub-vector F1 and second feature sub-vector F2, the extraction formula of characteristic vector F1, F2 is as follows:
Step (3) is according under the various motor patterns of human body, and the current value of plantar pressure sensor is all related to past value, structure
The AR model for building plantar pressure signal, acquires model coefficient η1,η2,…ηP, it is specific as follows:
If XiFor plantar pressure signal sequence, then the AR model of plantar pressure signal sequence is as follows:
Xi-η1Xi-1-η2Xi-2-...-ηpXi-p=Ci (2)
Wherein, P is the order of AR model, CiFor error coefficient, ηpAs AR coefficient；
AR model can describe the signal relation of each rank by error equation, and the error equation of P rank AR model is as follows:
Matrix form is written as by formula (3) is various:
C=X η-Y (4)
Wherein C=[CP+1,CP+2,…Cn]T, η=[η1,η2,…ηP]T,Y=[XP+1,
XP+2,…Xn]T；The then least square solution of η are as follows: η=(XTX)-1XTY；
Step (4) acts the AIC calculating for carrying out vola AR model by experiment to different daily behaviors；It is specific as follows:
P rank AR model residual variance unbiased esti-mator is as follows:
Wherein,
The AIC of AR model:
AIC=NLog ση 2+2p (6)
By experiment different daily behaviors are acted with the AIC calculating for carrying out vola AR model according to formula (6)；
The value and dimension p of the comprehensive AIC of step (5), proposes tradeoff confidence level Cre:
In formula, AICnorTo normalize AIC value, p is order, that is, intrinsic dimensionality of AR model, and k is dimension weighted index；Make to weigh
Higher, the corresponding order P of confidence level CreCAs most suitable order；
AR model coefficient of the step (6) 3 plantar pressure sensors It is configured to third feature vector F 3=[η1,η2,η3]。
2. the plantar pressure feature extracting method of human body daily behavior movement according to claim 1, it is characterised in that: institute
The human body daily behavior movement stated includes: station, on seat or sits on level ground, squat, lie；It walks, go upstairs, downstairs in level land
Ladder, running；Stand-seat, seat-stand, stand-seat level ground, sit level ground-stand, stand-crouching, crouching-are stood, are sat-lie, lie-
It sits；- falling, downstairs-is walked-falls, upstairs to fall, race-tumble.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606326.3A CN110226932A (en) | 2018-12-26 | 2018-12-26 | The plantar pressure feature extracting method of human body daily behavior movement |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201811606326.3A CN110226932A (en) | 2018-12-26 | 2018-12-26 | The plantar pressure feature extracting method of human body daily behavior movement |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110226932A true CN110226932A (en) | 2019-09-13 |
Family
ID=67861904
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201811606326.3A Pending CN110226932A (en) | 2018-12-26 | 2018-12-26 | The plantar pressure feature extracting method of human body daily behavior movement |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110226932A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111493454A (en) * | 2020-04-26 | 2020-08-07 | 湖北民族大学 | Weight measurement insole, shoe, system and weight measurement method |
| CN113229801A (en) * | 2021-03-04 | 2021-08-10 | 南京邮电大学 | Insole type sole pressure measuring system and method |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11113884A (en) * | 1997-10-08 | 1999-04-27 | Nippon Telegr & Teleph Corp <Ntt> | Walking analysis method, device thereof, and recording medium recording the method |
| US7716022B1 (en) * | 2005-05-09 | 2010-05-11 | Sas Institute Inc. | Computer-implemented systems and methods for processing time series data |
| CN106389074A (en) * | 2016-01-27 | 2017-02-15 | 北京航空航天大学 | Falling process stability predicting device and method based on plantar pressure sensing |
| CN106937872A (en) * | 2017-04-20 | 2017-07-11 | 杭州电子科技大学 | A kind of gait bilateral symmetric property evaluation method based on regression curve |
| CN107247893A (en) * | 2017-05-10 | 2017-10-13 | 广东工业大学 | A kind of electric personal identification method of the brain based on genetic algorithm dimensionality reduction |
| CN107622260A (en) * | 2017-10-26 | 2018-01-23 | 杭州电子科技大学 | Lower limb gait phase identification method based on multi-source bio signal |
| WO2018175935A1 (en) * | 2017-03-24 | 2018-09-27 | Medtronic Minimed, Inc. | Patient-specific glucose prediction systems and methods |
| CN108731732A (en) * | 2018-05-22 | 2018-11-02 | 洛阳中科汇成科技有限公司 | Based on periodic mode information to the processing method and system of plantar pressure |
| CN108836337A (en) * | 2018-05-04 | 2018-11-20 | 福建省莆田市双驰智能信息技术有限公司 | A method of personalized sufficient type health detection is carried out by foot movement state |
-
2018
- 2018-12-26 CN CN201811606326.3A patent/CN110226932A/en active Pending
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JPH11113884A (en) * | 1997-10-08 | 1999-04-27 | Nippon Telegr & Teleph Corp <Ntt> | Walking analysis method, device thereof, and recording medium recording the method |
| US7716022B1 (en) * | 2005-05-09 | 2010-05-11 | Sas Institute Inc. | Computer-implemented systems and methods for processing time series data |
| CN106389074A (en) * | 2016-01-27 | 2017-02-15 | 北京航空航天大学 | Falling process stability predicting device and method based on plantar pressure sensing |
| WO2018175935A1 (en) * | 2017-03-24 | 2018-09-27 | Medtronic Minimed, Inc. | Patient-specific glucose prediction systems and methods |
| CN106937872A (en) * | 2017-04-20 | 2017-07-11 | 杭州电子科技大学 | A kind of gait bilateral symmetric property evaluation method based on regression curve |
| CN107247893A (en) * | 2017-05-10 | 2017-10-13 | 广东工业大学 | A kind of electric personal identification method of the brain based on genetic algorithm dimensionality reduction |
| CN107622260A (en) * | 2017-10-26 | 2018-01-23 | 杭州电子科技大学 | Lower limb gait phase identification method based on multi-source bio signal |
| CN108836337A (en) * | 2018-05-04 | 2018-11-20 | 福建省莆田市双驰智能信息技术有限公司 | A method of personalized sufficient type health detection is carried out by foot movement state |
| CN108731732A (en) * | 2018-05-22 | 2018-11-02 | 洛阳中科汇成科技有限公司 | Based on periodic mode information to the processing method and system of plantar pressure |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111493454A (en) * | 2020-04-26 | 2020-08-07 | 湖北民族大学 | Weight measurement insole, shoe, system and weight measurement method |
| CN111493454B (en) * | 2020-04-26 | 2021-07-23 | 湖北民族大学 | Weight measurement insole, shoe, system and weight measurement method |
| CN113229801A (en) * | 2021-03-04 | 2021-08-10 | 南京邮电大学 | Insole type sole pressure measuring system and method |
| CN113229801B (en) * | 2021-03-04 | 2022-07-01 | 南京邮电大学 | Insole type sole pressure measuring system and method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Dannecker et al. | A comparison of energy expenditure estimation of several physical activity monitors | |
| JP7235260B2 (en) | Gait/foot evaluation system, terminal device, gait/foot evaluation method, and gait/foot evaluation program | |
| US20240070461A1 (en) | Method and system for activity classification | |
| US11660024B2 (en) | Method and system for analyzing human gait | |
| Howcroft et al. | Prospective fall-risk prediction models for older adults based on wearable sensors | |
| CN108244744B (en) | Motion state identification method, sole and shoe | |
| US20110054359A1 (en) | Footwear-based body weight monitor and postural allocation, physical activity classification, and energy expenditure calculator | |
| Di Rosa et al. | Concurrent validation of an index to estimate fall risk in community dwelling seniors through a wireless sensor insole system: A pilot study | |
| Hegde et al. | The pediatric SmartShoe: wearable sensor system for ambulatory monitoring of physical activity and gait | |
| Sazonova et al. | Accurate prediction of energy expenditure using a shoe-based activity monitor | |
| Sazonov et al. | Posture and activity recognition and energy expenditure estimation in a wearable platform | |
| CN105051799A (en) | Method for detecting falls and a fall detector. | |
| CN110313916A (en) | A kind of patient with diabetic feet plantar pressure characteristic recognition method | |
| CN112617807A (en) | Device and method for preventing and relieving frozen gait of Parkinson disease patient | |
| CN110226932A (en) | The plantar pressure feature extracting method of human body daily behavior movement | |
| Gimmon et al. | Gait coordination deteriorates in independent old-old adults | |
| Pasluosta et al. | Pull test estimation in Parkinson's disease patients using wearable sensor technology | |
| KR101974831B1 (en) | Method for Assessing Fall Risk and User Terminal therefor | |
| Liu et al. | SVM-based multi-sensor fusion for free-living physical activity assessment | |
| Liu et al. | Validation of an accelerometer-based fall prediction model | |
| CN113057627A (en) | Gait feature extraction method based on weak foot COP features and falling risk discrimination system | |
| Guo et al. | A shoe-integrated sensor system for long-term center of pressure evaluation | |
| Howcroft et al. | Understanding responses to gait instability from plantar pressure measurement and the relationship to balance and mobility in lower-limb amputees | |
| Wu et al. | A study on gait-based Parkinson's disease detection using a force sensitive platform | |
| El Achkar et al. | Physical activity recognition via minimal in-shoes force sensor configuration |
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: 20190913 |
|
| RJ01 | Rejection of invention patent application after publication |