CN109284695A - A kind of image makings method for improving based on data mining - Google Patents
A kind of image makings method for improving based on data mining Download PDFInfo
- Publication number
- CN109284695A CN109284695A CN201811017859.8A CN201811017859A CN109284695A CN 109284695 A CN109284695 A CN 109284695A CN 201811017859 A CN201811017859 A CN 201811017859A CN 109284695 A CN109284695 A CN 109284695A
- Authority
- CN
- China
- Prior art keywords
- behavior
- data
- neural network
- representing
- hidden layer
- 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.)
- Withdrawn
Links
- 238000000034 method Methods 0.000 title claims abstract description 22
- 238000007418 data mining Methods 0.000 title claims abstract description 17
- 238000013528 artificial neural network Methods 0.000 claims abstract description 22
- 238000003062 neural network model Methods 0.000 claims abstract description 17
- 239000011159 matrix material Substances 0.000 claims abstract description 12
- 230000006399 behavior Effects 0.000 claims description 73
- 230000006870 function Effects 0.000 claims description 15
- 230000001133 acceleration Effects 0.000 claims description 11
- 210000000689 upper leg Anatomy 0.000 claims description 4
- 210000000707 wrist Anatomy 0.000 claims description 4
- 210000001217 buttock Anatomy 0.000 claims description 3
- 210000002414 leg Anatomy 0.000 claims description 3
- 238000012886 linear function Methods 0.000 claims description 3
- 230000002194 synthesizing effect Effects 0.000 claims description 3
- 210000000038 chest Anatomy 0.000 claims 1
- 230000007613 environmental effect Effects 0.000 abstract 1
- 230000003542 behavioural effect Effects 0.000 description 2
- 238000010586 diagram Methods 0.000 description 2
- 238000004458 analytical method Methods 0.000 description 1
- 230000003796 beauty Effects 0.000 description 1
- 230000037237 body shape Effects 0.000 description 1
- 230000007547 defect Effects 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06V—IMAGE OR VIDEO RECOGNITION OR UNDERSTANDING
- G06V40/00—Recognition of biometric, human-related or animal-related patterns in image or video data
- G06V40/20—Movements or behaviour, e.g. gesture recognition
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/04—Architecture, e.g. interconnection topology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Landscapes
- Engineering & Computer Science (AREA)
- Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- General Physics & Mathematics (AREA)
- Molecular Biology (AREA)
- Computational Linguistics (AREA)
- Software Systems (AREA)
- Mathematical Physics (AREA)
- General Engineering & Computer Science (AREA)
- Life Sciences & Earth Sciences (AREA)
- Artificial Intelligence (AREA)
- Biomedical Technology (AREA)
- Biophysics (AREA)
- Computing Systems (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Human Computer Interaction (AREA)
- Psychiatry (AREA)
- Multimedia (AREA)
- Social Psychology (AREA)
- Image Analysis (AREA)
Abstract
The invention discloses a kind of image makings method for improving based on data mining, include the following steps: S1: body model parameter and the corresponding behavior attitude data of the professional dancer of acquisition a batch and/or model, and Cloud Server is uploaded to as criterion behavior attitude data, body model parameter, behavior attitude data constitute influence factor matrix X, body model parameter is environmental variance, and behavior attitude data is decision variable;S2: comprehensive speciality dancer and/or the daily behavior posture of model, acquisition user corresponds to the data sample composing indexes matrix Y of behavior posture, index matrix Y is learnt using BP neural network, trains, examine, and establishes the BP neural network model of behavior posture for the body model parameter of user;S3: predicting data using BP neural network model, obtains recommending decision variable X*, and decision variable X will be recommended*It is issued to user terminal, user is according to recommendation decision variable X*Factum posture is corrected, image makings are improved.
Description
Technical Field
The invention belongs to the field of neural network big data, and particularly designs an image gas quality improving method based on data mining.
Background
The image quality training not only enables people to obtain healthy beauty, but also enables people to obtain beautiful body shape, beautiful posture, beautiful action and beautiful quality, and because of the fact that the image quality training is more and more emphasized by people, the behavior posture correction system is used as a mode for improving the image quality of people and becomes a favorite choice of people. The training of the behavior posture can be realized at any time and any place in the ordinary life of people. However, people usually lack a reasonable guidance scheme, and the wrong method may cause the daily training of users to achieve the ideal effect, resulting in irreparable time loss and great energy loss.
At present, the problem to be solved is to establish a set of comprehensive behavior posture model and feed back the behavior posture data of the user to the user, so that the user can correct his posture in time. High complexity and nonlinearity are often reflected among all factors influencing behavior attitude scoring, certain difficulty exists in the adoption of a conventional prediction and analysis method, and the BP neural network has high modeling precision on a nonlinear system and is very suitable for building a behavior attitude model. The user utilizes the optimal behavior posture correction scheme of issuing to carry out daily training and promotes self image quality, provides a new thinking for the intelligent behavior posture correction of big data era.
Disclosure of Invention
The invention aims to overcome the defects of the prior art and provide a data mining-based image quality improving method so as to solve the problem of poor image quality caused by poor graceful behavior posture of people at present.
The purpose of the invention is realized as follows:
a data mining-based image gas quality improving method comprises the following steps:
s1: collecting body model parameters and corresponding behavior posture data of a batch of professional dancers and/or models, and uploading the body model parameters and the behavior posture data to a cloud server to serve as standard behavior posture data, wherein the body model parameters and the behavior posture data form an influence factor matrix X, the body model parameters are environment variables, and the behavior posture data are decision variables;
s2: synthesizing the daily behavior gestures of professional dancers and/or models, acquiring data samples of the behavior gestures corresponding to the users to form an index matrix Y, learning, training and checking the index matrix Y by using a BP neural network, and establishing a BP neural network model of the behavior gestures according to body model parameters of the users;
s3: predicting the behavior posture data by using the BP neural network model established in the S2 to obtain a recommended decision variable X*And will recommend the decision variable X*Sending the variable to a user terminal, and making a decision X by the user according to the recommendation*The behavior posture of the user is corrected, and the image quality of the user is improved.
Preferably, in step S1, the behavior posture data of the professional dancer and/or the model is collected by the sensor module; the behavior attitude data collected by the sensor module is converted into digital signals and uploaded to the cloud server.
Preferably, the sensor module is a ten-axis acceleration Bluetooth version sensor.
Preferably, in step S1, the body model parameters include height, weight, arm length, leg length, and circumference, and are manually entered into the cloud server.
Preferably, in step S1, the behavioral posture data includes posture data of standing, sitting and walking behaviors.
Preferably, the posture data of standing, sitting and walking respectively comprises the acceleration, the angle, the speed, the three-dimensional coordinate and the height of the back, the left and right wrists, the left and right thighs, the chest and the buttocks during the behavior.
Preferably, in step S2, a three-layer BP neural network model is constructed: setting the number of hidden layer nodes of the BP neural network model as l, setting the hidden layer node function as an S-shaped function tansig, and setting the number of output layer nodes to be consistent with the number of output variables; setting the node function of the output layer as a linear function purelin, and setting the weight value from the input layer to the hidden layer as w1With hidden layer node threshold of b1The weight from the hidden layer to the output layer is w2The output layer node threshold is b2。
Preferably, in step S2, the method for building the BP neural network model includes the following steps:
s21: weight w of initialized neural network parameters1、w2And a threshold value b1、b2;
S22: the initialized network parameters are calculated by the following formula
Wherein,representing a predicted value;
W1、W2respectively representing the weight values of the neural network parameters;
b1、b2threshold values respectively representing neural network parameters;
representing normalized input samples;
s23: calculating the actual sample output at that timeAnd the predicted valueThe total error of the system to the N training samples, the total error e criterion function is as follows:
wherein e represents an error performance indicator function;
representing the BP network output;
representing the actual output;
s24: correcting the weight and the threshold of the neural network parameter, wherein the specific formula is as follows:
wherein, w1ijη represents the learning rate;
representing a hidden layer output; x (i) represents an input sample;
wjkrepresenting the weight of the output layer and the hidden layer;
wherein, w2jkRepresenting the connection weight of the output layer and the hidden layer;
wherein,representing a hidden layer threshold;representing a hidden layer output; w is ajkTable output layer and hidden layer weights;
b2=b2+ηe
wherein i is 1,2, …, n; j ═ 1,2, …, l; k is 1,2, …, N; n is the sample size;
s25: re-estimation using updated weights and thresholds of neural network parametersS22 through S24 are repeated until the total error is less than the set point.
Preferably, in step S3, the user terminal has a gesture data interface, and the gesture data interface displays real-time behavior gesture data of the user and recommended behavior gesture data issued by the cloud server.
Preferably, the user terminal is provided with a behavior posture scoring system, and the behavior posture scoring system scores according to the closeness degree of the real-time behavior posture data of the user and the recommended behavior posture data.
Due to the adoption of the technical scheme, the optimal value of the behavior posture data is determined, so that a user can correct the posture through a recommendation scheme in daily training, and the purpose of improving the image quality score is achieved.
Drawings
FIG. 1 is a process framework diagram of the present invention;
FIG. 2 is a schematic diagram of modeling a BP neural network.
Detailed Description
Referring to fig. 1 and 2, a data mining-based image gas quality improving method includes the following steps:
s1: collecting body model parameters and corresponding behavior posture data of a batch of professional dancers and/or models, and uploading the body model parameters and the behavior posture data to a cloud server to serve as standard behavior posture data, wherein the body model parameters and the behavior posture data form an influence factor matrix X, the body model parameters are environment variables, and the behavior posture data are decision variables;
in the embodiment, behavior and posture data of a professional dancer and/or a model are collected through a sensor module, wherein the sensor module is a ten-axis acceleration Bluetooth sensor; the behavior attitude data collected by the sensor module is converted into digital signals and uploaded to the cloud server.
The body model parameters comprise height A (cm), weight B (kg), arm length C (cm), leg length D (cm) and three-dimensional E, and are manually recorded into the cloud server.
The behavioral gesture data includes gesture data of standing, sitting, and walking behaviors. The posture data of standing, sitting and walking respectively comprise the acceleration, the angle, the speed, the three-dimensional coordinate and the height of the back, the left wrist, the right wrist, the left thigh, the right thigh, the chest and the hip during the behavior. In this embodiment, the acceleration (a) measured by the sensor of the back is included1) Angle (theta)1) Velocity (v)1) Three-dimensional coordinate (x)1、y1、z1) Height (H)1) Acceleration (a) measured by sensors of the left and right wristsLeft 2、aRight 2) Angle (theta)Left 2、θRight 2) Velocity (v)Left 2、vRight 2) Three-dimensional coordinate (x)Left 2、yLeft 2、zLeft 2、xRight 2、yRight 2、zRight 2) Height (H)Left 2、HRight 2) Acceleration (a) measured by sensors of the left and right thighsLeft 3、aRight 3) Angle (theta)Left 3、θRight 3) Velocity (v)Left 3、vRight 3) Three-dimensional coordinate (x)Left 3、yLeft 3、zLeft 3、xRight 3、yRight 3、zRight 3) Height (H)Left 3、HRight 3) Acceleration (a) measured by a sensor of the breast4) Angle (theta)4) Velocity (v)4) Three-dimensional coordinate (x)4、y4、z4) Height (H)4) Acceleration measured by a sensor of the buttocks (a)5) Angle (theta)5) Velocity (v)5) Three-dimensional coordinate (x)5、y5、z5) Height (H)5)。
S2: synthesizing the daily behavior gestures of professional dancers and/or models, acquiring data samples of the behavior gestures corresponding to the users to form an index matrix Y, learning, training and checking the index matrix Y by using a BP neural network, and establishing a BP neural network model of the behavior gestures according to body model parameters of the users;
in this embodiment, a three-layer BP neural network model is constructed: setting the number of hidden layer nodes of the BP neural network model as l, hidingThe layer node function is an S-shaped function tansig, and the number of output layer nodes is consistent with the number of output variables; setting the node function of the output layer as a linear function purelin, and setting the weight value from the input layer to the hidden layer as w1With hidden layer node threshold of b1The weight from the hidden layer to the output layer is w2The output layer node threshold is b2. The method for establishing the BP neural network model comprises the following steps:
s21: weight w of initialized neural network parameters1、w2And a threshold value b1、b2;
S22: the initialized network parameters are calculated by the following formula
Wherein,representing a predicted value;
W1、W2respectively representing the weight values of the neural network parameters;
b1、b2threshold values respectively representing neural network parameters;
representing normalized input samples;
s23: calculating the actual sample output at that timeAnd the predicted valueBetweenThe total error e criterion function of the system for the total error of the N training samples is as follows:
wherein e represents an error performance indicator function;
representing the BP network output;
representing the actual output;
s24: correcting the weight and the threshold of the neural network parameter, wherein the specific formula is as follows:
wherein, w1ijη represents the learning rate;
representing a hidden layer output; x (i) represents an input sample;
wjk represents the output layer and hidden layer weights;
wherein, w2jkRepresenting the connection weight of the output layer and the hidden layer;
wherein,representing a hidden layer threshold;representing a hidden layer output; w is ajkTable output layer and hidden layer weights;
b2=b2+ηe
wherein i is 1,2, …, n; j ═ 1,2, …, l; k is 1,2, …, N; n is the sample size;
s25: re-estimation using updated weights and thresholds of neural network parametersS22 through S24 are repeated until the total error is less than the set point.
S3: predicting the behavior posture data by using the BP neural network model established in the S2 to obtain a recommended decision variable X*And will recommend the decision variable X*Sending the variable to a user terminal, and making a decision X by the user according to the recommendation*The behavior posture of the user is corrected, and the image quality of the user is improved.
The user terminal is provided with a posture data interface which displays real-time behavior posture data of a user and recommended behavior posture data issued by the cloud server. The user terminal can be a pc terminal, a mobile phone terminal and the like. Real-time behavior posture data of a user are acquired by wearing a corresponding sensor, and a three-dimensional motion perception picture is displayed on a posture data interface at the same time.
The user terminal is provided with a behavior posture scoring system, each scoring standard of the posture scoring system is provided with corresponding behavior posture data, and the behavior posture scoring system scores according to the closeness degree of the real-time behavior posture data of the user and the recommended behavior posture data. Specific scoring criteria are shown in table 1:
TABLE 1 Scoring standards
Finally, it is noted that the above-mentioned preferred embodiments illustrate rather than limit the invention, and that, although the invention has been described in detail with reference to the above-mentioned preferred embodiments, it will be understood by those skilled in the art that various changes in form and detail may be made therein without departing from the scope of the invention as defined by the appended claims.
Claims (10)
1. A data mining-based image gas quality improving method is characterized by comprising the following steps:
s1: collecting body model parameters and corresponding behavior posture data of a batch of professional dancers and/or models, and uploading the body model parameters and the behavior posture data to a cloud server to serve as standard behavior posture data, wherein the body model parameters and the behavior posture data form an influence factor matrix X, the body model parameters are environment variables, and the behavior posture data are decision variables;
s2: synthesizing the daily behavior gestures of professional dancers and/or models, acquiring data samples of the behavior gestures corresponding to the users to form an index matrix Y, learning, training and checking the index matrix Y by using a BP neural network, and establishing a BP neural network model of the behavior gestures according to body model parameters of the users;
s3: predicting the behavior posture data by using the BP neural network model established in the S2 to obtain a recommended decision variable X*And will recommend the decision variable X*Sending the variable to a user terminal, and making a decision X by the user according to the recommendation*The behavior posture of the user is corrected, and the image quality of the user is improved.
2. The image quality improving method based on data mining of claim 1, wherein in step S1, behavior and posture data of professional dancers and/or models are collected through sensor modules; the behavior attitude data collected by the sensor module is converted into digital signals and uploaded to the cloud server.
3. The image quality improving method based on data mining of claim 2, wherein the sensor module is a ten-axis acceleration Bluetooth version sensor.
4. The image quality improving method based on data mining of claim 1, wherein in step S1, the body model parameters include height, weight, arm length, leg length, and three-dimensional circumference, and are manually entered into the cloud server.
5. The image quality improving method based on data mining of claim 1, wherein in step S1, the behavior posture data includes posture data of standing, sitting and walking behaviors.
6. The data mining-based image quality improving method according to claim 5, wherein the posture data of standing, sitting and walking respectively comprise acceleration, angle, speed, three-dimensional coordinates and height of back, left and right wrists, left and right thighs, chest and buttocks during behavior.
7. The image quality improving method based on data mining of claim 1, wherein in step S2, a three-layer BP neural network model is constructed: setting the number of hidden layer nodes of the BP neural network model as l, setting the hidden layer node function as an S-shaped function tansig, and setting the number of output layer nodes to be consistent with the number of output variables; setting the node function of the output layer as a linear function purelin, and setting the weight value from the input layer to the hidden layer as w1With hidden layer node threshold of b1The weight from the hidden layer to the output layer is w2The output layer node threshold is b2。
8. The image quality improving method based on data mining of claim 7, wherein in step S2, the method for building the BP neural network model comprises the following steps:
s21: weight w of initialized neural network parameters1、w2And a threshold value b1、b2;
S22: the initialized network parameters are calculated by the following formula
Wherein,representing a predicted value;
w1、w2respectively representing the weight values of the neural network parameters;
b1、b2threshold values respectively representing neural network parameters;
representing normalized input samples;
s23: calculating the actual sample output at that timeAnd the predicted valueThe total error of the system to the N training samples, the total error e criterion function is as follows:
wherein e represents an error performance indicator function;
representing the BP network output;
representing the actual output;
s24: correcting the weight and the threshold of the neural network parameter, wherein the specific formula is as follows:
wherein, w1ijη represents the learning rate;
representing a hidden layer output; x (i) represents an input sample;
wjkrepresenting the weight of the output layer and the hidden layer;
wherein, w2jkRepresenting the connection weight of the output layer and the hidden layer;
wherein,representing a hidden layer threshold;representing a hidden layer output; w is ajkTable output layer and hidden layer weights;
b2=b2+ηe
wherein, i is 1,2, …, n, n is the number of nodes of the input layer; j is 1,2, …, l, l is the number of hidden layer nodes; k is 1,2, …, N is the number of nodes of the output layer;
s25: re-estimation using updated weights and thresholds of neural network parametersS22 through S24 are repeated until the total error is less than the set point.
9. The image quality improving method based on data mining of claim 1, wherein in step S3, the user terminal has a gesture data interface, and the gesture data interface displays real-time behavior gesture data of the user and recommended behavior gesture data issued by the cloud server.
10. The image quality improving method based on data mining of claim 9, wherein the user terminal has a behavior gesture scoring system, and the behavior gesture scoring system scores the user's real-time behavior gesture data and the recommended behavior gesture data according to their closeness.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811017859.8A CN109284695A (en) | 2018-09-03 | 2018-09-03 | A kind of image makings method for improving based on data mining |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811017859.8A CN109284695A (en) | 2018-09-03 | 2018-09-03 | A kind of image makings method for improving based on data mining |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109284695A true CN109284695A (en) | 2019-01-29 |
Family
ID=65183970
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811017859.8A Withdrawn CN109284695A (en) | 2018-09-03 | 2018-09-03 | A kind of image makings method for improving based on data mining |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109284695A (en) |
Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5781648A (en) * | 1995-04-07 | 1998-07-14 | California Institute Of Technology | Pulse domain neuromorphic integrated circuit for computing motion |
US7734387B1 (en) * | 2006-03-31 | 2010-06-08 | Rockwell Collins, Inc. | Motion planner for unmanned ground vehicles traversing at high speeds in partially known environments |
CN105446362A (en) * | 2015-12-07 | 2016-03-30 | 陆宁远 | Posture detection adjusting device and method based on assistance of computer science |
CN106119458A (en) * | 2016-06-21 | 2016-11-16 | 重庆科技学院 | Converter steelmaking process cost control method based on BP neutral net and system |
-
2018
- 2018-09-03 CN CN201811017859.8A patent/CN109284695A/en not_active Withdrawn
Patent Citations (4)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US5781648A (en) * | 1995-04-07 | 1998-07-14 | California Institute Of Technology | Pulse domain neuromorphic integrated circuit for computing motion |
US7734387B1 (en) * | 2006-03-31 | 2010-06-08 | Rockwell Collins, Inc. | Motion planner for unmanned ground vehicles traversing at high speeds in partially known environments |
CN105446362A (en) * | 2015-12-07 | 2016-03-30 | 陆宁远 | Posture detection adjusting device and method based on assistance of computer science |
CN106119458A (en) * | 2016-06-21 | 2016-11-16 | 重庆科技学院 | Converter steelmaking process cost control method based on BP neutral net and system |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN109102857B (en) | Intelligent limb rehabilitation training system and method | |
CN104033988B (en) | Air conditioner control system and control method of air conditioner control system | |
CN111158494B (en) | Posture correction device and posture correction method | |
CN106650687A (en) | Posture correction method based on depth information and skeleton information | |
CN107340859A (en) | The multi-modal exchange method and system of multi-modal virtual robot | |
CN107754225A (en) | A kind of intelligent body-building coaching system | |
CN110605724A (en) | Intelligence endowment robot that accompanies | |
CN107835324A (en) | A kind of back light brightness regulating method and mobile terminal | |
CN109117952B (en) | Robot emotion cognition method based on deep learning | |
CN109769213B (en) | Method for recording user behavior track, mobile terminal and computer storage medium | |
CN107018330A (en) | A kind of guidance method and device of taking pictures in real time | |
CN109248413A (en) | It is a kind of that medicine ball posture correcting method is thrown based on BP neural network and genetic algorithm | |
CN106472412B (en) | pet feeding method and system based on internet of things | |
CN108805058A (en) | Target object changes gesture recognition method, device and computer equipment | |
CN111917999A (en) | Video processing method, mobile terminal and readable storage medium | |
CN111539245A (en) | CPR (CPR) technology training evaluation method based on virtual environment | |
CN113034322A (en) | Internet-based online education supervision system and method | |
CN103729871A (en) | Cloud animation production method | |
CN109147891A (en) | A kind of image makings method for improving based on BP neural network and genetic algorithm | |
CN109243562A (en) | A kind of image makings method for improving based on Elman artificial neural network and genetic algorithms | |
CN108426349B (en) | Air conditioner personalized health management method based on complex network and image recognition | |
CN109284695A (en) | A kind of image makings method for improving based on data mining | |
CN116362109B (en) | Intelligent unmanned system and method based on digital twinning | |
CN110890141A (en) | Intelligent fitness planning system and method based on big data | |
CN116129467A (en) | Method for identifying gesture and behavior of transformer operation and maintenance personnel and gesture of tool |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190129 |
|
WW01 | Invention patent application withdrawn after publication |