CN109730700A - A kind of user emotion based reminding method - Google Patents
A kind of user emotion based reminding method Download PDFInfo
- Publication number
- CN109730700A CN109730700A CN201811648330.6A CN201811648330A CN109730700A CN 109730700 A CN109730700 A CN 109730700A CN 201811648330 A CN201811648330 A CN 201811648330A CN 109730700 A CN109730700 A CN 109730700A
- Authority
- CN
- China
- Prior art keywords
- user
- sequence
- skin conductance
- conductance signal
- eigenvalue
- 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- Withdrawn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
Landscapes
- Measurement Of The Respiration, Hearing Ability, Form, And Blood Characteristics Of Living Organisms (AREA)
Abstract
The present invention provides a kind of user emotion based reminding methods, sample including interval preset time to the physiological parameter of user to be identified and obtain heart rate variability rate sequence, skin conductance signal sequence;Characteristic parameter is extracted from the heart rate variability rate sequence, skin conductance signal sequence, the characteristic parameter includes the First Eigenvalue based on heart rate variability rate, Second Eigenvalue and third feature value based on skin conductance signal;The characteristic parameter is inputted into pre-set classifier in order to which classifier output is to the recognition result of user emotion state;Judge whether the recognition result is negative emotions;If so, call user's attention mood regulation.The present invention can slightly judge the psychological condition of user over a period to come according to the monitored results to user's physiological parameter, so that mood regulation prompting be generated for user, the mood of oneself is preferably managed convenient for user, keep physically and mentally healthy.
Description
Technical field
The present invention relates to data processing field more particularly to a kind of user emotion based reminding methods.
Background technique
As intellectual wearable device popularization degree is higher and higher, research has been had become for the data processing of physiological parameter
Hot spot, the data processing based on physiological parameter can be in order to grasp the physical condition and psychological condition of user, to be user
The various services based on physical condition and psychological condition are provided, for example, can play if user emotion is bad for user cheerful and light-hearted
Song adjust body and mind, Intelligent dialogue can also be carried out according to user's body state and psychological condition and user, therefore, physiology ginseng
Several data processings has higher researching value;
But the relevant technologies for the data processing of physiological parameter and immature in the prior art, it is based on to limit
User's body state and psychological condition provide the research and development of the technical solution of related service.
Summary of the invention
In order to solve the above-mentioned technical problem, the invention proposes a kind of user emotion based reminding methods.The present invention be specifically with
What following technical solution was realized:
A kind of user emotion based reminding method, comprising:
Interval preset time samples the physiological parameter of user to be identified and obtains heart rate variability rate sequence, skin pricktest
Lead signal sequence;
Characteristic parameter is extracted from the heart rate variability rate sequence, skin conductance signal sequence, the characteristic parameter includes
Based on the First Eigenvalue of heart rate variability rate, Second Eigenvalue and third feature value based on skin conductance signal;
The characteristic parameter is inputted into pre-set classifier in order to which the classifier is exported to user emotion state
Recognition result;
Judge whether the recognition result is negative emotions;
If so, call user's attention mood regulation.
Further, the recognition result is binaryzation as a result, including negative emotions and non-negative emotions, if user produces
Green coke is considered, depressive emotion will make the recognition result of emotional state for negative emotions.
It further, further include that record recognition result mentions if continuous recognition result three times is negative emotions for user
For adjusting mood suggestion;The suggestion be that play preset can be music that user brings pleasant mood, is that user's recommendation is attached
Close cuisines, the preferable film of user's evaluation, books and public place of entertainment.
Further, the acquisition methods of the First Eigenvalue of heart rate variability rate include:
It is obtained according to heart rate variability rate sequence to reproducing sequence;
Target sequence is obtained to the phase space reconfiguration for carrying out m dimension to reproducing sequence;
The relative distance calculated between target sequence adjacent element obtains target range sequence;
The First Eigenvalue of the heart rate variability rate is calculated according to preset formula.
Further, the acquisition methods of the Second Eigenvalue of skin conductance signal include:
It is obtained according to skin conductance signal sequence to convolution sequence;
Convolution sequence is obtained to convolution sequence and default window function progress convolution by described;
Second Eigenvalue is obtained according to the convolution sequence.
Further, the acquisition methods of the third feature value of skin conductance signal include:
Obtain skin conductance signal { elci};
According to formulaCalculate skin conductance signal { elciThird feature value;For parameter is concentrated, N is skin conductance signal { elciLength, n be concentrated parameter first inside ginseng
Number, p are the second inner parameter that parameter is concentrated.
A kind of user emotion based reminding method is set forth in detail in the embodiment of the present invention, can be according to the prison to user's physiological parameter
Control result slightly judges the psychological condition of user over a period to come, so that mood regulation prompting is generated for user, more convenient for user
The mood of good management oneself, keeps physically and mentally healthy.
Detailed description of the invention
In order to more clearly explain the embodiment of the invention or the technical proposal in the existing technology, to embodiment or will show below
There is attached drawing needed in technical description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
Some embodiments of invention for those of ordinary skill in the art without creative efforts, can be with
Other attached drawings are obtained according to these attached drawings.
Fig. 1 is a kind of user emotion based reminding method flow chart provided in an embodiment of the present invention;
Fig. 2 is the acquisition methods flow chart of the First Eigenvalue of heart rate variability rate provided in an embodiment of the present invention;
Fig. 3 is the acquisition methods flow chart of the Second Eigenvalue provided in an embodiment of the present invention based on skin conductance signal;
Fig. 4 is the acquisition methods flow chart of the third feature value provided in an embodiment of the present invention based on skin conductance signal;
Fig. 5 is the training process flow chart of classifier provided in an embodiment of the present invention;
Fig. 6 is the training method flow chart of sub-classifier provided in an embodiment of the present invention.
Specific embodiment
In order to enable those skilled in the art to better understand the solution of the present invention, below in conjunction in the embodiment of the present invention
Attached drawing, technical scheme in the embodiment of the invention is clearly and completely described, it is clear that described embodiment is only
The embodiment of a part of the invention, instead of all the embodiments.Based on the embodiments of the present invention, ordinary skill people
The model that the present invention protects all should belong in member's every other embodiment obtained without making creative work
It encloses.
It should be noted that description and claims of this specification and term " first " in above-mentioned attached drawing, "
Two " etc. be to be used to distinguish similar objects, without being used to describe a particular order or precedence order.It should be understood that using in this way
Data be interchangeable under appropriate circumstances, so as to the embodiment of the present invention described herein can in addition to illustrating herein or
Sequence other than those of description is implemented.In addition, term " includes " and " having " and their any deformation, it is intended that cover
Cover it is non-exclusive include, for example, the process, method, system, product or equipment for containing a series of steps or units are not necessarily limited to
Step or unit those of is clearly listed, but may include be not clearly listed or for these process, methods, product
Or other step or units that equipment is intrinsic.
The present invention provides a kind of user emotion based reminding method, as shown in Figure 1, which comprises
S101. interval preset time the physiological parameter of user to be identified is sampled and is obtained heart rate variability rate sequence,
Skin conductance signal sequence.
S102. characteristic parameter, the characteristic parameter are extracted from the heart rate variability rate sequence, skin conductance signal sequence
Including the First Eigenvalue based on heart rate variability rate, Second Eigenvalue and third feature value based on skin conductance signal.
S103. the characteristic parameter is inputted into pre-set classifier in order to which the classifier is exported to user emotion
The recognition result of state.
Specifically, the recognition result can be binaryzation as a result, specially negative emotions and non-negative emotions, if with
It is negative emotions that family, which generates the recognition result that the moods such as anxiety, depression all may be emotional state,.
S104. judge whether the recognition result is negative emotions.
S105. if so, call user's attention mood regulation.
Further, further includes:
Recognition result is recorded, if continuous recognition result three times is negative emotions, is provided for user and adjusts mood suggestion.
Specifically, the suggestion can be that play preset can be music that user brings pleasant mood, push away for user
Recommend neighbouring cuisines and the preferable film of user's evaluation, books and public place of entertainment.
In the implementation process of the embodiment of the present invention, inventor has studied all kinds of physiological emotion signals for anxiety and depression
The direction action of mood has obtained the First Eigenvalue based on heart rate variability rate based on result of study, is based on skin conductance signal
Second Eigenvalue and third feature value.Based on the First Eigenvalue of heart rate variability rate, second based on skin conductance signal is special
Value indicative and third feature value have following three main features:
(1) directive property is clear, can obtain the judgement of more specific anxiety and depression by carrying out data processing to it
As a result, and False Rate it is relatively low;
(2) heart rate variability rate and skin conductance signal relatively easily acquire, and therefore, can pass through common wearable device
It is acquired without bringing burden for user;
(3) characteristic value being further processed based on heart rate variability rate and skin conductance signal is had definitely
Direction action, the specific algorithm of characteristic value is provided by the embodiment of the present invention to be specifically defined.
Specifically, the embodiment of the present invention further discloses the acquisition methods of the First Eigenvalue of heart rate variability rate, such as Fig. 2 institute
Show, comprising:
S1. according to heart rate variability rate sequence { xiObtain to reproducing sequence
Wherein,Wherein N ' is the heart rate variability sequence { xiTotal length, it is seen then that
{yi τFor length beSequence, τ is segmentation parameter, can be set based on experience value.
S2. to described to reproducing sequenceThe phase space reconfiguration for carrying out m dimension obtains target sequence { zj m}。
Wherein, zj m={ yj,yj+1..., yj+m-1, wherein m is fixed value, and value is 2 in the embodiment of the present invention.
S3. target sequence { z is calculatedj mRelative distance between adjacent element obtains target range sequence { nj m}。
S4. the First Eigenvalue of the heart rate variability rate is calculated according to preset formula.
Specifically, the formula isWhereinWherein δ is { xi0.2 times of standard deviation,Formula is in the specific implementation processFor ideal value, but can be carried out in the processor in practical application
It is similar to approach.
Specifically, the embodiment of the present invention further discloses the acquisition methods of the Second Eigenvalue based on skin conductance signal,
As shown in Figure 3, comprising:
S10. according to skin conductance signal sequence { elciObtain to convolution sequence { elc*i}。
Specifically,
It S20. will be described to convolution sequence { elc*iWith default window function carry out convolution obtain convolution sequence { * dsti}。
Specifically, the window function is preferably Hanning window.Hanning window is also known as raised cosine window, when can be regarded as 3 rectangles
Between window the sum of frequency spectrum.
S30. Second Eigenvalue is obtained according to the convolution sequence.
Specifically, the acquisition of Second Eigenvalue is according to formula
Specifically, the embodiment of the present invention further discloses the acquisition methods of the third feature value based on skin conductance signal,
As shown in Figure 4, comprising:
S100. skin conductance signal { elc is obtainedi}。
S200. according to formulaCalculate skin conductance signal { elciThird it is special
Value indicative.
Specifically,It for parameter is concentrated, is specifically defined the present embodiment and provides and explain in detail, N is skin
Skin conductance signal { elciLength, n is the first inner parameter that parameter is concentrated, and can be set, typically larger than 0 and small
In 40, the more highly enriched effect of value is better, but calculating speed is also slower;P is the second inner parameter that parameter is concentrated, and is used for
Indicate that emphasis extracts the part of information in the skin conductance signal { elciIn position, emphasis of the embodiment of the present invention extract in
Between signal information, so value be 0.5.
SpecificallyWherein, Λn(i-1,
P, N-1) it is concentration core, core Λ is concentratedn(i-1, p, N-1) is defined asIts
In2F1() is hypergeometric function, and Μ (p, n, N) is and the related constant of p, n, N, value can be
The First Eigenvalue based on heart rate variability rate is being obtained, Second Eigenvalue and third based on skin conductance signal are special
On the basis of value indicative, as long as being inputted pre-set classifier can be obtained the recognition result of mood.The classifier can
To be obtained by a large amount of training sample training, specifically, the training process of the classifier may include following step, such as
Shown in Fig. 5, comprising:
S201. first sample set and the second sample set are obtained.
Specifically, first sample set is sample set there are negative emotions in the embodiment of the present invention, and the second sample set is not
There are the sample sets of negative emotions.Specifically, each element includes four items in first sample set and the second sample set, respectively
For the First Eigenvalue based on heart rate variability rate, Second Eigenvalue based on skin conductance signal, based on skin conductance signal
Third feature value and Emotion identification result.
If each sample is used (xi, yi) indicate, then the feature for classification in each sample is xiUnified mark
Know: the First Eigenvalue based on heart rate variability rate, Second Eigenvalue based on skin conductance signal, based on skin conductance signal
Third feature value;Correspondingly, its classification results belonged to uses yiIt indicates: if it is negative emotions, then Emotion identification result quilt
Labeled as 1, otherwise, it is marked as 0.
S202. training process control parameter and loop initialization control parameter and classifier are obtained.
The training process control parameter includes the maximum False Rate F of training resulttarget, the maximum of each straton classifier
False Rate fmax, the minimum detection rate d of each straton classifiermin。
Specifically, False Rate is the sample size misjudged and the ratio for participating in the sample size judged in the embodiment of the present invention
Value, verification and measurement ratio are the ratio of the sample size correctly judged and the sample size for participating in judgement.
The loop control parameter includes loop control variable, the False Rate and detection of sub-classifier in previous cycle result
Rate is specifically initialized according to the following formula respectively: loop control variable i=0, sub-classifier in previous cycle result
False Rate Fi=1 and verification and measurement ratio Di=1.
Classifier is initialized as sky.
S203. execute circuit training process: loop control variable increases 1 certainly, i.e. i=i+1;From the first sample set and
Respectively there is the half data of randomly selecting put back to obtain current training sample set in two sample sets;According to the current training sample set
Training meets i-th of sub-classifier C of preset requirementi。
It it is based on current first sample set and the second sample set in cyclic process each time puts back to extraction at random and work as
Preceding training sample, to promote the randomness of sub-classifier training to greatest extent.
S204. by i-th of sub-classifier CiIt cascades with current classifier to update current classifier;It updates currently
The False Rate F of classifieri+1=Fi*fiWith verification and measurement ratio Di+1=Di*di, wherein fiAnd diRespectively i-th of sub-classifier CiMistake
Sentence rate and verification and measurement ratio.
S205. judge whether the False Rate of current classifier is greater than maximum False Rate.
S206. if so, emptying the second sample set;Using current classifier for dividing for first sample set
Class, and the second sample set is added in the sample of classification error, and repeat step S203.
Null clear operation has been carried out to the second sample set first, and has been classified based on current cascade classifier, and will
The sample of misjudgement is included into the second sample set, to improve in training process for misjudgement sample and the sample for belonging to negative emotions
Attention rate so that the sample misjudged plays a role in training process next time, to improve trained precision, and
And haved the function that the sample for giving much attention to belong to negative emotions in the training process, so that side, which improves, belongs to negative feelings
The significance level of the sample of thread.
S207. if it is not, then process terminates, and current classifier is exported.
Specifically, the training method of sub-classifier is furthermore presented in the embodiment of the present invention, as shown in fig. 6, including.
S301. initializing current training sample concentrates the weight, training threshold value T and current training sample of each sample to concentrate
The adjustment number t of the weight distribution of sample.
It enables, current training sample concentrates the weight of sample to be distributed as SD0=(ω01,...ω0i...,ω0N),
Wherein N is the total sample number that current training sample is concentrated.
S302. using the current training sample with weight, according to training threshold value T training M linear meta classifier Gm
(x)。
Specifically, the linear meta classifier can be specially support vector machines (SVM), and specific training method belongs to existing
There is technology, the embodiment of the present invention does not repeat them here.The number M of linear basic classification device can be preset.
S303. each linear meta classifier G is verified using current training samplem(x) to obtain its False Rate em。
Specifically, False RateWherein t is the weight point that current training sample concentrates sample
The adjustment number of cloth, ωtiThe weight distribution of sample, I (G are concentrated for current training samplem(xi≠yi)) indicate that number is i's
Sample uses meta classifier Gm(x) there is erroneous judgement, then I (Gm(xi≠yi)) value be 1.
S304. doubtful sub-classifier is obtained according to False Rate
S305. the doubtful sub-classifier is verified to obtain its False Rate f (G (x)) and detection using current training sample
Rate d (G (x)).
If S306. False Rate f (G (x))≤fmaxAnd verification and measurement ratio d (G (x)) >=dmin, then determine the doubtful subclassification
Device reaches preset standard, terminates process.
Further, also as sub-classifier and step S204 is executed, specifically there are also f in step S204i=f
(G(x)),di=d (G (x)).
S306. otherwise, the weight that current training sample concentrates each sample is adjusted;Adjusting training threshold value T;Enable current training
The adjustment number of the weight distribution of sample increases 1 certainly in sample set;Return to step 302.
Specifically, the current training sample of adjustment concentrates the weight of each sample specifically: increases by the doubtful son
The weight of the sample of classifier mistake classification reduces the weight for the sample correctly classified by the doubtful sub-classifier, specific to adjust
The section process embodiment of the present invention without limitation, uses the prior art.
Specifically, training threshold value T can be suitably reduced in the iteration of next round, and specifically reducing method can be with people
Work is rule of thumb set, and the embodiment of the present invention does not limit its specific embodiment.
A kind of user emotion based reminding method is set forth in detail in the embodiment of the present invention, can be according to the prison to user's physiological parameter
Control result slightly judges the psychological condition of user over a period to come, so that mood regulation prompting is generated for user, more convenient for user
The mood of good management oneself, keeps physically and mentally healthy.
It should be understood that referenced herein " multiple " refer to two or more."and/or", description association
The incidence relation of object indicates may exist three kinds of relationships, for example, A and/or B, can indicate: individualism A exists simultaneously A
And B, individualism B these three situations.Character "/" typicallys represent the relationship that forward-backward correlation object is a kind of "or".
The serial number of the above embodiments of the invention is only for description, does not represent the advantages or disadvantages of the embodiments.
Those of ordinary skill in the art will appreciate that realizing that all or part of the steps of above-described embodiment can pass through hardware
It completes, relevant hardware can also be instructed to complete by program, the program can store in a kind of computer-readable
In storage medium, storage medium mentioned above can be read-only memory, disk or CD etc..
The foregoing is merely presently preferred embodiments of the present invention, is not intended to limit the invention, it is all in spirit of the invention and
Within principle, any modification, equivalent replacement, improvement and so on be should all be included in the protection scope of the present invention.
Claims (6)
1. a kind of user emotion based reminding method characterized by comprising
Interval preset time samples to the physiological parameter of user to be identified and obtains heart rate variability rate sequence, skin conductivity letter
Number sequence;
Characteristic parameter is extracted from the heart rate variability rate sequence, skin conductance signal sequence, the characteristic parameter includes being based on
The First Eigenvalue of heart rate variability rate, Second Eigenvalue and third feature value based on skin conductance signal;
The characteristic parameter is inputted into pre-set classifier in order to which the classifier exports the knowledge to user emotion state
Other result;
Judge whether the recognition result is negative emotions;
If so, call user's attention mood regulation.
2. according to the method described in claim 1, it is characterized by:
The recognition result is binaryzation as a result, including negative emotions and non-negative emotions, if user generates anxiety, depressed feelings
The recognition result for making emotional state is negative emotions by thread.
3. according to the method described in claim 2, it is characterized by:
Further include record recognition result, if continuous recognition result three times is negative emotions, provides adjusting mood for user and build
View;The suggestion be that play preset can be music that user brings pleasant mood, recommends neighbouring cuisines, user for user
Evaluate preferable film, books and public place of entertainment.
4. according to the method described in claim 2, it is characterized by:
The acquisition methods of the First Eigenvalue of heart rate variability rate include:
It is obtained according to heart rate variability rate sequence to reproducing sequence;
Target sequence is obtained to the phase space reconfiguration for carrying out m dimension to reproducing sequence;
The relative distance calculated between target sequence adjacent element obtains target range sequence;
The First Eigenvalue of the heart rate variability rate is calculated according to preset formula.
5. according to the method described in claim 2, it is characterized by:
The acquisition methods of the Second Eigenvalue of skin conductance signal include:
It is obtained according to skin conductance signal sequence to convolution sequence;
Convolution sequence is obtained to convolution sequence and default window function progress convolution by described;
Second Eigenvalue is obtained according to the convolution sequence.
6. according to the method described in claim 2, it is characterized by:
The acquisition methods of the third feature value of skin conductance signal include:
Obtain skin conductance signal { elci};
According to formulaCalculate skin conductance signal { elciThird feature value;For parameter is concentrated, N is skin conductance signal { elciLength, n be concentrated parameter first inside ginseng
Number, p are the second inner parameter that parameter is concentrated.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811648330.6A CN109730700A (en) | 2018-12-30 | 2018-12-30 | A kind of user emotion based reminding method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201811648330.6A CN109730700A (en) | 2018-12-30 | 2018-12-30 | A kind of user emotion based reminding method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN109730700A true CN109730700A (en) | 2019-05-10 |
Family
ID=66362912
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201811648330.6A Withdrawn CN109730700A (en) | 2018-12-30 | 2018-12-30 | A kind of user emotion based reminding method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN109730700A (en) |
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111248928A (en) * | 2020-01-20 | 2020-06-09 | 北京津发科技股份有限公司 | Pressure identification method and device |
CN114869284A (en) * | 2022-05-11 | 2022-08-09 | 吉林大学 | Monitoring system for driving emotion state and driving posture of driver |
CN115715680A (en) * | 2022-12-01 | 2023-02-28 | 杭州市第七人民医院 | Anxiety discrimination method and device based on connective tissue potential |
-
2018
- 2018-12-30 CN CN201811648330.6A patent/CN109730700A/en not_active Withdrawn
Cited By (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN111248928A (en) * | 2020-01-20 | 2020-06-09 | 北京津发科技股份有限公司 | Pressure identification method and device |
CN114869284A (en) * | 2022-05-11 | 2022-08-09 | 吉林大学 | Monitoring system for driving emotion state and driving posture of driver |
CN115715680A (en) * | 2022-12-01 | 2023-02-28 | 杭州市第七人民医院 | Anxiety discrimination method and device based on connective tissue potential |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Wang et al. | The acoustic emotion Gaussians model for emotion-based music annotation and retrieval | |
West et al. | Features and classifiers for the automatic classification of musical audio signals. | |
Zheng et al. | Student’s t-hidden Markov model for unsupervised learning using localized feature selection | |
Lu et al. | Automatic mood detection and tracking of music audio signals | |
Zhang et al. | Using multi-label classification for acoustic pattern detection and assisting bird species surveys | |
Nalini et al. | Music emotion recognition: The combined evidence of MFCC and residual phase | |
CN109730700A (en) | A kind of user emotion based reminding method | |
Babaee et al. | An overview of audio event detection methods from feature extraction to classification | |
Hsiao et al. | Methodology for stage lighting control based on music emotions | |
Nathan et al. | EMOSIC—An emotion based music player for Android | |
Ramanathan et al. | An intelligent music player based on emotion recognition | |
Krebs et al. | Inferring metrical structure in music using particle filters | |
CN108614987A (en) | The method, apparatus and robot of data processing | |
Wang et al. | Personalized music emotion recognition via model adaptation | |
Dang et al. | Dynamic multi-rater gaussian mixture regression incorporating temporal dependencies of emotion uncertainty using kalman filters | |
CN111782863A (en) | Audio segmentation method and device, storage medium and electronic equipment | |
Iqbal et al. | Stacked convolutional neural networks for general-purpose audio tagging | |
Somervuo | Time–frequency warping of spectrograms applied to bird sound analyses | |
Guo et al. | Continuous human action recognition in real time | |
López-García et al. | A Proposal to Compare the Similarity Between Musical Products. One More Step for Automated Plagiarism Detection? | |
Koutini et al. | Learning general audio representations with large-scale training of patchout audio transformers | |
CN109730665A (en) | A kind of physiological data processing method | |
CN110070891B (en) | Song identification method and device and storage medium | |
Haque et al. | An enhanced fuzzy c-means algorithm for audio segmentation and classification | |
KR101520572B1 (en) | Method and apparatus for multiple meaning classification related music |
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 | ||
WW01 | Invention patent application withdrawn after publication |
Application publication date: 20190510 |