CN108537261A - A kind of composition evaluating method based on brain wave - Google Patents
A kind of composition evaluating method based on brain wave Download PDFInfo
- Publication number
- CN108537261A CN108537261A CN201810267782.3A CN201810267782A CN108537261A CN 108537261 A CN108537261 A CN 108537261A CN 201810267782 A CN201810267782 A CN 201810267782A CN 108537261 A CN108537261 A CN 108537261A
- Authority
- CN
- China
- Prior art keywords
- feature
- composition
- brain wave
- language
- signal
- 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
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/217—Validation; Performance evaluation; Active pattern learning techniques
- G06F18/2193—Validation; Performance evaluation; Active pattern learning techniques based on specific statistical tests
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/21—Design or setup of recognition systems or techniques; Extraction of features in feature space; Blind source separation
- G06F18/214—Generating training patterns; Bootstrap methods, e.g. bagging or boosting
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F3/00—Input arrangements for transferring data to be processed into a form capable of being handled by the computer; Output arrangements for transferring data from processing unit to output unit, e.g. interface arrangements
- G06F3/01—Input arrangements or combined input and output arrangements for interaction between user and computer
- G06F3/011—Arrangements for interaction with the human body, e.g. for user immersion in virtual reality
- G06F3/015—Input arrangements based on nervous system activity detection, e.g. brain waves [EEG] detection, electromyograms [EMG] detection, electrodermal response detection
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Bioinformatics & Computational Biology (AREA)
- Evolutionary Biology (AREA)
- Evolutionary Computation (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Biomedical Technology (AREA)
- Dermatology (AREA)
- General Health & Medical Sciences (AREA)
- Neurology (AREA)
- Neurosurgery (AREA)
- Human Computer Interaction (AREA)
- Measurement And Recording Of Electrical Phenomena And Electrical Characteristics Of The Living Body (AREA)
Abstract
The invention discloses a kind of composition evaluating method based on brain wave.It includes training stage and evaluation and test stage, and the training stage refers to：With eeg signal, trains ordered structure feature, language expression difficulty feature, language to express multifarious Feature Selection Model using depth learning technology, feature is extracted according to Feature Selection Model, final training obtains composition scoring model；The evaluation and test stage refers to：Brain wave sensor obtains eeg signal, and extraction ordered structure feature, language expression difficulty feature, language express multifarious feature, composition evaluation and test carried out using composition scoring model.The beneficial effects of the invention are as follows：Brain wave detection, signal processing technology and machine learning method are run, the composition to learner is realized and carries out accurate, automatically evaluation and test, can quickly improve composition Learning efficiency.
Description
Technical field
The present invention relates to machine learning correlative technology fields, refer in particular to a kind of composition evaluating method based on brain wave.
Background technology
As the improvement of people's living standards, people grow to even greater heights for the enthusiasm of foreign language learning.How effectively fast research is
The automatic judgment composition of fast ground has great significance, and can not only significantly decrease the workload of composition teacher, and can carry
The efficiency of height composition study.Currently, the mainly artificial evaluation and test of composition evaluation and test.Artificial evaluation and test needs special teacher, needs simultaneously
It is artificial repeatedly to read to provide the evaluation of profession, due to the subjective will of people, different teachers' marking be also possible to it is different, in this way
The study of student is caused to perplex.With the development of modern science and technology, the development of brain wave technology enters fast traffic lane, new
Field is using more and more.
Invention content
The present invention is in order to overcome the above deficiencies in the prior art, to provide one kind and can quickly improve and make literature
Practise the composition evaluating method based on brain wave of efficiency.
To achieve the goals above, the present invention uses following technical scheme：
A kind of composition evaluating method based on brain wave, including training stage and evaluation and test stage, the training stage refer to
Be：With eeg signal, ordered structure feature, language expression difficulty feature, language are trained using deep learning technology
Multifarious Feature Selection Model is expressed, feature is extracted according to Feature Selection Model, final training obtains composition scoring model；Institute
The evaluation and test stage stated refers to：Brain wave sensor obtains eeg signal, and extraction ordered structure feature, language expression difficulty are special
Sign, language express multifarious feature, and composition evaluation and test is carried out using composition scoring model.
The present invention proposes composition method for automatically evaluating, by acquiring the eeg signal of user, passes through deep learning
Algorithm extraction expresses multifarious feature in relation to the ordered structure feature, language expression difficulty feature, language write a composition, and is beaten in composition
It gives a mark on sub-model, obtains final composition evaluation and test score.The present invention runs brain wave detection, signal processing technology and machine
Device learning method realizes the composition to learner and carries out accurate, automatically evaluation and test, can quickly improve composition Learning efficiency.
Preferably, the training stage, steps are as follows：
(1) data collection and mark establish eeg signal language material, composition corpus and mark file；Brain wave senses
Device detects human brain, will collect brain wave original signal every time and be converted to brain wave digital signal；Composition file is recorded simultaneously,
Manually composition file is handled, corresponding ordered structure feature is marked to corresponding eeg signal file, language expresses difficulty
Feature, language express multifarious artificial marking file；Setting ordered structure feature is divided into five grades, and it is special that language expresses difficulty
Sign is divided into five grades, and language expression diversity is divided into five grades, wherein the corresponding numerical value of five grades is 0,1,2,
3、4；
(2) it utilizes signal processing algorithm to handle brain wave digital signal, obtains spectrum signal；Detailed process is as follows：By brain
Electric wave digital signal carries out segment processing, and frequency-region signal is obtained using Fast Fourier Transform (FFT) to each segment signal, believes frequency domain
Number extraction power spectrum, finally to power spectrum carry out Log transformation, obtain Log power spectrum, i.e. spectrum signal；
(3) difficulty feature, language are expressed comprising ordered structure feature, language with what spectrum signal and step (1) marked
Multifarious artificial marking text is expressed, deep learning model training ordered structure feature, language expression difficulty feature, language are utilized
Speech expresses multifarious characteristic model, while extracting feature to spectrum signal using deep learning model；
(4) using the obtained characteristic model of training to brain wave digital signal extract related composition ordered structure feature,
Language expresses difficulty feature, language expresses multifarious feature score, and trains final composition to beat according to linear regression algorithm
Sub-model.
Preferably, in step (2), segment processing mode is specially：It is 1s per segment length, every section is disposed, to
After move 0.5s, had between adjacent two sections 0.5s overlapping, reprocessing, until being disposed；Fast Fourier Transform (FFT) be from
Dissipate the fast algorithm of Fourier transformation.
Preferably, in step (3), the deep learning model includes deep neural network, convolutional neural networks
And Recognition with Recurrent Neural Network；Deep learning is the branch of machine learning, is that one kind attempting use comprising labyrinth or by multiple non-
Multiple process layers that linear transformation is constituted carry out data the algorithm of higher level of abstraction, the feature of extraction include ordered structure feature,
Language expresses difficulty feature, language expresses diversity, these are characterized in that deep learning algorithm is automatically learned, later to brain electricity
It is labeled on the corresponding time slice of wave signal.
Preferably, in step (4), setting ordered structure feature is divided into five grades, and language expresses difficulty feature point
For five grades, language expression diversity is divided into five grades, wherein the corresponding numerical value of five grades is 0,1,2,3,4,
Linear regression algorithm formula is as follows：Y=AX+b, the formula are vector forms, wherein Y is final score, and A and b are spoken marking
Model parameter, A are vectors, and b is scalar, and X is the feature vector of extraction.
Preferably, the evaluation and test stage etch is as follows：
(a) brain wave sensor detects human brain, will collect brain wave original signal every time and be converted to brain wave number
Signal；
(b) utilize signal processing algorithm handle brain wave digital signal, obtain spectrum signal, by brain wave digital signal into
Row segment processing obtains frequency-region signal to each segment signal using Fast Fourier Transform (FFT), extracts power spectrum to frequency-region signal, most
Log transformation is carried out to power spectrum afterwards；
(c) the deep learning model obtained according to training expresses difficulty to spectrum signal extraction ordered structure feature, language
Feature, language express multifarious feature；
(d) the composition scoring model obtained using training, and composition is evaluated and tested according to the feature of extraction.
Preferably, in step (b), segment processing mode is specially：It is 1s per segment length, every section is disposed, to
After move 0.5s, had between adjacent two sections 0.5s overlapping, reprocessing, until being disposed；Fast Fourier Transform (FFT) be from
Dissipate the fast algorithm of Fourier transformation.
The beneficial effects of the invention are as follows：Brain wave detection, signal processing technology and machine learning method are run, is realized pair
Accurate, automatically evaluation and test that the composition of learner carries out, can quickly improve composition Learning efficiency.
Specific implementation mode
The present invention will be further described With reference to embodiment.
A kind of composition evaluating method based on brain wave, including training stage and evaluation and test stage, the training stage refer to
Be：With eeg signal, ordered structure feature, language expression difficulty feature, language are trained using deep learning technology
Multifarious Feature Selection Model is expressed, feature is extracted according to Feature Selection Model, final training obtains composition scoring model；Institute
The evaluation and test stage stated refers to：Brain wave sensor obtains eeg signal, and extraction ordered structure feature, language expression difficulty are special
Sign, language express multifarious feature, and composition evaluation and test is carried out using composition scoring model.
Wherein：Training stage, steps are as follows：
(1) data collection and mark establish eeg signal language material, composition corpus and mark file；Brain wave senses
Device detects human brain, will collect brain wave original signal every time and be converted to brain wave digital signal；Composition file is recorded simultaneously,
Manually composition file is handled, corresponding ordered structure feature is marked to corresponding eeg signal file, language expresses difficulty
Feature, language express multifarious artificial marking file；Setting ordered structure feature is divided into five grades, and it is special that language expresses difficulty
Sign is divided into five grades, and language expression diversity is divided into five grades, wherein the corresponding numerical value of five grades is 0,1,2,
3、4；
(2) it utilizes signal processing algorithm to handle brain wave digital signal, obtains spectrum signal；Detailed process is as follows：By brain
Electric wave digital signal carries out segment processing, and frequency-region signal is obtained using Fast Fourier Transform (FFT) to each segment signal, believes frequency domain
Number extraction power spectrum, finally to power spectrum carry out Log transformation, obtain Log power spectrum, i.e. spectrum signal；Segment processing mode has
Body is：It is 1s per segment length, every section is disposed, and moves backward 0.5s, and 0.5s is had between adjacent two sections and is overlapped, at repetition
Reason, until being disposed；Fast Fourier Transform (FFT) is the fast algorithm of discrete Fourier transform；
(3) difficulty feature, language are expressed comprising ordered structure feature, language with what spectrum signal and step (1) marked
Multifarious artificial marking text is expressed, deep learning model training ordered structure feature, language expression difficulty feature, language are utilized
Speech expresses multifarious characteristic model, while extracting feature to spectrum signal using deep learning model；Deep learning model packet
Include deep neural network, convolutional neural networks and Recognition with Recurrent Neural Network；Deep learning is the branch of machine learning, is that one kind attempts
The algorithm that using the multiple process layers constituted comprising labyrinth or by multiple nonlinear transformation data are carried out with higher level of abstraction, is carried
The feature taken includes ordered structure feature, language expression difficulty feature, language expression diversity, these are characterized in that deep learning is calculated
Method is automatically learned, later to being labeled on the corresponding time slice of eeg signal；
(4) using the obtained characteristic model of training to brain wave digital signal extract related composition ordered structure feature,
Language expresses difficulty feature, language expresses multifarious feature score, and trains final composition to beat according to linear regression algorithm
Sub-model；Setting ordered structure feature is divided into five grades, and language expression difficulty feature is divided into five grades, and language expression is various
Property be divided into five grades, wherein the corresponding numerical value of five grades be 0,1,2,3,4, linear regression algorithm formula is as follows：Y=
AX+b, the formula are vector forms, wherein Y is final score, and A and b are spoken scoring model parameters, and A is vector, and b is mark
Amount, X are the feature vectors of extraction.
It is as follows to evaluate and test stage etch：
(a) brain wave sensor detects human brain, will collect brain wave original signal every time and be converted to brain wave number
Signal；
(b) utilize signal processing algorithm handle brain wave digital signal, obtain spectrum signal, by brain wave digital signal into
Row segment processing obtains frequency-region signal to each segment signal using Fast Fourier Transform (FFT), extracts power spectrum to frequency-region signal, most
Log transformation is carried out to power spectrum afterwards；Segment processing mode is specially：It is 1s per segment length, every section is disposed, and moves backward
0.5s has 0.5s overlappings, reprocessing, until being disposed between adjacent two sections；Fast Fourier Transform (FFT) is direct computation of DFT
The fast algorithm of leaf transformation；
(c) the deep learning model obtained according to training expresses difficulty to spectrum signal extraction ordered structure feature, language
Feature, language express multifarious feature；
(d) the composition scoring model obtained using training, and composition is evaluated and tested according to the feature of extraction.
The present invention proposes composition method for automatically evaluating, by acquiring the eeg signal of user, passes through deep learning
Algorithm extraction expresses multifarious feature in relation to the ordered structure feature, language expression difficulty feature, language write a composition, and is beaten in composition
It gives a mark on sub-model, obtains final composition evaluation and test score.The present invention runs brain wave detection, signal processing technology and machine
Device learning method realizes the composition to learner and carries out accurate, automatically evaluation and test, can quickly improve composition Learning efficiency.
Claims (7)
1. a kind of composition evaluating method based on brain wave, characterized in that including training stage and evaluation and test stage, the training
Stage refers to：With eeg signal, train ordered structure feature, language expression difficulty special using deep learning technology
Sign, language express multifarious Feature Selection Model, extract feature according to Feature Selection Model, final training obtains composition marking
Model；The evaluation and test stage refers to：Brain wave sensor obtains eeg signal, extraction ordered structure feature, language table
Multifarious feature is expressed up to difficulty feature, language, composition evaluation and test is carried out using composition scoring model.
2. a kind of composition evaluating method based on brain wave according to claim 1, characterized in that the training stage
Steps are as follows：
(1) data collection and mark establish eeg signal language material, composition corpus and mark file；Brain wave sensor is examined
Human brain is surveyed, brain wave original signal will be collected every time and be converted to brain wave digital signal；Composition file is recorded simultaneously, manually
Composition file is handled, to corresponding eeg signal file mark corresponding ordered structure feature, language expression difficulty feature,
Language expresses multifarious artificial marking file；Setting ordered structure feature is divided into five grades, and language expresses difficulty feature point
For five grades, language expression diversity is divided into five grades, wherein the corresponding numerical value of five grades is 0,1,2,3,4；
(2) it utilizes signal processing algorithm to handle brain wave digital signal, obtains spectrum signal；Detailed process is as follows：By brain wave
Digital signal carries out segment processing, obtains frequency-region signal using Fast Fourier Transform (FFT) to each segment signal, is carried to frequency-region signal
Power spectrum is taken, Log transformation finally is carried out to power spectrum, obtains Log power spectrum, i.e. spectrum signal；
(3) it is expressed comprising ordered structure feature, language expression difficulty feature, language with what spectrum signal and step (1) marked
Multifarious artificial marking text utilizes deep learning model training ordered structure feature, language expression difficulty feature, language table
Feature is extracted to spectrum signal up to multifarious characteristic model, while using deep learning model；
(4) characteristic model obtained using training is to ordered structure feature of the brain wave digital signal extraction in relation to composition, language
Difficulty feature, the multifarious feature score of language expression are expressed, and trains final composition marking mould according to linear regression algorithm
Type.
3. a kind of composition evaluating method based on brain wave according to claim 2, characterized in that in step (2), point
Section processing mode be specially：It is 1s per segment length, every section is disposed, and moves backward 0.5s, 0.5s is had between adjacent two sections
Overlapping, reprocessing, until being disposed；Fast Fourier Transform (FFT) is the fast algorithm of discrete Fourier transform.
4. a kind of composition evaluating method based on brain wave according to claim 2, characterized in that in step (3), institute
The deep learning model stated includes deep neural network, convolutional neural networks and Recognition with Recurrent Neural Network；Deep learning is engineering
The branch of habit, be it is a kind of attempt using the multiple process layers constituted comprising labyrinth or by multiple nonlinear transformation to data into
The algorithm of row higher level of abstraction, the feature of extraction includes ordered structure feature, language expresses difficulty feature, language expresses diversity,
These are characterized in that deep learning algorithm is automatically learned, later to being labeled i.e. on the corresponding time slice of eeg signal
It can.
5. a kind of composition evaluating method based on brain wave according to claim 2, characterized in that in step (4), if
Determine ordered structure feature and be divided into five grades, language expression difficulty feature is divided into five grades, and language expression diversity is divided into five
A grade, wherein the corresponding numerical value of five grades is 0,1,2,3,4, linear regression algorithm formula is as follows：Y=AX+b, should
Formula is vector form, wherein Y is final score, and A and b are spoken scoring model parameters, and A is vector, and b is scalar, and X is to carry
The feature vector taken.
6. a kind of composition evaluating method based on brain wave according to Claims 2 or 3 or 4 or 5, characterized in that described
Evaluation and test stage etch it is as follows：
(a) brain wave sensor detects human brain, will collect brain wave original signal every time and be converted to brain wave digital signal；
(b) it utilizes signal processing algorithm to handle brain wave digital signal, obtains spectrum signal, brain wave digital signal is divided
Section processing, frequency-region signal is obtained to each segment signal using Fast Fourier Transform (FFT), and power spectrum is extracted to frequency-region signal, finally right
Power spectrum carries out Log transformation；
(c) the deep learning model obtained according to training, it is special to spectrum signal extraction ordered structure feature, language expression difficulty
Sign, language express multifarious feature；
(d) the composition scoring model obtained using training, and composition is evaluated and tested according to the feature of extraction.
7. a kind of composition evaluating method based on brain wave according to claim 6, characterized in that in step (b), point
Section processing mode be specially：It is 1s per segment length, every section is disposed, and moves backward 0.5s, 0.5s is had between adjacent two sections
Overlapping, reprocessing, until being disposed；Fast Fourier Transform (FFT) is the fast algorithm of discrete Fourier transform.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267782.3A CN108537261A (en) | 2018-03-28 | 2018-03-28 | A kind of composition evaluating method based on brain wave |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810267782.3A CN108537261A (en) | 2018-03-28 | 2018-03-28 | A kind of composition evaluating method based on brain wave |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108537261A true CN108537261A (en) | 2018-09-14 |
Family
ID=63481613
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810267782.3A Pending CN108537261A (en) | 2018-03-28 | 2018-03-28 | A kind of composition evaluating method based on brain wave |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108537261A (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584643A (en) * | 2018-11-05 | 2019-04-05 | 深圳大学 | A kind of language competence training method and its system |
| CN112765973A (en) * | 2021-01-18 | 2021-05-07 | 鲁东大学 | Scoring model training method and device and composition scoring method and device |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541261A (en) * | 2012-01-19 | 2012-07-04 | 北京工业大学 | Film editing and selecting auxiliary instrument and realization method based on characteristics of electroencephalogram signal |
| CN106713787A (en) * | 2016-11-02 | 2017-05-24 | 天津大学 | Evaluation method for watching comfort level caused by rolling subtitles of different speed based on EEG |
| CN107590445A (en) * | 2017-08-25 | 2018-01-16 | 西安电子科技大学 | Aesthetic images quality evaluating method based on EEG signals |
| CN107609492A (en) * | 2017-08-25 | 2018-01-19 | 西安电子科技大学 | Distorted image quality based on EEG signals perceives evaluation method |
-
2018
- 2018-03-28 CN CN201810267782.3A patent/CN108537261A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN102541261A (en) * | 2012-01-19 | 2012-07-04 | 北京工业大学 | Film editing and selecting auxiliary instrument and realization method based on characteristics of electroencephalogram signal |
| CN106713787A (en) * | 2016-11-02 | 2017-05-24 | 天津大学 | Evaluation method for watching comfort level caused by rolling subtitles of different speed based on EEG |
| CN107590445A (en) * | 2017-08-25 | 2018-01-16 | 西安电子科技大学 | Aesthetic images quality evaluating method based on EEG signals |
| CN107609492A (en) * | 2017-08-25 | 2018-01-19 | 西安电子科技大学 | Distorted image quality based on EEG signals perceives evaluation method |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109584643A (en) * | 2018-11-05 | 2019-04-05 | 深圳大学 | A kind of language competence training method and its system |
| CN112765973A (en) * | 2021-01-18 | 2021-05-07 | 鲁东大学 | Scoring model training method and device and composition scoring method and device |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN109255044A (en) | A kind of image intelligent mask method based on YOLOv3 deep learning network | |
| CN108898085A (en) | Intelligent road disease detection method based on mobile phone video | |
| CN104978884A (en) | Teaching system of preschool education profession student music theory and solfeggio learning | |
| CN110108992B (en) | Cable partial discharge fault identification method and system based on improved random forest algorithm | |
| CN105989842A (en) | Method and device for voiceprint similarity comparison and application thereof in digital entertainment on-demand system | |
| CN101197084A (en) | Automatic spoken English evaluating and learning system | |
| CN103117061A (en) | Method and device for identifying animals based on voice | |
| CN103970271A (en) | Daily activity identifying method with exercising and physiology sensing data fused | |
| CN108537261A (en) | A kind of composition evaluating method based on brain wave | |
| CN105825852A (en) | Oral English reading test scoring method | |
| CN106205633A (en) | A kind of imitation, performance exercise scoring system | |
| CN103377647A (en) | Automatic music notation recording method and system based on audio and video information | |
| CN101976564A (en) | Method for identifying insect voice | |
| CN101561868A (en) | Human motion emotion identification method based on Gauss feature | |
| CN106503691A (en) | A kind of identity mask method of face picture and device | |
| CN103793704B (en) | Supervising neighborhood preserving embedding face recognition method and system and face recognizer | |
| CN108491830A (en) | A kind of job site personnel uniform dress knowledge method for distinguishing based on deep learning | |
| CN104346389A (en) | Scoring method and system of semi-open-ended questions of oral test | |
| CN109165881A (en) | Teachers' instruction method for evaluating quality based on big data | |
| CN108509939A (en) | A kind of birds recognition methods based on deep learning | |
| CN110364184A (en) | Accuracy in pitch appraisal procedure based on depth convolutional neural networks DCNN and CTC algorithm | |
| CN109272986A (en) | A kind of dog sound sensibility classification method based on artificial neural network | |
| EP4027348A3 (en) | Affinity prediction method and apparatus, method and apparatus for training affinity prediction model, device and medium | |
| CN103366735A (en) | A voice data mapping method and apparatus | |
| CN108447504A (en) | A kind of oral evaluation method based on brain wave |
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: 20180914 |
|
| RJ01 | Rejection of invention patent application after publication |