CN107609736A - A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology - Google Patents
A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology Download PDFInfo
- Publication number
- CN107609736A CN107609736A CN201710677105.4A CN201710677105A CN107609736A CN 107609736 A CN107609736 A CN 107609736A CN 201710677105 A CN201710677105 A CN 201710677105A CN 107609736 A CN107609736 A CN 107609736A
- Authority
- CN
- China
- Prior art keywords
- unit
- analysis
- content
- teaching
- recognition
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention belongs to communicate and field of Educational Technology, it is related to a kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology.Turn text including prefabricated classroom Index module, data acquisition module, the recognition of face processing for extracting image, extraction audio signal vocal print recognition processing module, voice and identify the voice recognition processing module of high-frequency content and the natural language processing module of secondary analysis is carried out to content of text；Association analysis module is used to, using time value as index, establish association analysis view, and generate classroom instruction quantizating index analysis result；For diagnostic analysis module using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, forms instruction analysis result.The present invention utilizes artificial intelligence technology, establishes big data collection standard, accurate to obtain classroom instruction analyze data；Teaching process, knowledge content analysis and analysis of the students can be associated, analyze teaching efficiency caused by various teaching mode.
Description
Technical field
The invention belongs to communicate and field of Educational Technology, more particularly, to a kind of integrated application artificial intelligence technology
Teaching diagnostic analysis system and method.
Background technology
Artificial intelligence is research, develops intelligent theory, method, technology and application for simulating, extending and extending people
One new technological sciences of system.Artificial intelligence is a branch of computer science, and it attempts to understand the essence of intelligence, and
A kind of new intelligence machine that can be made a response in a manner of human intelligence is similar is produced, the research in the field includes machine
People, language identification, image recognition, natural language processing and expert system etc..Artificial intelligence is since the birth, theory and technology day
Beneficial ripe, application field also constantly expands, it is contemplated that the sci-tech product that following artificial intelligence is brought, it will be the wisdom of humanity
" container ".
Image recognition, refer to handle image using computer, analyzed and understood, to identify various different modes
Target and the technology to picture.
Application on Voiceprint Recognition is one kind of biological identification technology.Also referred to as Speaker Identification, there is two classes, i.e. speaker recognizes and said
People is talked about to confirm.Different tasks and application can use different sound groove recognition technology in e, may need to distinguish when such as reducing criminal investigation scope
Recognize technology, and confirmation technology is then needed during bank transaction.Application on Voiceprint Recognition is exactly that acoustical signal is converted into electric signal, then uses computer
It is identified.
Speech recognition technology be exactly allow machine by identification and understanding process voice signal be changed into corresponding text or
The high-tech of order.Speech recognition technology mainly includes Feature Extraction Technology, pattern match criterion and model training technology three
Aspect.
Natural language processing is computer science and an important directions in artificial intelligence field.It is studied can be real
The existing various theoretical and methods for carrying out efficient communication between people and computer with natural language.
Existing technical scheme, is diagnosed and is analyzed for classroom instruction, there is three kinds of modes：First, without using technology hand
Section, directly go to record the situation that teacher attends class by way of expert audits, then carry out subjective scoring, belong to complete artificial；Two
It was that teacher's upper class hour and some interactive caused Process Character data messages of student, this kind of auxiliary are recorded by using auxiliary equipment
Equipment generally requires teacher or student is participated among the generation of data, belongs to semi-automatic；Third, use some newer skills
Art, such as video tracking（It is common in recording and broadcasting system）, or speech recognition, to carry out automatic decision.
In existing technical scheme, the first all relies on substantial amounts of manpower with second and participated in, and lacks practical application effect.
Even the third more advanced scheme, due to the limitation of its technology application, for the data acquisition of classroom instruction analysis
The deviation of limitation and maximum probability be present.Moreover, in actual applications, it is limited in some traditional instruction analysis methods
（Such as S-T instruction analysis methods）, accuracy description is lacked to the complete procedure of classroom instruction.
The content of the invention
It is an object of the invention to overcome the deficiencies of the prior art and provide a kind of teaching of integrated application artificial intelligence technology
Diagnostic analysis system and method, using artificial intelligence technology, the big data collection standard of classroom instruction is established, accurately obtains classroom
The analyze data of teaching, automatically generates analysis result；Teaching process, knowledge content analysis and analysis of the students can be closed
Connection, analyzes teaching efficiency caused by various teaching mode.
To solve the above problems, technical scheme provided by the invention is：A kind of teaching of integrated application artificial intelligence technology
Diagnostic analysis system, wherein, including with lower module：
Prefabricated classroom Index module is used for according to the characteristics of this subject, and quantizating index setting is carried out to essential of classroom teaching；
Data acquisition module, which is used to gathering classroom to attend class, video and completes video to the conversion process of audio；
Recognition of face processing module is connected with data acquisition module, for carrying out image sampling to the video of recording, according to face
Recognition principle, feature extraction is carried out to the facial image in image；
Application on Voiceprint Recognition processing module is connected with data acquisition module, for carrying out blind source signal separation processing to audio file, is carried
Audio signal is taken, records the period of no sound, completes audio classification, and carry out characteristic value mark；
Voice recognition processing module is connected with data acquisition module, for using speech recognition engine, audio file to be carried out into language
Sound is identified, is converted into text, and semantic analysis is carried out to content of text, is identified high-frequency content and is generated practical intelligence collection of illustrative plates；
Natural language processing module is connected with voice recognition processing module, for the text generated to voice recognition processing module
Content carries out secondary analysis, completes the analysis of language feature, using cluster analysis, realizes the identification, positioning and mark of sensitive content
Note；
Association analysis module respectively with recognition of face processing module, Application on Voiceprint Recognition processing module, voice recognition processing module, nature
Language processing module connects, for using time value as index, establishing recognition of face processing module, Application on Voiceprint Recognition processing module, language
The association analysis view of sound recognition processing module, natural language processing module, and generate classroom instruction quantizating index analysis result；
Diagnostic analysis module is connected with association analysis module, prefabricated classroom Index module respectively, for being given birth to association analysis module
Into the preset classroom instruction quantizating index of classroom instruction quantizating index analysis result and prefabricated classroom Index module carry out pair
Than analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, is formed
Instruction analysis result.
Further, described recognition of face processing module includes face collecting unit, face characteristic judging unit, added
Time tag unit, focus scaling unit and feelings effect data generation unit；
Described face collecting unit is connected with data acquisition module, for carrying out image sampling to the video of recording；
Described face characteristic judging unit is connected with face collecting unit, for foundation recognition of face principle, in image
Facial image carries out feature extraction, and characteristic value is put in storage and accessed；
Described addition time tag unit is connected with face characteristic judging unit, for setting specific time interval value, is carried
Take student's face characteristic value in each interval time；
Described focus scaling unit is connected with adding time tag unit, in each sampling interval, by student
Come back the personnel amount listened to the teacher, and focus is set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus
It is set to 0；
Described feelings effect data generation unit is connected with focus scaling unit, for what is conversed for focus unit
Feelings effect data is learned in student's focus result, generation.
Further, described Application on Voiceprint Recognition processing module includes audio frequency characteristics value extraction unit, cluster analysis unit, divided
Class mark unit, time tag unit and teaching process data generating unit；
Described audio frequency characteristics value extraction unit is connected with data acquisition module, for being carried out to audio file at blind source signal
Reason, extract the period of no sound, and recorded time value；It is another to be additionally operable to read audio digital signals, according to（Sample frequency,
Sampled value）Form sampled, be stored in feature list；
Described cluster analysis unit is connected with audio frequency characteristics value extraction unit, for being extracted for audio frequency characteristics value extraction unit
The audio signal gone out carries out characteristic matching, completes cluster analysis；
Described classification annotation unit is connected with cluster analysis unit, for classifying to the characteristic value after matching, and is carried out
Characteristic value marks；
Described time tag unit is connected with classification annotation unit, for recording the time value of each characteristic value classification；
Described teaching process data generating unit is connected with time tag unit, for for audio frequency characteristics value extraction unit,
The data that cluster analysis unit, classification annotation unit and time tag unit are generated, generate teaching process data.
Further, described voice recognition processing module turns text unit, mark unit, the knowledge of the basic meaning of a word including voice
Other unit, keyword word frequency analysis unit and content of courses data generating unit；
Described voice turns text unit and is connected with data acquisition module, for the audio text generated for data acquisition module
Part, using speech recognition technology, audio file is subjected to speech recognition, changes into text；
Described mark unit turns text unit with voice and is connected, and enters for turning the content of text that text unit is generated to voice
Row participle, part-of-speech tagging；
Described basic meaning of a word recognition unit is connected with mark unit, is put in storage for identifying underlying semantics, and by the content of identification
Keep；
Described keyword word frequency analysis unit is connected with basic meaning of a word recognition unit, for carrying out semantic point to content of text
Analysis, by TF-IDF algorithms, high-frequency content is identified, all data are stored according to RDF data form；
Described content of courses data generating unit is connected with keyword word frequency analysis unit, for for keyword word frequency analysis
The high-frequency content that unit is identified, generate content of courses data.
Further, described natural language processing module includes secondary expectation storehouse processing unit, language feature analysis list
Member, language sentiment analysis unit, sensitive content recognition unit and teaching characteristic data generating unit；
Described secondary expectation storehouse processing unit is connected with voice recognition processing module, for establishing secondary corpus, to voice
Turn the text that text unit is generated and carry out secondary analysis；
Described language feature analytic unit is connected with secondary language material library unit, for completing the analysis of language feature；Described
Language feature includes word speed, word；
Described language sentiment analysis unit is connected with language feature analytic unit, for identifying the emotion in secondary corpus
Word, and emotion weight assignment is carried out to emotion word；
Described sensitive content recognition unit is connected with language sentiment analysis unit, for for secondary corpus, establishing special
Sensitive dictionary, and sensitive word is classified；Using cluster analysis, the sensitive word related to semanteme and emotion word are identified, according to
According to two dimensions of time and distance vector value, semantic amendment is carried out, realizes the identification, positioning and mark of sensitive content；
Described teaching characteristic data generating unit is connected with sensitive content recognition unit, for for sensitive content recognition unit
The data generated, generate teaching characteristic data.
The present invention also provides a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology, wherein, including it is following
Step：
S1., preset classroom index is set, according to the characteristics of this subject, quantizating index setting is carried out to essential of classroom teaching；
S2. data acquisition is carried out, collection classroom, which is attended class, video and completes video to the conversion process of audio；
S3. recognition of face processing, Application on Voiceprint Recognition processing, voice recognition processing and natural language processing are carried out, is carrying out face
Image sampling is carried out to the video of recording during identifying processing, according to recognition of face principle, the facial image in image carried out special
Sign extraction；Blind source signal separation processing is carried out to audio file when carrying out Application on Voiceprint Recognition processing, extracts audio signal, record does not have
There is the period of sound, complete audio classification, and carry out characteristic value mark；When carrying out voice recognition processing, known using voice
Other engine, audio file is subjected to speech recognition, is converted into text, semantic analysis is carried out to content of text, identifies high-frequency content
And generate practical intelligence collection of illustrative plates；When carrying out natural language processing, the content of text generated to voice recognition processing module enters
Row secondary analysis, the analysis of language feature is completed, using cluster analysis, realize the identification, positioning and mark of sensitive content；
S4. analysis is associated, at recognition of face result in S3 steps, Application on Voiceprint Recognition result, speech recognition
Result and natural language processing result are managed, using time value as index, establishes recognition of face processing module, Application on Voiceprint Recognition processing mould
Block, voice recognition processing module, the association analysis view of natural language processing module, and generate the analysis of classroom instruction quantizating index
As a result；
S5. diagnostic analysis is carried out, is carried out for the association analysis result in classroom index and S4 steps preset in S1 steps
Comparative analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, shape
Into instruction analysis result.
Further, comprise the following steps at described recognition of face：
S3011. face gathers, and the video of the recording gathered for data acquisition carries out image sampling；
S3012. face characteristic judges, for the human face data gathered in S3011, according to recognition of face principle, in image
Facial image carry out feature extraction, and by characteristic value be put in storage access；
S3013. time tag is added, the face characteristic value extracted for S3013 steps, specific time interval value is set,
Extract student's face characteristic value in each interval time；
S3014. focus conversion is carried out, to S3013 steps, in each sampling interval, student is come back the personnel to listen to the teacher
Quantity, focus are set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus is set to 0；
S3015. feelings effect data, the student's focus result conversed for S3014 steps are learned in generation, and feelings effect is learned in generation
Fruit data.
Further, described Application on Voiceprint Recognition processing comprises the following steps：
S3021. audio frequency characteristics value is extracted, the content of text changed for data acquisition, and blind source signal is carried out to audio file
Processing, extract the period of no sound, and recorded time value；It is another to be additionally operable to read audio digital signals, according to（Sampling frequency
Rate, sampled value）Form sampled, be stored in feature list；
S3022. cluster analysis is carried out, the audio frequency characteristics value extracted for S3021 steps, carries out characteristic matching, completes cluster
Analysis；
S3023. classification annotation is carried out, the characteristic value after being matched to S3022 steps is classified, and carries out characteristic value mark；
S3024. time tag is added, the time value of each characteristic value classification is recorded for the classification results of S3023 steps；
S3025. teaching process data are generated, are given birth to for S3021 steps, S3022 steps, S3023 steps and S3024 steps
Into data, generate teaching process data.
Further, described voice recognition processing comprises the following steps：
S3031. voice turns text, the audio file extracted for data acquisition, using speech recognition technology, by audio text
Part carries out speech recognition, changes into text；
S3032. it is labeled, the content of text generated to S3031 steps is segmented, part-of-speech tagging；
S3033. basic meaning of a word identification, identifies underlying semantics, and the content of identification is put in storage and kept；
S3034. keyword word frequency analysis, semantic analysis is carried out for the content of text of S3031 steps, by TF-IDF algorithms,
High-frequency content is identified, all data are stored according to RDF data form；
S3035. content of courses data are generated, the high-frequency content identified for S3034 steps, generate content of courses data.
Further, described natural language processing comprises the following steps：
S3041. two expectation storehouse processing, the text generated for voice recognition processing, establish secondary corpus, to text
Carry out secondary analysis；
S3042. language feature is analyzed, and for the secondary corpus of S3041 steps, carries out the analysis of language feature；Described language
Speech feature includes word speed, word；
S3043. language sentiment analysis, the emotion word in secondary corpus is identified, and emotion weight assignment is carried out to emotion word；
S3044. sensitive content identifies, for secondary corpus, establishes special sensitive dictionary, and sensitive word is classified；
Using cluster analysis, identify and semantic related sensitive word and emotion word, foundation two dimensions of time and distance vector value, progress
Semanteme amendment, realizes the identification, positioning and mark of sensitive content；
S3045. teaching characteristic data are generated, the data generated for S3044 steps, generate teaching characteristic data.
Compared with prior art, beneficial effect is：A kind of teaching of integrated application artificial intelligence technology provided by the invention
Diagnostic analysis system and method, 1. data acquisitions more complete and accurate, by the combination of artificial intelligence technology and statistical science, makes
It is more accurate to obtain analysis result；2. be not limited in traditional S-T analytic approach, can accurately identify teachers' instruction, classroom interactions,
Student grouping discussion, a variety of teaching processes such as instructional video, silent exercise are played, more have guidance to teaching diagnosis and the reform in education
Property；3. knowledge mapping can be automatically generated, and knowledge mapping is compared based on the content of courses of reality；4. association
Analysis of the students so that teaching method and its caused teaching efficiency can be associated, and can preferably carry out measure teaching analysis,
Foundation is provided to lift the Analysis of Policy Making of teaching quality；5. complete management system before the class, in class, after class can be formed,
Realize artificial intelligence in whole process applications such as teaching, management, resource constructions.
Brief description of the drawings
Fig. 1 is overall structure diagram of the present invention.
Embodiment
As shown in figure 1, a kind of teaching diagnostic analysis system of integrated application artificial intelligence technology, wherein, including following mould
Block：
Prefabricated classroom Index module is used for according to the characteristics of this subject, and quantizating index setting is carried out to essential of classroom teaching；
Data acquisition module, which is used to gathering classroom to attend class, video and completes video to the conversion process of audio；
Recognition of face processing module is connected with data acquisition module, for carrying out image sampling to the video of recording, according to face
Recognition principle, feature extraction is carried out to the facial image in image；
Application on Voiceprint Recognition processing module is connected with data acquisition module, for carrying out blind source signal separation processing to audio file, is carried
Audio signal is taken, records the period of no sound, completes audio classification, and carry out characteristic value mark；
Voice recognition processing module is connected with data acquisition module, for using speech recognition engine, audio file to be carried out into language
Sound is identified, is converted into text, and semantic analysis is carried out to content of text, is identified high-frequency content and is generated practical intelligence collection of illustrative plates；
Natural language processing module is connected with voice recognition processing module, for the text generated to voice recognition processing module
Content carries out secondary analysis, completes the analysis of language feature, using cluster analysis, realizes the identification, positioning and mark of sensitive content
Note；
Association analysis module respectively with recognition of face processing module, Application on Voiceprint Recognition processing module, voice recognition processing module, nature
Language processing module connects, for using time value as index, establishing recognition of face processing module, Application on Voiceprint Recognition processing module, language
The association analysis view of sound recognition processing module, natural language processing module, and generate classroom instruction quantizating index analysis result；
Diagnostic analysis module is connected with association analysis module, prefabricated classroom Index module respectively, for being given birth to association analysis module
Into the preset classroom instruction quantizating index of classroom instruction quantizating index analysis result and prefabricated classroom Index module carry out pair
Than analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, is formed
Instruction analysis result.
In the present invention, when carrying out diagnostic analysis, 1. using time value as dimension, structure is learned feelings, knowledge content, imparted knowledge to students
The association analysis view of journey, teaching characteristic；2. using the time as axis, instruction analysis result is formed；3. field research diagnosis is completed,
Form intuitively big data view；4. preset classroom instruction index is analyzed；5. automatically generate comparative analysis result
Reported with decision recommendation.
In certain embodiments, recognition of face processing module includes face collecting unit, face characteristic judging unit, added
Time tag unit, focus scaling unit and feelings effect data generation unit；Face collecting unit and data acquisition module
Block connects, for carrying out image sampling to the video of recording；Face characteristic judging unit is connected with face collecting unit, for according to
According to recognition of face principle, feature extraction is carried out to the facial image in image, and characteristic value is put in storage and accessed；Add time tag
Unit is connected with face characteristic judging unit, for setting specific time interval value, extracts student people in each interval time
Face characteristic value；Focus scaling unit is connected with adding time tag unit, in each sampling interval, student to be lifted
The personnel amount that head is listened to the teacher, focus are set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus sets
For 0；Learn feelings effect data generation unit to be connected with focus scaling unit, the student for conversing for focus unit is special
Feelings effect data is learned in note degree result, generation.
In the present invention, such as relating to arriving multiple cameras, then the feature set collected between different cameras is compared
It is right, confirm personnel's number of iterations according to the threshold value of setting, disappear weight, avoids personnel from repeatedly being counted；It can determine that in each sampling
In interval, student comes back the personnel amount listened to the teacher, and focus is set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line
Number）, focus is set to 0；In addition, can be according to statistical binomial distribution principle, the i.e. repeatedly Bernoulli trials of n times, can
To obtain the probability analysis of whole focus.Because the N of setting is sufficiently large, according to the law of large numbers of probability theory, chance event
Frequency is similar to its true probability, so as to obtain the confidential interval of whole classroom student entirety focus.
In the present invention, the personal focus behavior of any one student need to be such as identified, then whole school need to be established in early stage
Raw face picture library, increase face alignment are carried out so as to identify the personal absorbed degrees of data of each student, then according to above-mentioned algorithm
Identification.
In certain embodiments, Application on Voiceprint Recognition processing module includes audio frequency characteristics value extraction unit, cluster analysis unit, divided
Class mark unit, time tag unit and teaching process data generating unit；Audio frequency characteristics value extraction unit and data acquisition
Module connects, and for carrying out blind signal processing to audio file, extracts the period of no sound, and recorded time value；Separately
It is additionally operable to read audio digital signals, according to（Sample frequency, sampled value）Form sampled, be stored in feature list；Cluster
Analytic unit is connected with audio frequency characteristics value extraction unit, and the audio signal for being extracted for audio frequency characteristics value extraction unit is entered
Row characteristic matching, complete cluster analysis；Classification annotation unit is connected with cluster analysis unit, for entering to the characteristic value after matching
Row classification, and carry out characteristic value mark；Time tag unit is connected with classification annotation unit, for recording each characteristic value classification
Time value；
Teaching process data generating unit is connected with time tag unit, for for audio frequency characteristics value extraction unit, cluster point
The data that analysis unit, classification annotation unit and time tag unit are generated, generate teaching process data.
In certain embodiments, voice recognition processing module turns text unit, mark unit, the knowledge of the basic meaning of a word including voice
Other unit, keyword word frequency analysis unit and content of courses data generating unit；Voice turns text unit and data acquisition module
Block is connected, and for the audio file generated for data acquisition module, using speech recognition technology, audio file is carried out into language
Sound identifies, changes into text；Mark unit turns text unit with voice and is connected, for turning what text unit was generated to voice
Content of text is segmented, part-of-speech tagging；Basic meaning of a word recognition unit is connected with mark unit, for identifying underlying semantics, and
The content of identification is put in storage and kept；Keyword word frequency analysis unit is connected with basic meaning of a word recognition unit, for content of text
Semantic analysis is carried out, by TF-IDF algorithms, high-frequency content is identified, all data is stored according to RDF data form；
Content of courses data generating unit is connected with keyword word frequency analysis unit, for being identified for keyword word frequency analysis unit
High-frequency content, generate content of courses data.
In certain embodiments, natural language processing module includes secondary expectation storehouse processing unit, language feature analysis list
Member, language sentiment analysis unit, sensitive content recognition unit and teaching characteristic data generating unit；The processing of secondary expectation storehouse is single
Member is connected with voice recognition processing module, for establishing secondary corpus, is turned the text that text unit is generated to voice and is carried out
Secondary analysis；Language feature analytic unit is connected with secondary language material library unit, for completing the analysis of language feature；Wherein language
Feature includes word speed, word；Language sentiment analysis unit is connected with language feature analytic unit, for identifying in secondary corpus
Emotion word, and to emotion word carry out emotion weight assignment；Sensitive content recognition unit is connected with language sentiment analysis unit, is used
In for secondary corpus, special sensitive dictionary is established, and sensitive word is classified；Using cluster analysis, identification and language
Adopted related sensitive word and emotion word, according to two dimensions of time and distance vector value, carry out semantic amendment, realize sensitive content
Identification, positioning and mark；Teaching characteristic data generating unit is connected with sensitive content recognition unit, for in sensitivity
Hold the data that recognition unit is generated, generate teaching characteristic data.
The present invention also provides a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology, wherein, including it is following
Step：
S1., preset classroom index is set, according to the characteristics of this subject, quantizating index setting is carried out to essential of classroom teaching；
S2. data acquisition is carried out, collection classroom, which is attended class, video and completes video to the conversion process of audio；
S3. recognition of face processing, Application on Voiceprint Recognition processing, voice recognition processing and natural language processing are carried out, is carrying out face
Image sampling is carried out to the video of recording during identifying processing, according to recognition of face principle, the facial image in image carried out special
Sign extraction；Blind source signal separation processing is carried out to audio file when carrying out Application on Voiceprint Recognition processing, extracts audio signal, record does not have
There is the period of sound, complete audio classification, and carry out characteristic value mark；When carrying out voice recognition processing, known using voice
Other engine, audio file is subjected to speech recognition, is converted into text, semantic analysis is carried out to content of text, identifies high-frequency content
And generate practical intelligence collection of illustrative plates；When carrying out natural language processing, the content of text generated to voice recognition processing module enters
Row secondary analysis, the analysis of language feature is completed, using cluster analysis, realize the identification, positioning and mark of sensitive content；
S4. analysis is associated, at recognition of face result in S3 steps, Application on Voiceprint Recognition result, speech recognition
Result and natural language processing result are managed, using time value as index, establishes recognition of face processing module, Application on Voiceprint Recognition processing mould
Block, voice recognition processing module, the association analysis view of natural language processing module, and generate the analysis of classroom instruction quantizating index
As a result；
S5. diagnostic analysis is carried out, is carried out for the association analysis result in classroom index and S4 steps preset in S1 steps
Comparative analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, shape
Into instruction analysis result.
Specifically, comprise the following steps at recognition of face：
S3011. face gathers, and the video of the recording gathered for data acquisition carries out image sampling；
S3012. face characteristic judges, for the human face data gathered in S3011, according to recognition of face principle, in image
Facial image carry out feature extraction, and by characteristic value be put in storage access；
S3013. time tag is added, the face characteristic value extracted for S3013 steps, specific time interval value is set,
Extract student's face characteristic value in each interval time；
S3014. focus conversion is carried out, to S3013 steps, in each sampling interval, student is come back the personnel to listen to the teacher
Quantity, focus are set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus is set to 0；
S3015. feelings effect data, the student's focus result conversed for S3014 steps are learned in generation, and feelings effect is learned in generation
Fruit data.
Specifically, Application on Voiceprint Recognition processing comprises the following steps：
S3021. audio frequency characteristics value is extracted, the content of text changed for data acquisition, and blind source signal is carried out to audio file
Processing, extract the period of no sound, and recorded time value；It is another to be additionally operable to read audio digital signals, according to（Sampling frequency
Rate, sampled value）Form sampled, be stored in feature list；
S3022. cluster analysis is carried out, the audio frequency characteristics value extracted for S3021 steps, carries out characteristic matching, completes cluster
Analysis；
S3023. classification annotation is carried out, the characteristic value after being matched to S3022 steps is classified, and carries out characteristic value mark；
S3024. time tag is added, the time value of each characteristic value classification is recorded for the classification results of S3023 steps；
S3025. teaching process data are generated, are given birth to for S3021 steps, S3022 steps, S3023 steps and S3024 steps
Into data, generate teaching process data.
Specifically, voice recognition processing comprises the following steps：
S3031. voice turns text, the audio file extracted for data acquisition, using speech recognition technology, by audio text
Part carries out speech recognition, changes into text；
S3032. it is labeled, the content of text generated to S3031 steps is segmented, part-of-speech tagging；
S3033. basic meaning of a word identification, identifies underlying semantics, and the content of identification is put in storage and kept；
S3034. keyword word frequency analysis, semantic analysis is carried out for the content of text of S3031 steps, by TF-IDF algorithms,
High-frequency content is identified, all data are stored according to RDF data form；
S3035. content of courses data are generated, the high-frequency content identified for S3034 steps, generate content of courses data.
Specifically, natural language processing comprises the following steps：
S3041. two expectation storehouse processing, the text generated for voice recognition processing, establish secondary corpus, to text
Carry out secondary analysis；
S3042. language feature is analyzed, and for the secondary corpus of S3041 steps, carries out the analysis of language feature；Described language
Speech feature includes word speed, word；
S3043. language sentiment analysis, the emotion word in secondary corpus is identified, and emotion weight assignment is carried out to emotion word；
S3044. sensitive content identifies, for secondary corpus, establishes special sensitive dictionary, and sensitive word is classified；
Using cluster analysis, identify and semantic related sensitive word and emotion word, foundation two dimensions of time and distance vector value, progress
Semanteme amendment, realizes the identification, positioning and mark of sensitive content；
S3045. teaching characteristic data are generated, the data generated for S3044 steps, generate teaching characteristic data.
Obviously, the above embodiment of the present invention is only intended to clearly illustrate example of the present invention, and is not pair
The restriction of embodiments of the present invention.For those of ordinary skill in the field, may be used also on the basis of the above description
To make other changes in different forms.There is no necessity and possibility to exhaust all the enbodiments.It is all this
All any modification, equivalent and improvement made within the spirit and principle of invention etc., should be included in the claims in the present invention
Protection domain within.
Claims (10)
1. the teaching diagnostic analysis system of a kind of integrated application artificial intelligence technology, it is characterised in that including with lower module：
Prefabricated classroom Index module is used for according to the characteristics of this subject, and quantizating index setting is carried out to essential of classroom teaching；
Data acquisition module, which is used to gathering classroom to attend class, video and completes video to the conversion process of audio；
Recognition of face processing module is connected with data acquisition module, for carrying out image sampling to the video of recording, according to face
Recognition principle, feature extraction is carried out to the facial image in image；
Application on Voiceprint Recognition processing module is connected with data acquisition module, for carrying out blind source signal separation processing to audio file, is carried
Audio signal is taken, records the period of no sound, completes audio classification, and carry out characteristic value mark；
Voice recognition processing module is connected with data acquisition module, for using speech recognition engine, audio file to be carried out into language
Sound is identified, is converted into text, and semantic analysis is carried out to content of text, is identified high-frequency content and is generated practical intelligence collection of illustrative plates；
Natural language processing module is connected with voice recognition processing module, for the text generated to voice recognition processing module
Content carries out secondary analysis, completes the analysis of language feature, using cluster analysis, realizes the identification, positioning and mark of sensitive content
Note；
Association analysis module respectively with recognition of face processing module, Application on Voiceprint Recognition processing module, voice recognition processing module, nature
Language processing module connects, for using time value as index, establishing recognition of face processing module, Application on Voiceprint Recognition processing module, language
The association analysis view of sound recognition processing module, natural language processing module, and generate classroom instruction quantizating index analysis result；
Diagnostic analysis module is connected with association analysis module, prefabricated classroom Index module respectively, for being given birth to association analysis module
Into the preset classroom instruction quantizating index of classroom instruction quantizating index analysis result and prefabricated classroom Index module carry out pair
Than analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, is formed
Instruction analysis result.
2. a kind of teaching diagnostic analysis system of integrated application artificial intelligence technology according to claim 1, its feature exist
In, described recognition of face processing module include face collecting unit, face characteristic judging unit, add time tag unit,
Focus scaling unit and feelings effect data generation unit；
Described face collecting unit is connected with data acquisition module, for carrying out image sampling to the video of recording；
Described face characteristic judging unit is connected with face collecting unit, for foundation recognition of face principle, in image
Facial image carries out feature extraction, and characteristic value is put in storage and accessed；
Described addition time tag unit is connected with face characteristic judging unit, for setting specific time interval value, is carried
Take student's face characteristic value in each interval time；
Described focus scaling unit is connected with adding time tag unit, in each sampling interval, by student
Come back the personnel amount listened to the teacher, and focus is set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus
It is set to 0；
Described feelings effect data generation unit is connected with focus scaling unit, for what is conversed for focus unit
Feelings effect data is learned in student's focus result, generation.
3. a kind of teaching diagnostic analysis system of integrated application artificial intelligence technology according to claim 2, its feature exist
In, described Application on Voiceprint Recognition processing module include audio frequency characteristics value extraction unit, cluster analysis unit, classification annotation unit, when
Between tag unit and teaching process data generating unit；
Described audio frequency characteristics value extraction unit is connected with data acquisition module, for being carried out to audio file at blind source signal
Reason, extract the period of no sound, and recorded time value；It is another to be additionally operable to read audio digital signals, according to（Sample frequency,
Sampled value）Form sampled, be stored in feature list；
Described cluster analysis unit is connected with audio frequency characteristics value extraction unit, for being extracted for audio frequency characteristics value extraction unit
The audio signal gone out carries out characteristic matching, completes cluster analysis；
Described classification annotation unit is connected with cluster analysis unit, for classifying to the characteristic value after matching, and is carried out
Characteristic value marks；
Described time tag unit is connected with classification annotation unit, for recording the time value of each characteristic value classification；
Described teaching process data generating unit is connected with time tag unit, for for audio frequency characteristics value extraction unit,
The data that cluster analysis unit, classification annotation unit and time tag unit are generated, generate teaching process data.
4. a kind of teaching diagnostic analysis system of integrated application artificial intelligence technology according to claim 3, its feature exist
In described voice recognition processing module turns text unit, mark unit, basic meaning of a word recognition unit, keyword including voice
Word frequency analysis unit and content of courses data generating unit；
Described voice turns text unit and is connected with data acquisition module, for the audio text generated for data acquisition module
Part, using speech recognition technology, audio file is subjected to speech recognition, changes into text；
Described mark unit turns text unit with voice and is connected, and enters for turning the content of text that text unit is generated to voice
Row participle, part-of-speech tagging；
Described basic meaning of a word recognition unit is connected with mark unit, is put in storage for identifying underlying semantics, and by the content of identification
Keep；
Described keyword word frequency analysis unit is connected with basic meaning of a word recognition unit, for carrying out semantic point to content of text
Analysis, by TF-IDF algorithms, high-frequency content is identified, all data are stored according to RDF data form；
Described content of courses data generating unit is connected with keyword word frequency analysis unit, for for keyword word frequency analysis
The high-frequency content that unit is identified, generate content of courses data.
5. a kind of teaching diagnostic analysis system of integrated application artificial intelligence technology according to claim 4, its feature exist
In described natural language processing module includes secondary expectation storehouse processing unit, language feature analytic unit, language sentiment analysis
Unit, sensitive content recognition unit and teaching characteristic data generating unit；
Described secondary expectation storehouse processing unit is connected with voice recognition processing module, for establishing secondary corpus, to voice
Turn the text that text unit is generated and carry out secondary analysis；
Described language feature analytic unit is connected with secondary language material library unit, for completing the analysis of language feature；Described
Language feature includes word speed, word；
Described language sentiment analysis unit is connected with language feature analytic unit, for identifying the emotion in secondary corpus
Word, and emotion weight assignment is carried out to emotion word；
Described sensitive content recognition unit is connected with language sentiment analysis unit, for for secondary corpus, establishing special
Sensitive dictionary, and sensitive word is classified；Using cluster analysis, the sensitive word related to semanteme and emotion word are identified, according to
According to two dimensions of time and distance vector value, semantic amendment is carried out, realizes the identification, positioning and mark of sensitive content；
Described teaching characteristic data generating unit is connected with sensitive content recognition unit, for for sensitive content recognition unit
The data generated, generate teaching characteristic data.
6. a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology, it is characterised in that comprise the following steps：
S1., preset classroom index is set, according to the characteristics of this subject, quantizating index setting is carried out to essential of classroom teaching；
S2. data acquisition is carried out, collection classroom, which is attended class, video and completes video to the conversion process of audio；
S3. recognition of face processing, Application on Voiceprint Recognition processing, voice recognition processing and natural language processing are carried out, is carrying out face
Image sampling is carried out to the video of recording during identifying processing, according to recognition of face principle, the facial image in image carried out special
Sign extraction；Blind source signal separation processing is carried out to audio file when carrying out Application on Voiceprint Recognition processing, extracts audio signal, record does not have
There is the period of sound, complete audio classification, and carry out characteristic value mark；When carrying out voice recognition processing, known using voice
Other engine, audio file is subjected to speech recognition, is converted into text, semantic analysis is carried out to content of text, identifies high-frequency content
And generate practical intelligence collection of illustrative plates；When carrying out natural language processing, the content of text generated to voice recognition processing module enters
Row secondary analysis, the analysis of language feature is completed, using cluster analysis, realize the identification, positioning and mark of sensitive content；
S4. analysis is associated, at recognition of face result in S3 steps, Application on Voiceprint Recognition result, speech recognition
Result and natural language processing result are managed, using time value as index, establishes recognition of face processing module, Application on Voiceprint Recognition processing mould
Block, voice recognition processing module, the association analysis view of natural language processing module, and generate the analysis of classroom instruction quantizating index
As a result；
S5. diagnostic analysis is carried out, is carried out for the association analysis result in classroom index and S4 steps preset in S1 steps
Comparative analysis, using time value as dimension, structure learns feelings, knowledge content, teaching process, the association analysis view of teaching characteristic, shape
Into instruction analysis result.
7. a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology according to claim 6, its feature exist
In comprising the following steps at described recognition of face：
S3011. face gathers, and the video of the recording gathered for data acquisition carries out image sampling；
S3012. face characteristic judges, for the human face data gathered in S3011, according to recognition of face principle, in image
Facial image carry out feature extraction, and by characteristic value be put in storage access；
S3013. time tag is added, the face characteristic value extracted for S3013 steps, specific time interval value is set,
Extract student's face characteristic value in each interval time；
S3014. focus conversion is carried out, to S3013 steps, in each sampling interval, student is come back the personnel to listen to the teacher
Quantity, focus are set to 1, and do not come back the personnel amount listened to the teacher（Work attendance number-new line number）, focus is set to 0；
S3015. feelings effect data, the student's focus result conversed for S3014 steps are learned in generation, and feelings effect is learned in generation
Fruit data.
8. a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology according to claim 7, its feature exist
In the processing of described Application on Voiceprint Recognition comprises the following steps：
S3021. audio frequency characteristics value is extracted, the content of text changed for data acquisition, and blind source signal is carried out to audio file
Processing, extract the period of no sound, and recorded time value；It is another to be additionally operable to read audio digital signals, according to（Sampling frequency
Rate, sampled value）Form sampled, be stored in feature list；
S3022. cluster analysis is carried out, the audio frequency characteristics value extracted for S3021 steps, carries out characteristic matching, completes cluster
Analysis；
S3023. classification annotation is carried out, the characteristic value after being matched to S3022 steps is classified, and carries out characteristic value mark；
S3024. time tag is added, the time value of each characteristic value classification is recorded for the classification results of S3023 steps；
S3025. teaching process data are generated, are given birth to for S3021 steps, S3022 steps, S3023 steps and S3024 steps
Into data, generate teaching process data.
9. a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology according to claim 8, its feature exist
In described voice recognition processing comprises the following steps：
S3031. voice turns text, the audio file extracted for data acquisition, using speech recognition technology, by audio text
Part carries out speech recognition, changes into text；
S3032. it is labeled, the content of text generated to S3031 steps is segmented, part-of-speech tagging；
S3033. basic meaning of a word identification, identifies underlying semantics, and the content of identification is put in storage and kept；
S3034. keyword word frequency analysis, semantic analysis is carried out for the content of text of S3031 steps, by TF-IDF algorithms,
High-frequency content is identified, all data are stored according to RDF data form；
S3035. content of courses data are generated, the high-frequency content identified for S3034 steps, generate content of courses data.
10. a kind of teaching diagnostic analysis method of integrated application artificial intelligence technology according to claim 9, its feature exist
In described natural language processing comprises the following steps：
S3041. two expectation storehouse processing, the text generated for voice recognition processing, establish secondary corpus, to text
Carry out secondary analysis；
S3042. language feature is analyzed, and for the secondary corpus of S3041 steps, carries out the analysis of language feature；Described language
Speech feature includes word speed, word；
S3043. language sentiment analysis, the emotion word in secondary corpus is identified, and emotion weight assignment is carried out to emotion word；
S3044. sensitive content identifies, for secondary corpus, establishes special sensitive dictionary, and sensitive word is classified；
Using cluster analysis, identify and semantic related sensitive word and emotion word, foundation two dimensions of time and distance vector value, progress
Semanteme amendment, realizes the identification, positioning and mark of sensitive content；
S3045. teaching characteristic data are generated, the data generated for S3044 steps, generate teaching characteristic data.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710677105.4A CN107609736A (en) | 2017-08-09 | 2017-08-09 | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201710677105.4A CN107609736A (en) | 2017-08-09 | 2017-08-09 | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN107609736A true CN107609736A (en) | 2018-01-19 |
Family
ID=61065076
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201710677105.4A Pending CN107609736A (en) | 2017-08-09 | 2017-08-09 | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN107609736A (en) |
Cited By (14)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596395A (en) * | 2018-04-28 | 2018-09-28 | 北京比特智学科技有限公司 | The distribution method and device of course |
| CN108922288A (en) * | 2018-08-04 | 2018-11-30 | 温州科技职业学院 | A kind of intellectual education terminal system based on big data |
| CN109214664A (en) * | 2018-08-21 | 2019-01-15 | 重庆乐教科技有限公司 | A kind of emotion-directed behavior overall analysis system based on artificial intelligence |
| CN109275046A (en) * | 2018-08-21 | 2019-01-25 | 华中师范大学 | A kind of teaching data mask method based on double video acquisitions |
| CN109359613A (en) * | 2018-10-29 | 2019-02-19 | 四川文轩教育科技有限公司 | A kind of teaching process analysis method based on artificial intelligence |
| CN109447863A (en) * | 2018-10-23 | 2019-03-08 | 广州努比互联网科技有限公司 | A kind of 4MAT real-time analysis method and system |
| CN109636132A (en) * | 2018-11-21 | 2019-04-16 | 武汉邮电科学研究院有限公司 | Evaluate AI analysis system and smart city evaluation method in smart city |
| CN110232343A (en) * | 2019-06-04 | 2019-09-13 | 重庆第二师范学院 | Children personalized behavioral statistics analysis system and method based on latent variable model |
| WO2020010882A1 (en) * | 2018-07-11 | 2020-01-16 | 北京大米科技有限公司 | Data processing method, storage medium and electronic device |
| CN110727800A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Self-adaptive preschool education system and method for children |
| CN110727883A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Method and system for analyzing personalized growth map of child |
| CN111126373A (en) * | 2019-12-23 | 2020-05-08 | 北京中科神探科技有限公司 | Internet short video violation judgment device and method based on cross-modal identification technology |
| CN112116507A (en) * | 2020-09-15 | 2020-12-22 | 深圳市龙飞教育发展有限公司 | Education integration management system |
| CN114743418A (en) * | 2022-04-26 | 2022-07-12 | 简伟广 | Japanese teaching system based on AI intelligence |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN106548788A (en) * | 2015-09-23 | 2017-03-29 | 中国移动通信集团山东有限公司 | A kind of intelligent emotion determines method and system |
| CN106851216A (en) * | 2017-03-10 | 2017-06-13 | 山东师范大学 | A kind of classroom behavior monitoring system and method based on face and speech recognition |
-
2017
- 2017-08-09 CN CN201710677105.4A patent/CN107609736A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN106548788A (en) * | 2015-09-23 | 2017-03-29 | 中国移动通信集团山东有限公司 | A kind of intelligent emotion determines method and system |
| CN105681920A (en) * | 2015-12-30 | 2016-06-15 | 深圳市鹰硕音频科技有限公司 | Network teaching method and system with voice recognition function |
| CN106851216A (en) * | 2017-03-10 | 2017-06-13 | 山东师范大学 | A kind of classroom behavior monitoring system and method based on face and speech recognition |
Cited By (16)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN108596395A (en) * | 2018-04-28 | 2018-09-28 | 北京比特智学科技有限公司 | The distribution method and device of course |
| CN110727800A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Self-adaptive preschool education system and method for children |
| CN110727883A (en) * | 2018-06-29 | 2020-01-24 | 南京芝兰人工智能技术研究院有限公司 | Method and system for analyzing personalized growth map of child |
| WO2020010882A1 (en) * | 2018-07-11 | 2020-01-16 | 北京大米科技有限公司 | Data processing method, storage medium and electronic device |
| CN108922288A (en) * | 2018-08-04 | 2018-11-30 | 温州科技职业学院 | A kind of intellectual education terminal system based on big data |
| CN109214664A (en) * | 2018-08-21 | 2019-01-15 | 重庆乐教科技有限公司 | A kind of emotion-directed behavior overall analysis system based on artificial intelligence |
| CN109275046A (en) * | 2018-08-21 | 2019-01-25 | 华中师范大学 | A kind of teaching data mask method based on double video acquisitions |
| CN109275046B (en) * | 2018-08-21 | 2021-06-18 | 华中师范大学 | Teaching data labeling method based on double video acquisition |
| CN109447863A (en) * | 2018-10-23 | 2019-03-08 | 广州努比互联网科技有限公司 | A kind of 4MAT real-time analysis method and system |
| CN109359613A (en) * | 2018-10-29 | 2019-02-19 | 四川文轩教育科技有限公司 | A kind of teaching process analysis method based on artificial intelligence |
| CN109636132A (en) * | 2018-11-21 | 2019-04-16 | 武汉邮电科学研究院有限公司 | Evaluate AI analysis system and smart city evaluation method in smart city |
| CN110232343A (en) * | 2019-06-04 | 2019-09-13 | 重庆第二师范学院 | Children personalized behavioral statistics analysis system and method based on latent variable model |
| CN110232343B (en) * | 2019-06-04 | 2021-09-28 | 重庆第二师范学院 | Child personalized behavior statistical analysis system and method based on latent variable model |
| CN111126373A (en) * | 2019-12-23 | 2020-05-08 | 北京中科神探科技有限公司 | Internet short video violation judgment device and method based on cross-modal identification technology |
| CN112116507A (en) * | 2020-09-15 | 2020-12-22 | 深圳市龙飞教育发展有限公司 | Education integration management system |
| CN114743418A (en) * | 2022-04-26 | 2022-07-12 | 简伟广 | Japanese teaching system based on AI intelligence |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107609736A (en) | A kind of teaching diagnostic analysis system and method for integrated application artificial intelligence technology | |
| CN110991381B (en) | Real-time classroom student status analysis and indication reminding system and method based on behavior and voice intelligent recognition | |
| Li et al. | The Routledge handbook of second language acquisition and individual differences | |
| CN108281052B (en) | A kind of on-line teaching system and online teaching method | |
| CN106851216B (en) | A kind of classroom behavior monitoring system and method based on face and speech recognition | |
| CN107918821A (en) | Teachers ' classroom teaching process analysis method and system based on artificial intelligence technology | |
| US8682241B2 (en) | Method and system for improving the quality of teaching through analysis using a virtual teaching device | |
| CN107491890A (en) | One kind can quantify Classroom Teaching Quality Assessment system and method | |
| CN115239527B (en) | Teaching behavior analysis system based on knowledge base teaching feature fusion and modeling | |
| CN109697577A (en) | A kind of voice-based Classroom instruction quality evaluation method | |
| CN111027865A (en) | Classroom teaching analysis and quality assessment system and method based on intelligent behavior and expression recognition | |
| CN104978884A (en) | Teaching system of preschool education profession student music theory and solfeggio learning | |
| CN113744872A (en) | Intelligent interactive Alzheimer's disease auxiliary screening system | |
| Cook | An open vocabulary approach for detecting authentic questions in classroom discourse | |
| Wagner et al. | Applying cooperative machine learning to speed up the annotation of social signals in large multi-modal corpora | |
| CN110245253A (en) | A kind of Semantic interaction method and system based on environmental information | |
| CN116050892A (en) | Intelligent education evaluation supervision method based on artificial intelligence | |
| CN116825288A (en) | Autism rehabilitation course recording method and device, electronic equipment and storage medium | |
| Wang | [Retracted] Research on Open Oral English Scoring System Based on Neural Network | |
| Jingning | Speech recognition based on mobile sensor networks application in English education intelligent assisted learning system | |
| CN117078094A (en) | Teacher comprehensive ability assessment method based on artificial intelligence | |
| CN115527404A (en) | Artificial intelligence self-adaptation interactive teaching system | |
| CN113611172A (en) | English listening comprehension training method based on deep learning | |
| CN113505597A (en) | Method, device and storage medium for extracting keywords in video conference | |
| Zhao et al. | Design and Implementation of a Teaching Verbal Behavior Analysis Aid in Instructional Videos |
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 | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: Room 2108 and 2109, No. 563, lianggouling Road, Tianhe District, Guangzhou City, Guangdong Province (office only) Applicant after: GUANGZHOU THINK-HEIGHT INFORMATION TECHNOLOGY Co.,Ltd. Address before: 510640 Guangdong city of Guangzhou province Tianhe District gold Yinglu No. 1 Jin Ying building room 1705 Applicant before: GUANGZHOU THINK-HEIGHT INFORMATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180119 |