CN109308569A - A kind of teaching behavior analysis system and analysis method based on artificial intelligence - Google Patents
A kind of teaching behavior analysis system and analysis method based on artificial intelligence Download PDFInfo
- Publication number
- CN109308569A CN109308569A CN201810936797.4A CN201810936797A CN109308569A CN 109308569 A CN109308569 A CN 109308569A CN 201810936797 A CN201810936797 A CN 201810936797A CN 109308569 A CN109308569 A CN 109308569A
- Authority
- CN
- China
- Prior art keywords
- data
- unit
- teaching behavior
- analysis
- teaching
- 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
- 238000004458 analytical method Methods 0.000 title claims abstract description 114
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 25
- 230000006399 behavior Effects 0.000 claims abstract description 150
- 238000013523 data management Methods 0.000 claims abstract description 15
- 238000012216 screening Methods 0.000 claims abstract description 14
- 238000007405 data analysis Methods 0.000 claims abstract description 13
- 238000013135 deep learning Methods 0.000 claims abstract description 12
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000004088 simulation Methods 0.000 claims abstract description 6
- 238000012360 testing method Methods 0.000 claims abstract description 6
- 230000003542 behavioural effect Effects 0.000 claims description 45
- 238000011156 evaluation Methods 0.000 claims description 20
- 230000010354 integration Effects 0.000 claims description 16
- 238000013500 data storage Methods 0.000 claims description 15
- 210000000352 storage cell Anatomy 0.000 claims description 14
- 238000006116 polymerization reaction Methods 0.000 claims description 8
- 238000007726 management method Methods 0.000 claims description 7
- 238000000034 method Methods 0.000 claims description 6
- 238000004891 communication Methods 0.000 claims description 4
- 238000011157 data evaluation Methods 0.000 claims description 3
- 238000013136 deep learning model Methods 0.000 claims description 3
- 238000001914 filtration Methods 0.000 abstract 1
- 238000011161 development Methods 0.000 description 5
- 230000036651 mood Effects 0.000 description 5
- 238000003012 network analysis Methods 0.000 description 4
- 238000010586 diagram Methods 0.000 description 3
- 230000000694 effects Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000005540 biological transmission Effects 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 0.000 description 1
- 238000004321 preservation Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000009467 reduction Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- XLYOFNOQVPJJNP-UHFFFAOYSA-N water Substances O XLYOFNOQVPJJNP-UHFFFAOYSA-N 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
- G06Q10/06398—Performance of employee with respect to a job function
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Human Resources & Organizations (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Administration (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Educational Technology (AREA)
- Marketing (AREA)
- Theoretical Computer Science (AREA)
- Development Economics (AREA)
- Entrepreneurship & Innovation (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Operations Research (AREA)
- Game Theory and Decision Science (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Electrically Operated Instructional Devices (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses a kind of teaching behavior analysis system and analysis method based on artificial intelligence, the teaching behavior analysis system includes Data Management Unit, data processing unit and data evaluate and test unit, it specifically include the teaching behavior data video acquisition unit for collecting instructor, time shaft for creating multiple time shaft subelements in teaching behavior data establishes unit, for filtering out the data screening unit of a kind of teaching behavior characteristic respectively on each time shaft subelement, the data analysis unit analyzed teaching behavior characteristic is used for based on artificial intelligence.Teaching behavior analysis system of the invention uploads classroom instruction video by instructor, and automatic data aggregate, signature analysis, deep learning and modeling Simulation are carried out to the teaching behavior feature filtered out from the instructional video that creation has multiple time shafts arranged side by side based on artificial intelligence, so that teaching behavior analysis system is made detailed, accurate analysis to the teaching behavior of instructor.
Description
Technical field
The present invention relates to educational system technical fields, and in particular to a kind of teaching behavior analysis system based on artificial intelligence
And analysis method.
Background technique
A kind of effective teaching activities form for commenting class movable (classroom observing) to be General Promotion Specialized Quality is listened, it is extensive
Apply normal student culture and teacher continuing education in, be it is a kind of most directly, most specifically, most frequently be also it is most effective research mention
The ways and means of high Classroom Teaching listen that comment class be indispensable important ring in entire classroom instruction course of reforms
Section.
Listen that comment class mode (classroom observing) be the classroom being directly entered just at school at present, observer listens to the teacher at scene and passes through
Paper pen etc. records observed content, and correct problems is just needed to carry out classification, Reasons with the person of teaching after class, and solution is discussed.This biography
For the mode of system there are three main problem, first is the limitation of when and where, and all observation activities must during class hours and religion
It is completed in room.Second is that classroom behavior is written in water, lacks the complete documentation to classroom that can be faced jointly.So observer
Many opinions be all usually that comparison is generally and fuzzy, session discussing entertains defence mood to the person of giving lessons often after class.Third
It is not record evaluation result and evidence, the person of giving lessons has no basis in self-reflection, cannot record the person's of giving lessons history
Growth track and analysis teacher's law of development.
Summary of the invention
The embodiment of the present invention is designed to provide a kind of teaching behavior analysis system based on artificial intelligence and analysis side
Method, to solve the problems, such as existing teaching behavior analysis method, there are above-mentioned insufficient.
To achieve the above object, the embodiment of the present invention provides a kind of teaching behavior analysis system based on artificial intelligence,
Be characterized in that: the teaching behavior analysis system includes that Data Management Unit, data processing unit and data evaluate and test unit,
The Data Management Unit includes video acquisition unit, and the video acquisition unit is used to collect the teaching of instructor
Behavioral data；
The data processing unit includes that information uploading unit, data storage cell and time shaft establish unit, described
Teaching behavior data are uploaded to data storage list for connecting Data Management Unit and data storage cell by information uploading unit
Member, the time shaft establishes unit and obtains teaching behavior data from data storage cell, and creates in teaching behavior data
Multiple time shaft subelements arranged side by side；
The data evaluation and test unit includes data screening unit, data analysis unit and data integral unit, the data
Screening unit is used to obtain the teaching behavior data that creation has multiple time shaft subelements, and in each time shaft subelement
A kind of teaching behavior characteristic is filtered out in teaching behavior data, the data analysis unit is for obtaining teaching behavior spy
Data are levied, and teaching behavior is generated to the analysis of teaching behavior characteristic, study based on artificial intelligence and analyzes data, the data
Integral unit is for obtaining the teaching behavior analysis data on teaching behavior data and multiple time shaft subelements respectively and generating
Assessment report.
By using above-mentioned technical proposal, instructor's record and upload classroom teaching picture recording, establishing unit by time shaft is
The multiple time shafts arranged side by side of video creation are filtered out in the instructional video on each time shaft respectively using data screening unit
Important teaching behavior feature makes in each time shaft to include a kind of teaching behavior feature, by based on artificial intelligence
Data analysis unit carries out automatic data aggregate, signature analysis, deep learning and modeling to the teaching behavior feature filtered out
Simulation, makes teaching behavior analysis system make detailed, accurate analysis to the teaching behavior of instructor, and by instructor's
Multiple instructional video carries out network analysis, convenient for recording growth track and the analysis teacher's law of development of instructor's history.Its
Middle Data Integration unit can also combine evaluation result with video evidence, recognize instructor more intuitively and oneself award
Class hour there are the problem of, reduce instructor after class session discussing when defence mood, and resulting self-reflection or sight
Examining becomes really objective and more meaningful.
Further, the Data Management Unit further includes scale administrative unit, and the scale administrative unit is used for typing
Multiple teaching behavior characteristic indexs simultaneously generate evaluation charter according to multiple teaching behavior characteristic indexs.
Further, the data screening unit includes identification label subelement, and the identification label subelement is for obtaining
Creation is taken there are the teaching behavior data of multiple time shaft subelements, and by observer according to multiple teaching behaviors in evaluation charter
Characteristic index marks a kind of teaching behavior feature, the identification mark on each time shaft subelement of teaching behavior data
The teaching behavior feature that note subelement marks according to the observation generates behavioural characteristic flag data.
Further, the data analysis unit includes being ground based on the study subelement of deep learning algorithm and behavioural analysis
Sentence subelement, the behavioural characteristic flag data that subelement is generated for obtaining identification label subelement is studied and judged in the behavioural analysis,
And comprehensive analysis is carried out to teaching behavior data according to behavioural characteristic flag data and generates behavioural characteristic analysis data, the study
Subelement generates analogue data for obtaining behavioural characteristic analysis data and analyzing data deep learning model building according to behavioural characteristic.
Make observer according to evaluation amount after system time shaft multiple for video creation by using above-mentioned technical proposal
Multiple teaching behavior characteristic indexs in table mark a kind of teaching on each time shaft subelement of teaching behavior data
Behavioural characteristic studies and judges subelement by behavioural analysis and carries out data aggregate to the teaching behavior feature marked on each time shaft, and
So that behavioural analysis is studied and judged subelement according to the data of polymerization and comprehensive analysis is carried out to instructional video, using based on deep learning algorithm
Study subelement learnt, developed and given birth to modeling to analysis result and generate ideal classroom instruction behavior, make system anti-
During multiple use, the result of mode and law of development analysis to instructor's teaching behavior is more acurrate.
Further, the Data Management Unit further includes role management unit, and the role management unit obtains creation
There are the teaching behavior data of multiple time shaft subelements, and generates sight class task list according to multiple teaching behavior data.
By using above-mentioned technical proposal, sight class task list is generated using role management unit, sight class task is distributed into sight
The person of examining, then identification label is carried out by observer, so that observer is can choose suitable time and place completion work.
Further, the Data Management Unit further includes the information transmitting unit with communication module, the information hair
Send unit for assessment report and teaching behavior data that Data Integration unit generates to be sent to learner.
By using above-mentioned technical proposal, the assessment report for being generated Data Integration unit using information receiving unit and religion
It learns video and is sent to learner, wherein learner may include that mobile terminal or PC terminal or APP etc. realize that information is mutual
Dynamic receiving device, Data Integration unit can judge the quality of instructional video according to the assessment report of generation, for having higher rating
Instructional video, preferentially learner can be pushed to, convenient for improving the quality of teaching.
The embodiment of the present invention also provides a kind of teaching behavior analysis system and analysis method based on artificial intelligence, feature
It is, the described method comprises the following steps:
The evaluation charter of S1, the instructional video for uploading instructor to data storage cell respectively and setting；
It is that instructional video creates multiple time shafts arranged side by side that S2, the time shaft, which establish unit, by observer according to evaluation amount
Behavioural characteristic index on table identifies a kind of teaching behavior feature and is marked in the instructional video on each time shaft and commented
Valence；
S3, the behavioural analysis study and judge the teaching row that subelement polymerization observer marks on each time shaft of instructional video
It is characterized, and comprehensive characteristics analysis is carried out to instructional video according to the teaching behavior characteristic of polymerization；
S4, the study subelement are based on deep learning algorithm, and the signature analysis for studying and judging subelement according to behavioural analysis is deep
Degree study, and build to touch according to learning outcome and simulate ideal classroom instruction behavior；
S5, the Data Integration unit integrate behavioural analysis and study and judge the signature analysis result of subelement and learn subelement
Analog result generates assessment report, and assessment report and the instructional video of analysis are carried out matching storage.
Further, in the step S2, the time shaft in instructional video is the time shaft that can be retracted repeatedly, makes observer
Viewing instructional video is identified and is marked to the multiple teaching behavior feature of instructional video progress on time roller unit repeatedly.
Further, in the step S5, Data Integration unit is by information transmitting unit by assessment report and outstanding
Teaching class example is pushed to learner.
The embodiment of the present invention has the advantages that
1, teaching behavior analysis system of the invention is recorded and is uploaded classroom teaching picture recording by instructor, is built by time shaft
Vertical unit is the multiple time shafts arranged side by side of video creation, utilizes the data screening unit instructional video on each time shaft respectively
In filter out important teaching behavior feature, make in each time shaft to include a kind of teaching behavior feature, by being based on people
The data analysis unit of work intelligence carries out automatic data aggregate, signature analysis, depth to the teaching behavior feature filtered out
Practise and modeling Simulation, teaching behavior analysis system made to make detailed, accurate analysis to the teaching behavior of instructor, and by pair
The multiple instructional video of instructor carries out network analysis, convenient for recording growth track and the analysis teacher's growth of instructor's history
Rule；
2, teaching behavior analysis system of the invention can combine evaluation result with video evidence, make instructor
More intuitively recognize when oneself is given lessons there are the problem of, and reduce instructor after class session discussing when defence mood, make
The resulting self-reflection of instructor or observation become really objective and more meaningful；
3, teaching behavior analysis system of the invention can make observer watch instructional video repeatedly to time roller unit
On instructional video carry out multiple teaching behavior feature and identify and mark, spending convenient for observer can observe, more more times
Few time records the note, and makes observer that suitable time and place completion work may be selected by task distribution.
Detailed description of the invention
Fig. 1 is the main flow schematic diagram of teaching behavior analysis system provided in an embodiment of the present invention.
Fig. 2 is the flow diagram for the teaching behavior analysis system that the embodiment of the present invention 1 provides.
Fig. 3 is the flow diagram for the teaching behavior analysis system that the embodiment of the present invention 2 provides.
Specific embodiment
The following examples are used to illustrate the present invention, but are not intended to limit the scope of the present invention..
Embodiment 1
As depicted in figs. 1 and 2, the teaching behavior analysis system based on artificial intelligence that the present invention provides a kind of, including number
Unit is evaluated and tested according to administrative unit, data processing unit and data.
Data Management Unit includes video acquisition unit, and video acquisition unit is used to collect the teaching behavior number of instructor
According to wherein video acquisition unit is chosen as video camera, camera, mobile phone or camera etc., and there is the hardware for recording function of taking pictures to set
It is standby, when instructor imparts knowledge to students on classroom, entire teaching process is recorded under video and preservation using video acquisition unit
Come, the teaching behavior in video mainly includes that the mutual-action behavior between the behavioural characteristic and instructor and learner of instructor is special
Sign；
Data processing unit includes that information uploading unit, data storage cell and time shaft establish unit, wherein information
Teaching behavior data are uploaded to data storage cell for connecting Data Management Unit and data storage cell by uploading unit, when
Between axis establish unit and obtain teaching behavior data from data storage cell, and create in teaching behavior data multiple arranged side by side
Time shaft subelement；
Data evaluation and test unit includes data screening unit, data analysis unit and data integral unit, wherein data screening
Unit is used to obtain the teaching behavior data that creation has multiple time shaft subelements, and the teaching in each time shaft subelement
Filter out a kind of teaching behavior characteristic on behavioral data, data analysis unit is according to the teaching behavior characteristic of acquisition
According to based on artificial intelligence to the analysis of teaching behavior characteristic, study generation teaching behavior analysis data, and by Data Integration list
Member obtains the teaching behavior analysis data on teaching behavior data and multiple time shaft subelements respectively and generates assessment report, and
Assessment report and the instructional video of analysis are subjected to matching storage, by combining evaluation result with video evidence, make to teach
Scholar more intuitively recognize when oneself is given lessons there are the problem of, reduce instructor after class session discussing when defence mood,
And resulting self-reflection or observation become really objective and more meaningful.
As described above, can be the connection types connection such as data, circuit or communication between each unit, when instructor's record and on
After passing classroom teaching picture recording, establishing unit by time shaft is the multiple time shafts arranged side by side of video creation, utilizes data screening unit
Important teaching behavior feature is filtered out in the instructional video on each time shaft respectively, makes to include one in each time shaft
The teaching behavior feature of class carries out certainly the teaching behavior feature filtered out by the data analysis unit based on artificial intelligence
Dynamic data aggregate, signature analysis, deep learning and modeling Simulation, makes teaching behavior analysis system to the teaching behavior of instructor
Detailed, accurate analysis is made, and network analysis is carried out by the multiple instructional video to instructor, instructor goes through convenient for record
The growth track of history and analysis teacher's law of development.
Embodiment 2
Difference from Example 1 is, as shown in figure 3, Data Management Unit further includes scale administrative unit, wherein measuring
Table administrative unit generates evaluation charter for the multiple teaching behavior characteristic indexs of typing and according to multiple teaching behavior characteristic indexs.
Data screening unit includes identification label subelement, and identification label subelement has multiple time shafts for obtaining creation
The teaching behavior data of subelement, and by observer according to multiple teaching behavior characteristic indexs in evaluation charter in teaching behavior
A kind of teaching behavior feature is marked on each time shaft subelement of data, marks identification label subelement according to the observation
Remember that teaching behavior feature out generates behavioural characteristic flag data.
Data analysis unit include subelement is studied and judged based on the study subelement of deep learning algorithm and behavioural analysis, wherein
The behavioural characteristic flag data that subelement is generated for obtaining identification label subelement is studied and judged in behavioural analysis, and according to behavioural characteristic
Flag data carries out comprehensive analysis to teaching behavior data and generates behavioural characteristic analysis data, and study subelement is for obtaining behavior
Feature analysis data simultaneously analyzes data deep learning model building generation analogue data according to behavioural characteristic.When system is that video creation is more
After a time shaft, by observer according to multiple teaching behavior characteristic indexs in evaluation charter teaching behavior data it is each when
Between a kind of teaching behavior feature is marked on roller unit, subelement is studied and judged to marking on each time shaft by behavioural analysis
Teaching behavior feature carry out data aggregate, and according to the data of polymerization make behavioural analysis study and judge subelement to instructional video carry out
Comprehensive analysis is learnt, developed and is given birth to modeling to analysis result using the study subelement based on deep learning algorithm and generated
Ideal classroom instruction behavior, makes system during Reusability, to the mode and law of development of instructor's teaching behavior
The result of analysis is more acurrate.
Embodiment 3
Difference from Example 1 is, as shown in figure 3, Data Management Unit further includes role management unit, described
Business administrative unit obtains the teaching behavior data that creation has multiple time shaft subelements, and is generated according to multiple teaching behavior data
Sight class task list generates sight class task list using role management unit and sight class task is distributed to observer, makes observer can be with
Suitable time and place is selected to complete work.
Embodiment 5
Difference from Example 1 is, as shown in figure 3, Data Management Unit further includes the information with communication module
Transmission unit, information transmitting unit are used to assessment report and teaching behavior data that Data Integration unit generates being sent to study
Assessment report and instructional video that Data Integration unit generates are sent to learner's end using information receiving unit by person's terminal
End, wherein learner may include the receiving device that mobile terminal or PC terminal or APP etc. realize information interaction, Data Integration
Unit judges the quality of instructional video according to the assessment report of generation, can push preferentially for the instructional video having higher rating
To learner, convenient for improving the quality of teaching.
Embodiment 6
The embodiment of the present invention also provides a kind of teaching behavior analysis system and analysis method based on artificial intelligence, feature
It is, the described method comprises the following steps:
The evaluation charter of S1, the instructional video for uploading instructor to data storage cell respectively and setting；
It is that instructional video creates multiple time shafts arranged side by side that S2, the time shaft, which establish unit, by observer according to evaluation amount
Behavioural characteristic index on table identifies a kind of teaching behavior feature and is marked in the instructional video on each time shaft and commented
Valence；
Specifically, the time shaft in instructional video is the time shaft that can be retracted repeatedly, observer is made to watch teaching view repeatedly
Frequently the multiple teaching behavior feature of instructional video progress on time roller unit is identified and is marked, spending convenient for observer can be more
More time is observed, the less time records the note.
S3, the behavioural analysis study and judge the teaching row that subelement polymerization observer marks on each time shaft of instructional video
It is characterized, and comprehensive characteristics analysis is carried out to instructional video according to the teaching behavior characteristic of polymerization；
S4, the study subelement are based on deep learning algorithm, and the signature analysis for studying and judging subelement according to behavioural analysis is deep
Degree study, and build to touch according to learning outcome and simulate ideal classroom instruction behavior；
S5, the Data Integration unit integrate behavioural analysis and study and judge the signature analysis result of subelement and learn subelement
Analog result generates assessment report, and assessment report and the instructional video of analysis are carried out matching storage.
Wherein Data Integration unit can also be pushed assessment report and outstanding teaching class example by information transmitting unit
To learner.
Teaching behavior analysis system of the invention is recorded and is uploaded classroom teaching picture recording by instructor, is established by time shaft
Unit is the multiple time shafts arranged side by side of video creation, using data screening unit respectively in the instructional video on each time shaft
Important teaching behavior feature is filtered out, makes to include a kind of teaching behavior feature in each time shaft, by based on artificial
The data analysis unit of intelligence carries out automatic data aggregate, signature analysis, deep learning to the teaching behavior feature filtered out
And modeling Simulation, so that teaching behavior analysis system is made detailed, accurate analysis to the teaching behavior of instructor, and by religion
The multiple instructional video of scholar carries out network analysis, convenient for recording the growth track of instructor's history and analyzing teacher into calipers
Rule, and this system can combine evaluation result with video evidence, reduction instructor after class session discussing when
Mood is defendd, the resulting self-reflection of instructor or observation is made to become really objective and more meaningful.
Although above having used general explanation and specific embodiment, the present invention is described in detail, at this
On the basis of invention, it can be made some modifications or improvements, this will be apparent to those skilled in the art.Therefore,
These modifications or improvements without departing from theon the basis of the spirit of the present invention are fallen within the scope of the claimed invention.
Claims (9)
1. a kind of teaching behavior analysis system based on artificial intelligence, it is characterised in that: the teaching behavior analysis system includes
Data Management Unit, data processing unit and data evaluate and test unit,
The Data Management Unit includes video acquisition unit, and the video acquisition unit is used to collect the teaching behavior of instructor
Data；
The data processing unit includes that information uploading unit, data storage cell and time shaft establish unit, the information
Teaching behavior data are uploaded to data storage cell for connecting Data Management Unit and data storage cell by uploading unit, institute
State time shaft and establish unit and obtain teaching behavior data from data storage cell, and create in teaching behavior data it is multiple simultaneously
The time shaft subelement of column；
The data evaluation and test unit includes data screening unit, data analysis unit and data integral unit, the data screening
Unit is used to obtain the teaching behavior data that creation has multiple time shaft subelements, and the teaching in each time shaft subelement
A kind of teaching behavior characteristic is filtered out on behavioral data, the data analysis unit is for obtaining teaching behavior characteristic
According to, and teaching behavior is generated to the analysis of teaching behavior characteristic, study based on artificial intelligence and analyzes data, the Data Integration
Unit is for obtaining the teaching behavior analysis data on teaching behavior data and multiple time shaft subelements respectively and generating assessment
Report.
2. a kind of teaching behavior analysis system based on artificial intelligence according to claim 1, it is characterised in that: the number
It further include scale administrative unit according to administrative unit, the scale administrative unit is for the multiple teaching behavior characteristic indexs of typing and root
Evaluation charter is generated according to multiple teaching behavior characteristic indexs.
3. a kind of teaching behavior analysis system based on artificial intelligence according to claim 1, it is characterised in that: the number
It include identification label subelement according to screening unit, the identification label subelement has multiple time shaft subelements for obtaining creation
Teaching behavior data, and by observer according to multiple teaching behavior characteristic indexs in evaluation charter in teaching behavior data
A kind of teaching behavior feature is marked on each time shaft subelement, the identification label subelement marks according to the observation
Teaching behavior feature generate behavioural characteristic flag data.
4. a kind of teaching behavior analysis system based on artificial intelligence according to claim 1, it is characterised in that: the number
It include that subelement is studied and judged based on the study subelement of deep learning algorithm and behavioural analysis according to analytical unit, the behavioural analysis is ground
Sentence the behavioural characteristic flag data that subelement is generated for obtaining identification label subelement, and according to behavioural characteristic flag data pair
Teaching behavior data carry out comprehensive analysis and generate behavioural characteristic analysis data, and the study subelement is for obtaining behavioural characteristic point
It analyses data and data deep learning model building is analyzed according to behavioural characteristic and generate analogue data.
5. a kind of teaching behavior analysis system based on artificial intelligence according to claim 1, it is characterised in that: the number
It further include role management unit according to administrative unit, the role management unit obtains the teaching that creation has multiple time shaft subelements
Behavioral data, and sight class task list is generated according to multiple teaching behavior data.
6. a kind of teaching behavior analysis system based on artificial intelligence according to claim 1, it is characterised in that: the number
It further include that there is the information transmitting unit of communication module according to administrative unit, the information transmitting unit is used for Data Integration unit
The assessment report and teaching behavior data of generation are sent to learner.
7. a kind of teaching behavior analysis system and analysis side based on artificial intelligence described in -6 any one according to claim 1
Method, which is characterized in that the analysis method the following steps are included:
The evaluation charter of S1, the instructional video for uploading instructor to data storage cell respectively and setting；
It is that instructional video creates multiple time shafts arranged side by side that S2, the time shaft, which establish unit, by observer according on evaluation charter
Behavioural characteristic index identify a kind of teaching behavior feature in the instructional video on each time shaft and mark evaluation；
It is special that S3, the behavioural analysis study and judge the teaching behavior that subelement polymerization observer marks on each time shaft of instructional video
Sign, and comprehensive characteristics analysis is carried out to instructional video according to the teaching behavior characteristic of polymerization；
S4, the study subelement are based on deep learning algorithm, and the signature analysis depth of subelement is studied and judged according to behavioural analysis
It practises, and builds to touch according to learning outcome and simulate ideal classroom instruction behavior；
S5, the Data Integration unit integrate behavioural analysis and study and judge the signature analysis result of subelement and learn the simulation of subelement
As a result assessment report is generated, and assessment report and the instructional video of analysis are subjected to matching storage.
8. a kind of teaching behavior analysis system and analysis method based on artificial intelligence according to claim 7, feature
Be: in the step S2, the time shaft in instructional video is the time shaft that can be retracted repeatedly, and observer is made to watch teaching repeatedly
Video is identified and is marked to the multiple teaching behavior feature of instructional video progress on time roller unit.
9. a kind of teaching behavior analysis system and analysis method based on artificial intelligence according to claim 7, feature
Be: in the step S5, Data Integration unit is pushed assessment report and outstanding teaching class example by information transmitting unit
To learner.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810936797.4A CN109308569A (en) | 2018-08-16 | 2018-08-16 | A kind of teaching behavior analysis system and analysis method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810936797.4A CN109308569A (en) | 2018-08-16 | 2018-08-16 | A kind of teaching behavior analysis system and analysis method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN109308569A true CN109308569A (en) | 2019-02-05 |
Family
ID=65223960
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810936797.4A Pending CN109308569A (en) | 2018-08-16 | 2018-08-16 | A kind of teaching behavior analysis system and analysis method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN109308569A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767662A (en) * | 2019-03-13 | 2019-05-17 | 上海乂学教育科技有限公司 | It is suitble to the content verification system of adaptive teaching |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120040326A1 (en) * | 2010-08-12 | 2012-02-16 | Emily Larson-Rutter | Methods and systems for optimizing individualized instruction and assessment |
| CN104268188A (en) * | 2014-09-17 | 2015-01-07 | 广州迅云教育科技有限公司 | Method and system for classroom teaching and learning behavior analysis in informational environment |
| CN107832936A (en) * | 2017-10-31 | 2018-03-23 | 北京新学道教育科技有限公司 | A kind of E-learning evaluation method and system based on cloud data |
| CN107918821A (en) * | 2017-03-23 | 2018-04-17 | 广州思涵信息科技有限公司 | Teachers ' classroom teaching process analysis method and system based on artificial intelligence technology |
| CN108090857A (en) * | 2017-12-29 | 2018-05-29 | 复旦大学 | A kind of multi-modal student classroom behavior analysis system and method |
-
2018
- 2018-08-16 CN CN201810936797.4A patent/CN109308569A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| US20120040326A1 (en) * | 2010-08-12 | 2012-02-16 | Emily Larson-Rutter | Methods and systems for optimizing individualized instruction and assessment |
| CN104268188A (en) * | 2014-09-17 | 2015-01-07 | 广州迅云教育科技有限公司 | Method and system for classroom teaching and learning behavior analysis in informational environment |
| CN107918821A (en) * | 2017-03-23 | 2018-04-17 | 广州思涵信息科技有限公司 | Teachers ' classroom teaching process analysis method and system based on artificial intelligence technology |
| CN107832936A (en) * | 2017-10-31 | 2018-03-23 | 北京新学道教育科技有限公司 | A kind of E-learning evaluation method and system based on cloud data |
| CN108090857A (en) * | 2017-12-29 | 2018-05-29 | 复旦大学 | A kind of multi-modal student classroom behavior analysis system and method |
Non-Patent Citations (1)
| Title |
|---|
| 图灵主编: "《新概念中文Flash MX 2004实用教程》", 30 September 2004, 上海科学普及出版社 * |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109767662A (en) * | 2019-03-13 | 2019-05-17 | 上海乂学教育科技有限公司 | It is suitble to the content verification system of adaptive teaching |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Walid et al. | Construction of the assessment concept to measure students' high order thinking skills | |
| Frejd | Modes of modelling assessment—A literature review | |
| Joan | Flexible Learning as New Learning Design in Classroom Process to Promote Quality Education. | |
| Derry | Video research in classroom and teacher learning (Standardize that!) | |
| CN105006181A (en) | Customized learning device and method | |
| Önger et al. | An investigation into digital literacy views of social studies preservice teachers in the context of authentic learning | |
| CN110443730A (en) | Grinding based on SAAS learns service system and device | |
| Khine | Structural equation modeling approaches in educational research and practice | |
| Pasek et al. | Education needs in research data management for science-based disciplines: Self-assessment surveys of graduate and faculty at two public universities | |
| CN110232343A (en) | Children personalized behavioral statistics analysis system and method based on latent variable model | |
| Sajja et al. | Integrating AI and Learning Analytics for Data-Driven Pedagogical Decisions and Personalized Interventions in Education | |
| Liu et al. | Beyond Log Files: Using Multi-Modal Data Streams towards Data-Driven KC Model Improvement. | |
| Monita et al. | The Dynamics of Affective Assessment in MI Schools: Challenges and Solutions | |
| CN109308569A (en) | A kind of teaching behavior analysis system and analysis method based on artificial intelligence | |
| Meerah | Readiness of preparing postgraduate students in pursuit of their doctoral programme | |
| Siy et al. | Sparcs: A personalized problem-based learning approach for developing successful computer science learning experiences in middle school | |
| Zaric et al. | ILSA–an integrated learning styles analytics system | |
| Alías et al. | The impact of online teaching on Geology degree programs during COVID-19: A case study from the University of Barcelona (Spain) | |
| Irish et al. | Data Explorations: Secondary Students’ Knowledge, Skills and Attitudes Toward Working with Data | |
| Ebrahimzadeh et al. | Portfolio assessment as a window into reading development | |
| Hamidani | Ethnographic Research | |
| Khanare | Experiences and practices of form three integrated science teachers with regard to outcomes and assessment strategies: a case study of two schools in Lesotho. | |
| Syahputra et al. | GAMIFICATION ACTIVITIES ENGAGING PROSPECTIVE ELEMENTARY TEACHERS DURING ONLINE LEARNING | |
| Golja et al. | Towards understanding the development of 21st century capabilities: A scoping review of critical thinking | |
| CN117455126B (en) | Ubiquitous practical training teaching and evaluation management system and method |
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: 20190205 |
|
| RJ01 | Rejection of invention patent application after publication |