CN106205244A - Intelligent Computer Assist Instruction System based on information fusion Yu machine learning - Google Patents
Intelligent Computer Assist Instruction System based on information fusion Yu machine learning Download PDFInfo
- Publication number
- CN106205244A CN106205244A CN201610515579.4A CN201610515579A CN106205244A CN 106205244 A CN106205244 A CN 106205244A CN 201610515579 A CN201610515579 A CN 201610515579A CN 106205244 A CN106205244 A CN 106205244A
- Authority
- CN
- China
- Prior art keywords
- knowledge
- teaching
- student
- learning
- data
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B5/00—Electrically-operated educational appliances
- G09B5/08—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations
- G09B5/14—Electrically-operated educational appliances providing for individual presentation of information to a plurality of student stations with provision for individual teacher-student communication
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N20/00—Machine learning
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Software Systems (AREA)
- Educational Technology (AREA)
- Business, Economics & Management (AREA)
- Artificial Intelligence (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Data Mining & Analysis (AREA)
- Evolutionary Computation (AREA)
- Medical Informatics (AREA)
- Educational Administration (AREA)
- Computing Systems (AREA)
- General Engineering & Computer Science (AREA)
- Mathematical Physics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
A kind of Intelligent Computer Assist Instruction System based on information fusion Yu machine learning, including teaching process information fusion subsystem and teaching simulation executive subsystem;Described teaching process information fusion subsystem, for object, material and instrument key element involved in teaching process are carried out multi dimensional object information retrieval, process destructuring incomplete data, eliminate the coupled noise between each achievement data and associated redundant data, provide metadata support for teaching simulation executive subsystem;Described teaching simulation executive subsystem, excavates for the metadata uploading teaching process information fusion subsystem and integrates, the execution link involved by simulation teaching process;According to the evaluation of students ' learning performance and current teaching resource configuring condition, it is achieved Automatic Optimal and the dynamic dispatching to field research process.The present invention provides the Intelligent Computer Assist Instruction System based on information fusion Yu machine learning that a kind of intellectuality is higher, the suitability is good.
Description
Technical field
The present invention relates to computer-aided instruction field, especially relate to towards intelligence based on information fusion Yu machine learning
The design implementation method of energy computer aided instruction system.
Background technology
Computer-aided instruction (CAI) is the function utilizing advanced information technology such as mobile computing, multimedia, the network interconnection
With feature, utilize area of computer aided teacher to complete each teaching link, and by the interacting activity between computer, swash
Send out student learning enthusiasm and initiative, help student more effectively to learn, thus improve the quality of teaching.In this teaching shape
In formula, computer is primarily used to present instructional objectives, focal points and difficult point, record student learning situation, control student
The information such as study schedule, computer can receive various information by input equipment under the control of teaching software, and to it
It is analyzed judging, is provided with information targetedly according to judgement, export finally by outut device, show result.Make
With CAI system, the beneficially performance of cognitive subject effect, provide technical basis for formulating scientific and reasonable teaching method strategy;
The multimedia messages such as image that it is provided, sound, animation are conducive to acquisition and the holding of student knowledge, reach to improve teaching effect
The purpose of fruit.
It is fast-developing and perfect that the continuous progress and development of computer and network technology makes CAI technology have also been obtained;And
Being continuously introduced into of the new theory of many association areas, new method and new technique, the research contents also making CAI is the abundantest.When
The public communication tool that front the Internet (Internet) has necessitated, digitized campus network (DCN) obtains in education sector
Extensive application and popularization, and education, teaching process are produced profound influence.J.Foster et al. sets based on NeXT work station
Meter achieves the Long-Distance CAI System towards large scale integrated circuit.V.R.Frank&C.Karin proposes a kind of many based on network
The CAI system implementation method of media, and demonstrate its effectiveness in terms of the teaching in terms of computer graphics with advanced
Property.K.L.Li&J.Cheng proposes a kind of CAI implementation method based on WWW, has obtained relatively in the teaching of assembler language
Good application.Jiang Tiehai proposes a kind of Interpretation CAI implementation method based on .NET, and successfully solves the choosing of magnanimity material
Select, the problem such as multimedia breakpoint setup.DSS principle and technical method thereof are introduced CAI field by M.Li, and at tool
Body teaching practice achieves certain achievement.
According to the finding of above-mentioned document, CAI technology focuses mostly in multimedia teaching field in its early stage of development,
Make teaching implementation means more abundant, lively, thus improve teaching efficiency and quality;The introducing of networking technology is widened
The efficient working range of CAI so that it is be significantly increased in terms of the controlled range imparted knowledge to students, real-time, interactivity, but simply in reality
Improvement in terms of existing mode and development, do not have internal to change for the inherent mechanism of CAI.And along with modern science and technology
Progress and development, the requirement for higher education is more and more higher, especially in terms of medical speciality education, it is desirable to can be complete
Many is become to have study and the intensive training task of more highly difficult professional field knowledge.In this case, traditional CAI skill
Art cannot meet the basic demand of modern high professional education, therefore occurs in that computer supported education (CSE) concept, is i.e. working as
Before under the professional teaching requirement condition that day by day improves, need towards different discipline background, formulate different teaching coping strategys;
This computer-chronograph is not the most the ancillary technique in teaching process, and develops into critical support technology.
Summary of the invention
In order to overcome the deficiency that intellectuality is relatively low, the suitability is poor of existing computer-aided instruction mode, the present invention carries
For the Intelligent Computer Assist Instruction System based on information fusion Yu machine learning that a kind of intellectuality is higher, the suitability is good.
The technical solution adopted for the present invention to solve the technical problems is:
A kind of Intelligent Computer Assist Instruction System based on information fusion Yu machine learning, described intelligent computer-assisted
Teaching system includes teaching process information fusion subsystem and teaching simulation executive subsystem;
Described teaching process information fusion subsystem, for object, material and instrument involved in teaching process
Key element carries out multi dimensional object information retrieval, processes destructuring incomplete data, eliminate coupled noise between each achievement data with
Associated redundant data, provides metadata support for teaching simulation executive subsystem;
Described teaching simulation executive subsystem, is carried out for the metadata uploading teaching process information fusion subsystem
Excavate and integrate, the execution link involved by simulation teaching process;According to the evaluation of students ' learning performance and money of currently imparting knowledge to students
Source configuring condition, it is achieved Automatic Optimal and the dynamic dispatching to field research process.
Further, in described teaching process information fusion subsystem, the process of teaching process use processing is as follows:
1. determine that a concrete instructional class, as target, obtains the base of student by place universities and colleges educational administration management system
This file data, learns edge course, culture background information to it and carries out expanding with perfect, and the form of data record carries out table
State;
2. by the way of interview with questionnaire, the student information data that educational administration management system does not comprises is gathered, according to number
Carry out layout and preliminary normalization according to storehouse third normal form (3NF), set up the Students ' Learning information data table of extension;
3. use static mathematics statistic algorithm to carry out characteristic extraction, obtain direction student and learning edge structure, knowledge
Characteristic in terms of deposit, memory character and learning strategy, and obtain on this basis assembly average, variance, standard deviation,
Auto-correlation, cross-correlation and data-bias derivative data item;
4. the data object using rough set empirical learning system to process previous step carries out multi dimensional object information retrieval, place
Reason destructuring incomplete derivative data item, eliminates the coupled noise between each achievement data and associated redundant data, improves institute
Obtaining the availability of information, calculating for teaching process simulation provides data sequence complete, reliable.
Further, described teaching simulation executive subsystem is divided into 3 logic functional block: towards professional field knowledge
The hypertext knowledge base module of dot system, student's mould of teacher model and Student oriented learning process towards teachers ' teaching process
Block.
Further, described hypertext knowledge base module is the domain knowledge superset towards certain concrete specialty, including neck
Domain knowledge spot net example, procedural knowledge material example, structural knowledge material example, teacher's priori rules, difficulty problem
Example, knowledge migration process instance constituent element;Described domain knowledge spot net example, procedural knowledge material example, structuring
Knowledge material example is static constituent element, can only carry out regular update maintenance, and wherein domain knowledge spot net example passes through hypertext
On-link mode (OLM) builds association and completes content statement, and procedural knowledge material example and structural knowledge material example are by multistage
Embedded hypermedia carries out laddering construction and expression, described teacher's priori rules, difficulty problem-instance, knowledge migration process
Example is dynamic constituent element, is updated above-mentioned constituent element by the user interface of hypertext knowledge base module, deletes, supplements and expands
Exhibition operation.
Described teacher model is teaching-oriented process production rule inference mechanism, the process mould movable to teachers ' teaching
Intending, the student information completing to record student model processes, and uses the knowledge in knowledge base to make inferences, and makes
Decision-making and judgement;Teacher model is made up of with application programming interfaces teaching process inference component, and processing procedure is as follows: 1. student exists
After finishing Exercise, wake up teaching process inference component up by teacher model application programming interfaces;2. teaching process reasoning structure
Part carries out error diagnosis by recessive Markov model algorithm exercise done to student, and provides difference according to different situations
Information and guidance;If 3. student occurs that mistake, student are that the mistake caused because some knowledge point is ignorant of provides literary composition
This description, first finds this knowledge point by the way of preorder traversal in knowledge base;4. find in rule base and this knowledge point
Relevant rule of inference, utilizes self adaptation Bayes net algorithm to draw knowledge network path associated with this knowledge point, logical
Cross the study of teacher model instruction of papil, and relevant error reason analysis process is prompted to student.
Described student's module includes learning component, supervised learning component, intelligent man-machine interface without tutor, described
Learning component without tutor utilizes self organizing neural network algorithm to realize the simulation to students self study process and optimization, i.e. by from group
Knit neural network algorithm and independently call the knowledge rule in hypertext knowledge base module, set up new knowledge relationship, formed new
Knowledge rule;Described supervised learning component utilizes error backward propagation method algorithm having teacher to teach student
Learning process is simulated and optimizes, i.e. by manual type from the knowledge rule called hypertext knowledge base module, according to
Goal-selling carries out clustering learning step by step, and finally at setting threshold value, (instructional objectives) convergence terminates;Described intellectuality is man-machine
Interface tracking students'learning, process is as follows: 1. each course is set up independent unit, sets up the judgement of each unit level
Rule;2. student enters learning state, under the guidance of teacher model, selects learning content and exercise according to instructional objectives;③
If student completes the study of a class, provide level decision values, and when carrying out error diagnosis, and from teacher model and knowledge base
Information feedback students ' behavior diagnosed to system;4. it is typical record by information setting higher for feedback frequency, composition study
Process theme log file, the important evidence updated as base module.
Beneficial effects of the present invention is mainly manifested in:
1) use rough set (RS) method to carry out multi dimensional object information retrieval, process destructuring incomplete data, eliminate
Coupled noise between each achievement data and associated redundant data, improve the availability of data.
2) machine learning (ML) technology and cognitive psychology method are introduced, it is achieved the reality to Students ' Major Knowledge process
Time follow the trail of and make mistakes mechanism analysis, improve the quality of teaching.
3) data recorded excavated and integrate, and according to the evaluation of students ' learning performance and current teaching resource
Configuring condition, it is achieved Automatic Optimal and the dynamic dispatching to field research process.
Accompanying drawing explanation
Fig. 1 is that learning characteristic extracts and use processing schematic diagram;
Fig. 2 is teaching simulation executive subsystem framework schematic diagram.
Detailed description of the invention
The invention will be further described below in conjunction with the accompanying drawings.
See figures.1.and.2, a kind of intelligent computer-assisted instruction based on information fusion (IF) Yu machine learning (ML)
(ICAI) system, including teaching process information fusion subsystem (TPFS) and teaching simulation executive subsystem (TSES);
TPFS carries out multi dimensional object information retrieval to key elements such as object involved in teaching process, material, instruments, processes
Destructuring incomplete data, eliminates the coupled noise between each achievement data and associated redundant data, performs son for teaching simulation
System provides metadata support.
The metadata that teaching process information fusion subsystem is uploaded is excavated and is integrated by TSES, simulation teaching process institute
The execution link related to;According to the evaluation of students ' learning performance and current teaching resource configuring condition, it is achieved to field research
The Automatic Optimal of process and dynamic dispatching.
As it is shown in figure 1, in teaching process information fusion subsystem (TPFS), teaching process use processing process is such as
Under:
1. determine that a concrete instructional class, as target, obtains the base of student by place universities and colleges educational administration management system
This file data, learns edge course, culture background information to it and carries out expanding with perfect, and the form of data record carries out table
State.
2. by the way of interview with questionnaire, the student information data that educational administration management system does not comprises is gathered, according to number
Carry out layout and preliminary normalization according to storehouse third normal form (3NF), set up the Students ' Learning information data table (SID) of extension.
3. use static mathematical statistics (SMS) algorithm to carry out characteristic extraction, obtain direction student learn edge structure,
The characteristic of the aspects such as stock of knowledge, memory character, learning strategy, and obtain assembly average, variance, mark on this basis
The derivative data items such as accurate poor, auto-correlation, cross-correlation, data-bias.
4. considering said process, the non-computational data obtained by education administration system and alternate manner are regarded as to be had really
Qualitative framework, is complete.Owing to being not completely independent between each information index factor, therefore calculate acquisition by SMS
Data have coupling Cover Characteristics, are incomplete.And ICAI system is to have unified completeness for inputting the requirement of parameter,
So its result of calculation just has practical significance.Use the data pair that previous step is processed by rough set (LERS) empirical learning system
As carrying out multi dimensional object information retrieval, process destructuring incomplete derivative data item, eliminate the coupling between each achievement data
Noise and associated redundant data, improve the availability of obtained information, and calculating for teaching process simulation provides data complete, reliable
Sequence.LERS is without any prior information outside the data acquisition system that processes needed for providing problem, so uncertain to problem
It is more objective that the description of property or process can be described as ratio.Owing to said method fails to comprise process inaccuracy or uncertain original number
According to mechanism, institute's method described above and theory of probability, fuzzy mathematics and evidence theory etc. other process uncertain or inaccuracy problems
Theory have the strongest complementarity.
The Students ' Learning characteristic obtained based on above-mentioned work, and then analyze its learning process and Knowledge formation
Mechanism, carries out comparative study to it in the learning strategy quality condition of major field, and carries out index of correlation evaluation, set up SID
Subject data base, for follow-up ICAI system example and direction learning strategy optimization method research provide theoretical foundation with
Data are supported.
Teaching simulation executive subsystem (TSES), for field research Track character and step function demand, TSES can draw
It is divided into 3 logic functional block: towards the hypertext knowledge base module of professional field knowledge point system, towards teachers ' teaching process
Student's module of teacher model and Student oriented learning process, as shown in Figure 2.
(1) hypertext knowledge base module
Hypertext knowledge base module is super towards the domain knowledge of certain concrete specialty (such as mechanical engineering, clinical medicine etc.)
Collection, including domain knowledge spot net example, procedural knowledge material example, structural knowledge material example, teacher's priori rules,
The constituent elements such as difficulty problem-instance, knowledge migration process instance, as shown in Figure 2.Described domain knowledge spot net example, process
Sex knowledge material example, structural knowledge material example are static constituent element, can only carry out regular update maintenance, wherein domain knowledge
Spot net example builds association by hypertext link mode and completes content statement, procedural knowledge material example and structuring
Knowledge material example carries out laddering construction and expression by multistage embedded hypermedia.Described teacher's priori rules, difficulty
Problem-instance, knowledge migration process instance are dynamic constituent element, by the user interface of hypertext knowledge base module to above-mentioned constituent element
Be updated, delete, supplement, the operation such as extension.
Knowledge base should be able to embody the architecture of knowledge, and meets the needs of systematic teaching process, before and after being formed
Coherent relation or rudimentary knowledge system, form an applicable thinking or reasoning module.Contact between each knowledge point is
Complicated, the support of the leading knowledge of Learning demands of new knowledge point, the grasp of a knowledge point affects again of other knowledge
Practise and understand.Being a kind of mutual relation supported and be supported between visible knowledge point, they constitute a kind of staggered-mesh structure.Cause
This, the structure of knowledge base can regard a network structure as, and the relation between each knowledge point has fixing link to link, this
Sample is just easy to the reasoning of inference mechanism, draws correct result.
(2) teacher model
Teacher model is teaching-oriented process production rule inference mechanism, the process simulation movable to teachers ' teaching, complete
The student information that student model is recorded in pairs processes, and uses the knowledge in knowledge base to make inferences, and makes a policy
And judgement, as shown in Figure 2.Teacher model is made up of with application programming interfaces teaching process inference component, and process is as follows:
1. student is after finishing Exercise, wakes up teaching process inference component up by teacher model application programming interfaces;
2. teaching process inference component carries out error diagnosis by recessive Markov model algorithm exercise done to student,
And provide different informations and guidance according to different situations;
If 3. student occurs that mistake, student are that the mistake caused because some knowledge point is ignorant of provides text description, logical
The mode crossing preorder traversal first finds this knowledge point in knowledge base;
4. in rule base, find the rule of inference relevant to this knowledge point, utilize self adaptation Bayes net algorithm to draw
Knowledge network path associated with this knowledge point, by the study of teacher model instruction of papil, and relevant error reason
Analysis process is prompted to student.
Teacher model problem-solving ability should reach the level of domain expert, can analyze student to a certain knowledge point
Grasping level, diagnoses the behavior of solving a problem of student in time, and provides corresponding suggestion for operation, as solved prompting, police circles' prompting, guiding
Study etc..Student, after finishing Exercise, wakes up reasoning module up by relevant interface, and reasoning module is right according to certain rule
The done exercise of student carries out error diagnosis, and provides different informations and guidance according to different situations, to a great extent
On achieve one to one, individualized teaching.
(3) student's module
Student's module by learning component without tutor, supervised learning component, intelligent man-machine interface three part form, as attached
Shown in Fig. 2.
Learning component without tutor utilizes self organizing neural network (AR-ANN) algorithm to realize the simulation to students self study process
With optimization, i.e. independently call the knowledge rule in hypertext knowledge base module by self organizing neural network algorithm, set up new
Knowledge relationship, forms new knowledge rule (self-study achievement).
Supervised learning component utilizes error backward propagation method (BP-ANN) algorithm having teacher to teach student
Learning process be simulated with optimize, i.e. by manual type from the knowledge rule called hypertext knowledge base module, press
Carrying out clustering learning step by step according to goal-selling, finally at setting threshold value, (instructional objectives) convergence terminates.
Students'learning is followed the tracks of in intelligent man-machine interface, and process is as follows:
1. each course is set up independent unit, set up the decision rule of each unit level;
2. student enters learning state, under the guidance of teacher model, selects learning content and exercise according to instructional objectives;
If 3. student completes the study of a class, provide level decision values, and when carrying out error diagnosis, and from teacher model and
Knowledge base obtains the information feedback that students ' behavior is diagnosed by system;
4. it is typical record by information setting higher for feedback frequency, forms learning process theme log file, as knowing
Know the important evidence that library module updates.
Student's module gives the reason made mistake when following the tracks of study, as conceptual mistake method of perturbation, deemed-to-satisfy4 mistake are used
Process protocal analysis method and process network classification analysis method etc. of solving a problem.The prompting of correction, record simultaneously is given again after finding the cause
Under be used as the foundation of study coach;Study tracking is the record of learning process, writes down student learning history and progressive situation;
Module updates and is as deeply changing of Students ' Learning, by cladding process or mistake method, it can illustrate that what student had knows
Know and the gap of stored knowledge in computer system, update student's module further, proceed teachings and method certainly
Plan.
Finally, in addition it is also necessary to be only the specific embodiment of the present invention it is noted that listed above.Obviously, the present invention
It is not limited to above example, it is also possible to have many deformation.Those of ordinary skill in the art can be straight from present disclosure
Connect all deformation derived or associate, be all considered as protection scope of the present invention.
Claims (6)
1. an Intelligent Computer Assist Instruction System based on information fusion Yu machine learning, it is characterised in that: described intelligence
Computer aided instruction system includes teaching process information fusion subsystem and teaching simulation executive subsystem;
Described teaching process information fusion subsystem, for object, material and instrument key element involved in teaching process
Carry out multi dimensional object information retrieval, process destructuring incomplete data, eliminate the coupled noise between each achievement data to relevant
Redundant data, provides metadata support for teaching simulation executive subsystem;
Described teaching simulation executive subsystem, excavates for the metadata uploading teaching process information fusion subsystem
With integration, the execution link involved by simulation teaching process;Join according to evaluation and the current teaching resource of students ' learning performance
Put situation, it is achieved Automatic Optimal and the dynamic dispatching to field research process.
2. Intelligent Computer Assist Instruction System based on information fusion Yu machine learning as claimed in claim 1, its feature
It is: in described teaching process information fusion subsystem, the process of teaching process use processing is as follows:
1. determine that a concrete instructional class, as target, obtains the basic shelves of student by place universities and colleges educational administration management system
Case data, learn edge course, culture background information to it and carry out expanding with perfect, and the form of data record is stated;
2. by the way of interview with questionnaire, the student information data that educational administration management system does not comprises is gathered, according to data base
Third normal form (3NF) carries out layout and preliminary normalization, sets up the Students ' Learning information data table of extension;
3. use static mathematics statistic algorithm to carry out characteristic extraction, obtain direction student learn edge structure, stock of knowledge,
Characteristic in terms of memory character and learning strategy, and obtain on this basis assembly average, variance, standard deviation, from phase
Pass, cross-correlation and data-bias derivative data item;
4. the data object using rough set empirical learning system to process previous step carries out multi dimensional object information retrieval, processes non-
Structuring incomplete derivative data item, eliminates the coupled noise between each achievement data and associated redundant data, improves obtained letter
The availability of breath, calculates for teaching process simulation and provides data sequence complete, reliable.
3. Intelligent Computer Assist Instruction System based on information fusion Yu machine learning as claimed in claim 1 or 2, it is special
Levy and be: described teaching simulation executive subsystem is divided into 3 logic functional block: super towards professional field knowledge point system
Text knowledge's library module, student's module of teacher model and Student oriented learning process towards teachers ' teaching process.
4. Intelligent Computer Assist Instruction System based on information fusion Yu machine learning as claimed in claim 3, its feature
It is: described hypertext knowledge base module is the domain knowledge superset towards certain concrete specialty, including domain knowledge spot net
Example, procedural knowledge material example, structural knowledge material example, teacher's priori rules, difficulty problem-instance, knowledge migration
Process instance constituent element;Described domain knowledge spot net example, procedural knowledge material example, structural knowledge material example are
Static constituent element, can only carry out regular update maintenance, and wherein domain knowledge spot net example builds pass by hypertext link mode
Joining and complete content statement, procedural knowledge material example is entered by multistage embedded hypermedia with structural knowledge material example
The laddering construction and expression of row, described teacher's priori rules, difficulty problem-instance, knowledge migration process instance are dynamic group
Unit, is updated above-mentioned constituent element by the user interface of hypertext knowledge base module, deletes, supplements and extended operation.
5. Intelligent Computer Assist Instruction System based on information fusion Yu machine learning as claimed in claim 3, its feature
It is: described teacher model is teaching-oriented process production rule inference mechanism, the process simulation movable to teachers ' teaching,
The student information completing to record student model processes, and uses the knowledge in knowledge base to make inferences, and makes certainly
Plan and judgement;Teacher model is made up of with application programming interfaces teaching process inference component, and processing procedure is as follows: 1. student is doing
After complete Exercise, wake up teaching process inference component up by teacher model application programming interfaces;2. teaching process inference component
Carry out error diagnosis by recessive Markov model algorithm exercise done to student, and be given different according to different situations
Information and guidance;If 3. student occurs that mistake, student are that the mistake caused because some knowledge point is ignorant of provides text
Describe, by the way of preorder traversal, in knowledge base, first find this knowledge point;4. find in rule base and this knowledge point phase
The rule of inference closed, utilizes self adaptation Bayes net algorithm to draw knowledge network path associated with this knowledge point, passes through
The study of teacher model instruction of papil, and relevant error reason analysis process is prompted to student.
6. Intelligent Computer Assist Instruction System based on information fusion Yu machine learning as claimed in claim 3, its feature
It is: described student's module includes learning component, supervised learning component, intelligent man-machine interface, described nothing without tutor
Tutor learns component and utilizes self organizing neural network algorithm to realize the simulation to students self study process and optimization, i.e. passes through self-organizing
Neural network algorithm independently calls the knowledge rule in hypertext knowledge base module, sets up new knowledge relationship, forms new knowing
Know rule;Described supervised learning component utilizes error backward propagation method algorithm to student in have teacher to teach
Practise process simulation and optimization, i.e. by manual type from the knowledge rule called hypertext knowledge base module, according in advance
If target carries out clustering learning step by step, finally at setting threshold value, (instructional objectives) convergence terminates;Described intelligent human-machine interface
Mouth follows the tracks of students'learning, and process is as follows: 1. each course is set up independent unit, sets up the judgement rule of each unit level
Then;2. student enters learning state, under the guidance of teacher model, selects learning content and exercise according to instructional objectives;If 3.
Student completes the study of a class, provides level decision values, and when carrying out error diagnosis, and obtain from teacher model and knowledge base
The information feedback that students ' behavior is diagnosed by system;4. being typical record by information setting higher for feedback frequency, composition learnt
Journey theme log file, the important evidence updated as base module.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610515579.4A CN106205244A (en) | 2016-07-04 | 2016-07-04 | Intelligent Computer Assist Instruction System based on information fusion Yu machine learning |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201610515579.4A CN106205244A (en) | 2016-07-04 | 2016-07-04 | Intelligent Computer Assist Instruction System based on information fusion Yu machine learning |
Publications (1)
Publication Number | Publication Date |
---|---|
CN106205244A true CN106205244A (en) | 2016-12-07 |
Family
ID=57465848
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201610515579.4A Pending CN106205244A (en) | 2016-07-04 | 2016-07-04 | Intelligent Computer Assist Instruction System based on information fusion Yu machine learning |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN106205244A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN106991627A (en) * | 2017-03-28 | 2017-07-28 | 广西师范大学 | The distributed intelligence tutoring system acted on behalf of based on domain body and more |
CN108509439A (en) * | 2017-02-24 | 2018-09-07 | 上海莘越软件科技有限公司 | A kind of Algebra Teaching system |
WO2021036117A1 (en) * | 2019-08-30 | 2021-03-04 | 华中师范大学 | Method and device for constructing multi-spatial fused learning environment |
CN113297169A (en) * | 2021-02-26 | 2021-08-24 | 阿里云计算有限公司 | Database instance processing method, system, device and storage medium |
CN113450612A (en) * | 2021-05-17 | 2021-09-28 | 云南电网有限责任公司 | Development method of complete teaching device applied to relay protection training |
Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0434423A2 (en) * | 1989-12-20 | 1991-06-26 | Fujitsu Limited | A system for learning an external evaluation standard |
WO2002095534A3 (en) * | 2001-05-18 | 2003-04-24 | Biowulf Technologies Llc | Methods for feature selection in a learning machine |
CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
US20070136220A1 (en) * | 2005-12-08 | 2007-06-14 | Shigeaki Sakurai | Apparatus for learning classification model and method and program thereof |
CN101000600A (en) * | 2006-12-30 | 2007-07-18 | 南京凌越教育科技服务有限公司 | Study management system and method |
CN101576869A (en) * | 2009-05-31 | 2009-11-11 | 北京富邦科讯信息咨询有限公司 | Intelligent expert consulting system based on backboard model and method |
CN101630451A (en) * | 2009-08-26 | 2010-01-20 | 广州市陪你学教育科技有限公司 | Computer assisted instruction (CAI) expert system |
CN102360457A (en) * | 2011-10-20 | 2012-02-22 | 北京邮电大学 | Bayesian network and ontology combined reasoning method capable of self-perfecting network structure |
US20130198120A1 (en) * | 2012-01-27 | 2013-08-01 | MedAnalytics, Inc. | System and method for professional continuing education derived business intelligence analytics |
CN103400328A (en) * | 2013-08-05 | 2013-11-20 | 杨安康 | Class-type teaching evaluation system for multi-information platform polymerization and evaluation method for evaluation system |
CN103975362A (en) * | 2011-10-12 | 2014-08-06 | 阿波洛教育集团公司 | Course skeleton for adaptive learning |
-
2016
- 2016-07-04 CN CN201610515579.4A patent/CN106205244A/en active Pending
Patent Citations (11)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
EP0434423A2 (en) * | 1989-12-20 | 1991-06-26 | Fujitsu Limited | A system for learning an external evaluation standard |
WO2002095534A3 (en) * | 2001-05-18 | 2003-04-24 | Biowulf Technologies Llc | Methods for feature selection in a learning machine |
CN1435781A (en) * | 2003-02-24 | 2003-08-13 | 杨炳儒 | Intelligent decision supporting configuration method based on information excavation |
US20070136220A1 (en) * | 2005-12-08 | 2007-06-14 | Shigeaki Sakurai | Apparatus for learning classification model and method and program thereof |
CN101000600A (en) * | 2006-12-30 | 2007-07-18 | 南京凌越教育科技服务有限公司 | Study management system and method |
CN101576869A (en) * | 2009-05-31 | 2009-11-11 | 北京富邦科讯信息咨询有限公司 | Intelligent expert consulting system based on backboard model and method |
CN101630451A (en) * | 2009-08-26 | 2010-01-20 | 广州市陪你学教育科技有限公司 | Computer assisted instruction (CAI) expert system |
CN103975362A (en) * | 2011-10-12 | 2014-08-06 | 阿波洛教育集团公司 | Course skeleton for adaptive learning |
CN102360457A (en) * | 2011-10-20 | 2012-02-22 | 北京邮电大学 | Bayesian network and ontology combined reasoning method capable of self-perfecting network structure |
US20130198120A1 (en) * | 2012-01-27 | 2013-08-01 | MedAnalytics, Inc. | System and method for professional continuing education derived business intelligence analytics |
CN103400328A (en) * | 2013-08-05 | 2013-11-20 | 杨安康 | Class-type teaching evaluation system for multi-information platform polymerization and evaluation method for evaluation system |
Non-Patent Citations (2)
Title |
---|
杨英: "智能型计算机辅助教学系统的实现与研究", 《电脑知识与技术》 * |
陈颖: "基于超文本结构的智能计算机辅助教学系统", 《计算机研究与发展》 * |
Cited By (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108509439A (en) * | 2017-02-24 | 2018-09-07 | 上海莘越软件科技有限公司 | A kind of Algebra Teaching system |
CN108509439B (en) * | 2017-02-24 | 2022-04-05 | 上海莘越软件科技有限公司 | Algebra teaching system |
CN106991627A (en) * | 2017-03-28 | 2017-07-28 | 广西师范大学 | The distributed intelligence tutoring system acted on behalf of based on domain body and more |
WO2021036117A1 (en) * | 2019-08-30 | 2021-03-04 | 华中师范大学 | Method and device for constructing multi-spatial fused learning environment |
CN113297169A (en) * | 2021-02-26 | 2021-08-24 | 阿里云计算有限公司 | Database instance processing method, system, device and storage medium |
CN113450612A (en) * | 2021-05-17 | 2021-09-28 | 云南电网有限责任公司 | Development method of complete teaching device applied to relay protection training |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Song et al. | A bibliometric analysis of worldwide educational artificial intelligence research development in recent twenty years | |
Dutt et al. | A systematic review on educational data mining | |
CN106205244A (en) | Intelligent Computer Assist Instruction System based on information fusion Yu machine learning | |
Iglesias et al. | Learning teaching strategies in an adaptive and intelligent educational system through reinforcement learning | |
Li et al. | Progress, challenges and countermeasures of adaptive learning | |
Cannavacciuolo et al. | Technological innovation-enabling industry 4.0 paradigm: a systematic literature review | |
Wu | Student model construction of intelligent teaching system based on Bayesian network | |
CN107644572A (en) | A kind of tutoring system based on thought process | |
CN107644387A (en) | A kind of tutoring system for junior middle school's plane geometry thought process | |
Tian | Teaching effect evaluation system of ideological and political teaching based on supervised learning | |
Zheng et al. | A computer‐assisted instructional method based on machine learning in software testing class | |
Jin et al. | A complex event processing framework for an adaptive language learning system | |
Kang et al. | Construction of Chinese language teaching system model based on deep learning under the background of artificial intelligence | |
Diao et al. | Personalized learning resource recommendation based on course ontology and cognitive ability | |
Ouyang et al. | A systematic review of AI-driven educational assessment in STEM education | |
Gan et al. | AI-tutor: Generating tailored remedial questions and answers based on cognitive diagnostic assessment | |
Kaswan et al. | AI in personalized learning | |
Tian | The human resources development applications of machine learning in the view of artificial intelligence | |
CA2829249A1 (en) | Method for competency assessment of healthcare students and practitioners | |
Zhang | The realization of intelligent algorithm of knowledge point association analysis in English diagnostic practice system | |
Shi | [Retracted] Research on the Strategy of Autonomous Learning under the Dual‐Class Model of Ideological and Political Courses Based on the Knowledge Map Route | |
Chopade et al. | Modeling dynamic team interactions for intelligent tutoring | |
Xia | Prediction of learning behavior based on improved random forest algorithm | |
Saiyeda | From E-learning to S-learning: A review | |
Almaz et al. | The Future Role of Artificial Intelligence (AI) Design's Integration into Architectural and Interior Design Education is to Improve Efficiency, Sustainability, and Creativity |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
C06 | Publication | ||
PB01 | Publication | ||
C10 | Entry into substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20161207 |