CN107977708A - The student's DNA identity informations recommended towards individualized learning scheme define method - Google Patents
The student's DNA identity informations recommended towards individualized learning scheme define method Download PDFInfo
- Publication number
- CN107977708A CN107977708A CN201711190426.8A CN201711190426A CN107977708A CN 107977708 A CN107977708 A CN 107977708A CN 201711190426 A CN201711190426 A CN 201711190426A CN 107977708 A CN107977708 A CN 107977708A
- Authority
- CN
- China
- Prior art keywords
- student
- degree
- knowledge point
- understanding
- coefficient
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/06—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons
- G06N3/061—Physical realisation, i.e. hardware implementation of neural networks, neurons or parts of neurons using biological neurons, e.g. biological neurons connected to an integrated circuit
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/082—Learning methods modifying the architecture, e.g. adding, deleting or silencing nodes or connections
-
- 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—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
Abstract
The present invention provides a kind of student's DNA identity informations recommended towards individualized learning scheme and defines method, the global learning situation of student is described as a DNA tensor, all knowledge point degree of understanding coefficients in career are learnt by the statistic of property stage by stage and realize three-dimensional visualization, intuitively show student in the global learning situation in each stage, long short slab and time used;Intelligence extraction test papers can be carried out in examination base system according to the long short slab situation and are pushed to student's execution, then according to student's implementation status, the changing value of corresponding knowledge point degree of understanding coefficient is calculated, realizes the renewal of student's DNA tensors;It is optimal learning path according to comparing user and reaching the learning path of a certain degree used time length deducibility which user, also it can be inferred that having front and rear causality between which knowledge point.
Description
Technical field
The present invention relates to artificial intelligence and big data technical field, more specifically, is related to a kind of towards individualized learning
Student's DNA identity informations that scheme is recommended define method.
Background technology
With the popularization of Internet technology, the arriving in big data epoch, Web education has obtained rapid development, in face of mesh
The mass digital educational resource that even PB grades of the TB of preceding accumulation, the similar big data information processing technology demand of data mining is increasingly
Urgently.Educational resource push is the production of educational pattern and method reform in teaching that Modern Education Technology is guided using network by carrier
A kind of thing, it is intended to explore Student oriented and teacher, there is provided the service mode of good information resources.And personalized recommendation is this
Popular domain in research, combines personalized recommendation with educational resource, and learner is extracted with related big data digging technology
Learning behavior feature, be each user it is customized rationally effective Learning Scheme.
In modern education, because of technology and the missing of resource integrated method, student, which can not intuitively discover, its knowledge
Weak spot, so as to can not accomplish targetedly to practice when selecting examination question;It is and not yet in effect in learning process to make good use of
Causality between knowledge point, causes quickly to improve results.
The content of the invention
In view of the above problems, the object of the present invention is to provide a kind of student's DNA bodies recommended towards individualized learning scheme
Part information definition method, to solve the problems, such as pointed by above-mentioned background technology.
The student's DNA identity informations provided by the invention recommended towards individualized learning scheme define method, including:
Step S1:Knowledge point set of the statistic in some study stage;
Step S2:Utilize the corresponding degree of understanding coefficient in each knowledge point in BP neural network calculation knowledge point set;Its
In,
In using BP neural network calculation knowledge point set during the corresponding degree of understanding coefficient in each knowledge point,
Including:
Step S21:Using the accuracy of exercise and input of the speed as BP neural network is completed, by the corresponding reason in knowledge point
Output of the degree coefficient as BP neural network is solved, establishes the correspondence of BP neural network input and output, determines training sample
This collection;
Step S22:All degree of understanding coefficients in training sample are subjected to data normalization processing;
Step S23:Build three layers of BP neural network model;Wherein, the neuron of input layer is set as i, output layer
Neuron is k, and the neuron of hidden layer is j;The node function of hidden layer is S type functions, and the node function of output layer is
Linear function, the weights for making input layer to hidden layer are Wij, the Node B threshold of hidden layer is bj, the weights of hidden layer to output layer
ForThe Node B threshold of output layer is
Step S24:Three layers of BP neural network model are trained using training sample set, obtain network model;
The accuracy for every problem that student is done obtains the reason of the corresponding topic of the student with completing speed input network model
Solve degree coefficientAccording to degree of understanding coefficientThe degree of understanding coefficient of each knowledge point is calculated by following formula
UDi:
In above formula,Represent the degree of understanding coefficient that student inscribes the kth under i knowledge points, UDiIncluded for the knowledge point
All examination questions degree of understanding coefficient summation average;
Step S3:The degree of understanding coefficient for recording each knowledge point rises to the time point of lower level from present level;
Step S4:Knowledge point, degree of understanding coefficient corresponding with the knowledge point and the degree of understanding coefficient level are risen to
Time point synthesize one description student learn situation DNA tensors.
Compared with prior art, the global learning situation of student is described as a DNA tensor by the present invention, passes through stage
Statistic learns all knowledge point degree of understanding coefficients in career and realizes three-dimensional visualization, intuitively shows student every
Global learning situation, long short slab and the time used in a stage;It can be carried out according to the long short slab situation in examination base system
Intelligence extracts test papers and is pushed to student's execution.
Brief description of the drawings
By reference to the explanation below in conjunction with attached drawing, and with the present invention is more fully understood, of the invention is other
Purpose and result will be more apparent and should be readily appreciated that.In the accompanying drawings:
Fig. 1 is the stereogram formed according to the visualization of the DNA tensors of the embodiment of the present invention.
Embodiment
In the following description, for purposes of illustration, in order to provide the comprehensive understanding to one or more embodiments, explain
Many details are stated.It may be evident, however, that it can also realize these embodiments in the case of these no details.
In other examples, for the ease of the one or more embodiments of description, known structure and equipment are shown in block form an.
The student's DNA identity informations provided by the invention recommended towards individualized learning scheme define method, including as follows
Step:
Step S1:Knowledge point set of the statistic in some study stage.
Student can pass through many study stages in career is learnt, and each study stage can form the DNA letters of uniqueness
Matrix is ceased, corresponding DNA information matrix is the information such as different grades, subject, knowledge point.
By grade, subject attribute and student name, ID together as the label column of DNA information matrix, and student is owned
Knowledge point formed conjunction DNA information matrix be divided into corresponding block DNA information matrix according to the study stage.
Therefore step S1 only needs statistic in the knowledge point set involved in corresponding with the study stage piece of DNA information matrix
Close.
Step S2:Utilize the corresponding degree of understanding coefficient in each knowledge point in BP neural network calculation knowledge point set.
The UD of each knowledge point first can be set to 0 by the DNA information matrix of initial user, pass through follow-up exercise recommendation process
In, progressive updating.
In using BP neural network calculation knowledge point set during the corresponding degree of understanding coefficient in each knowledge point,
Including:
Step S21:Using the accuracy of exercise and input of the speed as BP neural network is completed, by the corresponding reason in knowledge point
Output of the degree coefficient as BP neural network is solved, establishes the correspondence of BP neural network input and output, determines training sample
This collection.
Do topic accuracy and refer to that correct score accounts for the ratio of examination question full marks.
Complete speed and refer to that the actual finish time of per pass examination question accounts for the ratio of standard deadline.
Accuracy, complete speed degree of understanding coefficient three one-to-one corresponding corresponding with knowledge point, determines training sample set,
It is as shown in the table:
Step S22:All degree of understanding coefficients in training sample are subjected to data normalization processing.
Step S23:Build three layers of BP neural network model.
Three layers of BP neural network model are respectively input layer, output layer and hidden layer, set input layer for including three layers
Neuron is i, and the neuron of output layer is k, and the neuron of hidden layer is j;The node function of hidden layer is S type letters
Number, the node function of output layer is linear function, and the weights for making input layer to hidden layer are Wij, the Node B threshold of hidden layer is
bj, the weights of hidden layer to output layer areThe Node B threshold of output layer is
Step S24:Three layers of BP neural network model are trained using above-mentioned training sample set, obtain network model.
The network model is a network model at utmost suiting BP neural network input and output correspondence, i.e.,
The prediction output of network model and the error of reality output are minimum.
Step S25:To obtain the student corresponding with completing speed input network model for the accuracy for every problem that student is done
The degree of understanding coefficient of the topicAccording to degree of understanding coefficientThe understanding journey of each knowledge point is calculated by following formula
Spend coefficient UDi:
In above formula,Represent the degree of understanding coefficient that student inscribes the kth under i knowledge points, UDiIncluded for the knowledge point
All examination questions degree of understanding coefficient summation average, so as to obtain the degree of understanding coefficient of each knowledge point.
Step S3:The degree of understanding coefficient for recording each knowledge point rises to the time point of lower level from present level.
The degree of understanding coefficient of knowledge point is divided into 10 grades by the present invention, from grade 1 to grade 10.
With raising of the student to the Grasping level of knowledge point, student can also improve the degree of understanding coefficient of the knowledge point
Grade.
Step S4:Knowledge point, degree of understanding coefficient corresponding with the knowledge point and the degree of understanding coefficient level are risen to
Time point synthesize one description student learn situation DNA tensors.
The DNA tensors describe overall learning state of the student in a certain study stage, have recorded the institute of the student
There is learning outcome, by information visualization, be integrated into a stereogram.
As shown in Figure 1, the X-axis in Fig. 1 describes the knowledge point of student;Y-axis describes degree of understanding coefficient level
The time point risen to;Z axis describes degree of understanding coefficient.
The degree of understanding change feelings for describing the student 5 knowledge points in week age of the histogram simple, intuitive
Condition.
The present invention learns in career all knowledge point degree of understanding coefficients by the statistic of property stage by stage and realizes three
Dimension visualization, intuitively shows student in the global learning situation in each stage, long short slab and time used;Can be according to this
Long short slab situation carries out intelligent Auto-generating Test Paper in examination base system and is pushed to student's execution, then according to student's implementation status, calculates
The changing value of the degree of understanding coefficient of corresponding knowledge point, realizes the renewal of the DNA tensors of the student;Certain is reached according to user is compared
The learning path of which user of one degree used time length deducibility is optimal learning path, also it can be inferred that between which knowledge point
With front and rear causality.
The above description is merely a specific embodiment, but protection scope of the present invention is not limited thereto, any
Those familiar with the art the invention discloses technical scope in, change or replacement can be readily occurred in, should all be contained
Cover within protection scope of the present invention.Therefore, protection scope of the present invention answers the scope of the claims of being subject to.
Claims (1)
1. a kind of student's DNA identity informations recommended towards individualized learning scheme define method, including:
Step S1:Knowledge point set of the statistic in some study stage;
Step S2:The corresponding degree of understanding coefficient in each knowledge point in the knowledge point set is calculated using BP neural network;Its
In,
The mistake of the corresponding degree of understanding coefficient in each knowledge point in the knowledge point set is being calculated using the BP neural network
Cheng Zhong, including:
Step S21:Using the accuracy of exercise and input of the speed as the BP neural network is completed, by the corresponding reason in knowledge point
Output of the degree coefficient as the BP neural network is solved, establishes the correspondence of the BP neural network input and output, really
Determine training sample set;
Step S22:All degree of understanding coefficients in the training sample are subjected to data normalization processing;
Step S23:Build three layers of BP neural network model;Wherein, the neuron of input layer is set as i, the nerve of output layer
Member is k, and the neuron of hidden layer is j;The node function of the hidden layer is S type functions, the node letter of the output layer
Number is linear function, and the weights for making the input layer to the hidden layer are Wij, the Node B threshold of the hidden layer is bj, it is described
The weights of hidden layer to the output layer areThe Node B threshold of the output layer is
Step S24:Three layers of BP neural network model is trained using the training sample set, obtains network model;
Step S25:The accuracy for every problem that student is done inputs the network model to obtain the student corresponding with completing speed
The degree of understanding coefficient of the topicAccording to the degree of understanding coefficientThe reason of each knowledge point is calculated by following formula
Solve degree coefficient UDi:
<mrow>
<msub>
<mi>UD</mi>
<mi>i</mi>
</msub>
<mo>=</mo>
<mfrac>
<mrow>
<msubsup>
<mi>UD</mi>
<mi>i</mi>
<mn>1</mn>
</msubsup>
<mo>+</mo>
<msubsup>
<mi>UD</mi>
<mi>i</mi>
<mn>2</mn>
</msubsup>
<mo>+</mo>
<mn>...</mn>
<mo>+</mo>
<msubsup>
<mi>UD</mi>
<mi>i</mi>
<mi>k</mi>
</msubsup>
</mrow>
<mi>k</mi>
</mfrac>
<mo>;</mo>
</mrow>
In above formula,Represent the degree of understanding coefficient that student inscribes the kth under i knowledge points, UDiThe institute included for the knowledge point
There is the average of the degree of understanding coefficient summation of examination question;
Step S3:The degree of understanding coefficient for recording each knowledge point rises to the time point of lower level from present level;
Step S4:By knowledge point, degree of understanding coefficient corresponding with the knowledge point and the degree of understanding coefficient level rise to when
Between point synthesis one description student learn situation DNA tensors.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711190426.8A CN107977708A (en) | 2017-11-24 | 2017-11-24 | The student's DNA identity informations recommended towards individualized learning scheme define method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201711190426.8A CN107977708A (en) | 2017-11-24 | 2017-11-24 | The student's DNA identity informations recommended towards individualized learning scheme define method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107977708A true CN107977708A (en) | 2018-05-01 |
Family
ID=62011356
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201711190426.8A Pending CN107977708A (en) | 2017-11-24 | 2017-11-24 | The student's DNA identity informations recommended towards individualized learning scheme define method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107977708A (en) |
Cited By (8)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108615423A (en) * | 2018-06-21 | 2018-10-02 | 中山大学新华学院 | Instructional management system (IMS) on a kind of line based on deep learning |
CN108765227A (en) * | 2018-06-20 | 2018-11-06 | 华南师范大学 | Study portrait method based on big data and artificial intelligence and robot system |
CN109934156A (en) * | 2019-03-11 | 2019-06-25 | 重庆科技学院 | A kind of user experience evaluation method and system based on ELMAN neural network |
CN110414628A (en) * | 2019-08-07 | 2019-11-05 | 清华大学深圳研究生院 | A kind of learning process planning and management method and system from wound course |
CN110674202A (en) * | 2019-09-19 | 2020-01-10 | 福建工程学院 | Individual learning method and device based on big data analysis and storage medium |
CN112015783A (en) * | 2020-08-30 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Interactive learning process generation method and system |
CN112116841A (en) * | 2020-09-10 | 2020-12-22 | 广州大学 | Personalized remote education system and method based on deep learning |
CN114730529A (en) * | 2019-11-11 | 2022-07-08 | 株式会社Z会 | Learning effect estimation device, learning effect estimation method, and program |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765842A (en) * | 2015-04-15 | 2015-07-08 | 中山大学 | Optimum study scheme pushing method and system |
CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
CN107274020A (en) * | 2017-06-15 | 2017-10-20 | 北京师范大学 | A kind of learner's subject based on collaborative filtering thought always surveys result prediction system and method |
-
2017
- 2017-11-24 CN CN201711190426.8A patent/CN107977708A/en active Pending
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN104765842A (en) * | 2015-04-15 | 2015-07-08 | 中山大学 | Optimum study scheme pushing method and system |
CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
CN107274020A (en) * | 2017-06-15 | 2017-10-20 | 北京师范大学 | A kind of learner's subject based on collaborative filtering thought always surveys result prediction system and method |
Non-Patent Citations (1)
Title |
---|
刘朝华: "数据挖掘技术在教育云平台中的应用研究", 《中国优秀硕士学位论文全文数据》 * |
Cited By (9)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN108765227A (en) * | 2018-06-20 | 2018-11-06 | 华南师范大学 | Study portrait method based on big data and artificial intelligence and robot system |
CN108615423A (en) * | 2018-06-21 | 2018-10-02 | 中山大学新华学院 | Instructional management system (IMS) on a kind of line based on deep learning |
CN109934156A (en) * | 2019-03-11 | 2019-06-25 | 重庆科技学院 | A kind of user experience evaluation method and system based on ELMAN neural network |
CN110414628A (en) * | 2019-08-07 | 2019-11-05 | 清华大学深圳研究生院 | A kind of learning process planning and management method and system from wound course |
CN110674202A (en) * | 2019-09-19 | 2020-01-10 | 福建工程学院 | Individual learning method and device based on big data analysis and storage medium |
CN114730529A (en) * | 2019-11-11 | 2022-07-08 | 株式会社Z会 | Learning effect estimation device, learning effect estimation method, and program |
CN112015783A (en) * | 2020-08-30 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Interactive learning process generation method and system |
CN112015783B (en) * | 2020-08-30 | 2021-07-16 | 上海松鼠课堂人工智能科技有限公司 | Interactive learning process generation method and system |
CN112116841A (en) * | 2020-09-10 | 2020-12-22 | 广州大学 | Personalized remote education system and method based on deep learning |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107977708A (en) | The student's DNA identity informations recommended towards individualized learning scheme define method | |
Asanbe et al. | Teachers’ performance evaluation in higher educational institution using data mining technique | |
CN109377797A (en) | Virtual portrait teaching method and device | |
CN106384319A (en) | Teaching resource personalized recommending method based on forgetting curve | |
Yuhana et al. | Combining fuzzy signature and rough sets approach for predicting the minimum passing level of competency achievement | |
CN105678381A (en) | Gender classification network training method, gender classification method and related device | |
Chen et al. | Education 4.0 using artificial intelligence for students performance analysis | |
Singh et al. | An empirical study of applications of data mining techniques for predicting student performance in higher education | |
CN106373057A (en) | Network education-orientated poor learner identification method | |
Wanjau et al. | Improving student enrollment prediction using ensemble classifiers | |
Singh et al. | Comparative Analysis of Classification Techniques for Predicting Computer Engineering Students' Academic Performance. | |
Paiva et al. | Helping teachers help their students: A human-ai hybrid approach | |
Kshirsagar et al. | Human intelligence analysis through perception of AI in teaching and learning | |
Karkhanis et al. | A study of application of data mining and analytics in education domain | |
Ghazali et al. | Review of personalized learning approaches and methods in e-learning environment | |
CN109635869A (en) | On-line study interfering system | |
CN108932593A (en) | A kind of cognition analysis of Influential Factors method and device | |
CN107832453A (en) | Virtual test paper recommendation method oriented to personalized learning scheme | |
CN114117033B (en) | Knowledge tracking method and system | |
Aziz et al. | Adaptive E-learning recommendation model based on the knowledge level and learning style | |
CN113919567A (en) | Test paper score prediction method combining knowledge tracking and sequence labeling model | |
Qasem et al. | Educational data mining (EDM): a review | |
Kawale et al. | Development of an e-learning system based on artificial intelligence | |
Azevedo et al. | Application of Pattern Recognition Techniques for MathE Questions Difficulty Level Definition | |
Bhatnagar et al. | Computational psychometrics analysis of learners’ motivational level using different parameters |
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 | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20180501 |