CN110046147A - It is applicable in user's learning ability value-acquiring method and its application of Adaptable System - Google Patents
It is applicable in user's learning ability value-acquiring method and its application of Adaptable System Download PDFInfo
- Publication number
- CN110046147A CN110046147A CN201910321952.6A CN201910321952A CN110046147A CN 110046147 A CN110046147 A CN 110046147A CN 201910321952 A CN201910321952 A CN 201910321952A CN 110046147 A CN110046147 A CN 110046147A
- Authority
- CN
- China
- Prior art keywords
- ability value
- user
- learning
- learning ability
- value
- 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
- 238000000034 method Methods 0.000 title claims abstract description 33
- 230000004044 response Effects 0.000 claims abstract description 18
- 238000012360 testing method Methods 0.000 claims abstract description 12
- 230000003044 adaptive effect Effects 0.000 claims description 10
- 230000000875 corresponding effect Effects 0.000 description 9
- 238000013473 artificial intelligence Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 3
- 230000008713 feedback mechanism Effects 0.000 description 3
- 238000005516 engineering process Methods 0.000 description 2
- 238000005259 measurement Methods 0.000 description 2
- 238000013179 statistical model Methods 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000006399 behavior Effects 0.000 description 1
- 230000003542 behavioural effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000001186 cumulative effect Effects 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013135 deep learning Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 230000003631 expected effect Effects 0.000 description 1
- 238000002474 experimental method Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000010801 machine learning Methods 0.000 description 1
- 238000013507 mapping Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000010606 normalization Methods 0.000 description 1
- 230000008569 process Effects 0.000 description 1
- 230000002787 reinforcement Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/211—Schema design and management
- G06F16/212—Schema design and management with details for data modelling support
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/21—Design, administration or maintenance of databases
- G06F16/219—Managing data history or versioning
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/20—Information retrieval; Database structures therefor; File system structures therefor of structured data, e.g. relational data
- G06F16/28—Databases characterised by their database models, e.g. relational or object models
- G06F16/284—Relational databases
-
- 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
- Engineering & Computer Science (AREA)
- Databases & Information Systems (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention relates to a kind of user's learning ability value-acquiring method for being applicable in Adaptable System and its applications, this method comprises: obtaining the history learning data of user, push test content according to the current power of user；According to user feedback data and the history learning data, the real-time learning ability value of user is obtained based on item response theory model and setting ability value codomain；History learning data are updated based on the real-time learning ability value.Compared with prior art, the present invention has many advantages, such as high reliablity, improves learning efficiency.
Description
Technical field
The present invention relates to online education technical fields, are related to a kind of learning device, are applicable in more particularly, to one kind adaptive
User's learning ability value-acquiring method of system and its application.
Background technique
With popularizing for artificial intelligence, the further investigation for the computerized algorithms such as machine learning, deep learning, reinforcement learn,
Artificial intelligence is in virtually change people's lives mode, or even the life style for helping planning following in advance.
Artificial intelligence has a preset condition to be, computer cluster needs are acquired according to user behavior data, from
And the behavioral data of study analysis user, and then the recommendation suitable resource adaptive for user, plan better learning path.
Adaptable System has possessed the teaching resource of above-mentioned magnanimity, where being diagnosed to be the weak knowledge point of user after, how for
It is the key factor of decision systems quality that optimum knowledge point is recommended at family.Firstly, it is necessary to establish a kind of system for user's
Feedback mechanism, and then carry out recommendation study.
The feedback mechanism of mainstream is item response theory at present, according to the information of topic, comprising: item difficulty, topic
The coefficient of hitting it of discrimination and topic obtains the feedback information that user is directed to the topic according to the answer situation of user.It is passing
In the project reactive machanism of system, the prerequisite of theoretical foundation has the following: ability one-dimensional, forms all of a certain test
Project is all the same latent trait of measurement；Local autonomy exists between project without correlation it is assumed that for some subject；
Item characteristic curve is it is assumed that correctly reflect model made by the functional relation between probability and its ability to a certain purpose is tested；
And above-mentioned assumed condition has some deficiencies behind: indicatrix can be cumulative with number of users, occurs adaptive
Adjustment, and this property for it is rear enter tester for be it is inequitable, system needs stable feedback mechanism；For quilt
For examination person, the information of feedback needs independent and stablizes: connecing assuming that subject similar in several abilities puts in different times
Tested person, obtained feedback should be consistent；And for the same project, in the case where item argument determines, give
To the feedback of subject, need only related with the current ability of subject.
Summary of the invention
It is an object of the present invention to overcome the above-mentioned drawbacks of the prior art and provide one kind to be applicable in adaptive system
User's learning ability value-acquiring method of system and its application.
The purpose of the present invention can be achieved through the following technical solutions:
A kind of user's learning ability value-acquiring method being applicable in Adaptable System, this method comprises:
The history learning data for obtaining user push test content according to the current power of user；
According to user feedback data and the history learning data, based on item response theory model and setting ability value value
Domain obtains the real-time learning ability value of user；
History learning data are updated based on the real-time learning ability value.
Further, the history learning data include that history is done topic record and learning records, user's study habit and known
Know point Grasping level data.
Further, described that energy is learnt based on item response theory model and setting ability value codomain acquisition user in real time
Force value specifically:
In the setting ability value codomain, calculates the corresponding topic of each possible ability value and answer questions probability, answered with topic
To the possibility ability value of maximum probability as the real-time learning ability value of user.
Further, 0.01 × N is divided between the adjacent possible ability value, wherein N is the maximum of ability value codomain
Value.
Further, the item response theory model expression are as follows:
Wherein, θ is the learning ability value of tested user, and a is the discrimination of project, and b is item difficulty parameter, and c is conjecture
Parameter；P (θ) is that the corresponding topic of user that learning ability value is θ answers questions probability, and D is project scale factor constant.
Further, this method further include:
The real-time learning ability value is saved to ability value database.
The present invention also provides a kind of adaptive learning methods, comprising the following steps:
Learning ability value is obtained according to user's learning ability value-acquiring method；
Corresponding learning Content is pushed based on the learning ability value.
The present invention also provides a kind of adaptive learning devices, comprising:
Ability value obtains module, for obtaining learning ability value according to user's learning ability value-acquiring method；
Pushing module, for pushing corresponding learning Content based on the learning ability value.
Compared with prior art, the present invention have with following the utility model has the advantages that
(1) codomain that ability value is finally calculated in the present invention is consistent, each tester may be got
Each ability value, and the probability for getting each ability value is determined by the ability of user, and unrelated with topic, when topic is joined
When number is consistent, the ability value fed back is single and constant for each testee；
(2) present invention freely sets ability value codomain, convenient for being applied to more mathematical statistical models and machine after normalization
Device learning model；
(3) present invention calculates the corresponding probability value of ability value that can each get in codomain, and the reflection of these probability values is
Ability of the testee in test embodies, and ability performance later can continue on Probability Basis before, feedback result
It is the accumulation feedback of the per pass topic done, so that the ability value of testee has inheritability；
(4) there is the ability value that the present invention obtains inheritability can build according between knowledge point in Adaptable System
Vertical knowledge mapping relationship predicts the tester in the possibility energy of other correlated knowledge points according to the ability value of a knowledge point
Force value and do topic performance；
(5) it can more effectively be improved learning efficiency based on learning ability value-acquiring method of the invention.
Detailed description of the invention
Fig. 1 is flow chart schematic diagram of the invention；
Fig. 2 is the distribution map of item response theory formula；
Fig. 3 is that user answers situation and ability value figure of changing.
Specific embodiment
The present invention is described in detail with specific embodiment below in conjunction with the accompanying drawings.The present embodiment is with technical solution of the present invention
Premised on implemented, the detailed implementation method and specific operation process are given, but protection scope of the present invention is not limited to
Following embodiments.
Embodiment 1
As shown in Figure 1, the present embodiment provides a kind of user's learning ability value-acquiring method for being applicable in Adaptable System, the party
Method includes: to obtain the history learning data of user, pushes test content according to the current power of user；According to user feedback number
According to and the history learning data, based on item response theory model and setting ability value codomain obtain user learn energy in real time
Force value；History learning data are updated based on the real-time learning ability value.
The history learning data include that history does topic record and learning records, user's study habit and knowledge point grasp journey
Degree evidence.
It is described specific based on item response theory model and the setting ability value codomain acquisition real-time learning ability value of user
Are as follows:
In the setting ability value codomain, calculates the corresponding topic of each possible ability value and answer questions probability, answered with topic
To the possibility ability value of maximum probability as the real-time learning ability value of user.
0.01 × N is divided between the adjacent possible ability value, wherein N is the maximum value of ability value codomain.Such as
In (0,100), the value that ability value may be got is 1,2,3,4 ... ..., 97,98,99.
The item response theory model expression are as follows:
Wherein, θ is the learning ability value of tested user, and a is the discrimination of project, and b is item difficulty parameter, and c is conjecture
Parameter；P (θ) is that the corresponding topic of user that learning ability value is θ answers questions probability, and D is project scale factor constant.
Item response theory is a series of general name of psychology statistical models, and target determines potential feature and survey
Whether the interactive relationship (Grasping level of user can regard potential feature as) between examination question and testee can pass through survey
Examination question reflects.
Item response theory assumes that subject has a kind of " latent trait ", and latent trait is to test reaction basis in observation analysis
A kind of statistics of upper proposition is conceived, and in test, latent trait generally refers to potential ability, and through common test total score conduct
The estimation of this potentiality.Item response theory, which thinks to be tested reaction on test item and achievement and their latent trait, to be had
Special relationship.Has the characteristics that permanent property by the item argument that item response theory is established, it is meant that different measurements
Score can unify.
The parameter for including in above-mentioned formula is explained as follows:
C indicates " conjecture parameter ", and intuitive meaning is, when the ability value of a testee is very low (such as close to 0),
But still it can correctly do probability to the project；
B indicate item difficulty parameter, according to the mobility of function it is found that change b will lead to image move left and right without
Change shape；
A indicates the discrimination of project, i.e. can a project distinguish the ability level of different testees, a well
Value it is more high have discrimination.
Item response theory realize premise include:
(1) in the case where test question information is certain, feedback information is only determined by performance of the user on the topic, and is presented
Positive correlation trend；
(2) different users do topic performance it is consistent when, obtained feedback information is consistent, and is stablized constant；
(3) feedback information is ability value of the user under the project.
The distribution map of item response theory formula is as indicated with 2.
In another embodiment, this method further include: save the real-time learning ability value to ability value database.
The calculated result of ability value, it should meet the described characteristic that can be inherited above, that is to say, that do to topic in user
When purpose, ascendant trend is presented in ability value；And when performing poor as topic, downward trend should be presented in ability value；And it needs
Within the scope of defined codomain, without departing from codomain.
According to the above characteristic, the test macro of system is adapted to intelligence, the study for simulating true student is done topic path, obtained
Ability value and to answer situation as shown in Figure 3.
The situation of continuously answering of Fig. 3 middle school student is [1,1,1,0,0,1,0,1,0,1], wherein 1 indicates to do pair, 0 indicates to do
It is wrong.System is fed back in figure shown in red line for student ability value.Most start continuously to do in the case where, ability value is presented
Ascendant trend；And when starting the case where doing wrong and occurring, ability value can decline；Generally, ability value meets situation of answering
Distribution, realizes expected effect.
Embodiment 2
The present embodiment provides a kind of adaptive learning methods, comprising the following steps:
Learning ability value is obtained according to user's learning ability value-acquiring method as described in Example 1；
Corresponding learning Content is pushed based on the learning ability value.
Embodiment 3
The present embodiment provides a kind of adaptive learning devices, comprising:
Ability value obtains module, for being learnt according to user's learning ability value-acquiring method as described in Example 1
Ability value；
Pushing module, for pushing corresponding learning Content based on the learning ability value.
The preferred embodiment of the present invention has been described in detail above.It should be appreciated that those skilled in the art without
It needs creative work according to the present invention can conceive and makes many modifications and variations.Therefore, all technologies in the art
Personnel are available by logical analysis, reasoning, or a limited experiment on the basis of existing technology under this invention's idea
Technical solution, all should be within the scope of protection determined by the claims.
Claims (8)
1. a kind of user's learning ability value-acquiring method for being applicable in Adaptable System, which is characterized in that this method comprises:
The history learning data for obtaining user push test content according to the current power of user；
According to user feedback data and the history learning data, obtained based on item response theory model and setting ability value codomain
Obtain the real-time learning ability value of user；
History learning data are updated based on the real-time learning ability value.
2. the user's learning ability value-acquiring method according to claim 1 for being applicable in Adaptable System, which is characterized in that institute
Stating history learning data includes that history does topic record and learning records, user's study habit and knowledge point Grasping level data.
3. the user's learning ability value-acquiring method according to claim 1 for being applicable in Adaptable System, which is characterized in that institute
It states and the real-time learning ability value of user is obtained based on item response theory model and setting ability value codomain specifically:
In the setting ability value codomain, calculates the corresponding topic of each possible ability value and answer questions probability, answered questions generally with topic
The maximum possible ability value of rate is as the real-time learning ability value of user.
4. the user's learning ability value-acquiring method according to claim 3 for being applicable in Adaptable System, which is characterized in that phase
0.01 × N is divided between the adjacent possible ability value, wherein N is the maximum value of ability value codomain.
5. the user's learning ability value-acquiring method according to claim 1 for being applicable in Adaptable System, which is characterized in that institute
State item response theory model expression are as follows:
Wherein, θ is the learning ability value of tested user, and a is the discrimination of project, and b is item difficulty parameter, and c is conjecture parameter；
P (θ) is that the corresponding topic of user that learning ability value is θ answers questions probability, and D is project scale factor constant.
6. the user's learning ability value-acquiring method according to claim 1 for being applicable in Adaptable System, which is characterized in that should
Method further include:
The real-time learning ability value is saved to ability value database.
7. a kind of adaptive learning method, which comprises the following steps:
Learning ability value is obtained according to user's learning ability value-acquiring method as described in claim 1；
Corresponding learning Content is pushed based on the learning ability value.
8. a kind of adaptive learning device characterized by comprising
Ability value obtains module, for obtaining study energy according to user's learning ability value-acquiring method as described in claim 1
Force value；
Pushing module, for pushing corresponding learning Content based on the learning ability value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910321952.6A CN110046147A (en) | 2019-04-22 | 2019-04-22 | It is applicable in user's learning ability value-acquiring method and its application of Adaptable System |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910321952.6A CN110046147A (en) | 2019-04-22 | 2019-04-22 | It is applicable in user's learning ability value-acquiring method and its application of Adaptable System |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110046147A true CN110046147A (en) | 2019-07-23 |
Family
ID=67278118
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910321952.6A Pending CN110046147A (en) | 2019-04-22 | 2019-04-22 | It is applicable in user's learning ability value-acquiring method and its application of Adaptable System |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110046147A (en) |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307320A (en) * | 2019-08-20 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information pushing method and device, mobile terminal and storage medium |
Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835087A (en) * | 2015-04-30 | 2015-08-12 | 泸州市金点教育科技有限公司 | Data processing method and apparatus for education test system |
| CN106682768A (en) * | 2016-12-08 | 2017-05-17 | 北京粉笔蓝天科技有限公司 | Prediction method, system, terminal and server of test score |
| CN107657559A (en) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | A kind of Chinese reading capability comparison method and system |
-
2019
- 2019-04-22 CN CN201910321952.6A patent/CN110046147A/en active Pending
Patent Citations (3)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104835087A (en) * | 2015-04-30 | 2015-08-12 | 泸州市金点教育科技有限公司 | Data processing method and apparatus for education test system |
| CN106682768A (en) * | 2016-12-08 | 2017-05-17 | 北京粉笔蓝天科技有限公司 | Prediction method, system, terminal and server of test score |
| CN107657559A (en) * | 2017-08-25 | 2018-02-02 | 北京享阅教育科技有限公司 | A kind of Chinese reading capability comparison method and system |
Cited By (1)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112307320A (en) * | 2019-08-20 | 2021-02-02 | 北京字节跳动网络技术有限公司 | Information pushing method and device, mobile terminal and storage medium |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Sghir et al. | Recent advances in Predictive Learning Analytics: A decade systematic review (2012–2022) | |
| Liu et al. | Fuzzy cognitive diagnosis for modelling examinee performance | |
| Douglas et al. | Challenges to assessing motivation in MOOC learners: An application of an argument-based approach | |
| WO2020010785A1 (en) | Classroom teaching cognitive load measuring system | |
| CN110516116A (en) | A kind of the learner's human-subject test method for digging and system of multistep layering | |
| Beck et al. | Limits to accuracy: how well can we do at student modeling? | |
| CN110502636A (en) | A kind of joint modeling and method for digging and system towards subjective and objective examination question | |
| CN106960245A (en) | A kind of individualized medicine evaluation method and system based on cognitive process chain | |
| CN112905784A (en) | Personalized test question recommendation method based on student portrait | |
| CN105205504A (en) | Image interest region quality evaluation index learning method based on data driving | |
| Wang et al. | Design of an adaptive examination system based on artificial intelligence recognition model | |
| Gowda et al. | Towards automatically detecting whether student learning is shallow | |
| Tu et al. | A polytomous model of cognitive diagnostic assessment for graded data | |
| CN117540104A (en) | Learning group difference evaluation method and system based on graph neural network | |
| Nithiyanandam et al. | Artificial intelligence assisted student learning and performance analysis using instructor evaluation model | |
| Zhou | Virtual Reality Revolutionizing Digital Marketing Design and Optimization of Online English Teaching in Universities with Wireless Network Technology Support in the Context of 5G | |
| CN116739858B (en) | Online learning behavior monitoring system based on time sequence analysis | |
| CN110046147A (en) | It is applicable in user's learning ability value-acquiring method and its application of Adaptable System | |
| CN109800880B (en) | Self-adaptive learning feature extraction system based on dynamic learning style information and application | |
| Wang et al. | Use machine learning to predict primary school students’ level of learning engagement | |
| CN105336235A (en) | Score setting method used for intelligent learning system | |
| Kardan et al. | A method to automatically construct a user knowledge model in a forum environment | |
| CN115205072A (en) | Cognitive diagnosis method for long-period evaluation | |
| Chen et al. | Design of Assessment Judging Model for Physical Education Professional Skills Course Based on Convolutional Neural Network and Few‐Shot Learning | |
| Han | An evaluation method of English online learning behaviour based on feature mining |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information |
Address after: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai, 2003 Applicant after: Shanghai squirrel classroom Artificial Intelligence Technology Co., Ltd Address before: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai, 2003 Applicant before: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. |
|
| CB02 | Change of applicant information | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190723 |
|
| RJ01 | Rejection of invention patent application after publication |