CN106384319A - Teaching resource personalized recommending method based on forgetting curve - Google Patents
Teaching resource personalized recommending method based on forgetting curve Download PDFInfo
- Publication number
- CN106384319A CN106384319A CN201610835330.1A CN201610835330A CN106384319A CN 106384319 A CN106384319 A CN 106384319A CN 201610835330 A CN201610835330 A CN 201610835330A CN 106384319 A CN106384319 A CN 106384319A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- teaching resource
- knowledge
- study
- current
- 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 56
- 230000000694 effects Effects 0.000 claims abstract description 39
- 238000011156 evaluation Methods 0.000 claims abstract description 7
- 230000003993 interaction Effects 0.000 claims description 60
- 230000008569 process Effects 0.000 claims description 29
- 230000002452 interceptive effect Effects 0.000 claims description 22
- 239000012141 concentrate Substances 0.000 claims description 9
- 238000010276 construction Methods 0.000 claims description 7
- 238000000605 extraction Methods 0.000 claims description 6
- 238000013467 fragmentation Methods 0.000 claims description 3
- 238000006062 fragmentation reaction Methods 0.000 claims description 3
- 238000012360 testing method Methods 0.000 claims description 3
- 230000002123 temporal effect Effects 0.000 claims description 2
- 210000004556 brain Anatomy 0.000 abstract description 6
- 238000007405 data analysis Methods 0.000 abstract description 4
- 238000005516 engineering process Methods 0.000 description 4
- 238000012552 review Methods 0.000 description 3
- 238000012549 training Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 2
- 230000006399 behavior Effects 0.000 description 2
- 238000005457 optimization Methods 0.000 description 2
- 235000010894 Artemisia argyi Nutrition 0.000 description 1
- 206010034719 Personality change Diseases 0.000 description 1
- 244000030166 artemisia Species 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000004891 communication Methods 0.000 description 1
- 230000007423 decrease Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 230000029087 digestion Effects 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012545 processing Methods 0.000 description 1
- 230000007115 recruitment Effects 0.000 description 1
- 238000011160 research Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (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)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The invention relates to the technical field of e-education, and discloses a teaching resource personalized recommending method based on a forgetting curve. The method comprises the steps: carrying out the big-data analysis of the current learning effect of a user in all knowledge points according to a human brain forgetting curve theory, and then quantitatively pushing a teaching resource, which is needed by a user the most, according to an evaluation result. Therefore, the method can solve a problem that the user has a selection obstacle when facing a large number of teaching resources, also can carries out the targeted personalized recommendation of the teaching resources according to the learning conditions of a user, also can bring convenience to the user for autonomous learning and self-learning, improves the learning efficiency, and facilitates the actual popularization and application.
Description
Technical field
A kind of the present invention relates to electronic field of Educational Technology, in particular it relates to teaching resource based on forgetting curve
Propertyization recommends method.
Background technology
With the continuous development of educational undertaking, the teaching resource based on the contents such as teaching notes, micro- class audio frequency and video or test question
(teaching resource issued especially on network) also extends continuous.In the face of the teaching resource of magnanimity, either student is also
It is that teacher feels at loose ends, that is, due to there is selection obstacle it is impossible to select suitable religion from the teaching resource of magnanimity
Learn resource, also cannot be directed to the individual study situation of student (due to the memory of each student, logicality and knowledge structure etc. no
Identical to the greatest extent, to the comprehension understanding of different problems, grasping expansion capability etc. also may not be consistent, such as student majored in liberal arts, students of science and technology etc.,
Each student learning efficiency is made to be likely to differ greatly) carry out targetedly teaching resource personalized recommendation.Thus no
By being traditional education or now relatively conventional online education, all it is difficult to solve to lead to the learning efficiency inclined because of individual diversity alienation
Low problem.
Content of the invention
For aforementioned problem of the prior art, the invention provides a kind of pushed away based on the teaching resource personalization of forgetting curve
Recommend method, it analyzes the current learning effect to each knowledge point for the user according to human brain forgetting curve theory come big data, then
According to assessment result quantitatively to user push in the urgent need to teaching resource, thus not only can solve user plane to magnanimity
Selection obstacle during teaching resource, can also be for the individual study situation of user, carries out targetedly teaching resource individual character
Change and recommend, and then user can be facilitated to carry out autonomous and self-aid learning, improve learning efficiency, be easy to actual promotion and application.
A kind of the technical solution used in the present invention, there is provided teaching resource personalized recommendation method based on forgetting curve,
Comprise the steps：S101. Cloud Server builds according to syllabus and/or examination outline and a set of comprises M knowledge point
Study system, and determine the correlation coefficient of any two knowledge points in study system, wherein, M is natural number；S102. cloud service
Device carries out fragmentation process successively to all of teaching resource, obtains each minimum teaching resource unit, then to all of
Little teaching Resource Unit carries out knowledge point cluster, obtains knowledge point corresponding with each knowledge point teaching resource pond；S103. interact
Interaction time information and study interaction data are uploaded to Cloud Server by terminal；S104. Cloud Server is to described study interaction number
According to carrying out knowledge point classification process, obtain multiple knowledge points knowledge point study interaction data, if exist this interactive terminal and
Comprise M knowledge point and the first data structure of knowledge point corresponding with each knowledge point learning process collection, then will be through extracting
To each knowledge point knowledge point study interaction data and described interaction time information be added to corresponding knowledge point and learnt
Cheng Jizhong, otherwise the first data structure according to described study system construction, and make M in described first data structure to know
Know point to correspond with M knowledge point in described study system, then again by the knowledge of each knowledge point through being obtained by extraction
Point study interaction data and described interaction time information are added to corresponding knowledge point learning process and concentrate；S105. it is directed to each
Knowledge point, Cloud Server builds the memory phantom based on forgetting curve according to corresponding knowledge point learning process collection, obtains
The current memory percentage ratio of this knowledge point；S106. Cloud Server is according to the current memory percentage ratio and any two of each knowledge point
The correlation coefficient of knowledge point, calculates the current learning effect assessed value of each knowledge point, if there is this interactive terminal and comprise M
Individual knowledge point and the second data structure of current learning effect assessed value corresponding with each knowledge point, then update each knowledge point
Current learning effect assessed value, otherwise according to described study system construction described in the second data structure, and make described second number
Correspond with M knowledge point in described study system according to M knowledge point in structure, then update working as of each knowledge point
Front learning effect assessed value；S107. Cloud Server, from described second data structure, searches current learning effect assessed value minimum
Knowledge point, then push quantitative teaching resource corresponding with this knowledge point to this interactive terminal, described quantitative teaching resource is calmly
Amount ground is randomly drawed from the teaching resource pond of knowledge point corresponding with this knowledge point and is obtained.
Optimize, in described step S106, Cloud Server calculates the current study of each knowledge point according to equation below
Recruitment evaluation value：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), ki,jIt is i-th knowledge point and j-th knowledge point in study system
Correlation coefficient, α1And η1It is respectively weight coefficient, i and j is respectively the natural number being not more than M.
Optimize, when described study interaction data comprises examination data, then also include as follows in described step S105
Step：For each knowledge point, Cloud Server is according to exam-oriented education evaluation index to the institute being in knowledge point learning process concentration
State examination data to be estimated, obtain the current grasp percentage ratio of this knowledge point；Then in described step S106, Cloud Server
According to current memory percentage ratio, the current correlation coefficient grasping percentage ratio and any two knowledge points of each knowledge point, calculate each
The current learning effect assessed value of individual knowledge point.
Optimize further, in described step S106, Cloud Server calculates working as of each knowledge point according to equation below
Front learning effect assessed value：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
QiFor the current grasp percentage ratio of i-th knowledge point, RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), QjFor j-th
The current grasp percentage ratio of knowledge point, ki,jIt is the correlation coefficient of i-th knowledge point and j-th knowledge point in study system,
α2、β2And η2It is respectively weight coefficient, i and j is respectively the natural number being not more than M.
Optimize, after described step S107, also comprise the steps：Interactive terminal is receiving described quantitative teaching money
Behind source, generate secondary study interaction data, then by the secondary interaction time information of record and described secondary study interaction data
It is uploaded to Cloud Server, be then back to execution step S104.
Optimize, after described step S104, also comprise the steps：When described knowledge point learning process concentrates knowledge
The record number of times of point study interaction data exceedes first threshold or when data capacity exceedes Second Threshold, then delete interaction time
Early knowledge point study interaction data and corresponding interaction time information.
Optimize, described teaching resource includes teaching notes, micro- class audio frequency and video and/or test question.
Optimize, described interactive terminal is smart mobile phone, panel computer, desktop computer, notebook computer, intelligent TV set
Or VR/AR equipment.
Optimize, the described step carrying out knowledge point cluster adopts K-Means algorithm.
To sum up, using a kind of teaching resource personalized recommendation method based on forgetting curve provided by the present invention, have
Following beneficial effect：(1) the method is current to each knowledge point come big data analysis user according to human brain forgetting curve theory
Learning effect, then according to assessment result quantitatively to user push in the urgent need to teaching resource, thus can solve use
Selection obstacle during magnanimity teaching resource faced by family；(2) the individual study situation of user can be directed to, targetedly taught
Learn individualized resource to recommend, and then user can be facilitated to carry out autonomous and self-aid learning, improve learning efficiency；(3) pass through for use
Family/interactive terminal and the data structure that builds, can intuitively fully understand the individual learning process situation of user and individual learn
Practise effect situation, facilitate teacher, student or the head of a family to grasp；(4) can avoid passively educating, conveniently realize individualized education, make
Teacher can accomplish to shoot the arrow at the target for different students in education activities, improve teaching efficiency, be easy to actual popularization with
Application.
Brief description
In order to be illustrated more clearly that the embodiment of the present invention or technical scheme of the prior art, below will be to embodiment or existing
Have technology description in required use accompanying drawing be briefly described it should be apparent that, drawings in the following description be only this
Some embodiments of invention, for those of ordinary skill in the art, on the premise of not paying creative work, acceptable
Other accompanying drawings are obtained according to these accompanying drawings.
Fig. 1 is the schematic flow sheet of the teaching resource personalized recommendation method based on forgetting curve that the present invention provides.
Specific embodiment
Hereinafter with reference to accompanying drawing, describe the teaching based on forgetting curve of present invention offer in detail by way of example
Resource individuation recommendation method.Here is it should be noted that the explanation for these way of example is used to help understand this
Bright, but do not constitute limitation of the invention.
The terms "and/or", only a kind of incidence relation of description affiliated partner, represents there may be three kinds of passes
System, for example, A and/or B, can represent：, there are tri- kinds of situations of A and B, the terms in individualism A, individualism B simultaneously
"/and " it is another kind of affiliated partner relation of description, represent there may be two kinds of relations, for example, and A/ and B, can represent：Individually deposit
In A, two kinds of situations of individualism A and B, in addition, character "/" herein, typically represent forward-backward correlation and close to liking a kind of "or"
System.
Embodiment one
Fig. 1 shows that the flow process of the teaching resource personalized recommendation method based on forgetting curve that the present invention provides is illustrated
Figure.The described teaching resource personalized recommendation method based on forgetting curve that the present embodiment provides, as follows including step.
S101. Cloud Server builds a set of study body comprising M knowledge point according to syllabus and/or examination outline
System, and determine the correlation coefficient of any two knowledge points in study system, wherein, M is natural number.
In described step S101, described Cloud Server is communication connection teaching resource server and each interactive terminal
Cloud device, for executing the key step of described teaching resource personalized recommendation method.Described syllabus and described examination
Outline can towards the term (i.e. learning age section) or towards certain section's purpose, it can be, but not limited to including double
The outline content such as base training (rudimentary knowledge training and basic skill training) or outward bound.Described knowledge point is minimum knowledge
Unit, such as knowledge trifle, language word and/or language syntax point etc..According to the correlation coefficient of described any two knowledge points
The priority continuous relationship of two knowledge points and interrelated relation and the numerical value between 0～1 determining, it can be artificial
Set it is also possible to determine, its numerical value shows that more greatly the dependency of two knowledge points (can be managed according to the Co-word analysis method of two knowledge points
Solve as similarity degree) higher, and numerical value is less shows that the dependency of two knowledge points is lower, such as the knowledge of grammar point in linguisticss
With geometry intermediate cam functional knowledge point, just there is no dependency completely, both correlation coefficienies are 0.
S102. Cloud Server carries out fragmentation process successively to all of teaching resource, obtains each minimum teaching resource
Unit, then carries out knowledge point cluster to all of minimum teaching resource unit, obtains knowledge point corresponding with each knowledge point
Teaching resource pond.
In described step S102, described teaching resource can be, but not limited to including teaching notes, micro- class audio frequency and video and/or examination
The resources such as topic.Minimum teaching resource list under affiliated knowledge point for multiple ownership is included in the teaching resource pond of described knowledge point
Unit.The described step carrying out knowledge point cluster can be, but not limited to using clustering algorithms such as K-Means algorithms.Described K-
Means algorithm is a kind of very typical clustering algorithm based on distance, using distance as the evaluation index of similarity, that is, thinks
The distance of two objects is nearer, and its similarity is bigger.Can be, but not limited to directly pass through Co-word analysis method in the present embodiment
To determine the dependency of two minimum teaching resource units, and then to be used as the evaluation index of similarity with dependency alternative distances.
S103. interaction time information and study interaction data are uploaded to Cloud Server by interactive terminal.
In described step S103, electronics that described interactive terminal is in the possession of the user and for electronic education and study
Equipment, it can be, but not limited to as smart mobile phone, panel computer, desktop computer, notebook computer, intelligent TV set or VR/AR
The electronic equipments such as equipment.Described interaction time information carries out man-machine interaction learning behavior (example for user using described interactive terminal
As online review, synchronization job or mock examination etc.) temporal information, its can be, but not limited to comprise to learn interaction time point and
Study interaction duration etc., additionally, described interaction time information keeps one with the data type of follow-up secondary interaction time information
Cause.Described study interaction data be user when carrying out man-machine interaction learning behavior, the data that recorded by described interactive terminal, its
Can be, but not limited to learn content (such as English glossary, each subject knowledge point and entertaining encyclopaedia etc.) or produced by user response
Feedback data (is for example directed to the examination data of mock examination).Additionally, described study interaction data and follow-up secondary study are handed over
Mutually the data type of data is consistent.
S104. Cloud Server application class algorithm carries out extraction processing to described study interaction data, obtains multiple knowledge
, if there is this interactive terminal and comprise M knowledge point and corresponding with each knowledge point in the knowledge point study interaction data of point
First data structure of knowledge point learning process collection, then learn interaction data by the knowledge point of each knowledge point through being obtained by extraction
It is added to corresponding knowledge point learning process with described interaction time information to concentrate, otherwise according to described study system construction
First data structure, and make M knowledge point in described first data structure and M knowledge point in described study system one by one
Corresponding, then again the knowledge point study interaction data of each knowledge point through being obtained by extraction and described interaction time information are added
Concentrate to corresponding knowledge point learning process.
After described step S104, optimization, also comprise the steps：When described knowledge point learning process concentrates knowledge
The record number of times of point study interaction data exceedes first threshold (such as 9 times) or data capacity exceedes Second Threshold (such as 10M ratio
Special) when, then delete the earliest knowledge point study interaction data of interaction time and corresponding interaction time information.Arranged by aforementioned
Apply, can early stage record data, make the first data structure maintain the scale that can safeguard, improve the process speed of subsequent step
Degree.
S105. it is directed to each knowledge point, Cloud Server builds bent based on forgeing according to corresponding knowledge point learning process collection
The memory phantom of line, obtains the current memory percentage ratio of this knowledge point.
In described step S105, described forgetting curve can be, but not limited to as guest's this forgetting curve great that ends, this forgetting song
Line is found by Chinese mugwort guest this (Hermann Ebbinghaus, 1850-1909) the great research of German psychologist, which depict the mankind big
The rule that brain is forgotten to new things：Prolongation over time, human brain is in decreases in non-linear trend to the memory percentage ratio of new things,
Thus can according to knowledge point learning process concentrate interaction time information architecture one be directed to corresponding knowledge point and based on forgeing
The memory phantom of curve, and obtain the current memory percentage ratio of corresponding knowledge point, if concentrating not in knowledge point learning process
There is any interaction time information, then the current memory percentage ratio initially corresponding to knowledge point is zero.Additionally, optimize, when described
When study interaction data comprises examination data, then also comprise the steps in described step S105：For each knowledge point, cloud
Server is estimated to the described examination data being in knowledge point learning process concentration according to exam-oriented education evaluation index, obtains
The current grasp percentage ratio of this knowledge point.Described current percentage ratio of grasping can be, but not limited to directly adopt obtaining of hundred-mark system examination
Dividing and to represent, if concentrate in knowledge point learning process there is not any examination data, initially corresponding to the current grasp of knowledge point
Percentage ratio is zero.
S106. the correlation coefficient of the current memory percentage ratio according to each knowledge point for the Cloud Server and any two knowledge points,
Calculate the current learning effect assessed value of each knowledge point, if there is this interactive terminal and comprise M knowledge point and and each
Second data structure of the corresponding current learning effect assessed value in knowledge point, then the current learning effect updating each knowledge point is commented
Valuation, otherwise the second data structure according to described study system construction, and make M knowledge in described second data structure
Point is corresponded with M knowledge point in described study system, then updates the current learning effect assessed value of each knowledge point.
In described step S106, Cloud Server calculates the current learning effect assessment of each knowledge point according to equation below
Value：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), ki,jIt is i-th knowledge point and j-th knowledge point in study system
Correlation coefficient, α1And η1It is respectively weight coefficient, i and j is respectively the natural number being not more than M.As an example, in this enforcement
In example, described weight coefficient α1It is set to 0.618, described weight coefficient η1It is set to 0.382.
If obtaining in described step S105 has the current grasp percentage ratio of each knowledge point, in described step S106
In, Cloud Server is according to the correlation of the current memory percentage ratio, current grasp percentage ratio and any two knowledge points of each knowledge point
Coefficient, calculates the current learning effect assessed value of each knowledge point.And in described step S106, Cloud Server is according to following public affairs
Formula calculates the current learning effect assessed value of each knowledge point：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
QiFor the current grasp percentage ratio of i-th knowledge point, RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), QjFor j-th
The current grasp percentage ratio of knowledge point, ki,jIt is the correlation coefficient of i-th knowledge point and j-th knowledge point in study system,
α2、β2And η2It is respectively weight coefficient, i and j is respectively the natural number being not more than M.As an example, in the present embodiment, described
Weight coefficient α2It is set to 0.382, described weight coefficient β2It is set to 0.236, described weight coefficient η2It is set to 0.382.
Additionally, in described step S106 according to described study system construction described in the second data structure when, initially each
The current learning effect assessed value of knowledge point is zero, so that follow-up update.
S107. Cloud Server, from described second data structure, searches the minimum knowledge point of current learning effect assessed value,
Then to this interactive terminal push quantitative teaching resource corresponding with this knowledge point, described quantitative teaching resource quantitatively from this
Randomly draw in the teaching resource pond of the corresponding knowledge point in knowledge point and obtain.
In described step S107, quantitatively refer to that the data capacity of educational resource obtained by randomly drawing is less than the 3rd threshold value
(such as 10M bit), in order to avoid the educational resource pushing is excessive, user is difficult to study digestion.In addition, described step S107 it
Afterwards, optimization, also comprises the steps：Interactive terminal, after receiving described quantitative teaching resource, generates secondary study interaction number
According to, then by record secondary interaction time information and described secondary study interaction data be uploaded to Cloud Server, be then back to
Execution step S104.Push thus by cyclically carrying out data analysiss and teaching resource, it is possible to achieve people and Cloud Server
Real-time, interactive：Targetedly new interpersonal study interbehavior can be carried out according to the quantitative teaching resource being pushed, produce
New study interaction data, then uploads the new material forming big data analysis, and then revises described first data structure and the
Two data structures, push more suitably individualized teaching resource, optimize the review content of user and review the learning strategy such as intensity,
Effectively reduce study intensity, improve learning efficiency.
To sum up, the teaching resource personalized recommendation method based on forgetting curve that the present embodiment is provided, has following skill
Art effect：(1) the method analyzes the current study effect to each knowledge point for the user according to human brain forgetting curve theory come big data
Really, then according to assessment result quantitatively to user push in the urgent need to teaching resource, thus can solve user plane pair
Selection obstacle during magnanimity teaching resource；(2) the individual study situation of user can be directed to, carry out targetedly teaching resource
Personalized recommendation, and then user can be facilitated to carry out autonomous and self-aid learning, improve learning efficiency；(3) by for user/interaction
Terminal and the data structure that builds, can intuitively fully understand the individual learning process situation of user and individual learning effect feelings
Condition, facilitates teacher, student or the head of a family to grasp；(4) can avoid passively educating, conveniently realize individualized education so that teacher exists
Can accomplish to shoot the arrow at the target for different students in education activities, improve teaching efficiency, be easy to actual promotion and application.
As described above, the present invention can preferably be realized.For a person skilled in the art, the religion according to the present invention
Lead, that designs multi-form does not need performing creative labour based on the teaching resource personalized recommendation method of forgetting curve.
Without departing from the principles and spirit of the present invention these embodiments are changed, change, replace, integrating and modification still
Fall within the scope of protection of the present invention.
Claims (9)
1. a kind of teaching resource personalized recommendation method based on forgetting curve is it is characterised in that comprise the steps：
S101. Cloud Server builds a set of study system comprising M knowledge point according to syllabus and/or examination outline,
And determine the correlation coefficient of any two knowledge points in study system, wherein, M is natural number；
S102. Cloud Server carries out fragmentation process successively to all of teaching resource, obtains each minimum teaching resource unit,
Then knowledge point cluster is carried out to all of minimum teaching resource unit, obtain teaching money in knowledge point corresponding with each knowledge point
Source pond；
S103. interaction time information and study interaction data are uploaded to Cloud Server by interactive terminal；
S104. Cloud Server carries out knowledge point classification process to described study interaction data, obtains the knowledge point of multiple knowledge points
, if there is this interactive terminal and comprise M knowledge point and knowledge point corresponding with each knowledge point and learn in study interaction data
First data structure of process collection, then by the knowledge point study interaction data of each knowledge point through being obtained by extraction and described interaction
Temporal information is added to corresponding knowledge point learning process and concentrates, otherwise the first data knot according to described study system construction
Structure, and so that M knowledge point in described first data structure is corresponded with M knowledge point in described study system, then
Again the knowledge point study interaction data of each knowledge point through being obtained by extraction and described interaction time information are added to corresponding
Knowledge point learning process is concentrated；
S105. it is directed to each knowledge point, Cloud Server builds based on forgetting curve according to corresponding knowledge point learning process collection
Memory phantom, obtains the current memory percentage ratio of this knowledge point；
S106. the correlation coefficient of the current memory percentage ratio according to each knowledge point for the Cloud Server and any two knowledge points, calculates
The current learning effect assessed value of each knowledge point, if there is this interactive terminal and comprise M knowledge point and with each knowledge
Second data structure of the corresponding current learning effect assessed value of point, then update the current learning effect assessment of each knowledge point
Value, otherwise the second data structure according to described study system construction, and make M knowledge point in described second data structure
Correspond with M knowledge point in described study system, then update the current learning effect assessed value of each knowledge point；
S107. Cloud Server, from described second data structure, searches the minimum knowledge point of current learning effect assessed value, then
To this interactive terminal push quantitative teaching resource corresponding with this knowledge point, described quantitative teaching resource quantitatively from this knowledge
Randomly draw in point corresponding knowledge point teaching resource pond and obtain.
2. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that
In described step S106, Cloud Server calculates the current learning effect assessed value of each knowledge point according to equation below：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), ki,jIt is i-th knowledge point and j-th knowledge point in study system
Correlation coefficient, α1And η1It is respectively weight coefficient, i and j is respectively the natural number being not more than M.
3. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that work as
When described study interaction data comprises examination data, then also comprise the steps in described step S105：For each knowledge
Point, Cloud Server is commented to the described examination data being in knowledge point learning process concentration according to exam-oriented education evaluation index
Estimate, obtain the current grasp percentage ratio of this knowledge point；
Then, in described step S106, Cloud Server is according to the current memory percentage ratio of each knowledge point, currently grasp percentage
The correlation coefficient with any two knowledge points for the ratio, calculates the current learning effect assessed value of each knowledge point.
4. as claimed in claim 3 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that
In described step S106, Cloud Server calculates the current learning effect assessed value of each knowledge point according to equation below：
In formula, PiFor the current learning effect assessed value of i-th knowledge point, RiFor the current memory percentage ratio of i-th knowledge point,
QiFor the current grasp percentage ratio of i-th knowledge point, RjThe current memory percentage ratio of the individual knowledge point of jth (j ≠ i), QjFor j-th
The current grasp percentage ratio of knowledge point, ki,jIt is the correlation coefficient of i-th knowledge point and j-th knowledge point in study system,
α2、β2And η2It is respectively weight coefficient, i and j is respectively the natural number being not more than M.
5. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that
After described step S107, also comprise the steps：Interactive terminal, after receiving described quantitative teaching resource, generates secondary study
Then the secondary interaction time information of record and described secondary study interaction data are uploaded to Cloud Server, so by interaction data
Return execution step S104 afterwards.
6. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that
After described step S104, also comprise the steps：When described knowledge point learning process concentrates knowledge point to learn interaction data
Record number of times exceedes first threshold or when data capacity exceedes Second Threshold, then delete the earliest knowledge point study of interaction time and hand over
Mutually data and corresponding interaction time information.
7. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that institute
State teaching resource and include teaching notes, micro- class audio frequency and video and/or test question.
8. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that institute
Stating interactive terminal is smart mobile phone, panel computer, desktop computer, notebook computer, intelligent TV set or VR/AR equipment.
9. as claimed in claim 1 a kind of teaching resource personalized recommendation method based on forgetting curve it is characterised in that
K-Means algorithm is adopted in the described step carrying out knowledge point cluster.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610835330.1A CN106384319A (en) | 2016-09-20 | 2016-09-20 | Teaching resource personalized recommending method based on forgetting curve |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201610835330.1A CN106384319A (en) | 2016-09-20 | 2016-09-20 | Teaching resource personalized recommending method based on forgetting curve |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN106384319A true CN106384319A (en) | 2017-02-08 |
Family
ID=57936955
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201610835330.1A Pending CN106384319A (en) | 2016-09-20 | 2016-09-20 | Teaching resource personalized recommending method based on forgetting curve |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN106384319A (en) |
Cited By (15)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220916A (en) * | 2017-05-27 | 2017-09-29 | 邹杰 | Pushing learning resource method and device |
| CN108874935A (en) * | 2018-06-01 | 2018-11-23 | 广东小天才科技有限公司 | Review content recommendation method based on voice search and electronic equipment |
| CN109389870A (en) * | 2017-08-10 | 2019-02-26 | 亿度慧达教育科技（北京）有限公司 | A kind of data adaptive method of adjustment and its device applied in electronic instruction |
| CN109446213A (en) * | 2018-10-16 | 2019-03-08 | 四川生学教育科技有限公司 | A kind of learning materials intelligently pushing method and device |
| CN109670110A (en) * | 2018-12-20 | 2019-04-23 | 蒋文军 | A kind of educational resource recommended method, device, equipment and storage medium |
| CN109739829A (en) * | 2019-01-15 | 2019-05-10 | 山东仁博信息科技有限公司 | A kind of student knowledge system anlysis system based on ongoing operations |
| CN109767366A (en) * | 2019-01-08 | 2019-05-17 | 汪胜利 | A kind of computer radar system of real time scan analysis vocabulary memorization effect |
| CN110120001A (en) * | 2019-05-08 | 2019-08-13 | 成都佳发安泰教育科技股份有限公司 | The method and system that a kind of knowledge based spectrum library mentions point in conjunction with memory curve |
| CN110136498A (en) * | 2018-02-08 | 2019-08-16 | 上海趣烁科技有限公司 | A kind of break-through formula interaction curriculum system based on study plan |
| CN110505498A (en) * | 2019-09-03 | 2019-11-26 | 腾讯科技（深圳）有限公司 | Processing, playback method, device and the computer-readable medium of video |
| CN112015991A (en) * | 2020-08-31 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Student learning reminding method |
| CN112380335A (en) * | 2020-11-24 | 2021-02-19 | 中教云智数字科技有限公司 | Digital education resource recommendation system |
| CN113407097A (en) * | 2021-07-07 | 2021-09-17 | 字出印象(北京)科技有限公司 | Image display apparatus, method, device, and computer-readable storage medium |
| CN117726082A (en) * | 2024-02-18 | 2024-03-19 | 暗物智能科技(广州)有限公司 | Teaching resource recommendation method and device, electronic equipment and readable storage medium |
| CN118098515A (en) * | 2024-04-25 | 2024-05-28 | 徐州医科大学 | Memory enhancement method and course learning system based on annealing algorithm |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201812A (en) * | 2006-12-14 | 2008-06-18 | 英业达股份有限公司 | System and method for executive auxiliary learning of language word by computer |
| CN102346976A (en) * | 2011-03-03 | 2012-02-08 | 郭华 | Electronic device assisted learning method based on knowledge structure and effect feedback |
| CN105608075A (en) * | 2014-09-26 | 2016-05-25 | 北大方正集团有限公司 | Related knowledge point acquisition method and system |
| CN105761183A (en) * | 2016-03-14 | 2016-07-13 | 成都爱易佰网络科技有限公司 | Knowledge point system teaching method and adaptive teaching system based on knowledge point measurement |
-
2016
- 2016-09-20 CN CN201610835330.1A patent/CN106384319A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101201812A (en) * | 2006-12-14 | 2008-06-18 | 英业达股份有限公司 | System and method for executive auxiliary learning of language word by computer |
| CN102346976A (en) * | 2011-03-03 | 2012-02-08 | 郭华 | Electronic device assisted learning method based on knowledge structure and effect feedback |
| CN105608075A (en) * | 2014-09-26 | 2016-05-25 | 北大方正集团有限公司 | Related knowledge point acquisition method and system |
| CN105761183A (en) * | 2016-03-14 | 2016-07-13 | 成都爱易佰网络科技有限公司 | Knowledge point system teaching method and adaptive teaching system based on knowledge point measurement |
Cited By (20)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107220916A (en) * | 2017-05-27 | 2017-09-29 | 邹杰 | Pushing learning resource method and device |
| CN109389870A (en) * | 2017-08-10 | 2019-02-26 | 亿度慧达教育科技（北京）有限公司 | A kind of data adaptive method of adjustment and its device applied in electronic instruction |
| CN109389870B (en) * | 2017-08-10 | 2021-06-04 | 亿度慧达教育科技（北京）有限公司 | Data self-adaptive adjusting method and device applied to electronic teaching |
| CN110136498A (en) * | 2018-02-08 | 2019-08-16 | 上海趣烁科技有限公司 | A kind of break-through formula interaction curriculum system based on study plan |
| CN108874935A (en) * | 2018-06-01 | 2018-11-23 | 广东小天才科技有限公司 | Review content recommendation method based on voice search and electronic equipment |
| CN108874935B (en) * | 2018-06-01 | 2021-03-30 | 广东小天才科技有限公司 | Review content recommendation method based on voice search and electronic equipment |
| CN109446213A (en) * | 2018-10-16 | 2019-03-08 | 四川生学教育科技有限公司 | A kind of learning materials intelligently pushing method and device |
| CN109670110A (en) * | 2018-12-20 | 2019-04-23 | 蒋文军 | A kind of educational resource recommended method, device, equipment and storage medium |
| CN109767366A (en) * | 2019-01-08 | 2019-05-17 | 汪胜利 | A kind of computer radar system of real time scan analysis vocabulary memorization effect |
| CN109739829A (en) * | 2019-01-15 | 2019-05-10 | 山东仁博信息科技有限公司 | A kind of student knowledge system anlysis system based on ongoing operations |
| CN110120001A (en) * | 2019-05-08 | 2019-08-13 | 成都佳发安泰教育科技股份有限公司 | The method and system that a kind of knowledge based spectrum library mentions point in conjunction with memory curve |
| CN110120001B (en) * | 2019-05-08 | 2021-07-20 | 成都佳发安泰教育科技股份有限公司 | Method and system for scoring based on combination of knowledge graph library and memory curve |
| CN110505498A (en) * | 2019-09-03 | 2019-11-26 | 腾讯科技（深圳）有限公司 | Processing, playback method, device and the computer-readable medium of video |
| CN112015991A (en) * | 2020-08-31 | 2020-12-01 | 上海松鼠课堂人工智能科技有限公司 | Student learning reminding method |
| CN112380335A (en) * | 2020-11-24 | 2021-02-19 | 中教云智数字科技有限公司 | Digital education resource recommendation system |
| CN112380335B (en) * | 2020-11-24 | 2024-07-02 | 中教云智数字科技有限公司 | Digital education resource recommendation system |
| CN113407097A (en) * | 2021-07-07 | 2021-09-17 | 字出印象(北京)科技有限公司 | Image display apparatus, method, device, and computer-readable storage medium |
| CN117726082A (en) * | 2024-02-18 | 2024-03-19 | 暗物智能科技(广州)有限公司 | Teaching resource recommendation method and device, electronic equipment and readable storage medium |
| CN117726082B (en) * | 2024-02-18 | 2024-06-11 | 暗物智能科技(广州)有限公司 | Teaching resource recommendation method and device, electronic equipment and readable storage medium |
| CN118098515A (en) * | 2024-04-25 | 2024-05-28 | 徐州医科大学 | Memory enhancement method and course learning system based on annealing algorithm |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN106384319A (en) | Teaching resource personalized recommending method based on forgetting curve | |
| Gil-Flores et al. | Factors that explain the use of ICT in secondary-education classrooms: The role of teacher characteristics and school infrastructure | |
| Jiang et al. | Expert feature-engineering vs. deep neural networks: which is better for sensor-free affect detection? | |
| CN107145559B (en) | Intelligent classroom Knowledge Management Platform and method based on semantic technology and game | |
| Pham et al. | A method for detection of learning styles in learning management systems | |
| CN113723853A (en) | Method and device for processing post competence demand data | |
| Mamcenko et al. | On using learning analytics to personalise learning in virtual learning environments | |
| CN107092593B (en) | Sentence semantic role recognition method and system for elementary mathematics hierarchical sampling application questions | |
| Dahiya | A survey on educational data mining | |
| CN109299805B (en) | Artificial intelligence-based online education course request processing method | |
| CN114896975A (en) | Online education intelligent teaching-aid-oriented autonomous evolution method and system | |
| Du | Design and Application of Intelligent Classroom in English Language and Literature Based on Artificial Intelligence Technology | |
| CN106971354A (en) | A kind of instruction analysis system based on big data | |
| Qiang | [Retracted] The Impact of the Development of 5G Technologies on the Ideological and Political Education of College Students | |
| Li | Convolutional Neural Network‐Based Mining of Civic Science Elements and Teaching Practice | |
| CN106126611A (en) | A kind of figure methods of exhibiting of teaching efficiency | |
| Tonita | Inclusive education: Developments and challenges in the Romanian education system | |
| CN110033402A (en) | Thinking mathematical studying method and computer learning system based on capacity sizing | |
| Zhu | Design and Application of an Intelligent Remote Learning System Based on Network Communication | |
| Zhao | Research on Educational Information Management System Based on Computer Big Data | |
| Ivanova et al. | Application of Artificial Neural Networks in Intelligent Tutoring: A Contemporary Glance | |
| Sirekanyan | Mind-map technology in foreign language teaching | |
| KR102599368B1 (en) | System for customized content providing based on big data and method the same | |
| Zheng | [Retracted] Analyzing College Students’ Reading Behavior by AI Techniques | |
| Yan | Research on innovative model of piano informatization teaching under the background of big data and soft computing |
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 |
Application publication date: 20170208 |
|
| RJ01 | Rejection of invention patent application after publication |