CN108647363A - Map construction, display methods, device, equipment and storage medium - Google Patents
Map construction, display methods, device, equipment and storage medium Download PDFInfo
- Publication number
- CN108647363A CN108647363A CN201810489378.0A CN201810489378A CN108647363A CN 108647363 A CN108647363 A CN 108647363A CN 201810489378 A CN201810489378 A CN 201810489378A CN 108647363 A CN108647363 A CN 108647363A
- Authority
- CN
- China
- Prior art keywords
- node
- illustrative plates
- probability
- collection
- rudimental
- 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 46
- 238000010276 construction Methods 0.000 title claims abstract description 34
- 238000005457 optimization Methods 0.000 claims abstract description 22
- 239000011159 matrix material Substances 0.000 claims description 88
- 238000013507 mapping Methods 0.000 claims description 60
- 238000012546 transfer Methods 0.000 claims description 21
- 230000007704 transition Effects 0.000 claims description 12
- 238000012163 sequencing technique Methods 0.000 claims description 7
- 238000004590 computer program Methods 0.000 claims description 6
- 238000005194 fractionation Methods 0.000 claims description 6
- 230000003044 adaptive effect Effects 0.000 abstract description 10
- 238000004364 calculation method Methods 0.000 description 15
- 230000008569 process Effects 0.000 description 14
- 238000011160 research Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 9
- 230000019771 cognition Effects 0.000 description 7
- 238000004891 communication Methods 0.000 description 7
- 238000012545 processing Methods 0.000 description 5
- 230000006870 function Effects 0.000 description 4
- 238000004458 analytical method Methods 0.000 description 3
- 238000001228 spectrum Methods 0.000 description 3
- 230000008859 change Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 238000010801 machine learning Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000004422 calculation algorithm Methods 0.000 description 1
- 230000000694 effects Effects 0.000 description 1
- 230000005611 electricity Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 238000011835 investigation Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000011002 quantification Methods 0.000 description 1
- 238000012360 testing method Methods 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
Landscapes
- Business, Economics & Management (AREA)
- Tourism & Hospitality (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Economics (AREA)
- General Health & Medical Sciences (AREA)
- Educational Administration (AREA)
- Marketing (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
This application discloses a kind of map construction, display methods, device, equipment and storage mediums, by obtaining rudimental knowledge collection of illustrative plates, the rudimental knowledge collection of illustrative plates includes directed line segment between several nodes and node, node on behalf meets a kind of topic to impose a condition, it is connected each other according to the logic of teaching between two nodes connected by directed line segment, adaptive learning can be supported based on the rudimental knowledge collection of illustrative plates.Further, the answer of all kinds of topics is recorded according to object, determines Grasping level of the object to each node in rudimental knowledge collection of illustrative plates;According to object to the Grasping level of each node in rudimental knowledge collection of illustrative plates, determine the attribute information of each node, the attribute information is used to instruct the learning sequence between node, and/or the structure optimization of rudimental knowledge collection of illustrative plates is instructed to adjust, and better support is provided for the practical application of collection of illustrative plates.
Description
Technical field
This application involves online education technical field, more specifically to a kind of map construction, display methods, device,
Equipment and storage medium.
Background technology
With the arrival of internet and big data epoch, traditional educational mode is increasingly difficult to growing to meet student
Individualized learning demand.The features such as adaptive on-line study teaches students in accordance with their aptitude due to it and is easy to use, starts gradually extensive
It uses.
The important component of adaptive learning is that student ability assessment and education resource are recommended, these are required for being based on one
The education sector knowledge hierarchy of a structuring.Therefore, a padagogical knowledge collection of illustrative plates is built to support adaptive learning to become current
Problem in the urgent need to address.
Invention content
In view of this, this application provides a kind of map construction, display methods, device, equipment and storage medium, it to be used for structure
Padagogical knowledge collection of illustrative plates is built to support adaptive learning.
To achieve the goals above, it is proposed that scheme it is as follows:
A kind of map construction method, including:
Rudimental knowledge collection of illustrative plates is obtained, the rudimental knowledge collection of illustrative plates includes directed line segment between several nodes and node, the section
Point represents a kind of topic for meeting and imposing a condition, and is mutually interconnected according to the logic of teaching between two nodes connected by directed line segment
System;
The answer of all kinds of topics is recorded according to object, determines grasp of the object to each node in the rudimental knowledge collection of illustrative plates
Degree;
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, the attribute information of each node, institute are determined
Attribute information is stated for instructing the learning sequence between node, and/or the structure optimization adjustment of the guidance rudimental knowledge collection of illustrative plates.
Preferably, described that the answer of all kinds of topics is recorded according to object, determine object in the rudimental knowledge collection of illustrative plates
The Grasping level of each node, including:
For each node in the rudimental knowledge collection of illustrative plates, the answer for corresponding to topic to the node according to object records,
Computing object corresponds to the average rate of topic in the node;
The average rate that object is corresponded to topic in the node, is determined as Grasping level of the object to the node.
Preferably, it is described according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determine each node
Attribute information, including:
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determines in the rudimental knowledge collection of illustrative plates and lead to
It crosses between two nodes of directed line segment connection and redirects probability, as the probability that redirects between priori node, described to redirect probability anti-
The learning sequence between node is reflected.
Preferably, it is described according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determine each node
Attribute information further includes:
Topic is corresponded to described to the Grasping level of each node in the rudimental knowledge collection of illustrative plates and each node according to object
Sequencing in answer record determines and redirects probability between any two node, probability is redirected as between posteriority node.
Preferably, Grasping level includes having grasped and not grasped;
It is described according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determine the rudimental knowledge collection of illustrative plates
In redirect probability between two nodes being connected by directed line segment, including:
For two nodes connected by directed line segment in the rudimental knowledge collection of illustrative plates:Preposition node and descendant node,
According to the quantity for the object that do not grasped to the descendant node, and meets and the descendant node is not grasped and to described preposition
The quantity for the object that node has been grasped, calculates the descendant node and redirects the first of preposition node and redirect probability;The preposition section
Point is directed toward the descendant node by directed line segment;
According to the quantity for the object grasped to the preposition node, and meet to the preposition node and described subsequent
The quantity for the object that node has been grasped, the calculating preposition node redirect the second of the descendant node and redirect probability.
Preferably, Grasping level includes having grasped and not grasped;
It is described according to object to the grasp of each node in the rudimental knowledge collection of illustrative plates as a result, and each node correspond to topic and exist
Sequencing in answer record determines the probability that redirects between any two node, including:
It is respectively first node and second node to define any two node in the rudimental knowledge collection of illustrative plates;
It is recorded according to the answer, determines and entitled elder generation is corresponded to first node, second node corresponds to entitled rear sequence
First object set of answer, and entitled elder generation is corresponded to second node, first node corresponds to entitled rear sequence answer
Second object set;
According in first object set, to the quantity for the object that the first node is not grasped, and meet to institute
The quantity of object that first node is not grasped and grasped to the second node is stated, the first node is calculated and redirects the second section
The third of point redirects probability;
According in first object set, to the quantity for the object that the first node has been grasped, and meet to institute
The quantity for stating the object that first node and the second node have been grasped calculates the first node redirects second node
Four redirect probability;
According in second object set, to the quantity for the object that the second node is not grasped, and meet to institute
The quantity of object that second node is not grasped and grasped to the first node is stated, the second node is calculated and redirects first segment
The fifth jump of point turns probability;
According in second object set, to the quantity for the object that the second node has been grasped, and meet to institute
The quantity for stating the object that second node and the first node have been grasped calculates the second node redirects first node
Six redirect probability.
Preferably, it is described according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determine each node
Attribute information further includes:
Probability is redirected according between the priori node, determines the significance level of each node, the significance level is for referring to
Lead the structure optimization adjustment of the rudimental knowledge collection of illustrative plates.
Preferably, described to redirect probability according between the priori node, determine the significance level of each node, including:
Probability is redirected according between the priori node, determines in the rudimental knowledge collection of illustrative plates that the transfer between node two-by-two is general
Rate forms probability transfer matrix;
According to preset start node significance level matrix and the probability transfer matrix, the final node weight of grey iterative generation
It includes the significance level of each node to want degree matrix, final node significance level matrix.
Preferably, described to redirect probability according between the priori node, it determines and is saved two-by-two in the rudimental knowledge collection of illustrative plates
Transition probability between point, including:
For any two node x in the rudimental knowledge collection of illustrative platesjAnd xi, decision node xiWhether it is node xjIt is preposition
Node;J and i values are [1, n], and n is node total number;
If not, it is determined that node xjTo node xiTransition probability be 0;
If so, according to node xjRedirect its each preposition node first redirects probability, determines node xjTo node xi's
Transition probability.
Preferably, described according to preset start node significance level matrix and the probability transfer matrix, grey iterative generation
Final node significance level matrix, including:
Using the start node significance level matrix as objective matrix;
The objective matrix is multiplied with the probability transfer matrix, obtains multiplied result;
Judge whether the multiplied result and the difference of the objective matrix reach the setting condition of convergence;
If so, the multiplied result to be determined as to final node significance level matrix;
If it is not, using the multiplied result as objective matrix, it is described by the objective matrix and the probability to return to execution
The step of transfer matrix is multiplied.
Preferably, further include:
Determine that significance level is less than the node of setting significance level lower threshold value, as low importance node;
The low importance node is deleted from the rudimental knowledge collection of illustrative plates, and by the preposition of the low importance node
Node is connect entirely with the descendant node of the low importance node, is adjusted rear knowledge mapping.
Preferably, further include:
Determine that significance level is more than the node of setting significance level upper threshold value, as high importance node;
According to preset fractionation rule, the high importance node is split into several child nodes;
The preposition node of the high importance node is connect entirely with each child node, by the high importance node
Descendant node is connect entirely with each child node, is adjusted rear knowledge mapping.
Preferably, further include:
Probability is redirected according between the posteriority node, structural adjustment is carried out to the rudimental knowledge collection of illustrative plates.
A kind of collection of illustrative plates display methods, including:
Explicit knowledge's collection of illustrative plates, the knowledge mapping include directed line segment between several nodes and node, and the node on behalf is full
A kind of topic to impose a condition enough;Pass through the logic according to teaching between two nodes of directed line segment connection in the knowledge mapping
It connects each other.
Preferably, further include:
Show the probability that redirects between two nodes being connected by directed line segment, the probability that redirects reflects between node
Learning sequence.
Preferably, further include:
Corresponding with each node node learning path of display, the clooating sequence of each node reflects in the node learning path
The learning sequence of each node, the learning sequence of each node is determined according to the probability that redirects between each node.
A kind of map construction device, including:
Rudimental knowledge collection of illustrative plates acquiring unit, for obtaining rudimental knowledge collection of illustrative plates, the rudimental knowledge collection of illustrative plates includes several sections
Directed line segment between point and node, the node on behalf meet a kind of topic to impose a condition, two connected by directed line segment
It is connected each other according to the logic of teaching between node;
Grasping level determination unit determines object to described preliminary for being recorded to the answer of all kinds of topics according to object
The Grasping level of each node in knowledge mapping;
Attribute information determination unit is used for according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, really
The attribute information of fixed each node, the attribute information are used to instruct the learning sequence between node, and/or the guidance rudimental knowledge
The structure optimization of collection of illustrative plates adjusts.
Preferably, the Grasping level determination unit includes:
Average rate computing unit, for being directed to each node in the rudimental knowledge collection of illustrative plates, according to object to described
Node corresponds to the answer record of topic, and computing object corresponds to the average rate of topic in the node;
Average rate determination unit is determined as pair for object to be corresponded to the average rate of topic in the node
As the Grasping level to the node.
Preferably, the attribute information determination unit includes:
Priori redirects probability determining unit, is used for according to object to the grasp journey of each node in the rudimental knowledge collection of illustrative plates
Degree determines and redirects probability between two nodes connected by directed line segment in the rudimental knowledge collection of illustrative plates, as priori node
Between redirect probability, the probability that redirects reflects learning sequence between node.
Preferably, the attribute information determination unit further includes:
Posteriority redirects probability determining unit, is used for according to object to the grasp journey of each node in the rudimental knowledge collection of illustrative plates
Degree and each node correspond to sequencing of the topic in the answer records, and determine and redirect probability between any two node,
Probability is redirected as between posteriority node.
Preferably, Grasping level includes having grasped and not grasped;
The priori redirects probability determining unit:
First redirects probability calculation unit, for for two connected by directed line segment in the rudimental knowledge collection of illustrative plates
Node:Preposition node and descendant node according to the quantity for the object that do not grasped to the descendant node, and meet to after described
After the quantity for the object that node is not grasped and has been grasped to the preposition node, calculates the descendant node and redirect preposition node
First redirects probability;The preposition node is directed toward the descendant node by directed line segment;
Second redirects probability calculation unit, for the quantity according to the object grasped to the preposition node, Yi Jiman
The quantity of object that foot has grasped the preposition node and the descendant node, calculate the preposition node redirect it is described after
Second after node redirects probability.
Preferably, Grasping level includes having grasped and not grasped;
The posteriority redirects probability determining unit:
Node definition unit is respectively first node and for defining any two node in the rudimental knowledge collection of illustrative plates
Two nodes;
Object set determination unit determined and corresponds to entitled elder generation with first node for being recorded according to the answer, second
Node corresponds to the first object set of entitled rear sequence answer, and corresponds to entitled elder generation, first node pair with second node
Answer the second object set of entitled rear sequence answer;
Third redirects probability calculation unit, for according in first object set, not grasped to the first node
Object quantity, and meet the quantity of object do not grasped to the first node and grasped to the second node,
It calculates the first node and redirects the third of second node and redirect probability;
The forth jump turns probability calculation unit, for according in first object set, having been grasped to the first node
Object quantity, and meet the quantity of object grasped to the first node and the second node, calculate institute
It states first node and redirects the forth jump of second node and turn probability;
The fifth jump turns probability calculation unit, for according in second object set, not grasped to the second node
Object quantity, and meet the quantity of object do not grasped to the second node and grasped to the first node,
It calculates the second node and redirects the fifth jump of first node and turn probability;
6th redirects probability calculation unit, for according in second object set, having been grasped to the second node
Object quantity, and meet the quantity of object grasped to the second node and the first node, calculate institute
It states second node and redirects the 6th of first node and redirect probability.
Preferably, the attribute information determination unit further includes:
Significance level determination unit determines the important journey of each node for redirecting probability according between the priori node
Degree, the significance level is for instructing the structure optimization of the rudimental knowledge collection of illustrative plates to adjust.
Preferably, the significance level determination unit includes:
Probability transfer matrix determination unit is determined and described is tentatively known for redirecting probability according between the priori node
Know in collection of illustrative plates the transition probability between node two-by-two, forms probability transfer matrix;
Significance level matrix generation unit, for being shifted according to preset start node significance level matrix and the probability
Matrix, the final node significance level matrix of grey iterative generation, final node significance level matrix include the important journey of each node
Degree.
Preferably, the probability transfer matrix determination unit includes:
Node judging unit, for for any two node x in the rudimental knowledge collection of illustrative platesjAnd xi, decision node xiIt is
No is node xjPreposition node;J and i values are [1, n], and n is node total number;
First transition probability determination unit, for when the judging result of the node judging unit is no, determining node
xjTo node xiTransition probability be 0;
Second transition probability determination unit is when being, according to node for the judging result in the node judging unit
xjRedirect its each preposition node first redirects probability, determines node xjTo node xiTransition probability.
Preferably, the significance level matrix generation unit includes:
First object matrix determination unit, for using the start node significance level matrix as objective matrix;
Matrix multiple unit obtains multiplied result for the objective matrix to be multiplied with the probability transfer matrix;
Judging unit is restrained, for judging whether the difference of the multiplied result and the objective matrix reaches setting convergence
Condition;
As a result determination unit, for it is described convergence judging unit judging result be when, the multiplied result is true
It is set to final node significance level matrix;
Second objective matrix determination unit is used for when the judging result of the convergence judging unit is no, by the phase
Multiply result as objective matrix, is back to the matrix multiple unit.
Preferably, further include:
Low importance node determination unit is made for determining that significance level is less than the node of setting significance level lower threshold value
For low importance node;
First knowledge mapping adjustment unit, for the low importance node to be deleted from the rudimental knowledge collection of illustrative plates,
And connect the preposition node of the low importance node entirely with the descendant node of the low importance node, know after being adjusted
Know collection of illustrative plates.
Preferably, further include:
High importance node determination unit is made for determining that significance level is more than the node of setting significance level upper threshold value
For high importance node;
Second knowledge mapping adjustment unit, for according to preset fractionation rule, the high importance node to be split into
Several child nodes;
Third knowledge mapping adjustment unit, for the preposition node of the high importance node and each child node is complete
Connection, the descendant node of the high importance node is connect entirely with each child node, is adjusted rear knowledge mapping.
Preferably, further include:
4th knowledge mapping adjustment unit, for redirecting probability according between the posteriority node, to the rudimental knowledge
Collection of illustrative plates carries out structural adjustment.
A kind of collection of illustrative plates display device, including:
Knowledge mapping display unit is used for explicit knowledge's collection of illustrative plates, and the knowledge mapping includes having between several nodes and node
To line segment, the node on behalf meets a kind of topic to impose a condition;Two connected by directed line segment in the knowledge mapping
It is connected each other according to the logic of teaching between a node.
Preferably, further include:
Probability display unit is redirected, it is described for showing the probability that redirects between two nodes connected by directed line segment
It redirects probability and reflects learning sequence between node.
Preferably, further include:
Learning path display unit, for showing node learning path corresponding with each node, the node learning path
In the clooating sequence of each node reflect the learning sequence of each node, the learning sequence of each node is according between each node
Probability is redirected to be determined.
A kind of map construction equipment, including:Memory and processor;
The memory, for storing program;
The processor realizes each step of map construction method as introduced above for executing described program.
A kind of collection of illustrative plates display equipment, including:Memory and processor;
The memory, for storing program;
The processor realizes each step of collection of illustrative plates display methods as introduced above for executing described program.
A kind of readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the computer program is handled
When device executes, each step of map construction method as introduced above is realized.
A kind of readable storage medium storing program for executing is stored thereon with computer program, real when the computer program is executed by processor
Each step of collection of illustrative plates display methods now as introduced above.
It can be seen from the above technical scheme that map construction method provided by the embodiments of the present application, obtains rudimental knowledge
Collection of illustrative plates, the rudimental knowledge collection of illustrative plates include directed line segment between several nodes and node, and node on behalf meets a kind of topic to impose a condition
Mesh connects each other according to the logic of teaching between two nodes connected by directed line segment, can be with based on the rudimental knowledge collection of illustrative plates
Support adaptive learning.Further, the application records the answer of all kinds of topics according to object, determines object to rudimental knowledge figure
The Grasping level of each node in spectrum;According to object to the Grasping level of each node in rudimental knowledge collection of illustrative plates, the category of each node is determined
Property information, which is used to instruct learning sequence between node, and/or instructs the structure optimization tune of rudimental knowledge collection of illustrative plates
It is whole.The application is by analyzing Grasping level of the object to each node in knowledge mapping, it may be determined that the attribute information of node, it is quantitative
Change ground collection of illustrative plates node is described, the structure optimization of the learning sequence and collection of illustrative plates between node can be instructed to adjust, is collection of illustrative plates
Practical application, which provides, preferably to be supported.
Description of the drawings
In order to illustrate the technical solutions in the embodiments of the present application or in the prior art more clearly, to embodiment or will show below
There is attached drawing needed in technology description to be briefly described, it should be apparent that, the accompanying drawings in the following description is only this
The embodiment of application for those of ordinary skill in the art without creative efforts, can also basis
The attached drawing of offer obtains other attached drawings.
Fig. 1 is a kind of map construction method flow diagram disclosed in the embodiment of the present application;
Fig. 2 illustrates a kind of knowledge mapping structural schematic diagram;
Fig. 3 illustrates a kind of node relationships structure chart;
Fig. 4 illustrates a kind of low importance node processing schematic diagram;
Fig. 5 illustrates a kind of high importance node processing schematic diagram;
Fig. 6 is a kind of map construction apparatus structure schematic diagram disclosed in the embodiment of the present application;
Fig. 7 illustrates map construction equipment or collection of illustrative plates shows the hardware block diagram of equipment.
Specific implementation mode
Below in conjunction with the attached drawing in the embodiment of the present application, technical solutions in the embodiments of the present application carries out clear, complete
Site preparation describes, it is clear that described embodiments are only a part of embodiments of the present application, instead of all the embodiments.It is based on
Embodiment in the application, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall in the protection scope of this application.
In order to realize the support to adaptive learning, present inventor, which thinks deeply, builds a kind of knowledge mapping.In view of working as
Preceding machine learning is popularized, and inventor by correlation machine learning algorithm first it is envisioned that directly build knowledge mapping.It is logical
It crosses further analysis to find, the knowledge mapping that this mode is built can not carry out analysis and phase from the angle of teaching and research cognition to collection of illustrative plates
The structural adjustment answered does not meet the result of education cognition.Also, collection of illustrative plates interior joint and relationships between nodes are not often quantitative to be retouched
It states, can not support practical application well.
For this purpose, inventor further furthers investigate, the following map construction scheme of the application is finally proposed.In following sides
In case, the application is based on teaching and research experience combination field research course construction rudimental knowledge collection of illustrative plates by teaching and research teacher, and definition is specific
Subject node and joint system.Then the answer record of student, the score feelings based on student in the case where node corresponds to topic are collected
Condition determines Grasping level of the student to each node.In conjunction with student to the Grasping level of each node in knowledge mapping, each node is determined
Attribute information, for instruction of papil to the learning sequence of each node, while the structure of rudimental knowledge collection of illustrative plates can also be instructed excellent
Change adjustment.The rudimental knowledge collection of illustrative plates that the application obtains meets teaching cognition and quantitative nodal community, can allow it to effectively
Participate in and support adaptive learning various aspects, both can with accurate description student ability, can also be applied to education resource recommend,
Learning path plans that learning difficulty is incremental, and application prospect is more extensive.
Next, the map construction method of the application is introduced in conjunction with attached drawing 1, as shown in Figure 1, this method includes:
Step S100, rudimental knowledge collection of illustrative plates is obtained, the rudimental knowledge collection of illustrative plates includes directed line between several nodes and node
Section;
Wherein, rudimental knowledge collection of illustrative plates can be built based on teaching and research experience combination field research course by teaching and research teacher
's.Rudimental knowledge collection of illustrative plates interior joint represents a kind of topic for meeting and imposing a condition, and the topic types of different node on behalf are different, lead to
Cross directed line segment connection two nodes between connected each other according to the logic of teaching.
In the rudimental knowledge collection of illustrative plates that the present embodiment obtains, node and traditional knowledge point, examination point can be different, the present embodiment
Can be using definition node as anchor point, anchor point is the angle classified from topic to define, and each anchor point represents specific a kind of topic,
Identical knowledge point or knowledge point combination are usually examined or check under same or analogous scene, there is similar idea and method skill of solving a problem
Ingeniously, difficulty is suitable.Anchor point is more in line with teaching cognition compared with knowledge point, examination point, because the topic of identical knowledge point may be also
With different solution and thinking, if classified according to knowledge point, these topics will be divided into the same knowledge point, can not embody
Difference between topic.And under the application anchor point system, these topics will be compartmentalized, and opposite classification is more careful.
Relationship is mainly to be determined by the logic learnt between rudimental knowledge collection of illustrative plates interior joint, i.e. priority in learning process
Sequentially.If being possible to grasp node B after only having grasped node A, that is, it is the necessary item for grasping node B to grasp node A
Part, then node A is referred to as the preposition of node B, corresponding, and node B is the subsequent of node A.It is embodied in rudimental knowledge collection of illustrative plates, node
A is directed toward node B by directed line segment.
As shown in Fig. 2, Fig. 2 illustrates a kind of knowledge mapping structural schematic diagram.Knowledge mapping includes multiple nodes in figure, no
With the different types of topic of node on behalf, connected by directed line segment between node.
Step S110, the answer of all kinds of topics is recorded according to object, determines object to each in the rudimental knowledge collection of illustrative plates
The Grasping level of node;
Specifically, the application can collect object and be recorded to the answer of all kinds of topics in advance, and answer record is comprising all right
As the answer result to every a kind of topic.Object can be student, the user etc. of a class, a grade or other set.Root
Different according to the application of constructed knowledge mapping, it is also different that the answer collected here records targeted object.
It is recorded by the answer of collection, it may be determined that Grasping level of the object to each node in rudimental knowledge collection of illustrative plates.The palm
The degree of holding can be qualitative or quantitative expression, such as indicate Grasping level in the form of score, or with " grasp ", " do not slap
Hold " form indicate.It is understood that two kinds of representations can be converted mutually.
Step S120, the category of each node is determined to the Grasping level of each node in the rudimental knowledge collection of illustrative plates according to object
Property information.
Specifically, the attribute information is used to instruct the learning sequence between node, and/or the guidance rudimental knowledge collection of illustrative plates
Structure optimization adjustment.
It, can be with accurate description object in determining object to rudimental knowledge collection of illustrative plates after the Grasping level of each node
Habit ability, be based on this, can further analysis node attribute information, wherein attribute information may include preset a variety of
The information of type attribute.By setting different types of attribute, between node can be instructed based on determining attribute information
Habit sequence, and/or the structure optimization of rudimental knowledge collection of illustrative plates is instructed to adjust.
Map construction method provided by the embodiments of the present application obtains rudimental knowledge collection of illustrative plates, if the rudimental knowledge collection of illustrative plates includes
Directed line segment between dry node and node, node on behalf meet a kind of topic to impose a condition, two connected by directed line segment
It is connected each other according to the logic of teaching between node, adaptive learning can be supported based on the rudimental knowledge collection of illustrative plates.Further, this Shen
Please the answer of all kinds of topics is recorded according to object, determines Grasping level of the object to each node in rudimental knowledge collection of illustrative plates;According to
Object determines the attribute information of each node to the Grasping level of each node in rudimental knowledge collection of illustrative plates, and the attribute information is for instructing
Learning sequence between node, and/or the structure optimization of rudimental knowledge collection of illustrative plates is instructed to adjust.The application is by analyzing object to knowledge
The Grasping level of each node in collection of illustrative plates, it may be determined that the attribute information of node is described collection of illustrative plates node to quantification, can
It instructs the structure optimization of the learning sequence and collection of illustrative plates between node to adjust, better support is provided for the practical application of collection of illustrative plates.
For step S110 in a upper embodiment, the answer of all kinds of topics is recorded according to object, determines object to described
The process of the Grasping level of each node in rudimental knowledge collection of illustrative plates, specific implementation process may include:
S1, it is directed to each node in the rudimental knowledge collection of illustrative plates, the answer for corresponding to topic to the node according to object is remembered
Record, computing object correspond to the average rate of topic in the node;
S2, the average rate that object is corresponded to topic in the node, are determined as grasp journey of the object to the node
Degree.
In the exemplary method of the present embodiment, using average rate of the object under the corresponding topic of node as to node
Grasping level.
Assuming that answer record shares m object, n node is shared in rudimental knowledge collection of illustrative plates, then m object is to knowledge mapping
In the Grasping level of each node can indicate that A is expressed as with Grasping level matrix A:
Wherein, aijIndicate that Grasping level of i-th of object on j-th of node, entire matrix A reflect whole objects and exist
Grasping level on whole nodes.By corresponding to topic under corresponding node, computing object is on node related topic
Average rate, as object to the Grasping level of node.Wherein, aijCalculation formula it is as follows:
Wherein, WijIndicate whole topic set of i-th of object on j-th of the node done, scoreitIndicate i-th
The score of t-th of topic of a object pair, stdscoretIndicate the standard scores of t-th of topic.
In next embodiment, to above-mentioned steps S120, according to object to each node in the rudimental knowledge collection of illustrative plates
Grasping level determines that the process of the attribute information of each node is introduced.
Several category attributes can be preset in the embodiment of the present application, and then determine the letter of the attribute of all categories of each node
Breath.In the case of one kind is exemplary, the category attribute that can be set is such as:Probability, node significance level etc. are redirected between node.Wherein,
Redirect probability between node again and can be divided into the probability that redirects between priori node, and between priori node to redirect probability opposite
Probability is redirected between posteriority node.The probability that redirects between priori node is to be connected by directed line segment in rudimental knowledge collection of illustrative plates
Node between redirect probability.The probability that redirects between posteriority node is to ignore to connect between each node in rudimental knowledge collection of illustrative plates to close
It is to redirect probability between any two node calculated according only to answer record.
By redirecting probability between determining priori node, the planning of learning path can be carried out.
By redirecting probability between determining posteriority node, can help to optimize rudimental knowledge collection of illustrative plates structure.
By determining node significance level, it can reflect effect of the node played in knowledge mapping, and then optimize preliminary
Knowledge mapping structure so that knowledge mapping is more reasonable, meets teaching and research cognition.
The several properties information of above-mentioned example can take any of which or a variety of combinations.Next, respectively to each
The determination process of attribute information is introduced.
First, the calculating process for redirecting probability between priori node is introduced.
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, it may be determined that the rudimental knowledge collection of illustrative plates
In by directed line segment connect two nodes between redirect probability, redirect probability as between priori node.This redirects probability
Reflect the learning sequence between node.
For in rudimental knowledge collection of illustrative plates by directed line segment connect two nodes, two nodes each other preposition node and after
After node, preposition node is directed toward descendant node by directed line segment.
It is empirically analyzed from teaching and research, if a node is not grasped, shows that the preposition node of the node is not grasped.Together
When, if in the case that a node has been grasped, it should learn its descendant node.Based on the above cognition, in order to describe between node
Relationship, define between priori node to redirect probability as follows:
W (x, y)=P (y | x=wrong)
Z (x, y)=P (y | x=right)
Wherein, x and y indicates node.In the case that W (x, y) indicates that node x is not grasped, recommend the priori of study node y general
Rate, W (x, y) reflect object and do not grasp the priori cost for learning node y in the case of node x, the more big then priori of W (x, y) at
This is smaller.
In the case that Z (x, y) indicates that node x grasped, recommend the prior probability of study node y, Z (x, y) is reflected pair
Priori cost as learning node y in the case of having grasped node x, the Z (x, y) the big, and then priori cost is smaller.
From the point of view of teaching traditionally, it should which the smaller node of preference learning priori cost is more conducive to student and follows in this way
The progressive study of sequence, this probability that redirects also between the priori node of bigger are consistent.The probability that redirects between priori node reflects
Learning sequence between node, can effectively instruction of papil learnt.
According to above-mentioned definition, calculates separately and redirect the first of preposition node when descendant node is not grasped and redirect probability, and
What preposition node redirected descendant node when having grasped second redirects probability.
Specifically:
For two nodes connected by directed line segment in rudimental knowledge collection of illustrative plates:Preposition node and descendant node, according to
To the quantity count1 for the object that descendant node is not grasped, and meets and descendant node is not grasped and preposition node has been grasped
Object quantity count2, calculate descendant node and redirect the first of preposition node and redirect probability.
Optionally, probability can be redirected using the ratio of count2 divided by count1 as first.
Further, according to the quantity count3 for the object grasped to preposition node, and meet to preposition node and after
After the quantity count4 for the object that node has been grasped, calculates preposition node and redirect the second of descendant node and redirect probability.
Optionally, probability can be redirected using the ratio of count4 divided by count3 as second.
Next, being illustrated by a specific example.
A kind of node relationships structure chart is illustrated referring to Fig. 3, Fig. 3.
For Fig. 3 interior joint x, there is f descendant node y1…yf, and g preposition node z1…zg。
Known m object then first redirects probability W (x, z to the Grasping level matrix A of n nodes in knowledge mappingi) and the
Two redirect probability Z (x, yj) calculation formula is as follows:
Wherein, the right in formula indicates that corresponding node has been grasped, and wrong indicates that corresponding node is not grasped.Count()
It indicates to meet the number of objects that corresponding node grasps situation.For W (x, zi) for, it indicates in the case where node x is not grasped,
Node ziThe probability grasped, if the probability is bigger, then it is assumed that ziIt is easier to grasp, learning cost is relatively low.It is identical, Z
(x, yj) indicate in the case where node x has been grasped, node yjThe probability grasped, the probability are bigger, then it is assumed that yjIt is easier to slap
It holds, learning cost is relatively low.
It is understood that the node and relationships between nodes that are manually marked in the rudimental knowledge collection of illustrative plates obtained may exist
Two less relevant nodes may be associated, or not associate two relevant nodes by certain error,
And then influence the use of knowledge mapping.
In order to avoid this problem, is introduced in the application and redirect probability between posteriority node, to find rudimental knowledge
Wrong node relationships in collection of illustrative plates, and then structure optimization adjustment is carried out to rudimental knowledge collection of illustrative plates.
Based on this, the calculating process for redirecting probability between posteriority node is introduced.
Specifically, the Grasping level of each node in the rudimental knowledge collection of illustrative plates and each node correspondence are inscribed according to object
Sequencing of the mesh in answer record, determines and redirects probability between any two node, as the jump between posteriority node
Turn probability.
In order to describe the relationship between node, define between posteriority node to redirect probability as follows:
Wherein, after C (x, y) indicates that node x corresponds to topic work mistake, and then node y corresponds to the probability that topic is opposed.It is right
It answers, G (x, y) indicates that node x is corresponded to after topic opposes, and and then node y corresponds to the probability that topic is opposed.C (y, x) and G (y,
X) similarly.
From the point of view of the definition of the two formulas of C (x, y) and G (x, y), probability W (x, y) is redirected between above-mentioned priori node
It is sufficiently close to Z (x, y), is all to reflect node x to oppose or stagger the time, the cost needed for study node y.Difference lies in C
(x, y) and G (x, y) need to ensure that node x corresponds to topic and first made on answer record, then node y corresponds to topic in statistics
And then made, and W (x, y) and Z (x, y) is not necessarily to sequencing.This is because for unknown relation node, without priori
Preposition, subsequent relationship, from answer record in view of, exactly answer sequence.Answer record it is forward to be preposition, answer record lean on
It is subsequent afterwards.Therefore, it is preposition to be that node x is considered as by C (x, y) and G (x, y), node y be considered as it is subsequent calculated, and C (y, x)
With G (y, x) then on the contrary, being to be considered as node y preposition, node x is considered as subsequent.
Based on above-mentioned definition, introduces and redirect probability calculation process between posteriority node:
Specifically:
Any two node is respectively first node x and second node y in S1, the definition rudimental knowledge collection of illustrative plates.
S2, recorded according to the answer, determine and entitled elder generation is corresponded to first node x, second node y correspond to it is entitled after
First object set of sequence answer, and entitled elder generation is corresponded to second node y, first node x corresponds to entitled rear sequence
Second object set of answer.
It is understood that between testing node after computation when redirecting probability, due to do not have priori mark node between
Preposition, subsequent relationship, but the answer sequence of topic is corresponded to according to answer record interior joint.Therefore, it is first had in the present embodiment
Count the first object set and the second object set for meeting above-mentioned condition.
S3, according in first object set, to the quantity count5 for the object that the first node is not grasped, and
Meet the quantity count6 of object for not grasping to the first node and having been grasped to the second node, calculates described first
The third that node redirects second node redirects probability.
The ratio of count6 divided by count5 can be determined as third and redirect probability C (x, y).
S4, according in first object set, to the quantity count7 for the object that the first node has been grasped, and
The quantity count8 for meeting the object grasped to the first node and the second node calculates the first node and jumps
The forth jump for turning second node turns probability.
The ratio of count8 divided by count7 can be determined as the forth jump and turn probability G (x, y).
S5, according in second object set, to the quantity count9 for the object that the second node is not grasped, and
Meet the quantity count10 of object for not grasping to the second node and having been grasped to the first node, calculates described the
The fifth jump that two nodes redirect first node turns probability.
The ratio of count10 divided by count9 can be determined as the fifth jump and turn probability C (y, x).
S6, according in second object set, to the quantity count11 for the object that the second node has been grasped, with
And meet the quantity count12 for the object grasped to the second node and the first node, calculate second section
Point redirects the 6th of first node and redirects probability.
The ratio of count12 divided by count11 can be determined as the 6th and redirect probability G (y, x).
The present embodiment redirects the sum of probability between posteriority node is determined, can redirect probability to rudimental knowledge based on this
Collection of illustrative plates carries out structural adjustment.Such as:
The higher nodes of C and G can be picked out, such as be picked out C and G more than the node of predetermined threshold value, first
Incidence relation is added in step knowledge mapping, or by hand inspection, considers whether to add in rudimental knowledge collection of illustrative plates from teaching and research angle
Add incidence relation.
Further, it for there are two nodes that priori marks relationship in rudimental knowledge collection of illustrative plates, can also be somebody's turn to do by calculating
Probability C and G are redirected between the posteriority node of two nodes, probability W and Z will be redirected between its priori node with two nodes
It makes comparisons respectively, specially:C and W compare, and G and Z compare, if difference is larger, if difference is more than preset difference value threshold value, then say
The bright priori interest is inaccurate, to cancel the incidence relation between two nodes in rudimental knowledge collection of illustrative plates.
Further, the calculating process of the significance level of node is introduced.
Probability is redirected according between the priori node, determines the significance level of each node, the significance level is for referring to
Lead the structure optimization adjustment of the rudimental knowledge collection of illustrative plates.
Specifically, in the significance level of calculate node, probability realization is redirected between the priori node based on foregoing description.
If it is understood that redirect probability between also calculating posteriority node before this, and based on this to rudimental knowledge collection of illustrative plates into
Gone structure adjusting and optimizing, then in knowledge mapping that can be after optimizing and revising between priori node redirect probability based on, meter
Calculate the significance level of each node.
It is understood that the probability that redirects between node reflects strong or weak relation between node, and node also have it is important
Point of degree.Different nodes are in subject, and proportion, learning difficulty and investigation frequency are different, i.e., important journey
Degree is different.In general, if the descendant node of a node is more, illustrate that the node is the premise for learning other nodes,
Remaining node could be grasped by only first grasping the node, and the node significance level is higher;Meanwhile if a node subsequent section
Point significance level is high, then its preposition node as an important node, significance level also should be higher.
Based on the cognition, probability is redirected according between the priori node first in the present embodiment, determines and described tentatively knows
Know in collection of illustrative plates the transition probability between node two-by-two, composition probability transfer matrix S.Further, important according to preset start node
Degree matrix P0And the probability transfer matrix S, the final node significance level matrix P of grey iterative generation, final node are important
Degree matrix P includes the significance level of each node.
Wherein, it when determining probability transfer matrix S, can specifically include:
For any two node x in the rudimental knowledge collection of illustrative platesjAnd xi, decision node xiWhether it is node xjIt is preposition
Node;J and i values are [1, n], and n is rudimental knowledge collection of illustrative plates interior joint total number;
If not, it is determined that node xjTo node xiTransition probability be 0;
If so, according to node xjRedirect its each preposition node first redirects probability, determines node xjTo node xi's
Transition probability.
It is to indicate S by following formula:
Wherein, sijIt indicates from node xjTo node xiTransition probability.It is relied on thereafter since the significance level of node calculates
After number of nodes and descendant node significance level, it is equivalent to from descendant node and is directed toward its preposition node, therefore adopted in the present embodiment
The first of descendant node is redirected with preposition node redirect probability W and indicate transition probability, specifically sijCalculating it is as follows:
Wherein, F xjThe preposition node of whole set, xj→xiIndicate node xiFor node xjPreposition node, xj↑xi
Indicate node xiIt is not node xjPreposition node.
Further, above-mentioned according to preset start node significance level matrix P0And the probability transfer matrix S, iteration
The process for generating final node significance level matrix P may include:
It is iterated according to the following formula:
Pn+1=SPn
Wherein PnIndicate node significance level matrix when iteration carries out n wheels, n values initial section as preset when being 0
Point significance level matrix P0.Assuming that there is n node x in rudimental knowledge collection of illustrative plates1…xn, then start node significance level matrix P0It can
To be expressed as:
P0=[I1 I2 … In]T
Wherein, IiIndicate node xiInitialization significance level, can be arrangedAll save
The initial significance level of point is consistent.
Iteration obtains final node significance level square until node significance level matrix converges to a definite value
Battle array P.
In practical calculating process, it is as follows that can the condition of convergence be set:
|Pn+1-Pn| < ε
Wherein, ε is a preset minimum, for limiting Pn+1And PnGap, if n-th wheel and (n+1)th wheel iteration life
At two matrix gaps very little can be by P it may be considered that be basically completed convergencen+1Or PnAs final node
Significance level matrix P.
If the angle for executing flow in method describes, the mistake of the final node significance level matrix P of grey iterative generation
Journey may include:
S1, using the start node significance level matrix as objective matrix;
S2, the objective matrix is multiplied with the probability transfer matrix, obtains multiplied result;
S3, judge whether the multiplied result and the difference of the objective matrix reach the setting condition of convergence;If so, executing
S4, if it is not, executing S5;
S4, the multiplied result is determined as to final node significance level matrix;
S5, using the multiplied result as objective matrix, return and execute S2.
The above-mentioned significance level that each node in rudimental knowledge collection of illustrative plates is determined, can be further to rudimental knowledge figure based on this
Spectrum carries out structure optimization adjustment.
It is understood that if the significance level of a node is too low, illustrate the node in entire knowledge mapping
Play the role of weaker, the definition of this node is likely that there are problem, it may be considered that deletes the node.
Specifically, the present embodiment can preset significance level lower threshold value, and then weight is determined from rudimental knowledge collection of illustrative plates
Degree is wanted to be less than the node of setting significance level lower threshold value, as low importance node.Further, by the low importance node
It is deleted from the rudimental knowledge collection of illustrative plates, and will be after the preposition node of the low importance node and the low importance node
It is connected entirely after node, is adjusted rear knowledge mapping.
The processing procedure of low importance node is illustrated in conjunction with Fig. 4.
In Fig. 4, node x is low importance node, and there are z1-zgA preposition node and y1-yfA descendant node.
By node x after being deleted in knowledge mapping, and its preposition node is connect entirely with descendant node, is referred to by preposition node
To descendant node.
After adjustment, between node z and node y to redirect probability as follows:
W(yj, zi)=W (x, zi)
Z(zi, yj)=Z (x, yj)
Further, if the significance level of a node is excessively high, it is excessively wide in range illustrates that the node may define, is not inconsistent
The node-classification requirement according to the careful classification of topic types is closed, therefore it can be split, several new nodes are divided into.
Specifically, the present embodiment can preset significance level upper threshold value, and then weight is determined from rudimental knowledge collection of illustrative plates
Degree is wanted to be more than the node of setting significance level upper threshold value, as high importance node.Further, it is advised according to preset fractionation
Then, the high importance node is split into several child nodes.And by the preposition node of the high importance node with it is each described
Child node connects entirely, and the descendant node of the high importance node is connect entirely with each child node, is adjusted rear knowledge
Collection of illustrative plates.
The processing procedure of high importance node is illustrated in conjunction with Fig. 5.
In Fig. 5, node x is high importance node, and there are z1-zgA preposition node and y1-yfA descendant node.
Node x is split into x1…xlTotal l child node.By z1-zgA preposition node and x1-xlA child node connects entirely,
By x1-xlA child node and y1-yfA descendant node connects entirely.
Wherein, significance level of the sum of the significance level of all child nodes equal to preceding node x after fractionation.After adjustment, section
Between point z and node y to redirect probability as follows:
Wherein, k value ranges are [1, l].IkFor node xkSignificance level, IxFor the significance level of node x.
In another embodiment of the application, a kind of collection of illustrative plates display methods is disclosed, which may include:
Explicit knowledge's collection of illustrative plates, the knowledge mapping include directed line segment between several nodes and node, and the node on behalf is full
A kind of topic to impose a condition enough;Pass through the logic according to teaching between two nodes of directed line segment connection in the knowledge mapping
It connects each other.
It specifically, can be with explicit knowledge's collection of illustrative plates when receiving idsplay order.
It is understood that the knowledge mapping shown in the present embodiment can be the knowledge mapping of above-mentioned structure, specifically may be used
To be the rudimental knowledge collection of illustrative plates obtained, or the knowledge mapping after optimizing and revising.
Under a kind of optional scene, user can show after registration logs in website provided in this embodiment in webpage
Show the knowledge mapping.Knowledge mapping based on display can support user to carry out adaptive learning.
Further alternative, the application method can further include:
Show the probability that redirects between two nodes being connected by directed line segment, the probability that redirects reflects between node
Learning sequence.
Specifically, while explicit knowledge's collection of illustrative plates, it can also will pass through two nodes of directed line segment connection in collection of illustrative plates
Between the probability that redirects shown, redirect probability and reflect learning sequence between node, user can advise according to probability is redirected
Draw the learning path of oneself.
It is understood that the embodiment of the present application can also be previously according to redirecting probability and generate each node between node
Learning sequence, and then while explicit knowledge's collection of illustrative plates, show that node learning path corresponding with each node, the node learn road
The clooating sequence of each node reflects the learning sequence of each node in diameter.By this display mode, it is intuitive to easily facilitate user
Determine each node learning sequence, use is simpler, conveniently.
Map construction device provided by the embodiments of the present application is described below, map construction device described below with
Above-described map construction method can correspond reference.
Referring to Fig. 6, Fig. 6 is a kind of map construction apparatus structure schematic diagram disclosed in the embodiment of the present application.As shown in fig. 6,
The map construction device includes:
Rudimental knowledge collection of illustrative plates acquiring unit 11, for obtaining rudimental knowledge collection of illustrative plates, the rudimental knowledge collection of illustrative plates includes several
Directed line segment between node and node, the node on behalf meet a kind of topic to impose a condition, two connected by directed line segment
It is connected each other according to the logic of teaching between a node;
Grasping level determination unit 12 determines object to described first for being recorded to the answer of all kinds of topics according to object
Walk the Grasping level of each node in knowledge mapping;
Attribute information determination unit 13, for according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates,
Determine the attribute information of each node, the attribute information is used to instruct the learning sequence between node, and/or guidance is described tentatively knows
Know the structure optimization adjustment of collection of illustrative plates.
Optionally, the Grasping level determination unit may include:
Average rate computing unit, for being directed to each node in the rudimental knowledge collection of illustrative plates, according to object to described
Node corresponds to the answer record of topic, and computing object corresponds to the average rate of topic in the node;
Average rate determination unit is determined as pair for object to be corresponded to the average rate of topic in the node
As the Grasping level to the node.
Optionally, the attribute information determination unit may include:
Priori redirects probability determining unit, is used for according to object to the grasp journey of each node in the rudimental knowledge collection of illustrative plates
Degree determines and redirects probability between two nodes connected by directed line segment in the rudimental knowledge collection of illustrative plates, as priori node
Between redirect probability, the probability that redirects reflects learning sequence between node.
It is understood that Grasping level may include having grasped and not grasped.Based on this, it is true that the priori redirects probability
Order member may include:
First redirects probability calculation unit, for for two connected by directed line segment in the rudimental knowledge collection of illustrative plates
Node:Preposition node and descendant node according to the quantity for the object that do not grasped to the descendant node, and meet to after described
After the quantity for the object that node is not grasped and has been grasped to the preposition node, calculates the descendant node and redirect preposition node
First redirects probability;The preposition node is directed toward the descendant node by directed line segment;
Second redirects probability calculation unit, for the quantity according to the object grasped to the preposition node, Yi Jiman
The quantity of object that foot has grasped the preposition node and the descendant node, calculate the preposition node redirect it is described after
Second after node redirects probability.
Further, the attribute information determination unit can also include:
Posteriority redirects probability determining unit, is used for according to object to the grasp journey of each node in the rudimental knowledge collection of illustrative plates
Degree and each node correspond to sequencing of the topic in the answer records, and determine and redirect probability between any two node,
Probability is redirected as between posteriority node.
Optionally, the posteriority redirects probability determining unit and may include:
Node definition unit is respectively first node and for defining any two node in the rudimental knowledge collection of illustrative plates
Two nodes;
Object set determination unit determined and corresponds to entitled elder generation with first node for being recorded according to the answer, second
Node corresponds to the first object set of entitled rear sequence answer, and corresponds to entitled elder generation, first node pair with second node
Answer the second object set of entitled rear sequence answer;
Third redirects probability calculation unit, for according in first object set, not grasped to the first node
Object quantity, and meet the quantity of object do not grasped to the first node and grasped to the second node,
It calculates the first node and redirects the third of second node and redirect probability;
The forth jump turns probability calculation unit, for according in first object set, having been grasped to the first node
Object quantity, and meet the quantity of object grasped to the first node and the second node, calculate institute
It states first node and redirects the forth jump of second node and turn probability;
The fifth jump turns probability calculation unit, for according in second object set, not grasped to the second node
Object quantity, and meet the quantity of object do not grasped to the second node and grasped to the first node,
It calculates the second node and redirects the fifth jump of first node and turn probability;
6th redirects probability calculation unit, for according in second object set, having been grasped to the second node
Object quantity, and meet the quantity of object grasped to the second node and the first node, calculate institute
It states second node and redirects the 6th of first node and redirect probability.
Further, the attribute information determination unit can also include:
Significance level determination unit determines the important journey of each node for redirecting probability according between the priori node
Degree, the significance level is for instructing the structure optimization of the rudimental knowledge collection of illustrative plates to adjust.
Optionally, the significance level determination unit may include:
Probability transfer matrix determination unit is determined and described is tentatively known for redirecting probability according between the priori node
Know in collection of illustrative plates the transition probability between node two-by-two, forms probability transfer matrix;
Significance level matrix generation unit, for being shifted according to preset start node significance level matrix and the probability
Matrix, the final node significance level matrix of grey iterative generation, final node significance level matrix include the important journey of each node
Degree.
Optionally, the probability transfer matrix determination unit may include:
Node judging unit, for for any two node x in the rudimental knowledge collection of illustrative platesjAnd xi, decision node xiIt is
No is node xjPreposition node;J and i values are [1, n], and n is node total number;
First transition probability determination unit, for when the judging result of the node judging unit is no, determining node
xjTo node xiTransition probability be 0;
Second transition probability determination unit is when being, according to node for the judging result in the node judging unit
xjRedirect its each preposition node first redirects probability, determines node xjTo node xiTransition probability.
Optionally, the significance level matrix generation unit may include:
First object matrix determination unit, for using the start node significance level matrix as objective matrix;
Matrix multiple unit obtains multiplied result for the objective matrix to be multiplied with the probability transfer matrix;
Judging unit is restrained, for judging whether the difference of the multiplied result and the objective matrix reaches setting convergence
Condition;
As a result determination unit, for it is described convergence judging unit judging result be when, the multiplied result is true
It is set to final node significance level matrix;
Second objective matrix determination unit is used for when the judging result of the convergence judging unit is no, by the phase
Multiply result as objective matrix, is back to the matrix multiple unit.
Optionally, the map construction device of the application can also include:
Low importance node determination unit is made for determining that significance level is less than the node of setting significance level lower threshold value
For low importance node;
First knowledge mapping adjustment unit, for the low importance node to be deleted from the rudimental knowledge collection of illustrative plates,
And connect the preposition node of the low importance node entirely with the descendant node of the low importance node, know after being adjusted
Know collection of illustrative plates.
Optionally, the map construction device of the application can also include:
High importance node determination unit is made for determining that significance level is more than the node of setting significance level upper threshold value
For high importance node;
Second knowledge mapping adjustment unit, for according to preset fractionation rule, the high importance node to be split into
Several child nodes;
Third knowledge mapping adjustment unit, for the preposition node of the high importance node and each child node is complete
Connection, the descendant node of the high importance node is connect entirely with each child node, is adjusted rear knowledge mapping.
Optionally, the map construction device of the application can also include:
4th knowledge mapping adjustment unit, for redirecting probability according between the posteriority node, to the rudimental knowledge
Collection of illustrative plates carries out structural adjustment.
Further collection of illustrative plates display device provided by the embodiments of the present application is described, collection of illustrative plates display device described below
Reference can be corresponded with above-described collection of illustrative plates display methods.
Collection of illustrative plates display device may include:
Knowledge mapping display unit is used for explicit knowledge's collection of illustrative plates, and the knowledge mapping includes having between several nodes and node
To line segment, the node on behalf meets a kind of topic to impose a condition;Two connected by directed line segment in the knowledge mapping
It is connected each other according to the logic of teaching between a node.
Optionally, collection of illustrative plates display device can also include:
Probability display unit is redirected, it is described for showing the probability that redirects between two nodes connected by directed line segment
It redirects probability and reflects learning sequence between node.
Optionally, collection of illustrative plates display device can also include:
Learning path display unit, for showing node learning path corresponding with each node, the node learning path
In the clooating sequence of each node reflect the learning sequence of each node, the learning sequence of each node is according between each node
Probability is redirected to be determined.
Map construction device provided by the embodiments of the present application can be applied to map construction equipment, such as server, terminal.Into
One step, collection of illustrative plates display device provided by the embodiments of the present application can be applied to collection of illustrative plates and show equipment, such as server, terminal.Collection of illustrative plates
It builds equipment and collection of illustrative plates shows that the hardware configuration of equipment can be identical, it is shown in Figure 7, illustrate map construction equipment or figure
Spectrum shows that the hardware block diagram of equipment, hardware configuration may include:
At least one processor 1, at least one communication interface 2, at least one processor 3 and at least one communication bus 4;
In the embodiment of the present application, processor 1, communication interface 2, memory 3, communication bus 4 quantity be it is at least one,
And processor 1, communication interface 2, memory 3 complete mutual communication by communication bus 4;
Processor 1 may be a central processor CPU or specific integrated circuit ASIC (Application
Specific Integrated Circuit), or be arranged to implement the integrated electricity of one or more of the embodiment of the present invention
Road etc.;
Memory 3 may include high-speed RAM memory, it is also possible to further include nonvolatile memory (non-volatile
Memory) etc., a for example, at least magnetic disk storage;
Wherein, memory has program stored therein, and processor can call the program that memory stores, described program to be used for:
Rudimental knowledge collection of illustrative plates is obtained, the rudimental knowledge collection of illustrative plates includes directed line segment between several nodes and node, the section
Point represents a kind of topic for meeting and imposing a condition, and is mutually interconnected according to the logic of teaching between two nodes connected by directed line segment
System;
The answer of all kinds of topics is recorded according to object, determines grasp of the object to each node in the rudimental knowledge collection of illustrative plates
Degree;
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, the attribute information of each node, institute are determined
Attribute information is stated for instructing the learning sequence between node, and/or the structure optimization adjustment of the guidance rudimental knowledge collection of illustrative plates.
Alternatively,
Explicit knowledge's collection of illustrative plates, the knowledge mapping include directed line segment between several nodes and node, and the node on behalf is full
A kind of topic to impose a condition enough;Pass through the logic according to teaching between two nodes of directed line segment connection in the knowledge mapping
It connects each other.
Optionally, the refinement function of described program and expanded function can refer to above description.
The embodiment of the present application also provides a kind of read-write storage medium, which can be stored with suitable for processing
The program that device executes, is used for when described program is executed by processor:
Rudimental knowledge collection of illustrative plates is obtained, the rudimental knowledge collection of illustrative plates includes directed line segment between several nodes and node, the section
Point represents a kind of topic for meeting and imposing a condition, and is mutually interconnected according to the logic of teaching between two nodes connected by directed line segment
System;
The answer of all kinds of topics is recorded according to object, determines grasp of the object to each node in the rudimental knowledge collection of illustrative plates
Degree;
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, the attribute information of each node, institute are determined
Attribute information is stated for instructing the learning sequence between node, and/or the structure optimization adjustment of the guidance rudimental knowledge collection of illustrative plates.
Alternatively,
Explicit knowledge's collection of illustrative plates, the knowledge mapping include directed line segment between several nodes and node, and the node on behalf is full
A kind of topic to impose a condition enough;Pass through the logic according to teaching between two nodes of directed line segment connection in the knowledge mapping
It connects each other.
Optionally, the refinement function of described program and expanded function can refer to above description.
Finally, it is to be noted that, herein, relational terms such as first and second and the like be used merely to by
One entity or operation are distinguished with another entity or operation, without necessarily requiring or implying these entities or operation
Between there are any actual relationship or orders.Moreover, the terms "include", "comprise" or its any other variant meaning
Covering non-exclusive inclusion, so that the process, method, article or equipment including a series of elements includes not only that
A little elements, but also include other elements that are not explicitly listed, or further include for this process, method, article or
The intrinsic element of equipment.In the absence of more restrictions, the element limited by sentence "including a ...", is not arranged
Except there is also other identical elements in the process, method, article or apparatus that includes the element.
Each embodiment is described by the way of progressive in this specification, the highlights of each of the examples are with other
The difference of embodiment, just to refer each other for identical similar portion between each embodiment.
The foregoing description of the disclosed embodiments enables professional and technical personnel in the field to realize or use the application.
Various modifications to these embodiments will be apparent to those skilled in the art, as defined herein
General Principle can in other embodiments be realized in the case where not departing from spirit herein or range.Therefore, the application
It is not intended to be limited to the embodiments shown herein, and is to fit to and the principles and novel features disclosed herein phase one
The widest range caused.
Claims (19)
1. a kind of map construction method, which is characterized in that including:
Rudimental knowledge collection of illustrative plates is obtained, the rudimental knowledge collection of illustrative plates includes directed line segment between several nodes and node, the node generation
Table meets a kind of topic to impose a condition, is connected each other according to the logic of teaching between two nodes connected by directed line segment;
The answer of all kinds of topics is recorded according to object, determines grasp journey of the object to each node in the rudimental knowledge collection of illustrative plates
Degree;
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, the attribute information of each node, the category are determined
Property information be used to instruct learning sequence between node, and/or the structure optimization adjustment of the guidance rudimental knowledge collection of illustrative plates.
2. according to the method described in claim 1, it is characterized in that, described record the answer of all kinds of topics according to object, really
Determine Grasping level of the object to each node in the rudimental knowledge collection of illustrative plates, including:
For each node in the rudimental knowledge collection of illustrative plates, the answer for corresponding to topic to the node according to object is recorded, is calculated
Object corresponds to the average rate of topic in the node;
The average rate that object is corresponded to topic in the node, is determined as Grasping level of the object to the node.
3. according to the method described in claim 1, it is characterized in that, it is described according to object to respectively being saved in the rudimental knowledge collection of illustrative plates
The Grasping level of point, determines the attribute information of each node, including:
According to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, determine in the rudimental knowledge collection of illustrative plates by having
Probability is redirected between two nodes connected to line segment, as the probability that redirects between priori node, the probability that redirects reflects
Learning sequence between node.
4. according to the method described in claim 3, it is characterized in that, it is described according to object to respectively being saved in the rudimental knowledge collection of illustrative plates
The Grasping level of point, determines the attribute information of each node, further includes:
Topic is corresponded in the answer to the Grasping level of each node in the rudimental knowledge collection of illustrative plates and each node according to object
Sequencing in record determines and redirects probability between any two node, probability is redirected as between posteriority node.
5. according to the method described in claim 3, it is characterized in that, it is described according to object to respectively being saved in the rudimental knowledge collection of illustrative plates
The Grasping level of point, determines the attribute information of each node, further includes:
Probability is redirected according between the priori node, determines the significance level of each node, the significance level is for instructing institute
State the structure optimization adjustment of rudimental knowledge collection of illustrative plates.
6. according to the method described in claim 5, it is characterized in that, described redirect probability according between the priori node, really
The significance level of fixed each node, including:
Probability is redirected according between the priori node, determines in the rudimental knowledge collection of illustrative plates transition probability between node two-by-two,
Form probability transfer matrix;
According to preset start node significance level matrix and the probability transfer matrix, the important journey of the final node of grey iterative generation
Matrix is spent, final node significance level matrix includes the significance level of each node.
7. according to claim 5-6 any one of them methods, which is characterized in that further include:
Determine that significance level is less than the node of setting significance level lower threshold value, as low importance node;
The low importance node is deleted from the rudimental knowledge collection of illustrative plates, and by the preposition node of the low importance node
It is connect entirely with the descendant node of the low importance node, is adjusted rear knowledge mapping;
And/or
Determine that significance level is more than the node of setting significance level upper threshold value, as high importance node;
According to preset fractionation rule, the high importance node is split into several child nodes;
The preposition node of the high importance node is connect entirely with each child node, by the subsequent of the high importance node
Node is connect entirely with each child node, is adjusted rear knowledge mapping.
8. according to the method described in claim 4, it is characterized in that, further including:
Probability is redirected according between the posteriority node, structural adjustment is carried out to the rudimental knowledge collection of illustrative plates.
9. a kind of collection of illustrative plates display methods, which is characterized in that including:
Explicit knowledge's collection of illustrative plates, the knowledge mapping include directed line segment between several nodes and node, and the node on behalf satisfaction is set
A kind of topic of fixed condition;By mutual according to the logic of teaching between two nodes of directed line segment connection in the knowledge mapping
Contact.
10. according to the method described in claim 9, it is characterized in that, further including:
Show the probability that redirects between two nodes being connected by directed line segment, the probability that redirects reflects study between node
Sequentially.
11. method according to claim 9 or 10, which is characterized in that further include:
Corresponding with each node node learning path of display, the clooating sequence of each node reflects respectively in the node learning path
The learning sequence of node, the learning sequence of each node is is determined according to the probability that redirects between each node.
12. a kind of map construction device, which is characterized in that including:
Rudimental knowledge collection of illustrative plates acquiring unit, for obtaining rudimental knowledge collection of illustrative plates, the rudimental knowledge collection of illustrative plates include several nodes and
Directed line segment between node, the node on behalf meet a kind of topic to impose a condition, two nodes connected by directed line segment
Between connected each other according to the logic of teaching;
Grasping level determination unit determines object to the rudimental knowledge for being recorded to the answer of all kinds of topics according to object
The Grasping level of each node in collection of illustrative plates;
Attribute information determination unit, for, to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, being determined each according to object
The attribute information of node, the attribute information are used to instruct the learning sequence between node, and/or the guidance rudimental knowledge collection of illustrative plates
Structure optimization adjustment.
13. device according to claim 12, which is characterized in that the attribute information determination unit includes:
Priori redirects probability determining unit, is used for according to object to the Grasping level of each node in the rudimental knowledge collection of illustrative plates, really
Probability is redirected between two nodes connected by directed line segment in the fixed rudimental knowledge collection of illustrative plates, as the jump between priori node
Turn probability, the probability that redirects reflects learning sequence between node.
14. device according to claim 13, which is characterized in that the attribute information determination unit further includes:
Significance level determination unit determines the significance level of each node, institute for redirecting probability according between the priori node
Significance level is stated for instructing the structure optimization of the rudimental knowledge collection of illustrative plates to adjust.
15. a kind of collection of illustrative plates display device, which is characterized in that including:
Knowledge mapping display unit is used for explicit knowledge's collection of illustrative plates, and the knowledge mapping includes directed line between several nodes and node
Section, the node on behalf meet a kind of topic to impose a condition;Two sections connected by directed line segment in the knowledge mapping
It is connected each other according to the logic of teaching between point.
16. device according to claim 15, which is characterized in that further include:
Probability display unit is redirected, it is described to redirect for showing the probability that redirects between two nodes connected by directed line segment
Probability reflects the learning sequence between node.
17. device according to claim 15 or 16, which is characterized in that further include:
Learning path display unit, it is each in the node learning path for display node learning path corresponding with each node
The clooating sequence of node reflects the learning sequence of each node, and the learning sequence of each node is according to redirecting between each node
Probability is determined.
18. a kind of map construction equipment, which is characterized in that including:Memory and processor;
The memory, for storing program;
The processor, for executing described program, realizing the map construction method as described in any one of claim 1-8
Each step, or realize each step of the collection of illustrative plates display methods as described in any one of claim 9-11.
19. a kind of readable storage medium storing program for executing, is stored thereon with computer program, which is characterized in that the computer program is handled
When device executes, each step of the map construction method as described in any one of claim 1-8 is realized, or realize as right is wanted
Seek each step of the collection of illustrative plates display methods described in any one of 9-11.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810489378.0A CN108647363A (en) | 2018-05-21 | 2018-05-21 | Map construction, display methods, device, equipment and storage medium |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201810489378.0A CN108647363A (en) | 2018-05-21 | 2018-05-21 | Map construction, display methods, device, equipment and storage medium |
Publications (1)
Publication Number | Publication Date |
---|---|
CN108647363A true CN108647363A (en) | 2018-10-12 |
Family
ID=63757209
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201810489378.0A Pending CN108647363A (en) | 2018-05-21 | 2018-05-21 | Map construction, display methods, device, equipment and storage medium |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN108647363A (en) |
Cited By (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783647A (en) * | 2018-12-21 | 2019-05-21 | 武汉思路富邦工程咨询有限公司 | The construction method of intelligence learning model |
CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
CN112800236A (en) * | 2021-01-14 | 2021-05-14 | 大连东软教育科技集团有限公司 | Method, device and storage medium for generating learning path based on knowledge graph |
CN113127644A (en) * | 2019-12-31 | 2021-07-16 | 奇安信科技集团股份有限公司 | Construction method and system of safety knowledge graph |
Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040202987A1 (en) * | 2003-02-14 | 2004-10-14 | Scheuring Sylvia Tidwell | System and method for creating, assessing, modifying, and using a learning map |
CN104376015A (en) * | 2013-08-15 | 2015-02-25 | 腾讯科技(深圳)有限公司 | Method and device for processing nodes in relational network |
CN107665473A (en) * | 2016-07-27 | 2018-02-06 | 科大讯飞股份有限公司 | Learning path planning method and device |
CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
CN107943853A (en) * | 2017-11-06 | 2018-04-20 | 浙江三米教育科技有限公司 | Knowledge node selects test method and its institute's computation machine equipment and storage medium |
-
2018
- 2018-05-21 CN CN201810489378.0A patent/CN108647363A/en active Pending
Patent Citations (5)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
US20040202987A1 (en) * | 2003-02-14 | 2004-10-14 | Scheuring Sylvia Tidwell | System and method for creating, assessing, modifying, and using a learning map |
CN104376015A (en) * | 2013-08-15 | 2015-02-25 | 腾讯科技(深圳)有限公司 | Method and device for processing nodes in relational network |
CN107665473A (en) * | 2016-07-27 | 2018-02-06 | 科大讯飞股份有限公司 | Learning path planning method and device |
CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
CN107943853A (en) * | 2017-11-06 | 2018-04-20 | 浙江三米教育科技有限公司 | Knowledge node selects test method and its institute's computation machine equipment and storage medium |
Cited By (7)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN109783647A (en) * | 2018-12-21 | 2019-05-21 | 武汉思路富邦工程咨询有限公司 | The construction method of intelligence learning model |
CN109902298A (en) * | 2019-02-13 | 2019-06-18 | 东北师范大学 | Domain Modeling and know-how estimating and measuring method in a kind of adaptive and learning system |
CN109902298B (en) * | 2019-02-13 | 2023-04-18 | 东北师范大学 | Domain knowledge modeling and knowledge level estimation method in self-adaptive learning system |
CN110837550A (en) * | 2019-11-11 | 2020-02-25 | 中山大学 | Knowledge graph-based question and answer method and device, electronic equipment and storage medium |
CN113127644A (en) * | 2019-12-31 | 2021-07-16 | 奇安信科技集团股份有限公司 | Construction method and system of safety knowledge graph |
CN113127644B (en) * | 2019-12-31 | 2024-03-15 | 奇安信科技集团股份有限公司 | Method and system for constructing safety knowledge graph |
CN112800236A (en) * | 2021-01-14 | 2021-05-14 | 大连东软教育科技集团有限公司 | Method, device and storage medium for generating learning path based on knowledge graph |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN108647363A (en) | Map construction, display methods, device, equipment and storage medium | |
CN110378818B (en) | Personalized exercise recommendation method, system and medium based on difficulty | |
Tunas Bangsa Pematangsiantar | Comparison of weighted sum model and multi attribute decision making weighted product methods in selecting the best elementary school in Indonesia | |
Hill et al. | Parental involvement in middle school: a meta-analytic assessment of the strategies that promote achievement. | |
Chen | Enhancement of student learning performance using personalized diagnosis and remedial learning system | |
Zopiatis et al. | Revisiting hospitality internship practices: A holistic investigation | |
Steele | Exploring the mathematical knowledge for teaching geometry and measurement through the design and use of rich assessment tasks | |
Hwang et al. | An expert system for improving web-based problem-solving ability of students | |
CN107544973A (en) | A kind of method and apparatus that data are handled | |
Noe | Invited reaction: Development of a generalized learning transfer system inventory | |
CN111476495A (en) | Evaluation and optimization method and system for improving learning efficiency | |
Dogan et al. | Association rule mining from an intelligent tutor | |
US8670846B2 (en) | System and method for conducting a competition | |
CN110705846A (en) | Intelligent teaching quality information processing system and method and information data processing terminal | |
Khalida et al. | Enhancing Usability of the Academic Information System at Bhayangkara University: A Design Thinking and System Usability Approach | |
Wallace et al. | Drafty: Enlisting users to be editors who maintain structured data | |
Drasgow et al. | Improving the measurement of psychological variables: Ideal point models rock! | |
Huang et al. | RESEARCH ON INDEPENDENT COLLEGE TEACHERS’TEACHING ABILITY BASED ON FACTOR ANALYSIS IN SPSS | |
Chen | An evaluation of the relationship between classroom practices and mathematics motivation from student and teacher perspectives | |
Shuib et al. | Elman neural network trained by using artificial bee colony for the classification of learning style based on students preferences | |
Zhu et al. | Computer Simulation for Construction Education Using the Structure-Behavior-Function Theory: A Pilot Study on Learning Estimating Concepts | |
CN109711760A (en) | It is suitble to measure the analysis method of adaptive students ' learning performance | |
TW201428666A (en) | Method for evaluating learning outcomes of individual concept and computer readable media thereof | |
Pan et al. | Research on Interdisciplinary Teaching Evaluation Model Based on Machine Learning | |
Zhao et al. | Construction on precise-personalized-learning evaluation system based on cipp evaluation model and integrated FCE-AHP method |
Legal Events
Date | Code | Title | Description |
---|---|---|---|
PB01 | Publication | ||
PB01 | Publication | ||
SE01 | Entry into force of request for substantive examination | ||
SE01 | Entry into force of request for substantive examination | ||
RJ01 | Rejection of invention patent application after publication | ||
RJ01 | Rejection of invention patent application after publication |
Application publication date: 20181012 |