CN107038508A - The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method - Google Patents
The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method Download PDFInfo
- Publication number
- CN107038508A CN107038508A CN201710416328.5A CN201710416328A CN107038508A CN 107038508 A CN107038508 A CN 107038508A CN 201710416328 A CN201710416328 A CN 201710416328A CN 107038508 A CN107038508 A CN 107038508A
- Authority
- CN
- China
- Prior art keywords
- learner
- learning
- knowledge
- study
- node
- 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 29
- 238000013507 mapping Methods 0.000 claims abstract description 21
- 238000013480 data collection Methods 0.000 claims abstract description 13
- 238000012545 processing Methods 0.000 claims abstract description 7
- 238000012360 testing method Methods 0.000 claims description 11
- 238000011156 evaluation Methods 0.000 claims description 4
- 238000012549 training Methods 0.000 claims description 4
- 230000000052 comparative effect Effects 0.000 claims description 3
- 230000001419 dependent effect Effects 0.000 claims description 3
- 238000005457 optimization Methods 0.000 abstract description 6
- 238000004458 analytical method Methods 0.000 abstract description 4
- 238000004364 calculation method Methods 0.000 abstract description 2
- 230000003993 interaction Effects 0.000 abstract description 2
- 230000003044 adaptive effect Effects 0.000 abstract 1
- 238000004064 recycling Methods 0.000 abstract 1
- 230000000875 corresponding effect Effects 0.000 description 22
- 238000010586 diagram Methods 0.000 description 18
- 230000000694 effects Effects 0.000 description 5
- 230000002452 interceptive effect Effects 0.000 description 5
- 238000011161 development Methods 0.000 description 3
- 238000010276 construction Methods 0.000 description 2
- 238000012217 deletion Methods 0.000 description 2
- 230000037430 deletion Effects 0.000 description 2
- 238000005516 engineering process Methods 0.000 description 2
- 230000000750 progressive effect Effects 0.000 description 2
- 238000009825 accumulation Methods 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000019771 cognition Effects 0.000 description 1
- 230000001149 cognitive effect Effects 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 238000013461 design Methods 0.000 description 1
- 239000004744 fabric Substances 0.000 description 1
- 230000010354 integration Effects 0.000 description 1
- 238000005065 mining Methods 0.000 description 1
- 238000012544 monitoring process Methods 0.000 description 1
- 238000003825 pressing Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 238000001228 spectrum Methods 0.000 description 1
- 230000003068 static effect Effects 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/04—Forecasting or optimisation specially adapted for administrative or management purposes, e.g. linear programming or "cutting stock problem"
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Strategic Management (AREA)
- Economics (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Marketing (AREA)
- General Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Game Theory and Decision Science (AREA)
- Entrepreneurship & Innovation (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The present invention be a kind of knowledge based collection of illustrative plates learning ability modeling and dynamic self-adapting target drives study point tissue and execution route recommend method, belong to Distributed Calculation and Software Engineering technology crossing domain.Incorporated experience into from reply autoincrement mode from the aspect of knowledge and reduction human expert interaction burden etc. two, the present invention is from Resource Modeling, resource processing, processing optimization and resource management are angularly studied, propose a kind of three layers can automatically abstracting adjustment solution framework, compatible Heuristics is supported to introduce and efficiently automatic semantic analysis by the resource optimization process for analyzing the adaptive automatically abstracting on Information Atlas and knowledge mapping for being calculated as core from data collection of illustrative plates with entity integrated frequency, correspondence 5W (whose (Who)/when (When)/where (Where), what (What) and how (How)) problem sort interface be connected user learning demand, the recycling description of learning process and learning objective etc., provide the user individualized learning service recommendation.
Description
Technical field
The present invention be a kind of knowledge based collection of illustrative plates learning ability modeling and dynamic self-adapting target drives study point
Tissue and execution route recommend method.It is mainly used in learner is spent minimum time and efforts(It is assumed that time, energy uniformly divide
The knowledge that cloth, unit interval and energy are obtained is as many)Most efficient learning guide is obtained, concern learner characteristics and study are needed
Difference is sought, is taught students in accordance with their aptitude, the individualized learning demand of learner is met, belongs to Distributed Calculation and Software Engineering technology is intersected
Field.
Background technology
With the development of kownledge economy, today's society proposes higher requirement to the acquisition of knowledge degree of people, intelligence
The suitable study point of selection recommends learner in tutoring system and the recommendation in individualized learning path has become again with optimization
Want problem.At present, on-line study problems faced is that online data are numerous and jumbled, cause learner be difficult to quickly locate it is suitable oneself
Education resource.It is Development of Distance Education qualitative leap to adapt to inquiry learning, and its immediate cause is with computer, telecommunication and cognition
The integrated use of the Knowledge Media of combination of sciences.Adapt to inquiry learning can suitably be learnt according to the feature selecting of learner content and
Learning method is used as recommendation.Learning path refers to the route and sequence of learning activities, is that learner refers in certain learning strategy
Lead down, the sequence according to learning objective and study content to the learning activities of required completion.Learning path be the resource of study,
Method, target, program, evaluation and monitoring etc. are organic into together with, and study content is presented to learner with different strategies.
Knowledge mapping formally proposes on May 17th, 2012 by Google, and its original intention is to improve the energy of search engine
Power, strengthens the search quality and search experience of user.At present, with the continuous hair that intelligent and individual info service is applied
Exhibition, knowledge mapping is widely used in the fields such as intelligent search, intelligent answer, personalized recommendation.Knowledge mapping has become
The strong tools of knowledge are represented with the digraph form of mark, and provide the semanteme of text message.Knowledge mapping is by will be every
Individual project, entity or user are represented as node, and those nodes of interaction between each other are chained up into structure by edge
The figure made.Side between node can represent any relation.Knowledge point is the substantially single of transmission knowledge information in learning activities
Member, single knowledge point should be able to embody knowledge content in itself refuse integrality, the set of knowledge point can guarantee that professional knowledge body
Relation between the global integrality knowledge point of system is the tie for connecting knowledge point, forms scattered knowledge point and is mutually related
The structure of knowledge.The present invention proposes a kind of learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting
Practise point tissue and execution route recommends method, have the aspect of progressive relationship enterprising from data, information and knowledge three study point
Refine to one step, targetedly one is provided efficiently for learner according to the current study condition and learning objective of learner
Lead strategy, it is considered to the difference of learner characteristics, teach students in accordance with their aptitude, it is ensured that learner learns on demand.
The content of the invention
Technical problem:It is an object of the invention to provide a kind of modeling of the learning ability of knowledge based collection of illustrative plates and dynamic self-adapting
Target drives study point tissue and execution route recommend method, for the learning demand and learning objective of learner, will learn
Habit point has from data, information and knowledge three further to be refined in the aspect of progressive relationship, and rational learn is recommended to learner
Point content and learning strategy are practised, study-leading person reaches learning objective, helps learner to improve learning efficiency, Optimization Learning effect
Really.
Technical scheme:The present invention is a kind of tactic method, can apply to provide learning guide for learner, contributes to
Solve under Network Study Environment, cognitive overload and study are got lost problem caused by a large amount of education resources.In a knowledge point collection of illustrative plates
On, present invention assumes that it is fixed that can be gained knowledge with unit energy under learner's unit interval, the node on knowledge mapping differs
Surely be it is independent, the present invention divide knowledge point foundation be the tissue according to textbook based on, knowledge point is divided into member and known
Know, Zhang Zhishi and piece knowledge, meta-knoeledge is the relatively independent, basic knowledge point that can not split again in knowledge hierarchy;Zhang Zhishi is
Obtained by related meta-knoeledge associative combination, express the more complete knowledge of certain limit internal ratio;Piece knowledge is to enter one to Zhang Zhishi
What the classification and summary of step were obtained.There is the similar knowledge point set of structure on collection of illustrative plates, but the semantic relation between knowledge point can
Can be different, having for the relation present invention definition between knowledge node following has five kinds(It is semantic)Relation is as shown in Figure 1:
1. first order relation:It node A must first be learnt could learn node B, i.e. learning knowledge point B to need knowledge point A support.First
Order relation has transitivity, including directly first order relation and indirect first order relation.If can directly learn after learning knowledge point A
Knowledge point B, then both meet directly first order relation.If other knowledge points of study are also needed to after learning knowledge point A to learn
Knowledge point B, then both meet first order relation indirectly;
2. cover relation:The knowledge point that node A is included covers node B, and learned node A can be without removing study node B again;
3. or relation:For final learning objective, study node A and node B can reach learning objective;
4. and relation(Parallel relation):It is independent between node, is not present with the knowledge point with relation in learning process
Sequencing;
5. necessary node:For final learning objective, the node of study must be removed;
6. free node:For some knowledge hierarchy, free node is the knowledge point useless to this knowledge hierarchy.
Method flow:
1. the study point tissue and execution of a kind of learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting
Recommend method in path, it is characterised in that the step of learning point recommendation and path optimization:
Step 1) oriented study point knowledge mapping is built, each knowledge of learner's team learning is drawn by big data training
Point to be spent the average level of time and efforts, i.e. study input, is made a mark as the weight of study point on collection of illustrative plates;
Step 2)Build exercise test library and Capability surveys questionnaire.Corresponding exercise test is built according to study point, according to ability
Examine or check type and build learner competencies questionnaire;
Step 3)Learner is pointed out to carry out exercise test.According to exercise test result, the preliminary palm for obtaining learner to study point
Hold situation;
Step 4)The learner obtained according to step 3 sets up learner's resource submodel to the study situation of knowledge point;
Step 5) learner competencies are investigated in the form of questionnaire.The present invention is by learner competencies horizontal division three etc.
Level be respectively " weak " " in " " strong ", according to Questionnaire results, acquisition learner memory capability, computing capability and inferential capability etc.
Level, entry evaluation learner's learning efficiency;
Step 6) according to the result of step 5, set up learner competencies submodel;
Step 7) the individual average ability level difference with learner colony of comparative learning person, mark off ability of learner etc.
Level;
Step 8) set up learner model.According to step 4 and the result of step 6, learner model is set up;
Step 9) obtain learner's anticipation learning input Expected_effort.Study input refers to that learner's plan can be with
To reach the time and efforts of learning objective input;
Step 10) learner's learning objective is obtained, and anticipation learning efficiency Expected_effi is calculated according to formula 1, wherein
Total_know refers to the knowledge point total amount that object knowledge is included:
(1);
Step 11) learner's target for getting of the learner model that is obtained according to step 8 and step 10 carries out to learning objective
Pattern match.Learning objective is divided, target type is determined;
Step 12) target type that is obtained according to step 11, it is determined that being traveled through on which layer resource processing framework.If learning
Habit person's learning objective is fairly simple, it is contemplated that study less input, learning ability is weaker, then on data collection of illustrative plates based on meta-knoeledge to
Learner recommends study point and learning path;If learner's learning objective difficulty is general, it is contemplated that study input is general, learning ability
Typically, then study point and learning path are recommended to learner based on Zhang Zhishi on Information Atlas;If learner's learning objective is difficult
Degree is larger, it is contemplated that study input is more, and learning ability is stronger, then recommends study point to learner based on piece knowledge on knowledge mapping
And learning path;
Step 13) mark learner's knowledge and object knowledge point on resource processing framework;
Step 14) dependent on the result obtained by step 13, traversal collection of illustrative plates finds out all first sequence nodes of object knowledge point;
Step 15) by step 14 produce it is all do not gain knowledge a little, there will be or relation knowledge node by learn the knowledge point
Required study input(That is weight)It is ranked up;
Step 16) cover the node of relation for existing, it is assumed that node A cover node B and node C contained by knowledge, judge node
Whether B and node C is all that learner is to reach the knowledge required for learning objective.If desired, calculate study node A and learn simultaneously
Practise the time and efforts needed for node B and node C;If need not, select the node for needing time and efforts less to be added to
Practise in path;
Step 17) result based on step 16 generation, other necessary nodes and parallel node are added in learning path;
Step 18) the complete learning path of output, recommend learner;
Step 19) in learner's learning process, the feedback of learner is constantly obtained, and monitor the change of external learning environment;
Step 20) result that is obtained according to step 19, learner actual learning efficiency Actual_effi is calculated according to formula 2,
Got_know represents the study point that learner has acquired, and the actual learning that Actual_effort is learner is put into, and statistics
The capacity variation of habit person, renewal learning person's model;According to the change of external learning environment, process resource framework is updated:
(2);
Step 21) learner model after the renewal that is obtained according to step 20, return to step 9 reacquires the study of learner
Target and anticipation learning input, learning path is planned according to the current study condition of learner again.
Architecture:
Fig. 2 gives the study point tissue of a kind of learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting
And execution route recommends the architecture of method, the knowledge hierarchy collection of illustrative plates of corresponding subject is built first, obtains the current of learner
Study condition and the learning objective finally to be realized, and mark on collection of illustrative plates the knowledge point of learner and do not gain knowledge
Point, the learning objective of learner is matched according to target pattern, generic is identified.Recommended based on data collection of illustrative plates to learner
Metadata, i.e., discrete knowledge point;Recommend the set of chapter data, i.e. correlated knowledge point to learner based on Information Atlas;It is based on
Knowledge mapping recommends piece knowledge to learner.By traveling through collection of illustrative plates, recommend to need the knowledge point of study and efficient to learner
Learning strategy.
Illustrating for data collection of illustrative plates, Information Atlas and knowledge mapping is given below.
Data collection of illustrative plates:Data collection of illustrative plates can record the frequency of meta-knoeledge appearance, including structure, time and three, space level
Frequency.Our definition structure frequency are that meta-knoeledge appears in number of times in different pieces of information structure, time frequency for meta-knoeledge when
Between track, spatial frequency is defined as the space tracking of meta-knoeledge.Pass between the node of each in figure can be described on data collection of illustrative plates
The tightness degree of connection, we are referred to as density, can reflect which meta-knoeledge contact is close, which meta-knoeledge contact is sparse.But
Accuracy on data collection of illustrative plates not to meta-knoeledge is analyzed, in fact it could happen that the meta-knoeledge of different names but is represented same and is known substantially
Know point, i.e. knowledge redundancy.To sum up, data collection of illustrative plates can only carry out static analysis to the data represented on collection of illustrative plates, it is impossible to analyze and pre-
Survey the dynamic change of data.
Data are the basic individual items of the numeral or other types information obtained by observing, but in no context
In the case of linguistic context, themselves is nonsensical.Data collection of illustrative plates can pass through the data knot such as array, chained list, queue, tree, stack, figure
Structure is expressed.On data collection of illustrative plates, by calculating the frequency of data, support and confidence level of the data on data collection of illustrative plates are drawn
Come deletion error or hash, the condition of deletion is the threshold requirement that must simultaneously meet support and confidence level, threshold value mistake
The big accuracy for being unfavorable for collection of illustrative plates expression, it is too small to be unfavorable for the integrality of expression, can be according to the result for calculating collection of illustrative plates feedback
Information is dynamically adjusted.
Information Atlas:Information is passed on by the context after data and data combination, by concept mapping and phase
The information of suitable analysis and explanation after the composition of relations of pass.Information Atlas can be expressed by relational database.Information
Data cleansing is carried out on collection of illustrative plates, redundant data is eliminated, it is preliminary abstract according to the interactive degree progress between node, improve the interior of design
Poly- property, by Metadata integration to chapter data.By drawing a circle to approve certain amount of entity, internal interactive degree and outside interactive degree are calculated,
Cohesion cohesion is equal to the ratio of internal interactive degree and outside interactive degree, and we set necessary between drawn a circle to approve knowledge point
It is interconnected.
Knowledge mapping:Knowledge is the overall understanding and consciousness obtained from the information of accumulation, Zhang Zhishi is carried out further
It is abstract and sort out can form a knowledge.Knowledge mapping can by the digraph comprising relation between node and node come
Expression.Various semantic relations can be included on knowledge mapping, and can carry out information inference and entity link, knowledge mapping without knot
Structure characteristic causes knowledge mapping can be with seamless link, so as to improve the marginal density and node density of knowledge mapping.Information inference
The support of dependency relation rule is needed, these rules can be by people's manual construction, but often time and effort consuming.At present, it is main
Inference rule is searched automatically dependent on the co-occurrence of relation, and using association mining technology.Paths ordering algorithm uses each different
Relation path as one-dimensional characteristic, built by building substantial amounts of relation path in knowledge graph the feature of relation classification to
Amount and relation grader extract relation.The correctness Cr of relation can be weighed by below equation:
Q presentation-entity E1 to entity E2 all relations, π represents a class relation,The weight of expression relation, can be by training
Draw, last correctness, which exceedes, thinks that the relation is set up after a certain threshold value.
Learner model:Multidate information in learner model in essential information and learning process comprising learner.Base
This information includes knowledge point, learning objective and not gained knowledge a little.Multidate information in learning process includes learner
Habit ability, is continuously evaluated the change of learner competencies in learner's learning process.
Beneficial effect:The inventive method proposes learning ability modeling and the dynamic self-adapting of a kind of knowledge based collection of illustrative plates
The study point tissue and execution route of target drives recommend method.With the following remarkable advantage:
(1)Reasonable disposition resource, improves the service efficiency of education resource:The reasonable disposition of education resource is China with effective use
Education resource on the important content of Development of Distance Education, network is enriched, and quality is very different, and the target of knowledge based collection of illustrative plates is driven
Dynamic study point is recommended to help learner on demand to learn, it is not necessary to take a significant amount of time and oneself needs is found in the resource of magnanimity
Education resource;
(2)Learning direction is guided for learner, it is to avoid knowledge is got lost:To learner's recommendation, there is provided learn with Optimization Learning path
Efficient strategy, helps learner to set up suitable knowledge hierarchy, learner is targetedly learnt, and improves study effect
Rate;
(3)The study situation of different learners is set up by analysis, learner model is set up, is targetedly different learners
Personalized learning guide is provided;
(4)According to extraneous academic environment, dynamic adjustment Distribution of knowledge gists and learning path.
Brief description of the drawings
Fig. 1 is the displaying for the incidence relation that may contain between node on knowledge mapping.
Fig. 2 be knowledge based collection of illustrative plates learning ability modeling and dynamic self-adapting target drives study point tissue and hold
Recommend the architecture of method in walking along the street footpath.
Fig. 3 is learner model.
Embodiment
A kind of knowledge based collection of illustrative plates learning ability modeling and dynamic self-adapting target drives study point tissue and hold
Walking along the street footpath recommend method specific embodiment be:
Step 1) corresponding to the operation 001 in Fig. 2, by the oriented study point process resource framework of existing resource construction,
Show that each knowledge point of learner's team learning to be spent the average level of time and efforts by big data training, that is, learn
Input, makes a mark as the weight of study point on collection of illustrative plates;
Step 2)Operation 002 builds exercise test library and Capability surveys questionnaire in corresponding diagram 2.Built according to study point corresponding
Exercise is tested, and examining or check type according to ability builds learner competencies questionnaire;
Step 3)Operation 003 points out learner to carry out exercise test in corresponding diagram 2.According to exercise test result, preliminary obtain is learned
Grasp situation of the habit person to study point;
Step 4)The learner that operation 004 is obtained according to step 3 in corresponding diagram 2 is to the study situation of knowledge point, and 005 sets up study
Person's resource submodel;
Step 5) in corresponding diagram 2 operation 006 learner competencies are investigated in the form of questionnaire.The present invention is by learner's energy
Power horizontal division Three Estate be respectively " weak " " in " " strong ", according to Questionnaire results, obtain learner's memory capability, calculate
The level such as ability and inferential capability, 007 entry evaluation learner's learning efficiency;
Step 6) in corresponding diagram 2 operation 008 according to the result of step 5, set up learner competencies submodel;
Step 7) 009 comparative learning person individual and the average ability level difference of learner colony, 010 are operated in corresponding diagram 2
Mark off the ability rating of learner;
Step 8) in corresponding diagram 2 operation 011 set up learner model.According to step 4 and the result of step 6, learner is set up
Model;
Step 9) in corresponding diagram 2 operation 012 obtain learner's anticipation learning input Expected_effort.Learning input is
It can be the time and efforts for reaching learning objective input to refer to learner's plan;
Step 10) in corresponding diagram 2 operation 013 obtain learner's learning objective, 014 calculates anticipation learning efficiency according to formula 1
Expected_effi, wherein Total_know refer to the knowledge point total amount that object knowledge is included:
(1);
Step 11) learner's mesh for getting of operation 015 is obtained according to step 8 in corresponding diagram 2 learner model and step 10
Mark carries out pattern match to learning objective.016 is divided learning objective, determines target type;
Step 12) target type that is obtained according to step 11, operation 017 determines which layer resource to handle framework in corresponding diagram 2
It is upper to be traveled through.If learner's learning objective is fairly simple, it is contemplated that less input for study, and learning ability is weaker, then in datagram
Study point and learning path are recommended to learner based on meta-knoeledge in spectrum;If learner's learning objective difficulty is general, it is contemplated that study
Input is general, and learning ability is general, then recommends study point and learning path to learner based on Zhang Zhishi on Information Atlas;If
Learner's learning objective difficulty is larger, it is contemplated that study input it is many, learning ability is stronger, then on knowledge mapping be based on piece knowledge to
Learner recommends study point and learning path;
Step 13) operation 018 mark learner's knowledge and object knowledge point on resource processing framework in corresponding diagram 2;
Step 14) result that depends on obtained by step 13, operation 019 travels through collection of illustrative plates and finds out object knowledge point in corresponding diagram 2
All first sequence nodes;
Step 15) in corresponding diagram 2 operation 020 by step 14 produce it is all do not gain knowledge a little, there will be or relation knowledge knot
Study input needed for pressing the study knowledge point(That is weight)It is ranked up;
Step 16) cover the node of relation for existing, it is assumed that node A cover node B and node C contained by knowledge, judge node
Whether B and node C is all that learner is to reach the knowledge required for learning objective.If desired, calculate study node A and learn simultaneously
Practise the time and efforts needed for node B and node C;If need not, select the node for needing time and efforts less to be added to
Practise in path;
Step 17) result based on step 16 generation, other necessary nodes and parallel node are added in learning path;
Step 18) the complete learning path of the output of operation 021 in corresponding diagram 2,022 recommends learner;
Step 19) in corresponding diagram 2 operation 023 in learner's learning process, constantly obtain the feedback of learner, and monitor outer
The change of portion's academic environment;
Step 20) operation 024 is obtained according to step 19 in corresponding diagram 2 result, learner's actual learning is calculated according to formula 2
Efficiency Actual_effi, Got_know represent the study point that learner has acquired, and Actual_effort is the reality of learner
Study input, and the capacity variation of statistical learning person, renewal learning person's model;According to the change of external learning environment, at renewal
Manage resource framework:
(2);
Step 21) learner model after operation 025 is obtained according to step 20 in corresponding diagram 2 renewal, return to step 9 is again
The learning objective and anticipation learning input of learner is obtained, learning path is planned according to the current study condition of learner again.
Claims (1)
1. the study point tissue and execution of a kind of learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting
Recommend method in path, it is characterised in that the step of study point is recommended and learning path optimizes:
Step 1) oriented study point knowledge mapping is built, each knowledge of learner's team learning is drawn by big data training
Point to be spent the average level of time and efforts, i.e. study input, is made a mark as the weight of study point on collection of illustrative plates;
Step 2)Exercise test library and Capability surveys questionnaire are built, building corresponding exercise according to study point tests, according to ability
Examine or check type and build learner competencies questionnaire;
Step 3)Learner is pointed out to carry out exercise test, according to exercise test result, the preliminary palm for obtaining learner to study point
Hold situation;
Step 4)The learner obtained according to step 3 sets up learner's resource submodel to the study situation of knowledge point;
Step 5) learner competencies are investigated in the form of questionnaire, the present invention is by learner competencies horizontal division three etc.
Level be respectively " weak " " in " " strong ", according to Questionnaire results, acquisition learner memory capability, computing capability and inferential capability etc.
Level, entry evaluation learner's learning efficiency;
Step 6) according to the result of step 5, set up learner competencies submodel;
Step 7) the individual average ability level difference with learner colony of comparative learning person, mark off ability of learner etc.
Level;
Step 8) learner model is set up, according to step 4 and the result of step 6, set up learner model;
Step 9) obtain learner anticipation learning input Expected_effort, study input refers to that learner's plan can be with
To reach the time and efforts of learning objective input;
Step 10) learner's learning objective is obtained, and anticipation learning efficiency Expected_effi is calculated according to formula 1, wherein
Total_know refers to the knowledge point total amount that object knowledge is included:
(1);
Step 11) learner's target for getting of the learner model that is obtained according to step 8 and step 10 carries out to learning objective
Pattern match, learning objective is divided, and determines target type;
Step 12) target type that is obtained according to step 11, it is determined that being traveled through on which layer resource processing framework, if
Habit person's learning objective is fairly simple, it is contemplated that study less input, learning ability is weaker, then on data collection of illustrative plates based on meta-knoeledge to
Learner recommends study point and learning path;If learner's learning objective difficulty is general, it is contemplated that study input is general, learning ability
Typically, then study point and learning path are recommended to learner based on Zhang Zhishi on Information Atlas;If learner's learning objective is difficult
Degree is larger, it is contemplated that study input is more, and learning ability is stronger, then recommends study point to learner based on piece knowledge on knowledge mapping
And learning path;
Step 13) mark learner's knowledge and object knowledge point on resource processing framework;
Step 14) dependent on the result obtained by step 13, traversal collection of illustrative plates finds out all first sequence nodes of object knowledge point;
Step 15) by step 14 produce it is all do not gain knowledge a little, there will be or relation knowledge node by learn the knowledge point
Required study input(That is weight)It is ranked up;
Step 16) cover the node of relation for existing, it is assumed that node A cover node B and node C contained by knowledge, judge node
Whether B and node C is all that learner is to reach the knowledge required for learning objective, if desired, calculates study node A and learns simultaneously
Practise the time and efforts needed for node B and node C;If need not, select the node for needing time and efforts less to be added to
Practise in path;
Step 17) result based on step 16 generation, other necessary nodes and parallel node are added in learning path;
Step 18) the complete learning path of output, recommend learner;
Step 19) in learner's learning process, the feedback of learner is constantly obtained, and monitor the change of external learning environment;
Step 20) result that is obtained according to step 19, learner actual learning efficiency Actual_effi is calculated according to formula 2,
Got_know represents the study point that learner has acquired, and the actual learning that Actual_effort is learner is put into, and statistics
The capacity variation of habit person, renewal learning person's model;According to the change of external learning environment, process resource framework is updated:
(2);
Step 21) learner model after the renewal that is obtained according to step 20, return to step 9 reacquires the study of learner
Target and anticipation learning input, learning path is planned according to the current study condition of learner again.
Priority Applications (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710416328.5A CN107038508A (en) | 2017-06-06 | 2017-06-06 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
Applications Claiming Priority (1)
Application Number | Priority Date | Filing Date | Title |
---|---|---|---|
CN201710416328.5A CN107038508A (en) | 2017-06-06 | 2017-06-06 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
Publications (1)
Publication Number | Publication Date |
---|---|
CN107038508A true CN107038508A (en) | 2017-08-11 |
Family
ID=59540950
Family Applications (1)
Application Number | Title | Priority Date | Filing Date |
---|---|---|---|
CN201710416328.5A Pending CN107038508A (en) | 2017-06-06 | 2017-06-06 | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method |
Country Status (1)
Country | Link |
---|---|
CN (1) | CN107038508A (en) |
Cited By (27)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107346346A (en) * | 2017-08-26 | 2017-11-14 | 海南大学 | Learner competencies modeling and learning process Optimal Management System based on data collection of illustrative plates, Information Atlas and knowledge mapping |
CN107734000A (en) * | 2017-09-23 | 2018-02-23 | 海南大学 | Storage and calculating Integrated optimization system towards the value-orientation of typing resource |
CN108052672A (en) * | 2017-12-29 | 2018-05-18 | 北京师范大学 | Promote structural knowledge map construction system and method using group study behavior |
CN108172047A (en) * | 2018-01-19 | 2018-06-15 | 上海理工大学 | A kind of network on-line study individualized resource real-time recommendation method |
CN108229578A (en) * | 2018-01-25 | 2018-06-29 | 海南大学 | Image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework |
CN108536799A (en) * | 2018-03-30 | 2018-09-14 | 上海乂学教育科技有限公司 | Adaptive teaching monitors and sees clearly information processing method |
CN108536861A (en) * | 2018-04-19 | 2018-09-14 | 中国科学院重庆绿色智能技术研究院 | A kind of interactive Training Methodology and its system of medical guide |
CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
CN108897879A (en) * | 2018-07-04 | 2018-11-27 | 北京希子教育科技有限公司 | A method of individualized teaching is realized by human-computer interaction |
CN109903201A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Personalized culture scheme generation method and system |
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 |
CN109920288A (en) * | 2019-03-29 | 2019-06-21 | 上海乂学教育科技有限公司 | Adaptive learning task intelligence generating means and computer learning system |
CN109949190A (en) * | 2019-03-22 | 2019-06-28 | 上海乂学教育科技有限公司 | Adaptive learning method and computer system based on learning efficiency |
CN110009957A (en) * | 2019-04-10 | 2019-07-12 | 上海乂学教育科技有限公司 | The big knowledge mapping test macro of mathematics and method in adaptive learning |
CN110032651A (en) * | 2019-04-18 | 2019-07-19 | 江苏师范大学 | A kind of constructing method of the individualized learning characteristic model of knowledge based map |
CN110197452A (en) * | 2019-06-11 | 2019-09-03 | 合肥明信软件技术有限公司 | A kind of intelligence adaptation on-line study and examination platform based on artificial intelligence technology |
CN110610002A (en) * | 2019-08-12 | 2019-12-24 | 华中师范大学 | Questionnaire information processing method and device, computer equipment and storage medium |
CN111309927A (en) * | 2020-02-17 | 2020-06-19 | 山东大学 | Knowledge graph mining-based personalized learning path recommendation method and system |
CN111310463A (en) * | 2020-02-10 | 2020-06-19 | 清华大学 | Test question difficulty estimation method and device, electronic equipment and storage medium |
CN111680170A (en) * | 2020-06-11 | 2020-09-18 | 南京星火技术有限公司 | Method and device for predicting physical characteristics of periodic structure and related product |
CN111859140A (en) * | 2020-07-28 | 2020-10-30 | 龙马智芯(珠海横琴)科技有限公司 | Knowledge recommendation method and device, recommendation equipment and readable storage medium |
CN111859144A (en) * | 2020-07-28 | 2020-10-30 | 科大讯飞股份有限公司 | Resource recommendation method, device, equipment and storage medium |
CN111914162A (en) * | 2020-06-01 | 2020-11-10 | 西安理工大学 | Method for guiding personalized learning scheme based on knowledge graph |
CN112199515A (en) * | 2020-11-17 | 2021-01-08 | 西安交通大学 | Polymorphic knowledge map driven knowledge service innovation method |
CN112258359A (en) * | 2020-10-30 | 2021-01-22 | 国网甘肃省电力公司 | Self-adaptive recommendation method and system |
CN113516574A (en) * | 2021-07-27 | 2021-10-19 | 北京爱学习博乐教育科技有限公司 | Self-adaptive learning system based on big data and deep learning and construction method thereof |
CN117252461A (en) * | 2023-08-29 | 2023-12-19 | 广州盈培教育科技有限公司 | Online training multimode teaching method and system based on big data |
-
2017
- 2017-06-06 CN CN201710416328.5A patent/CN107038508A/en active Pending
Cited By (37)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN107346346A (en) * | 2017-08-26 | 2017-11-14 | 海南大学 | Learner competencies modeling and learning process Optimal Management System based on data collection of illustrative plates, Information Atlas and knowledge mapping |
CN107734000A (en) * | 2017-09-23 | 2018-02-23 | 海南大学 | Storage and calculating Integrated optimization system towards the value-orientation of typing resource |
CN109903201A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Personalized culture scheme generation method and system |
CN109903201B (en) * | 2017-12-11 | 2022-04-19 | 北京三好互动教育科技有限公司 | Personalized culture protocol generation method and system |
CN108052672A (en) * | 2017-12-29 | 2018-05-18 | 北京师范大学 | Promote structural knowledge map construction system and method using group study behavior |
CN108172047A (en) * | 2018-01-19 | 2018-06-15 | 上海理工大学 | A kind of network on-line study individualized resource real-time recommendation method |
CN108172047B (en) * | 2018-01-19 | 2019-11-01 | 上海理工大学 | A kind of network on-line study individualized resource real-time recommendation method |
CN108229578A (en) * | 2018-01-25 | 2018-06-29 | 海南大学 | Image data target identification method based on three layers of data, information and knowledge collection of illustrative plates framework |
CN108536799A (en) * | 2018-03-30 | 2018-09-14 | 上海乂学教育科技有限公司 | Adaptive teaching monitors and sees clearly information processing method |
CN108536861A (en) * | 2018-04-19 | 2018-09-14 | 中国科学院重庆绿色智能技术研究院 | A kind of interactive Training Methodology and its system of medical guide |
CN108536861B (en) * | 2018-04-19 | 2022-03-18 | 中国科学院重庆绿色智能技术研究院 | Interactive training method and system for medical guide |
CN108776684B (en) * | 2018-05-25 | 2021-01-01 | 华东师范大学 | Optimization method, device, medium, equipment and system for edge weight in knowledge graph |
CN108776684A (en) * | 2018-05-25 | 2018-11-09 | 华东师范大学 | Optimization method, device, medium, equipment and the system of side right weight in knowledge mapping |
CN108897879A (en) * | 2018-07-04 | 2018-11-27 | 北京希子教育科技有限公司 | A method of individualized teaching is realized by human-computer interaction |
CN108897879B (en) * | 2018-07-04 | 2020-11-10 | 北京希子教育科技有限公司 | Method for realizing personalized teaching through man-machine interaction |
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 |
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 |
CN109949190A (en) * | 2019-03-22 | 2019-06-28 | 上海乂学教育科技有限公司 | Adaptive learning method and computer system based on learning efficiency |
CN109920288A (en) * | 2019-03-29 | 2019-06-21 | 上海乂学教育科技有限公司 | Adaptive learning task intelligence generating means and computer learning system |
CN110009957A (en) * | 2019-04-10 | 2019-07-12 | 上海乂学教育科技有限公司 | The big knowledge mapping test macro of mathematics and method in adaptive learning |
CN110032651A (en) * | 2019-04-18 | 2019-07-19 | 江苏师范大学 | A kind of constructing method of the individualized learning characteristic model of knowledge based map |
CN110197452A (en) * | 2019-06-11 | 2019-09-03 | 合肥明信软件技术有限公司 | A kind of intelligence adaptation on-line study and examination platform based on artificial intelligence technology |
CN110610002B (en) * | 2019-08-12 | 2022-07-01 | 华中师范大学 | Questionnaire information processing method and device, computer equipment and storage medium |
CN110610002A (en) * | 2019-08-12 | 2019-12-24 | 华中师范大学 | Questionnaire information processing method and device, computer equipment and storage medium |
CN111310463B (en) * | 2020-02-10 | 2022-08-05 | 清华大学 | Test question difficulty estimation method and device, electronic equipment and storage medium |
CN111310463A (en) * | 2020-02-10 | 2020-06-19 | 清华大学 | Test question difficulty estimation method and device, electronic equipment and storage medium |
CN111309927A (en) * | 2020-02-17 | 2020-06-19 | 山东大学 | Knowledge graph mining-based personalized learning path recommendation method and system |
CN111309927B (en) * | 2020-02-17 | 2023-07-18 | 山东大学 | Personalized learning path recommendation method and system based on knowledge graph mining |
CN111914162A (en) * | 2020-06-01 | 2020-11-10 | 西安理工大学 | Method for guiding personalized learning scheme based on knowledge graph |
CN111680170A (en) * | 2020-06-11 | 2020-09-18 | 南京星火技术有限公司 | Method and device for predicting physical characteristics of periodic structure and related product |
CN111859144A (en) * | 2020-07-28 | 2020-10-30 | 科大讯飞股份有限公司 | Resource recommendation method, device, equipment and storage medium |
CN111859140A (en) * | 2020-07-28 | 2020-10-30 | 龙马智芯(珠海横琴)科技有限公司 | Knowledge recommendation method and device, recommendation equipment and readable storage medium |
CN112258359A (en) * | 2020-10-30 | 2021-01-22 | 国网甘肃省电力公司 | Self-adaptive recommendation method and system |
CN112199515A (en) * | 2020-11-17 | 2021-01-08 | 西安交通大学 | Polymorphic knowledge map driven knowledge service innovation method |
CN112199515B (en) * | 2020-11-17 | 2023-08-15 | 西安交通大学 | Knowledge service innovation method driven by polymorphic knowledge graph |
CN113516574A (en) * | 2021-07-27 | 2021-10-19 | 北京爱学习博乐教育科技有限公司 | Self-adaptive learning system based on big data and deep learning and construction method thereof |
CN117252461A (en) * | 2023-08-29 | 2023-12-19 | 广州盈培教育科技有限公司 | Online training multimode teaching method and system based on big data |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
CN107038508A (en) | The study point tissue and execution route of the learning ability modeling of knowledge based collection of illustrative plates and the target drives of dynamic self-adapting recommend method | |
Janowicz et al. | Know, Know Where, KnowWhereGraph: A densely connected, cross-domain knowledge graph and geo-enrichment service stack for applications in environmental intelligence | |
CN107085618A (en) | Study point and learning path towards the 5W target drives based on data collection of illustrative plates, Information Atlas and knowledge mapping are recommended | |
Castro et al. | Applying data mining techniques to e-learning problems | |
Lavrov et al. | Organizational approach to the ergonomic examination of E-learning modules | |
Nilashi et al. | Assessing and prioritizing affecting factors in e-learning websites using AHP method and fuzzy approach | |
CN113851020A (en) | Self-adaptive learning platform based on knowledge graph | |
Khamparia et al. | A novel method of case representation and retrieval in CBR for e-learning | |
Sun et al. | Fuzzy knowledge graph system for artificial intelligence-based smart education | |
Akbar et al. | toward successful DevOps: a decision-making framework | |
Kour et al. | Analysis of student performance using Machine learning Algorithms | |
Ozcan et al. | A scientometric exploration of crowdsourcing: Research clusters and applications | |
Wu et al. | Using apriori algorithm on students’ performance data for Association Rules Mining | |
Akhrif et al. | Completeness based classification algorithm: a novel approach for educational semantic data completeness assessment | |
Daomin et al. | Appropriate learning resource recommendation in intelligent web-based educational system | |
Dimić et al. | An approach to educational data mining model accuracy improvement using histogram discretization and combining classifiers into an ensemble | |
Wen | Research on Effect Evaluation of Physical Education Teaching Based on Artificial Intelligence Expert Decision Making System | |
Lee et al. | An agent-based cognitive mapping system for sales opportunity analysis | |
Daniati et al. | Evaluation Framework for Decision Making Based on Sentiment Analysis in Social Media | |
Daniel et al. | A Bayesian belief network approach for modeling complex domains | |
Maroun et al. | Ontology-based approach for cybersecurity recruitment | |
Mediani et al. | Towards a recommendation system for the learner from a semantic model of knowledge in a collaborative environment | |
Rekha et al. | Ontology driven framework for assessing the syllabus fairness of a question paper | |
Begum et al. | Discovering student learning style using min max cascade neural network | |
Ogunkunle et al. | A data mining based optimization of selecting learning material in an intelligent tutoring system for advancing STEM education |
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 |
Application publication date: 20170811 |
|
RJ01 | Rejection of invention patent application after publication |