CN108804543A - A kind of knowledge-ID analysis method based on FP-Growth algorithms - Google Patents
A kind of knowledge-ID analysis method based on FP-Growth algorithms Download PDFInfo
- Publication number
- CN108804543A CN108804543A CN201810465713.3A CN201810465713A CN108804543A CN 108804543 A CN108804543 A CN 108804543A CN 201810465713 A CN201810465713 A CN 201810465713A CN 108804543 A CN108804543 A CN 108804543A
- Authority
- CN
- China
- Prior art keywords
- data
- knowledge
- tree
- item
- answering
- 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
Landscapes
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of knowledge-ID analysis methods based on FP-Growth algorithms, include the following steps：The examination question result data of answering for obtaining student first is gone forward side by side line number Data preprocess, traditional FP-Growth algorithms are improved in combination with item consolidation strategy, then the data set after sliding-model control is iterated with improved FP-Growth algorithms, finally obtain the relevant rules between each examination question of answering, and then the corresponding correlation rule known between knowledge-ID.Present invention decreases the complexities of tree, significantly reduce the scale of search space, while decreasing the generation of frequent item set, achieve the purpose that improve algorithm operational efficiency.
Description
Technical field
The present invention relates to information-based, mathematicization education sector, more particularly to a kind of examination question based on FP-Growth algorithms is known
Know point analysis method.
Background technology
In recent years, the big data epoch driven with the rapid development of mobile Internet and cloud computing are new " tide ", I
State's education informationization construction initially enters the application development critical period of profit point.During modern teaching, examination is used as it
In an important ring, be still to examine one of the important means of student's learning outcome, feedback teachers ' teaching situation.From educational assessment side
Face sees that a large amount of paper examination questions answer data and provide the foundation well for education big data analysis, and paper is as evaluation
The carrier of one of raw most effective way, also can real-time collecting student answer a large amount of related data informations of feedback.On the other hand,
Examination paper analysis is along with examining as helping to understand teaching efficiency, determine whether the effective way for achieving the desired purpose and requiring
An indispensable part during examination.How to excavate and be hidden in immense value information therein and efficiently used, for religion
Process provides scientific guidance and scientific basis, improves teaching management level, is urgently to be resolved hurrily during modern development
Problem.
Data are generally all imperfect, inconsistent dirty datas in real world, can not directly carry out data mining, or
Result is barely satisfactory.Quality in order to improve data mining produces Data Preprocessing Technology.These data processing techniques
It is used before data mining, substantially increases the quality of data mining pattern, reduce the actual excavation required time.Data
There are many methods for pretreatment：Data cleansing refers to carrying out the process for examining and verifying again to data, it is therefore intended that deletes weight
Mistake existing for complex information, correction, and data consistency is provided；Data validity analysis refers to excluding some to follow-up data point
The factor of division life interference, to ensure the reliability of anaphase；Data Discretization processing be in programming one it is common
Skill, it can effectively reduce time complexity, and basic thought is exactly only to consider to need to use in the case of numerous possible
Value.
Correlative connection that may be present between searching item and item is concentrated to be referred to as association analysis from large-scale data
(association analysis) or correlation rule learn (association rule learning).Correlation rule is
Implications shaped like X → Y, wherein X and Y is referred to as the guide of correlation rule and subsequent.The motivation that correlation rule initially proposes
To be proposed for market basket analysis (Market Basket Analysis) problem, due to can be found that previous data analysis with
The related law hidden between the data that statistical method is unable to get, therefore correlation rule is probed into all the time all by field
The attention of interior numerous scholar experts, the importance of researching value are self-evident.Association Rule Analysis nowadays business, medical treatment,
The fields such as finance, insurance, education, meteorological observation, security and industry manufacture are widely used.
FP-Growth algorithms are the association analysis algorithms that Han Jiawei et al. was proposed in 2000, it takes following plan of dividing and ruling
Slightly：A kind of data structure being known as frequent pattern tree (fp tree) (Frequent Pattern Tree) has been used in the algorithm.Frequency will be provided
The database compressing of numerous item collection retains item collection related information to a frequent pattern tree (fp tree) (FP-tree).FP-tree is one
The special prefix trees of kind, are made of frequent item head table and item prefix trees.FP-Growth algorithms are accelerated entire based on above structure
Mining process.Experiment shows that FP-growth has good adaptability to the rule of different length, while relatively being passed through in efficiency
The association rule algorithm Apriori algorithm of allusion quotation has huge raising.
FP-Growth algorithms can be improved optimization by item consolidation strategy.The theoretical foundation of item consolidation strategy is as follows：
If including including frequent item set Y in each affairs of frequent item set X, but not including any superset of frequent item set Y, then X
∪ Y shapes need not search any item collection of the element comprising X but not comprising Y again at a closed frequent item-sets.
Invention content
The shortcomings that it is a primary object of the present invention to overcome the prior art and deficiency provide a kind of based on FP-Growth calculations
The knowledge-ID analysis method of method improves tradition FP-Growth algorithms by item consolidation strategy, provides a kind of excavation examination examination
In topic between knowledge point relevance analysis method.
The purpose of the present invention is realized by the following technical solution：
A kind of knowledge-ID analysis method based on FP-Growth algorithms, includes the following steps：
1) it obtains examination question to answer result data, and it is pre-processed, the pretreatment, which includes data cleansing, data, to be had
The analysis of effect property and Data Discretization processing；
2) FP-Growth algorithms are advanced optimized：By using item consolidation strategy, to being produced in traditional FP-Growth algorithms
Raw FP-Tree carries out beta pruning, obtains improved FP-Growth algorithms；Significantly reduce the scale of search space, while also subtracting
Lack the generation of frequent item set, improves algorithm operational efficiency.
3) algorithm minimum support and min confidence are set, with improved FP-Growth algorithms to pretreated
Data set is iterated, and finds out the relevance between examination question according to operation result, and then corresponding is known between knowledge-ID
Correlation rule；
4) according to the correlation rule between the knowledge-ID, for teacher optimize the content of courses with improve instructional strategies,
Student's regularized learning algorithm emphasis provides decision-making foundation, while the recommendation function of associated examination question is provided for teachers and students, preferably helps
Student consolidates content.
In step 1), the data cleansing is specially：Data are examined and are verified, the information that fills a vacancy deletes weight
Complex information corrects error message, and adjusts the structure of data to ensure the consistency of data；
The data validity is analyzed：First calculate data reliability, validity index, detection data it is consistent
Property, reliability and validity, then calculate the degree-of-difficulty factor of examination question, reject some degree-of-difficulty factors beyond within the scope of given threshold
The examination question of (too high or too low) avoids interfering subsequent examination question association analysis part, ensures the reasonability of analysis.
The Data Discretization is handled：Sliding-model control is made to acquired result data of answering, by objective item
In result of correctly answering be quantified as 1, the result of answering of mistake is quantified as 0, and score is more than the topic total score 60% in subjective item
Result of answering, which is considered as, answers accurately, is quantified as 1, and score is considered as inaccuracy of answering less than the result of answering of the topic total score 60%, measures
Turn to 0.
The step 2), specifically includes following steps：
2.1) scan database, finds out the set of frequent episode, and obtains their support counting (frequency)；Frequent episode
Set sorts according to the sequence of successively decreasing of support counting；
2.2) FP-Tree is created：First, the root node of tree is created, is labeled as " null "；Following scan data again
Library, the item in each affairs is sequentially inserted into frequent pattern tree (fp tree) by the sequence obtained in step 2.1), and is created to each affairs
One branch, insertion while, record the frequency of each transaction item, i.e. support；When increasing branch, along common prefix
The counting in each stage increases by 1, is that the item after prefix creates node and chain；After all affairs are all inserted into, just
To the FP-Tree built；
2.3) beta pruning is carried out to FP-Tree by item consolidation strategy：Each in the FP-Tree that bottom-up traversal generates
Head node, then using the node as suffix, obtain include the node itself all prefix paths；If the path is single-stranded
, then each element can merge with this node on path, generate frequent item set and then need to pass through if single-stranded
Item consolidation strategy is to determine whether in the presence of the place that can be merged, if can carry out beta pruning；If can if merge after beta pruning；
2.4) in the path obtained after the completion of the step 2.3), using comprising all suffix nodes as new suffix knot
Point regenerates new FP-Tree trees according to FP-Tree trees generating mode in step 2.2)；
2.5) step 2.2) that iterates terminates to change to step 2.4) until all items all only exist a paths
Generation.
The step 4), specifically includes following steps：
4.1) teacher improves itself instructional strategies, emphatically reinforce rule in several knowledge points explanation and be associated with impart knowledge to students, together
The extension of the knowledge points Shi Jinhang is explained so that student is to the understanding for lecture contents of imparting knowledge to students more thoroughly deeper into student is to awarding for promotion
The grasp of class knowledge point；
4.2) student adjusts itself study policy and emphasis, reinforces related knowledge point according to associated examination question is recommended
Understand and practice, consolidates the content in classroom.
Compared with prior art, the present invention having the following advantages that and advantageous effect：
1) FP-Growth algorithms are optimized in the present invention.By using item consolidation strategy, to traditional FP-
Growth algorithms are improved, and the FP-Tree to be generated to algorithm carries out beta pruning in detail, reduces the complexity of tree, substantially
Degree reduces the scale of search space, while decreasing the generation of frequent item set, achievees the purpose that improve algorithm operational efficiency.
2) present invention extracts examination question data information and its result of answering miscellaneous and more in education sector, line number of going forward side by side
According to relevant treatments work such as cleaning, data validity analysis and Data Discretization processing, correlation rule is applied into education neck
Potential relevance between testing and assessing examination question is excavated in domain, finds the correlation rule between knowledge-ID, while passing through knowledge point
Between supporting relation, it is thus understood that influencing each other between forerunner knowledge point and subsequent knowledge point, according to correlation rule to teaching live
It is dynamic targetedly to be adjusted, effectively carry out the individualized teaching taught students in accordance with their aptitude.
3) the present invention provides a kind of knowledge-ID analysis methods based on FP-Growth algorithms.By making to test and appraisal
It answers result data to carry out statistical disposition and be iterated data set with improved FP-Growth algorithms, excavates examination question knowledge
Relevance between point optimizes the content of courses for teacher and improves instructional strategies, student adjusts according to obtained correlation rule
Learn emphasis and decision-making foundation is provided, while the recommendation function of associated examination question being provided for teachers and students, preferably student is helped to consolidate
Content.
Description of the drawings
Fig. 1 is a kind of flow chart of the knowledge-ID analysis method based on FP-Growth algorithms of the present invention.
Fig. 2 is the detailed visioning procedure figure of FP-Tree.
Fig. 3 is to create the FP-Tree instance graphs completed.
Fig. 4 is FP-Tree beta pruning process schematics.
Fig. 5 is that improved FP-Tree excavates flow chart.
Specific implementation mode
Present invention will now be described in further detail with reference to the embodiments and the accompanying drawings, but embodiments of the present invention are unlimited
In this.
As shown in Figure 1, being a kind of schematic diagram of the knowledge-ID analysis method based on FP-Growth algorithms.One kind is suitable
Analysis method for excavating hiding correlation rule between examination examination question included knowledge point, includes the following steps：
1) it obtains examination question to answer result data, and carries out data cleansing, data validity analysis and data discrete to it
The related pretreatment work such as change processing.
2) FP-Growth algorithms are advanced optimized, by using item consolidation strategy, to being produced in traditional FP-Growth algorithms
Raw FP-Tree carries out beta pruning, significantly reduces the scale of search space, while decreasing the generation of frequent item set, improves
Algorithm operational efficiency.
3) algorithm minimum support and min confidence are set, with improved FP-Growth algorithms to sliding-model control
Data set afterwards is iterated, and finds out the relevance between examination question according to operation result, so it is corresponding know knowledge-ID it
Between correlation rule.
4) according to obtained correlation rule, optimize the content of courses for teacher and improve instructional strategies, student's regularized learning algorithm
Emphasis provides decision-making foundation, while the recommendation function of associated examination question is provided for teachers and students, preferably helps student to consolidate and is learned
Content.
Specifically, related data pretreatment work in step 1), includes the following steps：
1.1) data cleansing：Data are examined and are verified, the information that fills a vacancy deletes duplicate message, corrects mistake
Information, and the structure of data is adjusted to ensure the consistency of data.
1.2) data validity is analyzed：Calculate reliability, the validity index of data first, it is the consistency of detection data, reliable
Property and validity, then calculate examination question degree-of-difficulty factor, reject the too high or too low examination question of some degree-of-difficulty factors, avoid to rear
Continuous examination question association analysis part interferes, and ensures the reasonability of analysis.
1.3) Data Discretization processing：Sliding-model control is made to acquired result data of answering, it will be correct in objective item
Result of answering be quantified as 1, the result of answering of mistake is quantified as 0, and score is more than the knot of answering of the topic total score 60% in subjective item
Fruit, which is considered as, answers accurately, is quantified as 1, score is considered as inaccuracy of answering less than the result of answering of the topic total score 60%, is quantified as 0.
As shown in Fig. 2, for the visioning procedure figure of FP-Tree.The refinement step that FP-Tree is created is as follows：
2.1) scan database finds out the set of frequent episode and corresponding support counting.The set of frequent episode according to
The sequence sequence of successively decreasing of support counting.
2.2) initial FP-Tree is established, the root node of tree is created, is labeled as " null ".
2.3) scan database again, the item in each affairs are sequentially inserted into frequency all in accordance with the sequence obtained in step 2.1
Numerous scheme-tree, and a branch is created to each affairs, insertion while, records the frequency of each transaction item, i.e. support.
2.4) when increasing branch, the counting in each stage on common prefix increases by 1, is that the item after prefix creates knot
Point and link.After all affairs are all inserted into, the FP-Tree that is just built.
Table 1 lists a Transaction Information and indicates example, according to FP-Tree foundation steps, the FP- of obtained establishment completion
Tree is as shown in Figure 3.
1 Transaction Information table of table
| TID | Item lists |
| 1 | a,b,c |
| 2 | a,c |
| 3 | b,c |
| 4 | a,b,c,e |
| 5 | a,b |
| 6 | a,b,d |
| 7 | b,d |
| 8 | b,c |
| 9 | a,b,e |
FP-Growth algorithm optimizations need to carry out beta pruning to FP-Tree with item consolidation strategy.The theory of item consolidation strategy
According to as follows：If including including frequent item set Y in each affairs of frequent item set X, but not including any of frequent item set Y
Superset, then X ∪ Y shapes are at a closed frequent item-sets, and need not search any item collection of the element comprising X but not comprising Y again.
As shown in figure 4, being FP-Tree beta pruning process schematics.For two individual paths of FP-Tree in figure, b, a,
e:1 } and { b, a, c, e:1 }, using e as suffix, two prefix path is respectively { b, a:1 } and { b, a, c:1 }, the two paths
In all include item collection { b, a } and not comprising { b, a } true superset, by item consolidation strategy it is found that item collection { e } and item collection { b, a } shape
At closed frequent item-sets { b, a, an e:2 }, and by { c } beta pruning is carried out.
As shown in figure 5, to excavate flow chart according to the improved FP-Tree of item consolidation strategy.Excavate the refinement step of FP-Tree
It is rapid as follows：
3.1) the head node of each in the FP-Tree generated before bottom-up traversal, then after being with the node
Sew, obtain its all prefix path, prefix path is then added to get to comprising the paths FP-Tree including this node.
If 3.2) path obtained in step 3.1 is single-stranded, each element can merge with this node on path,
Frequent item set is generated then to need through item consolidation strategy to determine whether in the presence of that can merge if single-stranded
Place, if beta pruning can be carried out.If can if merge after beta pruning.
3.3) in the path obtained after the completion of step 3.2, using comprising all suffix nodes as new suffix node, press
New FP-Tree trees are regenerated according to FP-Tree tree generating modes.
3.4) step that iterates 3.1-3.3 terminates iteration until all items all only exist a paths.
A kind of knowledge-ID analysis method based on FP-Growth algorithms, it may be convenient to be applied to numerous examinations and tie
Item analysis link after beam, implements function such as simultaneously：(1) to examination question data information and its work miscellaneous and more in examination process
It answers result to extract, and carries out the relevant treatments work such as data cleansing, data validity analysis and Data Discretization processing；
(2) result data collection of answering is iterated by improved FP-Growth algorithms, excavates the association between knowledge-ID
Property；(3) according to obtained correlation rule, optimize the content of courses for teacher and improve instructional strategies, student's regularized learning algorithm stresses
Point provides decision-making foundation, is targetedly adjusted to education activities, effectively carries out the individualized teaching taught students in accordance with their aptitude, simultaneously
The recommendation function of associated examination question is provided for teachers and students, preferably student is helped to consolidate content.
The above embodiment is a preferred embodiment of the present invention, but embodiments of the present invention are not by above-described embodiment
Limitation, it is other it is any without departing from the spirit and principles of the present invention made by changes, modifications, substitutions, combinations, simplifications,
Equivalent substitute mode is should be, is included within the scope of the present invention.
Claims (4)
1. a kind of knowledge-ID analysis method based on FP-Growth algorithms, which is characterized in that include the following steps：
1) it obtains examination question to answer result data, and it is pre-processed, the pretreatment includes data cleansing, data validity
Analysis and Data Discretization processing；
2) FP-Growth algorithms are advanced optimized：By using item consolidation strategy, to what is generated in traditional FP-Growth algorithms
FP-Tree carries out beta pruning, obtains improved FP-Growth algorithms；
3) algorithm minimum support and min confidence are set, with improved FP-Growth algorithms to pretreated data
Collection is iterated, and the relevance between examination question, and then the corresponding association known between knowledge-ID are found out according to operation result
Rule；
4) according to the correlation rule between the knowledge-ID, optimize the content of courses for teacher and improve instructional strategies, student
Regularized learning algorithm emphasis provides decision-making foundation, while the recommendation function of associated examination question is provided for teachers and students.
2. the knowledge-ID analysis method based on FP-Growth algorithms according to claim 1, which is characterized in that step
1) in, the data cleansing is specially：Data are examined and are verified, the information that fills a vacancy deletes duplicate message, corrects mistake
False information, and the structure of data is adjusted to ensure the consistency of data；
The data validity is analyzed：Reliability, the validity index of data, the consistency of detection data, can are calculated first
By property and validity, the degree-of-difficulty factor of examination question is then calculated, rejects some degree-of-difficulty factors beyond the examination within the scope of given threshold
Topic；
The Data Discretization is handled：Sliding-model control is made to acquired result data of answering, by objective item just
True result of answering is quantified as 1, and the result of answering of mistake is quantified as 0, and score is more than answering for the topic total score 60% in subjective item
As a result it is considered as and answers accurately, is quantified as 1, score is considered as inaccuracy of answering less than the result of answering of the topic total score 60%, is quantified as
0。
3. the knowledge-ID analysis method based on FP-Growth algorithms according to claim 1, which is characterized in that described
Step 2) specifically includes following steps：
2.1) scan database, finds out the set of frequent episode, and obtains their support counting；The set of frequent episode is according to branch
The sequence sequence of successively decreasing of degree of holding counting；
2.2) FP-Tree is created：First, the root node of tree is created, is labeled as " null "；Following scan database again, often
Item in a affairs is all sequentially inserted into frequent pattern tree (fp tree) by the sequence obtained in step 2.1), and creates one point to each affairs
Branch, insertion while, record the frequency of each transaction item, i.e. support；When increasing branch, each rank on common prefix
The counting of section increases by 1, is that the item after prefix creates node and chain；After all affairs are all inserted into, structure has just been obtained
The FP-Tree built up；
2.3) beta pruning is carried out to FP-Tree by item consolidation strategy：Each in the FP-Tree that bottom-up traversal generates
Head node, then using the node as suffix, obtain include the node itself all prefix paths；If the path is single-stranded,
Then each element can merge with this node on path, generate frequent item set and then need to close by item if single-stranded
And strategy is to determine whether in the presence of the place that can be merged, if can carry out beta pruning；If can if merge after beta pruning；
2.4) in the path obtained after the completion of the step 2.3), using comprising all suffix nodes as new suffix node, press
New FP-Tree trees are regenerated according to FP-Tree trees generating mode in step 2.2)；
2.5) step 2.2) that iterates is to step 2.4), until all items all only exist a paths, terminates iteration.
4. the knowledge-ID analysis method based on FP-Growth algorithms according to claim 1, which is characterized in that described
Step 4) specifically includes following steps：
4.1) teacher improves itself instructional strategies, emphatically reinforce rule in several knowledge points explanation and be associated with impart knowledge to students, while into
The extension of row knowledge point is explained so that student is to the understanding for lecture contents of imparting knowledge to students more thoroughly deeper into promotion student knows giving lessons
Know the grasp of point；
4.2) student adjusts itself study policy and emphasis, reinforces the understanding in relation to knowledge point according to associated examination question is recommended
With practice, consolidate the content in classroom.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810465713.3A CN108804543A (en) | 2018-05-16 | 2018-05-16 | A kind of knowledge-ID analysis method based on FP-Growth algorithms |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810465713.3A CN108804543A (en) | 2018-05-16 | 2018-05-16 | A kind of knowledge-ID analysis method based on FP-Growth algorithms |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108804543A true CN108804543A (en) | 2018-11-13 |
Family
ID=64092397
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810465713.3A Pending CN108804543A (en) | 2018-05-16 | 2018-05-16 | A kind of knowledge-ID analysis method based on FP-Growth algorithms |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108804543A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209698A (en) * | 2019-05-13 | 2019-09-06 | 浙江大学 | A kind of textile design creative design method based on silk relics data |
| CN110632439A (en) * | 2019-09-29 | 2019-12-31 | 国网河南省电力公司电力科学研究院 | Power distribution network single-phase earth fault diagnosis technology based on synchronous waveform and association rule |
| CN112286900A (en) * | 2019-07-16 | 2021-01-29 | 北京字节跳动网络技术有限公司 | Data processing method, device, equipment and storage medium |
| CN112699308A (en) * | 2021-01-13 | 2021-04-23 | 敖客星云(北京)科技发展有限公司 | Clustering algorithm-based subject knowledge point recommendation method and system |
| CN116721001A (en) * | 2023-08-10 | 2023-09-08 | 江苏网进科技股份有限公司 | Smart city resource management method based on digital twinning |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN107315822A (en) * | 2017-07-04 | 2017-11-03 | 国网浙江省电力公司杭州供电公司 | A kind of method for digging of Knowledge Relation |
-
2018
- 2018-05-16 CN CN201810465713.3A patent/CN108804543A/en active Pending
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107122452A (en) * | 2017-04-26 | 2017-09-01 | 中国科学技术大学 | Student's cognitive diagnosis method of sequential |
| CN107315822A (en) * | 2017-07-04 | 2017-11-03 | 国网浙江省电力公司杭州供电公司 | A kind of method for digging of Knowledge Relation |
Non-Patent Citations (1)
| Title |
|---|
| 马月坤: "改进的FP-Growth算法及其分布式并行实现", 《哈尔滨理工大学学报》 * |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110209698A (en) * | 2019-05-13 | 2019-09-06 | 浙江大学 | A kind of textile design creative design method based on silk relics data |
| CN112286900A (en) * | 2019-07-16 | 2021-01-29 | 北京字节跳动网络技术有限公司 | Data processing method, device, equipment and storage medium |
| CN110632439A (en) * | 2019-09-29 | 2019-12-31 | 国网河南省电力公司电力科学研究院 | Power distribution network single-phase earth fault diagnosis technology based on synchronous waveform and association rule |
| CN112699308A (en) * | 2021-01-13 | 2021-04-23 | 敖客星云(北京)科技发展有限公司 | Clustering algorithm-based subject knowledge point recommendation method and system |
| CN116721001A (en) * | 2023-08-10 | 2023-09-08 | 江苏网进科技股份有限公司 | Smart city resource management method based on digital twinning |
| CN116721001B (en) * | 2023-08-10 | 2023-11-17 | 江苏网进科技股份有限公司 | Smart city resource management method based on digital twinning |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108804543A (en) | A kind of knowledge-ID analysis method based on FP-Growth algorithms | |
| Bamforth et al. | Introduction: archaeological approaches to lithic production skill and craft learning | |
| CN113851020A (en) | Self-adaptive learning platform based on knowledge graph | |
| CN111143750B (en) | University computer class course management platform based on fragmented learning | |
| Fathi et al. | Future study of operations research based on scenario planning and soft systems methodology | |
| Al-Nadabi et al. | Predict the selection of mathematics subject for 11 th grade students using Data Mining technique | |
| CN111476352A (en) | Deep learning-based method for analyzing effectiveness of code scanning and evaluation data in hall | |
| Kumar et al. | A naive based approach of model pruned trees on learner's response | |
| Li | A Data Mining-Based Method for Quality Assessment of Ideological and Political Education in Universities | |
| Lacerda et al. | Research methods and success meaning in project management | |
| de Carvalho et al. | Applying Causal Inference in Educational Data Mining: A Pilot Study. | |
| Panasov et al. | Decision Trees-based Anomaly Detection in Computer Assessment Results | |
| Qoiriah et al. | Application of k-means algorithm for clustering student’s computer programming performance in automatic programming assessment tool | |
| Chen et al. | Research on Intelligent Tutoring System Based on Data-Mining Algorithms | |
| Aljohani et al. | Impacts of Applying Artificial Intelligence on Decision-Making Quality: A Descriptive Study in Saudi Arabian Private Sector Organizations | |
| Xu et al. | A novel three-way decision model for improving computational thinking based on grey correlation analysis | |
| Coats | A comparison of organizational performance in publicly traded companies with and without a mature organizational learning culture | |
| Gomes et al. | A Machine Learning Approach for the Identification of Learners' Misconceptions in Algebraic Problem-Solving | |
| Villa-Torrano et al. | Early prediction of students' efficiency during online assessments using a Long-Short Term Memory architecture. | |
| Mugambi et al. | Influence of knowledge management practices on performance of law firms in Nakuru town, Kenya | |
| Deng et al. | An apriori-based approach for teaching evaluation | |
| Han | An evaluation method of English online learning behaviour based on feature mining | |
| Creamer et al. | Assessing the Extent That the Gender and STEM Practice-Oriented Literature Is Evidence-Based. | |
| Huang et al. | Modeling Variation in Human Feedback with User Inputs: An Exploratory Methodology | |
| Wang | The blending teaching effect evaluation of distance education under the background of MOOC |
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: 20181113 |
|
| RJ01 | Rejection of invention patent application after publication |