CN110347893A - A kind of individualized learning content recommendation system based on subspace clustering - Google Patents
A kind of individualized learning content recommendation system based on subspace clustering Download PDFInfo
- Publication number
- CN110347893A CN110347893A CN201910661684.2A CN201910661684A CN110347893A CN 110347893 A CN110347893 A CN 110347893A CN 201910661684 A CN201910661684 A CN 201910661684A CN 110347893 A CN110347893 A CN 110347893A
- Authority
- CN
- China
- Prior art keywords
- content
- resource
- subspace clustering
- subspace
- learning content
- 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.)
- Withdrawn
Links
- 230000006399 behavior Effects 0.000 claims abstract description 9
- 230000000694 effects Effects 0.000 claims abstract description 6
- 230000002452 interceptive effect Effects 0.000 claims abstract description 5
- 238000002372 labelling Methods 0.000 claims description 12
- 238000010801 machine learning Methods 0.000 claims description 7
- 238000013135 deep learning Methods 0.000 claims description 5
- 238000012549 training Methods 0.000 claims description 5
- 238000004321 preservation Methods 0.000 claims description 4
- 230000003068 static effect Effects 0.000 claims description 4
- 230000006870 function Effects 0.000 claims description 3
- 230000006872 improvement Effects 0.000 claims description 3
- 238000004140 cleaning Methods 0.000 claims description 2
- 238000005457 optimization Methods 0.000 claims description 2
- 230000008901 benefit Effects 0.000 abstract description 4
- 230000002262 irrigation Effects 0.000 abstract 1
- 238000003973 irrigation Methods 0.000 abstract 1
- 238000005516 engineering process Methods 0.000 description 5
- 238000011156 evaluation Methods 0.000 description 4
- 230000007246 mechanism Effects 0.000 description 4
- 238000000034 method Methods 0.000 description 4
- 241001269238 Data Species 0.000 description 2
- 238000013473 artificial intelligence Methods 0.000 description 2
- 238000001914 filtration Methods 0.000 description 2
- 230000008569 process Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 230000003044 adaptive effect Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000007418 data mining Methods 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 230000004069 differentiation Effects 0.000 description 1
- 238000009472 formulation Methods 0.000 description 1
- 230000004927 fusion Effects 0.000 description 1
- 230000007786 learning performance Effects 0.000 description 1
- 239000000203 mixture Substances 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 238000002360 preparation method Methods 0.000 description 1
- 238000012163 sequencing technique Methods 0.000 description 1
- 230000008685 targeting Effects 0.000 description 1
- 238000012800 visualization Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/906—Clustering; Classification
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/95—Retrieval from the web
- G06F16/953—Querying, e.g. by the use of web search engines
- G06F16/9535—Search customisation based on user profiles and personalisation
-
- 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
- G06Q30/00—Commerce
- G06Q30/06—Buying, selling or leasing transactions
- G06Q30/0601—Electronic shopping [e-shopping]
- G06Q30/0631—Item recommendations
-
- 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
- G06Q50/2057—Career enhancement or continuing education service
Landscapes
- Engineering & Computer Science (AREA)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Accounting & Taxation (AREA)
- General Business, Economics & Management (AREA)
- General Engineering & Computer Science (AREA)
- Finance (AREA)
- Marketing (AREA)
- Human Resources & Organizations (AREA)
- Tourism & Hospitality (AREA)
- Data Mining & Analysis (AREA)
- Economics (AREA)
- Primary Health Care (AREA)
- General Health & Medical Sciences (AREA)
- Health & Medical Sciences (AREA)
- Development Economics (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Information Retrieval, Db Structures And Fs Structures Therefor (AREA)
Abstract
The invention discloses a kind of individualized learning content recommendation system based on subspace clustering, drip irrigation device includes the high-dimensional subspace clustering module of student, realizes that high dimensional data is gathered using subspace clustering algorithm；Commending contents engine modules comprising resource portrait and specific user are realized the portrait of content resource by learning Content resource tag module, then identify specific user by subspace special algorithm, generate recommendation results；The accurate display module of content, this part be it is application oriented, different interfaces can be designed according to concrete application and is showed, interface is shown by user, system is able to record that various information, such as user use the behaviors such as mode, the behaviour in service of resource, and the interactive information with system.The invention has the benefit that realizing the effect of " content appropriate is pushed to student appropriate in reasonable time ", the target of " varying with each individual, teach students in accordance with their aptitude " is really realized.
Description
Technical field
The invention belongs to content intelligent recommendation educational system technical field, and in particular to a kind of based on subspace clustering
Individualized learning content recommendation system.
Background technique
With quality-oriented education at home school, all kinds of training organizations it is universal, how by individualized education means, have
Arrow is put to promote the target that students ' learning performance is always school's pursuit.In the epoch that big data and artificial intelligence are prevailing, intelligence
Ground personalized recommendation engine is technology most popular both at home and abroad already, also more and more prominent in the status of education sector.
Internet penetrates into education sector just as air at present, on the one hand becomes the channel of many people study, can be with
It is linked into content resource abundant whenever and wherever possible；But on the other hand but needing to face covers the sky and the earth, largely homogeneity is interior
Hold, student is more and more difficult to the selection of accurate resource.It is known that each student is unique, their
Habit ability is different, level of learning is different, and each class achievement is different, so especially the intelligence learning of property one by one is needed to help
Hand solves the problems, such as the recommendation of personalized resource, so as to " learn from other's strong points to offset one's weaknesses " in all fields, on the whole capable of for quality-oriented education
Enough " advancing side by side ".It matches between student with independent individual character to solve the problems, such as this resource, has already appeared at present
It is based on data mining algorithm, such as collaborative filtering, cluster personalized recommendation teaching auxiliary system, is solved to a certain extent
The problem of conventional teaching platform determined centered on itself, has not fully taken into account the individual demand of user, can be for every
One system user is taught students in accordance with their aptitude, and the opposite resource for meeting user demand is provided.It is insufficient but there are still degree of refinement, for
The relatively wide in range deficiency of property.How to realize " content appropriate pass through in due course channel appropriate be pushed to it is appropriate
Student " is still our target.
Summary of the invention
The purpose of the present invention is to provide a kind of individualized learning content recommendation system based on subspace clustering, to solve
The problem of content initial evaluation and high-dimensional digitlization student cluster in study recommender system at present, realizes " content appropriate
Be pushed to student appropriate in reasonable time " effect, really realize " varying with each individual, teach students in accordance with their aptitude " target.
To achieve the above object, the invention provides the following technical scheme: a kind of personalization based on subspace clustering
Learning Content recommender system, comprising: learning Content resource tag module, the high-dimensional subspace clustering module of student, content push away
Recommend the accurate display module of engine modules, content；
Learning Content resource tag module, by intelligentized automated tag categorizing system, can to various content resources into
The effective labeling of row, that is, digitize, realize the portrait of content resource；
The high-dimensional subspace clustering module of student, realizes that high dimensional data is gathered using subspace clustering algorithm；
Commending contents engine modules comprising resource portrait and specific user, by learning Content resource tag module come real
The portrait of existing content office worker, then specific user is identified by subspace special algorithm, generate recommendation results.Generally according to recommendation
The difference of purpose can carry out the recommendation of diversified forms.There are two types of the most common recommendation results, and Top-N recommends, that is, N before recommending
A result is recommended.
The accurate display module of content, this part be it is application oriented, different interface exhibitions can be designed according to concrete application
It is existing, interface is shown by user, system is able to record that various information, such as user use the row such as mode, behaviour in service of resource
For, and the interactive information with system.
This programme is based on automated tag categorizing system, realizes the portrait of content resource, this solves content resource nature phase
Like the fusion application of property and dynamic similarity, while solving the problems, such as content resource initial evaluation.Pass through high-dimensional number simultaneously
The raw subspace clustering of chemistry is realized: by the high-dimensional digitlization of student and its data prediction, using subspace clustering
Algorithm realizes that tradition clusters insurmountable high-dimensional problem, this also makes the present invention program have extremely strong extended capability and adaptive
It should be able to power.
Preferably, the automated tag categorizing system includes the classification label system formulation portion formulated based on business demand
Divide, the cleaning training data set portion for preparing training data set part, retaining derivative effective field based on the data ecosphere
Divide, text participle model creation part, a variety of text models creation part, the model verifying improvement and optimization portion with linear weighted function
Divide, the preservation model part of the parameter of preservation model and weight.
Preferably, the machine learning model of the text participle model establishment portion sorting and deep learning algorithm be VSM,
One of TF-IDF algorithm, Bag-of-words bag of words are a variety of.
Preferably, during constructing resource tag, this system it is comprehensive using machine learning such as SVM/Bayes/NN and
The algorithm of deep learning carries out effective labeling to various content resources, that is, digitizes, to construct perfect automatic
Labeling system.
Preferably, during establishing content portrait, system is by the static information to content (in source resource, resource
Hold etc.), the data of multidate information and other information (such as commenting on) integrated, handled, to content progress labeling.
Preferably, the subspace clustering is the extension of traditional N-dimensional clustering, is allowed through creation row and column cluster
Simultaneously to be grouped feature and observation individual.Obtained group (cluster) is possible to the weight in the space of feature and observation individual
It is folded.
Technical effect and advantage of the invention:
The portrait that content resource is realized using mechanized classification tag system, realizes the labeling and digitlization of content resource,
The relevance and retrospective of content resource are also achieved, to recommend suitable content to lay the foundation to student.And high-dimensional number
Chemistry raw clustering algorithm, it can be achieved that student real classification, solve that traditional algorithm can not be competent at big data, big dimension is asked
Topic.
It can be truly realized " teaching students in accordance with their aptitude " in education sector, really realize that different individual users can obtain different push away
Content is recommended, corresponding resource is obtained in a manner of being more advantageous to self-growth, realizes the target of quality-oriented education comprehensively.In addition our
Case can also be promoted laterally in other industry, and the application of any required precision marketing scene can be promoted the use of, can be given
More effective effect, bigger benefit are brought using enterprise.
Detailed description of the invention
Fig. 1 is the solution of the present invention flow chart；
Fig. 2 is contents of the present invention resource portrait flow chart；
Fig. 3 is automated tag categorizing system figure of the invention；
Fig. 4 is 3-D data set figure.
Specific embodiment
Following will be combined with the drawings in the embodiments of the present invention, and technical solution in the embodiment of the present invention carries out clear, complete
Site preparation description, it is clear that described embodiments are only a part of the embodiments of the present invention, instead of all the embodiments.It is based on
Embodiment in the present invention, it is obtained by those of ordinary skill in the art without making creative efforts every other
Embodiment shall fall within the protection scope of the present invention.
The collaborative filtering mechanism that education content recommender system uses at present has been achieved with good benefit, realizes student's
Personalized intelligence learning solves the problems, such as the recommendation of personalized resource.But as a kind of recommendation mechanisms, however it remains it is certain
The shortcomings that, there are many problem of need to solve.Generally speaking, most typical problem has: initial evaluation problem and high-dimensional number
Change user's clustering problem to need to solve, individualized content recommender system can be made really to become " teaching students in accordance with their aptitude " through the invention
Intelligent recommendation system gives full play to big data and artificial intelligence technology in (movement) internet online education become increasingly popular
Play the role of more and more accurately " targeting ".
The present invention provides a kind of individualized learning content recommendation system based on subspace clustering as shown in Figure 1,
Including learning Content resource tag module, the high-dimensional subspace clustering module of student, commending contents engine modules and content essence
Quasi- display module.The learning Content resource tag module: by intelligentized automated tag categorizing system, to various contents
Resource carries out effective labeling, that is, digitizes, and realizes the portrait of content resource；The high-dimensional subspace clustering mould of student
Block: realize that high dimensional data is gathered using subspace clustering algorithm；Commending contents engine modules: it includes resource portrait and spy
Determine user, realize the portrait of content resource by learning Content resource tag module, then by subspace special algorithm come
It identifies specific user, generates recommendation results；The accurate display module of content: this part be it is application oriented, can be according to specifically answering
Showed with the interface for designing different, interface is shown by user, system is able to record that various information, such as user use resource
The behaviors such as mode, behaviour in service, and the interactive information with system.
One is done to each module below to illustrate.Learning Content resource tag module includes content resource portrait,
Content resource portrait is the labeling to content resource, and process is as shown in Figure 2: during establishing content portrait, system passes through
To the study number of the static information (source resource, resource content etc.), multidate information and other information (such as commenting on) of content
According to being integrated, being handled, labeling is carried out to content.In fact, label is a kind of to indicate content resource with brief language
A characteristic be suitble to " primary school " content such as some content belongs to " improving after class " class, read very high " height is read " etc.
Deng.A kind of digitized processing of content resource of this thing.
During constructing resource tag, this programme is comprehensive using machine learning and depth such as SVM/Bayes/NN
The algorithm of habit constructs automated tag categorizing system, as shown in Figure 3.
By intelligentized automated tag categorizing system, effective labeling can be carried out to various content resources, also
It is digitlization, this is the indispensable a part of recommended engine.
The another part for forming effective recommended engine is exactly high-dimensional student's the function of convergence.One targeted, practical
Recommender system be one " before thousand people " recommender system.And realize that this target factor in need of consideration is numerous, comprising: learn
Raw age, gender, region, family relationship, constellation, figure, hobby (reading, sport etc.), shopping, classmate's relationship, Shi Shengguan
System, family relationship, the grading for ging to school mechanism, the Historical Results of passing study or even life style etc. data, number of dimensions are super
Tens are crossed, is a kind of typical high dimensional data.In addition requirement of the system to real-time, this has had exceeded conventional statistics
Ability only just can effectively solve this problem using the model of machine learning.
High dimensional data refers to including having tens to several hundred, and the input of thousands of a features (or dimension) is arranged.This is example
Student's cluster in the document process and this programme such as typically encountered in bioinformatics (various sequencing datas) or NLP
Etc., it is typical high dimensional data that dimension (attribute) to be treated is especially mostly.High dimensional data is challenging, because are as follows:
High dimensional data will lead to so-called " curse of dimension ", i.e., all subspaces enumerate processing with why saying for dimension and
It is difficult to handle, while but also which understanding the visualization of machine learning result becomes.
Many dimensions directly may be without any relationship in high dimensional data, but meeting therefore can be possible effective
Group (cluster) is covered in noise data.
A kind of common mode of high dimensional data is feature selecting, but since different groups (cluster) needs different dimensions
Degree, therefore cannot be using the feature useless for a group (cluster) is simply deleted, because in addition this feature is likely to
The important feature of one group (cluster).
In the present solution, realizing using subspace clustering algorithm, the high-dimensional subspace clustering module of student is a kind of
It is the effective way for realizing high dimensional data clustering.Usual overall space refers to the space being made of all N-dimensional degree, and subspace
Cluster is a kind of technology that cluster is searched in different subspace (combinations of one or more dimensions).Basic assumption is that we can
To find the effective cluster only defined by dimension subset (not needing the consistency with all N number of features).For example, if we
The data attribute for considering input student is more than 50, only pass through check the wherein subset of certain 30 attribute can just find the " heart
Manage that quality is general, but like sport and mathematics " group (cluster), while other groups (cluster) may need other 40 attributes
Subset etc..In other words, subspace clustering is the extension of traditional N-dimensional clustering, is allowed poly- by creation row and column
Class simultaneously to be grouped feature and observation individual.Obtained group (cluster) is possible in the space of feature and observation individual
Overlapping.
Be illustrated in order to make it easy to understand, enumerating 3-D data set here: in Fig. 4, there are three dimension data acquisition system,
Wherein there are four group (clusters).Top half from the graph can be seen that and have intersection between two groups (cluster), this is to tradition
Clustering method cannot achieve differentiation.
The lower half portion of Fig. 4 is that the result two dimension of subspace clustering is shown, it can be seen that subspace clustering tries to find one
Sub-spaces (such as dimension A and C) wherein expected cluster readily identifies, and are easy to visualize and understand.
This is vital to the use of cluster result.It, can be more quasi- in this individualized teaching content recommendation system
Really, more targetedly.
Commending contents engine modules comprising resource portrait and specific user pass through learning Content resource tag module
It realizes the portrait of content office worker, then identifies specific user by subspace special algorithm, generate recommendation results.Generally according to
The difference for recommending purpose, can carry out the recommendation of diversified forms.There are two types of the most common recommendation results, and Top-N recommends, that is, pushes away
Top n result is recommended to be recommended.
User shows interface: this be user directly facing front end show, be the part of user interface.This part be towards
Application, different interfaces can be designed according to concrete application to be showed.In addition, by this interface, system can also be recorded respectively
Kind of information, for example user is using behaviors such as mode, the behaviours in service of resource, and with the interactive information of system etc..And these
Data are all significant datas that is further perfect and improving rate of accurateness, so this is also the important link for acquiring required data
One of.
The technical effect of this programme are as follows: the portrait model of content resource realizes the digitlization that content resource is recommended.By right
On the one hand the portrait of content resource can solve the initial evaluation problem of content resource, " cold start-up " for solving recommender system is asked
Topic；On the other hand digital basis can be provided for precisely matching User.
Using subspace clustering algorithm, high-dimensional digitlization student's clustering problem is realized.It is known that student's
Classification, the factor (dimension) of consideration is more, passes through deep learning algorithm, it is possible to more fully understand, hold user.It needs to consider
Dimension include age of student, gender, region, family relationship, the grading for ging to school mechanism, the Historical Results of passing study etc.
Information.This has been typically to need big data technology to handle high-dimensional problem.High dimensional data cluster is clustering
The difficult point and emphasis of technology, subspace clustering are the effective ways for realizing high dimensional data clustering.
Finally, it should be noted that the foregoing is only a preferred embodiment of the present invention, it is not intended to restrict the invention,
Although the present invention is described in detail referring to the foregoing embodiments, for those skilled in the art, still may be used
To modify the technical solutions described in the foregoing embodiments or equivalent replacement of some of the technical features,
All within the spirits and principles of the present invention, any modification, equivalent replacement, improvement and so on should be included in of the invention
Within protection scope.
Claims (7)
1. a kind of individualized learning content recommendation system based on subspace clustering, it is characterised in that: including learning Content resource
Labeling module, the high-dimensional subspace clustering module of student, commending contents engine modules, the accurate display module of content；
Learning Content resource tag module has various content resources by intelligentized automated tag categorizing system
The labeling of effect, that is, digitize, realize the portrait of content resource；
The high-dimensional subspace clustering module of student, realizes that high dimensional data is gathered using subspace clustering algorithm；
Commending contents engine modules comprising resource portrait and specific user, by learning Content resource tag module come real
The portrait of existing content resource, then specific user is identified by subspace special algorithm, generate recommendation results；
The accurate display module of content, this part be it is application oriented, different interfaces can be designed according to concrete application and is showed, lead to
It crosses user and shows interface, system is able to record various information, and user uses the behaviors such as mode, the behaviour in service of resource, Yi Jiyu
The interactive information of system.
2. a kind of individualized learning content recommendation system based on subspace clustering according to claim 1, feature exist
In: the automated tag categorizing system includes that the classification label system formulated based on business demand formulates part, based on data life
State circle prepares training data set part, the cleaning training data set part for retaining derivative effective field, text participle mould
Type creation part, a variety of text models creation part, the model verifying improvement and optimization part with linear weighted function, preservation model
The preservation model part of parameter and weight.
3. a kind of individualized learning content recommendation system based on subspace clustering according to claim 2, feature exist
In: the machine learning model and deep learning algorithm of the text participle model establishment portion sorting be VSM, TF-IDF algorithm,
One of Bag-of-words bag of words are a variety of.
4. a kind of individualized learning content recommendation system based on subspace clustering according to claim 2, feature exist
In: during constructing resource tag, a variety of text generation model parts be SVM, Bayes, NN machine learning and
One of algorithm of deep learning is a variety of, builds automated tag categorizing system.
5. a kind of individualized learning content recommendation system based on subspace clustering according to claim 1, feature exist
In: during establishing content portrait, for the system by the static information to content, static information includes source resource, money
Source contents, multidate information and other information are integrated, are handled such as the data of comment, carry out labeling to content.
6. a kind of individualized learning content recommendation system based on subspace clustering according to claim 1, feature exist
In: the subspace clustering is the extension of traditional N-dimensional clustering, by creation row and column cluster come simultaneously to feature and sight
It surveys individual to be grouped, obtained group or cluster can be overlapped in the space of feature and observation individual.
7. a kind of individualized learning content recommendation system based on subspace clustering according to claim 1, feature exist
In: the recommendation results are able to carry out the recommendation of diversified forms according to the difference for recommending purpose, and the recommendation results are Top-N
Recommend, i.e. recommendation top n result is recommended.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661684.2A CN110347893A (en) | 2019-07-22 | 2019-07-22 | A kind of individualized learning content recommendation system based on subspace clustering |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910661684.2A CN110347893A (en) | 2019-07-22 | 2019-07-22 | A kind of individualized learning content recommendation system based on subspace clustering |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110347893A true CN110347893A (en) | 2019-10-18 |
Family
ID=68179685
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910661684.2A Withdrawn CN110347893A (en) | 2019-07-22 | 2019-07-22 | A kind of individualized learning content recommendation system based on subspace clustering |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110347893A (en) |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807152A (en) * | 2019-10-31 | 2020-02-18 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
| CN111144732A (en) * | 2019-12-23 | 2020-05-12 | 江苏金智教育信息股份有限公司 | Student ability evaluation method and device based on behavior big data |
| CN111967541A (en) * | 2020-10-21 | 2020-11-20 | 上海冰鉴信息科技有限公司 | Data classification method and device based on multi-platform samples |
| CN113709062A (en) * | 2020-06-19 | 2021-11-26 | 天翼智慧家庭科技有限公司 | Resource adjustment method and system based on business dynamic portrait |
| CN115660608A (en) * | 2022-12-14 | 2023-01-31 | 揭阳职业技术学院 | One-stop innovative entrepreneurship incubation method |
-
2019
- 2019-07-22 CN CN201910661684.2A patent/CN110347893A/en not_active Withdrawn
Cited By (8)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110807152A (en) * | 2019-10-31 | 2020-02-18 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
| CN110807152B (en) * | 2019-10-31 | 2022-06-07 | 武汉天喻教育科技有限公司 | Method for creating recommendation engine system based on multiple services and storage medium |
| CN111144732A (en) * | 2019-12-23 | 2020-05-12 | 江苏金智教育信息股份有限公司 | Student ability evaluation method and device based on behavior big data |
| CN113709062A (en) * | 2020-06-19 | 2021-11-26 | 天翼智慧家庭科技有限公司 | Resource adjustment method and system based on business dynamic portrait |
| CN113709062B (en) * | 2020-06-19 | 2024-04-16 | 天翼视联科技有限公司 | Resource adjustment method and system based on business dynamic portrayal |
| CN111967541A (en) * | 2020-10-21 | 2020-11-20 | 上海冰鉴信息科技有限公司 | Data classification method and device based on multi-platform samples |
| CN111967541B (en) * | 2020-10-21 | 2021-01-05 | 上海冰鉴信息科技有限公司 | Data classification method and device based on multi-platform samples |
| CN115660608A (en) * | 2022-12-14 | 2023-01-31 | 揭阳职业技术学院 | One-stop innovative entrepreneurship incubation method |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110347893A (en) | A kind of individualized learning content recommendation system based on subspace clustering | |
| Bhatia | Data mining and data warehousing: principles and practical techniques | |
| Börner et al. | Skill discrepancies between research, education, and jobs reveal the critical need to supply soft skills for the data economy | |
| Xiaoyang et al. | Effectiveness of ideological and political education reform in universities based on data mining artificial intelligence technology | |
| Cechinel et al. | Mapping learning analytics initiatives in Latin America | |
| McNamara | Of intellectual monocultures and the study of IPE | |
| Fiaidhi | The next step for learning analytics | |
| CN107895026A (en) | A kind of implementation method of campus user portrait | |
| Granell | Multilingual information management: Information, technology and translators | |
| Karbhari et al. | Recommendation system using content filtering: A case study for college campus placement | |
| Pangrazio et al. | Datafication meets platformization: Materializing data processes in teaching and learning | |
| CN113886567A (en) | Teaching method and system based on knowledge graph | |
| Jacobs | Cultural impact on Lean Six Sigma and corporate success: Causal analyses considering the effects of national culture and leadership | |
| Aryal et al. | MoocRec: Learning styles-oriented MOOC recommender and search engine | |
| Wang et al. | Research on English teaching information pushing method based on intelligent adaptive learning platform | |
| Efrati et al. | A data mining approach to the analysis of students’ learning styles in an e-learning community: A case study | |
| Alzyoud et al. | Artificial intelligence in Jordanian education: Assessing acceptance via perceived cybersecurity, novelty value, and perceived trust | |
| D'Urzo et al. | Design-led repair & reuse: An approach for an equitable, bottom-up, innovation-driven circular economy | |
| Rahimi et al. | Investigating teachers’ perception about the educational benefits of Web 2.0 personal learning environments | |
| Tikhonova et al. | Exploring Academic Culture: Unpacking its Definition and Structure (A Systematic Scoping Review) | |
| Rather et al. | Information needs of users in the tech savvy environment and the influencing factors | |
| Hadeed et al. | Real-time based big data and e-learning: a survey and open research issues | |
| Zhang et al. | The track, hotspot and frontier of international MOOC research 2008–2018—a Scientometric analysis based on SCI and SSCI | |
| Hidayat et al. | Data analytics for effectiveness evaluation of islamic higher educationusing k-means algorithm | |
| Yang | English scores by distributed ID3 algorithm of computer network |
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 | ||
| WW01 | Invention patent application withdrawn after publication | ||
| WW01 | Invention patent application withdrawn after publication |
Application publication date: 20191018 |