CN108596804A - Multithreading online education evaluation method - Google Patents
Multithreading online education evaluation method Download PDFInfo
- Publication number
- CN108596804A CN108596804A CN201810405203.7A CN201810405203A CN108596804A CN 108596804 A CN108596804 A CN 108596804A CN 201810405203 A CN201810405203 A CN 201810405203A CN 108596804 A CN108596804 A CN 108596804A
- Authority
- CN
- China
- Prior art keywords
- information
- course
- learner
- label
- online
- 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
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Systems or methods specially adapted for specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06N—COMPUTING ARRANGEMENTS BASED ON SPECIFIC COMPUTATIONAL MODELS
- G06N3/00—Computing arrangements based on biological models
- G06N3/02—Neural networks
- G06N3/08—Learning methods
- G06N3/084—Backpropagation, e.g. using gradient descent
Abstract
The present invention relates to distance education technique fields, present invention solves the technical problem that being that providing one kind having correction mechanism, can carry out the multithreading online education evaluation method of various dimensions evaluation, include the following steps：S1 basic informations obtain：It obtains learner and needs the course classification information learnt and personal basic information, wherein individual's basic information includes the first man label information that learner provides；S2 audition courses push：The classification that online course is selected according to the course classification information that learner provides, the first man label information that learner provides is matched with the original tag information of online course, and the online course for selecting matching degree high is pushed as audition course to learner；S3 audition results are fed back：Learning effect information of the learner to the audition course is obtained, and obtains the first course label information that learner adds the audition course；S4 gives lessons recommendation；S5 give lessons label optimization；S6 prediction models optimize.
Description
Technical field
The present invention relates to distance education technique fields, and in particular to a kind of multithreading online education evaluation method.
Background technology
With the development of information technology, more and more personalized learning systems and course for self-study is opened
Hair.On-line study has gradually been played important in the teaching process of school eduaction and all kinds of adult education of different phase
Effect.It is related to the on-line study resource of every subjects, even same section's purpose online course resource appears in network in large quantities
On, although a large amount of education resource provides more choices for learner, this is but also how learner is selecting to be suitble to
There is new puzzlement in terms of the online course of oneself.
That is, thering is the difference lecturer that gives lessons to give lessons for same knowledge point even same teaching material on network.
The style of giving lessons of each lecturer has differences.And the learning style of each student also differs.To a certain extent, if
The learning style of give lessons style and the student of lecturer can be allowed to match as far as possible, then can greatly also promote student's
Learning effect.But in existing online education mode, it is this for learning style and give lessons style matching process still
It is being studied in industry.
Such as in the document that China Patent Publication No. is CN106408475A, a kind of online course fitness-for-service assessment is disclosed
Method, this method is on the basis of statistical analysis learner's self-study feature, online course instructional strategies, by largely learning
The self-study feature of habit person and statistics calculating is carried out to the learning effect of online course, establishes learner personal touch and study
Then correlation model between effect carries out learning effect of the learner in course to be selected using the correlation model pre-
It surveys, helps learner to pick out most suitable course according to prediction result and learn, that is, select the best course of prediction result
Learnt.
In actual use, inventor is found that the final effect of this method excessively relies on correlation model, has ignored
The influences of the factors to last prediction result such as social development, epoch progress and learner's altered self.It is established in correlation model
Initial stage, this method can also recommend best course, but lead to final result meeting with the variation of some objective factors below
Slowly there is deviation.That is the model neither one correction mechanism, below, whole system can be gradually deviated from initial result.And
And in above-mentioned evaluation method, the dimensional comparison of evaluation is single, belongs to a kind of evaluation method of single thread, and such mode exists
The evaluation result problem not high enough with the actual match degree of learner (student).
In view of the above-mentioned problems, being badly in need of one kind now there is correction mechanism, the online education that can carry out various dimensions evaluation to comment
Valence method.
Invention content
Present invention solves the technical problem that being that providing one kind having correction mechanism, can carry out the multi-thread of various dimensions evaluation
Journey online education evaluation method.
Base case provided by the invention is：Multithreading online education evaluation method, includes the following steps：
S1 basic informations obtain：It obtains learner and needs the course classification information learnt and personal basic information, wherein institute
It includes the first man label information that learner provides to state personal basic information；
S2 audition courses push：The classification that online course is selected according to the course classification information that learner provides, will learn
The first man label information that person provides is matched with the original tag information of online course, the online class for selecting matching degree high
Cheng Zuowei auditions course is pushed to learner；
S3 audition results are fed back：Learning effect information of the learner to the audition course is obtained, and obtains learner to this
First course label information of audition course addition；
S4 gives lessons recommendation：The audition curriculum information is combined to push prediction model prediction to learner according to learning effect information
Learning outcome information and advisory information, wherein advisory information include be suitble to and replace, if learner selection be suitble to, by first
Course label information is added in the label to be confirmed of the course, and primarily determines that the learner is suitble to have such initial labels
The online course of information analyzes the first course label information if learner selects to replace, will if without sensitive vocabulary
First course label information is added in the original tag information of the course, and the first course label is shielded if having sensitive vocabulary
Information；
S5 give lessons label optimization：After learner has learnt online course, the learner is obtained to the of the online course
Two course label informations, if label to be confirmed is identical as the second course label information, label to be confirmed is added to initial labels
Information reminds learner to select label and the second course to be confirmed if label to be confirmed is different from the second course label information
The weight information of label information, is then added in original tag information；
S6 prediction models optimize：It obtains the learning outcome of learner and is sent to prediction model, prediction model is according to study
As a result self study is carried out.
The operation principle and advantage of the present invention is：In the acquisition of S1 basic informations, the course class of learner can be obtained
Other information and personal basic information, course classification information are exactly specifically the course that learner wants study, personal basis letter
Breath includes first man label information, the self-assessment of similar learner.Then the class for the online course to be learnt is determined
Not, the original tag information of first man label information and online course is next subjected to first time matching, selection is specific
Online course is supplied to learner as audition course.
Obtain the first course of learning effect of the learner after having learnt audition course and learner to the audition course
Label information, specifically, obtaining evaluation of the learner to the learning efficiency of the audition course and to the audition course.Then root
The learning effect for learning the audition course according to learner is predicted with prediction model, it is contemplated that complete course of learner's study
Effect.Specifically, can how long need cost, needs that how many practice done, how many knowledge point can be grasped.According to pre-
The learning outcome information of survey is recommended to confirm or be replaced to learner.Specifically, being to learn generic other by comparing
The actual learning effect of learner is recommended to learner, for example, other learners generic more than 50%, can recommend to fit
It closes, it is on the contrary then recommend to replace.The step for, it is very important, because the first matching is mainly the letter that learner oneself provides
Breath, in this process, there may be cannot accurately recognize oneself to learner.Therefore it can be carried out according to the result of audition
Optimization.
If learner is suitble to this online course, that is, recommend to be learnt, and the first course label information is converted to and is waited for
Confirm label, learner can carry out the online course in second evaluation (addition the second course label letter after study
Breath), if identical twice, then it represents that the learner has accurate understanding to the online course, and label to be confirmed is turned
Turn to the original tag information of the online course.If evaluation is different twice, the information evaluated twice can be added according to weight
It is added in original tag information.It in this way can be according to the difference of learner and the progress of learner, to the initial mark of online course
Label information is reasonably optimized.
If learner be not suitable for, replace online course, recommended again, with find be suitble to the learner study
Line course.It after the completion of learner learns, gets learning outcome and then feeds back to prediction model, prediction model is carried out excellent
Change.
Multithreading online education evaluation method of the present invention is recommended audition course according to the self-evaluation of learner, is then collected
Learning effect predicts the complete online course of learner's study, according to prediction result recommendation learner confirmation or more
It changes, and gets first course label information of the learner to audition course.This process be the first dimension, first in other words
The evaluation of thread, the i.e. first impression of learner.Then after the completion of learner learns, the second course label information is obtained, it is right
Initial course label carries out re-optimization, this is the second dimension, the in other words evaluation of the second thread.In the above method, constantly
There is learner to participate in, the evaluation of various dimensions, multithreading is carried out to online course, constantly corrects initial course label information
Ensure the evaluation to course, ensures the accuracy of original tag information.Reached have correction mechanism, can to online course into
The effect of row various dimensions evaluation.
Further, in S3 audition results feedback, further include, it is again fixed according to school's effect information and personal basic information
Adopted second people's label information.
By the above-mentioned means, the error brought because learner is inaccurate to the understanding of oneself can be reduced.Specifically,
Second people's label information is generated according to school's effect information and personal basic information, corrects the deviation of first man label.
Further, further include S7 mapping relations establishment steps：Establish first man label information, the first course label letter
Breath, label to be confirmed and original tag information mapping model step by step, learner input first man label information after by
The information that grade mapping model prediction learner provides below confirms for learner, wherein mapping model is BP neural network step by step
Model.
Such design is a kind of forecast function, by constantly optimizing, can be carried by prediction before user fills in
It allows user to select for suitable option, improves the usage experience of learner.
Further, in S4 gives lessons recommendation, prediction model is BP neural network model.
Such design is the self-learning property using BP neural network model, is constantly optimized to prediction model.
Further, first man label information includes attention time of concentration information, is easy to the expression side of the lecturer received
Formula information, self-disciplining information and study habit information.
Such design can more accurately collect first man label information.
Further, original tag information includes the expression way information, class pace information and emphasis knowledge point of lecturer
Repetitive rate.
Such design preferably can show original tag information to learner.
Description of the drawings
Fig. 1 is the flow chart of multithreading online education evaluation method embodiment of the present invention.
Specific implementation mode
Below by the further details of explanation of specific implementation mode：
Embodiment is substantially as shown in Fig. 1：
Multithreading online education evaluation method, includes the following steps：
S1 basic informations obtain：It obtains learner and needs the course classification information learnt and personal basic information, wherein institute
It includes the first man label information that learner provides to state personal basic information, and first man label information includes that attention is concentrated
Temporal information, expression way information, self-disciplining information and the study habit information for being easy to the lecturer received；
S2 audition courses push：The classification that online course is selected according to the course classification information that learner provides, will learn
The first man label information that person provides is matched with the original tag information of online course, the online class for selecting matching degree high
Cheng Zuowei auditions course to learner push, original tag information include the expression way information of lecturer, class pace information with
And emphasis knowledge point repetitive rate.；
S3 audition results are fed back：Learning effect information of the learner to the audition course is obtained, and obtains learner to this
First course label information of audition course addition redefines second people according to school's effect information and personal basic information
Label information；
S4 gives lessons recommendation：The audition curriculum information is combined to push prediction model prediction to learner according to learning effect information
Learning outcome information and advisory information, wherein advisory information include be suitble to and replace, if learner selection be suitble to, by first
Course label information is added in the label to be confirmed of the course, and primarily determines that the learner is suitble to have such initial labels
The online course of information analyzes the first course label information if learner selects to replace, will if without sensitive vocabulary
First course label information is added in the original tag information of the course, and the first course label is shielded if having sensitive vocabulary
Information, wherein prediction model are BP neural network model；
S5 give lessons label optimization：After learner has learnt online course, the learner is obtained to the of the online course
Two course label informations, if label to be confirmed is identical as the second course label information, label to be confirmed is added to initial labels
Information reminds learner to select label and the second course to be confirmed if label to be confirmed is different from the second course label information
The weight information of label information, is then added in original tag information；
S6 prediction models optimize：It obtains the learning outcome of learner and is sent to prediction model, prediction model is according to study
As a result self study is carried out；
S7 mapping relations establishment steps：Establish first man label information, the first course label information, label to be confirmed with
And the mapping model step by step of original tag information, the mapping model prediction science step by step after learner inputs first man label information
The information that habit person provides below confirms for learner, wherein mapping model is BP neural network model step by step.
When concrete application：It is obtained by S1 basic informations, learner is allowed to provide course classification information and personal basic information,
Course classification information is exactly specifically the course that learner wants study, and personal basic information includes first man label letter
Breath, the self-assessment of similar learner.Learning effect and learner of the learner after having learnt audition course are obtained to the examination
The first course label information of course is listened, specifically, obtaining learner to the learning efficiency of the audition course and to the audition
The evaluation of course.Then the learning effect for learning the audition course according to learner is predicted with prediction model, it is contemplated that study
The effect of complete course of person's study.
Specifically, can how long need cost, needs that how many practice done, how many knowledge point can be grasped.Root
It is predicted that learning outcome information, to learner recommend confirm or replace.Specifically, being generic by comparing study
The actual learning effect of other learners is recommended to learner, in this embodiment, other learners generic more than 60%,
It can recommend to be suitble to, it is on the contrary then recommend to replace.The step for, it is very important, because the first matching mainly learner is certainly
The information that oneself provides, in this process, there may be cannot accurately recognize oneself to learner.It therefore can be according to audition
Result optimize.
The present embodiment recommends audition course according to the self-evaluation of learner, then collects learning effect, learns to learner
A complete online course is predicted, recommends learner to confirm or replace according to prediction result, and get learner to examination
Listen the first course label information of course.This process is the first dimension, the evaluation of first thread in other words, i.e. learner
First impression.Then after the completion of learner learns, the second course label information is obtained, initial course label is carried out excellent again
Change, this is the second dimension, the in other words evaluation of the second thread.In the above method, constantly have learner participate in come in, to
Line course carries out the evaluation of various dimensions, multithreading, constantly corrects evaluation of the initial course label information guarantee to course, ensures
The accuracy of original tag information.
For the realization above method, the present embodiment also discloses a kind of multithreading online education evaluation, including：
Basic information acquisition module needs the course classification information learnt and personal basic information for obtaining learner,
The wherein described personal basic information includes the first man label information that learner provides, and first man label information includes paying attention to
Power time of concentration information, expression way information, self-disciplining information and the study habit information for being easy to the lecturer received.It is specific and
Speech, the hardware support of basic information acquisition module can be the information input equipments such as mouse, keyboard, touch screen and microphone.
In the present embodiment, what basic information acquisition module was selected is a PC computer, and learner is submitted by PC computers in webpage
The document of XML format includes personal basic information and first man label information, wherein first man label information in document
Including attention time of concentration information, the expression way information for being easy to the lecturer received, self-disciplining information and study habit letter
Breath.Personal basic information includes name, age, graduation universities and colleges, birthplace and the achievement at school.
Audition course pushing module, the course classification information for being provided according to learner select the classification of online course,
The first man label information that learner provides is matched with the original tag information of online course, selects matching degree high
Online course is pushed as audition course to learner, and original tag information includes the expression way information of lecturer, class pace
Information and emphasis knowledge point repetitive rate.Specifically, audition course pushing module is arranged in server beyond the clouds, audition course
The hardware support of pushing module is the cloud database for having reading and writing data function, preserves online course in database beyond the clouds
And corresponding original tag information.In the present embodiment, it is Ali's Cloud Server of our company's rentals.More also
Need to briefly describe, by first man label information and original tag information carry out matched algorithm we using
The term vector technology of Word2vec carries out matching operation, we are with the versions of Ben Schmidt exploitations.Use skip-gram
Method creates co-occurrence matrix, is mounted in Ali's Cloud Server, due to considerably less (the i.e. first man mark of the dimension of vector space
The dimension signed in the dimension and original tag information in information is considerably less), substantially handling result is to go out the second.It is excellent at other
In the embodiment of choosing, the dimension in first man label information and original tag information is can be increased, in this embodiment
The numerical value of the dimension of selection is 100, and subsequent dimension is increased newly by user, and after number of dimensions has expired, the evaluation most started is tieed up
Information deletion is spent, is iterated in this way.
Audition result feedback module for obtaining learning effect information of the learner to the audition course, and obtains study
The first course label information that person adds the audition course redefines the according to school's effect information and personal basic information
Two people's label informations.Audition result feedback module is also provided in Ali's Cloud Server.Specifically learning effect is believed
Breath, is obtained by way of examination question, i.e., after the completion of audition course, paper, hundred-mark system, including 20 choosings are sent to learner
Topic is selected, often inscribes 5 points.It is also similarly to be obtained by way of examination in the learning success information of complete online course of final study
's.
It gives lessons recommending module, for combining the audition curriculum information to push prediction mould to learner according to learning effect information
The learning outcome information and advisory information of type prediction, wherein advisory information include being suitble to and replacing, if learner's selection is suitble to,
First course label information is added in the label to be confirmed of the course, and primarily determines that the learner is suitble at the beginning of having such
The online course of beginning label information is analyzed the first course label information, if learner selects to replace if without sensitive word
First course label information is then added in the original tag information of the course by remittance, and the Lesson One is shielded if having sensitive vocabulary
Journey label information, wherein prediction model are BP neural network model.Prediction model is in input layer and output layer in the present embodiment
Between increase three layers of neuron, 10 nodes are provided that in every layer of neuron.Main cause be we develop this be
System is presently also in close beta, it is contemplated that the relationship of arithmetic speed does not complicate this prediction model.Due to BP god
It is a kind of prior art through network model, details are not described herein again.
It gives lessons label optimization module, for after learner has learnt online course, obtaining the learner to the online class
Second course label information of journey, if label to be confirmed is identical as the second course label information, label to be confirmed is added to just
Beginning label information reminds learner to select label to be confirmed and the if label to be confirmed is different from the second course label information
The weight information of two course label informations, is then added in original tag information.Specifically, what is realized is exactly in learner
After complete online course of study, entire online course is evaluated after having sufficient understanding.And it is initial with learner
The evaluation of this online course is compared, in this way by learning front and back comparison, obtains more objective appraisal.
Prediction model optimization module, learning outcome for obtaining learner are simultaneously sent to prediction model, prediction model root
Self study is carried out according to learning outcome；
Mapping relations establish module, for establishing first man label information, the first course label information, label to be confirmed
And the mapping model step by step of original tag information, mapping model is predicted step by step after learner inputs first man label information
The information that learner provides below confirms for learner, wherein mapping model is BP neural network model step by step.
When specifically used：Recommend audition course according to the self-evaluation of learner, then collect learning effect, learner is learned
It practises a complete online course to be predicted, recommends learner to confirm or replace according to prediction result, and get learner couple
First course label information of audition course.This process is the first dimension, the in other words evaluation of first thread, i.e. learner
First impression.Then after the completion of learner learns, the second course label information is obtained, initial course label is carried out excellent again
Change, ensures the accuracy of evaluation.
Above-described is only the embodiment of the present invention, and the common sense such as well known concrete structure and characteristic are not made herein in scheme
Excessive description, technical field that the present invention belongs to is all before one skilled in the art know the applying date or priority date
Ordinary technical knowledge can know the prior art all in the field, and with using routine experiment hand before the date
The ability of section, one skilled in the art can improve in conjunction with self-ability and implement under the enlightenment that the application provides
This programme, some typical known features or known method should not implement the application as one skilled in the art
Obstacle.It should be pointed out that for those skilled in the art, without departing from the structure of the invention, can also make
Go out several modifications and improvements, these should also be considered as protection scope of the present invention, these all do not interfere with the effect that the present invention is implemented
Fruit and patent practicability.The scope of protection required by this application should be based on the content of the claims, the tool in specification
The records such as body embodiment can be used for explaining the content of claim.
Claims (6)
1. multithreading online education evaluation method, which is characterized in that include the following steps：
S1 basic informations obtain：It obtains learner and needs the course classification information learnt and personal basic information, wherein described
People's basic information includes the first man label information that learner provides；
S2 audition courses push：The classification that online course is selected according to the course classification information that learner provides, learner is carried
The first man label information of confession is matched with the original tag information of online course, and the online course for selecting matching degree high is made
It is pushed to learner for audition course；
S3 audition results are fed back：Learning effect information of the learner to the audition course is obtained, and obtains learner to the audition
First course label information of course addition；
S4 gives lessons recommendation：The audition curriculum information is combined to push prediction model is predicted to learner according to learning effect information
Result information and advisory information are practised, wherein advisory information includes being suitble to and replacing, if learner's selection is suitble to, by the first course
Label information is added in the label to be confirmed of the course, and primarily determines that the learner is suitble to have such original tag information
Online course, if learner select replace, the first course label information is analyzed, by first if without sensitive vocabulary
Course label information is added in the original tag information of the course, and the first course label letter is shielded if having sensitive vocabulary
Breath；
S5 give lessons label optimization：After learner has learnt online course, second class of the learner to the online course is obtained
Journey label information, if label to be confirmed is identical as the second course label information, label to be confirmed is added to original tag information,
If label to be confirmed is different from the second course label information, remind learner that label and the second course label to be confirmed is selected to believe
The weight information of breath, is then added in original tag information；
S6 prediction models optimize：It obtains the learning outcome of learner and is sent to prediction model, prediction model is according to learning outcome
Carry out self study.
2. multithreading online education evaluation method according to claim 1, it is characterised in that：, it is characterised in that：It is tried in S3
In listening result to feed back, further include that second people's label information is redefined according to school's effect information and personal basic information.
3. multithreading online education evaluation method according to claim 1, it is characterised in that：, it is characterised in that：Further include
S7 mapping relations establishment steps：Establish first man label information, the first course label information, label to be confirmed and initial mark
The mapping model step by step for signing information, mapping model is predicted behind learner step by step after learner inputs first man label information
The information of offer confirms for learner, wherein mapping model is BP neural network model step by step.
4. multithreading online education evaluation method according to claim 1, it is characterised in that：, it is characterised in that：It is awarded in S4
During class is recommended, prediction model is BP neural network model.
5. multithreading online education evaluation method according to claim 1, it is characterised in that：, it is characterised in that：First
People's label information includes attention time of concentration information, is easy to the lecturer received expression way information, self-disciplining information and
Study habit information.
6. multithreading online education evaluation method according to claim 1, it is characterised in that：, it is characterised in that：Initial mark
Label information includes the expression way information, class pace information and emphasis knowledge point repetitive rate of lecturer.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810405203.7A CN108596804A (en) | 2018-04-28 | 2018-04-28 | Multithreading online education evaluation method |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810405203.7A CN108596804A (en) | 2018-04-28 | 2018-04-28 | Multithreading online education evaluation method |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108596804A true CN108596804A (en) | 2018-09-28 |
Family
ID=63620107
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810405203.7A Pending CN108596804A (en) | 2018-04-28 | 2018-04-28 | Multithreading online education evaluation method |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108596804A (en) |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543841A (en) * | 2018-11-09 | 2019-03-29 | 北京泊远网络科技有限公司 | Deep learning method, apparatus, electronic equipment and computer-readable medium |
| CN110009535A (en) * | 2019-03-13 | 2019-07-12 | 重庆三峡学院 | Traditional Chinese culture teaching information processing system and method Internet-based |
| CN111754370A (en) * | 2020-07-01 | 2020-10-09 | 广州驰兴通用技术研究有限公司 | Artificial intelligence-based online education course management method and system |
| CN113673811A (en) * | 2021-07-05 | 2021-11-19 | 北京师范大学 | Session-based online learning performance evaluation method and device |
| CN113762801A (en) * | 2021-09-17 | 2021-12-07 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN117408580A (en) * | 2023-12-15 | 2024-01-16 | 青岛理工大学 | Course quality assessment method and device and electronic equipment |
Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
| CN102822882A (en) * | 2010-01-15 | 2012-12-12 | 阿波洛集团公司 | Dynamically recommending learning content |
| CN103886054A (en) * | 2014-03-13 | 2014-06-25 | 中国科学院自动化研究所 | Personalization recommendation system and method of network teaching resources |
| CN105138624A (en) * | 2015-08-14 | 2015-12-09 | 北京矩道优达网络科技有限公司 | Personalized recommendation method based on user data of on-line courses |
| CN106408475A (en) * | 2016-09-30 | 2017-02-15 | 中国地质大学（北京） | Online course applicability evaluation method |
| CN107230174A (en) * | 2017-06-13 | 2017-10-03 | 深圳市鹰硕技术有限公司 | A kind of network online interaction learning system and method |
-
2018
- 2018-04-28 CN CN201810405203.7A patent/CN108596804A/en active Pending
Patent Citations (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101105853A (en) * | 2007-08-16 | 2008-01-16 | 上海交通大学 | Personalized teaching-guiding system based on non-zero jumping-off point in network teaching |
| CN102822882A (en) * | 2010-01-15 | 2012-12-12 | 阿波洛集团公司 | Dynamically recommending learning content |
| CN103886054A (en) * | 2014-03-13 | 2014-06-25 | 中国科学院自动化研究所 | Personalization recommendation system and method of network teaching resources |
| CN105138624A (en) * | 2015-08-14 | 2015-12-09 | 北京矩道优达网络科技有限公司 | Personalized recommendation method based on user data of on-line courses |
| CN106408475A (en) * | 2016-09-30 | 2017-02-15 | 中国地质大学（北京） | Online course applicability evaluation method |
| CN107230174A (en) * | 2017-06-13 | 2017-10-03 | 深圳市鹰硕技术有限公司 | A kind of network online interaction learning system and method |
Cited By (10)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN109543841A (en) * | 2018-11-09 | 2019-03-29 | 北京泊远网络科技有限公司 | Deep learning method, apparatus, electronic equipment and computer-readable medium |
| CN110009535A (en) * | 2019-03-13 | 2019-07-12 | 重庆三峡学院 | Traditional Chinese culture teaching information processing system and method Internet-based |
| CN111754370A (en) * | 2020-07-01 | 2020-10-09 | 广州驰兴通用技术研究有限公司 | Artificial intelligence-based online education course management method and system |
| CN111754370B (en) * | 2020-07-01 | 2021-04-27 | 厦门致力于学在线教育科技有限公司 | Artificial intelligence-based online education course management method and system |
| CN113673811A (en) * | 2021-07-05 | 2021-11-19 | 北京师范大学 | Session-based online learning performance evaluation method and device |
| CN113673811B (en) * | 2021-07-05 | 2023-06-27 | 北京师范大学 | On-line learning performance evaluation method and device based on session |
| CN113762801A (en) * | 2021-09-17 | 2021-12-07 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN113762801B (en) * | 2021-09-17 | 2024-03-26 | 北京量子之歌科技有限公司 | Network course management method, device, equipment and storage medium |
| CN117408580A (en) * | 2023-12-15 | 2024-01-16 | 青岛理工大学 | Course quality assessment method and device and electronic equipment |
| CN117408580B (en) * | 2023-12-15 | 2024-03-22 | 青岛理工大学 | Course quality assessment method and device and electronic equipment |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108596804A (en) | Multithreading online education evaluation method | |
| Jaiswal et al. | Potential of Artificial Intelligence for transformation of the education system in India. | |
| Larusson et al. | Learning analytics: From research to practice | |
| Nguyen et al. | Deep learning versus traditional classifiers on Vietnamese students’ feedback corpus | |
| Wang et al. | Learners’ perceived AI presences in AI-supported language learning: a study of AI as a humanized agent from community of inquiry | |
| Shabalala | The SACMEQ II project in Swaziland: a study of the conditions of schooling and the quality of education | |
| Kleimola et al. | Learning analytics to develop future competences in higher education: a case study | |
| WO2022193040A1 (en) | Science teaching system and method for using same, and computer-readable storage medium | |
| Raleiras et al. | Automatic learning styles prediction: A survey of the State-of-the-Art (2006–2021) | |
| Huhta | Language and communication for professional purposes needs analysis methods in industry and business and their yield to stakeholders | |
| Abana | A decision tree approach for predicting student grades in Research Project using Weka | |
| Dey et al. | Evaluation of the convincing ability through presentation skills of pre-service management wizards using AI via T2 linguistic fuzzy logic | |
| Phillips et al. | An AI toolkit to support teacher reflection | |
| Ergasheva et al. | COMPREHENSIVE APPROACH TO ASSESSING STUDENTS KNOWLEDGE IN PRIMARY SCHOOL BASED ON THE INTERNATIONAL ASSESSMENT PROGRAM IN THE REPUBLIC OF UZBEKISTAN. | |
| Shapovalova et al. | Adaptive testing model as the method of quality knowledge control individualizing | |
| Fagbola et al. | Development of mobile-interfaced machine learning-based predictive models for improving students performance in programming courses | |
| Riggs et al. | Handbook for applied modeling: non-Gaussian and correlated data | |
| Yang et al. | Artificial intelligence-enabled interactive system modeling for teaching and learning based on cognitive web services | |
| Moonen-van Loon et al. | Toward automatic interpretation of narrative feedback in competency-based portfolios | |
| Weber et al. | Design and Evaluation of an AI-based Learning System to Foster Students' Structural and Persuasive Writing in Law Courses | |
| Ashrafimoghari | Big Data and Education: using big data analytics in language learning | |
| Sherzad | Shaping the selection of fields of study in Afghanistan through educational data mining approaches | |
| Sunarti et al. | Optimation Parameter and Attribute Naive Bayes in Machine Learning for Performance Assessment in Online Learning | |
| Ivanova et al. | Application of Artificial Neural Networks in Intelligent Tutoring: A Contemporary Glance | |
| Iqbal et al. | Early grade prediction using profile data |
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: 20180928 |
|
| RJ01 | Rejection of invention patent application after publication |