CN110288270A - Learning effect detection method based on artificial intelligence - Google Patents
Learning effect detection method based on artificial intelligence Download PDFInfo
- Publication number
- CN110288270A CN110288270A CN201910611892.1A CN201910611892A CN110288270A CN 110288270 A CN110288270 A CN 110288270A CN 201910611892 A CN201910611892 A CN 201910611892A CN 110288270 A CN110288270 A CN 110288270A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- student
- knowledge
- learned
- weak
- 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
- 238000001514 detection method Methods 0.000 title claims abstract description 54
- 230000000694 effects Effects 0.000 title claims abstract description 24
- 238000013473 artificial intelligence Methods 0.000 title claims abstract description 11
- 238000012360 testing method Methods 0.000 claims abstract description 19
- 238000013507 mapping Methods 0.000 claims abstract description 15
- 238000000034 method Methods 0.000 description 19
- 230000008569 process Effects 0.000 description 11
- 238000012545 processing Methods 0.000 description 8
- 238000011156 evaluation Methods 0.000 description 5
- 235000013399 edible fruits Nutrition 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 230000007246 mechanism Effects 0.000 description 3
- 230000015654 memory Effects 0.000 description 3
- 230000004044 response Effects 0.000 description 3
- 230000005540 biological transmission Effects 0.000 description 2
- 230000008859 change Effects 0.000 description 2
- 239000003814 drug Substances 0.000 description 2
- 238000002474 experimental method Methods 0.000 description 2
- 230000007786 learning performance Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 230000006403 short-term memory Effects 0.000 description 2
- 238000013461 design Methods 0.000 description 1
- 238000010586 diagram Methods 0.000 description 1
- 238000005194 fractionation Methods 0.000 description 1
- 238000012812 general test Methods 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000007689 inspection Methods 0.000 description 1
- 230000007774 longterm Effects 0.000 description 1
- 230000003287 optical effect Effects 0.000 description 1
- 230000008447 perception Effects 0.000 description 1
- 230000000750 progressive effect Effects 0.000 description 1
- 238000013102 re-test Methods 0.000 description 1
- 238000012552 review Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- 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
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Human Resources & Organizations (AREA)
- Educational Administration (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- Economics (AREA)
- Tourism & Hospitality (AREA)
- Educational Technology (AREA)
- General Physics & Mathematics (AREA)
- Physics & Mathematics (AREA)
- General Business, Economics & Management (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Health & Medical Sciences (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Quality & Reliability (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The learning effect detection method based on artificial intelligence that this application involves a kind of, the following steps are included: selecting a knowledge point as knowledge point to be learned from weak knowledge point list, wherein, each of weak knowledge point list knowledge point has respectively corresponded corresponding ability value；Pushing learning resource relevant to knowledge point to be learned is learnt to student；The study situation that learning knowledge point is treated according to student provides corresponding detection topic and detects to student；According to testing result, ability value corresponding with knowledge point to be learned is updated；And according to updated ability value, mark knowledge point to be learned.Learning effect detection method provided by the present application more effectively finds the weak knowledge point of student by way of knowledge mapping, and student is evaluated in a manner of ability value to the grasp situation of knowledge point, personalized complete detection scheme can be formulated for student.
Description
Technical field
This application involves education sector more particularly to a kind of learning effect detection methods based on artificial intelligence.
Background technique
In conventional teaching, teacher is to the inspection of students ' learning performance generally in operation and examination.In operation and examination
In, teacher probably can have a rough understanding to the acquisition of knowledge degree of student according to the answer situation of student.But it is difficult to
The statistics of full dose is carried out to mastery of knowledge situation.Also, usual teacher can detect difference by unified operation and examination
The learning effect of student can not provide personalized detection and evaluation also for student.
Summary of the invention
Why inventor can not accomplish comprehensive and individual character by long-term observation and experiment discovery in previous teaching
On the one hand the detection and evaluation of change are the influence due to domestic for a long time educational environment and educational concept, educator and religion
The importance that mechanism is unaware of personalized detection and evaluation is educated, is more likely to using standardized detection mode, in other words more
Tend to that student is cultivated and educated using unified mode, and student is evaluated using unified standard.And because of tradition
The fractionation of knowledge point is not very fine in teaching, if to carry out mastery of knowledge situation the statistics of full dose, needs to spend
The more time, so general test is not will do it comprehensive analysis.
On the other hand, personalized detection needs to formulate different detection schemes according to different students, it is also necessary to dynamically
The study situation of student is tracked, and correspondingly adjusts and update detection scheme.And in the past due to lacking big data and artificial intelligence
The support and application of technology also accomplish personalized detection towards a large amount of students without condition.
In view of the above drawbacks of the prior art, the application provides a kind of learning effect detection side based on artificial intelligence
Method more effectively finds the weak knowledge point of student by way of knowledge mapping, and student is evaluated in a manner of ability value to knowing
The grasp situation for knowing point, personalized detection scheme is formulated for student, makes it possible to more be had needle to the learning effect of student
Detection to property, so that the detection and evaluation to students ' learning performance are more accurate and comprehensive.
Knowledge mapping: all knowledge points in study stage and before are put together in the current study stage, are fabricated to tool
There is the knowledge mapping of preposition successor relationship.Preposition successor relationship: referring to that knowledge point b can not learn is can not learn because of knowledge point a, can
Claiming a is the preposition knowledge point of b, and b is the subsequent knowledge point of a.And knowledge mapping is exactly the preposition successor relationship between knowledge point
Mark the clear structure of knowledge.The knowledge point in each subject each study stage is combined in the way of big data,
And preposition successor relationship is marked to each knowledge point, be formed by knowledge mapping can promote significantly student study,
Understand and remembers.And it is this by big data generate knowledge mapping in the way of, traditional education sector be difficult to imagine also without
What method was realized.It is not had in traditional education sector due to the influence of integrated environment and the restriction of objective condition in other words
People wants in this way to go that all relevant knowledge points are associated and are marked.
Ability value: student grasps situation to the whole of some knowledge point.It is a kind of " latent that item response theory assumes that subject has
In speciality ", latent trait is a kind of statistics conception proposed on the basis of observation analysis is test and reacted, in test, potential spy
Matter generally refers to potential ability, and the estimation through common test total score as this potentiality.Item response theory is thought to be tested
Reaction and achievement and their latent trait on test item have special relationship.Latent trait is exactly our ability
Value.It is acquired using artificial intelligence technology and analyzes a large amount of students to the learning process of each knowledge point, thus to each knowledge point
Set and simultaneously dynamically adjust corresponding ability value, can the study situation effectively to student accurately evaluated.It is based on
This evaluation method that can quantify is conducive to intelligently push personalized education resource to student, and intelligently adjusts
The process of whole student's study.And it is this by artificial intelligence technology student is evaluated in the way of, in traditional education sector
Being difficult to imagine also cannot achieve.In other words in traditional education sector, due to the influence and objective condition of integrated environment
It restricts, never someone wants to go to be adjusted the Grasping level of each knowledge point for each student in this way.
In this application, for some specific student, it is set with corresponding ability value for each knowledge point,
Student can be judged to the grasp situation of knowledge point (such as: up to standard or not up to standard) according to ability value.In student's study or again
During habit, the case where learning or review according to student, ability value can be dynamically adjusted.
The application provides a kind of learning effect detection method based on artificial intelligence, comprising the following steps: from weak knowledge
Select a knowledge point as knowledge point to be learned in point list, wherein each of weak knowledge point list knowledge point point
It is not corresponding with corresponding ability value；Pushing learning resource relevant to knowledge point to be learned is learnt to student；According to
The raw study situation for treating learning knowledge point provides corresponding detection topic and detects to student；According to testing result, it updates
Ability value corresponding with knowledge point to be learned；And according to updated ability value, mark knowledge point to be learned.
In some embodiments, optionally, further comprise: judging to selected knowledge point from weak knowledge point list
Whether quantity reaches knowledge point amount threshold, wherein if the quantity of selected knowledge point is not up to knowledge point amount threshold,
It selects next knowledge point as knowledge point to be learned from weak knowledge point list, and repeats to push step, step, more is provided
New step, markers step.
In some embodiments, optionally, further comprise: judging to selected knowledge point from weak knowledge point list
Whether quantity reaches knowledge point amount threshold, wherein if the quantity of selected knowledge point reaches knowledge point amount threshold, root
According to student to the study situation of all selected knowledge points, corresponding detection topic is provided to student and carries out stage detection.
In some embodiments, optionally, knowledge point amount threshold is 2,3,4 or 5.
In some embodiments, optionally, further comprise: judging to know in weak knowledge point list with the presence or absence of non-selected
Know point, wherein if there are non-selected knowledge points in weak knowledge point list, select from weak knowledge point list next
Knowledge point repeats to push step, provides step, updates step, markers step as knowledge point to be learned.
In some embodiments, optionally, further comprise: judging to know in weak knowledge point list with the presence or absence of non-selected
Know point, wherein if non-selected knowledge point is not present in weak knowledge point list, terminate to detect.
In some embodiments, optionally, student is tested according to knowledge mapping to obtain weak knowledge point list,
Wherein, knowledge mapping includes the knowledge point for being marked with preposition successor relationship.
In some embodiments, optionally, selection step further comprises: in weak knowledge point list, from non-selected
Select the corresponding highest knowledge point of ability value as knowledge point to be learned in knowledge point.
In some embodiments, optionally, providing step further comprises: according to the wrong topic in students'learning
Difficulty and quantity determine detection topic difficulty and quantity.
In some embodiments, optionally, markers step further comprises:, will if updated ability value is up to standard
Knowledge point to be learned is labeled as having grasped, and deletes knowledge point to be learned from weak knowledge point list.
Compared with prior art, the technical solution of the application include at least following improvement and the utility model has the advantages that
First, it can detecte the Grasping level for the knowledge point learned.
Second, multiple knowledge point bundle tests after study, because study has a short time memory, if just finishing one
Knowledge point is just tested, and short-term memory may make student answer questions topic, is not necessarily and is really grasped, and system is mixed to student and learned
Several knowledge points are tested unified, achieve the purpose that test whether really to grasp.
Third is practiced in addition to test can also be played the role of consolidating to student every a period of time again, can reinforce slapping
Hold degree.
4th, the ability value of knowledge point is updated in test process, can be verified student and never be attended the meeting in learning process
Ability value variation.
It is described further below with reference to technical effect of the attached drawing to the design of the application, specific structure and generation, with
It is fully understood from the purpose, feature and effect of the application.
Detailed description of the invention
When following detailed description is read in conjunction with the figure, the application will be become more fully understood from, throughout the drawings, identical
Appended drawing reference represent identical part, in which:
Fig. 1 is the flow chart of one embodiment of the learning effect detection method of the application.
Specific embodiment
Below by the technical scheme in the embodiment of the application is clearly and completely described, it is clear that described implementation
Example is a part of the embodiment of the application, rather than whole embodiments.Based on the embodiment in the application, ordinary skill
Personnel's every other embodiment obtained without making creative work all should belong to the model of the application protection
It encloses.
The application provides a kind of learning effect detection method based on artificial intelligence, comprising the following steps:
First, select a knowledge point as knowledge point to be learned from weak knowledge point list, wherein weak knowledge point
Each of list knowledge point has respectively corresponded corresponding ability value.
In some embodiments, in weak knowledge point list, corresponding ability value highest is selected from non-selected knowledge point
A knowledge point as knowledge point to be learned.Wherein, the higher expression Grasping level of ability value is better, i.e., according to the grasp of student
Degree first selects the knowledge point that can most learn fastly.This easy first and difficult later mode, can guide student to promote by easy stages
The acceptance level of study course, student is preferable, and the process of study can also compare perception of accomplishment.Otherwise, if selection is slapped at the very start
The poor knowledge point of degree is held, then can be easier that student is allowed to generate sense of defeat, the acceptance level of student is poor, may will lose
Interest and confidence are gone, is unfavorable for that student is encouraged to persevere.
In some embodiments, student can be tested according to knowledge mapping to obtain weak knowledge point list,
In, knowledge mapping includes the knowledge point for being marked with preposition successor relationship.Knowledge mapping includes being marked with knowing for preposition successor relationship
Student's weakness knowledge point can be tested out by this test by knowing point, and which relevant knowledge point can analyze is due to
It will not just lead to the weakness knowledge point occur, can more accurately find the very crux that student can not learn, so as to suit the medicine to the illness
Prescribe medicine more targetedly guides student to learn.
Second, pushing learning resource relevant to knowledge point to be learned is learnt to student.Education resource can wrap
Include study document, audio, video, PPT, animation and relevant topic etc..And it is directed to each education resource, can be marked
It is marked with corresponding difficulty.It (can basis to the Grasping level of the knowledge point according to the type of education resource and difficulty and student
Ability value evaluates Grasping level) learning sequence can be reasonably combined, arranged in pairs or groups and be arranged to various education resources, thus shape
At personalized Learning Scheme.
In some embodiments, the quantity of topic can neatly be set according to Grasping level and/or learning time length
It sets, such as a knowledge point, 1,2,3,4,5,6,7,8,9 or 10 topic can be arranged, wherein according to a large amount of experiment
And analysis, the knowledge point moderate to a difficulty arrange 3 topics, Grasping level can be promoted larger in a relatively short period of time.
The sequence of topic can also correspondingly be adjusted according to difficulty and Grasping level, can be according to easy first and difficult later sequence arrangement
Topic can also be dynamically adjusted according to study course, for example students must be than very fast, then can the topic of promotion quickly
Purpose difficulty, and if students obtain slow, it can more slowly promote difficulty or keep identical difficulty is again to do one more
A bit.
Third treats the study situation of learning knowledge point according to student, provides corresponding detection topic and examines to student
It surveys.In some embodiments, detection topic can be determined according to the difficulty and quantity of the wrong topic in students'learning
Difficulty and quantity.
In some embodiments, the study video of system push knowledge point a and study topic, topic reach 3 topics, system meeting
Judge the knowledge point of this class study whether also in need.If the knowledge point for not needing to learn, system will judgemental knowledge
Point a in learning process whether wrong topic, if not provided, just terminating.If so, knowledge point a is just detected, push knowledge point a's
Detect topic, the difficulty and quantity that detect topic be according in students'learning wrong item difficulty and quantity determine
's.
4th, according to testing result, update ability value corresponding with knowledge point to be learned.More new knowledge in test process
The ability value of point can verify the ability value variation that student never attends the meeting in learning process.In some embodiments, student
It makes progress to the Grasping level of knowledge point, then the corresponding ability value in knowledge point is correspondingly improved according to progressive degree.
5th, according to updated ability value, mark knowledge point to be learned.In some embodiments, if it is updated
Ability value is up to standard, then is labeled as having grasped by knowledge point to be learned, and delete knowledge point to be learned from weak knowledge point list；
If updated ability value is below standard, by knowledge point to be learned labeled as not grasping, remain subsequent to be learnt or answered again
It practises, such as knowledge point addition to be learned need to be reviewed in knowledge point list.
After the detection for completing a knowledge point, it can also judge to selected knowledge point from weak knowledge point list
Whether quantity reaches knowledge point amount threshold, wherein if the quantity of selected knowledge point is not up to knowledge point amount threshold,
It selects next knowledge point as knowledge point to be learned from weak knowledge point list, and repeats to push step, step, more is provided
New step, markers step.If the quantity of selected knowledge point reaches knowledge point amount threshold, selected according to student whole
The study situation for selecting knowledge point provides corresponding detection topic to student and carries out stage detection, i.e., according to knowledge point amount threshold
Several knowledge points are put together and are detected again.In some embodiments, knowledge point amount threshold can for 2,3,4,5,6,
7,8,9,10.By largely testing and analyzing, using 3 or so knowledge points as one group, study and the effect consolidated are preferable.
In this way, can be after study by multiple knowledge point bundle tests.Because study has a short time memory, if
It just finishes a knowledge point just to test, short-term memory may make student answer questions topic, but be not necessarily and really grasp.And
System unifies test after mixing several knowledge points to student again, then can more effectively test whether student has really grasped this
A little knowledge points.Also, it is spaced a period of time re-test again after learning a knowledge point, can also be consolidated to student
Practice, so as to more effectively reinforce the Grasping level to knowledge point.
After completing a knowledge point or the detection in a stage, it can also judge whether deposit in weak knowledge point list
In non-selected knowledge point, wherein if there are non-selected knowledge points in weak knowledge point list, from weak knowledge point list
It selects next knowledge point as knowledge point to be learned, and repeats to push step, step is provided, updates step, markers step.Such as
Non-selected knowledge point is not present in fruit weakness knowledge point list, then terminates to detect.
In some embodiments, after the study for completing knowledge point a, if it find that the knowledge point b of study also in need,
System pushes the study video of knowledge point b again and study topic, topic reach 3 topics.System judges this class, and whether there are also need
The knowledge point to be learnt: if not provided, system will judgemental knowledge point a, b in learning process whether wrong topic, if not provided,
Just terminate.If so, just detection knowledge point a, b, system push knowledge point a one by one, the detection topic of b detects the difficulty of topic
And quantity be according in students'learning wrong item difficulty and quantity to determine, having detected is exactly to update the knowledge point
Ability value, if up to standard, just record knowledge point grasped, if not up to standard, just record knowledge point do not grasp.
If the knowledge point c of study also in need, system pushes the study video and study topic of knowledge point c, topic again
Reach 3 topics；System will judgemental knowledge point a, b, c in learning process whether wrong topic, if not provided, just terminating.If
Have, just detect knowledge point a, b, c, pushes knowledge point a one by one, the detection topic of b, c, the difficulty and quantity for detecting topic are bases
Wrong item difficulty and quantity in students'learning have detected the ability value for just updating the knowledge point come what is determined, if
It is up to standard, it just records knowledge point and has grasped, if not up to standard, just record knowledge point and do not grasp.
Then, system judges the knowledge point of this class study whether also in need: if not provided, just terminating course, such as
Fruit has knowledge point d, and the study video and study topic, topic for continuing to push knowledge point d reach 3 topics, and system judges this section
The knowledge point of class study whether also in need, if not then detection d finish three knowledge points one if there is continuing to learn
Group is detected, or is finished discontented 3 of the remaining knowledge point of this class and can also be detected, and is owned until finishing detect
Knowledge point, terminate course.
Method and system provided by the present application is illustrated in more detail with specific embodiment below.Following table
It is the knowledge mapping of knowledge point relevant to secondary radical, the preposition successor relationship between each knowledge point is marked.System according to
The map of subsequent relationship preposition in this way can make study very efficient using the method that preamble learns.
The weak knowledge point that system is determined by a student is c090201, c090205, c090303,
These knowledge points c090304, c090305 form weak knowledge point list A.
System is pushed to the knowledge point c090201 that student ability value can most be learned fastly according to student's situation.
System pushes the study video of knowledge point c090201 and study topic, topic reach 3 topics, and system judges this class
The knowledge point c090205 of study also in need.
System pushes the study video of knowledge point c090205 again and study topic, topic reach 3 topics；System judges this section
The knowledge point c090303 of class study also in need, study video and study topic of the system in push knowledge point c090303, topic
Mesh reaches 3 topics；System will judgemental knowledge point c090201, c090205, c090303 in learning process whether wrong topic, such as
Fruit does not have, and just terminates.If so, just detecting knowledge point c090201, c090205, c090303, knowledge point is pushed one by one
The detection topic of c090201, c090205, c090303, the difficulty and quantity for detecting topic are according in students'learning
Come what is determined, c090201 detects 15 star and inscribes for mistake item difficulty and quantity, c090205 one 2 star of detection, 15 star,
C090303 does not need to detect, and has detected the ability value for just updating the knowledge point, if up to standard, just record knowledge point and has grasped, such as
Fruit is not up to standard, just records knowledge point and does not grasp.
Then system judges this class there are also the knowledge point c090304 that learn of needs: continuing to push knowledge point
The study video and study topic of c090304, topic reach 3 topics, and system judges this class, and there are also the knowledge points that needs learn
C090305, the study video and study topic, topic for continuing to push knowledge point c090305 reach 3 topics, it is surplus to finish this class
2 remaining knowledge points are detected, mono- 5 stars topic of detection knowledge point c090304, and mono- 8 stars topic of detection c090305 has detected
With regard to updating the ability value of the knowledge point, if up to standard, just record knowledge point and grasped, if not up to standard, just record knowledge point not
It grasps, terminates course.
In some embodiments, above-mentioned various methods, module, device or system can be in one or more processing units
(for example, digital processing unit, analog processor, be designed to processing information digital circuit, be designed to processing letter
Analog circuit, state machine and/or other mechanisms for electronically handling information of breath) in be implemented.This or more
A processing unit may include the instruction in response to being electronically stored on electronic storage medium to execute some of method
Or one or more devices of all operations.The one or more processing unit may include by hardware, firmware and/or software
It is configured and is designed specifically for use in one or more devices of one or more operations of execution method.The above, only
The preferable specific embodiment of the application, but the protection scope of the application is not limited thereto, it is any to be familiar with the art
Technical staff is subject to equivalent replacement within the technical scope of the present application, according to the technical solution of the application and its inventive concept
Or change, should all it cover within the scope of protection of this application.
Presently filed embodiment can carry out in hardware, firmware, software or its various combination.It is also used as storing
On a machine-readable medium and the instruction that one or more processing units read and execute can be used to realize the application.?
In one embodiment, machine readable media may include readable in machine (for example, computing device) for storing and/or transmitting
The various mechanisms of the information of form.For example, machine readable storage medium may include read-only memory, random access memory,
Magnetic disk storage medium, optical storage media, flash memory device and other media for storing information, and it is machine readable
Transmission medium may include the transmitting signal (including carrier wave, infrared signal, digital signal) of diversified forms and be used for transmission letter
Other media of breath.Although in terms of the particular exemplary for executing certain movements and the angle of embodiment can be in above disclosure
It describes firmware, software, routine or instruction in content, but will be apparent that, this kind of description is merely for facilitating purpose and this kind of dynamic
Make actually by computing device, processing unit, processor, controller or other dresses for executing firmware, software, routine or instruction
It sets or machine generates.
This specification uses examples to disclose the application, and one or more of examples are described or are illustrated in explanation
Among book and its attached drawing.Each example is provided to explanation the application and provides, rather than in order to limit the application.In fact,
It is obvious to the skilled person that can be to this Shen in the case where not departing from scope of the present application or spirit
Row various modifications and variations that come in.For example, the diagram of a part as one embodiment or description feature can with it is another
One embodiment is used together, to obtain further embodiment.Therefore, it is intended that the application and covers and wanted in appended right
Seek the modifications and variations carried out in the range of book and its equivalent.
Claims (10)
1. a kind of learning effect detection method based on artificial intelligence, which comprises the following steps:
Select a knowledge point as knowledge point to be learned from weak knowledge point list, wherein the weakness knowledge point list
Each of knowledge point respectively corresponded corresponding ability value；
Pushing learning resource relevant to the knowledge point to be learned is learnt to student；
According to student to the study situation of the knowledge point to be learned, corresponding detection topic is provided and is detected to student；
According to testing result, ability value corresponding with the knowledge point to be learned is updated；And
According to updated ability value, the knowledge point to be learned is marked.
2. learning effect detection method according to claim 1, which is characterized in that further comprise:
Judge whether the quantity that selected knowledge point from the weak knowledge point list reaches knowledge point amount threshold, wherein
If the quantity of the selected knowledge point is not up to the knowledge point amount threshold, selected from the weak knowledge point list
Next knowledge point is selected as knowledge point to be learned, and repeat the push step, the offer step, the update step,
The markers step.
3. learning effect detection method according to any one of the preceding claims, which is characterized in that further comprise:
Judge whether the quantity that selected knowledge point from the weak knowledge point list reaches knowledge point amount threshold, wherein
If the quantity of the selected knowledge point reaches the knowledge point amount threshold, all described selected are known according to student
The study situation for knowing point provides corresponding detection topic to student and carries out stage detection.
4. learning effect detection method according to any one of the preceding claims, it is characterised in that:
The knowledge point amount threshold is 2,3,4 or 5.
5. learning effect detection method according to any one of the preceding claims, which is characterized in that further comprise:
Judge in the weak knowledge point list with the presence or absence of non-selected knowledge point, wherein if the weakness knowledge point list
In there are non-selected knowledge points, then select next knowledge point as knowledge point to be learned from the weak knowledge point list,
And repeat the push step, the offer step, the update step, the markers step.
6. learning effect detection method according to any one of the preceding claims, which is characterized in that further comprise:
Judge in the weak knowledge point list with the presence or absence of non-selected knowledge point, wherein if the weakness knowledge point list
In be not present non-selected knowledge point, then terminate to detect.
7. learning effect detection method according to any one of the preceding claims, it is characterised in that:
Student is tested according to knowledge mapping to obtain the weak knowledge point list, wherein the knowledge mapping includes
It is marked with the knowledge point of preposition successor relationship.
8. learning effect detection method according to any one of the preceding claims, which is characterized in that the selection step
Further comprise:
In the weak knowledge point list, select from non-selected knowledge point the correspondence highest knowledge point of ability value as
The knowledge point to be learned.
9. learning effect detection method according to any one of the preceding claims, which is characterized in that the offer step
Further comprise:
The difficulty and quantity of the detection topic are determined according to the difficulty of the wrong topic in students'learning and quantity.
10. learning effect detection method according to any one of the preceding claims, which is characterized in that the markers step
Further comprise:
If updated ability value is up to standard, by the knowledge point to be learned labeled as having grasped, and from the weak knowledge
The knowledge point to be learned is deleted in point list.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611892.1A CN110288270A (en) | 2019-07-08 | 2019-07-08 | Learning effect detection method based on artificial intelligence |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910611892.1A CN110288270A (en) | 2019-07-08 | 2019-07-08 | Learning effect detection method based on artificial intelligence |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN110288270A true CN110288270A (en) | 2019-09-27 |
Family
ID=68021305
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910611892.1A Pending CN110288270A (en) | 2019-07-08 | 2019-07-08 | Learning effect detection method based on artificial intelligence |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110288270A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081106A (en) * | 2019-12-13 | 2020-04-28 | 北京爱论答科技有限公司 | Job pushing method, system, equipment and storage medium |
| CN113906485A (en) * | 2020-04-30 | 2022-01-07 | 乐天集团股份有限公司 | Control device, system and method |
| CN117672027A (en) * | 2024-02-01 | 2024-03-08 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN118134710A (en) * | 2024-03-25 | 2024-06-04 | 山东畅想云教育科技有限公司 | Autonomous learning system based on digital teaching materials |
Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886779A (en) * | 2012-12-20 | 2014-06-25 | 北大方正集团有限公司 | Method and system for processing data |
| CN108335555A (en) * | 2018-01-26 | 2018-07-27 | 广州大学 | A kind of knowledge point system teaching method |
| CN108520020A (en) * | 2018-03-22 | 2018-09-11 | 东华大学 | A kind of real-time learning data analysis system based on SaaS |
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
-
2019
- 2019-07-08 CN CN201910611892.1A patent/CN110288270A/en active Pending
Patent Citations (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN103886779A (en) * | 2012-12-20 | 2014-06-25 | 北大方正集团有限公司 | Method and system for processing data |
| CN109903617A (en) * | 2017-12-11 | 2019-06-18 | 北京三好互动教育科技有限公司 | Individualized exercise method and system |
| CN108335555A (en) * | 2018-01-26 | 2018-07-27 | 广州大学 | A kind of knowledge point system teaching method |
| CN108520020A (en) * | 2018-03-22 | 2018-09-11 | 东华大学 | A kind of real-time learning data analysis system based on SaaS |
Cited By (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN111081106A (en) * | 2019-12-13 | 2020-04-28 | 北京爱论答科技有限公司 | Job pushing method, system, equipment and storage medium |
| CN113906485A (en) * | 2020-04-30 | 2022-01-07 | 乐天集团股份有限公司 | Control device, system and method |
| CN117672027A (en) * | 2024-02-01 | 2024-03-08 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN117672027B (en) * | 2024-02-01 | 2024-04-30 | 青岛培诺教育科技股份有限公司 | VR teaching method, device, equipment and medium |
| CN118134710A (en) * | 2024-03-25 | 2024-06-04 | 山东畅想云教育科技有限公司 | Autonomous learning system based on digital teaching materials |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN110288270A (en) | Learning effect detection method based on artificial intelligence | |
| CN109903617B (en) | Personalized exercise method and system | |
| Martinková et al. | Checking equity: Why differential item functioning analysis should be a routine part of developing conceptual assessments | |
| CN107544973B (en) | Method and device for processing data | |
| CN110246072B (en) | Review method executed by machine equipment | |
| Zingaro et al. | Identifying student difficulties with basic data structures | |
| Corney et al. | 'Explain in plain English'questions revisited: Data structures problems | |
| CN102074135A (en) | Method and device for building question bank | |
| CN110009956A (en) | English Grammar adaptive learning method and learning device | |
| US10643489B2 (en) | Constructed response scoring mechanism | |
| CN113657723A (en) | Knowledge point mastering condition diagnosis method, test question recommendation method and device | |
| CN109615009A (en) | Learning content recommendation method and electronic equipment | |
| CN108831229A (en) | A kind of Chinese automatic grading method | |
| CN112988844A (en) | Knowledge concept representation learning method based on student exercise sequence | |
| Magnusson et al. | How Should Learning Be Structured in Inquiry-based Science Instruction?:: Investigating the Interplay of 1st-and 2nd-hand Investigations | |
| Gagnon et al. | Filtering non-relevant short answers in peer learning applications. | |
| CN108629716A (en) | Accurate methods of review and education robot system based on big data and artificial intelligence | |
| Stöhr | Anywhere and anytime? An analysis of the use of mobile devices in MOOCs | |
| Chi et al. | To elicit or to tell: Does it matter? | |
| CN111127271A (en) | Teaching method and system for studying situation analysis | |
| CN112860983B (en) | Method, system, equipment and readable storage medium for pushing learning content | |
| Christman et al. | Exploring the CLASS with item response theory | |
| Singh et al. | Enhancing the effectiveness of educational hypermedia: A cognitive load approach | |
| Caballero | Evaluating and extending a novel course reform of introductory mechanics | |
| CN110349062B (en) | Artificial intelligence based pre-testing method |
Legal Events
| Date | Code | Title | Description |
|---|---|---|---|
| PB01 | Publication | ||
| PB01 | Publication | ||
| SE01 | Entry into force of request for substantive examination | ||
| SE01 | Entry into force of request for substantive examination | ||
| CB02 | Change of applicant information | ||
| CB02 | Change of applicant information |
Address after: 10th Floor, Building B7, Huaxin Tiandi, 188 Yizhou Road, Xuhui District, Shanghai, 2003 Applicant after: Shanghai squirrel classroom Artificial Intelligence Technology Co., Ltd Address before: 10th Floor, Building B7, Huaxin Tiandi, 188 Yizhou Road, Xuhui District, Shanghai, 2003 Applicant before: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. |
|
| RJ01 | Rejection of invention patent application after publication | ||
| RJ01 | Rejection of invention patent application after publication |
Application publication date: 20190927 |