CN108765227A - Study portrait method based on big data and artificial intelligence and robot system - Google Patents
Study portrait method based on big data and artificial intelligence and robot system Download PDFInfo
- Publication number
- CN108765227A CN108765227A CN201810630020.5A CN201810630020A CN108765227A CN 108765227 A CN108765227 A CN 108765227A CN 201810630020 A CN201810630020 A CN 201810630020A CN 108765227 A CN108765227 A CN 108765227A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- knowledge
- portrait
- study
- student
- 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
- 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
- G09B5/00—Electrically-operated educational appliances
- G09B5/02—Electrically-operated educational appliances with visual presentation of the material to be studied, e.g. using film strip
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Tourism & Hospitality (AREA)
- General Physics & Mathematics (AREA)
- Theoretical Computer Science (AREA)
- Strategic Management (AREA)
- Physics & Mathematics (AREA)
- General Health & Medical Sciences (AREA)
- Economics (AREA)
- Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
Study portrait method based on big data and artificial intelligence and robot system, including：Each students' work data are counted in preset time range to be weighted averagely the corresponding each operation accuracy in each knowledge point in the first knowledge point set, obtain total accuracy, using total accuracy as the Grasping level value of the corresponding knowledge point label in each knowledge point described in each student's portrait, study portrait is carried out to student by operation big data.The above method and system carry out study portrait by operation big data to student, to accurately reflect grasp situation of the different students to different knowledge points by learning portrait come objective, to improve the objectivity and accuracy of study portrait, for different students and different knowledge points, it realizes individualized learning and review, precision study and reviews, the efficiency for improving study and reviewing.
Description
Technical field
The present invention relates to information technology fields, more particularly to a kind of study portrait side based on big data and artificial intelligence
Method and robot system.
Background technology
The evaluation of existing knowledge point Grasping level is that student scores to teacher when the end of term and formed.
In realizing process of the present invention, inventor has found that at least there are the following problems in the prior art：It is old in the prior art
Teacher reviews to student to be carried out according to knowledge point in teaching programme, and the review of student oneself is also to be clicked through according to examination knowledge
It is capable, it thus can not be in conjunction with student to the grasp situation of each knowledge point, so that knowledge point that student has grasped and not
The knowledge point of grasp is reviewed with being all averaged strength, and so as to cause reviewing, effect is poor.Meanwhile the review of teacher or student are unified
, only it can be divided into 2 kinds of fixed types, basic review, general review.If basic review, only most important minority can be reviewed
Many knowledge points are all missed in knowledge point, so that review is not comprehensive, the knowledge point for having students bad can by leakage review
It can property.And general review is not only laborious but also time-consuming, also student's more times can be spent in review, the most key is
Wherein many knowledge point students have grasped, and review is extra.
Therefore, the existing technology needs to be improved and developed.
Invention content
Based on this, it is necessary to for the defect or deficiency for learning portrait in the prior art, provide based on big data with it is artificial
The study portrait method and robot system of intelligence, to solve the disadvantage that the subjectivity that study is drawn a portrait is strong, accuracy rate is low.
In a first aspect, a kind of study portrait method is provided, the method includes：
Accuracy calculates step, counts each students' work data in preset time range in the first knowledge point set
The corresponding each operation accuracy in each knowledge point is weighted average, obtains total accuracy；
Label assignment procedure, total accuracy is corresponding as each knowledge point described in each student's portrait
The Grasping level value of knowledge point label.
Preferably, further include before the accuracy calculates step：
Data step is obtained, obtains operation big data, the operation big data includes each work data of each student；
Knowledge point step is obtained, all knowledge points that study includes are obtained, as the first knowledge point set.
Preferably, further include after the label assignment procedure：
Receive query steps, obtain student to be checked and knowledge point set to be reviewed, by the knowledge to be reviewed
Point set is as the second knowledge point set；
Threshold value obtaining step, from obtaining the corresponding grasp journey in each knowledge point in the second knowledge point set in working knowledge library
The threshold value of degree；
Portrait step is obtained, the study portrait of the student to be checked is searched for and obtained in drawing a portrait knowledge base from study,
The corresponding knowledge point in each knowledge point for belonging to the second knowledge point set is obtained from the study portrait of the student to be checked
The Grasping level value of label；
Knowledge point selects step, judges whether the Grasping level value of the corresponding knowledge point label in each knowledge point is more than
Or the threshold value of knowledge point Grasping level corresponding equal to each knowledge point described in working knowledge library：It is then each to know described
Know point and third knowledge point set is added；It is no, then the 4th knowledge point set is added in each knowledge point；
The knowledge point set that the 4th knowledge point set is reviewed as needs is recommended use by knowledge point recommendation step
Family.
Preferably, include after use portrait step：
Collective's recommendation step obtains multiple students to be checked and same knowledge point set to be reviewed, to the multiple
Each student and the knowledge point set to be reviewed in student to be checked execute the knowledge point and select step, obtain institute
The 4th set for stating each student will count the occurrence number of different knowledge points in multiple four set, according to number from
M knowledge point is arrived before small selection greatly as needing the knowledge point set reviewed to recommend user, wherein M is predetermined number.
Preferably, the work data include each operation, the answer accuracy of the operation, the operation topic be related to
All knowledge points, operation complete time.
Second aspect provides a kind of study portrait system, the system comprises：
Accuracy computing module, for counting each students' work data in preset time range to the first knowledge point set
The corresponding each operation accuracy in each knowledge point is weighted average in conjunction, obtains total accuracy；
Label assignment module, for using total accuracy as each knowledge point pair described in each student's portrait
The Grasping level value for the knowledge point label answered.
Preferably, the system also includes：
Data module is obtained, for obtaining operation big data, the operation big data includes each operation of each student
Data；
Knowledge point module is obtained, all knowledge points for including for obtaining study, as the first knowledge point set.
Preferably, the system also includes：
Receive enquiry module, it, will be described to be reviewed for obtaining student to be checked and knowledge point set to be reviewed
Knowledge point set is as the second knowledge point set；
Threshold value acquisition module, for from obtaining the corresponding palm in each knowledge point in the second knowledge point set in working knowledge library
Hold the threshold value of degree；
Portrait module is obtained, the study picture for searching for and obtaining the student to be checked in drawing a portrait knowledge base from study
Picture obtains the corresponding knowledge in each knowledge point for belonging to the second knowledge point set from the study portrait of the student to be checked
The Grasping level value of point label；
Knowledge point selection module, for judge the corresponding knowledge point label in each knowledge point Grasping level value whether
The threshold value of knowledge point Grasping level corresponding more than or equal to each knowledge point described in working knowledge library：Be, then it will be described every
Third knowledge point set is added in one knowledge point；It is no, then the 4th knowledge point set is added in each knowledge point；
Knowledge point recommending module, the knowledge point set for reviewing the 4th knowledge point set as needs are recommended
User.
Preferably, the system also includes：
Collective's recommending module, for obtaining multiple students to be checked and same knowledge point set to be reviewed, to described
Each student and the knowledge point set to be reviewed in multiple students to be checked execute the knowledge point selection module, obtain
To the 4th set of each student, the occurrence number of different knowledge points in multiple 4th set will be counted, according to secondary
The knowledge point set that M knowledge point is reviewed as needs before number is chosen from big to small recommends user, wherein M is predetermined number.
The third aspect provides a kind of study portrait robot system, second party is each configured in the robot system
Study portrait system described in face.
The embodiment of the present invention has the following advantages that and advantageous effect：
The study portrait method and robot system based on big data and artificial intelligence that the embodiment of the present invention provides, system
Count each students' work data in preset time range to the corresponding each operation in each knowledge point in the first knowledge point set just
True rate is weighted averagely, obtains total accuracy, is known using total accuracy as each described in each student's portrait
The Grasping level value for knowing the corresponding knowledge point label of point, study portrait is carried out by operation big data to student, is learned to pass through
Practise portrait come it is objective accurately reflect grasp situation of the different students to different knowledge points, to improve study portrait objectivity
And accuracy is realized individualized learning and review, precision study and is reviewed, improve for different students and different knowledge points
Study and the efficiency reviewed.
Description of the drawings
Fig. 1 is the flow chart for the study portrait method that one embodiment of the present of invention provides；
Fig. 2 is the flow chart for the study portrait method that a preferred embodiment of the present invention provides；
Fig. 3 is the functional block diagram for the study portrait system that one embodiment of the present of invention provides；
Fig. 4 is the functional block diagram for the study portrait system that a preferred embodiment of the present invention provides.
Specific implementation mode
With reference to embodiment of the present invention, technical solution in the embodiment of the present invention is described in detail.
The embodiment of the present invention provides study portrait method and robot system based on big data and artificial intelligence.Big number
Include acquisition, the treatment technology of big data according to technology, artificial intelligence technology includes identification technology, study Portrait brand technology.
(1) the study portrait method based on big data and artificial intelligence
The method as shown in Figure 1, study that one embodiment provides is drawn a portrait, includes the following steps：
Accuracy calculates step S300, counts each students' work data in preset time range to the first knowledge point set
The corresponding each operation accuracy in each knowledge point is weighted average in conjunction, obtains total accuracy.
Label assignment procedure S400, using total accuracy as each knowledge point pair described in each student's portrait
The Grasping level value for the knowledge point label answered.Wherein, study portrait is a kind of user's portrait, and user's portrait is the core of artificial intelligence
One of heart technology.
The study portrait method that the embodiment provides grasps the study portrait of Kernel-based methods big data as knowledge point
The standard of the evaluation of degree, and by it is described study portrait for knowledge point Grasping level evaluation, to reduce or broken away from
The subjectivity of the evaluation of artificial judging panel, and then provide foundation targetedly precisely to review.
1, accuracy calculates step
In a preferred embodiment, accuracy calculating step S300 includes：
S301 obtains each student (such as Zhang San, 2018002 from big data repository；Etc.) all operation numbers
According to (for example, Zhang San, 2018002, operation 1, knowledge point 1,20%, knowledge point 2,80%, 90%；Zhang San, 2018002, operation 2,
Knowledge point 1,10%, knowledge point 3,90%, 20%；Etc.)；A study portrait is initialized for each student.
Whether S302 judges the operation deadline in each work data of each student in preset time range
It is interior (such as nearest 3 months, preset time range refer to reviewing be directed to recently how long in the knowledge that is learnt answer
It practises.Such as the review in a term, then it is this term to review time range, this term can be a nearest term,
It can be some pervious term, such as review the big course learned for the moment when preparing for the postgraduate qualifying examination, then review time range at this time
It is exactly big one that term.Such as the review in a week, then it is this week to review time range)：It is, then described in addition
The first operation set of each student.
S303 obtains each knowledge point in the first knowledge point set, and is in each student of each knowledge point
Practise portrait one knowledge point label of initialization.
S304 is obtained from the first operation set of each student containing each knowledge point in the first knowledge point set
(for example, knowledge point 1) work data (for example, Zhang San, 2018002, operation 1, knowledge point 1,20%, knowledge point 2,80%,
90%；Zhang San, 2018002, operation 2, knowledge point 1,10%, knowledge point 3,90%, 20%；Etc.) each student is added
Each knowledge point the second operation set.
S305 obtains each operation number from the second operation set of each knowledge point of each student
According to the weight shared by middle operation accuracy, each knowledge point (for example, knowledge point 1).
S306, to operation accuracy (for example, 90%, 20%) in each work data with each knowledge point
Weight (for example, 20%, 10%) shared by (for example, knowledge point 1) be weight be weighted it is average ((90% × 20%+20% ×
10%)/(20%+10%)), obtained value is as each student to the Grasping level of each knowledge point.It is not preferred
Ground is directly averaging ((90%+20%)/2) to operation accuracy (for example, 90%, 20%) in each work data, obtains
The value arrived is as each student to the Grasping level of each knowledge point.Preferably, further consider task difficulty
Factor, the corresponding accuracy of the corresponding each operation in each knowledge point are carried out by weights of weight shared by the difficulty of operation and knowledge point
Weighted average (such as different work is different to the investigation difficulty of the same knowledge point, shared weight is not in operation for the knowledge point
Together), obtain total accuracy (as the Grasping level to each knowledge point).
2, label assignment procedure
In a preferred embodiment, the label assignment procedure S400 includes：
S401 draws total accuracy as each student (i.e. to the Grasping level of each knowledge point)
The Grasping level value of the corresponding knowledge point label in each knowledge point as described in.If described from each student each is known
Second operation set for knowing point is combined into sky, the corresponding knowledge point label in each knowledge point described in each student's portrait
Grasping level value is set as 0.
The portrait is stored in portrait knowledge base by S402.
3, before accuracy calculating step
In a preferred embodiment, further include before the accuracy calculates step S300：
Data step S100 is obtained, obtains operation big data, the operation big data includes each operation of each student
Data.
Knowledge point step S200 is obtained, all knowledge points that study includes are obtained, as the first knowledge point set；It is preferred that
Ground, all knowledge points that study includes can be preset knowledge point sets, can also be the knowledge point set that user specifies,
Also knowledge point can be obtained by obtaining user's input, these knowledge can also be obtained from learning knowledge library or syllabus
Point can also be the knowledge point of a certain teaching unit, can also be the knowledge point of a certain period teaching.
The step of before the accuracy calculating step S300, is counted by operation big data, obtains study picture
Picture, so that study portrait can objectively reflect grasp situation of the student to each knowledge point, to be knowledge point
It targetedly precisely reviews and lays the first stone.
(1) in a further preferred embodiment, obtaining data step S100 includes：
S101, it includes name, number (such as Zhang San, 2018002 to obtain each student；Li Si, 2018003；King five,
2018005；Etc.), deposit big data repository (such as Hbase).
S102, the work data for obtaining each operation of each student include student name, student's number, job content,
The answer accuracy of weight, the operation shared by corresponding all knowledge points and each knowledge point, the operation deadline (for example,
Zhang San, 2018002, operation 1, knowledge point 1,20%, knowledge point 2,80%, 90%；Zhang San, 2018002, operation 2, knowledge point 1,
10%, knowledge point 3,90%, 20%；Etc.), it is stored in big data repository；Preferably, institute is also added in the difficulty of the operation
State work data.
(2) in a further preferred embodiment, obtaining knowledge point step S200 includes：
S201 obtains all knowledge points for learning to include (for example, knowledge point 1；Knowledge point 2；Etc.), know as first
Know point set.
4, after label assignment procedure
As shown in Fig. 2, in a preferred embodiment, further including after the label assignment procedure S400：
Receive query steps S500, obtains student to be checked and knowledge point set to be reviewed, it will be described to be reviewed
Knowledge point set is as the second knowledge point set；Preferably, the knowledge point set to be reviewed can be to be reviewed specifies
Knowledge point set can also be all knowledge points for waiting for general review, can also be all knowledge points for waiting for reviewing substantially.It is preferred that
Ground is reviewed substantially excessively when, and when into the general review stage, the second knowledge point set refers to belonging to full knowledge point
The each knowledge point for gathering but being not belonging to basic knowledge point set, so as to ensure to exclude comprehensively under the premise of reviewing substantially
Unnecessary review in review.
Threshold value obtaining step S600, from obtaining the corresponding palm in each knowledge point in the second knowledge point set in working knowledge library
Hold the threshold value of degree.Preferably, the threshold value of the Grasping level of a knowledge point refers to what the knowledge point needs to be grasped
Degree, such as it should be understood that knowledge point Grasping level threshold value it is relatively low, and the Grasping level threshold value of the knowledge point needed to be grasped
It is higher, need the Grasping level higher for the knowledge point skillfully grasped.Preferably, between the threshold value of the Grasping level is 0 to 1
Number shows that the knowledge point is not required to master when being 0, shows that the knowledge point needs absolutely to grasp when being 1.
Portrait step S700 is obtained, searches for and obtain the study picture of the student to be checked in drawing a portrait knowledge base from study
Picture obtains the corresponding knowledge in each knowledge point for belonging to the second knowledge point set from the study portrait of the student to be checked
The Grasping level value of point label.
Knowledge point selects step S800, judges the Grasping level value of the corresponding knowledge point label in each knowledge point (such as
The corresponding knowledge point label in each knowledge point described in fruit is not present, and illustrates that the student to be checked did not learn the knowledge point,
So being defaulted as 0) whether being greater than or equal to the threshold of the corresponding knowledge point Grasping level in each knowledge point described in working knowledge library
Value：It is that third knowledge point set then is added in each knowledge point, and (knowledge point is without multiple for the student to be checked
It practises)；It is no, then the 4th knowledge point set (for the student to be checked review knowledge point is added in each knowledge point
It needs to review).
Knowledge point recommendation step S900 recommends the knowledge point set that the 4th knowledge point set is reviewed as needs
User (user can be teacher, can also be student).Preferably, by each knowledge point pair in the 4th knowledge point set
The ratio of the Grasping level threshold value and Grasping level value of the knowledge point label answered, what the needs as each knowledge point were reviewed
Intensity.It is appreciated that each knowledge point need the intensity reviewed it is bigger illustrate to need flower more great strength go to review it is described every
One knowledge point.
Preferably, further include after knowledge point recommendation step S900：
Collective's recommendation step obtains multiple students to be checked and same knowledge point set to be reviewed (for example, to teacher
All students in taught course review), in the multiple student to be checked each student and it is described wait for it is multiple
The knowledge point set of habit executes the knowledge point and selects step, obtains the 4th set of each student, will count multiple institutes
The occurrence number for stating different knowledge points in the 4th set, M knowledge point, which is used as, before being chosen from big to small according to number needs to review
Knowledge point set recommend user (such as the multiple student where course teacher), wherein M is predetermined number.
The step of after the label assignment procedure S400, from being searched in the portrait of teaching efficiency by belonging to second
The Grasping level value of the corresponding knowledge point label in each knowledge point of knowledge point set, to obtain the student to be checked to institute
State the Grasping level of each knowledge point so as to the evaluation of knowledge point Grasping level be based on study portrait carry out, and
Study portrait is again carried out based on operation big data, so that the evaluation energy of the knowledge point Grasping level based on the present embodiment
It is enough objectively to reflect that grasp situation of the student to each knowledge point, different students are different to the grasp situation of different knowledge points, all
Which can objectively be reflected by learning portrait and knowledge point label, to for knowledge point, every reviewed for each student
How the review intensity of a difference knowledge point and time distribute offer objective basis, to realize the review of personalized, precision,
So that reviewing more intelligent.
(1) in a further preferred embodiment, receiving query steps S500 includes：
S501, it includes name, number (such as Zhang San, 2018002) to obtain student to be checked.
S502 obtains knowledge point set to be reviewed (for example, knowledge point 1；Knowledge point 2；Etc.), as the second knowledge point
Set.
(2) in a further preferred embodiment, threshold value obtaining step S600 includes：
Working knowledge is added in S601, the threshold value for obtaining the corresponding Grasping level in each knowledge point in the first knowledge point set
Library.
S602, from each knowledge point is obtained in the second knowledge point set in working knowledge library (for example, knowledge point 1；Knowledge point
2；Etc.) threshold value of corresponding Grasping level is (for example, knowledge point 1：60%；Knowledge point 2：70%；Etc.).
(3) in a further preferred embodiment, obtaining portrait step S700 includes：
S701 is searched in drawing a portrait knowledge base from study and is obtained the student's to be checked (such as Zhang San, 2018002)
Study portrait.
S702 is obtained from the study of the student to be checked portrait and is belonged to the second knowledge point set (for example, knowledge point
1；Knowledge point 2；Etc.) the corresponding knowledge point label in each knowledge point；If the corresponding knowledge point mark in each knowledge point
Label are not present, then increase the corresponding knowledge point label in each knowledge point in the study of the student to be checked portrait,
And the Grasping level value of the knowledge point label is set as 0.
S703 obtains the Grasping level value of the corresponding knowledge point label in each knowledge point (for example, knowledge point 1：
66%；Knowledge point 2：32%；Etc.).
(4) in a further preferred embodiment, knowledge point selects step S800：
S801 judges each knowledge point (for example, knowledge point 1；Knowledge point 2；Etc.) corresponding knowledge point label
Grasping level value is (for example, knowledge point 1：66%；Knowledge point 2：32%；Etc.) whether be greater than or equal to described in working knowledge library
The threshold value of the corresponding knowledge point Grasping level in each knowledge point is (for example, knowledge point 1：60%；Knowledge point 2：70%；Etc.)：It is,
Third knowledge point set (for the student to be checked knowledge then is added in each knowledge point (for example, knowledge point 1)
Point is without reviewing)；It is no, then it is (to be checked to this 4th knowledge point set to be added in each knowledge point (for example, knowledge point 2)
Student for the review knowledge point need to review).
(5) in a further preferred embodiment, knowledge point recommendation step S900：
S901, by the 4th knowledge point set (for example, knowledge point 1；Knowledge point 3) as the knowledge point set for needing to review
User is recommended in conjunction (user can be teacher, can also be student).
S902, by the Grasping level threshold value of the corresponding knowledge point label in each knowledge point in the 4th knowledge point set
(for example, knowledge point 2：70%；Knowledge point 3：80%) with Grasping level value (for example, knowledge point 2：32%；Knowledge point 3：50%)
Ratio (for example, knowledge point 2：70%/32%=2.1875；Knowledge point 3：80%/50%=1.6) it is used as each knowledge
The intensity that the needs of point are reviewed can also be used as the weight for the review time for needing to spend.It is appreciated that each knowledge point needs
The intensity to be reviewed is bigger to illustrate that flower more great strength is needed to go to review each knowledge point (for example, knowledge point 2 and knowledge point 3
Comparatively, the intensity bigger that the needs of knowledge point 2 are reviewed, so flower more great strength is needed to go to review knowledge point 2).
4, operation big data
In a preferred embodiment, the work data includes the answer accuracy (example of each operation, the operation
Right a few percent is such as done, for the score of operation topic divided by the total score of operation topic), all knowing of being related to of operation topic
Know point, the time that operation is completed.Preferably, the work data further includes in all knowledge points that the operation topic is related to
The corresponding weight in each knowledge point.Preferably, the work data further includes the difficulty of the operation topic.
(2) the study portrait system based on operation big data
System, including following module as shown in figure 3, a kind of study that one embodiment provides is drawn a portrait：
Accuracy computing module 300 counts each students' work data in preset time range to the first knowledge point set
The corresponding each operation accuracy in each knowledge point is weighted average in conjunction, obtains total accuracy.
Label assignment module S400, using total accuracy as each knowledge point pair described in each student's portrait
The Grasping level value for the knowledge point label answered.
The study portrait system has advantageous effect same as study portrait method noted earlier, no longer superfluous herein
It states.
1, accuracy computing module
In a preferred embodiment, the accuracy computing module 300 include unit 301,302,303,304,
305,306.Unit 301,302,303,304,305,306 respectively with step S301 described in preferred embodiment noted earlier,
S302, S303, S304, S305, S306 are corresponded, and it is no longer repeated herein.Unit 301,302,303,304,305,306
It is respectively used to execute described S301, S302, S303, S304, S305, S306.
The accuracy computing module 300 has advantageous effect same as accuracy noted earlier calculating step S300,
Details are not described herein.
2, label assignment module
In a preferred embodiment, the label assignment module 400 includes unit 401,402.Unit 401,402
It is corresponded respectively with step S401, S402 described in preferred embodiment noted earlier, it is no longer repeated herein.Unit
401, it 402 is respectively used to execute described S401, S402.
The label assignment module 400 has advantageous effect same as label assignment procedure S400 noted earlier, herein
It repeats no more.
3, before accuracy computing module
In a preferred embodiment, further include before the accuracy computing module 300：
Data module 100 is obtained, obtains operation big data, the operation big data includes each operation number of each student
According to；
Knowledge point module 200 is obtained, all knowledge points that study includes are obtained, as the first knowledge point set；It is preferred that
Ground, all knowledge points that study includes can be preset knowledge point sets, can also be the knowledge point set that user specifies,
Also knowledge point can be obtained by obtaining user's input, these knowledge can also be obtained from learning knowledge library or syllabus
Point can also be the knowledge point of a certain teaching unit, can also be the knowledge point of a certain period teaching.
Module before the accuracy computing module 300 has calculate step S300 with accuracy noted earlier before
The same advantageous effect of step, details are not described herein.
(1) in a further preferred embodiment, it includes unit 101,102 to obtain data module 100.Unit 101,
102 correspond with step S101, S102 described in preferred embodiment noted earlier respectively, and it is no longer repeated herein.It is single
Member 101,102 is respectively used to execute described S101, S102.
(2) in a further preferred embodiment, it includes unit 201 to obtain knowledge point module 200.Unit 201 divides
It is not corresponded with step S201 described in preferred embodiment noted earlier, it is no longer repeated herein.Unit 201 is used respectively
In the execution S201.
4, after label assignment module
As shown in figure 4, in a preferred embodiment, further including after the label assignment module 400：
Receive enquiry module 500, obtains student to be checked and knowledge point set to be reviewed, described to be reviewed is known
Point set is known as the second knowledge point set；Preferably, the knowledge point set to be reviewed can be reviewed specified be known
Know point set, can also be all knowledge points for waiting for general review, can also be all knowledge points for waiting for reviewing substantially.It is preferred that
Ground is reviewed substantially excessively when, and when into the general review stage, the second knowledge point set refers to belonging to full knowledge point
The each knowledge point for gathering but being not belonging to basic knowledge point set, so as to ensure to exclude comprehensively under the premise of reviewing substantially
Unnecessary review in review.
Threshold value acquisition module 600, from obtaining the corresponding palm in each knowledge point in the second knowledge point set in working knowledge library
Hold the threshold value of degree.Preferably, the threshold value of the Grasping level of a knowledge point refers to what the knowledge point needs to be grasped
Degree, such as it should be understood that knowledge point Grasping level threshold value it is relatively low, and the Grasping level threshold value of the knowledge point needed to be grasped
It is higher, need the Grasping level higher for the knowledge point skillfully grasped.Preferably, between the threshold value of the Grasping level is 0 to 1
Number shows that the knowledge point is not required to master when being 0, shows that the knowledge point needs absolutely to grasp when being 1.
Portrait module 700 is obtained, searches for and obtain the study picture of the student to be checked in drawing a portrait knowledge base from study
Picture obtains the corresponding knowledge in each knowledge point for belonging to the second knowledge point set from the study portrait of the student to be checked
The Grasping level value of point label；
Knowledge point selection module 800, judge the corresponding knowledge point label in each knowledge point Grasping level value (if
The corresponding knowledge point label in each knowledge point is not present, and illustrates that the student to be checked did not learn the knowledge point, institute
To be defaulted as 0) whether being greater than or equal to the threshold value of the corresponding knowledge point Grasping level in each knowledge point described in working knowledge library：
It is that third knowledge point set then is added in each knowledge point, and (knowledge point is without multiple for the student to be checked
It practises)；It is no, then the 4th knowledge point set (for the student to be checked review knowledge point is added in each knowledge point
It needs to review).
Knowledge point recommending module 900 recommends the knowledge point set that the 4th knowledge point set is reviewed as needs
User (user can be teacher, can also be student).Preferably, by each knowledge point pair in the 4th knowledge point set
The ratio of the Grasping level threshold value and Grasping level value of the knowledge point label answered, what the needs as each knowledge point were reviewed
Intensity.It is appreciated that each knowledge point need the intensity reviewed it is bigger illustrate to need flower more great strength go to review it is described every
One knowledge point.
Preferably, further include after knowledge point recommending module 900：
Collective's recommending module obtains multiple students to be checked and same knowledge point set to be reviewed (for example, to teacher
All students in taught course review), in the multiple student to be checked each student and it is described wait for it is multiple
The knowledge point set of habit executes the knowledge point and selects step, obtains the 4th set of each student, will count multiple institutes
The occurrence number for stating different knowledge points in the 4th set, M knowledge point, which is used as, before being chosen from big to small according to number needs to review
Knowledge point set recommend user (such as the multiple student where course teacher), wherein M is predetermined number.
Module has same as step after label assignment module S400 noted earlier after the label assignment module 400
Advantageous effect, details are not described herein.
(1) in a further preferred embodiment, it includes unit 501,502 to receive enquiry module 500.Unit 501,
502 is corresponding with step S501, S502 described in preferred embodiment noted earlier, and it is no longer repeated herein.Unit 501,502
For executing described S501, S502.
(2) in a further preferred embodiment, threshold value acquisition module 600 includes unit 601,602.Unit 601,
602 is corresponding with step S601, S602 described in preferred embodiment noted earlier, and it is no longer repeated herein.Unit 601,602
For executing described S601, S602.
(3) in a further preferred embodiment, it includes unit 701,702,703 to obtain portrait module 700.Unit
701, it 702,703 is corresponded respectively with step S701, S702, S703 described in preferred embodiment noted earlier, herein not
It repeats and repeats.Unit 701,702,703 is respectively used to execute described S701, S702, S703.
(4) in a further preferred embodiment, knowledge point selection module 800 includes unit 801.Unit 801 with
Step S801 described in preferred embodiment noted earlier is corresponded to, and it is no longer repeated herein.Unit 801 is described for executing
S801。
(5) in a further preferred embodiment, knowledge point recommending module 900 includes unit 901,902.Unit
901,902 is corresponding with step S901, S902 described in preferred embodiment noted earlier, and it is no longer repeated herein.Unit
901,902 for executing described S901, S902.
4, operation big data
In a preferred embodiment, the work data includes the answer accuracy (example of each operation, the operation
Right a few percent is such as done, for the score of operation topic divided by the total score of operation topic), all knowing of being related to of operation topic
Know point, the time that operation is completed.Preferably, the work data further includes in all knowledge points that the operation topic is related to
The corresponding weight in each knowledge point.Preferably, the work data further includes the difficulty of the operation topic.
(3) the study portrait robot system based on operation big data
A kind of study that one embodiment provides is drawn a portrait robot system, and is configured in the robot system
Practise portrait system.
The study portrait robot system has advantageous effect same as study portrait system noted earlier, herein not
It repeats again.
The study portrait method and system of robot based on big data and artificial intelligence that many embodiments of the present invention provide
System, counts each students' work data in preset time range to the corresponding each work in each knowledge point in the first knowledge point set
Industry accuracy is weighted averagely, obtains total accuracy, using total accuracy as every described in each student's portrait
The Grasping level value of the corresponding knowledge point label in one knowledge point carries out study portrait by operation big data to student, to logical
It crosses study portrait and carrys out the objective grasp situation for accurately reflecting different students to different knowledge points, to improve the visitor of study portrait
The property seen and accuracy realize individualized learning and review, precision study and review for different students and different knowledge points,
The efficiency for improving study and reviewing.
The study portrait method and system of robot based on big data and artificial intelligence that many embodiments of the present invention provide
System carries out study portrait by operation big data to student, so according to study portrait come recommend the knowledge point for needing to review and
All review time weightings for needing each knowledge point in knowledge point to need flower, to improve the objectivity of study portrait and accurate
Property, for different students and different knowledge points, using different review intensity, realize and precisely review, improve review specific aim,
Efficiency so that review highly efficient.
Several embodiments of the invention above described embodiment only expresses, the description thereof is more specific and detailed, but simultaneously
Cannot the limitation to the scope of the claims of the present invention therefore be interpreted as.It should be pointed out that for those of ordinary skill in the art
For, without departing from the inventive concept of the premise, various modifications and improvements can be made, these belong to the guarantor of the present invention
Protect range.Therefore, the protection domain of patent of the present invention should be determined by the appended claims.
Claims (10)
1. a kind of study portrait method, which is characterized in that the method includes：
Accuracy calculates step, counts each students' work data in preset time range to each in the first knowledge point set
The corresponding each operation accuracy in knowledge point is weighted averagely, obtains total accuracy；
Label assignment procedure, using total accuracy as the corresponding knowledge in each knowledge point described in each student's portrait
The Grasping level value of point label.
2. study portrait method according to claim 1, which is characterized in that the accuracy is also wrapped before calculating step
It includes：
Data step is obtained, obtains operation big data, the operation big data includes each work data of each student；
Knowledge point step is obtained, all knowledge points that study includes are obtained, as the first knowledge point set.
3. learning portrait method according to claim 1 to 2 any one of them, which is characterized in that the label assignment procedure
Further include later：
Receive query steps, obtain student to be checked and knowledge point set to be reviewed, by the knowledge point set to be reviewed
Cooperation is the second knowledge point set；
Threshold value obtaining step, from obtaining the corresponding Grasping level in each knowledge point in the second knowledge point set in working knowledge library
Threshold value；
Portrait step is obtained, the study portrait of the student to be checked is searched for and obtained in drawing a portrait knowledge base from study, from institute
It states in the study portrait of student to be checked and obtains the corresponding knowledge point label in each knowledge point for belonging to the second knowledge point set
Grasping level value；
Knowledge point selects step, judges whether the Grasping level value of the corresponding knowledge point label in each knowledge point is more than or waits
The threshold value of the corresponding knowledge point Grasping level in each knowledge point described in working knowledge library：It is, then by each knowledge point
Third knowledge point set is added；It is no, then the 4th knowledge point set is added in each knowledge point；
The knowledge point set that the 4th knowledge point set is reviewed as needs is recommended user by knowledge point recommendation step.
4. study portrait method according to claim 3, which is characterized in that wrapped after the knowledge point selection step
It includes：
Collective's recommendation step obtains multiple students to be checked and same knowledge point set to be reviewed, to the multiple to be checked
Each student and the knowledge point set to be reviewed in the student of inquiry execute the knowledge point and select step, obtain described every
The 4th set of one student will count the occurrence number of different knowledge points in multiple four set, according to number from greatly to
The knowledge point set that M knowledge point is reviewed as needs before small selection recommends user, wherein M is predetermined number.
5. study portrait method according to claim 1, which is characterized in that the work data include each operation,
The time of all knowledge points, operation completion that answer accuracy, the operation topic of the operation are related to.
6. a kind of study portrait system, which is characterized in that the system comprises：
Accuracy computing module, for counting each students' work data in preset time range in the first knowledge point set
The corresponding each operation accuracy in each knowledge point is weighted average, obtains total accuracy；
Label assignment module, for total accuracy is corresponding as each knowledge point described in each student's portrait
The Grasping level value of knowledge point label.
7. study portrait system according to claim 6, which is characterized in that the system also includes：
Data module is obtained, for obtaining operation big data, the operation big data includes each work data of each student；
Knowledge point module is obtained, all knowledge points for including for obtaining study, as the first knowledge point set.
8. learning portrait system according to claim 6 any one of them, which is characterized in that the system also includes：
Receive enquiry module, for obtaining student to be checked and knowledge point set to be reviewed, by the knowledge to be reviewed
Point set is as the second knowledge point set；
Threshold value acquisition module, for from obtaining the corresponding grasp journey in each knowledge point in the second knowledge point set in working knowledge library
The threshold value of degree；
Portrait module is obtained, the study portrait for the student to be checked to be searched for and obtained in drawing a portrait knowledge base from study,
The corresponding knowledge point in each knowledge point for belonging to the second knowledge point set is obtained from the study portrait of the student to be checked
The Grasping level value of label；
Knowledge point selection module, for judging whether the Grasping level value of the corresponding knowledge point label in each knowledge point is more than
Or the threshold value of knowledge point Grasping level corresponding equal to each knowledge point described in working knowledge library：It is then each to know described
Know point and third knowledge point set is added；It is no, then the 4th knowledge point set is added in each knowledge point；
Knowledge point recommending module, the knowledge point set for reviewing the 4th knowledge point set as needs recommend use
Family.
9. learning portrait system according to claim 8 any one of them, which is characterized in that the system also includes：
Collective's recommending module, for obtaining multiple students to be checked and same knowledge point set to be reviewed, to the multiple
Each student and the knowledge point set to be reviewed in student to be checked execute the knowledge point selection module, obtain institute
The 4th set for stating each student will count the occurrence number of different knowledge points in multiple four set, according to number from
M knowledge point is arrived before small selection greatly as needing the knowledge point set reviewed to recommend user, wherein M is predetermined number.
The robot system 10. a kind of study is drawn a portrait, which is characterized in that be respectively configured just like claim in the robot system
6-9 any one of them learns portrait system.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810630020.5A CN108765227A (en) | 2018-06-20 | 2018-06-20 | Study portrait method based on big data and artificial intelligence and robot system |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201810630020.5A CN108765227A (en) | 2018-06-20 | 2018-06-20 | Study portrait method based on big data and artificial intelligence and robot system |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN108765227A true CN108765227A (en) | 2018-11-06 |
Family
ID=63978714
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201810630020.5A Pending CN108765227A (en) | 2018-06-20 | 2018-06-20 | Study portrait method based on big data and artificial intelligence and robot system |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN108765227A (en) |
Cited By (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347341A (en) * | 2019-08-07 | 2021-02-09 | 上海流利说信息技术有限公司 | Learning question recommendation method, system and storage medium |
| CN112700075A (en) * | 2019-10-23 | 2021-04-23 | 上海泽稷教育培训有限公司 | Score evaluation method, system, storage medium and server |
| CN112784895A (en) * | 2021-01-18 | 2021-05-11 | 辽宁向日葵教育科技有限公司 | Teaching system based on user portrait label |
| CN116342339A (en) * | 2023-03-27 | 2023-06-27 | 读书郎教育科技有限公司 | Screening and distributing method based on question bank |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104157175A (en) * | 2014-08-27 | 2014-11-19 | 湖南堂堂清教育科技有限公司 | Teaching effect immediate feedback evaluation system |
| CN104299473A (en) * | 2013-07-20 | 2015-01-21 | 郑州学生宝电子科技有限公司 | Teaching and student learning error question knowledge base |
| CN105355111A (en) * | 2015-12-02 | 2016-02-24 | 华中师范大学 | After-class reinforced learning system based on learning situation analysis |
| CN107977708A (en) * | 2017-11-24 | 2018-05-01 | 重庆科技学院 | The student's DNA identity informations recommended towards individualized learning scheme define method |
| CN108122444A (en) * | 2016-11-28 | 2018-06-05 | 北京狸米科技有限公司 | A kind of adaptive and learning system and method |
-
2018
- 2018-06-20 CN CN201810630020.5A patent/CN108765227A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN104299473A (en) * | 2013-07-20 | 2015-01-21 | 郑州学生宝电子科技有限公司 | Teaching and student learning error question knowledge base |
| CN104157175A (en) * | 2014-08-27 | 2014-11-19 | 湖南堂堂清教育科技有限公司 | Teaching effect immediate feedback evaluation system |
| CN105355111A (en) * | 2015-12-02 | 2016-02-24 | 华中师范大学 | After-class reinforced learning system based on learning situation analysis |
| CN108122444A (en) * | 2016-11-28 | 2018-06-05 | 北京狸米科技有限公司 | A kind of adaptive and learning system and method |
| CN107977708A (en) * | 2017-11-24 | 2018-05-01 | 重庆科技学院 | The student's DNA identity informations recommended towards individualized learning scheme define method |
Cited By (6)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112347341A (en) * | 2019-08-07 | 2021-02-09 | 上海流利说信息技术有限公司 | Learning question recommendation method, system and storage medium |
| CN112347341B (en) * | 2019-08-07 | 2022-11-18 | 上海流利说信息技术有限公司 | Learning question recommendation method, system and storage medium |
| CN112700075A (en) * | 2019-10-23 | 2021-04-23 | 上海泽稷教育培训有限公司 | Score evaluation method, system, storage medium and server |
| CN112784895A (en) * | 2021-01-18 | 2021-05-11 | 辽宁向日葵教育科技有限公司 | Teaching system based on user portrait label |
| CN116342339A (en) * | 2023-03-27 | 2023-06-27 | 读书郎教育科技有限公司 | Screening and distributing method based on question bank |
| CN116342339B (en) * | 2023-03-27 | 2024-02-06 | 读书郎教育科技有限公司 | Screening and distributing method based on question bank |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN108765227A (en) | Study portrait method based on big data and artificial intelligence and robot system | |
| JP6701367B2 (en) | Method, device, and computer program for providing personalized educational content | |
| Weiss et al. | Test theory and methods | |
| CN109934744B (en) | Method, system and computer readable recording medium for providing educational service based on knowledge unit | |
| CN104504949A (en) | Remote education information platform system | |
| CN108597280A (en) | Teaching system and teaching method based on learning behavior analysis | |
| CN108804705A (en) | Method and education robot system are recommended in review based on big data and artificial intelligence | |
| CA2516160A1 (en) | System and method for creating, assessing, modifying, and using a learning map | |
| CN103064903B (en) | Picture retrieval method and device | |
| CN108629716A (en) | Accurate methods of review and education robot system based on big data and artificial intelligence | |
| CN107544973A (en) | A kind of method and apparatus that data are handled | |
| Vance et al. | Construct models of task performance. | |
| CN106600065A (en) | Individualized learning path extraction and jointing method and system based on directed hypergraph | |
| Abaidullah et al. | Identifying Hidden Patterns in Students" Feedback through Cluster Analysis | |
| JP2002072856A (en) | Lecture class-to-be-attended selecting device, lecture class-to-be-attended selecting method and storage medium | |
| CN109285405A (en) | It is competent at ability training method, equipment and system in post | |
| WO2018079968A1 (en) | Method and apparatus for providing personalized educational content, and computer program | |
| CN113535935A (en) | Method, apparatus, device and medium for volume grouping based on importance degree and priority | |
| Deuri | Attitude towards choice based credit system of post graduate level students in higher education: a study on Gauhatiuniversity | |
| CN110084109A (en) | A kind of low-resolution face image recognition methods, device, electronic equipment and storage medium | |
| CN106327937A (en) | System for remote guidance for students to finish homework through computer and method thereof | |
| CN109684436A (en) | A kind of correlating method of knowledge and application | |
| CN108399243A (en) | A kind of education question purpose recommendation method and device | |
| Panni et al. | A model for automatic partial evaluation of SQL queries | |
| CN113642880A (en) | Internet-based team training method and system |
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 |