CN110489602A - Knowledge point ability value predictor method, system, equipment and medium - Google Patents
Knowledge point ability value predictor method, system, equipment and medium Download PDFInfo
- Publication number
- CN110489602A CN110489602A CN201910686317.8A CN201910686317A CN110489602A CN 110489602 A CN110489602 A CN 110489602A CN 201910686317 A CN201910686317 A CN 201910686317A CN 110489602 A CN110489602 A CN 110489602A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- ability value
- new
- now
- data base
- 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.)
- Granted
Links
- 238000000034 method Methods 0.000 title claims abstract description 36
- 230000005540 biological transmission Effects 0.000 claims abstract description 24
- 238000012545 processing Methods 0.000 claims description 15
- 238000004590 computer program Methods 0.000 claims description 11
- 238000000605 extraction Methods 0.000 claims description 11
- 239000000284 extract Substances 0.000 claims description 9
- 230000008569 process Effects 0.000 claims description 6
- 238000010586 diagram Methods 0.000 claims description 5
- 238000001228 spectrum Methods 0.000 claims 2
- 238000013507 mapping Methods 0.000 abstract description 4
- 230000000875 corresponding effect Effects 0.000 description 10
- 230000004044 response Effects 0.000 description 10
- 238000012360 testing method Methods 0.000 description 9
- 230000008859 change Effects 0.000 description 4
- 238000005516 engineering process Methods 0.000 description 3
- 238000004458 analytical method Methods 0.000 description 1
- 230000015572 biosynthetic process Effects 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 238000006243 chemical reaction Methods 0.000 description 1
- 230000002596 correlated effect Effects 0.000 description 1
- 230000007812 deficiency Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000002452 interceptive effect Effects 0.000 description 1
- 238000012886 linear function Methods 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 238000013179 statistical model Methods 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
- 238000010998 test method Methods 0.000 description 1
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/30—Information retrieval; Database structures therefor; File system structures therefor of unstructured textual data
- G06F16/36—Creation of semantic tools, e.g. ontology or thesauri
- G06F16/367—Ontology
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/901—Indexing; Data structures therefor; Storage structures
- G06F16/9024—Graphs; Linked lists
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F16/00—Information retrieval; Database structures therefor; File system structures therefor
- G06F16/90—Details of database functions independent of the retrieved data types
- G06F16/903—Querying
- G06F16/90335—Query processing
-
- 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
Landscapes
- Engineering & Computer Science (AREA)
- Theoretical Computer Science (AREA)
- Business, Economics & Management (AREA)
- Databases & Information Systems (AREA)
- Physics & Mathematics (AREA)
- General Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Educational Administration (AREA)
- Educational Technology (AREA)
- Strategic Management (AREA)
- Computational Linguistics (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)
- Life Sciences & Earth Sciences (AREA)
- Animal Behavior & Ethology (AREA)
- Software Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
Abstract
The invention discloses knowledge point ability value predictor method, system, equipment and media, and the method includes the ability value vector of source knowledge point is extracted from initialized data base；Calculate the transmission factor between object knowledge point and source knowledge point；Calculate the new ability value vector of object knowledge point；Update the ability value vector of object knowledge point in initialized data base；Ability value vector according to updated object knowledge point obtains object knowledge point and estimates ability value；The ability value vector of next source knowledge point is extracted from initialized data base.Its context by utilizing in knowledge mapping between knowledge point of the invention, the ability value of its postposition knowledge point is estimated out by the ability value vector of known knowledge point, can the ability value quickly to the knowledge point in knowledge mapping estimate, and the ability value accuracy estimated on the knowledge point not learnt is high.
Description
Technical field
The invention belongs to field of computer technology more particularly to a kind of knowledge point ability value predictor method, system, equipment and
Medium.
Background technique
With the development of technology, online education have become it is a kind of instantly and its important educational mode, and in major enterprise
In the online education software of industry exploitation, the overwhelming majority needs to acquire the ability value number of user each knowledge point on the map of knowledge point
According to, then according to ability Value Data come arrange study plan, push away topic test etc. operation, the ability value that user is reflected on knowledge point
Item response theory is based primarily upon to obtain.
Item response theory is a series of general name of psychology statistical models, and target determines potential feature and survey
Whether the interactive relationship (Grasping level of user can regard potential feature as) between examination question and testee can pass through survey
Examination question reflects.
Item response theory assumes that testee has a kind of " latent trait ", and latent trait is to test to react in observation analysis
On the basis of a kind of statistics conception for proposing, in test, latent trait generally refers to potential ability, and through common test total score
Estimation as this potentiality.Item response theory thinks that reaction and achievement of the testee on test item are latent with theirs
There is special relationship in speciality.Has the characteristics that permanent property by the item argument that item response theory is established, it is meant that different
The score of measurement can be unified.
The common model expression of item response theory are as follows:
It is also referred to as item characteristic curve according to the curve that above-mentioned model formation is drawn, its significance lies in that description " is successfully answered
Relationship between the probability of a certain fc-specific test FC project " and " testee's ability " (i.e. θ in formula).
The parameter for including in above-mentioned formula is explained as follows:
C indicates " conjecture parameter ", and intuitive meaning is, when the ability value of a testee is very low (such as close to 0),
But still it can correctly do probability to the project；
B indicate item difficulty parameter, according to the mobility of function it is found that change b will lead to image move left and right without
Change shape；
A indicates the discrimination of project, i.e. can a project distinguish the ability level of different testees, a well
Value it is more high have discrimination.
It is recognised that item response theory is only to generate to the same project in the above-mentioned introduction to item response theory
Response, that is to say, that when user is when learning some project, current project can generate feedback, and sundry item is not
Have any change.
But it is all mutually related between education sector, knowledge point.Such as certain user is learning " equation
Definition " is after knowledge point, and user also just has the rudimentary knowledge of correlated knowledge point " solution of linear equation with one unknown ", and " unitary
The solution of linear function " is no longer completely new for a user.
In existing technology, needing to carry out each knowledge point test in advance just rough can know user at this
Ability value on a knowledge point, and the quantity of knowledge point be often it is huge, take this test method be it is inefficient, it is cumbersome
's.If the knowledge point of test is that user did not learnt, user when testing, can lack initiative, be difficult standard
True obtains ability Value Data of the user on non-learning knowledge point.
Summary of the invention
In view of the above-mentioned deficiencies in the prior art, the technical problem to be solved by the present invention is that providing knowledge point ability value
Predictor method, system, equipment and medium, by being known by known using the context between knowledge point in knowledge mapping
The ability value vector for knowing point estimates out the ability value of its postposition knowledge point, energy that can quickly to the knowledge point in knowledge mapping
Force value is estimated, and the ability value accuracy estimated on the knowledge point not learnt is high.
In order to solve the above technical problems, first aspect present invention provides knowledge point ability value predictor method, including following
Step:
Step 1: extracting the ability value vector V of source knowledge point from initialized data baseS, VS=[(Ps1, θs1)、(Ps2,
θs2)、(Ps3, θs3)、...(PsN, θsN)]；
Step 2: calculating the transmission factor δ between object knowledge point and source knowledge point, the object knowledge point is in knowledge point
With the postposition knowledge point of source Knowledge Relation in map, transmission factor δ calculating process includes:
Step 201 acquires the shortest path S between object knowledge point and source knowledge point according to knowledge point map；According to knowledge
The node in-degree λ of point map acquisition object knowledge point；
Step 202, from initialized data base extraction source knowledge point difficulty value d, 0 < d < 1；
Step 203, foundationCalculate transmission factor δ；
Step 3: calculating the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；After the completion of calculating, V is extractednew
In P, obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Step 4: extracting the current ability value vector V of object knowledge point from initialized data basenow, extract VnowIn P,
Obtain (Pnow1、Pnow2、Pnow3、...PnowN),
Calculate (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN),
New (P is obtained by calculated resultnow1、Pnow2、Pnow3、...PnowN)；
By new (Pnow1、Pnow2、Pnow3、...PnowN) return to ability value vector Vnow, obtain updated Vnow；It will more
V after newnowBack in initialized data base；
Step 5: finding out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value, and foundation
The P finds out corresponding θ, which estimates ability value for current goal knowledge point；
Step 6: extracting the ability value vector V of next source knowledge point from initialized data baseS, then execute step 2
To step 5.
Further, the current ability value vector V of object knowledge point is extracted from initialized data base in step 4nowWhen, if in advance
It sets and is not stored with ability value vector V in databasenowWhen, with V in step 3newAs updated Vnow, and by VnowIt returns
Into initialized data base.
Further, when the quantity of the maximum P of the numerical value found out in step 5 is greater than one, take multiple P corresponding more
The mean value of a θ estimates ability value as current goal knowledge point.
Second aspect of the present invention provides knowledge point ability value Prediction System, comprising:
Data extracting unit, the ability value vector V for the extraction source knowledge point from initialized data baseS, VS=[(Ps1,
θs1)、(Ps2, θs2)、(Ps3, θs3)、...(PsN, θsN)]；For extracting the new ability value vector V of object knowledge pointnewIn P, obtain
Obtain (Pnew1、Pnew2、Pnew3、...PnewN), the object knowledge point is the postposition in the map of knowledge point with source Knowledge Relation
Knowledge point；For extracting the current ability value vector V of object knowledge point from initialized data basenow, and extract VnowIn P, obtain
Obtain (Pnow1、Pnow2、Pnow3、...PnowN)；Difficulty value d, 0 < d < 1 for the extraction source knowledge point from initialized data base；
Data acquisition unit, for according to the shortest path S between knowledge point map acquisition object knowledge point and source knowledge point；
Node in-degree λ according to knowledge point map acquisition object knowledge point；
Data processing unit, for calculating the transmission factor δ between object knowledge point and source knowledge point,Based on
Calculate the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；For calculating (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×
Pnow3、...PnewN×PnowN), obtain new (Pnow1、Pnow2、Pnow3、...PnowN)；For by new (Pnow1、Pnow2、
Pnow3、...PnowN) return to ability value vector Vnow, to VnowIt is updated, and by updated VnowBack to initialized data base
In；For finding out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value, and found out according to the P
Corresponding θ, the θ estimate ability value for current goal knowledge point.
Further, data extracting unit extracts the current ability value vector V of object knowledge point from initialized data basenowWhen,
If not being stored with ability value vector V in initialized data basenowWhen, object knowledge point is calculated with it in data processing unit
New ability value vector VnewAs updated Vnow, and by updated VnowBack in initialized data base.
Further, when the quantity for the maximum P of numerical value that data processing unit is found out is greater than one, take multiple P corresponding
The mean value of multiple θ estimate ability value as current goal knowledge point.
Third aspect present invention also provides knowledge point ability value and estimates equipment, including memory, processor and is stored in
In the memory and the computer program that can run on the processor, when the processor executes the computer program
The step of realizing aforementioned first aspect or first aspect any implementation the method.
Fourth aspect present invention also provides a kind of computer readable storage medium, the computer-readable recording medium storage
There is computer program, aforementioned first aspect or first aspect any realization side are realized when the computer program is executed by processor
The step of formula the method.
Fifth aspect present invention also provides knowledge point ability value predictor method, comprising the following steps:
Step 1: extracting the ability value vector V of source knowledge point from initialized data baseS, VS=[(Ps1, θs1)、(Ps2,
θs2)、(Ps3, θs3)、...(PsN, θsN)]；
Step 2: calculating the transmission factor δ between object knowledge point and source knowledge point, the object knowledge point is in knowledge point
With the postposition knowledge point of source Knowledge Relation in map, transmission factor δ calculating process includes:
Step 201 acquires the shortest path S between object knowledge point and source knowledge point according to knowledge point map；According to knowledge
The node in-degree λ of point map acquisition object knowledge point；
Step 202, from initialized data base extraction source knowledge point difficulty value d, 0 < d < 1；
Step 203, foundationCalculate transmission factor δ；
Step 3: calculating the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；After the completion of calculating, V is extractednew
In P, obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Step 4: finding out (Pnew1、Pnew2、Pnew3、...PnewN) in the maximum P of numerical value, and find out according to the P corresponding
θ, which is that ability value is estimated in current goal knowledge point.
Further, when the quantity of the maximum P of the numerical value found out in step 4 is greater than one, take multiple P corresponding more
The mean value of a θ estimates ability value as current goal knowledge point.
Compared with the prior art, the present invention has the following advantages:
1, the present invention can estimate out the source Knowledge Relation by the ability value vector of the knowledge point knowledge point map Zhong Yuan
Postposition knowledge point ability value, acquisition is buried by data to each knowledge point in the map of knowledge point compared to the prior art
Mode acquisition capacity value one by one, the present invention can greatly save each knowledge point ability value acquisition in the map of knowledge point when
Between.
2, the present invention can estimate out its ability by the ability value vector of its preposition knowledge point to the knowledge point not learnt
Value is compared to the prior art calculated the ability value for the knowledge point not learnt using item response theory, and the present invention reduces
Energy consumption needed for computer calculates, especially in entire knowledge point map thus the ability value of knowledge point when calculating,
The present invention can significantly shorten calculating and spend the time.
3, the present invention states the degree of association between source knowledge point and object knowledge point, the variable of transmission factor δ with transmission factor δ
Using the shortest path S and object knowledge point intermediate node between the difficulty value d of source knowledge point, source knowledge point and object knowledge point
In-degree λ；The higher position for illustrating source knowledge point in the map of knowledge point the difficulty value d of source knowledge point more rearward, further illustrates
The high probability of relevance is bigger between object knowledge point and source knowledge point；Shortest path S between source knowledge point and object knowledge point is got over
It is small, illustrate that relevance is higher between object knowledge point and source knowledge point；Object knowledge point intermediate node in-degree λ is smaller, illustrates the target
The preposition knowledge point quantity of knowledge point is less, further illustrates that the relevance between source knowledge point and object knowledge point is higher；So
Transmission factorThe degree of association between source knowledge point and object knowledge point can be measured.Finally transmission factor δ substitution source is known
Know the ability value vector V of pointS, one for capable of obtaining object knowledge point estimates ability value vector Vnew, and with VnewIn probability
Data P ability value vector V original to object knowledge pointnowProbability data P be adjusted, if an object knowledge point is more than
One preposition source knowledge point, ability value vector VnowProbability data P by repeatedly adjustment, can tend to one more it is accurate really
Probability data P, the ability value θ then found out according to probability data P is better able to accurately reflect user on object knowledge point
Ability.
Below by drawings and examples, technical scheme of the present invention will be described in further detail.
Detailed description of the invention
Fig. 1 is the schematic diagram of a knowledge point map.
Fig. 2 is method flow schematic diagram of the invention.
Specific embodiment
Embodiment 1
Knowledge point ability value predictor method, as shown in Figure 2, comprising the following steps:
Step 1: extracting the ability value vector V of source knowledge point from initialized data baseS, ability value vector VSFor N-dimensional
Vector, VS=[(Ps1, θs1)、(Ps2, θs2)、(Ps3, θs3)、...(PsN, θsN)]；It is assumed herein that the ability value of some source knowledge point
Vector
VS=[(0.2,0.1), (0.4,0.2), (0.1,0.3), (0.2,0.4) (0.3,0.5)]；
Wherein Ps1=0.2, θs1When=0.1, representing user's ability value on the source knowledge point as 0.1 probability is 0.2；
Step 2: calculating the transmission factor δ between object knowledge point and source knowledge point, the object knowledge point is in knowledge point
With the postposition knowledge point of source Knowledge Relation in map, Fig. 1 is the schematic diagram of a knowledge point map, transmission factor δ calculating process
Include:
Step 201 acquires the shortest path S between object knowledge point and source knowledge point according to knowledge point map；Such as Fig. 1 institute
Show, the shortest path S=1 between object knowledge point 3 and source knowledge point, the shortest path S=between object knowledge point 2 and source knowledge point
2；Node in-degree λ according to knowledge point map acquisition object knowledge point；Node in-degree λ refers to that how many paths is directed toward this and knows
Know point, as shown in fig. 1, node in-degree λ=2 of object knowledge point 3,2 node in-degree λ=1 of object knowledge point；It needs to illustrate
That the value of shortest path S is smaller, illustrate between object knowledge point and source knowledge point be associated with it is closer；The value of node in-degree λ is got over
It is small, illustrate that the preposition knowledge point quantity of object knowledge point is fewer, further, illustrates object knowledge point and being associated between the knowledge point of source
It is closer；
Step 202, from initialized data base extraction source knowledge point difficulty value d, 0 < d < 1；It should be noted that one
The difficulty of knowledge point is higher, illustrates position of the knowledge point in the map of knowledge point more rearward, for example, knowledge point " addition " with know
Know point " calculus ", can determine that the difficulty of knowledge point " calculus " is significantly larger than knowledge point " addition ", knowledge point " addition "
Quantity of the quantity of postposition knowledge point far more than the postposition knowledge point of knowledge point " calculus "；The difficulty of source knowledge point is higher,
The quantity of its postposition knowledge point is fewer, i.e., fewer with the object knowledge of source Knowledge Relation point quantity, further, illustrates target
Knowledge point and being associated with for source knowledge point are closer；
Step 203, foundationCalculate transmission factor δ；Transmission factor δ is reflection object knowledge point and source knowledge point
Between correlation degree parameter；
Step 3: calculating the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；After the completion of calculating, V is extractednew
In P, obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Step 4: extracting the current ability value vector V of object knowledge point from initialized data basenow, extract VnowIn P,
Obtain (Pnow1、Pnow2、Pnow3、...PnowN),
Calculate (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN), it is obtained newly by calculated result
(Pnow1、Pnow2、Pnow3、...PnowN)；
By new (Pnow1、Pnow2、Pnow3、...PnowN) return to ability value vector Vnow, obtain updated Vnow；It will more
V after newnowBack in initialized data base；
Step 5: finding out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value, and foundation
The P finds out corresponding θ, which estimates ability value for current goal knowledge point；
Step 6: extracting the ability value vector V of next source knowledge point from initialized data baseS, then execute step 2
To step 5.
It should be noted that the value vector V that has the ability in the map of knowledge pointSKnowledge point can be used as source knowledge point；
I.e. for some knowledge point, source knowledge point, In are used as in the method and step implementation procedure of a step 2 to step 5
Another secondary step 2 knowledge point into the method and step implementation procedure of step 5 can become object knowledge point again.
In the present embodiment, the current ability value vector V of object knowledge point is extracted from initialized data base in step 4nowWhen, if
Ability value vector V is not stored in initialized data basenow, then with V in step 3newAs updated Vnow, and by VnowIt returns
It returns in initialized data base.
In the present embodiment, when the quantity of the maximum P of the numerical value found out in step 5 is greater than one, take multiple P corresponding
The mean value of multiple θ estimates ability value as current goal knowledge point.
It should be noted that the method for the invention, in this method step implementation procedure, step 2 of every execution is extremely
The ability value of step 5, the then all postposition knowledge points for the source knowledge point chosen in this implementation procedure will be updated once.
Embodiment 2
Knowledge point ability value Prediction System, comprising: data extracting unit, data acquisition unit and data processing unit.
Operational process is as follows when the Prediction System estimates knowledge point ability: this is sentenced to knowledge point shown in Fig. 1
For the ability value of object knowledge point 3 in map is estimated, it is illustrated；
The ability value vector V of data extracting unit extraction source knowledge point from initialized data baseS, ability value vector VSFor N-dimensional
Vector, VS=[(Ps1, θs1)、(Ps2, θs2)、(Ps3, θs3)、...(PsN, θsN)]；
Data acquisition unit is according to the shortest path S, such as Fig. 1 between knowledge point map acquisition object knowledge point and source knowledge point
Shown, in the present embodiment between object knowledge point 3 and source knowledge point shortest path S=1；
Node in-degree λ of the data acquisition unit according to knowledge point map acquisition object knowledge point 3；Node in-degree λ is referred to
How many paths is directed toward the knowledge point, as shown in fig. 1, node in-degree λ=2 of object knowledge point 3；
Data processing unit calculates the transmission factor δ between object knowledge point and source knowledge point,Herein, transmitting because
Sub- δ is the parameter of the correlation degree reflected between object knowledge point 3 and source knowledge point；
The new ability value vector V of data processing unit calculating object knowledge point 3new, Vnew=VS×δ；After the completion of calculating, number
V is extracted according to extraction unitnewIn P, obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Data extracting unit judges the current ability value vector V of object knowledge point 3 whether is stored in initialized data basenow,
If so, extracting the current ability value vector V of object knowledge point from initialized data basenow, extract VnowIn P, obtain
(Pnow1、Pnow2、Pnow3、...PnowN)；
Data processing unit calculates (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN), pass through meter
It calculates result and obtains new (Pnow1、Pnow2、Pnow3、...PnowN)；
Data processing unit is by new (Pnow1、Pnow2、Pnow3、...PnowN) return to ability value vector Vnow, updated
V afterwardsnow；By updated VnowBack in initialized data base, the V originally stored in initialized data base is updatednow；
Data processing unit finds out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value,
And corresponding θ is found out according to the P, which estimates ability value for current goal knowledge point 3；
Then data extracting unit extracts the ability value vector V of next source knowledge point from initialized data baseS, such as Fig. 1
Shown, can be used as next source knowledge point at this time is the object knowledge point 1 and object knowledge point 2 in Fig. 1, can be seen by Fig. 1
Object knowledge point 2 is the postposition knowledge point of object knowledge point 1 out, it is preferable that object knowledge is chosen in next source knowledge point
Point 1.
In the present embodiment, data extracting unit judges the current energy of object knowledge point 3 whether is stored in initialized data base
Force value vector VnowWhen, if it is not, then data processing unit calculates the new ability value vector V of object knowledge point 3newAs updated
VnowBack in initialized data base, and data processing unit finds out updated VnowIn (Pnow1、Pnow2、Pnow3、
...PnowN) in the maximum P of numerical value, and corresponding θ is found out according to the P, which is that ability is estimated in current goal knowledge point 3
Value.
In the present embodiment, when the quantity of the maximum P of the numerical value that data processing unit is found out is greater than one, multiple P pairs is taken
The mean value of the multiple θ answered estimates ability value as current goal knowledge point.
Embodiment 3
Knowledge point ability value estimates equipment, including memory, processor and storage are in the memory and can be in institute
The computer program run on processor is stated, the processor is realized described in previous embodiment 1 when executing the computer program
The step of method.
Embodiment 4
A kind of computer readable storage medium, the computer-readable recording medium storage have computer program, the meter
The step of 1 the method for previous embodiment is realized when calculation machine program is executed by processor.
The above is only presently preferred embodiments of the present invention, is not intended to limit the invention in any way, it is all according to the present invention
Technical spirit any simple modification to the above embodiments, change and equivalent structural changes, still fall within skill of the present invention
In the protection scope of art scheme.
Claims (10)
1. knowledge point ability value predictor method, it is characterised in that: the following steps are included:
Step 1: extracting the ability value vector V of source knowledge point from initialized data baseS, VS=[(Ps1, θs1)、(Ps2, θs2)、
(Ps3, θs3)、...(PsN, θsN)]；
Step 2: calculating the transmission factor δ between object knowledge point and source knowledge point, the object knowledge point is in knowledge point map
In postposition knowledge point with source Knowledge Relation, transmission factor δ calculating process includes:
Step 201 acquires the shortest path S between object knowledge point and source knowledge point according to knowledge point map；According to knowledge point diagram
The node in-degree λ of spectrum acquisition object knowledge point；
Step 202, from initialized data base extraction source knowledge point difficulty value d, 0 < d < 1；
Step 203, foundationCalculate transmission factor δ；
Step 3: calculating the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；After the completion of calculating, V is extractednewIn P,
Obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Step 4: extracting the current ability value vector V of object knowledge point from initialized data basenow, extract VnowIn P, obtain
(Pnow1、Pnow2、Pnow3、...PnowN),
Calculate (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN),
New (P is obtained by calculated resultnow1、Pnow2、Pnow3、...PnowN)；
By new (Pnow1、Pnow2、Pnow3、...PnowN) return to ability value vector Vnow, obtain updated Vnow；After updating
VnowBack in initialized data base；
Step 5: finding out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value, and looked for according to the P
Corresponding θ out, the θ estimate ability value for current goal knowledge point；
Step 6: extracting the ability value vector V of next source knowledge point from initialized data baseS, step 2 is then executed to step
Five.
2. ability value predictor method in knowledge point described in accordance with the claim 1, it is characterised in that: from initialized data base in step 4
Extract the current ability value vector V of object knowledge pointnowWhen, if not being stored with ability value vector V in initialized data basenowWhen,
With V in step 3newAs updated Vnow, and by VnowBack in initialized data base.
3. ability value predictor method in knowledge point described in accordance with the claim 1, it is characterised in that: the numerical value found out in step 5 is most
When the quantity of big P is greater than one, the mean value of the corresponding multiple θ of multiple P is taken to estimate ability as current goal knowledge point
Value.
4. knowledge point ability value Prediction System characterized by comprising
Data extracting unit, the ability value vector V for the extraction source knowledge point from initialized data baseS, VS=[(Ps1, θs1)、
(Ps2, θs2)、(Ps3, θs3)、...(PsN, θsN)]；For extracting the new ability value vector V of object knowledge pointnewIn P, obtain
(Pnew1、Pnew2、Pnew3、...PnewN), the object knowledge point is that the postposition in the map of knowledge point with source Knowledge Relation is known
Know point；For extracting the current ability value vector V of object knowledge point from initialized data basenow, and extract VnowIn P, obtain
(Pnow1、Pnow2、Pnow3、...PnowN)；Difficulty value d, 0 < d < 1 for the extraction source knowledge point from initialized data base；
Data acquisition unit, for according to the shortest path S between knowledge point map acquisition object knowledge point and source knowledge point；Foundation
The node in-degree λ of knowledge point map acquisition object knowledge point；
Data processing unit, for calculating the transmission factor δ between object knowledge point and source knowledge point,For calculating mesh
Mark the new ability value vector V of knowledge pointnew, Vnew=VS×δ；For calculating (Pnew1×Pnow1、Pnew2×Pnow2、Pnew3×
Pnow3、...PnewN×PnowN), obtain new (Pnow1、Pnow2、Pnow3、...PnowN)；For by new (Pnow1、Pnow2、
Pnow3、...PnowN) return to ability value vector Vnow, to VnowIt is updated, and by updated VnowBack to initialized data base
In；For finding out updated VnowIn (Pnow1、Pnow2、Pnow3、...PnowN) in the maximum P of numerical value, and found out according to the P
Corresponding θ, the θ estimate ability value for current goal knowledge point.
5. knowledge point ability value Prediction System according to claim 4, it is characterised in that: data extracting unit is from preset number
The current ability value vector V of object knowledge point is extracted according to librarynowWhen, if not being stored with ability value vector V in initialized data basenow
When, the new ability value vector V of object knowledge point is calculated with it for data processing unitnewAs updated Vnow, and will more
V after newnowBack in initialized data base.
6. knowledge point ability value Prediction System according to claim 4, it is characterised in that: the number that data processing unit is found out
When being worth the quantity of maximum P greater than one, mean value the estimating as current goal knowledge point of the corresponding multiple θ of multiple P is taken
Ability value.
7. knowledge point ability value estimates equipment, including memory, processor and storage are in the memory and can be described
The computer program run on processor, which is characterized in that the processor realizes such as right when executing the computer program
It is required that the step of 1,2 or 3 the method.
8. computer readable storage medium, the computer-readable recording medium storage has computer program, which is characterized in that institute
It states and realizes when computer program is executed by processor such as the step of claim 1,2 or 3 the method.
9. knowledge point ability value predictor method, it is characterised in that: the following steps are included:
Step 1: extracting the ability value vector V of source knowledge point from initialized data baseS, VS=[(Ps1, θs1)、(Ps2, θs2)、
(Ps3, θs3)、...(PsN, θsN)]；
Step 2: calculating the transmission factor δ between object knowledge point and source knowledge point, the object knowledge point is in knowledge point map
In postposition knowledge point with source Knowledge Relation, transmission factor δ calculating process includes:
Step 201 acquires the shortest path S between object knowledge point and source knowledge point according to knowledge point map；According to knowledge point diagram
The node in-degree λ of spectrum acquisition object knowledge point；
Step 202, from initialized data base extraction source knowledge point difficulty value d, 0 < d < 1；
Step 203, foundationCalculate transmission factor δ；
Step 3: calculating the new ability value vector V of object knowledge pointnew, Vnew=VS×δ；After the completion of calculating, V is extractednewIn P,
Obtain (Pnew1、Pnew2、Pnew3、...PnewN)；
Step 4: finding out (Pnew1、Pnew2、Pnew3、...PnewN) in the maximum P of numerical value, and corresponding θ is found out according to the P,
The θ estimates ability value for current goal knowledge point.
10. knowledge point ability value predictor method according to claim 9, it is characterised in that: the numerical value found out in step 4
When the quantity of maximum P is greater than one, the mean value of the corresponding multiple θ of multiple P is taken to estimate energy as current goal knowledge point
Force value.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910686317.8A CN110489602B (en) | 2019-07-25 | 2019-07-25 | Knowledge point capability value estimation method, system, device and medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN201910686317.8A CN110489602B (en) | 2019-07-25 | 2019-07-25 | Knowledge point capability value estimation method, system, device and medium |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN110489602A true CN110489602A (en) | 2019-11-22 |
| CN110489602B CN110489602B (en) | 2020-05-12 |
Family
ID=68547618
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN201910686317.8A Active CN110489602B (en) | 2019-07-25 | 2019-07-25 | Knowledge point capability value estimation method, system, device and medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN110489602B (en) |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN112115274A (en) * | 2020-09-16 | 2020-12-22 | 上海松鼠课堂人工智能科技有限公司 | Knowledge graph generation system considering time influence and block chain naming system |
| WO2022042149A1 (en) * | 2020-08-31 | 2022-03-03 | 上海松鼠课堂人工智能科技有限公司 | Intelligent adaptive homework system suitable for omo learning scenario |
Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004807A (en) * | 2006-01-17 | 2007-07-25 | 欧姆龙株式会社 | Factor estimating device, method and program recording medium therefor |
| US20150169544A1 (en) * | 2013-12-12 | 2015-06-18 | International Business Machines Corporation | Generating a Superset of Question/Answer Action Paths Based on Dynamically Generated Type Sets |
| CN105373547A (en) * | 2014-08-25 | 2016-03-02 | 北大方正集团有限公司 | Knowledge point importance calculation method and apparatus |
| CN107103000A (en) * | 2016-02-23 | 2017-08-29 | 广州启法信息科技有限公司 | It is a kind of based on correlation rule and the integrated recommended technology of Bayesian network |
| CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
| CN108830763A (en) * | 2018-07-19 | 2018-11-16 | 刘洋 | A kind of visualizing multidimensional knowledge management and learning system |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
| CN109636229A (en) * | 2018-12-20 | 2019-04-16 | 广东小天才科技有限公司 | Learning effect evaluation method and electronic equipment |
| CN110046235A (en) * | 2019-03-18 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of knowledge base appraisal procedure, device and equipment |
-
2019
- 2019-07-25 CN CN201910686317.8A patent/CN110489602B/en active Active
Patent Citations (9)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN101004807A (en) * | 2006-01-17 | 2007-07-25 | 欧姆龙株式会社 | Factor estimating device, method and program recording medium therefor |
| US20150169544A1 (en) * | 2013-12-12 | 2015-06-18 | International Business Machines Corporation | Generating a Superset of Question/Answer Action Paths Based on Dynamically Generated Type Sets |
| CN105373547A (en) * | 2014-08-25 | 2016-03-02 | 北大方正集团有限公司 | Knowledge point importance calculation method and apparatus |
| CN107103000A (en) * | 2016-02-23 | 2017-08-29 | 广州启法信息科技有限公司 | It is a kind of based on correlation rule and the integrated recommended technology of Bayesian network |
| CN109388744A (en) * | 2017-08-11 | 2019-02-26 | 北京龙之门网络教育技术股份有限公司 | A kind of adaptive learning recommended method and device |
| CN107784088A (en) * | 2017-09-30 | 2018-03-09 | 杭州博世数据网络有限公司 | The knowledge mapping construction method of knowledge based point annexation |
| CN108830763A (en) * | 2018-07-19 | 2018-11-16 | 刘洋 | A kind of visualizing multidimensional knowledge management and learning system |
| CN109636229A (en) * | 2018-12-20 | 2019-04-16 | 广东小天才科技有限公司 | Learning effect evaluation method and electronic equipment |
| CN110046235A (en) * | 2019-03-18 | 2019-07-23 | 阿里巴巴集团控股有限公司 | A kind of knowledge base appraisal procedure, device and equipment |
Non-Patent Citations (1)
| Title |
|---|
| ANDREW H.GOLD 等: "Knowledge Management：An Organizational Capabilities Perspective", 《JOURNAL OF MANAGEMENT OF INFORMATION SYSTEMS》 * |
Cited By (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| WO2022042149A1 (en) * | 2020-08-31 | 2022-03-03 | 上海松鼠课堂人工智能科技有限公司 | Intelligent adaptive homework system suitable for omo learning scenario |
| CN112115274A (en) * | 2020-09-16 | 2020-12-22 | 上海松鼠课堂人工智能科技有限公司 | Knowledge graph generation system considering time influence and block chain naming system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN110489602B (en) | 2020-05-12 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| Venturini et al. | Plssem: a stata package for structural equation modeling with partial least squares | |
| Hox et al. | How few countries will do? Comparative survey analysis from a Bayesian perspective | |
| West et al. | Model fit and model selection in structural equation modeling | |
| Rangel et al. | Towards an integrated computational tool for spatial analysis in macroecology and biogeography | |
| JP4627674B2 (en) | Data processing method and program | |
| CN112328891B (en) | Method for training search model, method for searching target object and device thereof | |
| US10140336B1 (en) | Accuracy testing of query optimizers | |
| Venanzi et al. | Trust-based fusion of untrustworthy information in crowdsourcing applications | |
| CN110442516B (en) | Information processing method, apparatus, and computer-readable storage medium | |
| CN109522972A (en) | A kind of dynamic process monitoring method based on latent variable autoregression model | |
| CN111537884B (en) | Method and device for acquiring service life data of power battery, computer equipment and medium | |
| Altomare et al. | Objective Bayesian search of Gaussian directed acyclic graphical models for ordered variables with non‐local priors | |
| CN113484813B (en) | Intelligent ammeter fault rate prediction method and system under multi-environment stress | |
| CN110489602A (en) | Knowledge point ability value predictor method, system, equipment and medium | |
| US20100235151A1 (en) | Feature parameter candidate generation apparatus and feature parameter candidate generation method | |
| KR20220024056A (en) | Method of Echo Signal Characteristics Parametric-Based Transducer Coherence Evaluation Method | |
| CN111782805A (en) | Text label classification method and system | |
| CN114513374B (en) | Network security threat identification method and system based on artificial intelligence | |
| CN113345588A (en) | Rapid attribute reduction method for incomplete data set | |
| Peng et al. | Uck-means: A customized k-means for clustering uncertain measurement data | |
| CN107390189A (en) | Multifunction radar behavior identification and method for quick predicting under the conditions of low prior information | |
| CN114416570B (en) | Equivalent variant detection method based on weighted software behavior diagram | |
| CN107977680A (en) | A kind of method of the sparse reconstruct of signal | |
| CN111507639B (en) | Financing risk analysis method and device | |
| Jennings et al. | Evaluation of model-data fit by comparing parametric and nonparametric item response functions: Application of a Tukey-Hann Procedure |
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 | ||
| GR01 | Patent grant | ||
| GR01 | Patent grant | ||
| CP01 | Change in the name or title of a patent holder | ||
| CP01 | Change in the name or title of a patent holder |
Address after: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai 200000 Patentee after: Shanghai squirrel classroom Artificial Intelligence Technology Co., Ltd Address before: Room B381, 588 Tianlin East Road, Xuhui District, Shanghai 200000 Patentee before: SHANGHAI YIXUE EDUCATION TECHNOLOGY Co.,Ltd. |