CN110489602B - Knowledge point capability value estimation method, system, device and medium - Google Patents
Knowledge point capability value estimation method, system, device and medium Download PDFInfo
- Publication number
- CN110489602B CN110489602B CN201910686317.8A CN201910686317A CN110489602B CN 110489602 B CN110489602 B CN 110489602B CN 201910686317 A CN201910686317 A CN 201910686317A CN 110489602 B CN110489602 B CN 110489602B
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- value
- now
- new
- target
- 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.)
- Active
Links
- 238000000034 method Methods 0.000 title claims abstract description 38
- 108010074506 Transfer Factor Proteins 0.000 claims abstract description 23
- 101100273916 Schizosaccharomyces pombe (strain 972 / ATCC 24843) wip1 gene Proteins 0.000 claims description 16
- 238000012545 processing Methods 0.000 claims description 15
- 238000004364 calculation method Methods 0.000 claims description 13
- 238000004590 computer program Methods 0.000 claims description 10
- 238000013075 data extraction Methods 0.000 claims description 10
- 230000008569 process Effects 0.000 claims description 10
- 239000000284 extract Substances 0.000 claims description 5
- 239000004576 sand Substances 0.000 claims description 2
- 238000012360 testing method Methods 0.000 description 10
- 238000010586 diagram Methods 0.000 description 2
- 230000004044 response Effects 0.000 description 2
- 238000013459 approach Methods 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 238000011161 development Methods 0.000 description 1
- 238000005265 energy consumption Methods 0.000 description 1
- 238000005516 engineering process Methods 0.000 description 1
- 230000006870 function Effects 0.000 description 1
- 230000003993 interaction Effects 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
Images
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 a method, a system, equipment and a medium for estimating the ability value of a knowledge point, wherein the method comprises the steps of extracting the ability value vector of a source knowledge point from a preset database; calculating a transfer factor between the target knowledge point and the source knowledge point; calculating a new capability value vector of the target knowledge point; updating the capability value vector of the target knowledge point in the preset database; acquiring the estimated capacity value of the target knowledge point according to the updated capacity value vector of the target knowledge point; and extracting the capability value vector of the next source knowledge point from the preset database. The invention can predict the capacity value of the post knowledge point through the known capacity value vector of the knowledge point by utilizing the context between the knowledge points in the knowledge map, can quickly predict the capacity value of the knowledge point in the knowledge map, and has high accuracy of the predicted capacity value on the unlearned knowledge point.
Description
Technical Field
The invention belongs to the technical field of computers, and particularly relates to a knowledge point capacity value estimation method, a knowledge point capacity value estimation system, knowledge point capacity value estimation equipment and a knowledge point capacity value estimation medium.
Background
With the development of technology, online education has become a current and important education mode, and in online education software developed by large enterprises, most of users need to collect capability value data of each knowledge point on a knowledge point map, and then arrange operations such as learning planning, topic test and the like according to the capability value data, and the capability value reflected by the user on the knowledge point is mainly obtained based on a project reflection theory.
The item reflection theory is a general term of a series of psychology statistical models, and aims to determine whether the potential characteristics and the interaction relationship between the test questions and the tested person (the mastery degree of the user can be regarded as the potential characteristics) can be reflected by the test questions.
Project response theory assumes that the testee has a "potential trait," which is a statistical idea proposed on the basis of observing, analyzing and testing responses, and in testing, the potential trait generally refers to potential ability, and the total score of the test is often used as an estimate of the potential. The project reaction theory considers that the reaction and the achievement of the tested person on the test project have special relation with the potential characteristics of the tested person. The project parameters established by the project reaction theory have the characteristic of permanence, which means that the scores of different measurement scales can be unified.
the curve drawn according to the above model formula is also referred to as a project characteristic curve, and is meant to describe the relationship between the "probability of successfully solving a particular test project" and the "ability of the testee" (i.e., θ in the formula).
The parameters contained in the above formula are explained as follows:
c represents a 'guess parameter', and intuitively means that when the ability value of a tested person is very low (such as close to 0), the probability that the item can be correctly done is still achieved;
b represents a project difficulty parameter, and according to the movement characteristic of the function, changing b can cause the image to move left and right without changing the shape;
a represents the discrimination of the item, i.e. whether one item can well discriminate different testees, and the higher the value of a, the more discriminating the item.
In the above description of the project reflection theory, it can be known that the project reflection theory only responds to the same project, that is, when a user learns a certain project, the current project generates feedback, and other projects do not change.
However, in the field of education, knowledge points are all related to each other. For example, after a user learns the "definition of equation" knowledge point, the user has the basic knowledge of the "solution of unary linear equation" of the relevant knowledge point, and the "solution of unary linear equation" is no longer completely new for the user.
In the prior art, each knowledge point needs to be tested in advance to roughly know the ability value of the user at the knowledge point, the number of the knowledge points is often huge, and the testing method is inefficient and tedious. If the tested knowledge points are not learned by the user, the user lacks initiative in testing, and it is difficult to accurately obtain the data of the ability values of the user on the unlearned knowledge points.
Disclosure of Invention
The technical problem to be solved by the present invention is to provide a method, a system, a device and a medium for estimating the knowledge point capability value, which can estimate the capability value of the knowledge point in the knowledge map quickly by estimating the capability value of the post-knowledge point through the known capability value vector of the knowledge point by using the context between the knowledge points in the knowledge map, and the accuracy of the estimated capability value on the unlearned knowledge point is high.
In order to solve the above technical problem, a first aspect of the present invention provides a method for estimating a knowledge point capability value, including the following steps:
step one, extracting a capability value vector V of a source knowledge point from a preset databaseS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)];
Step two, calculating a transfer factor delta between a target knowledge point and a source knowledge point, wherein the target knowledge point is a post knowledge point associated with the source knowledge point in a knowledge point map, and the calculation process of the transfer factor delta comprises the following steps:
step 201, collecting a shortest path S between a target knowledge point and a source knowledge point according to a knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
step 202, extracting a difficulty value d of a source knowledge point from a preset database, wherein d is more than 0 and less than 1;
step three, calculating a new capability value vector V of the target knowledge pointnew,Vnew=VSX δ; after the calculation is finished, extracting VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
Step four, extracting the current ability value vector V of the target knowledge point from the preset databasenowExtracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN),
Calculating (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN),
By calculating the result to obtain new (P)now1、Pnow2、Pnow3、...PnowN);
Will be new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowObtaining updated Vnow(ii) a V after updatingnowReturning to a preset database;
step five, finding out the updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point;
step six, extracting the capability value vector V of the next source knowledge point from the preset databaseSAnd then executing the step two to the step five.
Further, in the fourth step, the current ability value vector V of the target knowledge point is extracted from the preset databasenowIf the preset database does not store the capability value vector VnowIn the third step VnewAs updated VnowAnd will VnowAnd returning to the preset database.
Further, when the number of the P with the largest numerical value found in the fifth step is more than one, taking the average value of a plurality of θ corresponding to the plurality of P as the estimated capability value of the current target knowledge point.
The second aspect of the present invention provides a knowledge point capability value estimation system, including:
data extraction unitVector of capability values V for extracting source knowledge points from a preset databaseS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)](ii) a New capability value vector V for extracting target knowledge pointsnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN) The target knowledge point is a post knowledge point associated with the source knowledge point in the knowledge point map; used for extracting the current ability value vector V of the target knowledge point from the preset databasenowAnd extracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN) (ii) a The difficulty value d is used for extracting the source knowledge points from the preset database, and d is more than 0 and less than 1;
the data acquisition unit is used for acquiring the shortest path S between the target knowledge point and the source knowledge point according to the knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
a data processing unit for calculating a transfer factor delta between the target knowledge point and the source knowledge point,new capability value vector V for computing target knowledge pointsnew,Vnew=VSX δ; for calculating (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN) To obtain new (P)now1、Pnow2、Pnow3、...PnowN) (ii) a For mixing new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowTo V pairnowUpdating and updating the updated VnowReturning to a preset database; for finding updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the corresponding theta according to the P with the maximum numerical value, wherein the theta is the current target knowledge pointAnd estimating the capacity value.
Further, the data extraction unit extracts the current ability value vector V of the target knowledge point from the preset databasenowIf the preset database does not store the capability value vector VnowThen, the data processing unit calculates a new capability value vector V of the target knowledge point according to the new capability value vector VnewAs updated VnowAnd will update the VnowAnd returning to the preset database.
Further, when the number of the P with the largest value found by the data processing unit is greater than one, taking the average value of a plurality of θ corresponding to the plurality of P as the estimated capability value of the current target knowledge point.
The third aspect of the present invention further provides a knowledge point capability value estimation apparatus, including a memory, a processor, and a computer program stored in the memory and executable on the processor, where the processor implements the steps of the method according to the first aspect or any implementation manner of the first aspect when executing the computer program.
The fourth aspect of the present invention further provides a computer-readable storage medium, which stores a computer program, and the computer program, when executed by a processor, implements the steps of the method according to the first aspect or any implementation manner of the first aspect.
The fifth aspect of the present invention further provides a knowledge point capability value estimation method, including the following steps:
step one, extracting a capability value vector V of a source knowledge point from a preset databaseS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)];
Step two, calculating a transfer factor delta between a target knowledge point and a source knowledge point, wherein the target knowledge point is a post knowledge point associated with the source knowledge point in a knowledge point map, and the calculation process of the transfer factor delta comprises the following steps:
step 201, collecting a shortest path S between a target knowledge point and a source knowledge point according to a knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
step 202, extracting a difficulty value d of a source knowledge point from a preset database, wherein d is more than 0 and less than 1;
step three, calculating a new capability value vector V of the target knowledge pointnew,Vnew=VSX δ; after the calculation is finished, extracting VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
Step four, finding out (P)new1、Pnew2、Pnew3、...PnewN) And finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point.
Further, when the number of the P with the largest numerical value found in the fourth step is greater than one, taking the average value of the multiple θ corresponding to the multiple P as the estimated capability value of the current target knowledge point.
Compared with the prior art, the invention has the following advantages:
1. the method can estimate the capacity value of the post knowledge point associated with the source knowledge point through the capacity value vector of the source knowledge point in the knowledge point map, and compared with the prior art that the capacity values are acquired one by one for each knowledge point in the knowledge point map in a data buried point acquisition mode, the method can greatly save the acquisition time of each knowledge point capacity value in the knowledge point map.
2. Compared with the prior art that the capacity value of the unlearned knowledge point is calculated by adopting a project reflection theory, the invention reduces the energy consumption required by the computer calculation, and particularly can obviously shorten the calculation time when the capacity value of the knowledge point in the whole knowledge point map is calculated.
3. The invention is to transmitExpressing the association degree between the source knowledge point and the target knowledge point by a factor delta, and adopting the difficulty value d of the source knowledge point, the shortest path S between the source knowledge point and the target knowledge point and the node entry degree lambda between the target knowledge points as variables of a transfer factor delta; the higher the difficulty value d of the source knowledge point is, the later the position of the source knowledge point in the knowledge point map is, and the higher the probability of the high relevance between the target knowledge point and the source knowledge point is further illustrated; the smaller the shortest path S between the source knowledge point and the target knowledge point is, the higher the relevance between the target knowledge point and the source knowledge point is; the smaller the node entrance degree lambda between the target knowledge points is, the smaller the number of the preposed knowledge points of the target knowledge points is, and the higher the relevance between the source knowledge points and the target knowledge points is further illustrated; so as to transmit factorThe association degree between the source knowledge point and the target knowledge point can be measured. Finally substituting the transfer factor delta into the capability value vector V of the source knowledge pointSObtaining a vector V of the estimated ability value of the target knowledge pointnewAnd with VnewThe probability data P in (1) to the original ability value vector V of the target knowledge pointnowIf a target knowledge point is more than one preceding source knowledge point, the capability value vector V is adjustednowThe probability data P tends to be more accurate and accurate after being adjusted for many times, and then the capability value theta found out according to the probability data P can more accurately reflect the capability of the user on the target knowledge point.
The technical solution of the present invention is further described in detail by the accompanying drawings and embodiments.
Drawings
FIG. 1 is a schematic diagram of a knowledge point map.
FIG. 2 is a schematic flow chart of the method of the present invention.
Detailed Description
Example 1
The method for estimating the knowledge point capability value, as shown in fig. 2, includes the following steps:
step one, extracting one from a preset databaseVector of capability values V of individual source knowledge pointsSVector of capability values VSIs an N-dimensional vector, VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)](ii) a It is assumed here that a vector of capability values for a certain source knowledge point
VS=[(0.2,0.1)、(0.4,0.2)、(0.1,0.3)、(0.2,0.4)(0.3,0.5)];
Wherein P iss1=0.2,θs1When the value is 0.1, the probability representing that the ability value of the user on the source knowledge point is 0.1 is 0.2;
step two, calculating a transfer factor delta between a target knowledge point and a source knowledge point, wherein the target knowledge point is a post knowledge point associated with the source knowledge point in a knowledge point map, fig. 1 is a schematic diagram of the knowledge point map, and the calculation process of the transfer factor delta comprises the following steps:
step 201, collecting a shortest path S between a target knowledge point and a source knowledge point according to a knowledge point map; as shown in fig. 1, the shortest path S between the destination knowledge point 3 and the source knowledge point is 1, and the shortest path S between the destination knowledge point 2 and the source knowledge point is 2; acquiring the node degree lambda of a target knowledge point according to a knowledge point map; the node degree λ refers to how many paths point to the knowledge point, and as shown in fig. 1, the node degree λ of the target knowledge point 3 is 2, and the node degree λ of the target knowledge point 2 is 1; it should be noted that, the smaller the value of the shortest path S is, the more closely the association between the target knowledge point and the source knowledge point is; the smaller the value of the node approach lambda is, the smaller the number of the preposed knowledge points of the target knowledge point is, and further, the tighter the association between the target knowledge point and the source knowledge point is;
step 202, extracting a difficulty value d of a source knowledge point from a preset database, wherein d is more than 0 and less than 1; it should be noted that the higher the difficulty of a knowledge point, the later the position of the knowledge point in the knowledge point map is, for example, the difficulty of the knowledge point calculus is far higher than that of the knowledge point addition, and the number of the postamble knowledge points of the knowledge point addition is far greater than that of the postamble knowledge points of the knowledge point calculus; the higher the difficulty of the source knowledge point is, the smaller the number of the post knowledge points is, namely, the smaller the number of the target knowledge points associated with the source knowledge point is, and further, the closer the association between the target knowledge points and the source knowledge points is;
step 203, according toCalculating a transfer factor delta; the transfer factor delta is a parameter reflecting the degree of association between the target knowledge point and the source knowledge point;
step three, calculating a new capability value vector V of the target knowledge pointnew,Vnew=VSX δ; after the calculation is finished, extracting VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
Step four, extracting the current ability value vector V of the target knowledge point from the preset databasenowExtracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN),
Calculating (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN) The new (P) is obtained by calculating the resultnow1、Pnow2、Pnow3、...PnowN);
Will be new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowObtaining updated Vnow(ii) a V after updatingnowReturning to a preset database;
step five, finding out the updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point;
step six, extracting the capability value vector V of the next source knowledge point from the preset databaseSThen, the step two is executedAnd step five.
It should be noted that there is the ability to value vector V in the knowledge point mapSAll the knowledge points can be used as source knowledge points; that is, for a certain knowledge point, the knowledge point is used as a source knowledge point in the process of executing the method steps from the second step to the fifth step, and the knowledge point can be a target knowledge point in the process of executing the method steps from the second step to the fifth step.
In this embodiment, in step four, the current capability value vector V of the target knowledge point is extracted from the preset databasenowIf the preset database does not store the capability value vector VnowV in the third stepnewAs updated VnowAnd will VnowAnd returning to the preset database.
In this embodiment, when the number of P with the largest value found in the fifth step is greater than one, the average value of θ corresponding to P is taken as the estimated capability value of the current target knowledge point.
It should be noted that, in the execution process of the steps of the method, every time the steps from two to five are executed, the capability values of all post-knowledge points of the source knowledge point selected in the execution process of this time are updated once.
Example 2
Knowledge point capability value estimation system includes: the device comprises a data extraction unit, a data acquisition unit and a data processing unit.
The operation process of the prediction system when predicting the knowledge point capability is as follows: here, the estimation of the ability value of the target knowledge point 3 in the knowledge point map shown in fig. 1 is taken as an example for explanation;
the data extraction unit extracts the capability value vector V of the source knowledge point from the preset databaseSVector of capability values VSIs an N-dimensional vector, VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)];
The data acquisition unit acquires a shortest path S between the target knowledge point and the source knowledge point according to the knowledge point map, as shown in fig. 1, in this embodiment, the shortest path S between the target knowledge point 3 and the source knowledge point is 1;
the data acquisition unit acquires the node degree lambda of the target knowledge point 3 according to the knowledge point map; the node degree λ refers to how many paths point to the knowledge point, and as shown in fig. 1, the node degree λ of the target knowledge point 3 is 2;
the data processing unit calculates a transfer factor delta between the target knowledge point and the source knowledge point,here, the transfer factor δ is a parameter that reflects the degree of association between the target knowledge point 3 and the source knowledge point;
the data processing unit calculates a new capability value vector V for the target knowledge point 3new,Vnew=VSX δ; after the calculation is completed, the data extraction unit extracts VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
The data extraction unit judges whether the preset database stores the current ability value vector V of the target knowledge point 3nowIf yes, extracting the current ability value vector V of the target knowledge point from the preset databasenowExtracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN);
Data processing unit calculates (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN) The new (P) is obtained by calculating the resultnow1、Pnow2、Pnow3、...PnowN);
The data processing unit will be new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowObtaining updated Vnow(ii) a V after updatingnowReturning to the preset database, and updating the V previously stored in the preset databasenow;
Data processing unit finds updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point 3;
the data extraction unit then extracts the capability value vector V of the next source knowledge point from the preset databaseSAs shown in fig. 1, the target knowledge point 1 and the target knowledge point 2 in fig. 1 may be used as the next source knowledge point, and it can be seen from fig. 1 that the target knowledge point 2 is a post-knowledge point of the target knowledge point 1, so it is preferable that the next source knowledge point selects the target knowledge point 1.
In this embodiment, the data extraction unit determines whether the preset database stores the current ability value vector V of the target knowledge point 3nowIf not, the data processing unit calculates a new capability value vector V of the target knowledge point 3newAs updated VnowReturns to the preset database, and the data processing unit finds the updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) And finding out the value theta corresponding to the maximum value P according to the maximum value P, wherein the theta is the estimated capacity value of the current target knowledge point 3.
In this embodiment, when the number of the P with the largest value found by the data processing unit is greater than one, the average value of the θ corresponding to the P is taken as the estimated capability value of the current target knowledge point.
Example 3
Knowledge point capability value estimation device comprises a memory, a processor and a computer program stored in the memory and capable of running on the processor, wherein the processor implements the steps of the method of the embodiment 1 when executing the computer program.
Example 4
A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method of embodiment 1.
The above description is only a preferred embodiment of the present invention, and is not intended to limit the present invention, and all simple modifications, changes and equivalent structural changes made to the above embodiment according to the technical spirit of the present invention still fall within the protection scope of the technical solution of the present invention.
Claims (10)
1. The method for estimating the knowledge point capability value is characterized by comprising the following steps: the method comprises the following steps:
step one, extracting a capability value vector V of a source knowledge point from a preset databaseS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)]Theta is the ability value, and P is the probability that the user ability value is theta;
step two, calculating a transfer factor delta between a target knowledge point and a source knowledge point, wherein the target knowledge point is a post knowledge point associated with the source knowledge point in a knowledge point map, and the calculation process of the transfer factor delta comprises the following steps:
step 201, collecting a shortest path S between a target knowledge point and a source knowledge point according to a knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
step 202, extracting a difficulty value d of a source knowledge point from a preset database, wherein d is more than 0 and less than 1;
step three, calculating a new capability value vector V of the target knowledge pointnew,Vnew=VSX δ; after the calculation is finished, extracting VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
Step four, extracting the current ability value vector V of the target knowledge point from the preset databasenowExtracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN),
Calculating (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN),
By calculating the result to obtain new (P)now1、Pnow2、Pnow3、...PnowN);
Will be new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowObtaining updated Vnow(ii) a V after updatingnowReturning to a preset database;
step five, finding out the updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point;
step six, extracting the capability value vector V of the next source knowledge point from the preset databaseSAnd then executing the step two to the step five.
2. The method of estimating knowledge point capability value of claim 1, wherein: step four, extracting the current ability value vector V of the target knowledge point from the preset databasenowIf the preset database does not store the capability value vector VnowIn the third step VnewAs updated VnowAnd will VnowAnd returning to the preset database.
3. The method of estimating knowledge point capability value of claim 1, wherein: and when the number of the P with the largest numerical value found in the step five is more than one, taking the average value of a plurality of theta corresponding to the plurality of P as the estimated capacity value of the current target knowledge point.
4. Knowledge point capability value estimation system, characterized by, includes:
a data extraction unit for extracting capability values of the source knowledge points from a preset databaseVector VS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)]Theta is the ability value, and P is the probability that the user ability value is theta; new capability value vector V for extracting target knowledge pointsnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN) The target knowledge point is a post knowledge point associated with the source knowledge point in the knowledge point map; used for extracting the current ability value vector V of the target knowledge point from the preset databasenowAnd extracting VnowOf (1) to obtain (P)now1、Pnow2、Pnow3、...PnowN) (ii) a The difficulty value d is used for extracting the source knowledge points from the preset database, and d is more than 0 and less than 1;
the data acquisition unit is used for acquiring the shortest path S between the target knowledge point and the source knowledge point according to the knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
a data processing unit for calculating a transfer factor delta between the target knowledge point and the source knowledge point,new capability value vector V for computing target knowledge pointsnew,Vnew=VSX δ; for calculating (P)new1×Pnow1、Pnew2×Pnow2、Pnew3×Pnow3、...PnewN×PnowN) To obtain new (P)now1、Pnow2、Pnow3、...PnowN) (ii) a For mixing new (P)now1、Pnow2、Pnow3、...PnowN) Return to ability value vector VnowTo V pairnowUpdating and updating the updated VnowReturning to a preset database; for finding updated VnowIn (P)now1、Pnow2、Pnow3、...PnowN) Finding out the corresponding theta according to the P with the maximum numerical value, wherein the theta is the current target knowledge pointAnd estimating the capacity value.
5. The system of estimating knowledge point capability values of claim 4, wherein: the data extraction unit extracts the current ability value vector V of the target knowledge point from a preset databasenowIf the preset database does not store the capability value vector VnowThen, the data processing unit calculates a new capability value vector V of the target knowledge point according to the new capability value vector VnewAs updated VnowAnd will update the VnowAnd returning to the preset database.
6. The system of estimating knowledge point capability values of claim 4, wherein: and when the number of the P with the largest numerical value found by the data processing unit is more than one, taking the average value of a plurality of theta corresponding to the plurality of P as the estimated capacity value of the current target knowledge point.
7. Knowledge point capability value estimation device comprising a memory, a processor and a computer program stored in said memory and executable on said processor, characterized in that said processor implements the steps of the method according to claim 1, 2 or 3 when executing said computer program.
8. Computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the steps of the method according to claim 1, 2 or 3.
9. The method for estimating the knowledge point capability value is characterized by comprising the following steps: the method comprises the following steps:
step one, extracting a capability value vector V of a source knowledge point from a preset databaseS,VS=[(Ps1,θs1)、(Ps2,θs2)、(Ps3,θs3)、...(PsN,θsN)]Theta is the ability value, and P is the probability that the user ability value is theta;
step two, calculating a transfer factor delta between a target knowledge point and a source knowledge point, wherein the target knowledge point is a post knowledge point associated with the source knowledge point in a knowledge point map, and the calculation process of the transfer factor delta comprises the following steps:
step 201, collecting a shortest path S between a target knowledge point and a source knowledge point according to a knowledge point map; acquiring the node degree lambda of a target knowledge point according to a knowledge point map;
step 202, extracting a difficulty value d of a source knowledge point from a preset database, wherein d is more than 0 and less than 1;
step three, calculating a new capability value vector V of the target knowledge pointnew,Vnew=VSX δ; after the calculation is finished, extracting VnewOf (1) to obtain (P)new1、Pnew2、Pnew3、...PnewN);
Step four, finding out (P)new1、Pnew2、Pnew3、...PnewN) And finding out the theta corresponding to the P with the maximum numerical value according to the P, wherein the theta is the estimated capacity value of the current target knowledge point.
10. The method of estimating knowledge point capability value of claim 9, wherein: and when the number of the P with the largest numerical value found in the fourth step is more than one, taking the average value of a plurality of theta corresponding to the plurality of P as the estimated capacity value of the current target knowledge point.
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 CN110489602A (en) | 2019-11-22 |
CN110489602B true 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) |
Families Citing this family (2)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
CN112085630B (en) * | 2020-08-31 | 2021-06-29 | 上海松鼠课堂人工智能科技有限公司 | Intelligent adaptive operation system suitable for OMO learning scene |
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 |
Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Family Cites Families (6)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
JP5002963B2 (en) * | 2006-01-17 | 2012-08-15 | オムロン株式会社 | Factor estimation device, factor estimation program, recording medium storing factor estimation program, and factor estimation method |
US9971967B2 (en) * | 2013-12-12 | 2018-05-15 | 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 |
-
2019
- 2019-07-25 CN CN201910686317.8A patent/CN110489602B/en active Active
Patent Citations (3)
Publication number | Priority date | Publication date | Assignee | Title |
---|---|---|---|---|
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 |
Also Published As
Publication number | Publication date |
---|---|
CN110489602A (en) | 2019-11-22 |
Similar Documents
Publication | Publication Date | Title |
---|---|---|
Bøttcher et al. | deal: A package for learning Bayesian networks | |
Hoyle | Structural equation modeling for social and personality psychology | |
CN110046706B (en) | Model generation method and device and server | |
WO2023115761A1 (en) | Event detection method and apparatus based on temporal knowledge graph | |
CN109190537A (en) | A kind of more personage's Attitude estimation methods based on mask perceived depth intensified learning | |
CN107730131B (en) | Capability prediction and recommendation method and device for crowdsourced software developers | |
CN103415825A (en) | System and method for gesture recognition | |
CN110147428B (en) | Method, device, equipment and storage medium for updating knowledge point mastery degree | |
CN110489602B (en) | Knowledge point capability value estimation method, system, device and medium | |
JP2020091543A (en) | Learning device, processing device, neural network, learning method, and program | |
CN113409174A (en) | Knowledge point evaluation method and device | |
CN115545300B (en) | Method and device for predicting user behavior based on graph neural network | |
CN112580896A (en) | Knowledge point prediction method, knowledge point prediction device, knowledge point prediction equipment and storage medium | |
CN116306863A (en) | Collaborative knowledge tracking modeling method and system based on contrast learning | |
CN111444075A (en) | Method for automatically discovering key influence indexes | |
CN113239669B (en) | Test Question Difficulty Prediction Method | |
CN113743572A (en) | Artificial neural network testing method based on fuzzy | |
CN111639194B (en) | Knowledge graph query method and system based on sentence vector | |
CN113537693A (en) | Personnel risk level obtaining method, terminal and storage device | |
CN110070120B (en) | Depth measurement learning method and system based on discrimination sampling strategy | |
US20220343216A1 (en) | Information processing apparatus and information processing method | |
CN112241447B (en) | Learning situation data processing method and device, computer equipment and storage medium | |
CN108921434A (en) | A method of user capability prediction is completed by human-computer interaction | |
CN115129834A (en) | Question answering method and system | |
CN112861689A (en) | Searching method and device of coordinate recognition model based on NAS technology |
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. |