CN111897945B - Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics - Google Patents
Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics Download PDFInfo
- Publication number
- CN111897945B CN111897945B CN202010646225.XA CN202010646225A CN111897945B CN 111897945 B CN111897945 B CN 111897945B CN 202010646225 A CN202010646225 A CN 202010646225A CN 111897945 B CN111897945 B CN 111897945B
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- knowledge
- architecture
- points
- network model
- 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 50
- 238000002372 labelling Methods 0.000 title claims abstract description 28
- 230000006870 function Effects 0.000 claims description 54
- 238000004590 computer program Methods 0.000 claims description 13
- 238000005516 engineering process Methods 0.000 abstract description 6
- 238000004364 calculation method Methods 0.000 abstract description 3
- 238000010586 diagram Methods 0.000 description 10
- 238000012360 testing method Methods 0.000 description 4
- 239000011159 matrix material Substances 0.000 description 3
- 230000008569 process Effects 0.000 description 3
- 238000004422 calculation algorithm Methods 0.000 description 2
- 230000004048 modification Effects 0.000 description 2
- 238000012986 modification Methods 0.000 description 2
- 230000003287 optical effect Effects 0.000 description 2
- 238000012545 processing Methods 0.000 description 2
- 238000012549 training Methods 0.000 description 2
- 230000006978 adaptation Effects 0.000 description 1
- 230000009286 beneficial effect Effects 0.000 description 1
- 230000005540 biological transmission Effects 0.000 description 1
- 230000008859 change Effects 0.000 description 1
- 230000006872 improvement Effects 0.000 description 1
- 238000005259 measurement Methods 0.000 description 1
- 230000004044 response Effects 0.000 description 1
- 230000003068 static effect Effects 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
- G06F16/33—Querying
- G06F16/335—Filtering based on additional data, e.g. user or group profiles
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06F—ELECTRIC DIGITAL DATA PROCESSING
- G06F18/00—Pattern recognition
- G06F18/20—Analysing
- G06F18/24—Classification techniques
- G06F18/241—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches
- G06F18/2415—Classification techniques relating to the classification model, e.g. parametric or non-parametric approaches based on parametric or probabilistic models, e.g. based on likelihood ratio or false acceptance rate versus a false rejection rate
- G06F18/24155—Bayesian classification
-
- 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)
- Business, Economics & Management (AREA)
- Theoretical Computer Science (AREA)
- Physics & Mathematics (AREA)
- Data Mining & Analysis (AREA)
- General Physics & Mathematics (AREA)
- General Engineering & Computer Science (AREA)
- Tourism & Hospitality (AREA)
- Strategic Management (AREA)
- Educational Technology (AREA)
- Educational Administration (AREA)
- Bioinformatics & Computational Biology (AREA)
- Economics (AREA)
- Evolutionary Biology (AREA)
- Computer Vision & Pattern Recognition (AREA)
- Bioinformatics & Cheminformatics (AREA)
- Artificial Intelligence (AREA)
- Life Sciences & Earth Sciences (AREA)
- Probability & Statistics with Applications (AREA)
- Health & Medical Sciences (AREA)
- Evolutionary Computation (AREA)
- General Health & Medical Sciences (AREA)
- Human Resources & Organizations (AREA)
- Marketing (AREA)
- Primary Health Care (AREA)
- General Business, Economics & Management (AREA)
- Computational Linguistics (AREA)
- Databases & Information Systems (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application provides a method, a device, equipment and a medium for marking and pushing topics of a front knowledge point. The labeling method of the prepositioned knowledge points comprises the following steps: inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model; performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; wherein the second knowledge point architecture is annotated with a relationship of at least one knowledge point and a corresponding pre-knowledge point. Therefore, the marking of the front knowledge points of each knowledge point can be automatically completed, and on one hand, the time cost and the auditing cost of manual marking by a teacher can be reduced; on the other hand, compared with the method for obtaining the prepositioned knowledge points by carrying out similarity calculation on text information based on the knowledge points in the related technology, the technical scheme utilizes the answer data of students to reversely infer the prepositioned relations possibly existing between the knowledge points, avoids the mislabel condition that texts are similar and have no direct relation in practice, and improves the labeling accuracy.
Description
Technical Field
The present application relates to the field of data processing technologies, and in particular, to a method, an apparatus, a device, and a medium for labeling and question pushing of pre-knowledge points.
Background
The knowledge point is a basic unit in discipline learning, such as judgment of congruent triangle, property of congruent triangle, and the like, and is a knowledge point. When learning knowledge points, students often learn according to the chapter sequence of books. However, there is actually a complicated relationship between knowledge points, specifically, some knowledge points are the basis for learning other knowledge points, and these knowledge points as the learning basis of other knowledge points are called pre-knowledge points, but many knowledge points and their corresponding pre-knowledge points often have different textbooks, different grades, and even different learning segments. If the internal association among the knowledge points can be constructed, in particular to the association relationship between books and school segments, the method has important significance for helping students to better master the knowledge points and know the internal association among the knowledge points.
In the related art, a teacher with a relevant rich teaching background is invited to manually mark the relation between knowledge points, however, hundreds or even more knowledge points may exist in a certain discipline, and the relation between every two knowledge points may exist, which means that the teacher needs to spend a great deal of time to judge whether the relation exists between the knowledge points, and due to the overlarge quantity, the conditions of wrong marks, missed marks and the like are more likely to occur while consuming time; in another related art, automated labeling is achieved using similarity of texts identifying knowledge points, but only the similarity between texts is considered, and does not necessarily represent that they are relevant. Such as "historic meaning of the spicy revolution" and "historic meaning of the french great revolution" in the history discipline, these two knowledge points have the common text "historic meaning of the revolution", so that no matter what method is used to calculate the similarity, a conclusion that their similarity is very high can be obtained, but there is no direct connection between these two knowledge points. Therefore, the error caused by the automatic labeling of the knowledge point relation by using the method is large.
Disclosure of Invention
In order to overcome the problems in the related art, the application provides a method, a device, equipment and a medium for marking and pushing the topics of the preposed knowledge points.
According to a first aspect of an embodiment of the present application, there is provided a method for labeling a pre-knowledge point, the method including:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a second aspect of an embodiment of the present application, there is provided a method for pushing a question, the method including:
obtaining answer data of student users to each knowledge point;
acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture;
Pushing corresponding questions to the student users based on the mastery degree of the student users on each knowledge point;
the specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a third aspect of the embodiment of the present application, there is provided a labeling device for pre-knowledge points, the device including:
The input module is configured to input acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
The acquisition module is configured to perform structure learning on the Bayesian network model based on the answer data, and acquire a second knowledge point architecture; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a fourth aspect of an embodiment of the present application, there is provided a topic pushing device, including:
The first acquisition module is configured to acquire answer data of the student user on each knowledge point;
The second acquisition module is configured to acquire the mastery degree of each knowledge point of the student user based on the answer data and the appointed knowledge point architecture;
A pushing module configured to push corresponding topics to the student users based on the knowledge degree of the student users on each knowledge point;
the specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a fifth aspect of embodiments of the present application, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a sixth aspect of embodiments of the present application, there is provided a computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, the processor implementing the steps of:
obtaining answer data of student users to each knowledge point;
acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture;
Pushing corresponding questions to the student users based on the mastery degree of the student users on each knowledge point;
The specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower relationships among knowledge points, the second knowledge point architecture is marked with a prepositioned knowledge point of at least one knowledge point and a corresponding relationship, and the at least one knowledge point and the prepositioned knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to a seventh aspect of embodiments of the present application, there is provided a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to an eighth aspect of embodiments of the present application, there is provided a computer-readable storage medium having stored thereon a computer program which, when executed by a processor, performs the steps of:
obtaining answer data of student users to each knowledge point;
acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture;
Pushing corresponding questions to the student users based on the mastery degree of the student users on each knowledge point;
the specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
The technical scheme provided by the embodiment of the application can comprise the following beneficial effects:
According to the technical scheme, a large number of answer data of the student users for each knowledge point are collected and input into the Bayesian network model as sample data, and structure learning is carried out on the Bayesian network model based on the sample data, so that the answer data of the student users and the constructed Bayesian network model can be combined for learning to obtain a second knowledge point system structure, and potential prepositioned knowledge points of each knowledge point are marked in the knowledge point system structure. The constructed Bayesian network model comprises a first knowledge point architecture of the upper-lower relationship among knowledge points, and the marked knowledge points and the corresponding prepositioned knowledge points are the lowest-level knowledge points in the first knowledge point architecture. Therefore, the marking of the front knowledge points of each knowledge point can be automatically completed, and on one hand, the time cost and the auditing cost of manual marking by a teacher can be reduced; on the other hand, compared with the method for obtaining the prepositioned knowledge points by carrying out similarity calculation on the text information based on the knowledge points in the related technology, the technical scheme utilizes the answer data of students to reversely infer the prepositioned relations possibly existing between the knowledge points, can avoid the mislabel condition that texts are similar and have no direct relation in practice, and improves the labeling accuracy; and the knowledge points with the lowest level are found out, and the corresponding prepositive knowledge points are also the knowledge points with the lowest level, so that the prepositive relationship among specific knowledge points can be more intuitively known.
It is to be understood that both the foregoing general description and the following detailed description are exemplary and explanatory only and are not restrictive of the application as claimed.
Drawings
The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the application and together with the description, serve to explain the principles of the application.
Fig. 1 is a flowchart of a method for labeling pre-knowledge points according to an exemplary embodiment of the present application.
FIG. 2 is a partial schematic diagram of a knowledge point architecture, in accordance with an exemplary embodiment of the application.
Fig. 3 is a flowchart of a method for question pushing according to an exemplary embodiment of the present application.
Fig. 4 is a block diagram of a labeling device for pre-knowledge points according to an exemplary embodiment of the present application.
Fig. 5 is a block diagram illustrating a topic pushing device according to an exemplary embodiment of the present application.
Fig. 6 is a block diagram of a computer device according to an exemplary embodiment of the present application.
Fig. 7 is a block diagram of another computer device according to an exemplary embodiment of the present application.
Detailed Description
The following description of the embodiments of the present application will be made clearly and completely with reference to the accompanying drawings, in which it is apparent that the embodiments described are only some embodiments of the present application, but not all embodiments. All other embodiments, which can be made by those skilled in the art based on the embodiments of the application without making any inventive effort, are intended to be within the scope of the application.
Reference will now be made in detail to exemplary embodiments, examples of which are illustrated in the accompanying drawings. When the following description refers to the accompanying drawings, the same numbers in different drawings refer to the same or similar elements, unless otherwise indicated. The implementations described in the following exemplary examples do not represent all implementations consistent with the application. Rather, they are merely examples of apparatus and methods consistent with aspects of the application as detailed in the accompanying claims.
The terminology used herein is for the purpose of describing particular embodiments only and is not intended to be limiting of the application. As used in this specification and the appended claims, the singular forms "a," "an," and "the" are intended to include the plural forms as well, unless the context clearly indicates otherwise. It should also be understood that the term "and/or" as used herein refers to and encompasses any or all possible combinations of one or more of the associated listed items.
It should be understood that although the terms first, second, third, etc. may be used herein to describe various information, these information should not be limited by these terms. These terms are only used to distinguish one type of information from another. For example, first information may also be referred to as second information, and similarly, second information may also be referred to as first information, without departing from the scope of the application. The word "if" as used herein may be interpreted as "at … …" or "at … …" or "in response to a determination" depending on the context.
The method, the device, the computer equipment and the storage medium for labeling the prepositioned knowledge points and pushing the topics are described in detail below with reference to the accompanying drawings. The features of the examples and embodiments described below may be combined with each other without conflict.
The application provides a method for labeling prepositioned knowledge points, and fig. 1 is a flow chart of a method for labeling prepositioned knowledge points, which is shown in an exemplary embodiment of the application. As shown in fig. 1, the method for labeling the pre-knowledge points includes the following steps 101 to 102:
Step 101, inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points.
In the step, the acquired answer data of a plurality of student users are used as sample data to be input into a Bayesian network model. The answering data of a plurality of student users for each knowledge point can be collected from an online education platform, the online education platform can be a platform for providing services such as a learning question library, different exercise questions, test questions and the like are provided for different knowledge points, the student users can log in the platform for answering, and the background of the online education platform can acquire the answering data of the student users.
The Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture can be an existing basic knowledge point architecture and can be a knowledge point architecture comprising upper-level and lower-level relations among knowledge points. For example, the first knowledge point architecture may include a primary knowledge point, a secondary knowledge point, a tertiary knowledge point. Taking the "geometry" as an example, the "geometry" is a first-level knowledge point, the "triangle" and the "quadrangle" are second-level knowledge points, the "internal angle theorem of triangle", "nature of angular bisectors", "similar triangle" and "parallelogram" are third-level knowledge points, and so on. It can be understood that the first-level knowledge point, the second-level knowledge point and the third-level knowledge point are in a top-and-bottom relationship, wherein the first-level knowledge point is the highest-level knowledge point in the top-and-bottom relationship, and the third-level knowledge point is the lowest-level knowledge point in the top-and-bottom relationship.
In one possible implementation, the first knowledge point architecture may be a knowledge point architecture with the finest granularity, which may refer to subdividing the knowledge points into the smallest units, and in the above example, the three-level knowledge points may be the smallest units of the knowledge points.
In one possible implementation, the answer data of several student users to each knowledge point may be represented in a matrix, where the matrix is a matrix of student-knowledge points, and each element is answer data of one student on one knowledge point.
102, Performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
In this step, the structure learning is performed on the bayesian network model in combination with the answer data of the student user, so that the possible relationships between the knowledge points and the corresponding pre-knowledge points can be found out, in addition to the upper-level and lower-level relationships between the knowledge points in the first knowledge point architecture, and the relationships are marked and output so as to obtain the knowledge points and the corresponding pre-knowledge points. The acquired knowledge points and the corresponding pre-knowledge points are the knowledge points with the lowest level in the upper-lower relationship of the knowledge points of the first knowledge point architecture.
In one possible implementation, the noted knowledge points and their corresponding pre-knowledge points may be of the same superior knowledge points. For example, through structure learning of the bayesian network model, one of the pre-knowledge points of the three-level knowledge point "nature of triangle" is found as "triangle determination", which is also one three-level knowledge point, and has the same upper-level knowledge point "triangle" as "nature of triangle". It should be understood that a "triangle" is a "secondary knowledge point" and is a superior knowledge point of "nature of triangle" and "decision of triangle".
In another possible embodiment, the noted knowledge points and their corresponding pre-knowledge points may also be knowledge points having different upper levels. For example, through structure learning of a bayesian network model, one of the pre-knowledge points of the three-level knowledge points "inner angles of triangles and theorem" can be found as "property of parallel lines". The upper level knowledge points of the 'inner angle and theorem' of the triangle are 'triangle', the upper level knowledge points of the 'property of the parallel line' are 'intersecting line and parallel line', namely the upper level knowledge points of the 'inner angle and theorem' of the triangle and the upper level knowledge points of the 'property of the parallel line' are not identical.
In one possible implementation, after the second knowledge point architecture is obtained, the method further comprises combining the first knowledge point architecture with the second knowledge point architecture, the output comprising a relationship between a superior-inferior relationship between knowledge points and a relationship between at least one knowledge point and its corresponding pre-knowledge point. In this way, the knowledge points with the prepositive relationship can be intuitively known under the original basic upper and lower knowledge point architectures.
For easy understanding, fig. 2 is a schematic diagram of a knowledge point architecture according to an exemplary embodiment of the present application, where the knowledge point architecture is a second knowledge point architecture obtained after a bayesian network model is structurally studied in combination with answer data of a student user, as shown in fig. 2, each circle represents a knowledge point, a solid line represents an original relationship between knowledge points, that is, a relationship between a first knowledge point and a first knowledge point in the first knowledge point architecture, a dotted line represents a pre-relationship between a knowledge point extended after structural learning and a knowledge point, and an arrow of one knowledge point sending a dotted line points to another knowledge point, and a knowledge point indicated by the arrow is a pre-knowledge point of the knowledge point. As in fig. 2, one of the pre-knowledge points of the "triangle interior angles and theorem" is the "nature of parallel lines". It will be appreciated that the superior knowledge points "triangle", "intersecting line" and parallel line "of the two knowledge points are different knowledge points, but may have a correlation between them.
It will be appreciated that when a student does not have knowledge of a pre-knowledge point, the knowledge point is also largely unknown, and the student's knowledge of the knowledge point may be represented in the answer data, for example, if the student has poor knowledge of a knowledge point and its pre-knowledge point, the answer results of questions involving the knowledge point and the pre-knowledge point are poor when doing the questions, and therefore, the relationship between the potential knowledge point and the knowledge point may be reflected from the answer data of a large number of student users.
According to the labeling method of the pre-knowledge points, the answering data of a large number of student users on each knowledge point is collected and used as sample data to be input into the Bayesian network model, and the structure learning is carried out on the Bayesian network model based on the sample data, so that the answering data of the student users and the constructed Bayesian network model can be combined to learn to obtain a second knowledge point system structure, and the potential pre-knowledge points of each knowledge point are labeled in the knowledge point system structure. The constructed Bayesian network model comprises a first knowledge point architecture of the upper-lower relationship among knowledge points, and the marked knowledge points and the corresponding prepositioned knowledge points are the lowest-level knowledge points in the first knowledge point architecture. Therefore, the marking of the front knowledge points of each knowledge point can be automatically completed, and on one hand, the time cost and the auditing cost of manual marking by a teacher can be reduced; on the other hand, compared with the method for obtaining the prepositioned knowledge points by carrying out similarity calculation on the text information based on the knowledge points in the related technology, the technical scheme utilizes the answer data of students to reversely infer the prepositioned relations possibly existing between the knowledge points, can avoid the mislabel condition that texts are similar and have no direct relation in practice, and improves the labeling accuracy; and the knowledge points with the lowest level are found out, and the corresponding prepositive knowledge points are also the knowledge points with the lowest level, so that the prepositive relationship among specific knowledge points can be more intuitively known.
In an exemplary embodiment of the present application, the answer data of a knowledge point may include an average answer accuracy of the student user to the knowledge point. As a knowledge point can be provided with a plurality of different questions for students to practice and test, the average answer accuracy of all the questions related to the knowledge point can be taken as sample data, and the data has more referential property. In this embodiment, the step of inputting the collected answer data of the plurality of student users to each knowledge point into the bayesian network model may specifically include the following steps:
collecting average answer accuracy of a plurality of student users to each knowledge point;
and inputting the average answer accuracy of the plurality of student users to each knowledge point into the Bayesian network model.
In an exemplary embodiment of the present application, the average answer accuracy may be expressed in terms of percentages, such as 30%, 60%, 75%, etc.
In an exemplary embodiment of the present application, the average answer accuracy of the obtained knowledge points may be classified, that is, the average answer accuracy is discretized, and the class is used as data input into the bayesian network model. For example, the average answer accuracy is classified into three classes, poor, medium, and good. In an embodiment, the three levels may be divided according to the average answer accuracy of 60% and 90% as demarcation points. For example, the average answer accuracy is less than 60% and is equal to or greater than 60% and less than 90%, and the average answer accuracy is equal to or greater than 90%.
In an exemplary embodiment of the present application, the step of performing structure learning on the bayesian network model based on the answer data to obtain a second knowledge point architecture includes:
scoring the fitting degree of the Bayesian network model to the answer data by utilizing at least one scoring function;
and outputting the knowledge point architecture with the highest scoring result of the scoring function as a second knowledge point architecture.
In the foregoing embodiment, since various relationships may exist between the knowledge points, the bayesian network model may include a plurality of first knowledge point architectures, and the first knowledge point architectures may be traversed by at least one scoring function, where the scoring function may measure the fitting degree of the bayesian network model to the answer data, and find the knowledge point architecture that makes the scoring result of the scoring function highest, where the knowledge point architecture may be considered to be optimal, so that the relationship between the potential knowledge points and the knowledge points, including the potential pre-knowledge points of the knowledge points, is represented in the knowledge point architecture.
In an exemplary embodiment of the present application, the scoring function includes, but is not limited to, at least one of: a K2 scoring function, BDeu scoring function, and a BIC scoring function. Wherein the K2 scoring function and BDeu scoring function are Bayesian-based scoring functions, and the BIC scoring function is an informative-based scoring function.
The following describes the scoring functions:
1. Bayesian-based scoring function
The idea of the Bayesian-based scoring function is that the sample data is D (i.e., the student user's answer data) assuming the network structure is G (i.e., the relationship between knowledge points is G). Assuming that the prior probability of the network structure G is P (G), according to the bayesian formula, the posterior probability of the network structure G can be obtained as follows:
As can be seen from the formula, P (D) has no relation to the network structure, and therefore P (g|d) should be maximized to maximize the molecule. Thus, taking the logarithm for both sides is:
log P(G,D)＝log(P(G)P(D|G))＝log P(G)+log P(D|G)
the above formula is the basic formula of bayesian scoring, and since P (G) is generally a prior assumption about the network structure, which can be assumed to be known in general, the key is to determine P (d|g).
Assuming that the parameters of the model structure G are Θ G, then:
Where P (D|G, Θ G) is the likelihood function L (G, Θ G |D) of the model with respect to the data.
Assuming that the a priori distribution P (Θ G |g) of model parameters obeys the Dirichlet distribution of parameters α ijk, then there are:
Where Γ is a gamma function, r i is the state number of node V i, Θ ijk is the probability that its parent node is in the j state when the state value is k for V i. The result is carried into an integral type to obtain:
wherein m ijk is the number of samples in data D for which the state value of node V i is k and the parent state combination is j, namely:
taking the logarithm of the two sides of the above formula, the following steps are:
Different scoring criteria are used for different assumptions about α ijk in the above equation.
In particular, let α ijk =1, score K2, and the formula becomes:
In particular if it is assumed that Then BDeu is scored and the formula becomes:
2. scoring function based on information theory
The basic idea of the scoring function based on information theory is to compress the training data and mine the rules therein with a minimum description length MDL (Minimum Description Length).
First, the degree of fitting of the data needs to be considered, and therefore, likelihood functions, that is,:
on this basis, further consideration is given to the complexity of the parameters, and the required storage of training data D, i.e. BIC score, as follows:
From the above description, it can be seen that the idea of the bayesian-based network structure is to have some assumptions about the network structure (knowledge point architecture) in advance, and combine the data of the samples (student answer cases) to find the network structure that maximizes the scoring result, i.e. probability. In general, it is better for the case that the sample is large.
Since the second knowledge point architecture obtained by scoring by different scoring functions may be different, in order to improve the accuracy of the relationship between the obtained knowledge points, in an exemplary embodiment of the present application, before the second knowledge point architecture outputs, the method further comprises:
When the scoring functions are more than one, acquiring a knowledge point system structure with the highest scoring result of each scoring function;
And when the knowledge point system structure with the highest scoring result is marked with at least one first knowledge point as the same second knowledge point, determining the second knowledge point as the first knowledge point.
In this embodiment, the first knowledge point architecture is scored by adopting multiple scoring functions, and because the different scoring functions have different measurement angles, different second knowledge point architectures can be obtained by each scoring function, and intersection sets can be obtained for the obtained different second knowledge point architectures, and when the prepositive knowledge points marked with at least one first knowledge point in each second knowledge point architecture are the same second knowledge points, the second knowledge points are determined to be the prepositive knowledge points of the first knowledge points, that is, the correlation exists between the first knowledge points and the second knowledge points, or the relationship exists between the first knowledge points and the second knowledge points. In this way, the stringency and accuracy of determining the relationship between knowledge points can be improved.
In another exemplary embodiment of the present application, if only one scoring function is used to measure the fitting degree of the bayesian network model to the answer data, a greedy algorithm may be used to find the knowledge point architecture with the highest scoring result. For example, when a prepositioned knowledge point of one knowledge point is found for each knowledge point, according to a greedy algorithm, when a preset number of prepositioned knowledge points of the knowledge point are found, scoring of the rest of the unscored knowledge points can be omitted, so that the operation amount can be reduced, and the efficiency is improved.
The application also provides a question pushing method, and fig. 3 is a flowchart of a question pushing method according to an exemplary embodiment of the application. As shown in fig. 3, the title pushing method includes the following steps 301 to 303:
step 301, obtaining answer data of student users on each knowledge point.
Step 302, obtaining the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture.
Step 303, pushing corresponding questions to the student users based on the mastery degree of the student users on each knowledge point, wherein the appointed knowledge point architecture is a second knowledge point architecture obtained by performing structural learning on a Bayesian network model based on acquired answer data of a plurality of student users on each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
According to the question pushing method, the mastering degree of each knowledge point by the student user is determined by acquiring the answering data of the student user, the mastering degree of each knowledge point by the student user is compared with the optimized knowledge point system structure, and the weaker knowledge point and the front knowledge point can be determined to be mastered by the student user, so that the questions of the weaker knowledge point and the front knowledge point can be pushed, and the student user can do questions to improve the mastering degree of the knowledge points by the student user.
It should be understood that the specified knowledge point architecture may be obtained according to the method of labeling the pre-knowledge points in any of the above embodiments, where the pre-knowledge points of the potential knowledge points obtained by structure learning through the bayesian network model are included in the specified knowledge point architecture.
In an exemplary embodiment of the present application, the step of pushing the title includes the following steps:
obtaining the average answer accuracy of the student users to each knowledge point;
Determining at least two knowledge points based on the appointed knowledge point architecture, wherein the average answer accuracy of the at least two knowledge points is smaller than or equal to a set threshold value, and one knowledge point is a front knowledge point of the other knowledge point;
and increasing the pushing proportion of the topics corresponding to the prepositioned knowledge points.
In this embodiment, the average answer accuracy of each knowledge point by the student user is obtained, so that the mastering degree of each knowledge point by the student user can be determined, and by using the specified knowledge point architecture, the average answer accuracy of each knowledge point is compared, and if the mastering degree of the front knowledge point of at least one knowledge point is determined to be worse, the pushing proportion of the questions related to the front knowledge point can be increased, that is, more questions related to the front knowledge point are provided for the student user to practice and test, so that the mastering degree of the front knowledge point by the student user is improved.
In an exemplary embodiment of the application, answer data of a student user can be obtained in real time, if the average answer accuracy of a front knowledge point of a knowledge point is improved, it can be explained that the mastering degree of the student user on the front knowledge point is improved, and correspondingly, the pushing proportion of the questions corresponding to the knowledge point can be increased, so that the exercise and test of the student user on the knowledge point can be increased, and the mastering degree of the student user on the knowledge point can be improved. Therefore, the method and the device can be used for personalized pushing of the questions aiming at the grasping degree of the student user on the knowledge points, so that the student user can grasp each knowledge point effectively, and user experience is improved.
The various technical features of the above embodiments may be arbitrarily combined as long as there is no conflict or contradiction between the features, but are not described in detail, and therefore, the arbitrary combination of the various technical features of the above embodiments is also within the scope of the disclosure of the present specification.
The application also provides a device for labeling the front knowledge points, and fig. 4 is a structural block diagram of a device for labeling the front knowledge points, which is shown in an exemplary embodiment of the application. As shown in fig. 4, the apparatus 40 includes:
an input module 410 configured to input collected answer data of a plurality of student users to each knowledge point into a bayesian network model, wherein the bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises a superior-subordinate relationship between each knowledge point;
An obtaining module 420, configured to perform structure learning on the bayesian network model based on the answer data, to obtain a second knowledge point architecture; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
In an exemplary embodiment of the present application, the input module includes:
The acquisition sub-module is configured to acquire average answer accuracy of a plurality of student users to each knowledge point;
and the input sub-module is configured to input the average answer accuracy of the plurality of student users to each knowledge point into the Bayesian network model.
In an exemplary embodiment of the present application, the acquiring module includes:
The scoring sub-module is configured to score the fitting degree of the Bayesian network model to the answer data by utilizing at least one scoring function;
And the output sub-module is configured to output the knowledge point architecture with the highest scoring result of the scoring function as a second knowledge point architecture.
In an exemplary embodiment of the present application, the acquiring module further includes:
an acquisition sub-module configured to acquire, when the scoring function exceeds one, a knowledge point architecture having a highest scoring result for each scoring function before the second knowledge point architecture is output;
And the determining submodule is configured to determine that the second knowledge point is the prepositive knowledge point of the first knowledge point when the prepositive knowledge point marked with at least one first knowledge point in the knowledge point system structure with the highest scoring result is the same second knowledge point.
In an exemplary embodiment of the application, the scoring function includes at least one of: a K2 scoring function, BDeu scoring function, and a BIC scoring function.
In an exemplary embodiment of the present application, in the first knowledge point architecture, the at least one knowledge point and the pre-knowledge point are the lowest level knowledge points in the first knowledge point architecture.
The application also provides a question pushing device, and fig. 5 is a block diagram of a question pushing device according to an exemplary embodiment of the application. As shown in fig. 5, the apparatus 50 includes:
The first obtaining module 510 is configured to obtain answer data of the student user on each knowledge point;
a second obtaining module 520 configured to obtain the mastery degree of each knowledge point by the student user based on the answer data and the specified knowledge point architecture;
A pushing module 530 configured to push corresponding topics to the student user based on the degree of mastery of each knowledge point by the student user;
the specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
In an exemplary embodiment of the present application, the pushing module includes:
The acquisition sub-module is configured to acquire the average answer accuracy of the student user to each knowledge point;
A determining submodule configured to determine at least two knowledge points based on the specified knowledge point architecture, wherein the average answer accuracy of the at least two knowledge points is less than or equal to a set threshold value, and one knowledge point is a front knowledge point of the other knowledge point;
and the increasing submodule is configured to increase the pushing proportion of the topics corresponding to the pre-knowledge points.
The implementation process of the functions and roles of each module in the above device is specifically shown in the implementation process of the corresponding steps in the above method, and will not be described herein again.
For the device embodiments, reference is made to the description of the method embodiments for the relevant points, since they essentially correspond to the method embodiments. The apparatus embodiments described above are merely illustrative, wherein the modules illustrated as separate components may or may not be physically separate, and the components shown as modules may or may not be physical, i.e., may be located in one place, or may be distributed over a plurality of network modules. Some or all of the modules may be selected according to actual needs to achieve the purposes of the present application. Those of ordinary skill in the art will understand and implement the present application without undue burden.
The present application also provides a computer device, and fig. 6 is a block diagram of a computer device according to an exemplary embodiment of the present application. The computer device 60 includes:
A memory;
A processor for storing a computer program executable by the processor;
wherein the processor when executing the computer program performs the steps of:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
The present application also provides another computer device, and fig. 7 is a block diagram of another computer device according to an exemplary embodiment of the present application. The computer device 70 includes:
A memory;
A processor for storing a computer program executable by the processor;
wherein the processor when executing the computer program performs the steps of:
and obtaining answer data of the student user on each knowledge point.
And acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture.
Pushing corresponding questions to the student users based on the mastering degree of the student users on each knowledge point, wherein the appointed knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on a Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
The computer device may also include other hardware, depending on its actual functionality, which is not described in detail.
It should be understood that the two computer devices may be the same device or may be different devices.
The present application also provides a computer readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
The present application also provides another computer-readable storage medium having stored thereon a computer program which when executed by a processor performs the steps of:
and obtaining answer data of the student user on each knowledge point.
And acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture.
Pushing corresponding questions to the student users based on the mastering degree of the student users on each knowledge point, wherein the appointed knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on a Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower level relations among knowledge points, the second knowledge point architecture is marked with the relations between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture.
It should be understood that the two computer readable storage media may be the same storage medium or may be different storage media.
Embodiments of the application may take the form of a computer program product embodied on one or more readable media (including, but not limited to, magnetic disk storage, CD-ROM, optical storage, etc.) having program code embodied therein. Computer-usable readable media include both permanent and non-permanent, removable and non-removable media, and information storage may be implemented by any method or technology. The information may be computer readable instructions, data structures, modules of a program, or other data. Examples of computer readable media include, but are not limited to: phase change memory (PRAM), static Random Access Memory (SRAM), dynamic Random Access Memory (DRAM), other types of Random Access Memory (RAM), read Only Memory (ROM), erasable programmable read only memory (EEPROM), flash memory or other memory technology, compact disc read only memory (CD-ROM), digital Versatile Disks (DVD) or other optical storage, magnetic cassettes, magnetic tape magnetic disk storage or other magnetic storage devices, or any other non-transmission medium, may be used to store information that may be accessed by the computing device.
The foregoing describes certain embodiments of the present application. Other embodiments are within the scope of the following claims. In some cases, the actions or steps recited in the claims can be performed in a different order than in the embodiments and still achieve desirable results. In addition, the processes depicted in the accompanying figures do not necessarily require the particular order shown, or sequential order, to achieve desirable results. In some embodiments, multitasking and parallel processing are also possible or may be advantageous.
Other embodiments of the application will be apparent to those skilled in the art from consideration of the specification and practice of the application disclosed herein. This application is intended to cover any variations, uses, or adaptations of the application following, in general, the principles of the application and including such departures from the present disclosure as come within known or customary practice within the art to which the application pertains. It is intended that the specification and examples be considered as exemplary only, with a true scope and spirit of the application being indicated by the following claims.
It is to be understood that the application is not limited to the precise arrangements and instrumentalities shown in the drawings, which have been described above, and that various modifications and changes may be effected without departing from the scope thereof. The scope of the application is limited only by the appended claims.
The technical features of the above-described embodiments may be arbitrarily combined, and all possible combinations of the technical features in the above-described embodiments are not described for brevity of description, however, as long as there is no contradiction between the combinations of the technical features, they should be regarded as the scope of the present application.
The foregoing description of the preferred embodiments of the application is not intended to be limiting, but rather to enable any modification, equivalent replacement, improvement or the like to be made within the spirit and principles of the application.
Claims (12)
1. A method for labeling a pre-knowledge point, the method comprising:
Inputting acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
performing structure learning on the Bayesian network model based on the answer data to acquire a second knowledge point system structure; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding prepositioned knowledge point, and the at least one knowledge point and the prepositioned knowledge point are the knowledge points with the lowest level in the first knowledge point architecture; the step of determining the pre-knowledge point comprises:
And scoring the first knowledge point architectures by adopting a plurality of scoring functions, acquiring different second knowledge point architectures by each scoring function, acquiring intersection sets of the acquired different second knowledge point architectures, and determining that the second knowledge point is the front knowledge point of the first knowledge point when the front knowledge point marked with at least one first knowledge point in each second knowledge point architecture is the same second knowledge point.
2. The method for labeling pre-knowledge points according to claim 1, wherein the step of inputting the collected answer data of the plurality of student users to each knowledge point into the bayesian network model comprises:
collecting average answer accuracy of a plurality of student users to each knowledge point;
and inputting the average answer accuracy of the plurality of student users to each knowledge point into the Bayesian network model.
3. The method for labeling pre-knowledge points according to claim 1, wherein the step of performing structure learning on the bayesian network model based on the answer data to obtain a second knowledge point architecture comprises:
scoring the fitting degree of the Bayesian network model to the answer data by utilizing at least one scoring function;
and outputting the knowledge point architecture with the highest scoring result of the scoring function as a second knowledge point architecture.
4. A method of labeling pre-knowledge points in accordance with claim 3, wherein prior to output of the second knowledge point architecture, the method further comprises:
When the scoring functions are more than one, acquiring a knowledge point system structure with the highest scoring result of each scoring function;
And when the knowledge point system structure with the highest scoring result is marked with at least one first knowledge point as the same second knowledge point, determining the second knowledge point as the first knowledge point.
5. A method of labeling pre-knowledge points in accordance with claim 3, wherein said scoring function comprises at least one of: a K2 scoring function, BDeu scoring function, and a BIC scoring function.
6. The method for labeling pre-knowledge points according to any one of claims 1 to 5, wherein in the first knowledge point architecture, the at least one knowledge point and the pre-knowledge point are the lowest-level knowledge points in the first knowledge point architecture.
7. A method for pushing a title, the method comprising:
obtaining answer data of student users to each knowledge point;
acquiring the mastering degree of each knowledge point by the student user based on the answer data and the appointed knowledge point architecture;
Pushing corresponding questions to the student users based on the mastery degree of the student users on each knowledge point;
The specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower relationships among knowledge points, the second knowledge point architecture is marked with the relationships between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture; the step of determining the pre-knowledge point comprises:
And scoring the first knowledge point architectures by adopting a plurality of scoring functions, acquiring different second knowledge point architectures by each scoring function, acquiring intersection sets of the acquired different second knowledge point architectures, and determining that the second knowledge point is the front knowledge point of the first knowledge point when the front knowledge point marked with at least one first knowledge point in each second knowledge point architecture is the same second knowledge point.
8. The method of question pushing according to claim 7, wherein the step of question pushing includes:
obtaining the average answer accuracy of the student users to each knowledge point;
Determining at least two knowledge points based on the appointed knowledge point architecture, wherein the average answer accuracy of the at least two knowledge points is smaller than or equal to a set threshold value, and one knowledge point is a front knowledge point of the other knowledge point;
and increasing the pushing proportion of the topics corresponding to the prepositioned knowledge points.
9. A device for labeling pre-knowledge points, the device comprising:
The input module is configured to input acquired answer data of a plurality of student users to each knowledge point into a Bayesian network model, wherein the Bayesian network model comprises a first knowledge point architecture, and the first knowledge point architecture comprises upper and lower relationships among the knowledge points;
The acquisition module is configured to perform structure learning on the Bayesian network model based on the answer data, and acquire a second knowledge point architecture; the second knowledge point architecture is marked with a relation between at least one knowledge point and a corresponding prepositioned knowledge point, and the at least one knowledge point and the prepositioned knowledge point are the knowledge points with the lowest level in the first knowledge point architecture; the step of determining the pre-knowledge point comprises:
And scoring the first knowledge point architectures by adopting a plurality of scoring functions, acquiring different second knowledge point architectures by each scoring function, acquiring intersection sets of the acquired different second knowledge point architectures, and determining that the second knowledge point is the front knowledge point of the first knowledge point when the front knowledge point marked with at least one first knowledge point in each second knowledge point architecture is the same second knowledge point.
10. A topic pushing device, the device comprising:
The first acquisition module is configured to acquire answer data of the student user on each knowledge point;
The second acquisition module is configured to acquire the mastery degree of each knowledge point of the student user based on the answer data and the appointed knowledge point architecture;
A pushing module configured to push corresponding topics to the student users based on the knowledge degree of the student users on each knowledge point;
The specified knowledge point architecture is a second knowledge point architecture obtained by performing structure learning on the Bayesian network model based on acquired answer data of a plurality of student users aiming at each knowledge point; the Bayesian network model comprises a first knowledge point architecture, wherein the first knowledge point architecture comprises upper and lower relationships among knowledge points, the second knowledge point architecture is marked with the relationships between at least one knowledge point and a corresponding pre-knowledge point, and the at least one knowledge point and the pre-knowledge point are the knowledge points with the lowest level in the first knowledge point architecture; the step of determining the pre-knowledge point comprises:
And scoring the first knowledge point architectures by adopting a plurality of scoring functions, acquiring different second knowledge point architectures by each scoring function, acquiring intersection sets of the acquired different second knowledge point architectures, and determining that the second knowledge point is the front knowledge point of the first knowledge point when the front knowledge point marked with at least one first knowledge point in each second knowledge point architecture is the same second knowledge point.
11. A computer device comprising a memory, a processor and a computer program stored on the memory and executable on the processor, characterized in that the processor implements the steps of the method according to any one of claims 1 to 8 when the program is executed.
12. A computer readable storage medium, on which a computer program is stored, characterized in that the program, when being executed by a processor, implements the steps of the method as claimed in any one of claims 1 to 8.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646225.XA CN111897945B (en) | 2020-07-07 | 2020-07-07 | Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202010646225.XA CN111897945B (en) | 2020-07-07 | 2020-07-07 | Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics |
Publications (2)
| Publication Number | Publication Date |
|---|---|
| CN111897945A CN111897945A (en) | 2020-11-06 |
| CN111897945B true CN111897945B (en) | 2024-07-02 |
Family
ID=73191920
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202010646225.XA Active CN111897945B (en) | 2020-07-07 | 2020-07-07 | Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN111897945B (en) |
Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008350A (en) * | 2019-03-06 | 2019-07-12 | 杭州哲达科技股份有限公司 | A kind of pump Ankang knowledge base lookup method based on Bayesian inference |
| CN110473123A (en) * | 2019-07-09 | 2019-11-19 | 北京羽实箫恩信息技术股份有限公司 | A kind of multi-element intelligent educational method and system |
Family Cites Families (4)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| JP2005222115A (en) * | 2004-02-03 | 2005-08-18 | Inter Db:Kk | Event analysis and dealing system using bayesian network |
| WO2006087854A1 (en) * | 2004-11-25 | 2006-08-24 | Sharp Kabushiki Kaisha | Information classifying device, information classifying method, information classifying program, information classifying system |
| CN105678665A (en) * | 2016-03-14 | 2016-06-15 | 成都爱易佰网络科技有限公司 | System and method satisfying content development standard of self-adaptive teaching |
| US10043133B2 (en) * | 2016-04-08 | 2018-08-07 | Pearson Education, Inc. | Systems and methods of event-based content provisioning |
-
2020
- 2020-07-07 CN CN202010646225.XA patent/CN111897945B/en active Active
Patent Citations (2)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN110008350A (en) * | 2019-03-06 | 2019-07-12 | 杭州哲达科技股份有限公司 | A kind of pump Ankang knowledge base lookup method based on Bayesian inference |
| CN110473123A (en) * | 2019-07-09 | 2019-11-19 | 北京羽实箫恩信息技术股份有限公司 | A kind of multi-element intelligent educational method and system |
Also Published As
| Publication number | Publication date |
|---|---|
| CN111897945A (en) | 2020-11-06 |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107230174B (en) | Online interactive learning system and method based on network | |
| CN109977230B (en) | Selected question error cause analysis method suitable for adaptive teaching | |
| CN112395403B (en) | Knowledge graph-based question and answer method, system, electronic equipment and medium | |
| Petersen et al. | Reviewing CS1 exam question content | |
| CN111274411A (en) | Course recommendation method and device, electronic equipment and readable storage medium | |
| CN111242816B (en) | Multimedia teaching plan manufacturing method and system based on artificial intelligence | |
| CN112784608B (en) | Test question recommending method and device, electronic equipment and storage medium | |
| CN105677747A (en) | Method and system for managing knowledge points in online teaching | |
| Liyanage et al. | Using learning styles to enhance learning management systems | |
| CN114913729B (en) | Question selecting method, device, computer equipment and storage medium | |
| US20150026184A1 (en) | Methods and systems for content management | |
| CN116263782A (en) | Intelligent winding method, system and storage medium based on question bank | |
| Vagale et al. | Implementation of Personalized Adaptive E-learning System. | |
| Fatqurhohman | Characteristics of students in resolving word problems based on gender | |
| CN114254122A (en) | Test question generation method and device, electronic equipment and readable storage medium | |
| CN111897945B (en) | Method, device, equipment and medium for labeling prepositioned knowledge points and pushing topics | |
| US20170221163A1 (en) | Create a heterogeneous learner group | |
| CN112419815A (en) | Planning method and device for learning path | |
| CN112764760A (en) | Program evaluation-based auxiliary question answering system | |
| Nafa et al. | Conceptualize the domain knowledge space in the light of cognitive skills | |
| KR102496948B1 (en) | System and method for knowledge space-based learning location and route recommendation and recording medium storing program for executing the same, and computer program stored in recording medium for executing the same | |
| Alharbi et al. | Computer science learning objects | |
| Whitacre | Prospective elementary teachers learning to reason flexibly with sums and differences: Number sense development viewed through the lens of collective activity | |
| CN114971962A (en) | Student homework evaluation method and device, electronic device and storage medium | |
| CN111709551A (en) | Student test data processing method, system, device and medium based on similarity |
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 |