CN112785148A - Knowledge point mastery degree identification method and device, terminal device and storage medium - Google Patents
Knowledge point mastery degree identification method and device, terminal device and storage medium Download PDFInfo
- Publication number
- CN112785148A CN112785148A CN202110083470.9A CN202110083470A CN112785148A CN 112785148 A CN112785148 A CN 112785148A CN 202110083470 A CN202110083470 A CN 202110083470A CN 112785148 A CN112785148 A CN 112785148A
- Authority
- CN
- China
- Prior art keywords
- knowledge point
- user
- matrix
- target
- knowledge
- Prior art date
- Legal status (The legal status is an assumption and is not a legal conclusion. Google has not performed a legal analysis and makes no representation as to the accuracy of the status listed.)
- Pending
Links
- 238000000034 method Methods 0.000 title claims abstract description 45
- 239000011159 matrix material Substances 0.000 claims abstract description 220
- 230000006870 function Effects 0.000 claims description 58
- 238000005315 distribution function Methods 0.000 claims description 17
- 238000004590 computer program Methods 0.000 claims description 15
- 238000011478 gradient descent method Methods 0.000 claims description 11
- 238000012545 processing Methods 0.000 claims description 10
- 238000007476 Maximum Likelihood Methods 0.000 claims description 7
- 238000004422 calculation algorithm Methods 0.000 claims description 7
- 230000002708 enhancing effect Effects 0.000 claims description 3
- 230000003313 weakening effect Effects 0.000 claims description 3
- 230000014509 gene expression Effects 0.000 description 11
- 238000010586 diagram Methods 0.000 description 10
- 238000012549 training Methods 0.000 description 7
- 230000000694 effects Effects 0.000 description 2
- 238000013210 evaluation model Methods 0.000 description 2
- 238000003062 neural network model Methods 0.000 description 2
- 238000012360 testing method Methods 0.000 description 2
- 230000017105 transposition Effects 0.000 description 2
- 230000002159 abnormal effect Effects 0.000 description 1
- 238000003491 array Methods 0.000 description 1
- 238000004364 calculation method Methods 0.000 description 1
- 230000001419 dependent effect Effects 0.000 description 1
- 238000009795 derivation Methods 0.000 description 1
- 238000011156 evaluation Methods 0.000 description 1
- 238000012854 evaluation process Methods 0.000 description 1
- 239000000284 extract Substances 0.000 description 1
- 239000000463 material Substances 0.000 description 1
- 238000012986 modification Methods 0.000 description 1
- 230000004048 modification Effects 0.000 description 1
- 230000000717 retained effect Effects 0.000 description 1
- 238000005070 sampling Methods 0.000 description 1
- 239000000126 substance Substances 0.000 description 1
- 238000006467 substitution reaction Methods 0.000 description 1
Images
Classifications
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q10/00—Administration; Management
- G06Q10/06—Resources, workflows, human or project management; Enterprise or organisation planning; Enterprise or organisation modelling
- G06Q10/063—Operations research, analysis or management
- G06Q10/0639—Performance analysis of employees; Performance analysis of enterprise or organisation operations
-
- G—PHYSICS
- G06—COMPUTING; CALCULATING OR COUNTING
- G06Q—INFORMATION AND COMMUNICATION TECHNOLOGY [ICT] SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES; SYSTEMS OR METHODS SPECIALLY ADAPTED FOR ADMINISTRATIVE, COMMERCIAL, FINANCIAL, MANAGERIAL OR SUPERVISORY PURPOSES, NOT OTHERWISE PROVIDED FOR
- G06Q50/00—Information and communication technology [ICT] specially adapted for implementation of business processes of specific business sectors, e.g. utilities or tourism
- G06Q50/10—Services
- G06Q50/20—Education
- G06Q50/205—Education administration or guidance
-
- G—PHYSICS
- G09—EDUCATION; CRYPTOGRAPHY; DISPLAY; ADVERTISING; SEALS
- G09B—EDUCATIONAL OR DEMONSTRATION APPLIANCES; APPLIANCES FOR TEACHING, OR COMMUNICATING WITH, THE BLIND, DEAF OR MUTE; MODELS; PLANETARIA; GLOBES; MAPS; DIAGRAMS
- G09B7/00—Electrically-operated teaching apparatus or devices working with questions and answers
- G09B7/02—Electrically-operated teaching apparatus or devices working with questions and answers of the type wherein the student is expected to construct an answer to the question which is presented or wherein the machine gives an answer to the question presented by a student
Landscapes
- Business, Economics & Management (AREA)
- Engineering & Computer Science (AREA)
- Educational Administration (AREA)
- Human Resources & Organizations (AREA)
- Strategic Management (AREA)
- Theoretical Computer Science (AREA)
- General Physics & Mathematics (AREA)
- Economics (AREA)
- Educational Technology (AREA)
- Tourism & Hospitality (AREA)
- Physics & Mathematics (AREA)
- Entrepreneurship & Innovation (AREA)
- Marketing (AREA)
- Development Economics (AREA)
- General Business, Economics & Management (AREA)
- Quality & Reliability (AREA)
- Game Theory and Decision Science (AREA)
- Operations Research (AREA)
- Health & Medical Sciences (AREA)
- General Health & Medical Sciences (AREA)
- Primary Health Care (AREA)
- Management, Administration, Business Operations System, And Electronic Commerce (AREA)
- Electrically Operated Instructional Devices (AREA)
Abstract
The application is suitable for the technical field of computer-aided education and provides a knowledge point mastering degree identification method, a knowledge point mastering degree identification device, terminal equipment and a storage medium, wherein the method comprises the following steps: acquiring exercise data of a plurality of users respectively; respectively establishing potential scoring matrixes of a plurality of users and a plurality of knowledge points according to the exercise data; respectively establishing a user characteristic matrix and a knowledge point characteristic matrix which obey target distribution; updating the potential scoring matrix through the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix; and identifying the mastery degree of the target user on the target knowledge points according to the target scoring matrix and the data of the target user for practicing the exercises of the target knowledge points. By adopting the method to establish the user characteristic matrix and the knowledge point characteristic matrix which obey normal distribution to update the potential scoring matrix, the theory of the updated target scoring matrix is rigorous, and the accuracy rate of identifying the mastering degree of the user on the target knowledge point is higher.
Description
Technical Field
The application belongs to the technical field of computer-aided education, and particularly relates to a knowledge point mastering degree identification method and device, terminal equipment and a storage medium.
Background
In the traditional subject knowledge point evaluation process, the mastery degree of knowledge points of students is usually evaluated by sampling test questions of corresponding knowledge points according to the corresponding knowledge points learned by the students. For example, most of them adopt the strategy of examination score to evaluate the mastery degree of the students to the corresponding knowledge points. However, due to the limitation of the examination questions themselves, the examination questions cannot be evaluated in a refined manner according to the mastery degree of each knowledge point of each student. Such an evaluation method is too dependent on the examination performance of the student, and does not consider the actual learning condition (for example, the ordinary problem-making condition) of the student at all. Therefore, in the prior art, the problem that the mastery degree of students and knowledge points cannot be evaluated scientifically and accurately exists.
Disclosure of Invention
The embodiment of the application provides a knowledge point mastery degree identification method, a knowledge point mastery degree identification device, a terminal device and a storage medium, and can solve the problem that in the prior art, the mastery degrees of students and knowledge points cannot be evaluated scientifically and accurately.
In a first aspect, an embodiment of the present application provides a knowledge point mastery degree identification method, including:
acquiring exercise data of a plurality of users respectively, wherein the exercise data comprises data for the plurality of users to exercise exercises of a plurality of knowledge points respectively;
respectively establishing potential scoring matrixes of the users and the knowledge points according to the exercise data;
respectively establishing user feature matrixes of the users and knowledge point feature matrixes of the knowledge points, wherein the user feature matrixes and the knowledge point feature matrixes are subject to target distribution;
updating the potential scoring matrix through the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix;
and identifying the mastery degree of the target user on the target knowledge point according to the target scoring matrix and the data of the target user practicing the exercises of the target knowledge point.
In an embodiment, the acquiring exercise data of a plurality of users respectively includes:
respectively counting the exercise time length of each user for practicing the exercise of the knowledge points aiming at any exercise in any knowledge point;
if the exercise making duration is less than the preset duration, deleting data for the user to exercise the exercises of the knowledge points;
and if the exercise making duration is greater than or equal to the preset duration, determining the data of the exercise of the knowledge points by the user as the exercise data.
In an embodiment, the establishing potential scoring matrices for the plurality of users and the plurality of knowledge points according to the problem data respectively includes:
aiming at any user, inputting the data of practice of the user on the exercises of the knowledge points into a preset knowledge point scoring model respectively to obtain the mastering degree of the user on the knowledge points respectively;
and respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points.
In one embodiment, the potential scoring matrix includes an indicator function; the respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points comprises the following steps:
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is greater than a preset numerical value, setting the output value of the indication function as a first target value, wherein the first target value is used for enhancing the mastery degree of the knowledge point by the user; alternatively, the first and second electrodes may be,
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is less than or equal to a preset numerical value, setting the output value of the indication function as a second target value, wherein the second target value is used for weakening the mastery degree of the knowledge point by the user;
constructing the potential scoring matrix according to the first target value or the second target value.
In an embodiment, the updating the potential scoring matrix through the user feature matrix and the knowledge point feature matrix to obtain a target scoring matrix includes:
constructing an updating function through the user feature matrix, the knowledge point feature matrix and the potential scoring matrix;
and updating the potential scoring matrix according to the updating function to obtain a target scoring matrix.
In one embodiment, the update function is a joint distribution function; the constructing an update function through the user feature matrix, the knowledge point feature matrix and the potential scoring matrix comprises:
and carrying out matrix multiplication processing on the user characteristic matrix, the knowledge point characteristic matrix and the potential scoring matrix to obtain the joint distribution function.
In an embodiment, the updating the potential scoring matrix according to the update function to obtain a target scoring matrix includes:
calculating a maximum value in the update function according to a maximum likelihood estimation algorithm;
and updating the potential scoring matrix through a gradient descent method based on the maximum value to obtain the target scoring matrix.
In a second aspect, an embodiment of the present application provides an apparatus for recognizing a degree of knowledge point mastery, including:
the acquisition module is used for respectively acquiring exercise data of a plurality of users, wherein the exercise data comprises data for the plurality of users to respectively exercise exercises of a plurality of knowledge points;
the first establishing module is used for respectively establishing potential scoring matrixes of the users and the knowledge points according to the exercise data;
the second establishing module is used for respectively establishing a user characteristic matrix of the plurality of users and a knowledge point characteristic matrix of the plurality of knowledge points, and the user characteristic matrix and the knowledge point characteristic matrix are respectively subjected to target distribution;
the updating module is used for updating the potential scoring matrix based on the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix;
and the identification module is used for identifying the mastering degree of the target user on the target knowledge point according to the target scoring matrix and the data of practicing the target user on the problem of the target knowledge point.
In a third aspect, an embodiment of the present application provides a terminal device, which includes a memory, a processor, and a computer program stored in the memory and executable on the processor, and the processor, when executing the computer program, implements the method according to any one of the above first aspects.
In a fourth aspect, the present application provides a computer-readable storage medium, which stores a computer program, and when the computer program is executed by a processor, the computer program implements the method according to any one of the above first aspects.
In a fifth aspect, the present application provides a computer program product, which when run on a terminal device, causes the terminal device to execute the method of any one of the above first aspects.
Compared with the prior art, the embodiment of the application has the advantages that: the problem of model overfitting when a potential scoring matrix is established according to a small number of answers of a single user in the prior art can be solved by acquiring exercise data of a plurality of users to establish the potential scoring matrix. And then, respectively establishing a user characteristic matrix and a knowledge point characteristic matrix which obey normal distribution. Therefore, when the potential scoring matrix is updated based on the matrix obeying normal distribution, the theory of the obtained target scoring matrix is rigorous and has stronger interpretability, and the scoring of the knowledge point mastering degree realized based on the theory is more scientific. Therefore, when the terminal equipment identifies according to the exercise data of the target knowledge point, the accuracy of the terminal equipment identifying the mastery degree of the target knowledge point by the target user can be improved.
Drawings
In order to more clearly illustrate the technical solutions in the embodiments of the present application, the drawings needed to be used in the embodiments or the prior art descriptions will be briefly described below, and it is obvious that the drawings in the following description are only some embodiments of the present application, and it is obvious for those skilled in the art to obtain other drawings without creative efforts.
Fig. 1 is a flowchart illustrating an implementation of a knowledge point mastery degree identification method according to an embodiment of the present application;
fig. 2 is a schematic diagram illustrating an implementation manner of S101 of a knowledge point mastery degree identification method according to an embodiment of the present application;
fig. 3 is a schematic diagram illustrating an implementation manner of S102 of a knowledge point mastery degree identification method according to an embodiment of the present application;
fig. 4 is a schematic diagram illustrating an implementation manner of S1022 in a knowledge point mastery degree identification method according to an embodiment of the present application;
fig. 5 is a schematic diagram illustrating an implementation manner of S104 of a knowledge point mastery degree identification method according to an embodiment of the present application;
fig. 6 is a schematic diagram illustrating an implementation manner of S1042 of a knowledge point mastering degree identifying method according to an embodiment of the present application;
fig. 7 is a block diagram illustrating a structure of a knowledge point mastery level recognition apparatus according to an embodiment of the present application;
fig. 8 is a block diagram of a terminal device according to an embodiment of the present application.
Detailed Description
In the following description, for purposes of explanation and not limitation, specific details are set forth, such as particular system structures, techniques, etc. in order to provide a thorough understanding of the embodiments of the present application. It will be apparent, however, to one skilled in the art that the present application may be practiced in other embodiments that depart from these specific details. In other instances, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present application with unnecessary detail.
It will be understood that the terms "comprises" and/or "comprising," when used in this specification and the appended claims, specify the presence of stated features, integers, steps, operations, elements, and/or components, but do not preclude the presence or addition of one or more other features, integers, steps, operations, elements, components, and/or groups thereof.
Furthermore, in the description of the present application and the appended claims, the terms "first," "second," "third," and the like are used for distinguishing between descriptions and not necessarily for describing or implying relative importance.
The knowledge point mastering degree identification method provided by the embodiment of the application can be applied to terminal equipment such as a mobile phone, a tablet personal computer, a notebook computer, an ultra-mobile personal computer (UMPC), a netbook and the like, and the specific type of the terminal equipment is not limited at all in the embodiment of the application.
Referring to fig. 1, fig. 1 is a flowchart illustrating an implementation of a knowledge point mastery degree identification method according to an embodiment of the present application, where the method includes the following steps:
s101, exercise data of a plurality of users are respectively obtained, and the exercise data comprise data of practicing exercises of the plurality of knowledge points by the plurality of users.
In application, the exercise data is data for the user to exercise exercises on exercises of a plurality of knowledge points. The knowledge points can be the knowledge points which are set in the terminal equipment by the staff in advance. Illustratively, the problem can be divided into problems of subjects such as mathematics, English, physics and the like, each category of subject can be divided into a plurality of grades, and each grade contains corresponding knowledge points required to be learned, which can be consistent with the knowledge points on the corresponding teaching materials. It can be understood that the problem can be a large number of problems which accord with the knowledge point are cached in the terminal device according to the corresponding knowledge point in advance for the staff. The exercise data includes, but is not limited to, time of the user practicing the exercise, whether the answer is correct, and difficulty of the exercise, and is not limited thereto.
In the application, the exercise data of the user can be acquired by using the teaching equipment for exercise practice, and the teaching equipment can directly upload the acquired exercise data to a real-time data warehouse of the terminal equipment for caching the exercise data. The teaching device may be, for example and without limitation, an education tablet terminal, and the terminal device may be a teaching system or a teaching terminal having a data connection relationship with the education tablet terminal, or the teaching system includes the education tablet terminal. At this time, the exercise data is generated on the teaching device and then transmitted to the terminal device. Specifically, the user can log in an account on the education tablet terminal in advance, and then the education tablet terminal can record exercise data of the user when the user uses the education tablet terminal to practice exercises. Finally, the education tablet terminal can upload the exercise data to a real-time data warehouse of the teaching terminal (terminal equipment) for caching. The uploaded exercise data further comprise user data, namely an account number of the user logged in the education tablet terminal, and the user data are used for uniquely identifying the user.
It is understood that the above-mentioned users include not only students of schools but also other users who need to take examinations. For example, for a user who has participated in work, if the user needs to participate in the examination of the corresponding certificate, the user can download a corresponding teaching APP in the education tablet terminal to perform exercise, which is not limited to this.
It should be noted that, in the methods for predicting knowledge mastery degrees adopted in the academic world at present, learning modeling is mainly performed by using the exercise data of the user, and the mastery degree of the user on the knowledge points is predicted according to the modeled learning model. However, the data size of the problem data available to a single user is often severely insufficient. The learning model obtained by training according to the problem data generally cannot accurately output the mastery degree of the knowledge point by the user. Therefore, exercise data of a plurality of users can be acquired to participate in updating the matrix model, and the matrix model obtained after updating can accurately output the mastery degree of the users on the knowledge points.
S102, potential scoring matrixes of the users and the knowledge points are respectively established according to the exercise data.
In an application, for a plurality of knowledge points, a potential scoring matrix for each user with respect to each knowledge point may be constructed. And any potential scoring matrix is used for representing the mastery degree of the user on the corresponding knowledge point. For example, for the exercise data of a user relative to each knowledge point, the exercise data of each knowledge point can be input into the existing learning model respectively. Then, the learning model extracts the problem characteristics of the problem data to perform model processing, and then outputs the grasping degree of the user relative to each knowledge point. After acquiring the mastery degree, the terminal device can establish a potential scoring matrix between the user and each knowledge point according to the mastery degree. It can be understood that the potential scoring matrix contains unknown matrix parameters, and the potential scoring matrix can be updated and determined in the subsequent matrix processing to obtain a final target scoring matrix.
In other applications, the degree of mastery can be determined by the accuracy of the problem data of each knowledge point. For example, it has been described in S101 that the above problem data further includes whether the answer of the exercise performed on the problem by the user is accurate. Therefore, a plurality of exercises are correspondingly arranged on one knowledge point, and when the user exercises the plurality of exercises, the accuracy of the user exercising the plurality of exercises can be obtained. For example, the terminal device may count the number of exercises performed by the user and the number of exercises with correct exercise making, and then calculate the accuracy rate of the exercise performed by the user on the exercise of the knowledge point. Finally, the terminal device can use the accuracy as the mastery degree of the user on the knowledge point, so that the process that the terminal device needs to perform model training and the memory of the terminal device occupied by the model are reduced.
S103, respectively establishing user feature matrixes of the users and knowledge point feature matrixes of the knowledge points, wherein the user feature matrixes and the knowledge point feature matrixes are subject to target distribution.
In application, the target distribution includes, but is not limited to, a gaussian distribution (normal distribution), a chi-square distribution, and the like. In this embodiment, the statistical rules of education statistics show that the intelligence level of students, including learning ability and practical ability, is normally distributed. Thus, a normal test achievement distribution should follow a substantially normal distribution. It can be considered that, for a plurality of users, the degree of grasp of the user with respect to the knowledge point should also conform to the normal distribution. Therefore, in the present embodiment, both the user feature matrix and the knowledge point feature matrix may be subject to normal distribution. Furthermore, when the target scoring matrix is obtained after matrix processing is carried out on the matrix which obeys normal distribution, the theory of obtaining the target scoring matrix is strict and has stronger interpretability, and the scoring of the knowledge point mastering degree based on the theory is more scientific. Compared with the method for predicting the mastering degree of the user and the knowledge point by using the neural network model, the neural network model is generally low in interpretability, not only seriously occupies the computing resource of the terminal equipment, but also is not suitable for a rigorous teaching scene.
Specifically, the terminal device may preset U as a user feature matrix of the user, where U belongs to RD*NSimilarly, the terminal device may preset V as a knowledge point feature matrix of knowledge points, V ∈ RD*M(ii) a And D is a parameter needing to be adjusted, M is the number of knowledge points, N is the number of users, and R is a potential scoring matrix between the users and the knowledge points. Because the user characteristic matrix and the knowledge point characteristic matrix are both subjected to normal distribution, the user characteristic matrix U belonging to R can be setD*NObey μ to 0 and standard deviation to σuIs normally distributed. Similarly, a knowledge point feature matrix V ∈ R can be setD*MObey μ to 0 and standard deviation to σvIs normally distributed. Based on this, a matrix formula of the user feature matrix can be established:
wherein I is a predetermined indicator function, wherein
Denotes the standard deviation as σuThe user feature matrix of the ith user; and establishing a matrix formula of the knowledge point characteristic matrix:
wherein, I is a preset indication functionWherein
Denotes the standard deviation as σvKnowledge point feature matrix of the jth knowledge point of (1). When the initial value is set, μmay be other values (non-zero values), and this is not limitative.
And S104, updating the potential scoring matrix through the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix.
In application, the updating of the potential scoring matrix may be updating unknown parameters in the potential scoring matrix to obtain a target scoring matrix. And for the existing user matrix, knowledge point characteristic matrix and potential scoring matrix, a joint distribution function of the three matrixes can be established. And then, carrying out parameter solution on the joint distribution function according to a maximum likelihood estimation method so as to realize the effects of optimizing and updating the unknown parameters of the three matrixes and obtain a target scoring matrix.
It is to be added that the joint distribution function may be obtained by performing matrix multiplication on the user feature matrix, the knowledge point feature matrix, and the potential scoring matrix.
And S105, identifying the mastering degree of the target user on the target knowledge point according to the target scoring matrix and the data of practice of the target user on the problem of the target knowledge point.
In an application, the target user may be any one of the plurality of users in S101, or may be another user, which is not limited. It is understood that, for a plurality of knowledge points, the terminal device may acquire the problem data of the target user with respect to the target knowledge point and input the problem data into the target scoring matrix for calculation to identify the degree of grasp of the target user on the target knowledge point.
It is understood that the data that the target user exercises on the problem of the target knowledge point includes, but is not limited to: the total time, exercise accuracy rate, exercise comprehensive difficulty and other data of the target user for exercising the exercises of the target knowledge points. In addition, the terminal equipment can perform unified dimension processing on the data such as exercise time, exercise accuracy, exercise comprehensive difficulty and the like, and then obtain corresponding numerical values to participate in matrix operation.
In the embodiment, the problem of model overfitting when the potential scoring matrix is established according to a small number of answers of a single user in the past can be solved by acquiring exercise data of a plurality of users to establish the potential scoring matrix. And then, respectively establishing a user characteristic matrix and a knowledge point characteristic matrix which obey normal distribution. Therefore, when the potential scoring matrix is updated based on the matrix obeying normal distribution, the theory of the obtained target scoring matrix is rigorous and has stronger interpretability, and the scoring of the knowledge point mastering degree realized based on the theory is more scientific. Therefore, when the terminal equipment identifies according to the exercise data of the target knowledge point, the accuracy of the terminal equipment identifying the mastery degree of the target knowledge point by the target user can be improved.
Referring to fig. 2, in an embodiment, the step S101 of respectively obtaining exercise data of a plurality of users includes the following sub-steps S1011 to S1013, which are detailed as follows:
s1011, aiming at any exercise in any knowledge point, respectively counting exercise time length of each user for exercising the exercise of the knowledge point.
In application, the exercise making time is the time for the user to practice any exercise of the knowledge points. For example, after the user logs in the education APP of the education tablet terminal, a plurality of knowledge points are displayed in the interface of the education APP. And then, selecting the knowledge points according to a selection instruction input by the user on the interface, and performing exercise. However, in actual process, the user may have a false touch operation to select a wrong knowledge point. At this time, the education tablet terminal may use the time when the exercise is displayed in the interface as the start time, and use the time when the user exits from the exercise interface (reselects the knowledge point or exits from the education APP) as the end time. Therefore, the education tablet terminal can obtain the exercise time length of the user for exercising the exercise of each knowledge point.
It can be understood that when the user exercises the problem with the wrong knowledge point selected by the false touch operation, the user usually does the problem with the wrong knowledge point for a short time.
In other applications, the educational APP of the educational tablet terminal also typically has the function of randomly pushing any knowledge point exercises. Based on this, the educational tablet terminal may also record the time of the exercise the user exercises for each exercise. And then adding the exercise time of a plurality of exercises belonging to the same knowledge point, wherein the sum is used as exercise time for the user to exercise the exercises of the knowledge point. It should be added that, for the problem of randomly pushed arbitrary knowledge points, the pushed problem may be beyond the learning range (learned knowledge points) of the user. Based on this, the user may quickly and freely select or fill in answers while facing the problem of knowledge points in the situation. Therefore, after recording the exercise time of each exercise performed by the user, the education tablet terminal can delete the relevant exercise data with the exercise time being less than the preset exercise time. Then, the relevant exercise data with exercise time longer than or equal to the preset exercise time is retained, which is not limited.
And S1012, if the exercise making duration is less than the preset duration, deleting the data of the exercise of the knowledge points by the user.
And S1013, if the exercise making duration is greater than or equal to a preset duration, determining the data of the exercise of the knowledge points by the user as the exercise data.
In application, the preset duration can be set for a user according to an actual situation, and is used for judging whether a knowledge point of a current exercise of the user is generated after the user touches the exercise by mistake by the terminal equipment.
It can be understood that when the question making time length is less than the preset time length, it indicates that the user may be a random question making, or there is a case that the user has a wrong touch operation to select a wrong knowledge point. Based on this, it is considered that the exercise data for the user to exercise the exercise of the knowledge point has no reference value. Therefore, in order to make the established potential scoring matrix more reasonable and closer to the actual situation, the exercise data with the exercise time length less than the preset time length needs to be deleted, and only the exercise data of the knowledge points, which are trained by the user with the exercise time length greater than or equal to the preset time length, are reserved.
In other applications, when the education tablet terminal uploads the exercise data to the real-time data warehouse of the terminal device, the uploaded data may be abnormal, and the data may be missing. For example, the uploaded problem data lacks the accuracy of the user practicing the problem of the knowledge point, or lacks the duration of the user practicing the problem of the knowledge point. At this time, the terminal device needs to further filter the acquired problem data to ensure the usability of the problem data.
Referring to fig. 3, in an embodiment, S102 separately establishes potential scoring matrices for the users and the knowledge points according to the problem data, and further includes the following sub-steps S1021-S1022, which are detailed as follows:
s1021, aiming at any user, inputting the data of the user for practicing the exercises of the knowledge points into a preset knowledge point scoring model respectively to obtain the mastering degree of the user on the knowledge points respectively.
In application, the knowledge point scoring model may be a model obtained by a user training in advance according to existing exercise data, and is used for predicting the mastery degree of the user on the knowledge point according to the currently acquired exercise data. Specifically, for any arbitrary set of training data (problem data), the user can preset the real mastery degree corresponding to each set of training data. Then, the training data can be input into the initial knowledge point scoring model to obtain the degree of predictive mastery. Then, a loss value is calculated based on the true grasp degree and the predicted grasp degree. And finally, iteratively updating the model parameters in the initial knowledge point scoring model according to the loss values to obtain a final knowledge point scoring model.
It can be understood that, when the knowledge point scoring model is trained, the training can be performed by using the characteristics of the exercise accuracy, the exercise duration, the exercise difficulty and the like in the exercise data. Based on the knowledge point evaluation model, compared with the method for judging the mastery degree of the knowledge point by the user by using the exercise accuracy rate of the knowledge point by the user, the method for judging the mastery degree of the knowledge point by the user by using the knowledge point evaluation model has higher accuracy rate in determining the mastery degree of the knowledge point by the user.
It is to be added that the above knowledge point scoring model is used to preliminarily output the user's mastery degree of the knowledge point. Then, the terminal device can establish an initial potential feature matrix according to the mastery degree, and further update the potential feature matrix according to the user feature matrix and the knowledge point feature matrix on the basis. Therefore, a target scoring matrix with higher accuracy is obtained, and the accuracy of identifying the mastery degree of the target knowledge points by the target user is improved.
S1022, respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points.
In application, after the mastery degree of a plurality of knowledge points is determined, a potential scoring matrix which is subjected to normal distribution can be established, so that the theory of the obtained target scoring matrix is strict and has stronger interpretability.
Specifically, the potential scoring matrix R may be set to follow a gaussian distribution (normal distribution) with a mean value μ and a standard deviation σ, and the expression may be:
where Iij is an indication function, which indicates that if the degree of grasp of the knowledge point Vj by the student Ui meets the expected value, Iij is 1, and otherwise is 0. Wherein, p (RU, V, σ)2) A potential scoring matrix representing a standard deviation σ; t represents that the transposition step is executed on the matrix Ui to obtain a transposition matrix of the Ui.
It should be noted that, for a plurality of users and a plurality of knowledge points, a potential scoring matrix for each user and each knowledge point needs to be established. That is, the expression on the right side of the equal sign of the above expression means that p (RU, V, σ) is regarded as2) And representing the potential scoring matrix of the ith user and the jth knowledge point.
Referring to fig. 4, in one embodiment, the potential scoring matrix includes an indicator function; s1022, respectively constructing potential scoring matrices of the user and the knowledge points according to the mastery degrees of the knowledge points, and further including the following sub-steps S10221 to S10223, which are detailed as follows:
s10221, regarding the mastery degree of any knowledge point, if the mastery degree of the knowledge point is greater than a preset value, setting the output value of the indication function as a first target value, where the first target value is used to enhance the mastery degree of the knowledge point by the user. Alternatively, the first and second electrodes may be,
s10222, if the degree of knowledge of any knowledge point is less than or equal to a preset value, setting the output value of the indication function as a second target value, where the second target value is used to reduce the degree of knowledge of the knowledge point by the user.
S10223, constructing the potential scoring matrix according to the first target value or the second target value.
In application, the preset value, the first target value and the second target value may be values set by a user according to actual conditions, and the values may be changed by the user, which is not limited herein.
Specifically, reference may be made to the expression of the potential scoring matrix R in S1022, where Iij in the expression is an indication function, which indicates that if the mastery degree of the knowledge point Vj by the student Ui meets the expected value, Iij is 1, and otherwise is 0. At this time, the expected value is a predetermined value, 1 is a first target value, and 0 is a second target value. And a potential scoring matrix is established according to the numerical value output by the indication function, and the potential scoring matrix can be used for better expressing the mastery degree of the user on the knowledge point. Further, the value (predicted grasping degree) finally output from the potential score matrix is made closer to the actual value (actual grasping degree). Namely, after the feature matrix (potential scoring matrix) established according to the indication function is updated through the user feature matrix and the knowledge point feature matrix, when the mastery degree between the user and the knowledge point is identified according to the exercise data of the updated target scoring matrix, the accuracy of the estimated mastery degree is higher (namely, the estimated mastery degree is closer to the actual mastery degree of the user on the knowledge point).
Referring to fig. 5, in an embodiment, the step S104 of updating the potential scoring matrix through the user feature matrix and the knowledge point feature matrix to obtain a target scoring matrix further includes the following sub-steps S1041 to S1042, which are detailed as follows:
s1041, establishing an updating function through the user characteristic matrix, the knowledge point characteristic matrix and the potential scoring matrix.
In application, the update function may specifically be a joint distribution function, which is obtained by performing matrix multiplication on the user feature matrix, the knowledge point feature matrix, and the potential scoring matrix.
Specifically, reference may be made to the detailed descriptions in S103 and S1022 above, because the user feature matrix, the knowledge point feature matrix, and the potential scoring matrix are all normally distributed matrices. Therefore, the joint distribution of the three matrices R (potential scoring matrix), U (user feature matrix) and V (knowledge point feature matrix) can be obtained based on bayesian theory derivation. Namely, the three matrixes are multiplied, and the expression of the joint distribution function is as follows:
s1042, updating the potential scoring matrix according to the updating function to obtain a target scoring matrix.
In application, as can be seen from the function expression of the joint distribution in S1041, the joint distribution function is obtained by multiplying three matrices. Based on this, it can be considered that when the update function is updated, the three matrices are updated at the same time. Namely, the process of updating the updating function includes the process of updating the potential scoring matrix to obtain the target scoring matrix.
In application, when the update function is updated, the maximum likelihood estimation algorithm and the bayesian estimation algorithm can be used for processing, and the method is not limited.
Referring to fig. 6, in an embodiment, the step S1042 updates the potential scoring matrix according to the update function to obtain a target scoring matrix, and further includes the following sub-steps S10421-S10422, which are detailed as follows:
s10421, calculating a maximum value in the updating function according to a maximum likelihood estimation algorithm.
S10421, updating the potential scoring matrix through a gradient descent method based on the maximum value to obtain the target scoring matrix.
In application, the format of the joint distribution function expression in S1042 described above is consistent with that of the likelihood function expression. Based on this, the maximum likelihood estimation algorithm may be used to perform parameter solution on the joint distribution function, and then the joint distribution function is updated according to the solved parameters (e.g., the potential scoring matrix is updated).
Specifically, when calculating the maximum value in the update function, the above-mentioned joint distribution function may be subjected to logarithm processing, and the following expression may be obtained:
wherein C is a constant, and the meanings of the remaining letters can be specifically referred to the descriptions in S103 and S1022, which will not be described again. The parameter solving problem of the above formula can then be converted into a method of mathematically solving the minimum value according to a function. Specifically, the above formula can be specifically converted into:
wherein the content of the first and second substances,
at this time, the logarithmized functions (a function and B function) both carry "-", and the converted L function is not added with a "-sign. Based on this, it is considered that the minimum value of the L function is obtained after the minimum value is obtained, and the maximum value of the logarithmic function is obtained after "-" is added. Then, based on the maximum value, the parameter can be updated by a gradient descent method to obtain the parameter sigma2，
The value of (c). Based on this, the updated target scoring matrix can be obtained according to the above parameters and the expressions in S103 and S1022.
It should be noted that, the updated function is logarithmized, then the logarithmized function is transformed, and the minimum value of the transformed function is solved, which has the effect of simplifying the process of solving (calculating the maximum value) the joint distribution function.
In application, the gradient descent method includes, but is not limited to, a batch gradient descent method, a random gradient descent method, and a small batch gradient descent method, which is not limited thereto. In this embodiment, when updating the parameters by the batch gradient descent method, all samples (all problem data) are used for updating. Therefore, the potential scoring matrix can be updated by adopting a batch gradient descent method, so that the accuracy of identifying the user and the mastery degree of the knowledge point by the target scoring matrix is improved.
Referring to fig. 7, fig. 7 is a block diagram illustrating a structure of a knowledge point mastering level recognition apparatus according to an embodiment of the present application. The knowledge point mastering degree recognition apparatus in this embodiment includes modules for executing the steps in the embodiments corresponding to fig. 1 to 6. Please refer to fig. 1 to 6 and fig. 1 to 6 for the corresponding embodiments. For convenience of explanation, only the portions related to the present embodiment are shown. Referring to fig. 7, the knowledge point mastery degree recognition apparatus 700 includes: an obtaining module 710, a first establishing module 720, a second establishing module 730, an updating module 740, and an identifying module 750, wherein:
an obtaining module 710, configured to obtain exercise data of multiple users respectively, where the exercise data includes data obtained by the multiple users respectively practicing exercises on exercises of multiple knowledge points.
A first establishing module 720, configured to respectively establish potential scoring matrices for the multiple users and the multiple knowledge points according to the exercise data.
A second establishing module 730, configured to respectively establish a user feature matrix of the multiple users and a knowledge point feature matrix of the multiple knowledge points, where the user feature matrix and the knowledge point feature matrix both obey target distribution respectively.
And the updating module 740 is configured to update the potential scoring matrix based on the user feature matrix and the knowledge point feature matrix to obtain a target scoring matrix.
And the identifying module 750 is configured to identify the mastering degree of the target knowledge point by the target user according to the target scoring matrix and the data of practicing the problem of the target knowledge point by the target user.
In an embodiment, the obtaining module 710 is further configured to:
respectively counting the exercise time length of each user for practicing the exercise of the knowledge points aiming at any exercise in any knowledge point;
if the exercise making duration is less than the preset duration, deleting data for the user to exercise the exercises of the knowledge points;
and if the exercise making duration is greater than or equal to the preset duration, determining the data of the exercise of the knowledge points by the user as the exercise data.
In an embodiment, the first establishing module 720 is further configured to:
aiming at any user, inputting the data of practice of the user on the exercises of the knowledge points into a preset knowledge point scoring model respectively to obtain the mastering degree of the user on the knowledge points respectively;
and respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points.
In one embodiment, the potential scoring matrix includes an indicator function; the first establishing module 720 is further configured to:
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is greater than a preset numerical value, setting the output value of the indication function as a first target value, wherein the first target value is used for enhancing the mastery degree of the knowledge point by the user; alternatively, the first and second electrodes may be,
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is less than or equal to a preset numerical value, setting the output value of the indication function as a second target value, wherein the second target value is used for weakening the mastery degree of the knowledge point by the user;
constructing the potential scoring matrix according to the first target value or the second target value.
In an embodiment, the update module 740 is further configured to:
constructing an updating function through the user feature matrix, the knowledge point feature matrix and the potential scoring matrix;
and updating the potential scoring matrix according to the updating function to obtain a target scoring matrix.
In one embodiment, the update function is a joint distribution function; the update module 740 is further configured to:
and carrying out matrix multiplication processing on the user characteristic matrix, the knowledge point characteristic matrix and the potential scoring matrix to obtain the joint distribution function.
In an embodiment, the update module 740 is further configured to:
calculating a maximum value in the update function according to a maximum likelihood estimation algorithm;
and updating the potential scoring matrix through a gradient descent method based on the maximum value to obtain the target scoring matrix.
It should be understood that, in the structural block diagram of the knowledge point mastering degree recognition apparatus shown in fig. 7, each unit/module is used for executing each step in the embodiment corresponding to fig. 1 to 6, and each step in the embodiment corresponding to fig. 1 to 6 has been explained in detail in the above embodiment, and specific reference is made to the relevant description in the embodiment corresponding to fig. 1 to 6 and fig. 1 to 6, which is not repeated herein.
Fig. 8 is a block diagram of a terminal device according to another embodiment of the present application. As shown in fig. 8, the terminal apparatus 800 of this embodiment includes: a processor 810, a memory 820, and a computer program 830, such as a program for a knowledge point mastery level identification method, stored in the memory 820 and executable on the processor 810. The processor 810, when executing the computer program 830, implements the steps in each embodiment of the above-described knowledge point grasp degree identification method, for example, S101 to S105 shown in fig. 1. Alternatively, the processor 810, when executing the computer program 830, implements the functions of the modules in the embodiment corresponding to fig. 7, for example, the functions of the modules 710 to 750 shown in fig. 7, and refer to the related description in the embodiment corresponding to fig. 7 specifically.
Illustratively, the computer program 830 may be divided into one or more units, which are stored in the memory 820 and executed by the processor 810 to accomplish the present application. One or more elements may be a series of computer program instruction segments capable of performing specific functions, which are used to describe the execution of the computer program 830 in the terminal device 800.
The terminal equipment may include, but is not limited to, a processor 810, a memory 820. Those skilled in the art will appreciate that fig. 8 is merely an example of a terminal device 800 and does not constitute a limitation of terminal device 800 and may include more or fewer components than shown, or some components may be combined, or different components, e.g., terminal device may also include input output devices, network access devices, buses, etc.
The processor 810 may be a central processing unit, but may also be other general purpose processors, digital signal processors, application specific integrated circuits, off-the-shelf programmable gate arrays or other programmable logic devices, discrete gate or transistor logic, discrete hardware components, or the like. A general purpose processor may be a microprocessor or the processor may be any conventional processor or the like.
The storage 820 may be an internal storage unit of the terminal device 800, such as a hard disk or a memory of the terminal device 800. The memory 820 may also be an external storage device of the terminal device 800, such as a plug-in hard disk, a smart card, a flash memory card, etc. provided on the terminal device 800. Further, the memory 820 may also include both internal and external memory units of the terminal apparatus 800.
The above embodiments are only used to illustrate the technical solutions of the present application, and not to limit the same; although the present application has been described in detail with reference to the foregoing embodiments, it should be understood by those of ordinary skill in the art that: the technical solutions described in the foregoing embodiments may still be modified, or some technical features may be equivalently replaced; such modifications and substitutions do not substantially depart from the spirit and scope of the embodiments of the present application and are intended to be included within the scope of the present application.
Claims (10)
1. A knowledge point mastery degree recognition method is characterized by comprising the following steps:
acquiring exercise data of a plurality of users respectively, wherein the exercise data comprises data for the plurality of users to exercise exercises of a plurality of knowledge points respectively;
respectively establishing potential scoring matrixes of the users and the knowledge points according to the exercise data;
respectively establishing user feature matrixes of the users and knowledge point feature matrixes of the knowledge points, wherein the user feature matrixes and the knowledge point feature matrixes are subject to target distribution;
updating the potential scoring matrix through the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix;
and identifying the mastery degree of the target user on the target knowledge point according to the target scoring matrix and the data of the target user practicing the exercises of the target knowledge point.
2. The method for recognizing the degree of mastery of a knowledge point according to claim 1, wherein said acquiring exercise data of a plurality of users, respectively, comprises:
respectively counting the exercise time length of each user for practicing the exercise of the knowledge points aiming at any exercise in any knowledge point;
if the exercise making duration is less than the preset duration, deleting data for the user to exercise the exercises of the knowledge points;
and if the exercise making duration is greater than or equal to the preset duration, determining the data of the exercise of the knowledge points by the user as the exercise data.
3. The method for identifying the mastery level of a knowledge point according to claim 1, wherein the establishing potential scoring matrices for the plurality of users and the plurality of knowledge points respectively according to the problem data comprises:
aiming at any user, inputting the data of practice of the user on the exercises of the knowledge points into a preset knowledge point scoring model respectively to obtain the mastering degree of the user on the knowledge points respectively;
and respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points.
4. The method of recognizing knowledge point grasp degree according to claim 3, wherein said potential scoring matrix includes an indication function;
the respectively constructing potential scoring matrixes of the user and the knowledge points according to the mastery degrees of the knowledge points comprises the following steps:
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is greater than a preset numerical value, setting the output value of the indication function as a first target value, wherein the first target value is used for enhancing the mastery degree of the knowledge point by the user; alternatively, the first and second electrodes may be,
aiming at the mastery degree of any knowledge point, if the mastery degree of the knowledge point is less than or equal to a preset numerical value, setting the output value of the indication function as a second target value, wherein the second target value is used for weakening the mastery degree of the knowledge point by the user;
constructing the potential scoring matrix according to the first target value or the second target value.
5. The method for identifying the mastery level of a knowledge point according to claim 1, wherein the updating the potential scoring matrix by the user feature matrix and the knowledge point feature matrix to obtain a target scoring matrix comprises:
constructing an updating function through the user feature matrix, the knowledge point feature matrix and the potential scoring matrix;
and updating the potential scoring matrix according to the updating function to obtain a target scoring matrix.
6. The knowledge point mastery degree recognition method according to claim 5, wherein the update function is a joint distribution function;
the constructing an update function through the user feature matrix, the knowledge point feature matrix and the potential scoring matrix comprises:
and carrying out matrix multiplication processing on the user characteristic matrix, the knowledge point characteristic matrix and the potential scoring matrix to obtain the joint distribution function.
7. The method for identifying the degree of mastery of a knowledge point according to claim 5 or 6, wherein said updating the potential scoring matrix according to the updating function to obtain a target scoring matrix comprises:
calculating a maximum value in the update function according to a maximum likelihood estimation algorithm;
and updating the potential scoring matrix through a gradient descent method based on the maximum value to obtain the target scoring matrix.
8. An apparatus for recognizing a degree of grasp of a knowledge point, comprising:
the acquisition module is used for respectively acquiring exercise data of a plurality of users, wherein the exercise data comprises data for the plurality of users to respectively exercise exercises of a plurality of knowledge points;
the first establishing module is used for respectively establishing potential scoring matrixes of the users and the knowledge points according to the exercise data;
the second establishing module is used for respectively establishing a user characteristic matrix of the plurality of users and a knowledge point characteristic matrix of the plurality of knowledge points, and the user characteristic matrix and the knowledge point characteristic matrix are respectively subjected to target distribution;
the updating module is used for updating the potential scoring matrix based on the user characteristic matrix and the knowledge point characteristic matrix to obtain a target scoring matrix;
and the identification module is used for identifying the mastering degree of the target user on the target knowledge point according to the target scoring matrix and the data of practicing the target user on the problem of the target knowledge point.
9. A terminal device comprising a memory, a processor and a computer program stored in the memory and executable on the processor, characterized in that the processor implements the method according to any of claims 1 to 7 when executing the computer program.
10. A computer-readable storage medium, in which a computer program is stored which, when being executed by a processor, carries out the method according to any one of claims 1 to 7.
Priority Applications (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110083470.9A CN112785148A (en) | 2021-01-21 | 2021-01-21 | Knowledge point mastery degree identification method and device, terminal device and storage medium |
Applications Claiming Priority (1)
| Application Number | Priority Date | Filing Date | Title |
|---|---|---|---|
| CN202110083470.9A CN112785148A (en) | 2021-01-21 | 2021-01-21 | Knowledge point mastery degree identification method and device, terminal device and storage medium |
Publications (1)
| Publication Number | Publication Date |
|---|---|
| CN112785148A true CN112785148A (en) | 2021-05-11 |
Family
ID=75758356
Family Applications (1)
| Application Number | Title | Priority Date | Filing Date |
|---|---|---|---|
| CN202110083470.9A Pending CN112785148A (en) | 2021-01-21 | 2021-01-21 | Knowledge point mastery degree identification method and device, terminal device and storage medium |
Country Status (1)
| Country | Link |
|---|---|
| CN (1) | CN112785148A (en) |
Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256650A (en) * | 2017-06-20 | 2017-10-17 | 广东小天才科技有限公司 | A kind of exercise method for pushing, system and terminal device |
| CN109509126A (en) * | 2018-11-02 | 2019-03-22 | 中山大学 | A kind of personalized examination question recommended method based on user's learning behavior |
| US20190130511A1 (en) * | 2017-11-02 | 2019-05-02 | Act, Inc. | Systems and methods for interactive dynamic learning diagnostics and feedback |
| CN110019686A (en) * | 2019-04-11 | 2019-07-16 | 北京任学教育科技有限公司 | Determination method, apparatus, equipment and the storage medium of knowledge point master degree |
| CN110110226A (en) * | 2019-04-18 | 2019-08-09 | 国家电网有限公司 | A kind of proposed algorithm, recommender system and terminal device |
-
2021
- 2021-01-21 CN CN202110083470.9A patent/CN112785148A/en active Pending
Patent Citations (5)
| Publication number | Priority date | Publication date | Assignee | Title |
|---|---|---|---|---|
| CN107256650A (en) * | 2017-06-20 | 2017-10-17 | 广东小天才科技有限公司 | A kind of exercise method for pushing, system and terminal device |
| US20190130511A1 (en) * | 2017-11-02 | 2019-05-02 | Act, Inc. | Systems and methods for interactive dynamic learning diagnostics and feedback |
| CN109509126A (en) * | 2018-11-02 | 2019-03-22 | 中山大学 | A kind of personalized examination question recommended method based on user's learning behavior |
| CN110019686A (en) * | 2019-04-11 | 2019-07-16 | 北京任学教育科技有限公司 | Determination method, apparatus, equipment and the storage medium of knowledge point master degree |
| CN110110226A (en) * | 2019-04-18 | 2019-08-09 | 国家电网有限公司 | A kind of proposed algorithm, recommender system and terminal device |
Non-Patent Citations (2)
| Title |
|---|
| 李全等: "基于联合概率矩阵分解的个性化试题推荐方法", 《计算机应用》, vol. 38, no. 3, 10 March 2018 (2018-03-10), pages 639 - 643 * |
| 王伟;邵祝燕;周建阳;: "基于知识点的个性化习题推荐及其在医学计算机应用基础课程教学中的应用", 浙江医学教育, no. 04, 14 August 2020 (2020-08-14) * |
Similar Documents
| Publication | Publication Date | Title |
|---|---|---|
| CN107256650B (en) | Exercise pushing method and system and terminal equipment | |
| CN108197652B (en) | Method and apparatus for generating information | |
| CN111274411A (en) | Course recommendation method and device, electronic equipment and readable storage medium | |
| CN111159419B (en) | Knowledge tracking data processing method, system and storage medium based on graph convolution | |
| WO2022068435A1 (en) | Method for measuring knowledge point mastering state | |
| CN111241243A (en) | Knowledge measurement-oriented test question, knowledge and capability tensor construction and labeling method | |
| CN111914176B (en) | Question recommendation method and device | |
| WO2021174827A1 (en) | Text generation method and appartus, computer device and readable storage medium | |
| US11934790B2 (en) | Neural network training method and apparatus, semantic classification method and apparatus and medium | |
| CN112069329A (en) | Text corpus processing method, device, equipment and storage medium | |
| CN114742319A (en) | Method, system and storage medium for predicting scores of law examination objective questions | |
| KR102344724B1 (en) | Electronic apparatus for managing learning of student based on artificial intelligence, and learning management method | |
| WO2021047376A1 (en) | Data processing method, data processing apparatus and related devices | |
| CN112365384B (en) | Target event result index weight, influence factor value determination method and related device | |
| CN113283488A (en) | Learning behavior-based cognitive diagnosis method and system | |
| CN112598202B (en) | Test question difficulty evaluation method and device, storage medium and computing equipment | |
| CN116541711A (en) | Model training method, course recommendation method, device, equipment and medium | |
| CN112785148A (en) | Knowledge point mastery degree identification method and device, terminal device and storage medium | |
| CN112231373B (en) | Knowledge point data processing method, apparatus, device and computer readable medium | |
| CN115393132A (en) | Knowledge tracking model-based prediction method and related equipment | |
| CN111582404B (en) | Content classification method, device and readable storage medium | |
| CN112785039B (en) | Prediction method and related device for answer score rate of test questions | |
| CN114238106A (en) | Test time prediction method and device, electronic device and storage medium | |
| CN112528221A (en) | Knowledge and capability binary tracking method based on continuous matrix decomposition | |
| CN116433082B (en) | Evaluation report generation method and device, electronic equipment and storage medium |
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 |