A review content generation method, device, storage medium and electronic device

Abstract

The present application discloses a review content generation method, device, storage medium and electronic device, which relates to the field of data processing technology, including: determining the set of unmastered knowledge points corresponding to each target student in the syllabus knowledge points based on the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data; determining the first set of knowledge points to be reviewed by each target student within the review time and the different learning ability levels of each target student according to the set of unmastered knowledge points corresponding to each target student; generating the second set of knowledge points to be reviewed by the teacher within the review time according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time and the number of students who have not mastered; sending the second set of knowledge points to the corresponding target students. The present application can generate a more effective teaching review plan that improves review efficiency.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a review content generation method, device, storage medium and electronic device. Background Art

[0002] In the current review process, teachers cannot take into account the specific learning situation of each student due to the different situations of each student. Therefore, in the review process, it is impossible to accurately check and fill in the gaps for each student and maximize the student's score within a limited time.

[0003] At present, the teacher's final review content is mainly obtained by obtaining the teacher's teaching time and the knowledge points that need to be reviewed, determining the importance of the knowledge points that need to be reviewed, and filling the knowledge points and teaching time into the preset review content generation template according to the importance to generate the teacher's final review content.

[0004] However, using this review content generation method, which only generates review content based on teaching time and the importance of knowledge points, will result in the generated review content being unable to accurately improve students' review efficiency, thereby leading to poor review results for students. Summary of the invention

[0005] In view of this, the present application provides a review content generation method, device, storage medium and electronic device, the main purpose of which is to improve the current existing technology that only generates review content based on teaching time and the importance of knowledge points, which will result in the generated review content being unable to accurately improve students' review efficiency, thereby leading to poor review results for students.

[0006] In a first aspect, the present application provides a review content generation method, comprising:

[0007] Obtain the target students’ learning data, syllabus data, and review time;

[0008] Determine a set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points based on the correlation values ​​of the objective factor values ​​and the subjective factor values ​​of the knowledge point mastery in the learning data;

[0009] Determine the first set of knowledge points to be reviewed by each target student within the review time and the different learning ability levels of each target student according to the set of unmastered knowledge points corresponding to each target student;

[0010] Generate a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge point;

[0011] The second knowledge point set is sent to the corresponding target students.

[0012] In a second aspect, the present application provides a review content generation device, comprising:

[0013] An acquisition module is configured to acquire learning data, syllabus data, and review time of target students;

[0014] A determination module is configured to determine a set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points based on a correlation value between an objective factor value and a subjective factor value of the knowledge point mastery status in the learning data;

[0015] A grading module is configured to determine a first set of knowledge points to be reviewed by each target student within the review time and different learning ability levels of each target student according to a set of unmastered knowledge points corresponding to each target student;

[0016] A generating module is configured to generate a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge point;

[0017] The sending module is configured to send the second knowledge point set to the corresponding target students.

[0018] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, and when the computer program is executed by a processor, the review content generating method described in the first aspect is implemented.

[0019] In a fourth aspect, the present application provides an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein the processor implements the review content generation method described in the first aspect when executing the computer program.

[0020] By means of the above technical scheme, the present application provides a review content generation method, device, storage medium and electronic device. Compared with the current existing technology, the present application determines the first set of knowledge points to be reviewed by the target students in the syllabus knowledge points within the review time and the different learning ability levels of each target student through the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data, which can effectively improve the students' review efficiency and help students accurately find the content to be reviewed. Then, based on the first knowledge point set, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time and the number of students who have not mastered the content, a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels is generated. Students can be stratified according to their learning abilities. The second set of knowledge points for teachers at each level is generated based on the first set of knowledge points for students at that level. Teachers can help students review the specified teaching review content more accurately based on the knowledge points to be reviewed by students, thereby generating a more accurate and effective teaching review plan to help students improve their review efficiency and improve the students' review effect. BRIEF DESCRIPTION OF THE DRAWINGS

[0021] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0022] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0023] Figure 1 A schematic diagram of a process of generating review content provided by an embodiment of the present application is shown;

[0024] Figure 2 A schematic diagram of a process of generating review content provided by an embodiment of the present application is shown;

[0025] Figure 3 A schematic diagram of a process of generating review content provided by an embodiment of the present application is shown;

[0026] Figure 4 A schematic diagram showing an example provided by an embodiment of the present application;

[0027] Figure 5 A schematic diagram of the structure of a review content generation device provided in an embodiment of the present application is shown;

[0028] Figure 6 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0029] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0030] In order to improve the existing technology, the review content is currently generated only based on the teaching time and the importance of the knowledge point, which will result in the generated review content failing to accurately improve the students' review efficiency, thereby resulting in poor review results for students. This embodiment provides a method for generating review content, such as Figure 1 As shown, the method includes:

[0031] Step 101: Obtain the target student's learning data, syllabus data, and review time.

[0032] In an embodiment of the present application, the target student may be any one or more of the students who need to review, and accordingly, the learning data may be the student's historical learning data, which may specifically include the student's historical grades, the student's regular homework grades, random classroom test grades, the student's average study time, classroom performance scores, teacher evaluation scores, etc.

[0033] In some examples, the syllabus data may include syllabus knowledge points and scores corresponding to the syllabus knowledge points. The syllabus knowledge points may be a set of examination knowledge points corresponding to the examinations that the target students take in the examination syllabus of the Ministry of Education. Correspondingly, the review time may be the time between the students starting to review and the examination.

[0034] For example, if the target students are all students in grade M, the learning data, syllabus knowledge points and review time of all students in grade M are obtained.

[0035] Step 102: Determine a set of unmastered knowledge points corresponding to each target student in the syllabus knowledge points based on the correlation values ​​between the objective factor values ​​and the subjective factor values ​​of the knowledge point mastery in the learning data.

[0036] Optionally, the subjective factor value of the knowledge point mastery in the learning data can be determined by the subjective factors that affect the students' mastery of the knowledge points. Specifically, it can be obtained based on at least the students' average learning time, classroom performance scores, and teacher evaluation scores in the learning data.

[0037] Correspondingly, the objective factor value of the knowledge point mastery in the learning data can be determined by the objective factors that affect the students' mastery of knowledge points. Specifically, it can be obtained based on at least the students' historical grades, regular homework grades, and random classroom test grades in the learning data.

[0038] For this embodiment, the set of unmastered knowledge points corresponding to each target student can be a combination of knowledge points that need to be reviewed by each target student in the syllabus knowledge points. It should be noted that in this embodiment, each target student corresponds to a set of unmastered knowledge points.

[0039] Step 103: Determine the first set of knowledge points to be reviewed by each target student within the review time and the different learning ability levels of each target student based on the set of unmastered knowledge points corresponding to each target student.

[0040] In an embodiment of the present application, the first set of knowledge points to be reviewed may be a set of knowledge points that the students need to review within the review time among the set of knowledge points that have not been mastered.

[0041] It should be noted that each target student needs to determine the corresponding learning ability level, and the corresponding learning ability levels of different students may be consistent or inconsistent.

[0042] Step 104: Generate a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels based on the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge points.

[0043] For this embodiment, the knowledge point score corresponding to each knowledge point can be the examination score corresponding to each knowledge point specified in the examination syllabus of the Ministry of Education, that is, the score corresponding to the knowledge point in the examination syllabus; accordingly, the review time corresponding to each knowledge point can include the time that students need to review after class and the time that teachers need to explain in class. It should be noted that the review time can include the teacher's explanation time in class and the student's independent review time after class.

[0044] In some examples, students of different ability levels are assigned different review plans, and the review plans can be implemented by one teacher or by different teachers.

[0045] When executed by a teacher, the second set of knowledge points to be reviewed by the target students of the level is determined based on the time available for the teacher for a learning ability level. In this case, the time a teacher uses for a learning ability level will be divided by the number of learning ability levels. When dividing the time, it can be divided equally or based on a predetermined logic. Specifically, the embodiments of the present disclosure do not limit this.

[0046] When different teachers provide individual tutoring for students of different learning ability levels, the overall time of the teachers at that level should be allocated to the students at that level.

[0047] How the teacher's review time is determined is based on specific circumstances, and the embodiments of the present disclosure do not limit this.

[0048] It should be noted that the second knowledge point set generated by the present application can be the knowledge point set with the highest score improvement for students at each level. Specifically, the highest score improvement value can be the highest cumulative value of the knowledge point scores from knowledge points that have never been mastered to knowledge points that have been mastered.

[0049] Step 105: Send the second knowledge point set to the corresponding target students.

[0050] In an embodiment of the present application, when the second knowledge point set is sent to the target student, it can be a client sent to the student. The client refers to a program corresponding to the server that provides local services to the user. The client is usually installed on the user's computer or device and runs in conjunction with the server to achieve data exchange and functional services. The client can be any form of application as long as it can communicate with the remote server. Specifically, the client in the embodiment of the present application can be a program installed on the teacher's or student's computer or device.

[0051] Furthermore, the client is used to output the teaching review content, and the teaching content output can be in different forms, such as tables, files, animations, sounds, etc.

[0052] Compared with the current existing technology, the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data of this embodiment determines the first knowledge point set to be reviewed by the target students in the syllabus knowledge points within the review time and the different learning ability levels of each target student, which can effectively improve the students' review efficiency and help students accurately find the content to be reviewed. Then, based on the first knowledge point set, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time and the number of students who have not mastered the content, a second knowledge point set to be reviewed by the teacher within the review time for different learning ability levels is generated. Students can be stratified according to their learning ability. The second knowledge point set of teachers at each level is generated based on the first knowledge point set of students at that level. Teachers can help students review the designated teaching review content more accurately based on the students' knowledge points to be reviewed, thereby generating a more accurate and effective teaching review plan to help students improve their review efficiency and improve students' review effect.

[0053] As a refinement and extension of the above embodiment, when determining the set of unmastered knowledge points corresponding to each target student in the syllabus knowledge points based on the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data, the following methods may be used but are not limited to: Figure 2 As shown, the method includes:

[0054] Step 201: Based on the learning data, a correlation analysis is performed on the objective factor value and the subjective factor value of the knowledge point mastery status in the syllabus data to obtain the correlation value between the objective factor value and the subjective factor value.

[0055] Optionally, step 201 may be performed using, but not limited to, the following methods, including:

[0056] Step 11: Perform linear regression on the student's historical scores, regular homework scores, random classroom test scores, and constant terms in the learning data to obtain the objective factor values.

[0057] In some examples, linear regression processing is performed on the student's historical scores, the student's regular homework scores, the random classroom test scores, and the constant term in the learning data, and the objective factor value can be calculated by the following formula 3:

[0058] Y=K0+A*V1+B*V2+C*V3 (Formula 3)

[0059] In Formula 3, Y is the coefficient of students’ mastery of objective knowledge points, A is the student’s history score, B is the student’s regular homework score, C is the random classroom test score, K0 is the constant term, and V1, V2, and V3 are partial regression coefficients.

[0060] In the present application, linear regression is a statistical method used to establish a linear relationship between a dependent variable (also called a response variable or target variable) and one or more independent variables (also called explanatory variables or features). It is one of the most basic forms of regression analysis and is widely used in fields such as data analysis, predictive modeling, and machine learning.

[0061] Step 12: Perform linear regression on the average learning time of students, classroom performance scores, teacher evaluation scores, and constant terms in the learning data to obtain the subjective factor value.

[0062] Optionally, the partial regression coefficient is an important concept in multiple linear regression analysis. In multiple linear regression, the partial regression coefficient measures the marginal contribution of an independent variable to the dependent variable after controlling the influence of other independent variables. In other words, the partial regression coefficient reflects the average effect of an independent variable on the dependent variable when other independent variables remain unchanged.

[0063] Accordingly, the average learning time of students, classroom performance score, teacher evaluation score, and constant term in the learning data are subjected to linear regression to obtain the subjective factor value, which can be calculated using Formula 4 as shown below:

[0064] P=N0+D*H1+E*H2+F*H3 (Formula 4)

[0065] In Formula 4, P is the coefficient of students' subjective knowledge mastery, D is the average learning time of students, E is the classroom performance score, F is the teacher's evaluation score, N0 is a constant term, and H1, H2, and H3 are partial regression coefficients.

[0066] Step 13: Calculate the correlation value between the objective factor value and the subjective factor value by using the following formula 1;

[0067] M=∑(Yi-Ymean)*(Pi-Pmean) / (n*sY*sP) (Formula 1)

[0068] Among them, Yi and Pi represent the numerical value of the i-th student respectively, Ymean and Pmean represent the mean values ​​of Y and P respectively, sYsP represent the standard deviation of YP respectively; the value range of M is [-1,1]. When the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P; when the M value = 0, it means there is no correlation; when the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P.

[0069] Step 202: Determine a set of unmastered knowledge points corresponding to each target student in the syllabus knowledge points according to a threshold interval of correlation values ​​between the objective factor values ​​and the subjective factor values.

[0070] Optionally, step 203 may specifically include:

[0071] Step 21, determine the threshold interval of the correlation value between the objective factor value and the subjective factor value of the target student's corresponding knowledge point; if the correlation value between the objective factor value and the subjective factor value of the target student's corresponding target knowledge point is in the threshold interval [-1,0] or (0,1], and at least one of the objective factor value or the subjective factor value is less than the predetermined threshold, then execute step 22; otherwise, execute step 23.

[0072] Step 22: Determine whether the target students have not mastered the target knowledge points.

[0073] Step 23: Determine whether the target students have mastered the target knowledge points.

[0074] In the embodiment of the present application, the predetermined threshold can be set by itself. For example, if the predetermined threshold is 60, the value range of M is [-1, 1]. When the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P, indicating that the evaluation credibility of Y and P is high. When the M value = 0, it means that there is no correlation and the evaluation credibility is low. When the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P. If the M value is in the interval [-1, 0] or the M value is in the interval (0, 1] and one of X or Y is less than 60, it is determined that the student has not mastered the knowledge point, otherwise the student has mastered the knowledge point.

[0075] For example, if the predetermined threshold is 30, the M value is in the interval [-1, 0] or the M value is in the interval (0, 1] and one of X or Y is less than 30, then it is determined that the student has not mastered the knowledge point, otherwise the student has mastered the knowledge point. Examples are not given here one by one.

[0076] Further, when determining the different learning ability levels of each target student according to the set of unmastered knowledge points corresponding to each target student, the following methods may be used but are not limited to: Figure 3 As shown, the method includes:

[0077] Step 301: Determine the student ability value corresponding to each target student based on the similarity between the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed corresponding to the target student.

[0078] In an embodiment of the present application, the first set of knowledge points to be reviewed can be the set of knowledge points with the highest score improvement values ​​corresponding to each target student. Specifically, the first set of knowledge points with the highest score improvement values ​​for each target student within the review time can be generated by a backpack model. Specifically, the set of unmastered knowledge points, the knowledge point scores corresponding to each knowledge point, and the review time can be put into the student backpack, and the backpack capacity can be set, so as to obtain the student review content with the highest score improvement value for each student within the preset review time.

[0079] In some examples, the Knapsack Model is a classic combinatorial optimization problem that is widely used in computer science and operations research. This problem can be described as: given a set of items, each item has its own weight and value, how to select items within a limited total weight to maximize the total value of the items.

[0080] In the embodiment of the present application, the preset threshold interval may be a pre-set learning ability interval, that is, each target student may be classified into a corresponding learning ability level according to the preset threshold interval.

[0081] Optionally, when step 301 is specifically executed, the following methods may be used but are not limited to:

[0082] According to the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed by the target student, the student ability value corresponding to each target student is calculated by the following formula 2, and the formula 2 includes:

[0083] J(A,B)=|A∪B| / |A∩B| (Formula 2)

[0084] Among them, J is the student ability score, A is the set of knowledge points that each student has not mastered, B is the set of the first knowledge points to be reviewed by each student, |A∩B| is the size of the intersection of sets A and B, and |A∪B| is the size of the union of sets A and B.

[0085] For example, if the set of unmastered knowledge points includes knowledge point 1, knowledge point 2, knowledge point 3, knowledge point 4 and knowledge point 5, and the first knowledge point set corresponding to target student 1 includes knowledge point 1 and knowledge point 2, then the student ability value of target student 1 can be determined to be 2 / 5; for another example, the first knowledge point set corresponding to target student 2 includes knowledge point 2, knowledge point 3 and knowledge point 4, then the student ability value of target student 2 can be determined to be 3 / 5, and so on, and examples will not be given one by one here.

[0086] Step 302: According to the relationship between the student ability value and the preset threshold range, each target student is assigned to a corresponding preset learning ability level, and the different learning ability levels of each target student are determined.

[0087] Among them, when executing step 302, J(A, B) can be sorted and a judgment threshold (g, f) can be set to obtain, specifically, g<f; when J(A, B)≥f, it is taken as a set M; when f>J(A, B)≥g, it is taken as a set F; when J(A, B)<g, it is taken as a set K; and students are assigned to corresponding classes according to the set they belong to.

[0088] Exemplarily, if the judgment threshold (g, f) is set, g is 2 / 5, and f is 4 / 5, three learning ability levels can be determined. Specifically, the first learning ability level can be J(A, B)≥4 / 5, the second learning ability level can be 2 / 5>J(A, B)≥4 / 5, and the third learning ability level can be J(A, B)<2 / 5. Then, according to the student ability value corresponding to target student 1 of 2 / 5, the target student can be assigned to the second learning ability level, and according to the student ability value corresponding to target student 2 of 3 / 5, the target student can be assigned to the second learning ability level.

[0089] Furthermore, when executing step 105, the following method may be used, but is not limited to the following method, which includes:

[0090] Step 41, determining the total score of each knowledge point corresponding to each knowledge point based on the product of the number of students who have not mastered each knowledge point in the first knowledge point set of different learning ability levels and the score of the knowledge point;

[0091] Step 42: input the total score and review time into a preset backpack model to determine a set of target knowledge points that can be put into the backpack of the preset backpack model;

[0092] Step 43: determine the target knowledge point set as the second knowledge point set to be reviewed by the teacher within the review time.

[0093] When executing step 41 to step 43, the following methods may be used, including:

[0094] The review time and knowledge point scores corresponding to the knowledge points that a single student has not mastered can be shown in the following Table 1:

[0095] Table 1

[0096]

[0097] For example, there are N unlearned knowledge points and a backpack with a capacity of V (the remaining class hours for the subject). The time occupied by the i-th knowledge point is Ci and the score is Wi. Find out which knowledge points can maximize the total score in the backpack (how to get the maximum score improvement within a limited review time).

[0098] The transfer equation is shown in Formula 5 below:

[0099] F[i,v] = max{F[i-1,v], F[i-1,v-Ci] + Wi} (Formula 5)

[0100] In formula 5, the array is initialized to dp[N+1][W+1], where N is the knowledge point that has not been mastered, W is the remaining class hours for the subject, and dp[i][j] represents the maximum value of the first i knowledge points placed in a backpack with a capacity of j.

[0101] Furthermore, all elements in the dp array are initialized to 0. Traverse the unlearned knowledge points. For each knowledge point i, start from the backpack capacity W and traverse in reverse order to the weight w of item i, and update the value in the dp array: if w>j, it means that the current backpack capacity cannot accommodate item i, so dp[i][j]=dp[i-1][j], that is, do not select the current item and keep the maximum value of the first i-1 items.

[0102] Correspondingly, if w<=j, the current backpack can put down item i, update dp[i][j], and take the larger value of the current item value v[i] plus the previous state dp[i-1][jw] (that is, the maximum value under the remaining capacity): dp[i][j]=max(dp[i-1][j],dp[i-1][jw] + v[i]). After traversing all items, dp[N][W] is the maximum value after putting in all items. Abstractly calculate the ID set of the knowledge points that the student should review.

[0103] The most reviewed knowledge points of all students are obtained, and the knowledge points that all students should review are obtained (the number of repetitions of each knowledge point), and then a review plan for the whole class is generated. The situation of the missing knowledge points in the class can be shown in Table 2 below:

[0104] Table 2

[0105]

[0106] In some examples, the current teacher cannot take into account the specific learning situation of each student during the review process due to the inconsistency of each student's situation. Therefore, it is impossible to accurately check and fill in the gaps for each student during the review process, and maximize the student's score within a limited time. Students do not know how to review at the end of the semester, grasp the key points and fill in the gaps: If there is no clear review goal and plan, students will feel confused and do not know what to review and how to start the review. Therefore, making a detailed review plan, including the content to be reviewed every day, review time, review methods, etc., can help students review better. If students do not master the knowledge points in their usual study, they will feel at a loss when reviewing. Therefore, students need to listen carefully, take notes, and review and consolidate the knowledge points they have learned in time during their usual study. Some students may simply repeat the textbooks or notes without using more effective review methods, such as summarizing, doing exercises, and discussing and communicating. Therefore, students need to try different review methods to find the most suitable method for themselves.

[0107] During the learning process, students may not have a clear understanding of the knowledge structure of the semester, or may not fully understand the knowledge points in the course. However, the review by the teacher at the end of the semester is conducted uniformly, and there are only limited class hours, which cannot cover every student, and each student's learning ability is different.

[0108] Compared with the current existing technology, this embodiment determines the set of unmastered knowledge points corresponding to each student in the knowledge point set of the syllabus, and then generates the student review content with the highest score improvement value for each student within the preset review time based on the knowledge point score and review time corresponding to each knowledge point in the unmastered knowledge point set, which can effectively improve the students' review efficiency and help students accurately find the content to be reviewed; by summarizing the stratified student review content, the teacher's corresponding knowledge point set to be taught is obtained, and then based on the knowledge point score, review time and the number of students who have not mastered the knowledge point set to be taught, the teacher generates the teaching review content with the highest overall score improvement value within the preset teaching review time, which can allocate students with similar learning abilities to the same level, avoiding the situation where high-ability students waste time and low-ability students do not understand thoroughly due to different student abilities; using the optimal solutions of all students as source information and using the backpack again to figure out how the teacher can obtain the overall maximum score improvement within a limited time, the teacher can help specify the teaching review content based on the student review plan, and the teacher can more accurately and effectively help students improve their scores and help students improve their review efficiency.

[0109] In order to illustrate the specific implementation process of this embodiment, the following specific application examples are given: Figure 4 As shown, but not limited to:

[0110] If you need to generate a review plan for students and teachers for the final exam of semester A, the teacher needs to enter the Ministry of Education's syllabus for the final exam of semester A and the corresponding scores into the system, number the knowledge points in the syllabus, and then set the time the teacher needs to review each knowledge point in the syllabus in class.

[0111] According to the student's history score A, the student's regular homework score B, the random classroom test score C, and the constant term K0, linear regression is performed. V1, V2, and V3 are partial regression coefficients to determine the student's objective factors;

[0112] Linear regression is performed based on the average learning time D, classroom performance score E, teacher evaluation score F, and constant term N0. H1, H2, and H3 are partial regression coefficients to determine the subjective factors of students.

[0113] Compare the two to get the correlation and judge the student's mastery M. Among them, the value range of M is [-1,1]. When the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P, indicating that the evaluation credibility of Y and P is high. When the M value = 0, it means that there is no correlation and the evaluation credibility is low. When the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P. If the M value is in the interval [-1,0] or the M value is in the interval (0,1] and one of X or Y is less than 60, it is judged that the student has not mastered the knowledge point, otherwise the student has mastered the knowledge point.

[0114] Generate an ID for the set of unmastered knowledge points for each student, put each student's set of unmastered knowledge points into the student's backpack, determine the set of knowledge points to be reviewed with the highest improvement score for each student through the backpack algorithm, and generate a review score improvement plan for each student within a limited time based on the existing review time and the set of knowledge points to be reviewed.

[0115] Collect each student's set A of unmastered knowledge points and set B of knowledge points to be reviewed, and calculate the similarity between set A and set B through J(A,B)=|A∪B| / |A∩B|, where J is the student's ability score, |A∩B| is the size of the intersection of sets A and B, and |A∪B| is the size of their union.

[0116] Sort the students' ability scores J(A, B) and set the judgment threshold (g, f), where g<f; when J(A, B)≥f, divide the corresponding students into set M; when f>J(A, B)≥g, divide the corresponding students into set F; when J(A, B)<g, divide the corresponding students into set K; assign students in different sets to corresponding levels.

[0117] For students at different levels, input the teacher's available review time W for different subjects and abstract the teacher's backpack model. The model in the teacher's backpack is a backpack including N unmastered knowledge points and a capacity of V (the remaining class hours for the subject). The time occupied by the i-th knowledge point is Ci and the score is Wi. The transfer equation is used to find out which knowledge points can maximize the total score in the backpack (that is, to solve how to obtain the maximum score improvement within a limited review time).

[0118] The transfer equation is as follows: F[i,v]=max{F[i-1,v],F[i-1,v-Ci] + Wi}

[0119] In the teacher's backpack model, the array is initialized to dp[N+1][W+1], where N is the knowledge point that has not been mastered, W is the remaining class hours for the subject, and dp[i][j] represents the maximum value of the first i knowledge points put into a backpack with a capacity of j. All elements in the dp array are initialized to 0.

[0120] Traverse the knowledge points that have not been mastered. For each knowledge point i, start from the backpack capacity W and traverse in reverse order to the weight w of item i, and update the value in the dp array: if w>j, it means that the current backpack capacity cannot accommodate item i, so dp[i][j]=dp[i-1][j], that is, do not select the current item and keep the maximum value of the previous i-1 items. If w<=j, the current backpack can accommodate item i, update dp[i][j], and take the larger value of the current item value v[i] plus the previous state dp[i-1][jw] (that is, the maximum value under the remaining capacity): dp[i][j]= max(dp[i-1][j], dp[i-1][jw]+ v[i]).

[0121] After traversing all the items, dp[N][W] is the maximum value after putting in all the items, that is, the abstract calculation of the ID set of the knowledge points that the student should review, and the set of knowledge points to be reviewed with the highest score improvement value for all students, and then the review plan with the highest score improvement value obtained by the teacher.

[0122] Compared with the current existing technology, the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data of this embodiment determines the first knowledge point set to be reviewed by the target students in the syllabus knowledge points within the review time and the different learning ability levels of each target student, which can effectively improve the students' review efficiency and help students accurately find the content to be reviewed. Then, based on the first knowledge point set, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time and the number of students who have not mastered the knowledge point, a second knowledge point set to be reviewed by the teacher at different learning ability levels within the review time is generated, and students can be stratified according to their learning abilities, Students with similar learning abilities are assigned to the same level to avoid the situation where high-ability students waste time and low-ability students do not understand thoroughly due to different abilities. The second knowledge point set of teachers at each level is generated based on the first knowledge point set of students at that level, which is equivalent to taking the optimal solution of all students as source information and using the backpack again to figure out how teachers can obtain the overall maximum score improvement within a limited time. This allows teachers to help students review the designated teaching review content more accurately based on the knowledge points to be reviewed, and then generate more accurate and effective teaching review plans to help students improve their review efficiency, thereby improving students' review effects.

[0123] Further, as Figure 1 and Figure 2 The specific implementation of the method shown in the embodiment provides a review content generation device, such as Figure 5 As shown, the device includes: an acquisition module 41, a determination module 42, a classification module 43, a generation module 44, and a sending module 45.

[0124] An acquisition module 41 is configured to acquire learning data, syllabus data and review time of a target student;

[0125] A determination module 42 is configured to determine a set of unmastered knowledge points corresponding to each target student in the syllabus knowledge points based on a correlation value between an objective factor value and a subjective factor value of the knowledge point mastery status in the learning data;

[0126] The grading module 43 is configured to determine the first set of knowledge points to be reviewed by each target student within the review time and the different learning ability levels of each target student according to the set of unmastered knowledge points corresponding to each target student;

[0127] A generating module 44 is configured to generate a second set of knowledge points to be reviewed by the teacher at different learning ability levels within the review time according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge point;

[0128] The sending module 45 is configured to send the second knowledge point set to the corresponding target students.

[0129] In some examples of the present embodiment, the determination module 42 is specifically configured to perform a correlation analysis on the objective factor values ​​and the subjective factor values ​​of the knowledge point mastery in the syllabus data based on the learning data to obtain the correlation values ​​of the objective factor values ​​and the subjective factor values; and determine the set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points according to the threshold interval of the correlation values ​​of the objective factor values ​​and the subjective factor values.

[0130] In some examples of this embodiment, the determination module 42 is further configured to perform linear regression processing on the student's historical scores, the student's regular homework scores, the random classroom test scores, and the constant term in the learning data to obtain the objective factor value; perform linear regression processing on the student's average learning time, classroom performance score, teacher evaluation score, and the constant term in the learning data to obtain the subjective factor value; calculate by the following formula 1 to obtain the correlation value of the objective factor value and the subjective factor value;

[0131] M=∑(Yi-Ymean)*(Pi-Pmean) / (n*sY*sP) Formula 1; where Yi and Pi represent the numerical value of the i-th student respectively, Ymean and Pmean represent the mean values ​​of Y and P respectively, and sYsP represents the standard deviation of YP respectively; the value range of M is [-1,1]. When the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P; when the M value = 0, it means there is no correlation; when the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P.

[0132] In some examples of the present embodiment, the determination module 42 is further configured to determine a threshold interval in which the correlation value of the objective factor value and the subjective factor value of the target student's corresponding knowledge point is located; if the correlation value of the objective factor value and the subjective factor value of the target student's corresponding target knowledge point is in the threshold interval [-1,0] or (0,1], and at least one of the objective factor value or the subjective factor value is less than a predetermined threshold, it is determined that the target student has not mastered the target knowledge point; otherwise, it is determined that the target student has mastered the target knowledge point.

[0133] In some examples of the present embodiment, the grading module 43 is specifically configured to determine the student ability value corresponding to each target student based on the similarity between the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed by the target student; and assign each target student to a corresponding preset learning ability level based on the relationship between the student ability value and the preset threshold range, so as to determine the different learning ability levels of each target student.

[0134] In some examples of the present embodiment, the grading module 43 is further specifically configured to calculate, based on the set of unmastered knowledge points corresponding to each target student and the set of first knowledge points to be reviewed by the target student, the following formula 2 is used to obtain the student ability value corresponding to each target student. Formula 2 includes: J(A,B)=|A∪B| / |A∩B|Formula 2; wherein J is the student ability score, A is the set of unmastered knowledge points for each student, B is the set of first knowledge points to be reviewed by each student, |A∩B| is the size of the intersection of sets A and B, and |A∪B| is the size of the union of sets A and B.

[0135] In some examples of the present embodiment, the generation module 44 is further specifically configured to determine the total knowledge point score corresponding to each knowledge point based on the product of the number of students who have not mastered each knowledge point in the first knowledge point set at different learning ability levels and the score of the knowledge point; input the total score and the review time into a preset backpack model to determine a set of target knowledge points that can be placed in the backpack of the preset backpack model; and determine the set of target knowledge points as a set of second knowledge points to be reviewed by the teacher within the review time.

[0136] It should be noted that for other corresponding descriptions of the functional units involved in the review content generation device provided in this embodiment, reference can be made to Figure 1 and Figure 2 The corresponding description in will not be repeated here.

[0137] Based on the above Figure 1 and Figure 2The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figure 1 and Figure 2 The method shown.

[0138] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0139] like Figure 6 The figure shows a hardware structure diagram of an electronic device of the present invention, including:

[0140] at least one processor 501; and,

[0141] A memory 502 is communicatively connected to at least one of the processors 501; wherein,

[0142] The memory 502 stores instructions that can be executed by at least one of the processors. The instructions are executed by at least one of the processors so that the at least one of the processors can execute the review content generation method as described above.

[0143] Figure 6 A processor 501 is taken as an example.

[0144] The electronic device may further include: an input device 503 and a display device 504 .

[0145] The processor 501, the memory 502, the input device 503 and the display device 504 may be connected via a bus or other means, and the figure takes the connection via a bus as an example.

[0146] The memory 502 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the review content generation method in the embodiment of the present application, for example, Figure 1 , Figure 2 The processor 501 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 502, that is, the review content generation method in the above embodiment is implemented.

[0147] The memory 502 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required by at least one function; the data storage area may store data created according to the use of the review content generation method, etc. In addition, the memory 502 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 502 may optionally include a memory remotely arranged relative to the processor 501, and these remote memories may be connected to the device for executing the review content generation method via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0148] The input device 503 can receive input user clicks and generate signal inputs related to user settings and function controls of the review content generation method. The display device 504 can include display devices such as a display screen.

[0149] The one or more modules are stored in the memory 502 , and when executed by the one or more processors 501 , the review content generation method in any of the above method embodiments is executed.

[0150] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0151] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0152] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0153] Through the description of the above implementation methods, those skilled in the art can clearly understand that the present application can be implemented by means of software plus a necessary general hardware platform, or by hardware. By applying the solution of this embodiment, compared with the current prior art, the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data of this embodiment determines the first set of knowledge points to be reviewed by the target students within the review time in the syllabus knowledge points and the different learning ability levels of each target student, which can effectively improve the students' review efficiency and help students accurately find the content to be reviewed. Then, based on the first set of knowledge points, the knowledge point scores corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge, a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels is generated, and students can be reviewed according to their learning abilities. The students are stratified and assigned to the same level with similar learning abilities to avoid the situation in which high-ability students waste time and low-ability students do not understand thoroughly due to different abilities of students. The second knowledge point set of teachers at each level is generated based on the first knowledge point set of students at that level, which is equivalent to taking the optimal solution of all students as source information and using the backpack again to figure out how teachers can obtain the overall maximum score improvement within a limited time. This allows teachers to help students review the designated teaching review content more accurately based on the knowledge points to be reviewed, and then generate more accurate and effective teaching review plans to help students improve their review efficiency, thereby improving students' review effects.

[0154] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0155] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A review content generation method, characterized in that: include: Obtain the target students’ learning data, syllabus data, and review time; Determine the set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points based on the correlation values ​​of the objective factor values ​​and the subjective factor values ​​of the knowledge point mastery in the learning data, including: performing a correlation analysis between the objective factor values ​​and the subjective factor values ​​of the knowledge point mastery in the syllabus data based on the learning data to obtain the correlation values ​​of the objective factor values ​​and the subjective factor values, including: performing linear regression processing on the student's historical grades, the student's regular homework grades, the random classroom test grades, and the constant term in the learning data to obtain the objective factor value; performing linear regression processing on the student's average learning time, classroom performance score, teacher evaluation score, and the constant term in the learning data to obtain the subjective factor value; and calculating by the following formula 1 to obtain the correlation value of the objective factor value and the subjective factor value; M=∑(Yi-Ymean)*(Pi-Pmean) / (n*sY*sP)Formula 1 Among them, Yi and Pi represent the objective factor value and subjective factor value of the i-th student respectively, Ymean and Pmean represent the mean values ​​of Y and P respectively, sYsP represent the standard deviation of YP respectively; the value range of M is [-1,1], when the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P; when the M value = 0, it means there is no correlation, and when the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P; According to the threshold interval where the correlation value of the objective factor value and the subjective factor value is located, determining the set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points, including: determining the threshold interval where the correlation value of the objective factor value and the subjective factor value of the knowledge point corresponding to the target student is located; if the correlation value of the objective factor value and the subjective factor value corresponding to the target knowledge point of the target student is in the threshold interval [-1,0] or (0,1] and at least one of the objective factor value or the subjective factor value is less than a predetermined threshold, it is determined that the target student has not mastered the target knowledge point; otherwise, it is determined that the target student has mastered the target knowledge point; Determine the first set of knowledge points to be reviewed by each target student within the review time and the different learning ability levels of each target student according to the set of unmastered knowledge points corresponding to each target student; Generate a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge point; The second knowledge point set is sent to the corresponding target students.

2. The method according to claim 1, characterized in that Determining the different learning ability levels of each target student based on the set of unmastered knowledge points corresponding to each target student includes: Determine the student ability value corresponding to each target student according to the similarity between the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed corresponding to the target student; According to the relationship between the student ability value and the preset threshold range, each of the target students is assigned to a corresponding preset learning ability level, and a different learning ability level of each of the target students is determined.

3. The method according to claim 2, characterized in that Determining the student ability value corresponding to each target student according to the similarity between the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed corresponding to the target student includes: According to the set of unmastered knowledge points corresponding to each target student and the first set of knowledge points to be reviewed by the target student, the student ability value corresponding to each target student is calculated by the following formula 2, and the formula 2 includes: J(A,B)=|A∪B| / |A∩B|Formula 2 Among them, J is the student ability score, A is the set of knowledge points that each student has not mastered, B is the set of the first knowledge points to be reviewed by each student, |A∩B| is the size of the intersection of sets A and B, and |A∪B| is the size of the union of sets A and B.

4. The method according to any one of claims 1 to 3, characterized in that The generating of a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge points comprises: Determine the total score of each knowledge point based on the product of the number of students who have not mastered each knowledge point in the first knowledge point set at different learning ability levels and the score of the knowledge point; Input the total score and review duration into a preset backpack model to determine a set of target knowledge points that can be put into the backpack of the preset backpack model; The target knowledge point set is determined as a second knowledge point set to be reviewed by the teacher within the review time.

5. A review content generating device, characterized in that: include: An acquisition module is configured to acquire learning data, syllabus data, and review time of target students; The determination module is configured to determine the set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points based on the correlation value of the objective factor value and the subjective factor value of the knowledge point mastery in the learning data, including: performing a correlation analysis of the objective factor value and the subjective factor value of the knowledge point mastery in the syllabus data based on the learning data to obtain the correlation value of the objective factor value and the subjective factor value, including: performing linear regression processing on the student's historical grades, the student's regular homework grades, the random classroom test grades, and the constant term in the learning data to obtain the objective factor value; performing linear regression processing on the student's average learning time, classroom performance score, teacher evaluation score, and the constant term in the learning data to obtain the subjective factor value; calculating by the following formula 1 to obtain the correlation value of the objective factor value and the subjective factor value; M=∑(Yi-Ymean)*(Pi-Pmean) / (n*sY*sP)Formula 1 Among them, Yi and Pi represent the objective factor value and subjective factor value of the i-th student respectively, Ymean and Pmean represent the mean values ​​of Y and P respectively, sYsP represent the standard deviation of YP respectively; the value range of M is [-1,1], when the M value is infinitely close to 1, it means that there is a strong positive correlation between Y and P; when the M value = 0, it means there is no correlation, and when the M value is infinitely close to -1, it means that there is a strong negative correlation between Y and P; According to the threshold interval where the correlation value of the objective factor value and the subjective factor value is located, determining the set of unmastered knowledge points corresponding to each of the target students in the syllabus knowledge points, including: determining the threshold interval where the correlation value of the objective factor value and the subjective factor value of the knowledge point corresponding to the target student is located; if the correlation value of the objective factor value and the subjective factor value corresponding to the target knowledge point of the target student is in the threshold interval [-1,0] or (0,1] and at least one of the objective factor value or the subjective factor value is less than a predetermined threshold, it is determined that the target student has not mastered the target knowledge point; otherwise, it is determined that the target student has mastered the target knowledge point; A grading module is configured to determine a first set of knowledge points to be reviewed by each target student within the review time and different learning ability levels of each target student according to a set of unmastered knowledge points corresponding to each target student; A generating module is configured to generate a second set of knowledge points to be reviewed by the teacher within the review time for different learning ability levels according to the first set of knowledge points, the knowledge point score corresponding to each knowledge point in the syllabus knowledge points, the review time, and the number of students who have not mastered the knowledge point; The sending module is configured to send the second knowledge point set to the corresponding target students.

6. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 4 is implemented.

7. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 4 is implemented.

Images