Teaching material generation method, device, storage medium and electronic device

Abstract

The present disclosure provides a teaching material generation method, apparatus, storage medium, and electronic device. The method includes: extracting a first important knowledge point cluster from a teaching material, extracting a second important knowledge point cluster from a historical question bank, and extracting a third important knowledge point cluster from a feature dataset; using a first similarity algorithm to evaluate the similarity between the second important knowledge point cluster and the third important knowledge point cluster, and evaluating a first candidate knowledge point cluster with similar importance within the knowledge point range corresponding to the first important knowledge point cluster based on the similarity evaluation result; using a second similarity algorithm to evaluate a second candidate knowledge point cluster with similar importance within the knowledge point range, and selecting the same first target knowledge point; updating the first important knowledge point cluster based on the first target knowledge point to obtain an updated first target important knowledge point cluster, and generating an electronic teaching material based on the first target important knowledge point cluster.

Description

Technical Field

[0001] The present disclosure relates to the field of intelligent education, and particularly to a teaching material generation method, apparatus, storage medium and electronic device. Background Art

[0002] In recent years, with the continuous advancement and development of computer technology and education informatization, computer and artificial intelligence technologies have been gradually applied to various daily education and teaching activities. The optimization of knowledge point clusters can effectively help teachers improve the hit rate of important knowledge points, thereby improving the teaching efficiency of teachers and the learning effect of students.

[0003] Currently, the teaching material generation method in related technologies is obtained by calculating the knowledge point scores through a knowledge tree structure based on teaching material knowledge points. However, in fact, there are situations where knowledge points are omitted or the importance of knowledge points is not high among the important knowledge points determined by calculating the knowledge point scores using the knowledge tree structure, which leads to low accuracy of the knowledge points recommended to users. For example, in the scenario of teachers' lesson preparation, low accuracy of the knowledge points recommended to teachers will result in low lesson preparation efficiency. Summary of the Invention

[0004] The present disclosure provides a teaching material generation method, apparatus, storage medium and electronic device.

[0005] According to a first aspect of the present disclosure, there is provided a teaching material generation method, the method comprising:

[0006] extracting a first important knowledge point cluster from a teaching material, a second important knowledge point cluster from a historical question bank, and a third important knowledge point cluster from a feature dataset including factors affecting students' wrong answers based on an intelligent education terminal;

[0007] evaluating the similarity between the importance identification vector corresponding to the second important knowledge point cluster and the importance identification vector corresponding to the third important knowledge point cluster using a first similarity algorithm, and evaluating a first candidate knowledge point cluster with similar importance within the scope of the knowledge points corresponding to the first important knowledge point cluster based on the similarity evaluation result;

[0008] evaluating a second candidate knowledge point cluster with similar importance within the scope of the knowledge points using a second similarity algorithm, and selecting the same first target knowledge points from the first candidate knowledge point cluster and the second candidate knowledge point cluster;

[0009] updating the first important knowledge point cluster based on the first target knowledge points to obtain an updated first target important knowledge point cluster, and generating an electronic teaching material based on the first target important knowledge point cluster.

[0010] In some embodiments of the present disclosure, a first important knowledge point cluster is extracted from textbooks based on an intelligent education terminal, including:

[0011] Perform text analysis on the textbook based on the intelligent education terminal to obtain the knowledge points in the textbook;

[0012] Perform hierarchical processing on the knowledge points according to the association relationship between the knowledge points to obtain the hierarchical identifiers corresponding to the knowledge points;

[0013] Perform coding processing on the hierarchical identifiers corresponding to the knowledge points to obtain the identification code values of the knowledge points at each level;

[0014] Based on the hierarchical identifiers corresponding to the knowledge points and the identification code values of the knowledge points at each level, determine the set of importance level identification vectors corresponding to the knowledge points, and generate a basic knowledge point cluster according to the set of identification vectors;

[0015] Determine the first important knowledge point cluster based on the importance level of the knowledge points in the basic knowledge point cluster.

[0016] In some embodiments of the present disclosure, determining the first important knowledge point cluster based on the importance level of the knowledge points in the basic knowledge point cluster includes:

[0017] Determine the difficulty level corresponding to the knowledge points in the basic knowledge point cluster according to the refinement degree of the knowledge points in the basic knowledge point cluster;

[0018] Use a pre-trained evaluation model to determine the importance level corresponding to the knowledge points in the basic knowledge point cluster;

[0019] Perform screening in the basic knowledge point cluster based on the importance level corresponding to the knowledge points and a first preset screening threshold, and determine the set of screened knowledge points as the first important knowledge point cluster. The first preset screening threshold is an initial value set for the importance level corresponding to the knowledge points.

[0020] In some embodiments of the present disclosure, a second important knowledge point cluster is extracted from the historical question bank, including:

[0021] Based on all the knowledge points involved in the historical question bank and a pre-trained important knowledge point evaluation model, determine the difficulty level score of each knowledge point among all the knowledge points involved in the historical question bank;

[0022] Perform screening among all the knowledge points involved in the historical question bank based on the difficulty level score of each knowledge point among all the knowledge points involved in the historical question bank and a second preset screening threshold, and determine the set of screened knowledge points as the second important knowledge point cluster. The second preset screening threshold is an initial value set for the difficulty level corresponding to the knowledge points.

[0023] In some embodiments of the present disclosure, a third most important knowledge point cluster is extracted from the feature dataset containing the influencing factors for students' wrong answers to questions, including:

[0024] Based on the feature dataset containing the influencing factors for students' wrong answers to questions, using a preset wrong-question correlation evaluation model to determine the correlation between each influencing factor for students' wrong answers to questions and the wrong questions in the feature dataset containing the influencing factors for students' wrong answers to questions. The influencing factors for students' wrong answers to questions include subjective factors and objective factors;

[0025] Select the features in the feature dataset containing the influencing factors for students' wrong answers to questions that are caused by objective factors, and sort the features that are caused by objective factors for students' wrong answers to questions in descending order of correlation;

[0026] Determine the knowledge point set corresponding to the feature with the largest correlation as the third most important knowledge point cluster.

[0027] In some embodiments of the present disclosure, after updating the first most important knowledge point cluster based on the first target knowledge point to obtain the updated first target most important knowledge point cluster, the method further includes:

[0028] Using a first similarity algorithm to evaluate the similarity between the importance level identification vector corresponding to the second most important knowledge point cluster and the importance level identification vector corresponding to the third most important knowledge point cluster, and evaluating a third candidate knowledge point cluster with similar importance levels outside the knowledge point range corresponding to the first most important knowledge point cluster based on the similarity evaluation result;

[0029] Using a second similarity algorithm to evaluate a fourth candidate knowledge point cluster with similar importance levels outside the knowledge point range, and selecting the same second target knowledge point from the third candidate knowledge point cluster and the fourth candidate knowledge point cluster.

[0030] If the importance level identification vector corresponding to the second target knowledge point is the same as the importance level identification vector corresponding to the knowledge point in the basic knowledge point cluster, then use the importance level identification vector corresponding to the second target knowledge point to update the first target most important knowledge point cluster to obtain the updated second target most important knowledge point cluster;

[0031] Generating an e-textbook based on the first target most important knowledge point cluster, including:

[0032] Generating an e-textbook based on the second target most important knowledge point cluster to obtain the updated e-textbook.

[0033] In some embodiments of the present disclosure, after generating the e-textbook based on the second target most important knowledge point cluster, the method includes:

[0034] Highlight the knowledge points in the updated e-textbook by using the knowledge points in the second most important knowledge point cluster and / or the knowledge points in the third most important knowledge point cluster.

[0035] According to a second aspect of the present disclosure, there is provided a textbook generation device, which includes:

[0036] An extraction unit, configured to extract a first most important knowledge point cluster from a textbook based on a smart education terminal, extract a second most important knowledge point cluster from a historical question bank, and extract a third most important knowledge point cluster from a feature dataset including factors affecting students' wrong questions;

[0037] An evaluation unit, configured to perform similarity evaluation on the importance level identification vectors corresponding to the second most important knowledge point cluster and the importance level identification vectors corresponding to the third most important knowledge point cluster by using a first similarity algorithm, and evaluate a first candidate knowledge point cluster with similar importance levels within the scope of the knowledge points corresponding to the first most important knowledge point cluster based on the similarity evaluation result;

[0038] A screening unit, configured to evaluate a second candidate knowledge point cluster with similar importance levels within the scope of the knowledge points by using a second similarity algorithm, and select the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster;

[0039] A generation unit, configured to update the first most important knowledge point cluster based on the first target knowledge point to obtain an updated first target important knowledge point cluster, and generate an e-textbook according to the first target important knowledge point cluster.

[0040] According to a third aspect of the present disclosure, there is provided a computer-readable storage medium, on which a computer program is stored, and when the computer program is executed by a processor, the method described in the foregoing first aspect is implemented.

[0041] According to a fourth aspect of the present disclosure, there is provided an electronic device, including a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, and when the processor executes the computer program, the method described in the foregoing first aspect is implemented.

[0042] The teaching material generation method, device, storage medium and electronic device provided by the present disclosure extract the first important knowledge point cluster from teaching materials, the second important knowledge point cluster from historical question banks, and the third important knowledge point cluster from the feature data set including the influencing factors of students' wrong questions based on intelligent education terminals; use the first similarity algorithm to evaluate the similarity of the importance identification vectors corresponding to the second important knowledge point cluster and the importance identification vectors corresponding to the third important knowledge point cluster, and evaluate the first candidate knowledge point cluster with similar importance within the scope of the knowledge points corresponding to the first important knowledge point cluster based on the similarity evaluation result; use the second similarity algorithm to evaluate the second candidate knowledge point cluster with similar importance within the scope of the knowledge points, and select the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster; update the first important knowledge point cluster based on the first target knowledge point to obtain the updated first target important knowledge point cluster, and generate an electronic teaching material according to the first target important knowledge point cluster. This solution updates the first important knowledge point cluster by using the importance identification vectors corresponding to the second important knowledge point cluster and the importance identification vectors corresponding to the third important knowledge point cluster to obtain the first target knowledge point cluster, solves the problems of knowledge point omission and low importance in the first important knowledge point cluster, improves the accuracy of the first important knowledge point cluster. Finally, by generating an electronic teaching material according to the first target important knowledge point cluster and providing more accurate knowledge points to teachers, the lesson preparation efficiency of teachers can be improved.

[0043] It should be understood that the content described in this part is not intended to identify the key or important features of the embodiments of the present application, nor is it used to limit the scope of the present application. Other features of the present application will become easily understood through the following description. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] The drawings are used to better understand the solution and do not constitute a limitation to the present disclosure. Among them:

[0045] Figure 1 It is a schematic flowchart of a teaching material generation method provided by an embodiment of the present disclosure;

[0046] Figure 2 It is a schematic flowchart of a method for determining the first important knowledge point cluster provided by an embodiment of the present disclosure;

[0047] Figure 3 It is a schematic diagram of a knowledge point network provided by an embodiment of the present disclosure;

[0048] Figure 4 It is a schematic diagram of a screening process provided by an embodiment of the present disclosure;

[0049] Figure 5Flow diagram of the method for determining the first important knowledge point cluster provided by an embodiment of the present disclosure;

[0050] Figure 6 Flow diagram of the method for determining the second important knowledge point cluster provided by an embodiment of the present disclosure;

[0051] Figure 7 Flow diagram of the method for determining the third important knowledge point cluster provided by an embodiment of the present disclosure;

[0052] Figure 8 Flow diagram of the method for obtaining the updated e - textbook provided by an embodiment of the present disclosure;

[0053] Figure 9 Flow diagram of the method for obtaining the update method of the first important knowledge point cluster provided by an embodiment of the present disclosure;

[0054] Figure 10 Structural diagram of a teaching material generation device provided by an embodiment of the present disclosure;

[0055] Figure 11 Hardware structural diagram of an electronic device provided by an embodiment of the present disclosure. Detailed implementation manners

[0056] The following makes an explanation of the exemplary embodiments of the present disclosure with reference to the accompanying drawings. Various details of the embodiments of the present disclosure are included to facilitate understanding, and they should be considered merely exemplary. Therefore, those of ordinary skill in the art should recognize that various changes and modifications can be made to the embodiments described herein without departing from the scope and spirit of the present disclosure. Similarly, for the sake of clarity and conciseness, the description of well - known functions and structures is omitted below.

[0057] In recent years, with the continuous advancement and development of computer technology and educational informatization, computer and artificial intelligence technologies have gradually been applied to various daily educational teaching activities. The optimization of knowledge point clusters can effectively help teachers improve the hit rate of important knowledge points, thereby improving teachers' teaching efficiency and students' learning effects.

[0058] Currently, the teaching material generation method in related technologies is obtained by calculating the knowledge point scores through a knowledge tree structure based on teaching material knowledge points. However, in fact, there are situations where important knowledge points determined by calculating knowledge point scores using the knowledge tree structure have knowledge point omissions or the importance of knowledge points is not high, which in turn leads to low accuracy of the knowledge points recommended to users. For example, in the scenario of teachers' lesson preparation, low accuracy of the knowledge points recommended to teachers will result in low lesson preparation efficiency.

[0059] To solve the problems in the related art, the textbook generation method provided by the present disclosure extracts the first important knowledge point cluster from textbooks, the second important knowledge point cluster from historical question banks, and the third important knowledge point cluster from the feature dataset containing the influencing factors of students' wrong questions based on a smart education terminal; uses the first similarity algorithm to evaluate the similarity of the importance identification vectors corresponding to the second important knowledge point cluster and the third important knowledge point cluster, and evaluates the first candidate knowledge point cluster with similar importance within the scope of the knowledge points corresponding to the first important knowledge point cluster based on the similarity evaluation result; uses the second similarity algorithm to evaluate the second candidate knowledge point cluster with similar importance within the scope of the knowledge points, and selects the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster; updates the first important knowledge point cluster based on the first target knowledge point to obtain the updated first target important knowledge point cluster, and generates an e-textbook according to the first target important knowledge point cluster. This solution updates the first important knowledge point cluster based on the importance identification vectors corresponding to the second important knowledge point cluster and the third important knowledge point cluster to obtain the first target knowledge point cluster, solves the problems of missing knowledge points and low importance in the first important knowledge point cluster, improves the accuracy of the first important knowledge point cluster. Finally, by generating an e-textbook according to the first target important knowledge point cluster and providing teachers with more accurate knowledge points, the teaching preparation efficiency of teachers can be improved.

[0060] The following describes the textbook generation method, device, electronic device, and storage medium according to the embodiments of the present disclosure with reference to the accompanying drawings.

[0061] Figure 1 It is a schematic flowchart of a textbook generation method provided by an embodiment of the present disclosure. As Figure 1 shown, the method includes:

[0062] Step 101, extract the first important knowledge point cluster from textbooks, the second important knowledge point cluster from historical question banks, and the third important knowledge point cluster from the feature dataset containing the influencing factors of students' wrong questions based on a smart education terminal;

[0063] In some embodiments, the smart education terminal can be implemented based on hardware devices (such as tablet computers, smart whiteboards), or can be based on software application programs installed on ordinary computers or mobile devices. Usually, these terminals can be connected to cloud services to achieve functions such as accessing rich educational resources and data synchronization.

[0064] In some embodiments, the content in the teaching materials can be uploaded to the first knowledge point analysis module of the intelligent education terminal, and the content in the teaching materials can be textually analyzed to obtain the knowledge points in the teaching materials, and then the first important knowledge point cluster can be determined according to the importance degree of the knowledge points.

[0065] In one embodiment, the second important knowledge point cluster can be extracted from the historical question bank according to the importance degree of the knowledge points. The historical question bank refers to the collection of questions accumulated by the online education platform in the past, including exercise questions, examination questions, etc. of various subjects, grades, and knowledge points, and records information such as question knowledge points, difficulty levels, and students' answering situations. The historical question bank can be a real-time updated question bank.

[0066] In one embodiment, the data acquisition scope in the historical question bank can be based on classes, so that teachers can prepare lessons according to the learning levels of the students in the class.

[0067] In some embodiments, a feature data set including the influencing factors of students' wrong answers can be obtained from the log data of the learning management system.

[0068] In some embodiments, since there are many factors that affect students' wrong answers, including misreading questions, writing wrong answers, and really not understanding, etc., it is impossible to effectively obtain the students' mastery of knowledge points. Therefore, it is necessary to screen out the knowledge points that students really don't know how to do from the feature data set including the influencing factors of students' wrong answers to obtain the third important knowledge point cluster, so as to facilitate teachers to understand the students' mastery of knowledge points.

[0069] Step 102: Use the first similarity algorithm to evaluate the similarity between the importance degree identification vector corresponding to the second important knowledge point cluster and the importance degree identification vector corresponding to the third important knowledge point cluster, and evaluate the first candidate knowledge point cluster with similar importance degree within the scope of the knowledge points corresponding to the first important knowledge point cluster based on the similarity evaluation result;

[0070] In some embodiments, the first similarity algorithm can be one of algorithms such as the Jaccard similarity algorithm, the cosine similarity algorithm, the Euclidean distance algorithm, and the Manhattan distance algorithm.

[0071] In some embodiments, the importance degree identification vector corresponds to the knowledge points one by one. The importance degree can include first and second levels, third levels, etc. The identification vector is determined by the classification and coding of the knowledge points. The application does not limit the number of levels of the importance degree.

[0072] In some embodiments, taking the Jaccard similarity algorithm as an example of the first similarity algorithm, the mathematical expression for evaluating the similarity between the importance level identification vector corresponding to the second most important knowledge point cluster and the importance level identification vector corresponding to the third most important knowledge point cluster using the Jaccard similarity algorithm is as follows:

[0073] Formula 1

[0074] In Formula 1, G represents the second most important knowledge point cluster, and H represents the third most important knowledge point cluster. represents the number of knowledge points in the intersection between the second most important knowledge point cluster and the third most important knowledge point cluster. represents the number of knowledge points in the union between the second most important knowledge point cluster and the third most important knowledge point cluster. represents the similarity between the second most important knowledge point cluster and the third most important knowledge point cluster.

[0075] In some embodiments, based on the above similarity evaluation results, a first candidate knowledge point cluster with similar importance levels is evaluated within the scope of the knowledge points corresponding to the first most important knowledge point cluster. Specifically, the first most important knowledge point cluster is obtained by a preliminary screening of the basic knowledge point cluster and contains a large number of important knowledge points, and can include most of the knowledge points in the second most important knowledge point cluster and the third most important knowledge point cluster. Therefore, within the large scope of the first most important knowledge point cluster, the knowledge points with similar importance levels in the second most important knowledge point cluster and the third most important knowledge point cluster can be determined, that is, the knowledge points in the first candidate knowledge point cluster. Among them, the knowledge points with similar importance levels can include first-level knowledge points, second-level knowledge points, and third-level knowledge points.

[0076] Step 103: Use the second similarity algorithm to evaluate a second candidate knowledge point cluster with similar importance levels within the scope of the knowledge points, and select the same first target knowledge points from the first candidate knowledge point cluster and the second candidate knowledge point cluster;

[0077] In some embodiments, the second similarity algorithm can also be one of various algorithms such as the Jaccard similarity algorithm, the improved cosine similarity algorithm, the Euclidean distance algorithm, and the Manhattan distance algorithm. However, to make up for the deficiencies of a single similarity algorithm, preferably, a similarity algorithm different from that in step 102 is adopted here. Specifically, if the Jaccard similarity algorithm is adopted in the aforementioned step 102, the Jaccard similarity algorithm is used to calculate the similarity between individuals with symbolic metrics. The disadvantage is that it cannot measure the specific value of the difference and can only draw conclusions of being the same or different. Since the knowledge points in this application include multiple levels, when determining similar knowledge points, the principle of hierarchical matching needs to be followed. If only the Jaccard similarity is used, there will be cases such as q(1, 0, 1), and the output result is also similar, but the secondary level is 0, which does not meet the consistency standard. Therefore, the cosine similarity algorithm can be selected in this step for further verification. The improved cosine similarity algorithm has been improved to a certain extent in measuring the differences of each dimension value, but there are still certain deficiencies in accuracy. The two methods can complement each other's advantages.

[0078] In some embodiments, the improved cosine similarity algorithm is used to evaluate a second candidate knowledge point cluster with similar importance within the scope of knowledge points. The mathematical expression of the improved cosine similarity algorithm is as follows:

[0079] Formula 2

[0080] In Formula 2, represents the similarity between the second important knowledge point cluster G and the third important knowledge point cluster H. n is the nth knowledge point, and N is the total number of knowledge points after alignment of the second important knowledge point cluster G and the third important knowledge point cluster H. is the nth knowledge point vector in the second important knowledge point cluster G. is the mean value of the nth knowledge point vector after alignment of the second important knowledge point cluster G and the third important knowledge point cluster H. is the nth knowledge point vector in the third important knowledge point cluster H.

[0081] In some embodiments, the same first target knowledge points are selected from the first candidate knowledge point cluster and the second candidate knowledge point cluster. Specifically, the similarities of the second important knowledge point cluster and the third important knowledge point cluster are obtained by using the Jaccard similarity algorithm and the cosine similarity algorithm respectively. If the judgment results of the two similarity algorithms are consistent, the knowledge points with consistent similarity judgment results are determined as the first target knowledge points.

[0082] Step 104: Update the first important knowledge point cluster based on the first target knowledge points to obtain the updated first target important knowledge point cluster, and generate an e - textbook according to the first target important knowledge point cluster.

[0083] In some embodiments, there may be problems such as omissions, inaccuracies, or low importance levels in the knowledge points in the first important knowledge point cluster. By updating the first important knowledge point cluster based on the first target knowledge points, the updated first target important knowledge point cluster is obtained, which solves the problems of knowledge point omissions and low importance levels in the first important knowledge point cluster and improves the accuracy rate of the first important knowledge point cluster.

[0084] In some embodiments, by generating e-textbooks based on the first target important knowledge point cluster, knowledge points with higher accuracy rates can be provided to teachers, thereby improving the teaching preparation efficiency of teachers.

[0085] As a possible implementation manner, as Figure 2 shown in the flowchart of a method for determining the first important knowledge point cluster, based on the above embodiments, the specific process of extracting the first important knowledge point cluster from the textbook by the intelligent education terminal includes the following steps:

[0086] Step 201: Perform text analysis on the textbook by the intelligent education terminal to obtain the knowledge points in the textbook;

[0087] In some embodiments, the content in the textbook can be uploaded to the first knowledge point analysis module, and the knowledge points corresponding to the content in the textbook can be extracted by using text analysis. Specifically, the knowledge points corresponding to the content in the textbook can be extracted by using keywords. Before performing text analysis, preprocessing of the content in the textbook can also be included, such as word segmentation and removal of stop words.

[0088] Step 202: Perform hierarchical processing on the knowledge points according to the association relationships between the knowledge points to obtain the hierarchical identifiers corresponding to the knowledge points;

[0089] In some embodiments, the hierarchical identifier refers to assigning specific marks to the knowledge points at each level in a multi-level classification structure for easy distinction and management. Through the hierarchical identifiers of the knowledge points, the hierarchical relationships of the knowledge points can be clearly displayed, which is helpful for the construction of the knowledge point network. The knowledge points are used as nodes in the knowledge network, and the knowledge points classified by chapter in the textbook are used as the first-level classification nodes, corresponding to the main nodes in the knowledge network; the knowledge points classified by section in the textbook are used as the second-level classification nodes, corresponding to the subordinate nodes of the first-level classification nodes in the knowledge network, which are used to represent each subsection in each chapter; the knowledge points classified by unit results can be used as the third-level classification nodes, and the corresponding knowledge points are the subordinate nodes of the second-level classification nodes in the knowledge network, which are used to further subdivide the specific knowledge points under each unit. The association relationships between the knowledge points refer to the above-mentioned chapters, sections, and units.

[0090] In some embodiments, the hierarchical identifier corresponding to the knowledge point can be an English letter. For example, A represents a first-level classification node, B represents a second-level classification node, and C represents a third-level classification node.

[0091] Step 203: Perform encoding processing on the hierarchical identifier corresponding to the knowledge point to obtain the identifier coding value of the knowledge point at each level.

[0092] In some embodiments, each knowledge point corresponds to a unique identifier coding value, and the identifier coding value can be one or a combination of multiple identifier forms such as numbers, letters, and special symbols.

[0093] In some embodiments, when using English letters as the hierarchical identifier, for different knowledge points on the same hierarchical node, numbers can be used for encoding. For example, if there are 3 first-level classification nodes, they can be encoded as A1, A2, and A3 respectively. Another example is that if there are two second-level classification nodes, they can be encoded as B1 and B2. At the same time, the first-level classification nodes associated with B1 and B2 also need to be encoded.

[0094] Step 204: Based on the hierarchical identifier corresponding to the knowledge point and the identifier coding value of the knowledge point at each level, determine the set of importance level identifier vectors corresponding to the knowledge point, and generate the basic knowledge point cluster according to the set of identifier vectors.

[0095] In some embodiments, the first-level classification node appears in the form of a single-unit identifier vector, and the multi-level classification node appears in the form of a combination of multiple-unit identifier vectors.

[0096] In some embodiments, the knowledge points in the textbook can be divided into n levels, as Figure 3 shown, Figure 3 is a schematic diagram of the knowledge point network provided by the embodiments of the present disclosure. When n = 3, the corresponding knowledge point cluster U = [An, Bm, Ck]. Specifically, the first-level classification An (A in the figure) in the knowledge point network serves as the main node and is classified by chapter to obtain An = [A1, A2... An]; the second-level classification Bm serves as the subordinate node of An and is classified by section to obtain Bm = [A1b1, A1b2, A2b1... Anbm]; the third-level classification Ck serves as the subordinate node of Bm and is classified by unit result to obtain Ck = [A1b1c1, A1b2c2, A1b2c3... Anbmck].

[0097] In some embodiments, the corresponding identifier vector is generated according to the identifier coding, and the knowledge point network is constructed based on the identifier vector. The knowledge point network is used to represent the relationship between knowledge points, and then multiple knowledge point networks are combined into a comprehensive set of identifier vectors, that is, the basic knowledge point cluster Uori.

[0098] Step 205: Determine the first important knowledge point cluster based on the importance degree of the knowledge points in the basic knowledge point cluster.

[0099] In some embodiments, a pre-trained evaluation model can be used to evaluate the importance degree of each knowledge point in the basic knowledge point cluster, and then the first important knowledge point cluster is determined according to the importance degree.

[0100] In some embodiments, as Figure 4 shown, Figure 4 is a schematic diagram of the screening process provided by the embodiments of the present disclosure. Specifically, knowledge points with a relatively high importance degree are screened out from the knowledge points in the basic knowledge point cluster Uori to obtain the first important knowledge point cluster Unew.

[0101] As a possible implementation manner, as Figure 5 shown is a schematic flowchart of a method for determining the first important knowledge point cluster. On the basis of the above embodiments, the specific process of determining the first important knowledge point cluster based on the importance degree of the knowledge points in the basic knowledge point cluster includes the following steps:

[0102] Step 501: Determine the difficulty level corresponding to the knowledge points in the basic knowledge point cluster according to the refinement degree of the knowledge points in the basic knowledge point cluster;

[0103] In some embodiments, the refinement degree of a knowledge point refers to the classification level of the knowledge point in the knowledge point network. The higher the classification level corresponding to the knowledge point, the higher the refinement degree of the knowledge point. For example, knowledge points A1B1 and A1B1C1 are respectively the secondary classification node and the tertiary classification node in the aforementioned knowledge point network, then the refinement degree of knowledge point A1B1 is lower than that of knowledge point A1B1C1.

[0104] In some embodiments, the knowledge points in the basic knowledge point cluster are classified in detail, and their difficulty levels are determined according to the refinement degree of the knowledge points. For example, the refinement degree corresponding to a knowledge point can be determined according to the chapter, section, and unit to which the knowledge point belongs in the textbook text; or the refinement degree corresponding to a knowledge point can also be determined according to the form of the identification vector corresponding to the knowledge point (the form of a single unit or a combination of multiple units).

[0105] In some embodiments, according to the refinement degree of the knowledge points, the difficulty level of the knowledge points is determined. The higher the refinement degree of the knowledge points, the higher the corresponding difficulty level, which can provide a basis for generating questions with different difficulty levels in the future.

[0106] Step 502: Use the pre-trained evaluation model to determine the importance degree corresponding to the knowledge points in the basic knowledge point cluster;

[0107] In some embodiments, the importance level corresponding to the knowledge points in the basic knowledge point cluster can be calculated according to a pre-trained evaluation model, and its mathematical expression is as follows:

[0108] Formula 3

[0109] In Formula 3, Z, X, V, and W are respectively the numbers of identification vectors corresponding to the first-level, second-level, third-level, and n-level knowledge points in the basic knowledge point cluster. 、 、 、 are respectively the weight coefficients corresponding to the importance levels of the first-level, second-level, third-level, and n-level identification vectors. 、 、 、 are respectively the weighted scores corresponding to the importance levels of the first-level, second-level, third-level, and n-level identification vectors, and , because as the refinement degree of the knowledge points gets deeper, the proportion of importance increases.

[0110] In some embodiments, the magnitude of the weight coefficient corresponding to the importance level of the identification vector can reflect the importance level of each hierarchical knowledge point, and the magnitude of the weight coefficient can be adjusted according to the actual situation.

[0111] Step 503: Screen in the basic knowledge point cluster based on the importance level corresponding to the knowledge points and a first preset screening threshold, and determine the set of screened knowledge points as the first important knowledge point cluster. The first preset screening threshold is the initial value set for the importance level corresponding to the knowledge points.

[0112] In some embodiments, the selection of the first preset screening threshold is related to the importance of the knowledge points in the first important knowledge point cluster. If the first preset screening threshold is too small, it will result in a large number of knowledge points in the first important knowledge point cluster and low importance levels. If the first preset threshold is too large, it will result in too few knowledge points in the first important knowledge point cluster. The knowledge points in the first important knowledge point cluster have high importance levels, but some relatively important knowledge points may be excluded. Further, in the scenario of teacher lesson preparation, if the first preset threshold is too large, it will lead to a smaller scope of teacher lesson preparation and not cover most important knowledge points. Also, in the review scenario, if the first preset threshold is too large, some important examination points will not be covered.

[0113] In some embodiments, the first preset screening threshold can be set with an initial threshold by using methods such as self-definition, average method, median, etc. This embodiment does not make any limitations in this regard.

[0114] In some embodiments, a first preset screening threshold T1 can be determined. When G > T1, the identified knowledge point vector is used as the important knowledge point cluster.

[0115] In some embodiments, by screening in the basic knowledge point cluster based on the importance level corresponding to the knowledge point and the first preset screening threshold, and determining the set of screened knowledge points as the first important knowledge point cluster, more important knowledge points can be obtained.

[0116] As a possible implementation, as Figure 6 shown in the flowchart of a method for determining the second important knowledge point cluster. On the basis of the above embodiments, the specific process of extracting the second important knowledge point cluster from the historical question bank includes the following steps:

[0117] Step 601: Based on all the knowledge points involved in the historical question bank and the pre-trained important knowledge point evaluation model, determine the difficulty level score of each knowledge point among all the knowledge points involved in the historical question bank.

[0118] In some embodiments, based on the historical question bank, according to the identification vectors (Wn, Rm, Hk) corresponding to the knowledge points in the question bank, the corresponding basic knowledge point cluster Zori = [Wn, Rm, Hk] of the question bank can be generated.

[0119] In some embodiments, the difficulty level score of each knowledge point among all the knowledge points involved in the historical question bank can be calculated through the pre-trained important knowledge point evaluation model, and its mathematical expression is as follows:

[0120] Formula 4

[0121] In Formula 4, Gj is the number of occurrences of the test point knowledge point, Gq is the number of error frequency occurrences of the test point knowledge point, Gr is the number of branches of the test point knowledge point, is the weight score corresponding to each index, is the difficulty level score of the knowledge point.

[0122] Step 602: Based on the difficulty level score of each knowledge point among all the knowledge points involved in the historical question bank and the second preset screening threshold, screen among all the knowledge points involved in the historical question bank, and determine the set of screened knowledge points as the second important knowledge point cluster. The second preset screening threshold is the initial value set for the difficulty level corresponding to the knowledge point.

[0123] In some embodiments, the second preset screening threshold can be obtained by the same method as the first preset screening threshold, or by a method different from the first preset screening threshold, that is, one of the methods such as customization, average method, median method, etc., or can be obtained by multiple of the methods such as customization, average method, median method, etc., and then taking the average of multiple values obtained by multiple methods. This embodiment does not make any limitations in this regard.

[0124] In some embodiments, the second preset screening threshold T2 can be determined. When yG > T2 in the aforementioned step 601, important knowledge points are screened out to obtain the second important knowledge point cluster.

[0125] In some embodiments, the selection of the second preset screening threshold is related to the importance of the knowledge points in the second important knowledge point cluster. If the second preset screening threshold is too small, it will result in a large number of knowledge points in the second important knowledge point cluster and low importance. If the second preset threshold is too large, it will result in too few knowledge points in the second important knowledge point cluster. The knowledge points in the second important knowledge point cluster are highly important, but some relatively important knowledge points may be excluded. Further, in the scenario of teacher lesson preparation, if the second preset threshold is too large, it will lead to a smaller range of teacher lesson preparation and be insufficient to cover most important knowledge points. Also, in the review scenario, if the second preset threshold is too large, some important examination points will not be covered.

[0126] As a possible implementation method, as Figure 7 shown in the flowchart of a method for determining the third important knowledge point cluster, on the basis of the above embodiments, the specific process of extracting the third important knowledge point cluster from the feature dataset including the influencing factors of students' wrong questions includes the following steps:

[0127] Step 701: Based on the feature dataset including the influencing factors of students' wrong questions, use the preset wrong question correlation evaluation model to determine the correlation between each influencing factor of students' wrong questions and the wrong questions in the feature dataset including the influencing factors of students' wrong questions. The influencing factors of students' wrong questions include subjective factors and objective factors;

[0128] In some embodiments, the subjective factors can include emotion characteristics such as positive, plain, negative, etc.; concentration characteristics such as concentrated, distracted, vulnerable to external factors, etc.; question-solving style characteristics such as careful, careless, lack of patience, etc.; the objective factors can include knowledge point mastery situation characteristics such as proficient, skilled, unskilled, etc.; question-solving efficiency characteristics such as fast, medium, slow, etc.; question difficulty level characteristics: simple, ordinary, difficult, etc.

[0129] In some embodiments, by using a preset wrong-question correlation evaluation model, the correlation between each wrong-question influencing factor and wrong questions can be obtained, and according to the magnitude of the correlation, it can be known the influence of the wrong-question influencing factors on students' wrong questions.

[0130] In some embodiments, the preset wrong-question correlation evaluation model can be a pre-trained correlation evaluation model.

[0131] Step 702: Screen out the features of wrong questions caused by objective factors from the feature dataset containing students' wrong-question influencing factors, and sort the features of wrong questions caused by objective factors in descending order of correlation;

[0132] In some embodiments, algorithms such as hierarchical clustering algorithm, principal component analysis method, or correlation coefficient matrix can be used to screen out the features of wrong questions caused by objective factors from the feature dataset containing students' wrong-question influencing factors.

[0133] In some embodiments, by sorting the features of wrong questions caused by objective factors in descending order of correlation, the screening speed of the feature with the largest subsequent correlation can be improved.

[0134] Step 703: Determine the knowledge point set corresponding to the feature with the largest correlation as the third most important knowledge point cluster.

[0135] In some embodiments, the feature with the largest correlation is the feature with the greatest influence on wrong questions among objective factors. By determining the knowledge points corresponding to the objective factors with the greatest influence on students' wrong questions as the third most important knowledge point cluster, the knowledge points caused by subjective factors for students' wrong questions can be excluded.

[0136] As a possible implementation, as Figure 8 shown in the flowchart of a method for obtaining an updated e-textbook, on the basis of the above embodiments, after updating the first important knowledge point cluster based on the first target knowledge points to obtain the updated first target important knowledge point cluster, the textbook generation method further includes the following steps:

[0137] Step 801: Use the first similarity algorithm to evaluate the similarity between the importance identification vector corresponding to the second important knowledge point cluster and the importance identification vector corresponding to the third important knowledge point cluster, and evaluate the third candidate knowledge point cluster with similar importance outside the knowledge point range corresponding to the first important knowledge point cluster based on the similarity evaluation result;

[0138] In some embodiments, based on the above similarity evaluation results, a first candidate knowledge point cluster with similar importance is evaluated outside the knowledge point range corresponding to the first important knowledge point cluster. Specifically, the first important knowledge point cluster is obtained by a preliminary screening of the basic knowledge point cluster, and contains a large number of important knowledge points, which can include most of the knowledge points in the second important knowledge point cluster and the third important knowledge point cluster. However, there are cases of knowledge point omission during the preliminary screening process. Therefore, outside the range of the first important knowledge point cluster, knowledge points with similar importance in the second important knowledge point cluster and the third important knowledge point cluster can be determined, that is, the knowledge points in the third candidate knowledge point cluster.

[0139] Step 802: Use the second similarity algorithm to evaluate a fourth candidate knowledge point cluster with similar importance outside the knowledge point range, and select the same second target knowledge points from the third candidate knowledge point cluster and the fourth candidate knowledge point cluster.

[0140] In some embodiments, the difference between this step and the foregoing step 103 lies in the different range of relevance evaluation, and the implementation manners of the remaining contents are the same as those of the foregoing step 103, and will not be elaborated here.

[0141] Step 803: If the importance identification vector corresponding to the second target knowledge point is the same as the importance identification vector corresponding to the knowledge point in the basic knowledge point cluster, then use the importance identification vector corresponding to the second target knowledge point to update the first target important knowledge point cluster to obtain an updated second target important knowledge point cluster;

[0142] In some embodiments, although the importance identification vector corresponding to the second target knowledge point is not in the first important knowledge point cluster, it is still in the basic knowledge point cluster. Therefore, it is also necessary to perform similarity matching with the knowledge points in the basic knowledge point cluster. If the similarity matching is successful, then use the importance identification vector corresponding to the second target knowledge point to update the first target important knowledge point cluster.

[0143] In some embodiments, as Figure 9 shown Figure 9The flowchart of a method for updating a first important knowledge point according to an embodiment of the present disclosure. Specifically, taking the two knowledge points as third-level classification nodes as an example, first, perform the aforementioned steps 102 to 103 on the third-level classification nodes to obtain whether the two knowledge points are similar. If the determination result is similar, bind the knowledge points to the question bank; if the determination result is dissimilar, perform the aforementioned steps 102 to 103 on the corresponding second-level classification nodes in the third-level classification nodes to obtain whether the two knowledge points are similar. If the determination result is similar, bind the knowledge points to the question bank; if the determination result is dissimilar, perform the aforementioned steps 102 to 103 on the corresponding first-level classification nodes in the third-level classification nodes to obtain whether the two knowledge points are similar. If the determination result is similar, bind the knowledge points to the question bank (corresponding to Figure 9 the process of same-level matching); if the determination result is dissimilar, perform the aforementioned steps 801 to 803 on the third-level classification nodes (corresponding to Figure 9 the process of cross-matching). If the determination result is dissimilar, store the dissimilar knowledge points in the alternative library; if the determination result is similar, then perform a similarity determination with the first basic knowledge point cluster (corresponding to the basic knowledge point cluster) (implemented based on same-level matching). If the determination result is dissimilar, store the dissimilar knowledge points in the alternative library. If the determination result is similar, bind the knowledge points to the question bank and update the first important knowledge point cluster.

[0144] In some embodiments, cross-matching is for calibrating the accuracy of the first important knowledge point set.

[0145] Generate an e-textbook based on the first target important knowledge point cluster, including:

[0146] Step 804, generate an e-textbook based on the second target important knowledge point cluster to obtain an updated e-textbook.

[0147] In some embodiments, by generating an e-textbook based on the second target important knowledge point cluster to obtain an updated e-textbook, knowledge points with higher accuracy can be provided to teachers, thereby further improving the teaching preparation efficiency of teachers.

[0148] In some embodiments, in the student review scenario, the updated e-textbook can also provide more accurate knowledge points to students to improve the efficiency of students during review.

[0149] As a possible implementation manner, on the basis of the above embodiments, after generating an e-textbook based on the second target important knowledge point cluster, the textbook generation method further includes:

[0150] Highlight the knowledge points in the updated e-textbook by using the knowledge points in the second important knowledge point cluster and / or the knowledge points in the third important knowledge point cluster.

[0151] In some embodiments, by using the knowledge points in the second important knowledge point cluster and / or the knowledge points in the third important knowledge point cluster to mark the knowledge points in the updated e-textbook, the teacher can be assisted in adjusting the content of the lesson plan according to the overall learning level of the class.

[0152] Corresponding to the above textbook generation method, the present invention also proposes a textbook generation device. Since the device embodiments of the present invention correspond to the above method embodiments, the details not disclosed in the device embodiments can be referred to the above method embodiments, and will not be elaborated herein.

[0153] Figure 10 It is a schematic structural diagram of a textbook generation device provided by an embodiment of the present disclosure, as Figure 10 shown, the textbook generation device 1000 includes:

[0154] An extraction unit 1001, configured to extract a first important knowledge point cluster from a textbook, a second important knowledge point cluster from a historical question bank, and a third important knowledge point cluster from a feature dataset including the influencing factors of students' wrong questions based on a smart education terminal;

[0155] An evaluation unit 1002, configured to perform similarity evaluation on the importance level identification vectors corresponding to the second important knowledge point cluster and the importance level identification vectors corresponding to the third important knowledge point cluster by using a first similarity algorithm, and evaluate a first candidate knowledge point cluster with similar importance levels within the range of knowledge points corresponding to the first important knowledge point cluster based on the similarity evaluation result;

[0156] A screening unit 1003, configured to evaluate a second candidate knowledge point cluster with similar importance levels within the range of knowledge points by using a second similarity algorithm, and select the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster;

[0157] A generation unit 1004, configured to update the first important knowledge point cluster based on the first target knowledge point to obtain an updated first target important knowledge point cluster, and generate an e-textbook according to the first target important knowledge point cluster.

[0158] In some implementation manners of the present disclosure, the extraction unit 1001 is configured to:

[0159] Perform text analysis on the textbook based on a smart education terminal to obtain the knowledge points in the textbook;

[0160] Perform hierarchical processing on the knowledge points according to the association relationship between the knowledge points to obtain a hierarchical identifier corresponding to the knowledge points;

[0161] Encode the hierarchical identifiers corresponding to the knowledge points to obtain the identifier coding values of the knowledge points at each level.

[0162] Based on the hierarchical identifiers corresponding to the knowledge points and the identifier coding values of the knowledge points at each level, determine the set of importance level identifier vectors corresponding to the knowledge points, and generate a basic knowledge point cluster according to the set of identifier vectors.

[0163] Determine the first important knowledge point cluster based on the importance levels of the knowledge points in the basic knowledge point cluster.

[0164] In some embodiments of the present disclosure, the extraction unit 1001 is configured to:

[0165] Determine the difficulty levels corresponding to the knowledge points in the basic knowledge point cluster according to the refinement degrees of the knowledge points in the basic knowledge point cluster.

[0166] Use a pre-trained evaluation model to determine the importance levels corresponding to the knowledge points in the basic knowledge point cluster.

[0167] Based on the importance levels corresponding to the knowledge points and a first preset screening threshold, screen in the basic knowledge point cluster, and determine the set of screened knowledge points as the first important knowledge point cluster. The first preset screening threshold is an initial value set for the importance levels corresponding to the knowledge points.

[0168] In some embodiments of the present disclosure, the extraction unit 1001 is configured to:

[0169] Based on all the knowledge points involved in the historical question bank and a pre-trained important knowledge point evaluation model, determine the difficulty level scores of each knowledge point among all the knowledge points involved in the historical question bank.

[0170] Based on the difficulty level scores of each knowledge point among all the knowledge points involved in the historical question bank and a second preset screening threshold, screen in all the knowledge points involved in the historical question bank, and determine the set of screened knowledge points as the second important knowledge point cluster. The second preset screening threshold is an initial value set for the difficulty levels corresponding to the knowledge points.

[0171] In some embodiments of the present disclosure, the extraction unit 1001 is configured to:

[0172] Based on the feature dataset including the influencing factors of students' wrong questions, use a preset wrong question correlation evaluation model to determine the correlation between each influencing factor of students' wrong questions and the wrong questions in the feature dataset including the influencing factors of students' wrong questions. The influencing factors of students' wrong questions include subjective factors and objective factors.

[0173] Select the features of wrong answers caused by objective factors from the feature dataset containing the influencing factors of students' wrong answers, and sort the features of wrong answers caused by objective factors in descending order of relevance;

[0174] Determine the set of knowledge points corresponding to the feature with the greatest relevance as the third most important knowledge point cluster.

[0175] In some embodiments of the present disclosure, the teaching material generation device 1000 further includes an update unit, and the update unit is configured to:

[0176] Use the first similarity algorithm to evaluate the similarity between the importance identification vector corresponding to the second most important knowledge point cluster and the importance identification vector corresponding to the third most important knowledge point cluster, and evaluate a third candidate knowledge point cluster with similar importance outside the knowledge point range corresponding to the first most important knowledge point cluster based on the similarity evaluation result;

[0177] Use the second similarity algorithm to evaluate a fourth candidate knowledge point cluster with similar importance outside the knowledge point range, and select the same second target knowledge point from the third candidate knowledge point cluster and the fourth candidate knowledge point cluster.

[0178] If the importance identification vector corresponding to the second target knowledge point is the same as the importance identification vector corresponding to the knowledge points in the basic knowledge point cluster, then use the importance identification vector corresponding to the second target knowledge point to update the first target important knowledge point cluster to obtain an updated second target important knowledge point cluster;

[0179] In some embodiments of the present disclosure, the generation unit 1004 is configured to:

[0180] Generate an electronic teaching material based on the second target important knowledge point cluster to obtain an updated electronic teaching material.

[0181] In some embodiments of the present disclosure, the teaching material generation device 1000 further includes a marking unit, and the marking unit is configured to:

[0182] Use the knowledge points in the second most important knowledge point cluster and / or the knowledge points in the third most important knowledge point cluster to mark the key points of the knowledge points in the updated electronic teaching material.

[0183] It should be noted that the foregoing explanations of the method embodiments also apply to the device of this embodiment, with the same principle, and will not be limited in this embodiment.

[0184] Based on the above method as Figures 1 to 8 shown, correspondingly, this embodiment also provides a computer program product, including a computer program, and the computer program realizes the above method as Figures 1 to 8 shown when executed by a processor.

[0185] Based on the above-mentioned method as Figures 1 to 8 shown, correspondingly, this 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 method as Figures 1 to 8 shown is implemented.

[0186] Based on such an understanding, the technical solution of this application can be embodied in the form of a software product. The software product can be stored in a non-volatile storage medium (which can be a CD-ROM, a USB flash drive, a mobile hard disk, etc.), and includes several instructions for causing a computer device (which can be a personal computer, a server, or a network device, etc.) to execute the methods in various implementation scenarios of this application.

[0187] As Figure 11 shown, the following is a schematic hardware structure diagram of an electronic device according to the present invention, including:

[0188] At least one processor 1101; and,

[0189] A memory 1102 communicatively connected to at least one of the processors 1101; wherein,

[0190] The memory 1102 stores instructions executable by at least one of the processors. The instructions are executed by at least one of the processors so that at least one of the processors can execute the teaching material generation method as described above.

[0191] Figure 11 Taking one processor 1101 as an example in

[0192] The electronic device may further include: an input device 1103 and a display device 1104.

[0193] The processor 1101, the memory 1102, the input device 1103, and the display device 1104 may be connected through a bus or other means. In the figure, the connection through a bus is taken as an example.

[0194] The memory 1102, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the review content generation method in the embodiments of this application. For example, Figures 1 to 8 the method flow as shown. The processor 1101 executes various functional applications and data processing by running the non-volatile software programs, instructions, and modules stored in the memory 1102, that is, implements the teaching material generation method in the above-mentioned embodiments.

[0195] The memory 1102 may include a program storage area and a data storage area. The program storage area may store an operating system and application programs required for at least one function. The data storage area may store data created according to the usage of the review content generation method, etc. In addition, the memory 1102 may include a high-speed random access memory and may also include non-volatile memory, such as at least one magnetic disk storage device, a flash memory device, or other non-volatile solid-state storage devices. In some embodiments, the memory 1102 may optionally include a memory remotely disposed relative to the processor 1101, and these remote memories may be connected to the device executing the review content generation method through a network. Examples of the above network include but are not limited to the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0196] The input device 1103 may receive input user clicks and generate signal inputs related to user settings and function controls of the review content generation method. The display device 1104 may include a display screen and other display devices.

[0197] When the one or more modules are stored in the memory 1102 and run by the one or more processors 1101, they execute the teaching material generation method in any of the above method embodiments.

[0198] Optionally, the above physical device may further include a user interface, a network interface, a camera, a radio frequency (RF) circuit, sensors, an audio circuit, a WI-FI module, etc. The user interface may include a display screen and an input unit such as a keyboard, etc. Optionally, the user interface may further 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.

[0199] Those skilled in the art can understand that the above physical device structure provided in this embodiment does not limit the physical device, and it may include more or fewer components, or combine certain components, or have different component arrangements.

[0200] The storage medium may further include an operating system and a network communication module. The operating system is a program for managing the hardware and software resources of the above physical device and supports the operation of information processing programs and other software and / or programs. The network communication module is used to implement communication between components inside the storage medium and communication between other hardware and software in the information processing physical device.

[0201] Through the description of the above embodiments, 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 can also be implemented by hardware. By applying the solution of this embodiment, compared with the current existing technologies, this embodiment obtains the first historical data set of multiple historical students, and based on the first historical data set, constructs a learning performance prediction model, where the first historical data set includes the learning performances of multiple historical students; obtains the second historical data set of multiple historical students, and based on the second historical data set, constructs a learning performance prediction model, where the second historical data set includes the learning performances of multiple historical students; constructs a teaching material generation model based on the learning performance prediction model and the learning performance prediction model; determines the learning ability of the target student based on the teaching material generation model, and realizes constructing a teaching material generation model by constructing a learning performance prediction model and a learning performance prediction model, so that the teaching material generation model can comprehensively evaluate the learning performance of the target student in the objective aspect and the learning performance in the subjective aspect, improves the accuracy and diversity of the teaching material generation model, helps schools or parents more intuitively and clearly understand the all-round development of students' learning ability, discovers in time the reasons for students' performance decline, and intervenes as early as possible to guide a targeted learning tutoring plan.

[0202] 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 actual relationship or order between these entities or operations. Moreover, the term "comprising", "including" or any other variant thereof is intended to cover a non-exclusive inclusion, so that a process, method, article or device including a series of elements not only includes those elements, but also includes other elements not expressly listed, or further includes elements inherent to such process, method, article or device. Without further limitation, an element defined by the statement "including a..." does not exclude the existence of additional identical elements in the process, method, article or device including the said element.

[0203] The above are only specific embodiments of the present application, enabling those skilled in the art to understand or implement the present application. Various modifications to these embodiments will be obvious 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 these embodiments described herein, but will conform to the widest scope consistent with the principles and novel features claimed herein.

Claims

1. A teaching material generation method, characterized in that: include: Based on the smart education terminal, the first important knowledge point cluster is extracted from the textbook, the second important knowledge point cluster is extracted from the history question bank, and the third important knowledge point cluster is extracted from the feature data set containing the factors affecting students' wrong answers; Using a first similarity algorithm, a similarity evaluation is performed on the importance identification vector corresponding to the second important knowledge point cluster and the importance identification vector corresponding to the third important knowledge point cluster, and based on the similarity evaluation result, a first candidate knowledge point cluster with similar importance is evaluated within the knowledge point range corresponding to the first important knowledge point cluster; Using a second similarity algorithm, evaluating the second candidate knowledge point clusters with similar importance in the second important knowledge point cluster and the third important knowledge point cluster within the knowledge point range, and selecting the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster; The first important knowledge point cluster is updated based on the first target knowledge point to obtain an updated first target important knowledge point cluster, and an electronic teaching material is generated based on the first target important knowledge point cluster.

2. The method according to claim 1, characterized in that The step of extracting the first important knowledge point cluster from the teaching material based on the smart education terminal includes: Performing text analysis on the teaching material based on the smart education terminal to obtain knowledge points in the teaching material; Classifying the knowledge points according to the association relationship between the knowledge points to obtain classification identifiers corresponding to the knowledge points; Encoding the hierarchical identification corresponding to the knowledge point to obtain an identification coding value of the knowledge point at each level; Determine a set of importance identification vectors corresponding to the knowledge points based on the classification identifications corresponding to the knowledge points and the identification code values ​​of the knowledge points at each classification, and generate a basic knowledge point cluster based on the identification vector set; The first important knowledge point cluster is determined based on the importance of knowledge points in the basic knowledge point cluster.

3. The method according to claim 2, characterized in that The determining the first important knowledge point cluster based on the importance of the knowledge points in the basic knowledge point cluster includes: Determining the difficulty level corresponding to the knowledge points in the basic knowledge point cluster according to the degree of refinement of the knowledge points in the basic knowledge point cluster; Using a pre-trained evaluation model, determining the importance of the knowledge points in the basic knowledge point cluster; The basic knowledge point cluster is screened based on the importance of the knowledge points and a first preset screening threshold, and the screened knowledge point set is determined as the first important knowledge point cluster, wherein the first preset screening threshold is an initial value set for the importance of the knowledge points.

4. The method according to claim 1, characterized in that: The step of extracting the second most important knowledge point cluster from the history question bank includes: Determine the difficulty level score of each of the knowledge points involved in the history question bank based on all the knowledge points involved in the history question bank and the pre-trained important knowledge point evaluation model; Based on the difficulty level score of each knowledge point in all the knowledge points involved in the historical question bank and the second preset screening threshold, all the knowledge points involved in the historical question bank are screened, and the screened knowledge point set is determined as the second important knowledge point cluster, and the second preset screening threshold is the initial value set for the difficulty level corresponding to the knowledge point.

5. The method according to claim 1, characterized in that The third important knowledge point cluster is extracted from the feature data set containing the factors affecting students' wrong answers, including: Based on the feature data set containing the influencing factors of students' wrong answers, a preset wrong answer correlation evaluation model is used to determine the correlation between each wrong answer influencing factor and the wrong answer in the feature data set containing the influencing factors of students' wrong answers, wherein the wrong answer influencing factors include subjective factors and objective factors; Screening out features of objective factors that cause students to make mistakes in the questions from the feature data set containing factors affecting students' mistakes in the questions, and sorting the features of objective factors that cause students to make mistakes in the questions from large to small according to the correlation; The knowledge point set corresponding to the feature with the greatest correlation is determined as the third important knowledge point cluster.

6. The method according to claim 2, characterized in that After the first important knowledge point cluster is updated based on the first target knowledge point to obtain an updated first target important knowledge point cluster, the method further includes: Using a first similarity algorithm, a similarity evaluation is performed on the importance identification vector corresponding to the second important knowledge point cluster and the importance identification vector corresponding to the third important knowledge point cluster, and based on the similarity evaluation result, a third candidate knowledge point cluster with similar importance is evaluated outside the knowledge point range corresponding to the first important knowledge point cluster; Using a second similarity algorithm, evaluating a fourth candidate knowledge point cluster with similar importance in the second important knowledge point cluster and the third important knowledge point cluster outside the knowledge point range, and selecting the same second target knowledge point from the third candidate knowledge point cluster and the fourth candidate knowledge point cluster; If the importance identification vector corresponding to the second target knowledge point is the same as the importance identification vector corresponding to the knowledge point in the basic knowledge point cluster, then the first target important knowledge point cluster is updated using the importance identification vector corresponding to the second target knowledge point to obtain an updated second target important knowledge point cluster; The step of generating an electronic teaching material based on the first target important knowledge point cluster includes: An electronic textbook is generated based on the second target important knowledge point cluster to obtain an updated electronic textbook.

7. The method according to claim 6, characterized in that After the electronic teaching material is generated according to the second target important knowledge point cluster, the method comprises: The knowledge points in the updated electronic teaching material are highlighted by using the knowledge points in the second important knowledge point cluster and / or the knowledge points in the third important knowledge point cluster.

8. A teaching material generating device, characterized in that: include: An extraction unit, used to extract a first important knowledge point cluster from the textbook, a second important knowledge point cluster from the history question bank, and a third important knowledge point cluster from a feature data set containing factors affecting students' wrong answers based on the smart education terminal; an evaluation unit, configured to perform similarity evaluation on the importance identification vector corresponding to the second important knowledge point cluster and the importance identification vector corresponding to the third important knowledge point cluster using a first similarity algorithm, and to evaluate a first candidate knowledge point cluster with similar importance within the knowledge point range corresponding to the first important knowledge point cluster based on the similarity evaluation result; a screening unit, configured to evaluate, within the knowledge point range, second candidate knowledge point clusters with similar importance in the second important knowledge point cluster and the third important knowledge point cluster using a second similarity algorithm, and select the same first target knowledge point from the first candidate knowledge point cluster and the second candidate knowledge point cluster; A generating unit is used to update the first important knowledge point cluster based on the first target knowledge point to obtain an updated first target important knowledge point cluster, and generate an electronic teaching material based on the first target important knowledge point cluster.

9. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the teaching material generating method according to any one of claims 1 to 7 is implemented.

10. 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 teaching material generating method according to any one of claims 1 to 7 is implemented.

Images