Note generation method based on intelligent learning terminal

Abstract

The invention provides a note generation method based on an intelligent learning terminal, and the method comprises the steps: building a dependency relationship graph through presetting a first knowledge point learning relationship, and building an answer counting matrix and a dependency error matrix based on a knowledge point answer sample and the dependency relationship graph, so as to correct errors in the dependency relationship graph, and improve the accuracy of note generation. The accuracy of determining the incidence relation between the first knowledge points is improved; and determining a weak knowledge point set corresponding to the knowledge point answering sample according to the answering condition of the knowledge point answering sample, matching the weak knowledge point set with the corrected dependency relationship graph, and generating personalized learning notes corresponding to the knowledge point answering sample by using preset learning materials. And the flexibility and accuracy of learning note generation are improved.

Description

Technical Field

[0001] The present disclosure relates to the field of computer technology, and in particular to a note generation method based on an intelligent learning terminal. Background Art

[0002] In recent years, with the continuous advancement of computer technology and educational informatization, computer and artificial intelligence technology have gradually been applied to various daily educational and teaching activities. More and more intelligent devices are gradually being applied to teaching scenarios. Students can learn through intelligent devices to provide students with more convenient learning services. In the process of students using intelligent devices to study, intelligent devices can provide students with the function of taking study notes.

[0003] At present, students can usually only be provided with pre-set study notes based on the chapters and types of textbooks, which may result in the study notes provided not being adapted to the needs of students. Alternatively, the students may be tested to determine the knowledge points that they have poorly mastered, and thus study notes may be provided to them. However, providing study notes only for the knowledge points that students have poorly mastered may result in students only being able to master individual knowledge points, and being unable to achieve serial learning between knowledge points. For solutions that can provide study notes that serially connect multiple knowledge points, a pre-set method is usually used to serially connect the knowledge points, and the serial relationship cannot be updated in a timely manner, and personalized study notes cannot be provided to students. Summary of the invention

[0004] The present disclosure provides a note generation method based on an intelligent learning terminal.

[0005] According to a first aspect of the present disclosure, a note generation method based on an intelligent learning terminal is provided, the method comprising: based on a preset first knowledge point learning relationship, using an attention network model to extract associated features of the first knowledge point to construct a dependency graph of the first knowledge point, the first knowledge point comprising a preceding first knowledge point and a dependent first knowledge point; in response to a dependency graph update instruction, obtaining a knowledge point answer sample to determine an average dependency error of the first knowledge point and an answer count matrix of the first knowledge point in the dependency graph; based on the average dependency error and the answer status of the knowledge point answer sample, determining a dependency error matrix of the dependent first knowledge point; based on the answer count matrix and the dependency error matrix, determining an error of the preset first knowledge point learning relationship to update the dependency graph; based on a first knowledge point set corresponding to a single knowledge point answer sample, updating a preset mastery probability of the first knowledge point set to determine a weak knowledge point set corresponding to the knowledge point answer sample; based on the weak knowledge point set and the updated dependency graph, generating learning notes using preset learning materials.

[0006] In some embodiments of the present disclosure, based on a preset first knowledge point learning relationship, an attention network model is used to extract associated features of the first knowledge point to construct a dependency graph of the first knowledge point, including: based on the preset first knowledge point learning relationship, an associated feature vector of the first knowledge point is extracted; based on the associated feature vector, an initial relationship graph of the first knowledge point is constructed using a triple method; the initial relationship graph is vectorized to obtain vectorized codes of the first knowledge points corresponding to adjacent nodes; based on the vectorized codes, invisible features between the first knowledge points are determined; based on the invisible features, the initial relationship graph is updated to construct a dependency graph.

[0007] In some embodiments of the present disclosure, obtaining knowledge point answer samples to determine the average dependency error of the first knowledge point in the dependency graph and the answer count matrix of the first knowledge point includes: based on the dependency graph, determining the first correct answer sample of the preceding first knowledge point, the first incorrect answer sample dependent on the first knowledge point, the second correct answer sample dependent on the first knowledge point, and the number of dependent first knowledge points of the preceding first knowledge point in the knowledge point answer samples; based on the first correct answer sample, the second correct answer sample and the first incorrect answer sample, determining the abnormal samples and the answer count matrix in the knowledge point answer samples; based on the dependent knowledge point set corresponding to the knowledge point answer samples, the second correct answer sample, the abnormal samples and the number of dependent first knowledge points of the preceding first knowledge point, determining the average dependency error, the dependent knowledge point set consisting of the preceding first knowledge point and the dependent first knowledge point.

[0008] In some embodiments of the present disclosure, determining abnormal samples and an answer count matrix in knowledge point answer samples based on the first correct answer sample and the second correct answer sample includes: determining that the preceding first knowledge point answer corresponding to the same sample source is incorrect based on the first correct answer sample and the first incorrect answer sample, and when the answer to the first knowledge point is correct, determining the first correct answer sample corresponding to the same sample source as an abnormal sample; determining the answer count matrix based on the number of first correct answer samples, the number of second correct answer samples, and the number of abnormal samples.

[0009] In some embodiments of the present disclosure, determining the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample, and the number of dependent first knowledge points of the preceding first knowledge point includes: determining the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample, and the number of dependent first knowledge points of the preceding first knowledge point in combination with the following formula 1: Formula 1, Where M represents the average dependency error, N(E) represents the number of dependent first knowledge points corresponding to the previous first knowledge point, i represents the previous first knowledge point, j represents the dependent first knowledge point, and E represents the set of dependent knowledge points. represents the number of abnormal samples, Indicates the number of the second correct answer samples.

[0010] In some embodiments of the present disclosure, based on the average dependency error and the answer situation of the knowledge point answer sample, determining the dependency error matrix that depends on the first knowledge point includes: based on the knowledge point answer sample, determining the number of first correct answer samples, the number of second correct answer samples, and the total number of knowledge point answer samples; based on the number of first correct answer samples, the number of second correct answer samples, the total number, and the average dependency error, combined with the following formula 2, determining the dependency error matrix: Formula 2, in, represents the dependency error matrix, represents the number of the first correct answer samples, and n represents the total number.

[0011] In some embodiments of the present disclosure, based on the answer count matrix and the dependency error matrix, determining the error of the preset first knowledge point learning relationship to update the dependency graph includes: based on the answer count matrix and the dependency error matrix, combined with the following formula 3, determining the dependency error of the dependent knowledge point set includes: Formula 3, Where Diff represents the dependency error of the dependent knowledge point set, m represents the diagonal elements in the answer count matrix and the dependency error matrix, represents the answer count matrix; When the dependency error is greater than a preset error threshold, it is determined that there is an error in the dependency graph for the first knowledge point included in the dependent knowledge point set; based on the first knowledge point included in the dependent knowledge point set, the dependency graph is updated using the attention network model.

[0012] In some embodiments of the present disclosure, based on the first knowledge point set corresponding to the single knowledge point answer sample, the preset mastery probability of the first knowledge point set is updated to determine the weak knowledge point set corresponding to the knowledge point answer sample, including: determining the correct answer probability of the first knowledge point set based on the knowledge point answer sample; based on the first knowledge point set corresponding to the single knowledge point answer sample, and the correct answer probability, updating the preset mastery probability of the first knowledge point set to obtain the sample mastery probability; determining the weak knowledge point set of the knowledge point answer sample based on the sample mastery probability and the preset knowledge point mastery threshold.

[0013] In some embodiments of the present disclosure, based on the first knowledge point set corresponding to the single knowledge point answer sample and the correct answer probability, the preset mastery probability of the first knowledge point set is updated to obtain the sample mastery probability, including: determining the update weight of the preset mastery probability based on the correct answer probability; determining the updated mastery probability based on the answer situation of the knowledge point answer sample, the first knowledge point set corresponding to the single knowledge point answer sample, the preset mastery probability, and the update weight; and normalizing the updated mastery probability to obtain the sample mastery probability.

[0014] In some embodiments of the present disclosure, determining the weak knowledge point set of the knowledge point answer sample based on the sample mastery probability and the preset knowledge point mastery threshold includes: determining the comprehensive mastery probability of the first knowledge point in the knowledge point answer sample based on the sample mastery probability and the preset knowledge point weight in combination with the following formula 4: Formula 4, in, , represents the comprehensive mastery probability, Indicates the preset knowledge point weight, Indicates the first knowledge point, represents the first knowledge point set, Represents the sample mastery probability; compare the comprehensive mastery probability with the preset knowledge point mastery threshold to determine the set of weak knowledge points.

[0015] In some embodiments of the present disclosure, based on a set of weak knowledge points and an updated dependency graph, using preset learning materials, generating learning notes includes: matching the first knowledge point in the set of weak knowledge points with the updated dependency graph to determine the knowledge points that need to be included in the learning notes; based on the knowledge points that need to be included in the learning notes, extracting corresponding knowledge content from the preset learning materials to generate learning notes.

[0016] In summary, the present disclosure proposes a note generation method based on an intelligent learning terminal, including: based on a preset first knowledge point learning relationship, using an attention network model to extract the associated features of the first knowledge point to construct a dependency graph of the first knowledge point, the first knowledge point including a preceding first knowledge point and a dependent first knowledge point; in response to a dependency graph update instruction, obtaining a knowledge point answer sample to determine the average dependency error of the first knowledge point in the dependency graph and an answer count matrix of the first knowledge point; based on the average dependency error and the answer situation of the knowledge point answer sample, determining the dependency error matrix of the dependent first knowledge point; based on the answer count matrix and the dependency error matrix, determining the error of the preset first knowledge point learning relationship to update the dependency graph; based on the first knowledge point set corresponding to the single knowledge point answer sample, updating the preset mastery probability of the first knowledge point set to determine the weak knowledge point set corresponding to the knowledge point answer sample; based on the weak knowledge point set and the updated dependency graph, generating learning notes using preset learning materials. The method disclosed in the present invention constructs a dependency graph by presetting the learning relationship of the first knowledge point, and constructs an answer count matrix and a dependency error matrix based on the knowledge point answer samples and the dependency graph to correct the errors existing in the dependency graph, thereby improving the accuracy of determining the association relationship between the first knowledge points; and then determines the set of weak knowledge points corresponding to the knowledge point answer samples based on the answer situation of the knowledge point answer samples, thereby matching the set of weak knowledge points with the corrected dependency graph, and using the preset learning materials to generate personalized learning notes corresponding to the knowledge point answer samples, thereby improving the flexibility and accuracy of learning note generation.

[0017] It should be understood that the content described in this section is not intended to identify the key or important features of the embodiments of the present application, nor is it intended 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

[0018] The accompanying drawings are used to better understand the present solution and do not constitute a limitation of the present disclosure. Figure 1 A flowchart of a method for generating notes based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 2 A schematic diagram of a flow chart of a second method for generating notes based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 3 A schematic diagram of a flow chart of a third method for generating notes based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 4 A schematic diagram of a fourth method for generating notes based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 5A flowchart of a fifth method for generating notes based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 6 A schematic diagram of the structure of a note generating device based on an intelligent learning terminal provided in an embodiment of the present disclosure; Figure 7 A schematic diagram of the hardware structure of an electronic device provided in an embodiment of the present disclosure. DETAILED DESCRIPTION

[0019] The following is a description of exemplary embodiments of the present disclosure in conjunction with the accompanying drawings, including various details of the embodiments of the present disclosure to facilitate understanding, which should be considered as merely exemplary. Therefore, it should be recognized by those of ordinary skill in the art that various changes and modifications may 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 in the following description.

[0020] In recent years, with the continuous advancement of computer technology and educational informatization, computer and artificial intelligence technology have gradually been applied to various daily educational and teaching activities. More and more intelligent devices are gradually being applied to teaching scenarios. Students can learn through intelligent devices to provide students with more convenient learning services. In the process of students using intelligent devices to study, intelligent devices can provide students with the function of taking study notes.

[0021] At present, students can usually only be provided with pre-set study notes based on the chapters and types of textbooks, which may result in the study notes provided not being adapted to the needs of students. Alternatively, the students may be tested to determine the knowledge points that they have poorly mastered, and thus study notes may be provided to them. However, providing study notes only for the knowledge points that students have poorly mastered may result in students only being able to master individual knowledge points, and being unable to achieve serial learning between knowledge points. For solutions that can provide study notes that serially connect multiple knowledge points, a pre-set method is usually used to serially connect the knowledge points, and the serial relationship cannot be updated in a timely manner, and personalized study notes cannot be provided to students.

[0022] In order to solve the problems in the related technology, the present invention proposes a note generation method based on an intelligent learning terminal, which constructs a dependency graph by presetting the first knowledge point learning relationship, and constructs an answer count matrix and a dependency error matrix based on the knowledge point answer samples and the dependency graph to correct the errors existing in the dependency graph, thereby improving the accuracy of determining the association relationship between the first knowledge points; and then, according to the answer situation of the knowledge point answer samples, the weak knowledge point set corresponding to the knowledge point answer samples is determined, so as to match the weak knowledge point set with the corrected dependency graph, and use the preset learning materials to generate personalized learning notes corresponding to the knowledge point answer samples, thereby improving the flexibility and accuracy of learning note generation.

[0023] A note generation method based on an intelligent learning terminal according to an embodiment of the present disclosure is described below with reference to the accompanying drawings.

[0024] Figure 1 The following is a flow chart of a method for generating notes based on an intelligent learning terminal provided by an embodiment of the present disclosure. Figure 1 As shown, the method can be applied to an intelligent learning terminal, including: Step 101: Based on the preset first knowledge point learning relationship, the attention network model is used to extract the associated features of the first knowledge point to construct a dependency graph of the first knowledge point.

[0025] In some embodiments, the intelligent learning terminal can be implemented based on hardware devices (such as tablet computers, smart whiteboards), or based on software applications installed on ordinary computers or mobile devices. Usually, these intelligent learning terminals can be connected to cloud services to access rich educational resources and perform data synchronization. In other words, the intelligent learning terminal can record the first student's problem-solving, learning, reviewing and other processes while the first student is doing the exercises and learning, thereby providing personalized learning notes for the user.

[0026] Optionally, the smart learning terminal can also synchronously display the teacher's operations, knowledge point annotations (for example, on the smart learning terminal), explanation content, dynamic demonstrations, etc. for students.

[0027] In some embodiments, the first knowledge point may be any knowledge point in any subject, which is not limited in the present disclosure. For example, it is shown in Table 1: Table 1

[0028] In some embodiments, the preset first knowledge point learning relationship may be a predefined logical relationship and learning order between the first knowledge points, for example, the first knowledge point 1 is a prerequisite for the first knowledge point 2; the first knowledge point 3 needs to be mastered before understanding the first knowledge point 4.

[0029] In some embodiments, through the attention network model, the correlation features between the preset first knowledge point learning relationships are extracted to construct a dependency graph, wherein each node in the dependency graph is a first knowledge point, and the edge between each node indicates the existence of a dependency relationship between two first knowledge points.

[0030] Furthermore, according to the preset first knowledge point learning relationship, the first knowledge point can be divided into a pre-conditional first knowledge point and a dependent first knowledge point, wherein the pre-conditional first knowledge point is a pre-conditional learning condition of the dependent first knowledge point, that is, the learning order is to first learn the pre-conditional first knowledge point and then learn the dependent first knowledge point. For example, the trigonometric function knowledge point can be the pre-conditional first knowledge point, and the inverse trigonometric function knowledge point can be the dependent first knowledge point of the trigonometric function knowledge point.

[0031] In some embodiments, a preceding first knowledge point may correspond to one or more dependent first knowledge points, which is not limited in the present disclosure.

[0032] In some embodiments, the preceding first knowledge point and the dependent first knowledge point are relative, that is, a first knowledge point can be both a preceding first knowledge point and a dependent first knowledge point. For example, a trigonometric function knowledge point can be a preceding first knowledge point of an inverse trigonometric function knowledge point, or a dependent first knowledge point of arithmetic operations knowledge point.

[0033] In some embodiments, the specific model of the attention network model is not limited, and it can be, for example, a neighborhood calibration graph attention network model (Neighborhood Calibration Graph Attention Network, NCGAT) and other models.

[0034] Specifically, based on the preset first knowledge point learning relationship, the associated feature vector of the first knowledge point can be extracted; based on the associated feature vector, the initial relationship graph of the first knowledge point can be constructed using the triple method; the initial relationship graph can be vectorized to obtain the vectorized encoding of the first knowledge point corresponding to the adjacent nodes; based on the vectorized encoding, the invisible features between the first knowledge points can be determined; based on the invisible features, the initial relationship graph can be updated to construct a dependency graph.

[0035] For example, the preset first knowledge point learning relationship may be initialized and embedded, and each first knowledge point may be initialized as an embedding vector, and the dimension of the embedding vector is 64 dimensions (but not limited thereto, and may also be other dimensions); Use NCGAT to capture the characteristics and relationships of the first knowledge point, so that the representation of each first knowledge point can reflect its position and importance in the entire knowledge system; The NCGAT model is used to compute embedding representations for each first knowledge point, where these embedding representations capture the relationships and dependencies between knowledge points.

[0036] Furthermore, the specific structure and execution process of the NCGAT model are as follows: Input layer: Extract knowledge points from the preset first knowledge point learning relationship (such as teaching objectives, course outline, chapter content, summary and review, and expert teaching knowledge base, etc.), and select the corresponding first knowledge points and related relationship features as model input.

[0037] Graph construction layer: Based on the knowledge points extracted from the above content and their associated features, the Subject-Action-Object (SAO) triple method is used to construct the knowledge point network association graph structure. SAO triples are used to construct the initial knowledge point network structure with knowledge points and associated features. Triples can be composed of basic, advanced, difficult and other levels. The triple classification of the first knowledge point is based on examining the same type of knowledge point set. Its complexity and difficulty increase with the level change, which can be used to extract the invisible dependency relationship between the first knowledge points.

[0038] Embedding layer: The knowledge point association network graph built based on SAO triples is vectorized, where the vectorized code is generated in sequence from basic, advanced, and difficult according to the hierarchical order of the SAO triple architecture to obtain vectorized codes of multiple single knowledge point sets.

[0039] Graph attention network layer: Using the graph attention network, a hidden masked self-attention layer is used to capture the importance of neighbor nodes in graph structured data. For example, there may be a combination of knowledge point units in a single knowledge point set, and the same test point may be examined in combination with multiple knowledge points, that is, there is a situation where the knowledge point set is crossed. This invisible feature of the knowledge point association network is used as a feature extractor by each layer of the graph attention network to aggregate information from neighboring nodes and generate new node feature representations by learning convolution kernel weights. Then, the attention mechanism is used to assign a unique attention score to each neighboring node to identify more important neighboring nodes. The knowledge point association network is updated through the graph attention network to generate the above-mentioned dependency graph. Since the graph attention network is a local model that allows exploration of neighboring nodes without accessing the entire graph, it can ensure that the invisible knowledge point association feature is incorporated from a single knowledge point set without damaging the initial knowledge point association network graph, thereby improving the accuracy of graph attention network construction.

[0040] Step 102: In response to the dependency graph update instruction, obtain knowledge point answer samples to determine the average dependency error of the first knowledge point in the dependency graph and the answer count matrix of the first knowledge point.

[0041] In some embodiments, when the user is ready to generate learning notes, a dependency graph update instruction may be sent to the intelligent learning terminal to update the dependency graph and improve the accuracy of the generated learning notes.

[0042] In some embodiments, the intelligent learning terminal obtains knowledge point answer samples in response to the dependency graph update instruction, where the knowledge point answer samples can be knowledge point answer samples based on classes, study groups, specific student groups, etc. The present disclosure does not limit the scope of the knowledge point answer samples.

[0043] In some examples, based on the dependency graph, the first correct answer sample corresponding to the preceding first knowledge point, the first incorrect answer sample dependent on the first knowledge point, the second correct answer sample dependent on the first knowledge point, and the number of dependent first knowledge points of the preceding first knowledge point can be determined in the knowledge point answer sample; then, based on the first correct answer sample, the second correct answer sample and the first incorrect answer sample, the abnormal samples and the answer count matrix in the knowledge point answer sample are determined; and based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point, the average dependency error is determined. For details, see Figure 3 The embodiments shown will not be described in detail here.

[0044] In some embodiments, the average dependency error is used to indicate the error of the association relationship between different first knowledge points in the dependency graph.

[0045] In some embodiments, the answer count matrix is ​​used to indicate the number of correct answers for combinations of different first knowledge points in the large sample of knowledge points.

[0046] Step 103: Based on the average dependency error and the answer status of the knowledge point answer samples, determine the dependency error matrix that depends on the first knowledge point.

[0047] In some examples, the number of first correct answer samples, the number of second correct answer samples, and the total number of knowledge point answer samples can be determined based on the knowledge point answer samples; and then the dependency error matrix can be determined based on the number of first correct answer samples, the number of second correct answer samples, the total number, and the average dependency error. For details, see Figure 4 The embodiments shown will not be described in detail here.

[0048] In some embodiments, the dependency error matrix may be used to indicate the number of errors between the preceding first knowledge point and the dependent first knowledge point in the knowledge point answer sample.

[0049] Step 104: Based on the answer count matrix and the dependency error matrix, determine the error of the preset first knowledge point learning relationship to update the dependency graph.

[0050] In some embodiments, the error value of the dependent knowledge point set consisting of the preceding first knowledge point and the dependent first knowledge point can be determined based on the answer count matrix and the dependency error matrix, so that when the dependency error is greater than a preset error threshold, it is determined that the first knowledge point included in the dependent knowledge point set has an error in the dependency graph; and based on the first knowledge point included in the dependent knowledge point set, the dependency graph is updated using the attention network model.

[0051] Step 105 , based on the first knowledge point set corresponding to the single knowledge point answer sample, the preset mastery probability of the first knowledge point set is updated to determine the weak knowledge point set corresponding to the knowledge point answer sample.

[0052] In some embodiments, the probability of correct answers for a first knowledge point set can be determined based on knowledge point answer samples; based on the first knowledge point set corresponding to a single knowledge point answer sample and the probability of correct answers, the preset mastery probability of the first knowledge point set is updated to obtain the sample mastery probability; based on the sample mastery probability and the preset knowledge point mastery threshold, the weak knowledge point set of the knowledge point answer sample is determined.

[0053] In other words, by using the probability of correct answers in the knowledge point answer samples, the first knowledge point corresponding to the first knowledge point in the knowledge point answer samples that is poorly mastered is determined, thereby determining the weak knowledge point set. For details, see Figure 6 The embodiments shown will not be described in detail here.

[0054] Step 106, based on the weak knowledge point set and the updated dependency graph, using preset learning materials, generate learning notes.

[0055] In some embodiments, the first knowledge point in the weak knowledge point set can be matched with the updated dependency graph to determine the knowledge points that need to be included in the learning notes; then, based on the knowledge points that need to be included in the learning notes, the corresponding knowledge content is extracted from the preset learning materials to generate learning notes.

[0056] For example, the preset learning materials can be stored in the intelligent learning terminal, and the corresponding knowledge points in the preset learning materials can be extracted through semantic analysis, cluster analysis and other technologies. The weak knowledge point set determined above is matched with the updated dependency graph, and finally learning notes suitable for users corresponding to the knowledge point answer samples are automatically generated on the intelligent learning terminal device, such as key knowledge point annotations and material links under the knowledge point annotations, thereby realizing the generation of personalized notes and adapting to the learning strategy plans of different users.

[0057] In summary, the present disclosure proposes a note generation method based on an intelligent learning terminal, including: based on a preset first knowledge point learning relationship, using an attention network model to extract the associated features of the first knowledge point to construct a dependency graph of the first knowledge point, the first knowledge point including a preceding first knowledge point and a dependent first knowledge point; in response to a dependency graph update instruction, obtaining a knowledge point answer sample to determine the average dependency error of the first knowledge point in the dependency graph and an answer count matrix of the first knowledge point; based on the average dependency error and the answer situation of the knowledge point answer sample, determining the dependency error matrix of the dependent first knowledge point; based on the answer count matrix and the dependency error matrix, determining the error of the preset first knowledge point learning relationship to update the dependency graph; based on the first knowledge point set corresponding to the single knowledge point answer sample, updating the preset mastery probability of the first knowledge point set to determine the weak knowledge point set corresponding to the knowledge point answer sample; based on the weak knowledge point set and the updated dependency graph, using preset learning materials, generating learning notes. The method disclosed in the present invention constructs a dependency graph by presetting the learning relationship of the first knowledge point, and constructs an answer count matrix and a dependency error matrix based on the knowledge point answer samples and the dependency graph to correct the errors existing in the dependency graph, thereby improving the accuracy of determining the association relationship between the first knowledge points; and then determines the set of weak knowledge points corresponding to the knowledge point answer samples based on the answer situation of the knowledge point answer samples, thereby matching the set of weak knowledge points with the corrected dependency graph, and using the preset learning materials to generate personalized learning notes corresponding to the knowledge point answer samples, thereby improving the flexibility and accuracy of learning note generation.

[0058] As a possible implementation, Figure 2 The flowchart of the second method for generating notes based on the intelligent learning terminal is shown in FIG. 1 , based on the above embodiment, step 102 is further explained, and includes the following steps: Step 201: Based on the dependency graph, determine the first correct answer sample corresponding to the preceding first knowledge point, the first incorrect answer sample dependent on the first knowledge point, the second correct answer sample dependent on the first knowledge point, and the number of the preceding first knowledge point dependent on the first knowledge point in the knowledge point answer sample.

[0059] In some embodiments, the first knowledge points included in the knowledge point answer sample can be determined based on the association relationship between the various first knowledge points in the dependency graph, and the preceding first knowledge points and the dependent first knowledge points can be divided based on the included first knowledge points.

[0060] For example, the knowledge point answer sample includes three first knowledge points V1, V2 and V3. According to the dependency graph, it can be determined that V1 is the preceding first knowledge point of V2 and V3, and V2 can be the preceding first knowledge point of V3.

[0061] Step 202, based on the first correct answer sample, the second correct answer sample and the first incorrect answer sample, determine the abnormal samples and the answer count matrix in the knowledge point answer samples.

[0062] In some embodiments, based on the first correct answer sample and the first incorrect answer sample, it is determined that the answer to the preceding first knowledge point corresponding to the same sample source is incorrect, and when the answer to the dependent first knowledge point is correct, the first correct answer sample corresponding to the same sample source is determined as an abnormal sample, and then, based on the number of first correct answer samples, the number of second correct answer samples, and the number of abnormal samples, the answer count matrix is ​​determined.

[0063] For example, if in the knowledge point answer samples, user 1 gives an incorrect answer to knowledge point V1, but gives a correct answer to knowledge point V2, then the answer samples of user 1 to knowledge point V1 and knowledge point V2 can be determined as abnormal samples.

[0064] For example, the first correct answer sample, the second correct answer sample, the first wrong answer sample, and the second wrong answer sample dependent on the first knowledge point can be counted in the following table, where 1 indicates a correct answer and 0 indicates an incorrect answer: Table 2

[0065] Further, according to Table 2, the answer count matrix is ​​constructed, where the answer count matrix can be a The matrix of is the number of the first knowledge point, each element in the answer count matrix Representing knowledge points Wrong answer but knowledge points The number of correct answers can be counted according to Table 2. The value of The values ​​of can be shown in Table 3: Table 3

[0066] It should be understood that the pre-conditioning first knowledge point and the dependent first knowledge point may cover all the first knowledge points.

[0067] It should be understood that and There may be a dependency relationship or there may not be a dependency relationship, and this disclosure is not limited to this.

[0068] Step 203, determining the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point.

[0069] In some embodiments, the dependent knowledge point set consists of a preceding first knowledge point and a dependent first knowledge point.

[0070] In some embodiments, the average dependency error can be determined based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample, and the number of dependent first knowledge points of the preceding first knowledge point, combined with the following formula 1: Formula 1, Where M represents the average dependency error, N(E) represents the number of dependent first knowledge points corresponding to the previous first knowledge point, i represents the previous first knowledge point, j represents the dependent first knowledge point, and E represents the set of dependent knowledge points. represents the number of abnormal samples, Indicates the number of the second correct answer samples.

[0071] As a possible implementation, Figure 3 The flowchart of the third method for generating notes based on the intelligent learning terminal is shown, which further explains step 103 based on the above embodiment and includes the following steps: Step 301: Based on the knowledge point answer samples, determine the number of first correct answer samples, the number of second correct answer samples and the total number of knowledge point answer samples.

[0072] In some embodiments, the number of first correct answer samples, the number of second correct answer samples and the total number of knowledge point answer samples can be determined by counting the knowledge point answer samples.

[0073] Step 302: Determine a dependency error matrix based on the number of first correct answer samples, the number of second correct answer samples, the total number and the average dependency error.

[0074] In some embodiments, the dependency error matrix may be determined based on the number of first correct answer samples, the number of second correct answer samples, the total number, and the average dependency error in combination with the following formula 2: Formula 2, in, represents the dependency error matrix, represents the number of the first correct answer samples, and n represents the total number.

[0075] For example, when it is determined that the first knowledge point combination (i, j) has a dependency relationship according to the dependency graph, the average dependency error can be multiplied by the knowledge point The number of correct answer samples is used to determine the dependent error matrix, where the first knowledge point combination is a combination of any two first knowledge points in the knowledge point answer samples.

[0076] For example, according to the dependency graph, when it is determined that the first knowledge point combination (i, j) and its inverse (j, i) have no dependency relationship, it means that the two first knowledge points have no correlation, so the knowledge points can be used to identify the first knowledge point combination (i, j) and its inverse (j, i). The error probability is multiplied by the knowledge point The number of correct samples is used to determine the dependent error matrix.

[0077] For example, when it is determined that the first knowledge point combination (j, i) has a dependency relationship according to the dependency graph, the knowledge point The number of correct samples minus the number of knowledge points The number of correct samples, plus the knowledge points The number of correct samples is multiplied by the average dependency error of the knowledge point dependencies to determine the dependency error matrix.

[0078] As a possible implementation, Figure 4 The flowchart of the fourth method for generating notes based on the intelligent learning terminal is shown in the figure. Based on the above embodiment, step 104 is further explained, and includes the following steps: Step 401, based on the answer count matrix and the dependency error matrix, determine the dependency error of the dependent knowledge point set.

[0079] In some embodiments, the dependency error of the dependent knowledge point set can be determined based on the answer count matrix and the dependency error matrix in combination with the following formula 3: Formula 3, Where Diff represents the dependency error of the dependent knowledge point set, m represents the diagonal elements in the answer count matrix and the dependency error matrix, represents the answer count matrix.

[0080] Step 402: When the dependency error is greater than a preset error threshold, it is determined that an error exists in the dependency graph for the first knowledge point included in the dependent knowledge point set.

[0081] In some embodiments, when the dependency error is greater than a preset error threshold, it is determined that there is an error in the first knowledge point included in the dependency knowledge point set in the dependency graph; in other words, by judging whether the dependency error is greater than the preset error threshold, a set of dependent knowledge points with larger deviations in the dependency graph is screened out.

[0082] Step 403: Based on the first knowledge point included in the dependent knowledge point set, the dependency graph is updated using the attention network model.

[0083] In some embodiments, a set of dependent knowledge points with larger deviations in the dependency graph is screened out, which can be the actual learning path in the knowledge point answer sample. Therefore, the features of the set of dependent knowledge points with dependency errors greater than a preset threshold can be extracted and input into the attention network model to iteratively update the dependency graph, thereby obtaining an updated dependency graph.

[0084] As a possible implementation, Figure 5 The fifth flow chart of the note generation method based on the intelligent learning terminal shown in the figure further explains step 105 based on the above embodiment, and includes the following steps: Step 501, based on knowledge point answer samples, determine the correct answer probability of the first knowledge point set.

[0085] In some embodiments, statistics may be collected on knowledge point answer samples to determine the probability of correct answers to the first knowledge point set.

[0086] In some embodiments, the probability of correct answers to the first knowledge point set may also be calculated and determined based on the preset mastery probability of the first knowledge point set.

[0087] In some embodiments, the first knowledge point set for the knowledge point answer samples and the preset mastering probability of the first knowledge point set may be as shown in Table 4: Table 4

[0088] in, .

[0089] Furthermore, the probability of a correct answer can be calculated using the following formula: , Among them, R(q) represents the probability of correct answer, Indicates whether the current knowledge point answer sample q contains the first knowledge point set , which is calculated as follows: if the current knowledge point answer sample q contains the first knowledge point set ,but The value is 1; if the current knowledge point answer sample q does not contain the first knowledge point set ,but The value is 0.

[0090] Step 502, based on the first knowledge point set corresponding to the single knowledge point answer sample and the correct answer probability, the preset mastery probability of the first knowledge point set is updated to obtain the sample mastery probability.

[0091] In some embodiments, the updated weight of the preset mastery probability can be determined based on the probability of correct answers; the updated mastery probability can be determined based on the answer status of the knowledge point answer samples, the first knowledge point set corresponding to the single knowledge point answer samples, the preset mastery probability, and the updated weight; the updated mastery probability is normalized to obtain the sample mastery probability.

[0092] Specifically, the update weight can be determined by the following formula: , Among them, θ and θ compl represents the update weight, and k represents the preset parameter.

[0093] Specifically, the mastering probability is updated by the following formula: If the current knowledge point answer sample q is a correct answer sample, the first mastery probability can be determined by the following formula: , in represents the first mastery probability; If the current knowledge point answer sample q is a wrong answer sample, the second mastering probability can be determined by the following formula: , in represents the second mastery probability; Then, the first grasping probability and the second grasping probability are normalized, and the result of the normalization is determined as the sample grasping probability.

[0094] Step 503, based on the sample mastery probability and the preset knowledge point mastery threshold, determine the weak knowledge point set of the knowledge point answer sample.

[0095] When the sample mastering probability is less than a preset knowledge point mastering threshold, one or more first knowledge points corresponding to the sample mastering probability may be determined as weak knowledge points, thereby constructing a weak knowledge point set.

[0096] Among them, the preset knowledge point mastery threshold can be multiple thresholds to distinguish the weakness of the first knowledge point. For example, when the sample mastery probability is less than 30, it can be considered that the first knowledge point corresponding to the sample mastery probability has not been mastered; for example, when the sample mastery probability is less than 90 and greater than or equal to 30, it can be considered that the first knowledge point corresponding to the sample mastery probability needs to be consolidated.

[0097] Corresponding to the above-mentioned note generation method based on an intelligent learning terminal, the present invention also provides a note generation device based on an intelligent learning terminal. Since the device embodiment of the present invention corresponds to the above-mentioned method embodiment, for the details not disclosed in the device embodiment, reference may be made to the above-mentioned method embodiment, and no further elaboration will be provided in the present invention.

[0098] Figure 6 FIG. is a schematic structural diagram of a note generation device based on an intelligent learning terminal provided by an embodiment of the present disclosure. As Figure 6 shown, the device includes: A construction unit 610, configured to extract associated features of a first knowledge point by using an attention network model based on a preset first knowledge point learning relationship, so as to construct a dependency graph of the first knowledge point, where the first knowledge point includes a preposed first knowledge point and a dependent first knowledge point; A first determination unit 620, configured to obtain a knowledge point answering sample in response to a dependency graph update instruction, so as to determine an average dependency error of the first knowledge point in the dependency graph and an answering count matrix of the first knowledge point; A second determination unit 630, configured to determine a dependency error matrix of the dependent first knowledge point based on the average dependency error and the answering situation of the knowledge point answering sample; An update unit 640, configured to determine an error of the preset first knowledge point learning relationship based on the answering count matrix and the dependency error matrix, so as to update the dependency graph; A third determination unit 650, configured to update a preset mastery probability of the first knowledge point set corresponding to a single knowledge point answering sample, so as to determine a weak knowledge point set corresponding to the knowledge point answering sample; A generation unit 660, configured to generate learning notes by using preset learning materials based on the weak knowledge point set and the updated dependency graph.

[0099] In some embodiments of the present disclosure, the construction unit 610 is further configured to: extract an associated feature vector of the first knowledge point based on a preset first knowledge point learning relationship; construct an initial relationship graph of the first knowledge point by using a triple method based on the associated feature vector; vectorize the initial relationship graph to obtain a vectorized encoding of the first knowledge point corresponding to adjacent nodes; determine an implicit feature between the first knowledge points based on the vectorized encoding; and update the initial relationship graph based on the implicit feature to construct a dependency graph.

[0100] In some embodiments of the present disclosure, the first determination unit 620 is further used to: determine the first correct answer sample of the preceding first knowledge point, the first incorrect answer sample dependent on the first knowledge point, the second correct answer sample dependent on the first knowledge point, and the number of dependent first knowledge points of the preceding first knowledge point in the knowledge point answer sample based on the dependency graph; determine the abnormal samples and the answer count matrix in the knowledge point answer sample based on the first correct answer sample, the second correct answer sample and the first incorrect answer sample; determine the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point, wherein the dependent knowledge point set consists of the preceding first knowledge point and the dependent first knowledge point.

[0101] In some embodiments of the present disclosure, the first determination unit 620 is further used to: determine, based on the first correct answer sample and the first incorrect answer sample, that the answer to the preceding first knowledge point corresponding to the same sample source is incorrect, and when the answer to the dependent first knowledge point is correct, determine the first correct answer sample corresponding to the same sample source as an abnormal sample; determine the answer count matrix based on the number of first correct answer samples, the number of second correct answer samples, and the number of abnormal samples.

[0102] In some embodiments of the present disclosure, the first determining unit 620 is further used to determine the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample, and the number of dependent first knowledge points of the preceding first knowledge point, in combination with the following formula 1: Formula 1, Where M represents the average dependency error, N(E) represents the number of dependent first knowledge points corresponding to the previous first knowledge point, i represents the previous first knowledge point, j represents the dependent first knowledge point, and E represents the set of dependent knowledge points. represents the number of abnormal samples, Indicates the number of the second correct answer samples.

[0103] In some embodiments of the present disclosure, the second determination unit 630 is further used to: determine the number of first correct answer samples, the number of second correct answer samples, and the total number of knowledge point answer samples based on the knowledge point answer samples; determine the dependency error matrix based on the number of first correct answer samples, the number of second correct answer samples, the total number, and the average dependency error in combination with the following formula 2: Formula 2, in, represents the dependency error matrix, represents the number of the first correct answer samples, and n represents the total number.

[0104] In some embodiments of the present disclosure, the updating unit 640 is further configured to: determine the dependency error of the dependent knowledge point set based on the answer count matrix and the dependency error matrix in combination with the following formula 3: Formula 3, Where Diff represents the dependency error of the dependent knowledge point set, m represents the diagonal elements in the answer count matrix and the dependency error matrix, represents the answer count matrix; When the dependency error is greater than a preset error threshold, determining that a first knowledge point included in the dependent knowledge point set has an error in the dependency relationship graph; Based on the first knowledge point included in the dependent knowledge point set, the dependency graph is updated using the attention network model.

[0105] In some embodiments of the present disclosure, the third determination unit 650 is further used to: determine the correct answer probability of the first knowledge point set based on the knowledge point answer samples; update the preset mastery probability of the first knowledge point set based on the first knowledge point set corresponding to the single knowledge point answer sample and the correct answer probability to obtain the sample mastery probability; determine the weak knowledge point set of the knowledge point answer sample based on the sample mastery probability and the preset knowledge point mastery threshold.

[0106] In some embodiments of the present disclosure, the third determination unit 650 is further used to: determine the updated weight of the preset mastery probability based on the correct answer probability; determine the updated mastery probability based on the answer situation of the knowledge point answer sample, the first knowledge point set corresponding to the single knowledge point answer sample, the preset mastery probability, and the updated weight; and normalize the updated mastery probability to obtain the sample mastery probability.

[0107] In some embodiments of the present disclosure, the third determining unit 650 is further configured to determine the comprehensive mastery probability of the first knowledge point in the knowledge point answer sample based on the sample mastery probability and the preset knowledge point weights in combination with the following formula 4: Formula 4, in, , represents the comprehensive mastery probability, Indicates the preset knowledge point weight, Indicates the first knowledge point, represents the first knowledge point set, Represents the sample mastery probability; compare the comprehensive mastery probability with the preset knowledge point mastery threshold to determine the set of weak knowledge points.

[0108] In some embodiments of the present disclosure, the generation and determination unit 660 is also used to: match the first knowledge point in the weak knowledge point set with the updated dependency graph to determine the knowledge points that need to be included in the study notes; based on the knowledge points that need to be included in the study notes, extract corresponding knowledge content from preset learning materials to generate study notes.

[0109] It should be noted that the above explanation of the method embodiment is also applicable to the device of this embodiment, and the principle is the same, which is not limited in this embodiment.

[0110] Based on the above Figures 1 to 5 The method shown in the figure, accordingly, this embodiment also provides a computer program product, including a computer program, which implements the above-mentioned Figures 1 to 5 The method shown.

[0111] Based on the above Figures 1 to 5 The 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 Figures 1 to 5 The method shown.

[0112] 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.

[0113] like Figure 7 The figure shows a hardware structure diagram of an electronic device of the present invention, including: at least one processor 701; and, A memory 702 that is communicatively connected to at least one of the processors 701; wherein, The memory 702 stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the note generation method based on the intelligent learning terminal as described above.

[0114] Figure 7 A processor 701 is taken as an example.

[0115] The electronic device may further include: an input device 703 and a display device 704 .

[0116] The processor 701, the memory 702, the input device 703 and the display device 704 may be connected via a bus or other means, and the figure takes the connection via a bus as an example.

[0117] The memory 702 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, Figures 1 to 5 The processor 701 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 702, that is, realizing a note generation method based on an intelligent learning terminal in the above embodiment.

[0118] The memory 702 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 702 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 702 may optionally include a memory remotely arranged relative to the processor 701, 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.

[0119] The input device 703 can receive user clicks and generate signal inputs related to user settings and function controls of the review content generation method. The display device 704 can include display devices such as a display screen.

[0120] The one or more modules are stored in the memory 702, and when executed by the one or more processors 701, a note generation method based on an intelligent learning terminal in any of the above method embodiments is executed.

[0121] 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.

[0122] 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.

[0123] 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.

[0124] 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.

[0125] By applying the scheme of this embodiment, compared with the current existing technology, this scheme constructs a dependency graph by presetting the first knowledge point learning relationship, and constructs an answer count matrix and a dependency error matrix based on the knowledge point answer samples and the dependency graph to correct the errors existing in the dependency graph, thereby improving the accuracy of determining the association relationship between the first knowledge points; and then, according to the answer situation of the knowledge point answer samples, the weak knowledge point set corresponding to the knowledge point answer samples is determined, so as to match the weak knowledge point set with the corrected dependency graph, and use the preset learning materials to generate personalized learning notes corresponding to the knowledge point answer samples, thereby improving the flexibility and accuracy of learning note generation.

[0126] It should be noted that, in this article, relational terms such as "preceding" 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.

[0127] 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 note generation method based on an intelligent learning terminal, characterized in that: The method comprises: Based on the preset first knowledge point learning relationship, the attention network model is used to extract the associated features of the first knowledge point to construct a dependency graph of the first knowledge point, wherein the first knowledge point includes a preceding first knowledge point and a dependent first knowledge point; In response to a dependency graph update instruction, obtaining a knowledge point answer sample to determine an average dependency error of the first knowledge point in the dependency graph and an answer count matrix of the first knowledge point; Determine the dependency error matrix of the first knowledge point based on the average dependency error and the answer status of the knowledge point answer samples; Based on the answer count matrix and the dependency error matrix, determining the error of the preset first knowledge point learning relationship to update the dependency relationship graph; Based on a first knowledge point set corresponding to a single knowledge point answer sample, updating a preset mastering probability of the first knowledge point set to determine a weak knowledge point set corresponding to the knowledge point answer sample; Based on the set of weak knowledge points and the updated dependency graph, learning notes are generated using preset learning materials.

2. The method according to claim 1, characterized in that The method of extracting the associated features of the first knowledge point based on the preset first knowledge point learning relationship and using the attention network model to construct a dependency graph of the first knowledge point includes: Based on the preset first knowledge point learning relationship, extracting a correlation feature vector of the first knowledge point; Based on the associated feature vector, construct an initial relationship graph of the first knowledge point using a triple method; Vectorizing the initial relationship graph to obtain vectorized codes of first knowledge points corresponding to adjacent nodes; Based on the vectorized encoding, determining invisible features between the first knowledge points; Based on the invisible features, the initial relationship graph is updated to construct a dependency relationship graph.

3. The method according to claim 1, characterized in that The step of obtaining knowledge point answer samples to determine the average dependency error of the first knowledge point and the answer count matrix of the first knowledge point in the dependency graph includes: Based on the dependency graph, determine the first correct answer sample of the preceding first knowledge point, the first incorrect answer sample that depends on the first knowledge point, the second correct answer sample that depends on the first knowledge point, and the number of the preceding first knowledge point that depends on the first knowledge point in the knowledge point answer sample; Based on the first correct answer sample, the second correct answer sample and the first incorrect answer sample, determining abnormal samples in the knowledge point answer samples and the answer count matrix; The average dependency error is determined based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point, wherein the dependent knowledge point set is composed of the preceding first knowledge point and the dependent first knowledge point.

4. The method according to claim 3, characterized in that The determining, based on the first correct answer sample and the second correct answer sample, abnormal samples in the knowledge point answer sample and the answer count matrix comprises: Based on the first correct answer sample and the first incorrect answer sample, when it is determined that the answer to the preceding first knowledge point corresponding to the same sample source is incorrect and the answer to the dependent first knowledge point is correct, the first correct answer sample corresponding to the same sample source is determined as the abnormal sample; The answer count matrix is ​​determined based on the number of the first correct answer samples, the number of the second correct answer samples, and the number of the abnormal samples.

5. The method according to claim 3, characterized in that: The determining the average dependency error based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point comprises: Based on the dependent knowledge point set corresponding to the knowledge point answer sample, the second correct answer sample, the abnormal sample and the number of dependent first knowledge points of the preceding first knowledge point, the average dependency error is determined in combination with the following formula 1: Formula 1, Wherein, M represents the average dependency error, N(E) represents the number of dependent first knowledge points corresponding to the preceding first knowledge point, i represents the preceding first knowledge point, j represents the dependent first knowledge point, and E represents the dependent knowledge point set. represents the number of abnormal samples, Represents the number of the second correct answer samples.

6. The method according to claim 3, characterized in that: The step of determining the dependency error matrix of the first knowledge point based on the average dependency error and the answer status of the knowledge point answer samples includes: Based on the knowledge point answer samples, determine the number of the first correct answer samples, the number of the second correct answer samples, and the total number of the knowledge point answer samples; Based on the number of the first correct answer samples, the number of the second correct answer samples, the total number and the average dependency error, the dependency error matrix is ​​determined in combination with the following formula 2: Formula 2, Among them, the represents the dependency error matrix, the represents the number of the first correct answer samples, and n represents the total number.

7. The method according to claim 1, characterized in that The step of determining the error of the preset first knowledge point learning relationship based on the answer count matrix and the dependency error matrix to update the dependency graph includes: Based on the answer count matrix and the dependency error matrix, combined with the following formula 3, determining the dependency error of the dependent knowledge point set includes: Formula 3, Wherein, Diff represents the dependency error of the dependent knowledge point set, m represents the diagonal elements in the answer count matrix and the dependency error matrix, and represents the answer count matrix; When the dependency error is greater than a preset error threshold, determining that a first knowledge point included in the dependent knowledge point set has an error in the dependency relationship graph; Based on the first knowledge point included in the dependent knowledge point set, the dependency graph is updated using the attention network model.

8. The method according to claim 1, characterized in that: The updating of the preset mastering probability of the first knowledge point set based on the first knowledge point set corresponding to the single knowledge point answer sample to determine the weak knowledge point set corresponding to the knowledge point answer sample includes: Determining the probability of correct answers to the first knowledge point set based on the knowledge point answer samples; Based on the first knowledge point set corresponding to the single knowledge point answer sample and the correct answer probability, updating the preset mastery probability of the first knowledge point set to obtain a sample mastery probability; Based on the sample mastery probability and a preset knowledge point mastery threshold, a set of weak knowledge points of the knowledge point answer sample is determined.

9. The method according to claim 8, characterized in that The updating of the preset mastering probability of the first knowledge point set based on the first knowledge point set corresponding to the single knowledge point answer sample and the correct answer probability to obtain the sample mastering probability includes: Based on the correct answer probability, determining an update weight for the preset mastery probability; Determine an updated mastering probability based on the answering status of the knowledge point answering sample, the first knowledge point set corresponding to the single knowledge point answering sample, the preset mastering probability, and the updating weight; The updated mastering probability is normalized to obtain the sample mastering probability.

10. The method according to claim 8, characterized in that The determining of the weak knowledge point set of the knowledge point answer sample based on the sample mastery probability and the preset knowledge point mastery threshold comprises: Based on the sample mastery probability and the preset knowledge point weight, combined with the following formula 4, the comprehensive mastery probability of the first knowledge point in the knowledge point answer sample is determined: Formula 4, in, , represents the comprehensive mastery probability, represents the preset knowledge point weight, represents the first knowledge point, represents the first knowledge point set, represents the probability of mastering the sample; The comprehensive mastery probability is compared with the preset knowledge point mastery threshold to determine the weak knowledge point set.

11. The method according to claim 1, characterized in that: The generating of learning notes based on the weak knowledge point set and the updated dependency graph using preset learning materials includes: Matching the first knowledge point in the weak knowledge point set with the updated dependency graph to determine the knowledge points that the study notes need to include; Based on the knowledge points that the study notes need to contain, corresponding knowledge content is extracted from preset learning materials to generate the study notes.

Images