An Online Education Platform Data-Driven Teaching Content Recommendation Method and System

Abstract

The present invention relates to the field of intelligent recommendation technology, and particularly relates to a method and system for recommending teaching content driven by data on an online education platform. An online education platform data-driven teaching content recommendation system includes: a knowledge point mastery feature data construction module, a mastery degree analysis module, a gap knowledge point determination module, and an educational content recommendation module. The present invention determines the user's knowledge point mastery degree by analyzing the user's assessment data, and analyzes the educational content knowledge graph through a mastery degree analysis model, studies the dependency relationship between knowledge points, analyzes the deeper knowledge point mastery degree, and then obtains a more accurate judgment of the knowledge point mastery degree. Based on the deep mastery feature data of knowledge points, the gap knowledge points with low user knowledge point mastery degree are determined, and the learning path of educational content to be recommended is determined through the gap knowledge points, so as to realize the recommendation of educational content for users to check for deficiencies and make up for them.

Description

Technical Field

[0001] The present invention relates to the technical field of intelligent recommendation, and particularly relates to a method and system for recommending teaching content driven by data on an online education platform. Background Art

[0002] With the rapid development and popularization of online education platforms, learning resources have become increasingly rich, and the teaching content available to users has shown an explosive growth. However, the content recommendation mechanisms of existing education platforms mainly recommend based on curriculum integrity, popularity, user historical behavior, or simple knowledge point association relationships, lacking accurate identification and targeted analysis of learners' actual knowledge mastery status. Such a recommendation method is difficult to meet the personalized learning needs of learners, especially unable to effectively solve the "knowledge gap" problem in the learning process, resulting in low learning efficiency, poor learning experience, and even a series of problems such as a decline in learning motivation and an incomplete construction of the knowledge system. Summary of the Invention

[0003] The present invention determines the degree of knowledge point mastery of users by analyzing the assessment data of users, and analyzes the educational content knowledge graph through a mastery degree analysis model, studies the dependency relationships between knowledge points, analyzes the deeper degree of knowledge point mastery, and then obtains a more accurate judgment of the degree of knowledge point mastery. Based on the deep mastery feature data of knowledge points, the gap knowledge points with low user knowledge point mastery are determined, and the learning path of educational content to be recommended is determined through the gap knowledge points, enabling the recommendation of educational content for users to fill in the gaps.

[0004] The present invention provides a method for recommending teaching content driven by data on an online education platform, including:

[0005] Obtain the assessment data for the user, and construct knowledge point mastery feature data based on the assessment data of the user. The knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the assessment accuracy rate of the user under the corresponding knowledge point;

[0006] Send the knowledge point mastery feature data and the educational content knowledge graph into the mastery degree analysis model for processing, and output the deep mastery feature data of knowledge points;

[0007] Determine a set of gap knowledge points based on the deep mastery feature data of knowledge points and the educational content knowledge graph. The set of gap knowledge points includes several gap knowledge points;

[0008] Determine the learning path of educational content based on the set of gap knowledge points and the educational content knowledge graph. The learning path of educational content includes educational content arranged in the learning order, and the recommendation of educational content is realized through the learning path of educational content;

[0009] The mastery level analysis model includes a graph convolutional layer, a dependency strengthening layer, and an output layer. The graph convolutional layer is used to perform feature fusion on the knowledge point mastery feature data based on the educational content knowledge graph to construct the fused knowledge point mastery feature. The dependency strengthening layer is used to strengthen the fused knowledge point mastery feature based on the educational content knowledge graph to construct the strengthened knowledge point mastery feature. The output layer is used to perform a fully connected operation on the strengthened knowledge point mastery feature to obtain the deep knowledge point mastery feature data.

[0010] Preferably, the educational content knowledge graph is used to describe the dependency relationships between all knowledge points in the educational content and is constructed in the following manner:

[0011] Construct a number of groups of knowledge point entity - dependency relationship - knowledge point entity triples, and form the educational content knowledge graph with all the knowledge point entity - dependency relationship - knowledge point entity triples. The dependency relationships include a pre - dependency relationship, a correlation relationship, and an auxiliary enhancement relationship. The weight values corresponding to the pre - dependency relationship, the correlation relationship, and the auxiliary enhancement relationship are the pre - dependency relationship strength, the correlation strength, and the auxiliary enhancement degree, respectively.

[0012] Preferably, the knowledge point mastery feature data and the educational content knowledge graph are fed into the mastery level analysis model for processing to output the deep knowledge point mastery feature data, which specifically includes the following steps:

[0013] Perform feature fusion on the knowledge point mastery feature data based on the educational content knowledge graph through the graph convolutional layer to construct the fused knowledge point mastery feature, which specifically includes the following content: Obtain the corresponding dependency relationship adjacency matrix based on the educational content knowledge graph. The size of the dependency relationship adjacency matrix is N×N, where N is the total number of knowledge point entities. The data stored in the i - th row and j - th column of the dependency relationship adjacency matrix is the dependency relationship vector between the i - th knowledge point entity and the j - th knowledge point entity, and satisfies i, j = 1, 2, 3, …, N. The dependency relationship vector includes the pre - dependency relationship strength, the correlation strength, and the auxiliary enhancement degree between the i - th knowledge point entity and the j - th knowledge point entity. Perform graph convolution operations through the following formula: H(t + 1)=σ(H(t)AW(t)), where H(t) is the fused feature map output in the t - th iteration, A is the normalized dependency relationship adjacency matrix, W(t) is the graph convolution weight matrix corresponding to the t - th iteration, and σ(·) is the sigmoid function; until the number of iterations reaches the iteration upper limit E, complete the feature fusion, and record the fused feature map output in the last iteration as the fused knowledge point mastery feature;

[0014] Feature enhancement of the mastery features of integrated knowledge points is performed based on the educational content knowledge graph through a dependency relationship enhancement layer to construct enhanced mastery features of knowledge points, which specifically includes the following: constructing a corresponding knowledge point feature value vector V and a knowledge point feature key vector K based on the mastery features of integrated knowledge points, constructing a corresponding knowledge point feature query vector Q based on the dependency relationship adjacency matrix, and performing a self-attention mechanism operation through the following formula: G = softmax(QK T / D 0.5 )V, where G is the enhanced mastery feature of the knowledge point, T is the matrix transpose operation, and D is the dimension size of the knowledge point feature key vector K to achieve feature enhancement;

[0015] Perform a fully connected operation on the enhanced mastery features of the knowledge points to obtain the deep mastery feature data of the knowledge points.

[0016] Preferably, a set of missing knowledge points is determined based on the deep mastery feature data of the knowledge points and the educational content knowledge graph, which specifically includes the following steps:

[0017] Traverse the knowledge points in the deep mastery feature data of the knowledge points, and perform the following operations on the selected knowledge points: determine whether the corresponding deep mastery degree value of the knowledge point is lower than the first mastery threshold. If the corresponding deep mastery degree value of the knowledge point is lower than the first mastery threshold, record the selected knowledge point as a missing knowledge point. If the corresponding deep mastery degree value of the knowledge point is not lower than the first mastery threshold, do nothing; until all the knowledge points in the deep mastery feature data of the knowledge points are traversed, output all the missing knowledge points;

[0018] Split the pre - dependency education content knowledge directed graph and the auxiliary enhancement education content knowledge directed graph that only have pre - dependency relationships and auxiliary enhancement relationships from the education content knowledge graph. Traverse all gap knowledge points and perform the following operations for each gap knowledge point: In the pre - dependency education content knowledge directed graph, traverse against the pre - dependency relationship based on the gap knowledge point, record the knowledge point entities, and obtain the pre - dependency path. In the auxiliary enhancement education content knowledge directed graph, traverse against the auxiliary enhancement relationship based on the gap knowledge point, record the knowledge point entities, and obtain the auxiliary enhancement path; until all gap knowledge points have been traversed, output all pre - dependency paths and auxiliary enhancement paths. For all pre - dependency paths, form the first candidate knowledge point set by all the knowledge point entities that overlap in all pre - dependency paths. Traverse all the knowledge point entities in the first candidate knowledge point set, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as gap knowledge points, where the second mastery threshold is higher than the first mastery threshold. For all auxiliary enhancement paths, form the second candidate knowledge point set by all the knowledge point entities that overlap in all auxiliary enhancement paths. Traverse all the knowledge point entities in the second candidate knowledge point set, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as gap knowledge points;

[0019] Form a gap knowledge point set by all the gap knowledge points.

[0020] Preferably, determine the education content learning path based on the gap knowledge point set and the education content knowledge graph, which specifically includes the following steps: Map all the gap knowledge points in the gap knowledge point set to the education content knowledge graph, split out the education content learning path that retains the pre - dependency relationship and the auxiliary enhancement relationship, and associate each knowledge point entity in the education content learning path with the corresponding education content.

[0021] Preferably, train the mastery level analysis model, which specifically includes the following steps:

[0022] Obtain a number of mastery level analysis training samples. The mastery level analysis training samples include knowledge point mastery feature data and the education content knowledge graph. Form a mastery level analysis training set by all the mastery level analysis training samples, and perform unsupervised training on the mastery level analysis model through the mastery level analysis training set. The training objective is that for all the mastery level analysis training samples of the same user at the same time, the knowledge point deep mastery feature data output by the mastery level analysis model is consistent.

[0023] The present invention also provides an online education platform data - driven teaching content recommendation system, including:

[0024] The knowledge point mastery feature data construction module is used to obtain the assessment data for the user, construct the knowledge point mastery feature data based on the user's assessment data, and the knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the assessment accuracy rate of the user under the corresponding knowledge point;

[0025] The mastery degree analysis module is used to process the knowledge point mastery feature data and the educational content knowledge graph in the mastery degree analysis model, and output the deep mastery feature data of the knowledge points;

[0026] The gap knowledge point determination module is used to determine the set of gap knowledge points based on the deep mastery feature data of the knowledge points and the educational content knowledge graph, and the set of gap knowledge points includes several gap knowledge points;

[0027] The educational content recommendation module is used to determine the educational content learning path based on the set of gap knowledge points and the educational content knowledge graph. The educational content learning path includes the educational content arranged in the learning order, and realizes the recommendation of the educational content through the educational content learning path.

[0028] The present invention has the following advantages:

[0029] The present invention determines the mastery degree of the user's knowledge points by analyzing the user's assessment data, and analyzes the educational content knowledge graph through the mastery degree analysis model, studies the dependency relationship between the knowledge points, analyzes the deeper mastery degree of the knowledge points, and then obtains a more accurate judgment of the mastery degree of the knowledge points. Then, based on the deep mastery feature data of the knowledge points, the gap knowledge points with low mastery degree of the user's knowledge points are determined, and the educational content learning path to be recommended is determined through the gap knowledge points, which can realize the recommendation of educational content for the user to fill in the gaps. Brief Description of the Drawings

[0030] Figure 1 It is a schematic structural diagram of an online education platform data-driven teaching content recommendation system adopted in an embodiment of the present invention. Detailed Embodiments

[0031] In order to enable those skilled in the art of the present technology to better understand the technical solutions in the present invention, the following will clearly and completely describe the technical solutions in the embodiments of the present invention with reference to the accompanying drawings in the embodiments of the present invention.

[0032] Embodiment 1, an online education platform data-driven teaching content recommendation method, includes:

[0033] Obtain the assessment data for users. During the learning process on the online education platform, there will be assessments in the forms of after-class exercises and comprehensive test papers to reflect the users' mastery of the learned content. Here, the assessment data refers to the assessment accuracy rates corresponding to each knowledge point under various historical assessment methods. It should be noted that each exercise in the assessment corresponds to a knowledge point, and a one-to-one mapping between the exercises and the knowledge points is established. Here, the knowledge points are obtained from the educational content knowledge graph constructed based on the corresponding educational content. For example, the knowledge points corresponding to "High School Mathematics: Functions and Derivatives" include "Function Monotonicity", "Function Value Range", and "Geometric Meaning of Derivatives", etc.; construct the knowledge point mastery characteristic data based on the users' assessment data. Here, the knowledge point mastery characteristic data includes the characteristic vectors corresponding to each knowledge point and the assessment accuracy rates of the users under the corresponding knowledge points. Specifically, during the historical assessment process executed by the users, there are several questions corresponding to each knowledge point. The accuracy rate of all questions under each knowledge point is statistically calculated, which is the assessment accuracy rate corresponding to the knowledge point. The assessment accuracy rate can reflect the users' mastery of the knowledge point. The characteristic vector corresponding to the knowledge point is specifically the data after the word embedding operation;

[0034] The educational content knowledge graph is used to describe the dependency relationships between all knowledge points in the educational content and is constructed in the following way: Obtain the textbook content and video lecture materials corresponding to the educational content, and perform named entity recognition by combining models such as TF-IDF, TextRank, and BERT to obtain the corresponding knowledge point entities. Here, each knowledge point entity corresponds to a knowledge point. The experts annotate the dependency relationships between the knowledge points to construct several groups of knowledge point entity - dependency relationship - knowledge point entity triples. And it should be noted that the educational content knowledge graph here corresponds to a directed graph. Combine all the knowledge point entity - dependency relationship - knowledge point entity triples to form the educational content knowledge graph;

[0035] The dependencies here include pre - dependency relationships, correlation relationships, and auxiliary enhancement relationships. The weight values corresponding to the pre - dependency relationship, correlation relationship, and auxiliary enhancement relationship are the pre - dependency strength, correlation strength, and auxiliary enhancement degree respectively. The pre - dependency strength is the necessity strength of knowledge point A as a pre - condition for knowledge point B calculated through a conditional probability model. The correlation strength is the similarity degree between knowledge point A and knowledge point B calculated through the cosine similarity algorithm. The auxiliary enhancement degree is used to describe the degree of promotion of mastering knowledge point A for learning knowledge point B, which can be marked through expert experience or obtained through A / B test experiments. The specific calculation method of the auxiliary enhancement degree is as follows: Divide the experimental personnel into an experimental group and a control group. The experimental group first learns knowledge point A and then knowledge point B, and the control group learns knowledge point B without learning knowledge point A. Calculate the corresponding learning efficiencies Q1 and Q2 of the experimental group and the control group respectively. The auxiliary enhancement degree is 1 - (Q2 / Q1). However, the latter A / B test experiment requires a large amount of manpower and material resources and is relatively complicated. We can first use a small number of experimental samples as labeled data, and then train a model through semi - supervised methods to replace the experiment;

[0036] Send the knowledge point mastery feature data and the educational content knowledge graph into the mastery degree analysis model for processing, and output the deep - level knowledge point mastery feature data. The deep - level knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the deep - level mastery degree value under the corresponding knowledge point. It should be noted that during the user's assessment process, there may be errors in the test questions caused by the user's own carelessness and other reasons, which affect the judgment of the knowledge point mastery degree. On the other hand, an important aspect of the knowledge point mastery degree is its application in the comprehensive aspect. For example, if knowledge point A is a pre - condition for knowledge point B, the test questions corresponding to knowledge point A may have a high assessment accuracy rate, but the assessment accuracy rate corresponding to knowledge point B is low, which indicates that the comprehensive application mastery degree of knowledge point A may be low, and it will affect the judgment of the knowledge point mastery degree of knowledge point A. Therefore, by analyzing the educational content knowledge graph in the mastery degree analysis model, studying the dependencies between knowledge points, and then adjusting the judgment of the mastery degree of different knowledge points;

[0037] Determine the gap knowledge point set based on the deep - level knowledge point mastery feature data and the educational content knowledge graph. The gap knowledge point set includes several gap knowledge points. Here, the gap knowledge points refer to the knowledge points with low user mastery degree, that is, the educational content that the user needs to supplement;

[0038] Determine the educational content learning path based on the gap knowledge point set and the educational content knowledge graph. The educational content learning path includes educational content arranged in the learning order. Here, the educational content includes textbooks, explanatory videos, etc. The recommendation of educational content is realized through the educational content learning path;

[0039] This application determines the user's knowledge point mastery level by analyzing the user's assessment data, and analyzes the educational content knowledge graph through a mastery level analysis model to study the dependency relationships between knowledge points, analyze the deeper-level knowledge point mastery level, and then obtain a more accurate judgment of the knowledge point mastery level. Based on the deep mastery feature data of knowledge points, the missing knowledge points with low user knowledge point mastery level are determined, and the learning path of educational content to be recommended is determined through the missing knowledge points, which can realize the recommendation of educational content for users to fill in the gaps.

[0040] The knowledge point mastery feature data and the educational content knowledge graph are sent into the mastery level analysis model for processing, and the deep mastery feature data of knowledge points are output. The specific steps are as follows:

[0041] The mastery level analysis model includes a graph convolutional layer, a dependency relationship strengthening layer, and an output layer. The graph convolutional layer is used to perform feature fusion on the knowledge point mastery feature data based on the educational content knowledge graph to construct fused knowledge point mastery features. Here, the feature fusion adjusts the mastery level corresponding to each knowledge point according to the dependency relationship between knowledge points, weakening the test questions errors caused by the user's own carelessness, etc. For example, the mastery levels corresponding to two knowledge points with a relatively high correlation strength should be similar; the dependency relationship strengthening layer is used to perform feature strengthening on the fused knowledge point mastery features based on the educational content knowledge graph to construct strengthened knowledge point mastery features. Here, the strengthened knowledge point mastery features strengthen the mastery level corresponding to each knowledge point according to the dependency relationship between knowledge points. If knowledge point A is a prerequisite for knowledge point B, the test questions corresponding to knowledge point A may have a relatively high assessment accuracy rate, but the assessment accuracy rate corresponding to knowledge point B is relatively low, then the mastery level corresponding to knowledge point A should be reduced; the output layer is used to perform a fully connected operation on the strengthened knowledge point mastery features to obtain the deep mastery feature data of knowledge points;

[0042] Feature fusion is performed on the feature data of knowledge point mastery based on the educational content knowledge graph through a graph convolutional layer to construct the fused knowledge point mastery features, which specifically includes the following: Obtain the corresponding dependency adjacency matrix based on the educational content knowledge graph. The size of the dependency adjacency matrix is N×N, where N is the total number of knowledge point entities. The data stored in the i-th row and j-th column of the dependency adjacency matrix is the dependency relationship vector between the i-th knowledge point entity and the j-th knowledge point entity, and it satisfies i, j = 1, 2, 3, …, N. The dependency relationship vector includes the forward dependency intensity, correlation intensity, and auxiliary enhancement intensity between the i-th knowledge point entity and the j-th knowledge point entity. It should be noted that the educational content knowledge graph is a directed graph, and the forward dependency intensity and auxiliary enhancement intensity will only store the corresponding values when there is a directed connection. In the case of no directed connection, the values of the corresponding items of the forward dependency intensity and auxiliary enhancement intensity are zero. Perform graph convolution operations through the following formula: H(t + 1) = σ(H(t)AW(t)), where H(t) is the fused feature map output in the t-th iteration, A is the normalized dependency adjacency matrix, W(t) is the graph convolution weight matrix corresponding to the t-th iteration, and σ(·) is the sigmoid function; until the number of iterations reaches the iteration upper limit E, feature fusion is completed, and the fused feature map output in the last iteration is recorded as the fused knowledge point mastery feature, and E is generally 3;

[0043] Feature enhancement is performed on the fused knowledge point mastery features based on the educational content knowledge graph through a dependency relationship enhancement layer to construct the enhanced knowledge point mastery features, which specifically includes the following: Construct the corresponding knowledge point feature value vector V and knowledge point feature key vector K based on the fused knowledge point mastery features, construct the corresponding knowledge point feature query vector Q based on the dependency adjacency matrix, and perform self-attention mechanism operations through the following formula: G = softmax(QK T / D 0.5 )V, where G is the enhanced knowledge point mastery feature, T is the matrix transpose operation, and D is the dimension size of the knowledge point feature key vector K to achieve feature enhancement;

[0044] It should be noted that the self-attention mechanism operation refers to the Transformer model. In the self-attention mechanism operation of the Transformer model, the input features will be multiplied by the corresponding value weight matrix, key weight matrix, and query weight matrix respectively to construct the corresponding value vector, key vector, and query vector, and then through the formula G = softmax(QK T / D 0.5)V implements the self-attention mechanism operation. In this application, the basis of the query vector is no longer the input features (the features of mastering the integrated knowledge points) themselves, but the dependency adjacency matrix derived from the educational content knowledge graph, which can strengthen the mastery level corresponding to each knowledge point based on the dependency relationship between knowledge points.

[0045] Determine the set of knowledge points with gaps based on the deep mastery feature data of knowledge points and the educational content knowledge graph, which specifically includes the following steps:

[0046] Traverse the knowledge points in the deep mastery feature data of knowledge points, and perform the following operations for the selected knowledge points: Determine whether the deep mastery level value corresponding to the knowledge point is lower than the first mastery threshold. The first mastery threshold is set manually, generally 0.6. If the deep mastery level value corresponding to the knowledge point is lower than the first mastery threshold, mark the selected knowledge point as a knowledge point with a gap. If the deep mastery level value corresponding to the knowledge point is not lower than the first mastery threshold, it means that the user's mastery level of this knowledge point meets the expectation, and no operation is performed; until all knowledge points in the deep mastery feature data of knowledge points are traversed, output all knowledge points with gaps.

[0047] Split the pre-dependency educational content knowledge directed graph and the auxiliary enhancement educational content knowledge directed graph that only have pre-dependency relationships and auxiliary enhancement relationships from the educational content knowledge graph. Traverse all knowledge points with gaps, and perform the following operations for each knowledge point with a gap: In the pre-dependency educational content knowledge directed graph, traverse based on the knowledge point with a gap against the pre-dependency relationship, record the knowledge point entities, and obtain the pre-dependency path. In the auxiliary enhancement educational content knowledge directed graph, traverse based on the knowledge point with a gap against the auxiliary enhancement relationship, record the knowledge point entities, and obtain the auxiliary enhancement path. Both the pre-dependency path and the auxiliary enhancement path represent the influence of different knowledge points on the knowledge point with a gap; until all knowledge points with gaps are traversed, output all pre-dependency paths and auxiliary enhancement paths. For all pre-dependency paths, form the first set of candidate knowledge points by combining all the overlapping knowledge point entities of all pre-dependency paths. Traverse all the knowledge point entities in the first set of candidate knowledge points, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as knowledge points with gaps. Here, the second mastery threshold is also set manually, and the second mastery threshold is higher than the first mastery threshold. When supplementing the knowledge points with a lower mastery level, since knowledge points are interdependent, it is necessary to judge the mastery level of the previously learned knowledge points again and relax the judgment requirements. For all auxiliary enhancement paths, form the second set of candidate knowledge points by combining all the overlapping knowledge point entities of all auxiliary enhancement paths. Traverse all the knowledge point entities in the second set of candidate knowledge points, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as knowledge points with gaps.

[0048] Combine all the missing knowledge points to form a set of missing knowledge points.

[0049] Determine the learning path of educational content based on the set of missing knowledge points and the educational content knowledge graph, which specifically includes the following steps:

[0050] Map all the missing knowledge points in the set of missing knowledge points to the educational content knowledge graph, segment the learning path of educational content that retains the prerequisite dependency relationship and the auxiliary enhancement relationship, and associate each knowledge point entity in the learning path of educational content with the corresponding educational content.

[0051] Train the mastery analysis model, which specifically includes the following steps:

[0052] Obtain several mastery analysis training samples. The mastery analysis training samples include knowledge point mastery feature data and the educational content knowledge graph. Here, the knowledge point mastery feature data is obtained manually based on the evaluation data collected from the actual online education platform. Combine all the mastery analysis training samples to form a mastery analysis training set, and perform unsupervised training on the mastery analysis model through the mastery analysis training set. The training objective is that for all the mastery analysis training samples of the same user at the same time, the deep knowledge point mastery feature data output by the mastery analysis model is consistent. The consistency can be calculated in the following way: Perform clustering analysis on all the deep knowledge point mastery feature data output by the mastery analysis model, use the cluster center as the average value, and use the calculated mean square deviation value as the consistency.

[0053] Example 2, An online education platform data-driven teaching content recommendation system, see Figure 1 , including:

[0054] Knowledge point mastery feature data construction module, which is used to obtain the evaluation data for users. During the learning process of users on the online education platform, there will be evaluations in the form of after-class exercises and comprehensive test papers, etc., to reflect the degree of mastery of the content learned by users. Here, the evaluation data refers to the evaluation accuracy rate corresponding to each knowledge point under various historical evaluation methods. It should be noted that each exercise in the evaluation corresponds to a knowledge point, and a one-to-one mapping between the exercise and the knowledge point is established. Here, the knowledge points are obtained from the educational content knowledge graph constructed based on the corresponding educational content. For example, the knowledge points corresponding to "High school mathematics functions and derivatives" include "Function monotonicity", "Function value range", and "Geometric meaning of derivatives", etc.; based on the evaluation data of users, knowledge point mastery feature data is constructed. Here, the knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the evaluation accuracy rate of the user under the corresponding knowledge point. Specifically, during the evaluation process executed by the user in history, there are several questions corresponding to each knowledge point. The accuracy rate of all questions under each knowledge point is statistically calculated, which is the evaluation accuracy rate corresponding to the knowledge point. Through the evaluation accuracy rate, the mastery situation of the user for the knowledge point can be reflected. The feature vector corresponding to the knowledge point is specifically the data after word embedding operation;

[0055] Mastery degree analysis module, which is used to send the knowledge point mastery feature data and the educational content knowledge graph into the mastery degree analysis model for processing, and output the in-depth knowledge point mastery feature data. The in-depth knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the in-depth mastery degree value under the corresponding knowledge point. It should be noted that during the evaluation process of users, there may be errors in questions caused by reasons such as the user's carelessness, which affect the judgment of the mastery degree of knowledge points. On the other hand, an important aspect of the mastery degree of knowledge points is the application in the comprehensive aspect. For example, knowledge point A is a prerequisite for knowledge point B. The questions corresponding to knowledge point A may have a high evaluation accuracy rate, but the evaluation accuracy rate corresponding to knowledge point B is low. That indicates that the comprehensive application mastery degree of knowledge point A may be low, which will affect the judgment of the mastery degree of knowledge point A. Therefore, by analyzing the educational content knowledge graph in the mastery degree analysis model, the dependency relationship between knowledge points is studied, and then the judgment of the mastery degree of different knowledge points is adjusted;

[0056] Gap knowledge point determination module, which is used to determine the set of gap knowledge points based on the in-depth knowledge point mastery feature data and the educational content knowledge graph. The set of gap knowledge points includes several gap knowledge points. Here, the gap knowledge points refer to the knowledge points with low mastery degree of users, that is, the educational content that users need to supplement;

[0057] An educational content recommendation module is used to determine an educational content learning path based on a set of knowledge gaps and an educational content knowledge graph. The educational content learning path includes educational content arranged in a learning order. Here, the educational content includes teaching materials, explanatory videos, etc. The recommendation of educational content is realized through the educational content learning path.

[0058] It should be understood that those of ordinary skill in the art can make improvements or transformations according to the above description, and all such improvements and transformations should fall within the protection scope of the appended claims of the present invention. The parts not described in detail in this specification belong to the prior art well known to those skilled in the art.

Claims

1. A method for recommending teaching content driven by data on an online education platform, characterized in that, Including: Obtain the assessment data for the user, and construct the knowledge point mastery feature data based on the user's assessment data. The knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the assessment accuracy of the user under the corresponding knowledge point; Send the knowledge point mastery feature data and the educational content knowledge graph into the mastery degree analysis model for processing, and output the deep knowledge point mastery feature data; Determine the set of knowledge points with gaps based on the deep knowledge point mastery feature data and the educational content knowledge graph. The set of knowledge points with gaps includes several knowledge points with gaps; Determine the educational content learning path based on the set of knowledge points with gaps and the educational content knowledge graph. The educational content learning path includes educational content arranged in the learning order, and the recommendation of educational content is realized through the educational content learning path; The mastery degree analysis model includes a graph convolutional layer, a dependency reinforcement layer, and an output layer. Among them, the graph convolutional layer is used to perform feature fusion on the knowledge point mastery feature data based on the educational content knowledge graph to construct the fused knowledge point mastery feature; The dependency reinforcement layer is used to perform feature reinforcement on the fused knowledge point mastery feature based on the educational content knowledge graph to construct the reinforced knowledge point mastery feature; the output layer is used to perform a fully connected operation on the reinforced knowledge point mastery feature to obtain the deep knowledge point mastery feature data; The educational content knowledge graph is used to describe the dependency relationship between all knowledge points in the educational content, and is constructed in the following way: Construct several groups of knowledge point entity - dependency relationship - knowledge point entity triples, and form the educational content knowledge graph with all the knowledge point entity - dependency relationship - knowledge point entity triples. The dependency relationships include the prerequisite dependency relationship, the correlation relationship, and the auxiliary enhancement relationship. The weight values corresponding to the prerequisite dependency relationship, the correlation relationship, and the auxiliary enhancement relationship are the prerequisite dependency strength, the correlation strength, and the auxiliary enhancement degree respectively; The prerequisite dependency strength is the necessity strength of knowledge point A as a prerequisite for knowledge point B calculated by the conditional probability model. The correlation strength is the similarity degree between knowledge point A and knowledge point B calculated by the cosine similarity algorithm. The auxiliary enhancement degree is used to describe the degree of promotion of mastering knowledge point A to learning knowledge point B, and is marked through expert experience or obtained through an A / B test experiment; Determine the set of knowledge points with gaps based on the deep knowledge point mastery feature data and the educational content knowledge graph, specifically including the following steps: Traverse the knowledge points in the deep knowledge point mastery feature data, and perform the following operations on the selected knowledge points: judge whether the deep mastery degree value corresponding to the knowledge point is lower than the first mastery threshold. If the deep mastery degree value corresponding to the knowledge point is lower than the first mastery threshold, mark the selected knowledge point as a knowledge point with a gap. If the deep mastery degree value corresponding to the knowledge point is not lower than the first mastery threshold, no operation is performed; Until all the knowledge points in the deep knowledge point mastery feature data are traversed, output all the knowledge points with gaps; Split the pre - dependency education content knowledge directed graph and the auxiliary enhancement education content knowledge directed graph with only pre - dependency relationships and auxiliary enhancement relationships from the education content knowledge graph. Traverse all gap knowledge points and perform the following operations for each gap knowledge point: In the pre - dependency education content knowledge directed graph, traverse backward along the pre - dependency relationship based on the gap knowledge point, record the knowledge point entities, and obtain the pre - dependency path. In the auxiliary enhancement education content knowledge directed graph, traverse backward along the auxiliary enhancement relationship based on the gap knowledge point, record the knowledge point entities, and obtain the auxiliary enhancement path; until all gap knowledge points have been traversed, output all pre - dependency paths and auxiliary enhancement paths. For all pre - dependency paths, form the first candidate knowledge point set by all knowledge point entities that overlap in all pre - dependency paths. Traverse all knowledge point entities in the first candidate knowledge point set, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as gap knowledge points, where the second mastery threshold is higher than the first mastery threshold. For all auxiliary enhancement paths, form the second candidate knowledge point set by all knowledge point entities that overlap in all auxiliary enhancement paths. Traverse all knowledge point entities in the second candidate knowledge point set, and mark the knowledge points corresponding to the knowledge point entities with a deep mastery level value lower than the second mastery threshold as gap knowledge points; Form a gap knowledge point set from all gap knowledge points.

2. An online education platform data-driven teaching content recommendation method according to claim 1, characterized in that, Send the knowledge point mastery feature data and the education content knowledge graph into the mastery level analysis model for processing, and output the deep mastery feature data of knowledge points, which specifically includes the following steps: Perform feature fusion on the knowledge point mastery feature data based on the education content knowledge graph through a graph convolutional layer to construct the fused knowledge point mastery feature, which specifically includes the following content: Obtain the corresponding dependency relationship adjacency matrix based on the education content knowledge graph. The size of the dependency relationship adjacency matrix is N×N, where N is the total number of knowledge point entities. The data stored in the i - th row and j - th column of the dependency relationship adjacency matrix is the dependency relationship vector between the i - th knowledge point entity and the j - th knowledge point entity, and satisfies i, j = 1, 2, 3, …, N. The dependency relationship vector includes the pre - dependency relationship strength, correlation strength, and auxiliary enhancement degree between the i - th knowledge point entity and the j - th knowledge point entity. Perform graph convolutional operations through the following formula: H(t + 1)=σ(H(t)AW(t)), where H(t) is the fused feature map output in the t - th iteration, A is the normalized dependency relationship adjacency matrix, W(t) is the graph convolutional weight matrix corresponding to the t - th iteration, and σ(·) is the sigmoid function; until the number of iterations reaches the iteration upper limit E, complete the feature fusion, and mark the fused feature map output in the last iteration as the fused knowledge point mastery feature; Based on the educational content knowledge graph, the feature strengthening layer based on the dependency relationship strengthens the mastery feature of the integrated knowledge points to construct the strengthened mastery feature of the knowledge points, which specifically includes the following: constructing the corresponding knowledge point feature value vector V and knowledge point feature key vector K based on the mastery feature of the integrated knowledge points, constructing the corresponding knowledge point feature query vector Q based on the dependency relationship adjacency matrix, and performing the self-attention mechanism operation through the following formula: G = softmax(QK T / D 0.5 )V, where G is the strengthened mastery feature of the knowledge points, T is the matrix transpose operation, and D is the dimension size of the knowledge point feature key vector K to achieve feature strengthening; Perform a fully - connected operation on the enhanced knowledge point mastery feature to obtain the deep mastery feature data of knowledge points.

3. An online education platform data-driven teaching content recommendation method according to claim 2, wherein, Determine the learning path of educational content based on the set of missing knowledge points and the educational content knowledge graph, which specifically includes the following steps: Map all the missing knowledge points in the set of missing knowledge points to the educational content knowledge graph, segment the learning path of educational content that retains the prerequisite dependency relationship and the auxiliary enhancement relationship, and associate each knowledge point entity in the learning path of educational content with the corresponding educational content.

4. An online education platform data-driven teaching content recommendation method according to claim 3, characterized in that Train the mastery analysis model, which specifically includes the following steps: Obtain several mastery analysis training samples. The mastery analysis training samples include knowledge point mastery feature data and the educational content knowledge graph. Combine all the mastery analysis training samples into a mastery analysis training set, and perform unsupervised training on the mastery analysis model through the mastery analysis training set. The training objective is that for all the mastery analysis training samples of the same user at the same time period, the knowledge point deep mastery feature data output by the mastery analysis model is consistent.

5. An online education platform data-driven teaching content recommendation system, characterized in that, The system applies the method for recommending teaching content driven by data of an online education platform according to any one of claims 1-4 above, including: A knowledge point mastery feature data construction module, which is used to obtain the evaluation data of the user, and construct the knowledge point mastery feature data based on the evaluation data of the user. The knowledge point mastery feature data includes the feature vector corresponding to each knowledge point and the evaluation accuracy rate of the user under the corresponding knowledge point; A mastery analysis module, which is used to send the knowledge point mastery feature data and the educational content knowledge graph into the mastery analysis model for processing, and output the knowledge point deep mastery feature data; A missing knowledge point determination module, which is used to determine the set of missing knowledge points based on the knowledge point deep mastery feature data and the educational content knowledge graph. The set of missing knowledge points includes several missing knowledge points; An educational content recommendation module, which is used to determine the learning path of educational content based on the set of missing knowledge points and the educational content knowledge graph. The learning path of educational content includes educational content arranged in the learning order, and realizes the recommendation of educational content through the learning path of educational content.

Images