Intelligent generation system of digital teaching materials based on digital education

Abstract

The present invention relates to the field of digital education technology, and specifically to an intelligent digital teaching material generation system based on digital education, comprising an educational resource acquisition module, a knowledge graph construction module, a teaching material content generation module, a knowledge tracking module, and a teaching material presentation module. The present invention introduces a graph embedding method based on a hyperbolic space graph convolutional network and a robustness-improved hierarchical clustering algorithm to perform low-dimensional embedding and multi-layer structure optimization on the initial knowledge graph to construct an educational knowledge graph with a semantic hierarchy. The present invention also introduces a graph-structured learning behavior modeling method to construct a student-knowledge point heterogeneous graph structure, and uses a heterogeneous graph convolutional network to model the interactive behavior between students and knowledge points, thereby obtaining a knowledge state graph for each student and improving the accuracy of individual knowledge mastery modeling.

Description

Technical Field

[0001] The present invention relates to the field of digital education technology, and in particular to a digital teaching material intelligent generation system based on digital education. Background Art

[0002] With the rapid development of information technology, digital education has gradually become an important development direction of the education industry. The static content and fixed structure of traditional textbooks can no longer meet the needs of personalized teaching and smart education. However, the existing digital textbook generation process still has problems such as limited educational resource processing capabilities, a single knowledge graph structure, weak semantic hierarchy, and inaccurate tracking of students' knowledge status. Most existing systems rely on manual extraction and structural templates, and are unable to efficiently integrate multi-source heterogeneous teaching resources. They lack deep semantic understanding and structured organization capabilities of resource content. In addition, current knowledge graphs are mostly constructed in a shallow point-to-point association manner, failing to construct a multi-layer knowledge graph that reflects the semantic hierarchy and abstract structure of educational content, limiting the systematic organization and reasoning application of knowledge. Current learning tracking methods are mostly based on answer data statistics, lacking in-depth analysis based on graph structure behavior modeling, making it difficult to fully and accurately portray students' mastery of each knowledge point, resulting in inaccurate textbook recommendations and personalized presentation. Summary of the Invention

[0003] In response to the above situation, in order to overcome the defects of the existing technology, the present invention provides an intelligent generation system of digital teaching materials based on digital education. To address the problem of limited educational resource processing capabilities, the present invention uses natural language processing (NLP) and image recognition technology through an educational resource acquisition module to perform semantic analysis and entity extraction on teaching content data, construct a semantic metadata set, and achieve efficient integration and semantic unit representation of multi-source educational resources; to address the problems of a single knowledge graph structure and weak semantic hierarchy, the present invention introduces a graph embedding method based on a hyperbolic space graph convolutional network and a hierarchical clustering algorithm with improved robustness, performs low-dimensional embedding and multi-layer structure optimization on the initial knowledge graph, constructs an educational knowledge graph with a semantic hierarchy, and enhances the systematic expression and hierarchical understanding capabilities between knowledge; to address the problem of inaccurate student knowledge status tracking, the present invention introduces a graph-structured learning behavior modeling method, constructs a student-knowledge point heterogeneous graph structure, and uses a heterogeneous graph convolutional network to model the interactive behavior between students and knowledge points, obtains the knowledge status graph of each student, and improves the accuracy of individual knowledge mastery modeling.

[0004] The technical solution adopted by the present invention is as follows: The digital teaching material intelligent generation system based on digital education provided by the present invention includes an educational resource acquisition module, a knowledge graph construction module, a teaching material content generation module, a knowledge tracking module and a teaching material presentation module, specifically including the following contents:

[0005] The educational resource acquisition module collects teaching content data, uses NLP and image recognition technology to perform semantic analysis and entity extraction on the teaching content data, obtains educational semantic units and constructs a semantic metadata set;

[0006] The knowledge graph construction module performs structured processing on the semantic metadata set to construct an initial knowledge graph, including nodes and edges, and introduces an embedding method based on a hyperbolic space graph convolutional network to perform low-dimensional representation learning on the initial knowledge graph to obtain an educational knowledge graph with a semantic hierarchical structure;

[0007] The teaching material content generation module is based on an educational knowledge graph with a semantic hierarchy, and uses graph structure expansion and semantic reasoning methods to cluster relevant knowledge points and expand paths for the target teaching topic to generate corresponding teaching material content units;

[0008] The knowledge tracking module introduces a graph-structured learning behavior modeling method to obtain the knowledge state map of each student by constructing a student-knowledge point heterogeneous graph structure;

[0009] The teaching material presentation module provides a visual teaching material content presentation method based on the teaching material content units and the educational knowledge graph with a semantic hierarchy, combined with the knowledge status graph of each student.

[0010] Furthermore, in the educational resource acquisition module, teaching content data includes textbook texts, teaching lesson plans, teacher explanations, question bank materials, online course content, and multimedia resources, and educational semantic units include concept entities, knowledge points, teaching objectives, and topic tags;

[0011] Furthermore, in the teaching material content generation module, the teaching material content units include concept explanations, example explanations, diagrams and exercises.

[0012] Furthermore, the knowledge graph construction module specifically includes the following steps:

[0013] Step S1: Structural processing: clarify and standardize the semantic metadata, map the educational semantic units into nodes, and establish edges based on the relationships between the educational semantic units. Each edge represents the semantic connection between different nodes.

[0014] Step S2: Construct an initial knowledge graph, and construct an initial knowledge graph of knowledge points, teaching objectives, and concept entities based on nodes and edges;

[0015] Step S3: Based on the embedding of the hyperbolic space graph convolutional network, a hyperbolic space graph convolutional network is introduced to perform low-dimensional representation learning on the initial knowledge graph, embed the nodes into the hyperbolic space, and obtain the embedded vector representation of each node;

[0016] Step S4: Calculate the structure, based on the embedding vector representation of each node, and use the hierarchical clustering algorithm based on robustness improvement to cluster the educational semantic units to form a multi-level semantic grouping structure;

[0017] Step S5: Structural optimization, jointly evaluate the similarity between nodes and the original connection relationship, and use the hierarchical adjustment algorithm to adjust the connection method of the edges to obtain an educational knowledge graph with a semantic hierarchical structure.

[0018] Furthermore, in step S4, a hierarchical clustering algorithm based on robustness improvement is used to cluster the educational semantic units, which specifically includes the following steps:

[0019] Step S41: Denoising: performing density analysis on the embedded vector representation of each educational information unit, using a density-based noise discrimination mechanism to identify and remove abnormal samples, and obtaining a denoised set of educational information units;

[0020] Step S42: Construct a k-nearest-neighbor directed graph based on the denoised set of education information units. Map each education information unit to a node in the graph, and determine its k nearest neighbor nodes based on the Euclidean distance between the embedding vectors. Connect them to form directed edges, and set the weights of the directed edges based on the relative distances between the nodes.

[0021] Step S43: Graph merging and clustering: a group of nodes with close embedding vector distances are grouped together to form a cluster. Multiple clusters are constructed to form a semantic hierarchy. In the k-nearest neighbor directed graph, the directed edges are iteratively traversed in the order of their weights. The graph merging operation is performed until all directed edges are traversed.

[0022] Step S44: Determine the number of clusters. During the graph merging process in step S43, record the change in the number of clusters after each graph merging operation, construct a mapping sequence between iteration rounds and cluster numbers, count the number of merging iterations corresponding to each cluster number, and select the cluster number corresponding to the maximum number of merging iterations as the final clustering result.

[0023] Step S45: Constructing a semantic abstract representation: performing mean pooling on the embedding vectors of the educational information units in each cluster to obtain the semantic center vector of the cluster as the abstract semantic representation of the current level cluster, identifying the common features of this type of educational semantic units;

[0024] Step S46: Multi-layer structure generation, using a top-down hierarchical strategy to recursively execute steps S41 to S45 to construct a multi-layer semantic hierarchy.

[0025] Furthermore, the knowledge tracking module specifically includes the following steps:

[0026] Step Q1: Learning behavior data collection: collecting students' learning behavior data, including answer records, homework submission status, learning resource access frequency, and video learning duration;

[0027] Step Q2: Construct a heterogeneous graph of students and knowledge points. Based on the collected learning behavior data, a heterogeneous graph structure consisting of student nodes and knowledge point nodes is constructed. Each student is represented as a student node, and each knowledge point is represented as a knowledge point node. Directed edges in the heterogeneous graph are generated based on the interaction between students and knowledge points.

[0028] Step Q3: Graph embedding representation learning: A heterogeneous graph convolutional network is used to learn node representations for the student-knowledge point heterogeneous graph. By combining graph structure information with node attribute information, each node is mapped to a low-dimensional embedding vector.

[0029] Step Q4: Based on the low-dimensional embedding vector and the embedding features of its adjacent knowledge point nodes, calculate the knowledge mastery score of each student on different knowledge points to form the student's knowledge status map.

[0030] The beneficial effects achieved by the present invention using the above scheme are as follows:

[0031] (1) To address the problem of limited educational resource processing capabilities, the present invention uses natural language processing (NLP) and image recognition technology through an educational resource acquisition module to perform semantic analysis and entity extraction on teaching content data, construct a semantic metadata set, and achieve efficient integration and semantic unit representation of multi-source educational resources;

[0032] (2) To address the problem of a single knowledge graph structure and weak semantic hierarchy, this paper introduces a graph embedding method based on a hyperbolic space graph convolutional network and a hierarchical clustering algorithm with improved robustness, performs low-dimensional embedding and multi-layer structure optimization on the initial knowledge graph, constructs an educational knowledge graph with a semantic hierarchy, and enhances the systematic expression and hierarchical understanding capabilities of knowledge.

[0033] (3) To address the problem of inaccurate tracking of students’ knowledge status, the present invention introduces a graph-structured learning behavior modeling method, constructs a student-knowledge point heterogeneous graph structure, and uses a heterogeneous graph convolutional network to model the interaction between students and knowledge points, thereby obtaining a knowledge status map for each student and improving the accuracy of individual knowledge mastery modeling. BRIEF DESCRIPTION OF THE DRAWINGS

[0034] Figure 1 This is a block diagram of the digital teaching material intelligent generation system based on digital education proposed by the present invention.

[0035] The accompanying drawings are used to provide further understanding of the present invention and constitute a part of the specification. They are used to explain the present invention together with the embodiments of the present invention and do not constitute a limitation of the present invention. DETAILED DESCRIPTION

[0036] The technical solutions in the embodiments of the present invention will be clearly and completely described below in conjunction with the drawings in the embodiments of the present invention. Obviously, the described embodiments are only part of the embodiments of the present invention, rather than all the embodiments; based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making creative work are within the scope of protection of the present invention.

[0037] Example 1, see Figure 1 The digital teaching material intelligent generation system based on digital education provided by the present invention includes an educational resource acquisition module, a knowledge graph construction module, a teaching material content generation module, a knowledge tracking module, and a teaching material presentation module, specifically including the following contents:

[0038] The educational resource acquisition module collects teaching content data, uses NLP and image recognition technology to perform semantic analysis and entity extraction on the teaching content data, obtains educational semantic units and constructs a semantic metadata set;

[0039] The knowledge graph construction module performs structured processing on the semantic metadata set to construct an initial knowledge graph, including nodes and edges, and introduces an embedding method based on a hyperbolic space graph convolutional network to perform low-dimensional representation learning on the initial knowledge graph to obtain an educational knowledge graph with a semantic hierarchical structure;

[0040] The teaching material content generation module is based on an educational knowledge graph with a semantic hierarchy, and uses graph structure expansion and semantic reasoning methods to cluster relevant knowledge points and expand paths for the target teaching topic to generate corresponding teaching material content units;

[0041] The knowledge tracking module introduces a graph-structured learning behavior modeling method to obtain the knowledge state map of each student by constructing a student-knowledge point heterogeneous graph structure;

[0042] The teaching material presentation module provides a visual presentation method for teaching material content based on teaching material content units and an educational knowledge graph with a semantic hierarchy, combined with each student's knowledge status graph;

[0043] In the educational resource acquisition module, teaching content data includes textbook texts, teaching lesson plans, teacher explanations, question bank materials, online course content, and multimedia resources. Educational semantic units include concept entities, knowledge points, teaching objectives, and topic tags.

[0044] In the teaching material content generation module, the teaching material content units include concept explanations, example question explanations, diagrams and exercises.

[0045] Example 2: This example is based on the above example. The knowledge graph construction module specifically includes the following steps:

[0046] Step S1: Structural processing: clarify and standardize the semantic metadata, map the educational semantic units into nodes, and establish edges based on the relationships between the educational semantic units. Each edge represents the semantic connection between different nodes.

[0047] Step S2: Construct an initial knowledge graph, and construct an initial knowledge graph of knowledge points, teaching objectives, and concept entities based on nodes and edges;

[0048] Step S3: Based on the embedding of the hyperbolic space graph convolutional network, a hyperbolic space graph convolutional network is introduced to perform low-dimensional representation learning on the initial knowledge graph, embed the nodes into the hyperbolic space, and obtain the embedded vector representation of each node;

[0049] Step S4: Calculate the structure, based on the embedding vector representation of each node, and use the hierarchical clustering algorithm based on robustness improvement to cluster the educational semantic units to form a multi-level semantic grouping structure;

[0050] Step S5: Structural optimization, jointly evaluate the similarity between nodes and the original connection relationship, and use the hierarchical adjustment algorithm to adjust the connection method of the edges to obtain an educational knowledge graph with a semantic hierarchical structure.

[0051] In this embodiment, in the teaching topic of "Junior Middle School Mathematics - Linear Function", the application process of the knowledge graph construction module is demonstrated, which specifically includes the following steps:

[0052] Structured processing: Educational semantic units include: linear function, function graph, function expression, slope, intercept, function increase and decrease, graph and practical problem modeling, teaching goal A (mastering the form of linear function expression), teaching goal B (understanding the connection between graph and algebra);

[0053] Convert the above semantic units into nodes in the knowledge graph and identify the semantic connection relationships between them. For example, there is a "has image" relationship between "linear function" and "function graph", a "contains" relationship between "function expression" and "slope", and a "goal coverage" relationship between "teaching goal A" and "function expression".

[0054] Based on the above nodes and edges, construct the initial knowledge graph;

[0055] The following multi-level structure is formed:

[0056] First-level clustering:

[0057] [Linear function]

[0058] Second level clustering:

[0059] [Function expression, slope, intercept]

[0060] [Function graph, increase and decrease of function]

[0061] Three-level clustering:

[0062] [Teaching Objective A, Teaching Objective B]

[0063] A semantic hierarchy is formed from "core concepts" to "constituent elements" to "teaching objectives".

[0064] Example 3: This example is based on the above example. In step S4, a hierarchical clustering algorithm based on robustness improvement is used to cluster educational semantic units. Specifically, the following steps are included:

[0065] Step S41: Denoising: performing density analysis on the embedded vector representation of each educational information unit, using a density-based noise discrimination mechanism to identify and remove abnormal samples, and obtaining a denoised set of educational information units;

[0066] Step S42: Construct a k-nearest-neighbor directed graph based on the denoised set of education information units. Map each education information unit to a node in the graph, and determine its k nearest neighbor nodes based on the Euclidean distance between the embedding vectors. Connect them to form directed edges, and set the weights of the directed edges based on the relative distances between the nodes.

[0067] Step S43: Graph merging and clustering: a group of nodes with close embedding vector distances are grouped together to form a cluster. Multiple clusters are constructed to form a semantic hierarchy. In the k-nearest neighbor directed graph, the directed edges are iteratively traversed in the order of their weights. The graph merging operation is performed until all directed edges are traversed.

[0068] Step S44: Determine the number of clusters. During the graph merging process in step S43, record the change in the number of clusters after each graph merging operation, construct a mapping sequence between iteration rounds and cluster numbers, count the number of merging iterations corresponding to each cluster number, and select the cluster number corresponding to the maximum number of merging iterations as the final clustering result.

[0069] Step S45: Constructing a semantic abstract representation: performing mean pooling on the embedding vectors of the educational information units in each cluster to obtain the semantic center vector of the cluster as the abstract semantic representation of the current level cluster, identifying the common features of this type of educational semantic units;

[0070] Step S46: Multi-layer structure generation, using a top-down hierarchical strategy to recursively execute steps S41 to S45 to construct a multi-layer semantic hierarchy.

[0071] In this embodiment, the educational information units extracted by the system include the semantic content corresponding to the following embedding vectors: linear function, function graph, function expression, slope, intercept, increase and decrease of function, x-axis intersection, nonlinear function, teaching objective A, and teaching objective B;

[0072] Among them, “nonlinear function” appears in some semantic contexts, but is not strongly related to the topic of “linear function”. It is detected as an outlier through the density-based noise discrimination mechanism and is removed;

[0073] For the embedding vectors of any two semantic units, calculate the Euclidean distance:

[0074] "Function expression" and "Slope": 0.21;

[0075] "Function expression" and "Intercept": 0.25;

[0076] "Function expression" and "linear function": 0.28;

[0077] “Function Expression” and “Teaching Objective A”: 0.49;

[0078] The rest are calculated in sequence to obtain the complete distance matrix;

[0079] (2) Determine the three nearest neighbors of each node

[0080] Taking "function expression" as an example, the three semantic units whose embedding vectors are closest are:

[0081] slope (0.21);

[0082] intercept(0.25);

[0083] Linear function (0.28);

[0084] Add three directed edges from the Function Expression node to its neighbors:

[0085] Function expression → slope (weight 0.21);

[0086] Function expression → intercept (weight 0.25);

[0087] Function expression → linear function (weight 0.28);

[0088] Linear function:

[0089] Function expression (0.28);

[0090] Function graph (0.32);

[0091] the increase and decrease of the function (0.36);

[0092] Slope:

[0093] intercept (0.19);

[0094] Function expression (0.21);

[0095] x-axis intersection point (0.33);

[0096] Function image:

[0097] Linear function (0.32);

[0098] the increase and decrease of the function (0.29);

[0099] Teaching objective B (0.44);

[0100] Function increase and decrease:

[0101] Function graph (0.29);

[0102] Linear function (0.36);

[0103] x-axis intersection point (0.38);

[0104] x-axis intersection:

[0105] intercept (0.27);

[0106] Function expression (0.30);

[0107] slope (0.33);

[0108] Teaching Objective A:

[0109] Teaching objective B (0.20);

[0110] Function graph (0.43);

[0111] Linear function (0.45);

[0112] Teaching Objective B:

[0113] Teaching objective A (0.20);

[0114] the increase and decrease of the function (0.42);

[0115] intercept (0.48);

[0116] Constructing the graph structure:

[0117] The system ultimately constructs a directed graph with nine nodes, each with three outgoing edges. Each edge represents the nearest neighbor relationship between semantic units in the form of a starting point → an end point, and the edge weight is saved as a distance indicator.

[0118] 9 educational semantic units (nodes):

[0119] V={v1: linear function, v2: function graph, v3: function expression, v4: slope, v5: intercept, v6: increase and decrease of function, v7: x-axis intersection, v8: teaching objective A, v9: teaching objective B};

[0120] Initially, each node is an independent cluster;

[0121] Merger Round 1:

[0122] Edge: Teaching Objective A → Teaching Objective B (0.20);

[0123] Operation: Merge v8 (teaching target A) and v9 (teaching target B) into a cluster C1 = {v8, v9};

[0124] Updated number of clusters: 9 → 8;

[0125] Merger Round 2:

[0126] Sides: Slope → Intercept (0.19);

[0127] Operation: Merge v4 and v5 into a cluster C2 = {v4, v5};

[0128] Updated number of clusters: 8 → 7;

[0129] Merger Round 3:

[0130] Side: FunctionExpression→ Slope(0.21);

[0131] Note: v4 and v5 are already in C2. The function expression (v3) is added to C2 → C2 = {v3, v4, v5}.

[0132] Updated number of clusters: 7 → 6;

[0133] Merger Round 4:

[0134] Edge: FunctionExpression → LinearFunction(0.28);

[0135] v3 is in C2, v1 is not merged → merge v1 into C2 → C2 = {v1, v3, v4, v5};

[0136] Updated number of clusters: 6 → 5;

[0137] Merger Round 5:

[0138] Side: x-axis intersection → intercept (0.27);

[0139] v5 is already in C2, v7 is not merged → merge v7 → C2 = {v1, v3, v4, v5, v7};

[0140] Updated number of clusters: 5 → 4;

[0141] Merger Round 6:

[0142] Edge: increase or decrease of function → function graph (0.29);

[0143] v2, v6 → merge into a new cluster C3 = {v2, v6};

[0144] Update the number of clusters: 4 → 3;

[0145] Merger Round 7:

[0146] Side: x-axis intersection → function expression (0.30);

[0147] v7 and v3 are already in C2, so they are skipped (already in the same cluster);

[0148] Merger Round 8:

[0149] Edge: linear function → function graph (0.32);

[0150] v1 ∈ C2, v2 ∈ C3 → merge C2 ∪ C3 → C2+C3 = {v1, v2, v3, v4, v5,v6, v7};

[0151] Update the number of clusters: 3 → 2;

[0152] Current cluster status:

[0153] C2' = {v1, v2, v3, v4, v5, v6, v7};

[0154] C1 = {v8, v9};

[0155] Merger Round 9:

[0156] Side: Teaching Objective B → Intercept (0.48);

[0157] v9 ∈ C1, v5 ∈ C2' → merge C1 and C2';

[0158] Final clustering: all semantic units are merged into one large cluster;

[0159] The number of clusters is 3 for two consecutive rounds, which is the hierarchical cluster number with the most stable structure and the best expression of semantic hierarchy, and the clustering result is determined to be 3 categories;

[0160] Perform mean pooling on the nodes in each cluster and extract the central embedding vector of the cluster as the semantic abstraction of the educational semantic unit.

[0161] Cluster A (function concept class): {v1: linear function, v3: function expression, v4: slope, v5: intercept, v7: x-axis intersection};

[0162] Cluster B (image and change): {v2: function image, v6: function increase and decrease};

[0163] Cluster C (teaching objective class): {v8: teaching objective A, v9: teaching objective B}.

[0164] Embodiment 4, based on the above embodiment, the knowledge tracking module specifically includes the following steps:

[0165] Step Q1: Learning behavior data collection: collecting students' learning behavior data, including answer records, homework submission status, learning resource access frequency, and video learning duration;

[0166] Step Q2: Construct a heterogeneous graph of students and knowledge points. Based on the collected learning behavior data, a heterogeneous graph structure consisting of student nodes and knowledge point nodes is constructed. Each student is represented as a student node, and each knowledge point is represented as a knowledge point node. Directed edges in the heterogeneous graph are generated based on the interaction between students and knowledge points.

[0167] Step Q3: Graph embedding representation learning: A heterogeneous graph convolutional network is used to learn node representations for the student-knowledge point heterogeneous graph. By combining graph structure information with node attribute information, each node is mapped to a low-dimensional embedding vector.

[0168] Step Q4: Based on the low-dimensional embedding vector and the embedding features of its adjacent knowledge point nodes, calculate the knowledge mastery score of each student on different knowledge points to form the student's knowledge status map.

[0169] In this example, the student behavior data collected:

[0170] Student ID Knowledge Points Correct answer Assignment Submission Video viewing time Visit frequency A1 K1 1 1 320 5 A1 K2 0 1 180 3 A2 K1 1 0 260 4 A2 K3 0 0 90 2

[0171] Construct the following heterogeneous graph structure:

[0172] Node Set = {S1, S2, K1, K2, K3}

[0173] S1 --> K1 (because answering questions + homework + video + visit ≥ threshold)

[0174] S1 --> K2

[0175] S2 --> K1

[0176] S2 --> K3

[0177] The code used for graph embedding representation learning is as follows:

[0178] import torch

[0179] import torch.nn.functional as F

[0180] from torch_geometric.nn import RGCNConv

[0181] class HeteroGNN(torch.nn.Module):

[0182] def __init__(self, in_channels, hidden_channels, out_channels, num_relations):

[0183] super().__init__()

[0184] self.conv1 = RGCNConv(in_channels, hidden_channels, num_relations)

[0185] self.conv2 = RGCNConv(hidden_channels, out_channels, num_relations)

[0186] def forward(self, x, edge_index, edge_type):

[0187] x = F.relu(self.conv1(x, edge_index, edge_type))

[0188] x = self.conv2(x, edge_index, edge_type)

[0189] return x

[0190] z_S1 = [0.8, 0.3, 0.6]

[0191] z_K1 = [0.9, 0.2, 0.7]

[0192] z_K2 = [0.2, 0.6, 0.5]

[0193] def mastery_score(student_embed, kp_embed):

[0194] return torch.sigmoid(torch.dot(student_embed, kp_embed))

[0195] score_S1_K1 = mastery_score(z_S1, z_K1) # The output may be 0.91, indicating a high degree of mastery;

[0196] score_S1_K2 = mastery_score(z_S1, z_K2) # The output may be 0.62, indicating average mastery.

[0197] It should be noted that, in this document, relational terms such as first and second, etc., are used only to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any actual relationship or order between these entities or operations. Moreover, the terms "comprises," "comprising," or any other variations thereof are intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that includes a list of elements includes not only those elements but also other elements not explicitly listed, or elements inherent to such process, method, article, or apparatus.

[0198] While embodiments of the present invention have been shown and described, it will be appreciated by those skilled in the art that various changes, modifications, substitutions, and variations may be made to these embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the appended claims and their equivalents.

[0199] The present invention and its embodiments are described above. This description is not restrictive. The drawings show only one embodiment of the present invention, and the actual structure is not limited thereto. In short, if a person skilled in the art is inspired by this and, without departing from the purpose of the present invention, designs structures and embodiments similar to this technical solution without inventiveness, they shall fall within the scope of protection of the present invention.

Claims

1. An intelligent digital teaching material generation system based on digital education, characterized by: It includes educational resource acquisition module, knowledge graph construction module, textbook content generation module, knowledge tracking module and textbook presentation module, specifically including the following contents: The educational resource acquisition module collects teaching content data, uses NLP and image recognition technology to perform semantic analysis and entity extraction on the teaching content data, obtains educational semantic units and constructs a semantic metadata set; The knowledge graph construction module performs structured processing on the semantic metadata set to construct an initial knowledge graph, including nodes and edges, and introduces an embedding method based on a hyperbolic space graph convolutional network to perform low-dimensional representation learning on the initial knowledge graph to obtain an educational knowledge graph with a semantic hierarchical structure; The teaching material content generation module is based on an educational knowledge graph with a semantic hierarchy, and uses graph structure expansion and semantic reasoning methods to cluster relevant knowledge points and expand paths for the target teaching topic to generate corresponding teaching material content units; The knowledge tracking module introduces a graph-structured learning behavior modeling method to obtain the knowledge state map of each student by constructing a student-knowledge point heterogeneous graph structure; The teaching material presentation module provides a visual presentation method for teaching material content based on teaching material content units and an educational knowledge graph with a semantic hierarchy, combined with each student's knowledge status graph; The knowledge graph construction module specifically includes the following steps: Step S1: Structural processing: clarify and standardize the semantic metadata, map the educational semantic units into nodes, and establish edges based on the relationships between the educational semantic units. Each edge represents the semantic connection between different nodes. Step S2: Construct an initial knowledge graph, and construct an initial knowledge graph of knowledge points, teaching objectives, and concept entities based on nodes and edges; Step S3: Based on the embedding of the hyperbolic space graph convolutional network, a hyperbolic space graph convolutional network is introduced to perform low-dimensional representation learning on the initial knowledge graph, embed the nodes into the hyperbolic space, and obtain the embedded vector representation of each node; Step S4: Calculate the structure, based on the embedding vector representation of each node, and use the hierarchical clustering algorithm based on robustness improvement to cluster the educational semantic units to form a multi-level semantic grouping structure; Step S5: Structural optimization, jointly evaluate the similarity between nodes and the original connection relationship, and use the hierarchical adjustment algorithm to adjust the connection method of the edges to obtain an educational knowledge graph with a semantic hierarchical structure.

2. The digital teaching material intelligent generation system based on digital education according to claim 1 is characterized in that: In the educational resource acquisition module, teaching content data includes textbook texts, teaching lesson plans, teacher explanations, question bank materials, online course content, and multimedia resources. Educational semantic units include concept entities, knowledge points, teaching objectives, and topic tags. In the teaching material content generation module, the teaching material content units include concept explanations, example question explanations, diagrams and exercises.

3. The digital teaching material intelligent generation system based on digital education according to claim 1 is characterized in that: Step S4, clustering the educational semantic units using a hierarchical clustering algorithm based on robustness improvement, specifically including the following steps: Step S41: Denoising: performing density analysis on the embedded vector representation of each educational information unit, using a density-based noise discrimination mechanism to identify and remove abnormal samples, and obtaining a denoised set of educational information units; Step S42: Construct a k-nearest-neighbor directed graph based on the denoised set of education information units. Map each education information unit to a node in the graph, and determine its k nearest neighbor nodes based on the Euclidean distance between the embedding vectors. Connect them to form directed edges, and set the weights of the directed edges based on the relative distances between the nodes. Step S43: Graph merging and clustering: a group of nodes with close embedding vector distances are grouped together to form a cluster. Multiple clusters are constructed to form a semantic hierarchy. In the k-nearest neighbor directed graph, the directed edges are iteratively traversed in the order of their weights. The graph merging operation is performed until all directed edges are traversed. Step S44: Determine the number of clusters. During the graph merging process in step S43, record the change in the number of clusters after each graph merging operation, construct a mapping sequence between iteration rounds and cluster numbers, count the number of merging iterations corresponding to each cluster number, and select the cluster number corresponding to the maximum number of merging iterations as the final clustering result. Step S45: Constructing a semantic abstract representation: performing mean pooling on the embedding vectors of the educational information units in each cluster to obtain the semantic center vector of the cluster as the abstract semantic representation of the current level cluster, identifying the common features of the educational semantic units; Step S46: Multi-layer structure generation, using a top-down hierarchical strategy to recursively execute steps S41 to S45 to construct a multi-layer semantic hierarchy.

Images