Learning path recommendation method integrating hierarchical knowledge graph and deep knowledge tracing

Abstract

The present invention discloses a learning path recommendation method that integrates hierarchical knowledge graphs and deep knowledge tracking, which belongs to the field of data analysis technology and includes the following steps: KGDKT model construction, which constructs a deep knowledge tracking model that can consider the logical relationship between knowledge points; learning path search, which generates all paths from the starting knowledge point to the target knowledge point based on the hierarchical course knowledge graph and KGDKT; optimal path selection, which predicts the learner's mastery of the target knowledge point on different paths through KGDKT, and selects the path with the best learning effect and recommends it to the learner. The path generated by the method of the present invention conforms to the logical relationship between knowledge points, can adapt to the learner's dynamically changing knowledge level, and improves the learner's learning effect on the target knowledge point.

Description

Technical Field

[0001] The present invention belongs to the field of data analysis technology, and in particular relates to a learning path recommendation method that integrates hierarchical knowledge graphs and deep knowledge tracking. Background Art

[0002] Personalized learning path recommendation aims to recommend the most appropriate learning path based on learners' interests, knowledge level, and learning ability, thereby improving learning outcomes and satisfaction. There are two main approaches to learning path recommendation: global optimal path recommendation and local iterative path recommendation. Global optimal path recommendation provides a complete learning path at once, but does not consider the learner's evolving knowledge state during the learning process. Local iterative path recommendation dynamically recommends based on the learner's evolving knowledge state during the learning process. However, because learning paths are constructed during the learning process, learners cannot fully grasp the learning content beforehand. Global path recommendation can be categorized by the recommendation method: graph-based, evolutionary algorithm-based, and clustering-based. Graph-based methods represent relationships between knowledge points using graphs to assist in path generation; evolutionary algorithm-based methods view the learning process as an evolutionary process, optimizing learning paths through methods such as genetic algorithms; and clustering-based methods cluster learners based on their characteristics, recommending the same learning path to similar learners.

[0003] Flaws and shortcomings of existing technologies: First, a major flaw in global path recommendation methods is that they fail to consider changes in a learner's knowledge level during the learning process, resulting in low path recommendation accuracy. Knowledge level reflects a learner's mastery of a particular knowledge point and is a crucial factor in personalized learning path recommendation. Due to differences in learner knowledge levels, different learners may require different learning paths for the same target knowledge point. Therefore, ignoring the changes in a learner's knowledge level during the learning process makes it impossible to accurately recommend personalized learning paths.

[0004] Secondly, Deep Learning-based Knowledge Tracing (DLKT) is the current mainstream method for characterizing learners' knowledge levels. It is used to obtain learners' mastery of knowledge points and, in turn, reflect their knowledge level. However, existing DLKT models rarely consider the relationship between knowledge points and other knowledge points when predicting their mastery, ignoring the mutual influence between the mastery levels of different knowledge points. This results in inaccurate predictions of knowledge point mastery, affecting the measurement of learners' knowledge levels and, consequently, the effectiveness of learning path recommendations.

[0005] Based on this, the present invention designs a learning path recommendation method that integrates hierarchical knowledge graph and deep knowledge tracking to solve the above problems. Summary of the Invention

[0006] The purpose of the present invention is to solve the problems in the above-mentioned background technology and to propose a learning path recommendation method that integrates hierarchical knowledge graph and deep knowledge tracking.

[0007] To achieve the above objectives, the present invention adopts the following technical solution: a learning path recommendation method integrating hierarchical knowledge graph and deep knowledge tracking, comprising the following steps:

[0008] KGDKT model construction, building a deep knowledge tracking model that can consider the logical relationship between knowledge points;

[0009] Learning path search algorithm, based on the hierarchical course knowledge graph and KGDKT, generates all paths from the starting knowledge point to the target knowledge point;

[0010] The optimal path selection algorithm uses the KGDKT model to predict the improvement effect of each path on the target knowledge point, and selects a path that can maximize the learner's mastery of the target knowledge point.

[0011] Preferably, before constructing the KGDKT model, a hierarchical course knowledge graph needs to be constructed;

[0012] The KGDKT model construction specifically includes representing the knowledge graph as a vector e through knowledge graph embedding technology. q , e q The feature of the DTransformer model is integrated to complete the integration of the hierarchical course knowledge graph and DTransformer. A custom AttentionLayer layer is implemented and the hidden state of the last encoder layer of DTransformer is extracted as the feature f. This layer receives two input feature vectors f and e. q , and fuse them into a new vector a through the attention mechanism. Specifically, first define the weight matrix, then calculate the attention score and perform normalization, and finally obtain the fused vector a through weighted summation. The process is shown in formula (1), where W a is the weight matrix used to transform f, U a is used to convert e q The weight matrix, is the weight vector used to calculate the attention score, s is f and e q Attention score between

[0013]

[0014] Preferably, the learning path search algorithm specifically includes determining the starting knowledge point set SKP according to the learner's mastery of the knowledge point, and generating all paths {path a ,path b ,…,path n};

[0015] The algorithm first determines the target knowledge point and the starting knowledge point. The target knowledge point is specified by the learner, and the starting knowledge point is determined based on the learner's mastery of the knowledge point. Specifically, the KGDKT model is used to predict the learner's mastery of all knowledge points. The knowledge points that the learner has already mastered are used as starting knowledge points and added to the knowledge point set SKP. In order to find all possible paths from all starting knowledge points in SKP to the target knowledge point t and ensure that all prerequisite knowledge points have been learned before learning a certain knowledge point, it is necessary to consider the learning order of knowledge points with multiple prerequisite knowledge points.

[0016] Based on this, a backward breadth-first search algorithm (B-BFS) is proposed. Starting from the target knowledge point, the algorithm traces back the HKG along the prerequisite relationship to the starting knowledge point. If the starting knowledge point cannot be found or there is no starting knowledge point that meets the conditions, the algorithm continues to trace back to the knowledge point without a prerequisite and uses it as the starting point of the learning path.

[0017] The learning order of multiple parallel prerequisite knowledge points is determined by their difficulty level, and they are learned in a progressively more difficult order. The difficulty level is determined by the learner's mastery of these knowledge points; higher difficulty points correspond to lower mastery levels. This algorithm works by reversely searching for prerequisite knowledge points, ensuring that all necessary prerequisite knowledge points have been learned before starting to learn a particular knowledge point, and that multiple parallel prerequisite knowledge points conform to a progressively more difficult learning order.

[0018] Finally, the path is constructed in the order of queue dequeue, and after reversing the direction of the path, it is added to the candidate path set Paths.

[0019] Preferably, the optimal path selection algorithm specifically includes the target knowledge point learning effect E p As shown in formula 2, where E s Indicates the learner's initial mastery of the target knowledge point, E e Indicates the learner's final mastery of the target knowledge point;

[0020] The goal of the algorithm is to select a path from the candidate learning path set Paths that can maximize the learner's learning effect of the target knowledge point and recommend the path to the learner;

[0021] First, a learning path search algorithm based on the hierarchical course knowledge graph is used to search for all learning paths from the knowledge points in the starting knowledge point set SKP to the target knowledge point t in HKG, and a candidate learning path set Paths is obtained;

[0022] Secondly, for each path in Paths, KGDKT is used to predict the learner's learning effect on each path to select the path. Specifically, KGDKT is first used to predict the initial mastery level E of each path before learning t. s , Secondly, according to the order of the knowledge points in the path, predict the learner's mastery of each knowledge point in the path in turn, and form a new interaction record with the predicted results, which is added to the historical interaction record H to complete the update of H, and then complete the prediction of the mastery of other knowledge points, and finally obtain the mastery level E of the target knowledge point t after learning each path e , calculate the E obtained by learning each path through formula (2) p Value, select E p The largest path is recommended to learners;

[0023]

[0024] In summary, due to the adoption of the above technical solution, the beneficial effects of the present invention are:

[0025] 1. In the present invention, in terms of modeling the learner's knowledge level, by integrating the knowledge graph, the KGDKT model can improve the accuracy of predicting the learner's knowledge level, thereby improving the accuracy of path recommendation; in terms of the relationship between knowledge points in learning path recommendation, the path generated by the learning path search algorithm based on the hierarchical course knowledge graph proposed in this patent is more in line with the logical relationship between knowledge points, and adapts to the learner's knowledge level, avoiding the impact of the target knowledge point learning effect due to the failure to learn the prerequisite knowledge points; in terms of the optimal path selection for learning path recommendation, the KGDKT model takes into account the changes in the learner's knowledge level during the learning process along the path and the knowledge level at the target knowledge point, so that the path is more adapted to the learner's knowledge level and can improve the learner's learning effect at the target knowledge point. BRIEF DESCRIPTION OF THE DRAWINGS

[0026] Figure 1 This is a framework diagram of the learning path recommendation method proposed in this invention that integrates hierarchical knowledge graph and deep knowledge tracking;

[0027] Figure 2 This is the KGDKT model diagram of the learning path recommendation method that integrates hierarchical knowledge graph and deep knowledge tracing proposed in this invention;

[0028] Figure 3This is a flow chart of the learning path search algorithm based on the hierarchical course knowledge graph, which is a learning path recommendation method that integrates the hierarchical knowledge graph and deep knowledge tracking proposed in the present invention. DETAILED DESCRIPTION

[0029] The following will clearly and completely describe the technical solutions in the embodiments of the present invention in conjunction with the accompanying drawings. Obviously, the described embodiments are only part of the embodiments of the present invention, not all of the embodiments. Based on the embodiments of the present invention, all other embodiments obtained by ordinary technicians in this field without making any creative efforts shall fall within the scope of protection of the present invention.

[0030] Please see the attached Figure 1 -Attached Figure 3 The present invention provides a technical solution: a learning path recommendation method integrating hierarchical knowledge graph and deep knowledge tracking, comprising the following steps:

[0031] KGDKT model construction, building a deep knowledge tracking model that can consider the logical relationship between knowledge points;

[0032] Learning path search algorithm, based on the hierarchical course knowledge graph and KGDKT, generates all paths from the starting knowledge point to the target knowledge point;

[0033] The optimal path selection algorithm uses the KGDKT model to predict the improvement effect of each path on the target knowledge point, and selects a path that can maximize the learner's mastery of the target knowledge point.

[0034] Specifically, before constructing the KGDKT model, it is necessary to build a hierarchical course knowledge graph;

[0035] The KGDKT model construction specifically includes representing the knowledge graph as a vector e through knowledge graph embedding technology. q , e q The feature of the DTransformer model is integrated to complete the integration of the hierarchical course knowledge graph and DTransformer. A custom AttentionLayer layer is implemented and the hidden state of the last encoder layer of DTransformer is extracted as the feature f. This layer receives two input feature vectors f and e. q , and fuse them into a new vector a through the attention mechanism. Specifically, first define the weight matrix, then calculate the attention score and perform normalization, and finally obtain the fused vector a through weighted summation. The process is shown in formula (1), where W a is the weight matrix used to transform f, U a is used to convert e q The weight matrix, is the weight vector used to calculate the attention score, s is f and e q Attention score between

[0036] h1=W a f

[0037] h q =U a e q

[0038]

[0039]

[0040] a=α(W f f+U f e q ).

[0041] Specifically, the learning path search algorithm specifically includes determining the starting knowledge point set SKP according to the learner's mastery of the knowledge point, and generating all paths {path a ,path b ,…,path n};

[0042] The algorithm first determines the target knowledge point and the starting knowledge point. The target knowledge point is specified by the learner, and the starting knowledge point is obtained based on the user's mastery of the knowledge point. Specifically, the KGDKT model is used to predict the learner's mastery of all knowledge points. The knowledge points that the learner has mastered are used as starting knowledge points and added to the knowledge point set SKP. In order to find all possible paths from all starting knowledge points in SKP to the target knowledge point t and ensure that all prerequisite knowledge points have been learned before learning a certain knowledge point, it is necessary to consider the learning order of knowledge points with multiple prerequisite knowledge points.

[0043] Based on this, a backward breadth-first search algorithm (B-BFS) is proposed. Starting from the target knowledge point, the algorithm traces back the HKG along the prerequisite relationship to the starting knowledge point. If the starting knowledge point cannot be found or there is no starting knowledge point that meets the conditions, the algorithm continues to trace back to the knowledge point without a prerequisite and uses it as the starting point of the learning path.

[0044] The learning order of multiple parallel prerequisite knowledge points is determined by their difficulty level, and they are learned in a progressively more difficult order. The difficulty level is determined by the learner's mastery of these knowledge points; higher difficulty points correspond to lower mastery levels. This algorithm works by reversely searching for prerequisite knowledge points, ensuring that all necessary prerequisite knowledge points have been learned before starting to learn a particular knowledge point, and that multiple parallel prerequisite knowledge points conform to a progressively more difficult learning order.

[0045] Finally, the path is constructed in the order of queue dequeue, and after reversing the direction of the path, it is added to the candidate path set Paths.

[0046] Specifically, the optimal path selection algorithm specifically includes the target knowledge point learning effect E p As shown in formula 2, where E s Indicates the learner's initial mastery of the target knowledge point, E e Indicates the learner's final mastery of the target knowledge point;

[0047] The goal of the algorithm is to select a path from the candidate learning path set Paths that can maximize the learner's learning effect of the target knowledge point and recommend the path to the learner;

[0048] First, a learning path search algorithm based on the hierarchical course knowledge graph is used to search for all learning paths from the knowledge points in the starting knowledge point set SKP to the target knowledge point t in HKG, and a candidate learning path set Paths is obtained;

[0049] Secondly, for each path in Paths, KGDKT is used to predict the learner's learning effect on each path to select the path. Specifically, KGDKT is first used to predict the initial mastery level E of each path before learning t. s , Secondly, according to the order of the knowledge points in the path, predict the learner's mastery of each knowledge point in the path in turn, and form a new interaction record with the predicted results, which is added to the historical interaction record H to complete the update of H, and then complete the prediction of the mastery of other knowledge points, and finally obtain the mastery level E of the target knowledge point t after learning each path e , calculate the E obtained by learning each path through formula (2) p Value, select E p The largest path is recommended to learners;

[0050]

[0051] The above description is only a preferred specific embodiment of the present invention, but the scope of protection of the present invention is not limited thereto. Any technician familiar with the technical field, within the technical scope disclosed by the present invention, who makes equivalent replacements or changes based on the technical solution and inventive concept of the present invention, should be covered by the scope of protection of the present invention.

Claims

1. A learning path recommendation method that integrates hierarchical knowledge graph and deep knowledge tracking, characterized by: The following steps are involved: KGDKT model construction, building a deep knowledge tracking model that can consider the logical relationship between knowledge points; Learning path search algorithm, based on the hierarchical course knowledge graph and KGDKT, generates all paths from the starting knowledge point to the target knowledge point; The optimal path selection algorithm uses the KGDKT model to predict the improvement effect of each path on the target knowledge point and selects the path that can maximize the learner's mastery of the target knowledge point; Before constructing the KGDKT model, it is necessary to build a hierarchical course knowledge graph; The KGDKT model construction specifically includes representing the knowledge graph as a vector e through knowledge graph embedding technology. q , e q The feature of the DTransformer model is integrated to complete the integration of the hierarchical course knowledge graph and DTransformer. A custom AttentionLayer layer is implemented and the hidden state of the last encoder layer of DTransformer is extracted as the feature f. This layer receives two input feature vectors f and e. q , and fuse them into a new vector a through the attention mechanism. Specifically, first define the weight matrix, then calculate the attention score and perform normalization, and finally obtain the fused vector a through weighted summation. The process is shown in formula (1), where W a is the weight matrix used to transform f, U a is used to convert e q The weight matrix, is the weight vector used to calculate the attention score, s is f and e q Attention score between h1=W a f h q =U a have been q a=α(W f f+U f e q )。 2. The learning path recommendation method integrating hierarchical knowledge graph and deep knowledge tracking according to claim 1 is characterized in that: The learning path search algorithm specifically includes determining the starting knowledge point set SKP according to the learner's mastery of the knowledge point, and generating all paths {path a ,path b ,…,path n }; The algorithm first determines the target knowledge point and the starting knowledge point. The target knowledge point is specified by the learner, and the starting knowledge point is determined based on the learner's mastery of the knowledge point. Specifically, the KGDKT model is used to predict the learner's mastery of all knowledge points. The knowledge points that the learner has already mastered are used as starting knowledge points and added to the knowledge point set SKP. In order to find all possible paths from all starting knowledge points in SKP to the target knowledge point t and ensure that all prerequisite knowledge points have been learned before learning a certain knowledge point, it is necessary to consider the learning order of knowledge points with multiple prerequisite knowledge points. Based on this, a backward breadth-first search algorithm (B-BFS) is proposed. Starting from the target knowledge point, the algorithm traces back the HKG along the prerequisite relationship to the starting knowledge point. If the starting knowledge point cannot be found or there is no starting knowledge point that meets the conditions, the algorithm continues to trace back to the knowledge point without a prerequisite and uses it as the starting point of the learning path. The learning order of multiple parallel prerequisite knowledge points is determined by their difficulty level, and they are learned in a progressively more difficult order. The difficulty level is determined by the learner's mastery of these knowledge points; higher difficulty points correspond to lower mastery levels. This algorithm works by reversely searching for prerequisite knowledge points, ensuring that all necessary prerequisite knowledge points have been learned before starting to learn a particular knowledge point, and that multiple parallel prerequisite knowledge points conform to a progressively more difficult learning order. Finally, the path is constructed in the order of queue dequeue, and after reversing the direction of the path, it is added to the candidate path set Paths.

3. The learning path recommendation method integrating hierarchical knowledge graph and deep knowledge tracking according to claim 1 is characterized in that: The optimal path selection algorithm specifically includes predicting the learner's mastery of target knowledge points on different paths through KGDKT, selecting a path with the best learning effect and recommending it to the learner, and the target knowledge point learning effect E p As shown in Formula 2, where E s Indicates the learner's initial mastery of the target knowledge point, E e Indicates the learner's final mastery of the target knowledge point; The goal of the algorithm is to select a path from the candidate learning path set Paths that can maximize the learner's learning effect of the target knowledge point and recommend the path to the learner; First, a learning path search algorithm based on the hierarchical course knowledge graph is used to search for all learning paths from the knowledge points in the starting knowledge point set SKP to the target knowledge point t in HKG, and a candidate learning path set Paths is obtained; Secondly, for each path in Paths, KGDKT is used to predict the learner's learning effect on each path to select the path. Specifically, KGDKT is first used to predict the initial mastery level E of each path before learning t. s , Secondly, according to the order of the knowledge points in the path, predict the learner's mastery of each knowledge point in the path in turn, and form a new interaction record with the predicted results, which is added to the historical interaction record H to complete the update of H, and then complete the prediction of the mastery of other knowledge points, and finally obtain the mastery level E of the target knowledge point t after learning each path e , calculate the E obtained by learning each path through formula (2) p Value, select E p The largest path is recommended to learners;

Images