Construction method of advanced knowledge map

Abstract

The invention is suitable for the technical field of knowledge maps, and provides a knowledge advanced map construction method, which comprises the following steps: acquiring a target knowledge point; according to the target knowledge point, determining related courses and an association relationship between the related courses from a pre-constructed course knowledge graph; constructing a knowledge basic map according to the related curriculums and the association relationship; and according to the at least one preset course attribute of the related course, performing learning stage division on the knowledge basic map to obtain a knowledge advanced map comprising a plurality of learning stages. According to the method, the knowledge map suitable for course learning can be quickly and accurately constructed.

Description

Technical Field

[0001] The present invention belongs to the technical field of knowledge maps, and in particular relates to a method for constructing an advanced knowledge map. Background Art

[0002] As an effective knowledge management tool, knowledge maps play a vital role in course learning. They intuitively display the overall knowledge structure of a course and the distribution of various knowledge points. They provide learners with a visual knowledge framework, clearly illustrating the connections and structures between knowledge points. This helps students clarify learning goals and paths, build a knowledge system, and improve learning efficiency.

[0003] In related technologies, when constructing a knowledge map, it is usually necessary to manually collect a large amount of data, filter out useful information, organize and classify it, and then manually design graphics, connect nodes, etc., and manually draw the knowledge map. This traditional construction method is usually applicable to fixed knowledge systems. For course learning, different learners, or the same learner at different stages, have different learning needs, so it is necessary to construct a targeted knowledge map. The traditional construction method has a cumbersome operation process, a huge workload of drawing and modifying, a long time consumption and prone to errors. At the same time, traditional knowledge maps cannot provide learners with a systematic learning navigation solution.

[0004] Therefore, there is an urgent need for a new way to construct knowledge maps to support course learning. Summary of the Invention

[0005] In view of this, an embodiment of the present invention provides a method for constructing a knowledge advancement map to quickly and accurately construct a knowledge map suitable for course learning.

[0006] An embodiment of the present invention provides a method for constructing a knowledge advancement map, comprising:

[0007] Acquire target knowledge points;

[0008] According to the target knowledge point, determine the relevant courses and the relationship between the relevant courses from the pre-built course knowledge map;

[0009] Constructing a knowledge base map based on the relevant courses and the association relationships;

[0010] According to at least one preset course attribute of the relevant course, the knowledge base map is divided into learning stages to obtain a knowledge advancement map including multiple learning stages.

[0011] As a possible implementation, the association relationship includes: first repair and subsequent repair;

[0012] Accordingly, the knowledge base map is constructed based on the relevant courses and the association relationships, including:

[0013] According to the prerequisite and successor relationships between the related courses, arrows are connected to the related courses to obtain a tree-like learning route for the related courses;

[0014] Based on the tree-like learning route, a knowledge base map is constructed.

[0015] As a possible implementation method, the preset course attributes include: learning difficulty;

[0016] Accordingly, the step of dividing the knowledge base map into stages according to at least one preset course attribute of the relevant course includes:

[0017] Obtain at least one learning difficulty threshold and sort them from small to large;

[0018] In the knowledge base map, searching from front to back for the first relevant course on each bifurcation whose learning difficulty is greater than a first learning difficulty threshold as a first dividing point; dividing all relevant courses before the first dividing point into a learning stage;

[0019] Starting from each first dividing point, find the first relevant course on each bifurcation whose learning difficulty is greater than the next learning difficulty threshold from the front to the back, and use it as the second dividing point; divide all relevant courses before the second dividing point into one learning stage;

[0020] If there is no related course on the fork with a learning difficulty greater than the corresponding learning difficulty threshold, then the fork and all previous related courses will be incorporated into the current learning stage;

[0021] Repeat the above steps until the learning stages for all learning difficulty thresholds are divided.

[0022] As a possible implementation, the preset course attribute further includes: centrality; the centrality of the related course is: the number of related courses associated with the related course;

[0023] Accordingly, the step of dividing the knowledge base map into stages according to at least one preset course attribute of the relevant course further includes:

[0024] After completing the division of learning stages according to all learning difficulty thresholds, determine whether the centrality of each relevant course is greater than the preset centrality threshold;

[0025] If the centrality of any relevant course is greater than the centrality threshold, the relevant course and the previous relevant courses in the current learning stage will be classified into the previous learning stage.

[0026] As a possible implementation method, the preset course attributes further include: time cost;

[0027] Accordingly, the step of dividing the knowledge base map into learning stages according to at least one preset course attribute of the relevant course further includes:

[0028] Calculate the total time cost for each learning stage based on the time cost of each relevant course in each learning stage;

[0029] If the total time cost corresponding to any learning stage is greater than the preset time cost threshold, the learning stage is further divided into two learning stages.

[0030] As a possible implementation, the learning phase is further divided into two learning phases, including:

[0031] Determining a target learning difficulty threshold based on the learning difficulty thresholds corresponding to the current learning stage and the previous learning stage; wherein the target learning difficulty threshold is between the learning difficulty thresholds corresponding to the current learning stage and the previous learning stage;

[0032] In this learning phase, the first relevant course with a learning difficulty greater than the target learning difficulty threshold is searched from front to back on each bifurcation as the target dividing point;

[0033] Based on the target dividing point, the learning phase is further divided into two learning phases.

[0034] As a possible implementation manner, obtaining at least one learning difficulty threshold includes:

[0035] Obtain learners' historical learning data;

[0036] evaluating the learner's learning ability time series based on the historical learning data;

[0037] According to the learning ability time series, the learning difficulty threshold is determined within a preset learning difficulty threshold value range through a pre-trained neural network model.

[0038] As a possible implementation method, after obtaining the knowledge advancement map including multiple learning stages, the method further includes:

[0039] Set advanced examination papers and conditions for each learning stage;

[0040] After the learner completes any learning stage, the learner is tested through the advanced test paper of the learning stage and the test results are obtained;

[0041] Determining whether the advancement conditions are met based on the test results;

[0042] If the advancement condition is met, the next learning stage of the knowledge advancement map is opened; if the advancement condition is not met, the next learning stage of the knowledge advancement map is not opened.

[0043] As a possible implementation, the method further includes:

[0044] Access to multimodal course resources;

[0045] Convert multimodal course resources into structured text data and extract entities from the text data to obtain corresponding knowledge points;

[0046] Conduct course association mining on knowledge points to construct the course knowledge graph.

[0047] As a possible implementation method, the obtaining of multimodal course resources includes: obtaining multimodal course resources from a website by using crawler technology.

[0048] Compared with the prior art, the embodiments of the present invention have the following beneficial effects:

[0049] The embodiment of the present invention pre-constructs a course knowledge graph. According to the target knowledge points, it can determine the relevant courses from the course knowledge graph, and automatically construct a knowledge base map based on the association between the relevant courses, so as to quickly and accurately construct a knowledge map suitable for course learning, and help learners clarify their learning goals and paths; further, according to at least one course attribute of the relevant course, the knowledge base map is divided into learning stages to obtain a knowledge advancement map containing multiple learning stages, which can provide learners with a systematic and staged learning navigation plan and improve learning efficiency. BRIEF DESCRIPTION OF THE DRAWINGS

[0050] In order to more clearly illustrate the technical solutions in the embodiments of the present invention, the following briefly introduces the drawings required for use in the embodiments or the description of the prior art. Obviously, the drawings described below are only some embodiments of the present invention. For ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative work.

[0051] Figure 1 This is a schematic diagram of the construction process of the course knowledge graph provided by an embodiment of the present invention;

[0052] Figure 2 1 is a flow chart of a method for constructing a knowledge advancement map provided by an embodiment of the present invention;

[0053] Figure 3 This is a diagram of the division of learning stages provided by an embodiment of the present invention. Figure 1 ;

[0054] Figure 4 This is a diagram of the division of learning stages provided by an embodiment of the present invention. Figure 2 . DETAILED DESCRIPTION

[0055] In the following description, specific details such as particular system structures and techniques are provided for purposes of illustration, not limitation, to facilitate a thorough understanding of the embodiments of the present invention. However, it will be apparent to those skilled in the art that the present invention may be practiced in other embodiments without these specific details. In other cases, detailed descriptions of well-known systems, devices, circuits, and methods are omitted so as not to obscure the description of the present invention with unnecessary detail.

[0056] In order to illustrate the technical solution of the present invention, specific embodiments are provided below.

[0057] A knowledge map is a knowledge management tool that visually presents concepts, knowledge points, and their interrelationships within a knowledge domain. Its general structure includes nodes, which represent knowledge elements such as concepts, knowledge points, and themes; and lines, which represent relationships between nodes, such as causal, progressive, and parallel relationships. In education, knowledge maps can help students clarify learning goals and paths, build a systematic knowledge system, and improve learning efficiency and effectiveness.

[0058] A course knowledge graph is a structured form of knowledge representation that presents course-related information in a graphical format. Nodes represent entities such as courses and knowledge points, while edges represent the relationships between these entities, such as the knowledge points included in a course, the prerequisite relationships between knowledge points, and the contextual relationships between courses. By constructing a course knowledge graph, we can clearly demonstrate the connections between various elements in the curriculum system, providing a foundation for subsequent operations.

[0059] See also Figure 1 As shown, the process of constructing the course knowledge graph in this embodiment is as follows:

[0060] (1) Course resource data acquisition.

[0061] Multimodal course resources such as pictures, texts, videos, etc. can be obtained from websites and other channels through crawler technology, manual methods, etc.

[0062] (2) Data preprocessing and storage.

[0063] For different types of data, this embodiment converts unstructured multimodal teaching data into structured text data, and then performs entity extraction on the text data to obtain corresponding knowledge points.

[0064] (3) Knowledge graph construction.

[0065] We use association rule mining methods to mine course associations for pre-processed courses or knowledge points, building a professional knowledge graph that integrates multiple course resources. We extract knowledge elements from text data through technologies such as entity recognition and relationship extraction, and organize them into a knowledge graph.

[0066] Knowledge graphs can be stored using a graph database-based approach. Graph databases focus on efficient graph queries and searches, storing data using nodes and edges and capable of storing data including attribute values. Therefore, to facilitate queries related to target knowledge points, a graph database-based approach is used to store the data structure of the course knowledge graph. This approach better supports the storage and query of relationships between knowledge points and their attribute information.

[0067] Furthermore, this embodiment searches for related courses based on the course knowledge graph and generates a knowledge map based on the contextual relationship between courses. It can quickly and accurately construct a knowledge map suitable for course learning, provide learners with an intuitive and clear learning navigation, help them better understand the course system and knowledge structure, reasonably arrange the learning sequence, and significantly improve learning efficiency.

[0068] Figure 2 This is a schematic diagram of the implementation process of the method for constructing a knowledge advancement map provided by an embodiment of the present invention. Figure 2 As shown, the method includes:

[0069] Step S201, obtaining target knowledge points.

[0070] The target knowledge points here may be keywords that the learner wants to learn, such as "programming", or more specifically "sorting algorithm", etc., which are not limited in this embodiment.

[0071] Step S202: Determine relevant courses and the relationships between relevant courses from a pre-built course knowledge graph based on the target knowledge point.

[0072] This embodiment pre-builds a course knowledge graph for a specific field. A dedicated knowledge graph is a knowledge graph built for a specific field or industry, for a specific task or user group. Because it is targeted at a specific field, a dedicated knowledge graph can perform more detailed screening and verification of data to ensure the accuracy and reliability of knowledge. For example, in a knowledge graph built specifically for the programming field, it covers many aspects of knowledge such as the syntax, semantics, data structure, algorithm, programming framework, and development tools of the programming language. Various knowledge is integrated, represented, and associated, which can help developers learn, develop, and solve problems more efficiently.

[0073] Based on a given target knowledge point, the course knowledge graph is searched for courses that are directly or indirectly related to it. For example, if the target knowledge point is "Convolutional Neural Networks," the knowledge graph may reveal a direct connection to the "Deep Learning" course, as this course primarily covers various deep learning models, including convolutional neural networks. It may also be indirectly related to the "Machine Learning" course, as machine learning is the foundation of deep learning, and some of the algorithms and theories in the "Machine Learning" course are prerequisites for understanding convolutional neural networks. After identifying relevant courses, the knowledge graph is further analyzed to identify the specific connections between these courses and their relationship types. For example, both "Advanced Mathematics" and "Probability Theory and Mathematical Statistics" are related to "Machine Learning." Calculus and other knowledge in "Advanced Mathematics" form the foundation for the derivation of some algorithms in "Machine Learning," resulting in a foundational support relationship. Probability Theory and Mathematical Statistics, on the other hand, provides the theoretical basis for data modeling and analysis in "Machine Learning," creating a theoretical-applied relationship. By identifying these connections, we can better understand the logical connections between courses and provide strong support for learning path planning.

[0074] Step S203: construct a knowledge base map based on relevant courses and association relationships.

[0075] In this embodiment, constructing a knowledge base map based on relevant courses and association relationships is a process of presenting the knowledge covered by the courses and their association relationships in a visual form.

[0076] As a possible implementation method, the association relationship may include: prerequisites and successors, and the process of constructing the knowledge base map may be: according to the prerequisite and successor relationships between the relevant courses, arrows are connected to the relevant courses with the association relationship to obtain a tree-like learning route for the relevant courses; based on the tree-like learning route, the knowledge base map is constructed.

[0077] The prerequisite relationship between courses means that before studying a certain course, you must first master the knowledge and skills of certain other courses, otherwise it will be difficult to understand and grasp the content of the course. The successor relationship between courses means that after studying a certain course, you can further learn the knowledge and skills of certain other courses. These courses are usually in-depth extensions and expansions of the course.

[0078] Arrows connect related courses based on established prerequisite and successor relationships. For example, starting with "Advanced Mathematics," arrows point to the dependent courses "Probability Theory and Mathematical Statistics" and "Algorithm Analysis." After completing "Data Structures," arrows point to its subsequent course, "Database Principles." These arrow connections clearly demonstrate the sequence and dependencies between courses, forming a tree-like learning path. This tree-like learning path intuitively illustrates the logical order between courses, allowing learners to clearly see what comes first and what comes later.

[0079] While tree-like learning paths primarily reflect the sequential order of courses, knowledge maps are more comprehensive and enriching. When constructing a knowledge base map, in addition to the sequential relationship between courses, you can also add other relevant information, such as the main content, key points and difficulties, reference materials, and learning suggestions. Furthermore, the layout of course nodes and the style of arrows in the map can be adjusted based on the degree of connection and closeness between courses, making the knowledge base map more intuitive and easy to understand. Through the knowledge base map, learners can not only understand the order in which courses should be studied, but also access more comprehensive learning resources and guidance.

[0080] Step S204: dividing the knowledge base map into learning stages according to at least one preset course attribute of the relevant course to obtain a knowledge advancement map including multiple learning stages.

[0081] Course attributes such as difficulty, depth, and knowledge type can all be used as preset course attributes. Based on these attributes, the knowledge base map can be divided into multiple learning stages. These divided learning stages are clearly presented in the knowledge progression map. Within each learning stage, the courses included in that stage are displayed, and the relationships between courses are represented using lines or arrows. This provides learners with a reasonable learning path, helping them clarify which courses to study at each learning stage and how to transition from one stage to the next, thereby achieving gradual accumulation of knowledge and improvement of abilities.

[0082] Exemplarily, the knowledge advancement map can set advanced test papers and advancement conditions for each learning stage; after the learner completes any learning stage, the learner is tested with the advanced test paper of that learning stage, and the test results are obtained; based on the test results, it is determined whether the advancement conditions are met; if the advancement conditions are met, the next learning stage of the knowledge advancement map is opened; if the advancement conditions are not met, the next learning stage of the knowledge advancement map is not opened.

[0083] The embodiment of the present invention pre-constructs a course knowledge graph. According to the target knowledge points, it can determine the relevant courses from the course knowledge graph, and automatically construct a knowledge base map based on the association between the relevant courses, so as to quickly and accurately construct a knowledge map suitable for course learning, and help learners clarify their learning goals and paths; further, according to at least one course attribute of the relevant course, the knowledge base map is divided into learning stages to obtain a knowledge advancement map containing multiple learning stages, which can provide learners with a systematic and staged learning navigation plan and improve learning efficiency.

[0084] In one embodiment of the present invention, an algorithm for dividing the knowledge base map into stages is also designed to divide the learning stages more reasonably. Figure 3 and Figure 4 , the process of dividing the learning stages in this embodiment is described in detail.

[0085] Figure 3 This is a knowledge base map generated for the knowledge point "Sorting Algorithm". Among them, K0-K9 represent: sorting algorithm, merge sort, insertion sort, selection sort, exchange sort, direct insertion sort, shell sort, heap sort, selection sort and bubble sort respectively.

[0086] (1) Obtain at least one learning difficulty threshold and sort them from small to large; in the knowledge base map, find the first relevant course on each fork from front to back whose learning difficulty is greater than the first learning difficulty threshold, as the first dividing point; divide all relevant courses before the first dividing point into a learning stage; starting from each first dividing point, find the first relevant course on each fork from front to back whose learning difficulty is greater than the next learning difficulty threshold, as the second dividing point; divide all relevant courses before the second dividing point into a learning stage; among them, if there is no relevant course on the fork with a learning difficulty greater than the corresponding learning difficulty threshold, then merge the fork and the previous relevant courses into the currently divided learning stage; repeat the above steps until the learning stage division of all learning difficulty thresholds is completed.

[0087] See also Figure 4 As shown in the figure, assume that the first learning difficulty threshold is N1. Follow each bifurcation to find related courses with a learning difficulty greater than N1. If K1, K3, and K4 are all greater than N1, and K2 is not greater than K1, continue searching along K2. If K5 and K6 are both greater than N1, then all related courses before K1, K3, K4, K5, and K6 (i.e., K0 and K2) are divided into one learning stage 1.

[0088] Learning Phase 2 builds upon the foundation of Learning Phase 1. Assume the second learning difficulty threshold is N2. Starting from the boundary between Learning Phases 1 and 2, follow each bifurcation to search for relevant courses with a learning difficulty greater than N2. If K7, K8, and K9 are all greater than N2, then all relevant courses before K7, K8, and K9 (i.e., K3 and K4) are grouped into Learning Phase 2. Since K1, K5, and K6 are not greater than N2 and have reached the end of the learning phase, they are directly merged into Learning Phase 2.

[0089] By analogy, the remaining K7, K8 and K9 are divided into a learning stage 3.

[0090] Because learning difficulty thresholds are arranged from smallest to largest, the difficulty of each learning stage increases sequentially, allowing learners to progress from easy to difficult, from shallow to deep, in a gradual, step-by-step process. Furthermore, it's generally assumed that earlier courses are less difficult than later ones. However, this may not always be the case, resulting in the appropriate learning stages. The learning stages are primarily a suggestion; learners can edit and modify the learning stages in the knowledge map based on their specific circumstances to create a learning plan that suits them.

[0091] (2) After completing the division of learning stages according to all learning difficulty thresholds, determine whether the centrality of each related course is greater than the preset centrality threshold; if the centrality of any related course is greater than the centrality threshold, then the related course and the previous related courses in the current learning stage will be divided into the previous learning stage.

[0092] The centrality of a related course is the number of related courses associated with the related course. The higher the centrality, the more important the course. In this embodiment, for related courses with a centrality greater than the centrality threshold, the related course and the previous related courses are divided into the previous learning stage to achieve the purpose of learning important courses first. Figure 4 In the example, assuming that the centrality of K4 is greater than the centrality threshold, K4 and the previous courses are promoted from learning stage 2 to learning stage 1.

[0093] (3) Based on the time cost of each relevant course in each learning stage, calculate the total time cost corresponding to each learning stage; if the total time cost corresponding to any learning stage is greater than the preset time cost threshold, then the learning stage is further divided into two learning stages.

[0094] This embodiment presets a time cost threshold, which is determined based on factors such as learning goals, learning plans, and the learner's energy and schedule. For example, the time cost threshold is set at 120 hours. The total time cost of each learning stage is compared with the threshold. If the total time cost of a learning stage exceeds the threshold, then the learning stage needs to be further divided to avoid excessive content and excessive learning time in a single stage.

[0095] For example, a target learning difficulty threshold can be determined based on the learning difficulty thresholds corresponding to the current learning phase and the previous learning phase. The target learning difficulty threshold lies between the learning difficulty thresholds corresponding to the current learning phase and the previous learning phase, such as the median of the learning difficulty thresholds corresponding to the current learning phase and the previous learning phase. Within the current learning phase, the first relevant course on each bifurcation whose learning difficulty exceeds the target learning difficulty threshold is searched from front to back, serving as the target demarcation point. Based on the target demarcation point, the current learning phase is further divided into two learning phases.

[0096] In some embodiments, the learning difficulty threshold may be determined by:

[0097] Obtain learners' historical learning data;

[0098] Evaluate the learner's learning ability time series based on historical learning data;

[0099] According to the learning ability time series, within the preset learning difficulty threshold value range, the learning difficulty threshold is determined by a pre-trained neural network model.

[0100] Learners' historical learning data includes multiple aspects of information. From the perspective of the learning process, it includes the duration of each study session, the time of study, and the completion of assignments and tests. From the perspective of learning outcomes, it covers test scores, assignment scores, and the level of mastery of knowledge points. On the learning platform, the system can record learners' learning behaviors in different courses, the accuracy rate of completing exercises, and other data. This data can comprehensively reflect the learner's learning process and performance.

[0101] A learning ability time series refers to how a learner's learning ability changes over time. Learning ability is assessed through analysis of historical learning data. For example, statistical methods or specific assessment models can be used to quantify learning ability based on changes in test scores, the speed and quality of assignment completion, and other data at different time points. For example, if a learner's math course completion accuracy improves and their test scores gradually rise over a certain period of time, it can be considered that their math learning ability is on an upward trend during this period. Arranging learning ability at different time points creates a learning ability time series. This time series can help understand the dynamic changes in a learner's learning ability and identify the characteristics and trends of their learning ability at different stages.

[0102] Based on a time series of learning ability, data related to a learner's learning ability is input into a pre-trained neural network model. Based on the input data and learned patterns and regularities, the model determines a learning difficulty threshold appropriate for the learner within a preset range of learning difficulty thresholds. For example, if a learner's learning ability time series shows a gradual increase in learning ability, the neural network model may select a relatively high learning difficulty threshold within the range and recommend more challenging learning content. Conversely, if learning ability is declining, the model may select a lower difficulty threshold to ensure that the learner gradually regains confidence and ability in learning. This determined learning difficulty threshold can better adapt to the learner's actual learning ability and improve learning outcomes.

[0103] It should be understood that the order of execution of the steps in the above embodiments does not necessarily mean the order of execution. The order of execution of each process should be determined by its function and internal logic, and should not constitute any limitation on the implementation process of the embodiments of the present invention.

[0104] The embodiments described above are only used to illustrate the technical solutions of the present invention, rather than to limit the same. Although the present invention has been described in detail with reference to the aforementioned embodiments, those skilled in the art should understand that they can still modify the technical solutions described in the aforementioned embodiments, or make equivalent replacements for some of the technical features therein. These modifications or replacements do not deviate the essence of the corresponding technical solutions from the spirit and scope of the technical solutions of the various embodiments of the present invention, and should all be included in the scope of protection of the present invention.

Claims

1. A method for constructing a knowledge advancement map, characterized in that: include: Acquire target knowledge points; According to the target knowledge point, determine the relevant courses and the relationship between the relevant courses from the pre-built course knowledge map; Constructing a knowledge base map based on the relevant courses and the association relationships; According to at least one preset course attribute of the relevant course, the knowledge base map is divided into learning stages to obtain a knowledge advancement map including multiple learning stages.

2. The method for constructing a knowledge advancement map according to claim 1, wherein: The association relationship includes: first repair and subsequent repair; Accordingly, the knowledge base map is constructed based on the relevant courses and the association relationships, including: According to the prerequisite and successor relationships between the related courses, arrows are connected to the related courses to obtain a tree-like learning route for the related courses; Based on the tree-like learning route, a knowledge base map is constructed.

3. The method for constructing a knowledge advancement map according to claim 2, wherein: The preset course attributes include: learning difficulty; Accordingly, the step of dividing the knowledge base map into stages according to at least one preset course attribute of the relevant course includes: Obtain at least one learning difficulty threshold and sort them from small to large; In the knowledge base map, searching from front to back for the first relevant course on each bifurcation whose learning difficulty is greater than a first learning difficulty threshold as a first dividing point; dividing all relevant courses before the first dividing point into a learning stage; Starting from each first dividing point, find the first relevant course on each bifurcation whose learning difficulty is greater than the next learning difficulty threshold from the front to the back, and use it as the second dividing point; divide all relevant courses before the second dividing point into one learning stage; If there is no related course on the fork with a learning difficulty greater than the corresponding learning difficulty threshold, then the fork and all previous related courses will be incorporated into the current learning stage; Repeat the above steps until the learning stages for all learning difficulty thresholds are divided.

4. The method for constructing a knowledge advancement map according to claim 3, wherein: The preset course attributes also include: centrality; the centrality of the related course is: the number of related courses associated with the related course; Accordingly, the step of dividing the knowledge base map into stages according to at least one preset course attribute of the relevant course further includes: After completing the division of learning stages according to all learning difficulty thresholds, determine whether the centrality of each relevant course is greater than the preset centrality threshold; If the centrality of any relevant course is greater than the centrality threshold, the relevant course and the previous relevant courses in the current learning stage will be classified into the previous learning stage.

5. The method for constructing a knowledge advancement map according to claim 3, wherein: The preset course attributes also include: time cost; Accordingly, the step of dividing the knowledge base map into learning stages according to at least one preset course attribute of the relevant course further includes: Calculate the total time cost for each learning stage based on the time cost of each relevant course in each learning stage; If the total time cost corresponding to any learning stage is greater than the preset time cost threshold, the learning stage is further divided into two learning stages.

6. The method for constructing a knowledge advancement map according to claim 5, wherein: The learning phase is further divided into two learning phases, including: Determining a target learning difficulty threshold based on the learning difficulty thresholds corresponding to the current learning stage and the previous learning stage; wherein the target learning difficulty threshold is between the learning difficulty thresholds corresponding to the current learning stage and the previous learning stage; In this learning phase, the first relevant course with a learning difficulty greater than the target learning difficulty threshold is searched from front to back on each bifurcation as the target dividing point; Based on the target dividing point, the learning phase is further divided into two learning phases.

7. The method for constructing a knowledge advancement map according to claim 3, wherein: The obtaining of at least one learning difficulty threshold comprises: Obtain learners' historical learning data; evaluating the learner's learning ability time series based on the historical learning data; According to the learning ability time series, the learning difficulty threshold is determined within a preset learning difficulty threshold value range through a pre-trained neural network model.

8. The method for constructing a knowledge advancement map according to any one of claims 1 to 7, wherein: After obtaining the knowledge advancement map including multiple learning stages, the method further includes: Set advanced examination papers and conditions for each learning stage; After the learner completes any learning stage, the learner is tested through the advanced test paper of the learning stage and the test results are obtained; Determining whether the advancement conditions are met based on the test results; If the advancement condition is met, the next learning stage of the knowledge advancement map is opened; if the advancement condition is not met, the next learning stage of the knowledge advancement map is not opened.

9. The method for constructing a knowledge advancement map according to any one of claims 1 to 7, wherein: The method further comprises: Access to multimodal course resources; Convert multimodal course resources into structured text data and extract entities from the text data to obtain corresponding knowledge points; Conduct course association mining on knowledge points to construct the course knowledge graph.

10. The method for constructing a knowledge advancement map according to claim 9, wherein: The obtaining of multimodal course resources includes: obtaining multimodal course resources from a website by using crawler technology.

Images