Intelligent learning path pushing method and device based on knowledge tree, equipment and medium

Abstract

The invention provides a learning path intelligent pushing method based on a knowledge tree, and the method specifically comprises the steps: constructing a multi-dimensional structure knowledge tree, each node of the knowledge tree representing a knowledge point, and each knowledge point having a plurality of father nodes or child nodes; user data are collected, a multi-modal user portrait is constructed, a learning path is generated according to the user portrait and the knowledge tree, and the learning path comprises a plurality of associated knowledge points and association relationships; according to the current knowledge point of the learning path, the corresponding knowledge point learning content or knowledge point question is pushed, the constructed multi-dimensional structure knowledge tree improves the correlation of the knowledge points, the learning path is pushed based on the user portrait, the personalized learning requirement of the user is met, and the learning efficiency of the user is improved. The invention further provides an intelligent learning path pushing device based on the knowledge tree, computer equipment and a readable storage medium.

Description

Technical Field

[0001] The present invention relates to the field of intelligent assisted learning technology, and more specifically, to a method, device, computer equipment and readable storage medium for intelligently pushing learning paths based on a knowledge tree. Background Art

[0002] With the development of science and technology, the application of computer technology is becoming more and more extensive, and intelligent assisted learning based on computing devices is gradually emerging. Users use learning platforms or systems to achieve intelligent assisted learning through devices such as computers, tablets or mobile phones, which can improve the efficiency of independent learning. In existing learning platforms or systems, static knowledge trees or linear lists of knowledge points are usually used to display learning content. Knowledge points are displayed through a fixed hierarchical structure. The correlation between knowledge points is weak, and it is often impossible to effectively manage a large number of knowledge points. Accordingly, existing assisted learning plans learning paths based on knowledge graphs and pushes learning content to users according to preset rules. However, the path planning and push mode are fixed and cannot distinguish and meet the personalized learning needs of users. The intelligent question bank is not very intelligent, the assisted learning is not very intelligent, and the user experience is poor. There is a need to propose improved technical solutions. Summary of the Invention

[0003] In view of the above, the present invention aims to solve at least one of the technical problems existing in the prior art. To this end, the present invention proposes a method, device, computer equipment and readable storage medium for intelligent push of learning paths based on a knowledge tree. By constructing a knowledge tree with a multi-dimensional structure, collecting user data to construct a user portrait and generating a learning path accordingly, and then pushing learning content or questions, the constructed multi-dimensional knowledge point map realizes the multi-dimensional association of knowledge points, improves the relevance of knowledge points, and thus can improve the effectiveness of knowledge push. The learning path is generated according to the user portrait constructed by user data, which improves the pertinence of the pushed content and further improves the effectiveness of knowledge push. The intelligent push method has a simple process and high efficiency.

[0004] To this end, in a first aspect, an embodiment of the present invention provides a method for intelligently pushing a learning path based on a knowledge tree, the method specifically comprising:

[0005] Construct a multi-dimensional knowledge tree, where each node represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes;

[0006] Collect user data and build multimodal user profiles. Generate learning paths based on user profiles and knowledge trees. The learning paths include multiple related knowledge points and relationships.

[0007] According to the current knowledge point of the learning path, push the corresponding knowledge point learning content or knowledge point questions.

[0008] Preferably, the constructing of a multi-dimensional structured knowledge tree specifically includes:

[0009] Construct a multi-dimensional structured knowledge tree based on the imported knowledge point graph; and / or,

[0010] Extracting knowledge point text features based on the pre-trained SciBERT model, calculating the cosine similarity between knowledge points, generating associated edges, and constructing a multi-dimensional structured knowledge tree based on the knowledge points and associated edges; and / or,

[0011] Modify the hierarchical position of knowledge points and establish or modify the relationship between knowledge points according to user operation instructions.

[0012] Preferably, the constructing of the multi-dimensional structure knowledge tree further includes:

[0013] Analyze the semantic similarity between knowledge points based on the Graph Attention Network (GAT), build a real-time feedback reinforcement learning model (DQN algorithm), and dynamically adjust the association weights of knowledge points based on user learning results; and / or,

[0014] Determine that when the user's learning stay time at a knowledge point exceeds a threshold, the associated edge weight of the corresponding knowledge point is strengthened.

[0015] Preferably, the determination that when the user's study stay time at a knowledge point exceeds a threshold value, the associated edge weight enhancement of the corresponding knowledge point is triggered specifically includes: determining that when the user's study stay time at a knowledge point exceeds a threshold value, recalculating the associated weight of the associated edge of the knowledge point according to the associated weight calculation formula, and updating the multidimensional knowledge tree structure. The associated weight calculation formula is:

[0016]

[0017] Among them, S ij is the semantic similarity, T u,i is the length of time that user u stays at knowledge point i, α is the first preset weight coefficient of semantic similarity, β is the second preset weight coefficient of user behavior data, ∑ u T u,i is the sum of the residence time of all users u at knowledge point i, and max(T) is the maximum residence time of all knowledge points.

[0018] Preferably, the collecting of user data and constructing a multimodal user profile, and generating a learning path based on the user profile and the knowledge tree, specifically includes:

[0019] Analyze user-annotated "confusion points" text based on natural language processing (NLP), associate weak links in knowledge points, and generate corresponding learning paths; and / or,

[0020] Collecting environmental data and determining the form of content to be pushed based on the environmental data, the environmental data including device type and / or network latency; and / or,

[0021] Based on the Bayesian optimization algorithm, the optimal weights of "consolidating weak points" and "exploring new knowledge points" are determined, and the corresponding learning path is generated.

[0022] Preferably, the method further comprises:

[0023] Based on the user's mastery of knowledge points, choose to associate knowledge points upward or downward, and update the push learning path.

[0024] Preferably, the method of selecting upward or downward associated knowledge points based on the user's mastery of knowledge points and updating and pushing learning paths specifically includes:

[0025] Based on the error rate of users' knowledge point answers, the user's knowledge point mastery is determined, and comparative exercises are generated and pushed based on the knowledge points with low mastery, or high-level application cases are generated and pushed based on the knowledge points with high mastery.

[0026] In a second aspect, an embodiment of the present invention further provides a device for intelligently pushing learning paths based on a knowledge tree, the device specifically comprising:

[0027] The knowledge tree construction module is used to construct a multi-dimensional structured knowledge tree. Each node of the knowledge tree represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes.

[0028] The learning path generation module is used to collect user data and build a multimodal user profile. Based on the user profile and knowledge tree, a learning path is generated. The learning path includes multiple related knowledge points and related relationships.

[0029] The knowledge push module is used to push the corresponding knowledge point learning content or knowledge point questions based on the current knowledge point of the learning path.

[0030] In a third aspect, an embodiment of the present invention further provides a computer device comprising: a memory and a processor and a computer program stored in the memory. When the computer program is executed on the processor, the method for intelligently pushing learning paths based on a knowledge tree as described in the first aspect is implemented.

[0031] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for intelligently pushing learning paths based on a knowledge tree as described in the first aspect is implemented.

[0032] The method for intelligently pushing learning paths based on a knowledge tree provided by an embodiment of the present invention establishes associations between knowledge points by constructing a knowledge tree with a multi-dimensional structure. The method is conducive to forming a learning path with compound learning rules based on knowledge points and associations. Data is further collected for users, and user portraits are constructed based on the collected user data, thereby generating personalized learning paths and pushing them accordingly. The learning paths generated based on user portraits and multi-dimensional knowledge trees not only conform to the learning rules of compound knowledge points but also meet the personalized learning needs of users, have good auxiliary learning effects, and provide users with a good user experience. BRIEF DESCRIPTION OF THE DRAWINGS

[0033] Figure 1 A flowchart of a method for intelligently pushing learning paths based on a knowledge tree according to an embodiment of the present invention;

[0034] Figure 2 A schematic diagram of the framework structure of a knowledge tree-based learning path intelligent push device provided by an embodiment of the present invention;

[0035] Figure 3 A schematic diagram of the framework structure of a computer device provided in an embodiment of the present invention. DETAILED DESCRIPTION

[0036] The following describes embodiments of the present invention in detail, examples of which are shown in the accompanying drawings, wherein the same or similar reference numerals throughout represent the same or similar elements or elements having the same or similar functions. The embodiments described below with reference to the accompanying drawings are exemplary and are intended to be used to explain the present invention, and are not to be construed as limiting the present invention.

[0037] The disclosure below provides many different embodiments or examples for realizing different structures of the present invention. In order to simplify the disclosure of the present invention, the components and settings of specific examples are described below. Of course, they are merely examples and are not intended to limit the present invention. In addition, the present invention may repeat reference numbers and / or letters in different examples. This repetition is for the purpose of simplicity and clarity and does not in itself indicate the relationship between the various embodiments and / or settings discussed. In addition, the present invention provides examples of various specific processes and materials, but those skilled in the art will appreciate the applicability of other processes and / or the use of other materials.

[0038] Please refer to Figure 1 The present invention aims to provide a method for intelligently pushing learning paths based on a knowledge tree, which is used in an online learning platform or learning management system to provide path planning and corresponding knowledge content push for users to help them improve their learning efficiency. The method specifically includes the following steps:

[0039] S10. Construct a multi-dimensional knowledge tree, where each node of the knowledge tree represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes;

[0040] S20: Collect user data and build a multimodal user profile, and generate a learning path based on the user profile and the knowledge tree. The learning path includes multiple related knowledge points and related relationships.

[0041] S30. Push corresponding knowledge point learning content or knowledge point questions based on the current knowledge point in the learning path.

[0042] In this embodiment, a graphical multidimensional structure is constructed to represent the relationship between knowledge points. Each knowledge point can have multiple parent nodes or child nodes, and can be labeled with different association types (such as "Basic", "Advanced", "Application"), so that the association relationship between knowledge points can be clearly displayed.

[0043] Furthermore, the step S10 of constructing a multi-dimensional structured knowledge tree specifically includes: constructing a multi-dimensional structured knowledge tree based on the imported knowledge point graph. The system can directly import the knowledge point graph as the basis for constructing the knowledge tree.

[0044] As you can understand, building a knowledge tree can also involve: extracting knowledge point text features based on the pre-trained SciBERT model, calculating the cosine similarity between knowledge points, generating associated edges, and constructing a multi-dimensional structured knowledge tree based on the knowledge points and associated edges. Using semantic associations, we can also mine the associations between knowledge points and construct a corresponding knowledge tree.

[0045] It is understandable that the construction of the knowledge tree can also: modify the hierarchical position of knowledge points and establish or modify the association relationship between knowledge points according to user operation instructions.

[0046] In order to handle a large collection of knowledge points, a flexible management interface based on graphical interaction is adopted. Administrators can manage, edit, and delete knowledge points through a visual interface, and support dynamic adjustment of the relationship between knowledge points. The graphical interface can easily manage the multi-dimensional knowledge tree structure through dragging, connecting, etc.

[0047] Each node in the knowledge tree graphical interface represents a knowledge point. The size and color of the node reflect the mastery level of that knowledge point. For example, knowledge points with higher mastery levels have larger nodes and darker colors. The system supports dynamic dragging and hierarchical adjustment. Administrators can easily modify node properties and hierarchical relationships by clicking and dragging nodes, or using the right-click menu.

[0048] In addition, in the pop-up window of each knowledge point node, administrators can view and adjust the detailed information of the knowledge point, and dynamically set the parent-child relationship, difficulty level, and recommended question types for the knowledge point. The system can also update the mastery level of each knowledge point in real time based on the user's answer results and push related questions.

[0049] Furthermore, the step S10 of constructing a multi-dimensional structure knowledge tree further includes:

[0050] Based on the Graph Attention Network (GAT), the semantic similarity between knowledge points is analyzed, and a real-time feedback reinforcement learning model (DQN algorithm) is constructed to dynamically adjust the association weights of knowledge points based on user learning outcomes. Accordingly, administrators can drag and drop cross-disciplinary knowledge points on an interactive canvas, and the system automatically generates a heat map of association strength.

[0051] Furthermore, the step S10 of constructing a multi-dimensional structure knowledge tree further includes:

[0052] Determine that when the user's learning stay time at a knowledge point exceeds a threshold, the associated edge weight of the corresponding knowledge point is strengthened.

[0053] Furthermore, the method of determining that when the user's study stay time at a knowledge point exceeds a threshold, triggering the corresponding knowledge point's associated edge weight enhancement specifically includes: determining that when the user's study stay time at a knowledge point exceeds a threshold, recalculating the associated weight of the associated edge of the knowledge point according to an associated weight calculation formula, and updating the multidimensional knowledge tree structure. The associated weight calculation formula is:

[0054]

[0055] Among them, S ij is the semantic similarity, T u,i is the length of time that user u stays at knowledge point i, α is the first preset weight coefficient of semantic similarity, β is the second preset weight coefficient of user behavior data, ∑ u T u,i is the sum of the residence time of all users u at knowledge point i, and max(T) is the maximum residence time of all knowledge points.

[0056] For example, when a user stays on a certain knowledge point for more than a preset threshold (e.g., 300 seconds), the weight reinforcement mechanism is triggered. The system recalculates the association weights of this knowledge point with other knowledge points based on the formula and updates the knowledge tree structure in real time. For example, if user A stays on the knowledge point "Trigonometric Functions" significantly longer than the average, then the ∑ u T u,i The term increases, resulting in the weight W of related knowledge points such as "vector operation" ij Improvement, relevant knowledge content or topics will be pushed first in subsequent recommendation paths.

[0057] Furthermore, the step S20 collects user data and constructs a multimodal user profile, and generates a learning path based on the user profile and the knowledge tree, specifically including:

[0058] Based on natural language processing (NLP), the "confusion point" text annotated by users is analyzed, the weak links of knowledge points are associated, and the corresponding learning path is generated.

[0059] It is understood that step S20 may further include collecting environmental data and determining the form of push content based on the environmental data, where the environmental data includes device type and / or network latency. The push content may include a video explanation or a text summary. For example, if the environmental data indicates a smooth network status on a computer device, a video explanation may be used for push content, while if the environmental data indicates a certain network latency on a mobile device, a text summary may be used for push content.

[0060] It is understood that step S20 may also include determining the optimal weights between "strengthening weak points" and "exploring new knowledge points" based on a Bayesian optimization algorithm, and generating a corresponding learning path. The Bayesian optimization algorithm is a well-known optimization algorithm in the field of artificial intelligence, and its specific implementation details are not detailed here.

[0061] Furthermore, the method further comprises the steps of:

[0062] S40. According to the user's mastery of knowledge points, select upward or downward associated knowledge points and update the push learning path.

[0063] Furthermore, the step S40 selects upward or downward associated knowledge points based on the user's knowledge point mastery, and updates the pushed learning path, specifically including:

[0064] Based on the error rate of users' knowledge point answers, the user's knowledge point mastery is determined, and comparative exercises are generated and pushed based on the knowledge points with low mastery, or high-level application cases are generated and pushed based on the knowledge points with high mastery.

[0065] For example, if user A has a high error rate in answering questions on the "Trigonometric Functions" knowledge point and has answered fewer than 30 questions in total, the system will automatically associate the "Vector Operations" knowledge point with basic knowledge content or comparative exercises to reinforce their learning. If the user correctly answers three questions in a row, the "Unlock Advanced Application Cases" branch will be triggered, which will push advanced knowledge content or questions.

[0066] Please refer to Figure 2 In a second aspect, an embodiment of the present invention further provides a device 100 for intelligently pushing a learning path based on a knowledge tree, the device specifically comprising:

[0067] The knowledge tree construction module 10 is used to construct a multi-dimensional structured knowledge tree, where each node of the knowledge tree represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes;

[0068] The learning path generation module 20 is used to collect user data and build a multimodal user profile, and generate a learning path based on the user profile and the knowledge tree. The learning path includes multiple related knowledge points and related relationships;

[0069] The knowledge push module 30 is used to push corresponding knowledge point learning content or knowledge point questions based on the current knowledge point in the learning path.

[0070] Please refer to Figure 3 In a third aspect, an embodiment of the present invention further provides a computer device 200, comprising: a memory 201, a processor 202, and a computer program 203 stored on the memory 201. When the computer program 203 is executed on the processor 202, the method for intelligently pushing learning paths based on the knowledge tree as described in the first aspect is implemented.

[0071] The computer device 200 may be a desktop computer, a notebook computer, a PDA, a cloud server, or other computing devices. The computer device 200 may include, but is not limited to, a processor 202 and a memory 201. Those skilled in the art will appreciate that Figure 3 This is merely an example of the computer device 200 and does not constitute a limitation on the computer device 200 . The computer device 200 may include more or fewer components than shown in the figure, or a combination of certain components, or different components. For example, the computer device 200 may also include input and output devices, network access devices, etc.

[0072] In some embodiments, the memory 201 may be an internal storage unit of the computer device 200, such as a hard disk or memory of the computer device 3. In other embodiments, the memory 201 may also be an external storage device of the computer device 200, such as a plug-in hard disk, a smart memory card (SmartMedia Card, SMC), a secure digital (Secure Digital, SD) card, a flash card, etc. equipped on the computer device 200. Furthermore, the memory 201 may also include both an internal storage unit of the computer device 200 and an external storage device. The memory 201 is used to store operating devices, application programs, boot loaders (Boot Loader), data and other programs, such as the program code of the computer program. The memory 201 may also be used to temporarily store data that has been output or is to be output.

[0073] The processor 202 may be a central processing unit (CPU), or other general-purpose processors, digital signal processors (DSP), application-specific integrated circuits (ASIC), field-programmable gate arrays (FPGA), or other programmable logic devices, discrete gate or transistor logic devices, or discrete hardware components. A general-purpose processor may be a microprocessor or any conventional processor.

[0074] In a fourth aspect, an embodiment of the present invention further provides a computer-readable storage medium having a computer program stored thereon. When the computer program is executed by a processor, the method for intelligently pushing learning paths based on a knowledge tree as described in the first aspect is implemented.

[0075] In this embodiment, if the integrated unit is implemented as a software functional unit and sold or used as an independent product, it can be stored in a computer-readable storage medium. Based on this understanding, the present application implements all or part of the process of the above-mentioned method embodiment by instructing the relevant hardware through a computer program. The computer program can be stored in a computer-readable storage medium. When the computer program is executed by a processor, it can implement the steps of each of the above-mentioned method embodiments. The computer program includes computer program code, which can be in source code form, object code form, executable file, or some intermediate form. The computer-readable medium can at least include: any entity or device capable of carrying computer program code to the camera / terminal device, recording medium, computer memory, read-only memory (ROM), random access memory (RAM), electric carrier signal, telecommunication signal, and software distribution medium. For example, a USB flash drive, mobile hard drive, magnetic disk, or optical disk. In some jurisdictions, based on legislation and patent practice, computer-readable media cannot be electric carrier signals or telecommunication signals.

[0076] The method for intelligently pushing learning paths based on a knowledge tree provided by an embodiment of the present invention establishes associations between knowledge points by constructing a knowledge tree with a multi-dimensional structure. The method is conducive to forming a learning path with compound learning rules based on knowledge points and associations. Data is further collected for users, and user portraits are constructed based on the collected user data, thereby generating personalized learning paths and pushing them accordingly. The learning paths generated based on user portraits and multi-dimensional knowledge trees not only conform to the learning rules of compound knowledge points but also meet the personalized learning needs of users, have good auxiliary learning effects, and provide users with a good user experience.

[0077] In the description of this specification, the reference terms "one embodiment", "some embodiments", "examples", "specific examples", or "some examples" mean that the specific features, structures, materials or characteristics described in conjunction with the embodiment or example are included in at least one embodiment or example of the present invention. In this specification, the schematic expressions of the above terms do not necessarily refer to the same embodiment or example. Moreover, the specific features, structures, materials or characteristics described can be combined in any one or more embodiments or examples in a suitable manner. In addition, those skilled in the art can combine and combine different embodiments or examples described in this specification and features of different embodiments or examples without contradiction.

[0078] 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 the embodiments without departing from the principles and spirit of the invention, and that the scope of the invention is defined by the claims and their equivalents.

Claims

1. A method for intelligently pushing learning paths based on a knowledge tree, characterized in that: The method specifically includes: Construct a multi-dimensional knowledge tree, where each node represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes; Collect user data and build multimodal user profiles. Generate learning paths based on user profiles and knowledge trees. The learning paths include multiple related knowledge points and relationships. According to the current knowledge point of the learning path, push the corresponding knowledge point learning content or knowledge point questions.

2. The method for intelligently pushing learning paths based on a knowledge tree according to claim 1, characterized in that: The construction of the multi-dimensional structure knowledge tree specifically includes: Construct a multi-dimensional structured knowledge tree based on the imported knowledge point graph; and / or, Extracting knowledge point text features based on the pre-trained SciBERT model, calculating the cosine similarity between knowledge points, generating associated edges, and constructing a multi-dimensional structured knowledge tree based on the knowledge points and associated edges; and / or, Modify the hierarchical position of knowledge points and establish or modify the relationship between knowledge points according to user operation instructions.

3. The method for intelligently pushing learning paths based on a knowledge tree according to claim 2, characterized in that: The constructing of the multi-dimensional structure knowledge tree further includes: Analyze the semantic similarity between knowledge points based on the Graph Attention Network (GAT), build a real-time feedback reinforcement learning model (DQN algorithm), and dynamically adjust the association weights of knowledge points based on user learning results; and / or, Determine that when the user's learning stay time at a knowledge point exceeds a threshold, the associated edge weight of the corresponding knowledge point is strengthened.

4. The method for intelligently pushing learning paths based on a knowledge tree according to claim 3, characterized in that: The method of determining that when a user's study stay time at a knowledge point exceeds a threshold, triggering the corresponding knowledge point's associated edge weight enhancement specifically includes: determining that when a user's study stay time at a knowledge point exceeds a threshold, recalculating the associated weight of the associated edge of the knowledge point according to an associated weight calculation formula, and updating the multidimensional knowledge tree structure. The associated weight calculation formula is: Among them, S ij is the semantic similarity, T u,i is the length of time that user u stays at knowledge point i, α is the first preset weight coefficient of semantic similarity, β is the second preset weight coefficient of user behavior data, ∑ u T u,i is the sum of the residence time of all users u at knowledge point i, and max(T) is the maximum residence time of all knowledge points.

5. The method for intelligently pushing learning paths based on a knowledge tree according to claim 1, characterized in that: The process of collecting user data and constructing a multimodal user profile, and generating a learning path based on the user profile and the knowledge tree, specifically includes: Analyze user-annotated "confusion points" text based on natural language processing (NLP), associate weak links in knowledge points, and generate corresponding learning paths; and / or, Collecting environmental data and determining the form of content to be pushed based on the environmental data, the environmental data including device type and / or network latency; and / or, Based on the Bayesian optimization algorithm, the optimal weights of "consolidating weak points" and "exploring new knowledge points" are determined, and the corresponding learning path is generated.

6. The method for intelligently pushing learning paths based on a knowledge tree according to claim 1, characterized in that: The method further comprises: Based on the user's mastery of knowledge points, choose to associate knowledge points upward or downward, and update the push learning path.

7. The method for intelligently pushing learning paths based on a knowledge tree according to claim 6, characterized in that: Based on the user's mastery of knowledge points, the user selects upward or downward related knowledge points and updates the learning path, specifically including: Based on the error rate of users' knowledge point answers, the user's knowledge point mastery is determined, and comparative exercises are generated and pushed based on the knowledge points with low mastery, or high-level application cases are generated and pushed based on the knowledge points with high mastery.

8. A device for intelligently pushing learning paths based on a knowledge tree, characterized in that: The device specifically includes: The knowledge tree construction module is used to construct a multi-dimensional structured knowledge tree. Each node of the knowledge tree represents a knowledge point, and each knowledge point has multiple parent nodes or child nodes. The learning path generation module is used to collect user data and build a multimodal user profile. Based on the user profile and knowledge tree, a learning path is generated. The learning path includes multiple related knowledge points and related relationships. The knowledge push module is used to push the corresponding knowledge point learning content or knowledge point questions based on the current knowledge point of the learning path.

9. A computer device, characterized in that: include: A memory, a processor, and a computer program stored in the memory, which, when executed on the processor, implements the method for intelligently pushing a learning path based on a knowledge tree as claimed in any one of claims 1 to 8.

10. A computer-readable storage medium, characterized in that A computer program is stored thereon, and when the computer program is executed by a processor, the method for intelligently pushing a learning path based on a knowledge tree as claimed in any one of claims 1 to 8 is implemented.

Images