An AI agent-based companion learning system

Abstract

The application discloses an AI intelligent agent-based accompanying learning system, and relates to the technical field of education, comprising a knowledge point learning grid module and a learning path generation module, wherein the knowledge point learning grid module is connected with the learning path generation module; the knowledge point learning grid module is used for generating attribute information of a knowledge point based on basic learning information, prerequisite knowledge information and correlation information, and constructing a knowledge graph corresponding to a knowledge point set based on the attribute information; the knowledge graph is mapped in a knowledge point learning grid corresponding to course material information to obtain a target knowledge point learning grid; the learning path generation module is used for generating a learning plan of a student in a target time period based on the knowledge point learning grid in the knowledge point learning grid module, and generating a learning path of the student based on the learning plan; and the knowledge point learning grid module is used for displaying the learning path generated by the learning path generation module to a student end through the knowledge point learning grid. The application can improve the learning efficiency of students.

Description

Technical Field

[0001] This application relates to the field of educational technology, and in particular to a learning companion system based on an AI intelligent agent. Background Technology

[0002] With the rapid development of online education, personalized learning systems have become an important tool for improving learning efficiency. However, most existing systems can only generate learning plans based on students' basic information and preset goals. While they clarify "what to learn," they cannot explain "why to learn these things" or "how the content is related." Students often only passively execute planned tasks, struggling to understand the inherent logic between knowledge points and the design intent of the learning path. This results in a lack of systematic understanding of the learning process, hindering efficiency improvement.

[0003] Knowledge graph technology, as a mainstream solution for structuring knowledge, has been introduced into adaptive learning systems, aiming to present the relationships between knowledge points through semantic networks. However, its effectiveness still faces significant challenges in practical applications.

[0004] Existing learning companion systems often rely on manual construction by experts or automatic data mining for their knowledge graphs. The former is highly subjective and lacks scalability, making it difficult to cover all implicit connections. While the latter can discover some data patterns, it lacks dynamic optimization of connection strength and continuous verification of teaching effectiveness. Furthermore, learning plans generated based on such graphs often simply transform static knowledge topologies directly into learning sequences, failing to clearly demonstrate the logical connections between knowledge points and the basis for path design to students. The presentation of learning plans by the learning companion system is merely a simple display of the generated results, causing the learning process to remain at the level of passively completing tasks. It fails to achieve deep learning and effective transfer through understanding the knowledge structure, and it also fails to improve learning efficiency by using the learning companion system. Summary of the Invention

[0005] In view of this, this application provides a learning companion system based on AI intelligent agents. The main purpose is to improve the technical problem that the existing learning companion systems simply present the generated learning plan to the student, which results in the learning process remaining at the level of passively completing tasks. They cannot achieve deep learning and effective transfer by understanding the knowledge structure, nor can they improve learning efficiency by using the learning companion system.

[0006] Firstly, this application provides a learning companion system based on an AI intelligent agent, including:

[0007] The knowledge point learning grid module and the learning path generation module are connected together.

[0008] The knowledge point learning grid module is used to determine the basic learning information of knowledge points in the knowledge point set corresponding to the course material information, as well as the prerequisite knowledge information and correlation information between knowledge points, based on the basic learning information, the prerequisite knowledge information and the correlation information; generate attribute information of knowledge points based on the basic learning information, the prerequisite knowledge information and the correlation information, and construct a knowledge graph corresponding to the knowledge point set based on the attribute information; map the knowledge graph in the knowledge point learning grid corresponding to the course material information to obtain the target knowledge point learning grid;

[0009] The learning path generation module is used to generate a student's learning plan for a target time period based on the knowledge point learning grid in the knowledge point learning grid module, generate the student's learning path based on the learning plan, and send the learning path to the knowledge point learning grid module.

[0010] The knowledge point learning grid module is used to display the learning path generated by the learning path generation module to the student terminal through the knowledge point learning grid; wherein, the target knowledge point learning grid is a learning grid that includes the attribute information of knowledge points and the relationship information between knowledge points.

[0011] Secondly, this application provides an electronic device, including the learning companion system described in the first aspect.

[0012] Using the above technical solution, this application provides an AI-based learning companion system, comprising: a knowledge point learning grid module and a learning path generation module, the knowledge point learning grid module being connected to the learning path generation module; the knowledge point learning grid module is used to determine the basic learning information of the knowledge points in the knowledge point set, as well as the prerequisite knowledge information and correlation information between the knowledge points, based on the knowledge point set corresponding to the course material information; generate attribute information of the knowledge points based on the basic learning information, prerequisite knowledge information, and correlation information, and construct a knowledge graph corresponding to the knowledge point set based on the attribute information; map the knowledge graph in the knowledge point learning grid corresponding to the course material information to obtain the target knowledge point learning grid; the learning path generation module is used to generate a student's learning plan within a target time period based on the knowledge point learning grid in the knowledge point learning grid module, and generate the student's learning path based on the learning plan, and send the learning path to the knowledge point learning grid module; the knowledge point learning grid module is used to display the learning path generated by the learning path generation module to the student end through the knowledge point learning grid; wherein, the target knowledge point learning grid is a learning grid that includes the attribute information of the knowledge points and the correlation information between the knowledge points. Compared with existing technologies, this application, through the knowledge point learning grid module in the learning companion system, can acquire course knowledge points and related information within the student's target time period. Combining basic learning, prerequisites, and relevance information, it constructs a knowledge graph, transforming scattered knowledge points into a structured knowledge network and clearly presenting the inherent connections between knowledge. Furthermore, by mapping the knowledge graph to an intuitive target knowledge point learning grid and sending the resulting knowledge graph to the learning path generation module, the learning path generation module can generate a learning plan based on the grid. The learning path is then displayed through the target knowledge point learning grid in the knowledge point learning grid module. This allows the learning companion system to accurately and clearly present the relationships between knowledge points to students through the learning path, enabling students to effectively understand the knowledge structure and achieve deep learning and transfer through the relationships between knowledge points represented by the learning path. Ultimately, this learning companion system can help students improve their learning efficiency. Attached Figure Description

[0013] The accompanying drawings, which are included to provide a further understanding of this disclosure and form part of this disclosure, illustrate exemplary embodiments of the present disclosure and are used to explain the disclosure, but do not constitute an undue limitation of the disclosure. In the drawings:

[0014] Figure 1 This diagram illustrates the structure of a learning companion system based on an AI agent, as provided in an embodiment of this disclosure.

[0015] Figure 2 This illustration shows a schematic diagram of a knowledge point learning grid provided in an embodiment of this application;

[0016] Figure 3 A schematic diagram of a directed edge knowledge graph provided in an embodiment of this application is shown;

[0017] Figure 4 A schematic diagram of an undirected edge knowledge graph provided in an embodiment of this application is shown;

[0018] Figure 5 A schematic diagram of a centrality analysis provided in an embodiment of this application is shown;

[0019] Figure 6 A schematic diagram of the structure of an electronic device provided in an embodiment of this disclosure is shown;

[0020] exist Figure 1 middle:

[0021] 1-Knowledge Point Learning Grid Module;

[0022] 2-Learning path generation module;

[0023] 3-Learning Behavior Collection Module;

[0024] 4-Mastery Analysis Module;

[0025] 5-Learning Intent Analysis Module;

[0026] 6-Knowledge Point Location Module;

[0027] 7-Knowledge Point Status Analysis Module;

[0028] 8. Learning materials recommendation module. Detailed Implementation

[0029] In the description of this disclosure, it should be understood that the terms "center," "longitudinal," "lateral," "length," "width," "thickness," "upper," "lower," "front," "rear," "left," "right," "vertical," "horizontal," "top," "bottom," "inner," "outer," "clockwise," and "counterclockwise," etc., indicate the orientation or positional relationship based on the orientation or positional relationship shown in the accompanying drawings, and are only for the convenience of describing this disclosure and simplifying the description, and are not intended to indicate or imply that the device or element referred to must have a specific orientation, or be constructed and operated in a specific orientation, and therefore should not be construed as a limitation of this disclosure.

[0030] Furthermore, the terms "first" and "second" are used for descriptive purposes only and should not be construed as indicating or implying relative importance or implicitly specifying the number of technical features indicated. Thus, a feature defined as "first" or "second" may explicitly or implicitly include one or more of that feature. In the description of this disclosure, "a plurality of" means two or more, unless otherwise expressly specified.

[0031] In this disclosure, unless otherwise expressly specified and limited, the terms "installation," "connection," "linking," "fixing," etc., should be interpreted broadly. For example, they can refer to a fixed connection, a detachable connection, or an integral connection; they can refer to a mechanical connection or an electrical connection; they can refer to a direct connection or an indirect connection through an intermediate medium; and they can refer to the internal connection between two components. Those skilled in the art can understand the specific meaning of the above terms in this disclosure according to the specific circumstances.

[0032] The present disclosure will be described in detail below with reference to the accompanying drawings and embodiments. It should be noted that, unless otherwise specified, the embodiments and features in the embodiments of the present disclosure can be combined with each other.

[0033] The following is combined with Figure 1 This disclosure describes an AI-based learning companion system according to some embodiments.

[0034] This disclosure provides an AI-based learning companion system, such as... Figure 1 As shown, it includes: a knowledge point learning grid module 1 and a learning path generation module 2, which are connected. The knowledge point learning grid module 1 is used to determine the basic learning information of the knowledge points in the knowledge point set corresponding to the course material information, as well as the prerequisite knowledge information and correlation information between the knowledge points. Based on the basic learning information, prerequisite knowledge information and correlation information, it generates the attribute information of the knowledge points and constructs the knowledge graph corresponding to the knowledge point set based on the attribute information. It maps the knowledge graph in the knowledge point learning grid corresponding to the course material information to obtain the target knowledge point learning grid. The learning path generation module 2 is used to generate the student's learning plan within the target time period based on the knowledge point learning grid in the knowledge point learning grid module, and generate the student's learning path based on the learning plan, and send the learning path to the knowledge point learning grid module 1. The knowledge point learning grid module 1 is used to display the learning path generated by the learning path generation module 2 to the student through the knowledge point learning grid. The target knowledge point learning grid is a learning grid that includes the attribute information of the knowledge points and the correlation information between the knowledge points.

[0035] In this embodiment of the application, the learning companion system can be the backend system corresponding to the AI ​​learning assistant installed on the learning tablet. The learning companion system can store data such as students' basic information, learning records, and course materials.

[0036] In this embodiment of the application, the target time period can be any learning cycle set by the student, such as a week, a month, or a semester. The specific target time period can be selected by the student according to their learning needs or set by default by the system in conjunction with the teaching progress.

[0037] For the embodiments of this application, course information may include relevant learning materials such as textbook content, teaching syllabus, online course videos, and exercise sets that students need to learn within the corresponding time period.

[0038] In the embodiments of this application, the knowledge point set can be a set of learning units extracted from course material information. Each unit can correspond to a specific knowledge content, and multiple knowledge points together constitute the knowledge point set of the corresponding course material information.

[0039] In the embodiments of this application, basic learning information may be basic attribute information related to the learning of knowledge points. Specifically, basic learning information may include the difficulty, importance, learning time, and chapter to which the knowledge point belongs.

[0040] In this embodiment of the application, the prerequisite knowledge information may be related information about other knowledge points that need to be mastered in advance before learning the knowledge point.

[0041] In the embodiments of this application, the relevance information can be the degree of association between different knowledge points. The relevance information can be used to identify whether there is a connection or complementarity between different knowledge points in terms of content.

[0042] In this embodiment, students need to fill in basic information such as class, grade, name, age, and semester when logging into the learning companion system via a learning tablet. The learning companion system can generate a user ID based on this information. The user ID can be used to associate all the student's learning data. When it is necessary to generate a learning plan for a target time period, the knowledge point learning grid module 1 can first retrieve the course materials information for the corresponding semester from the resource library of the knowledge point learning grid module 1 based on the student's ID and the selected target time period.

[0043] In this embodiment of the application, the knowledge point learning grid module 1 can use natural language processing (NLP) technology to perform structured analysis on the retrieved course material information. Specifically, it can analyze the content of the textbook catalog, teaching syllabus, curriculum standards, etc., identify the core concepts, theorems, skill points, etc., and then establish a hierarchical knowledge structure, that is, the breakdown from course to chapter to knowledge point, and finally obtain the set of knowledge points corresponding to the course material information within the target time period.

[0044] In this embodiment of the application, after determining the set of knowledge points, the system will further extract the basic learning information of each knowledge point. The difficulty of each knowledge point can be quantitatively evaluated by data such as the complexity of the content involved in the knowledge point and the average mastery time of students. The importance of each knowledge point can be determined by combining factors such as the requirements of the teaching syllabus and the proportion of the exam score. The learning time of each knowledge point can be estimated based on the amount of content and difficulty of the knowledge point. For example, each knowledge point requires about 45 minutes of learning time.

[0045] For example, the knowledge point learning grid module 1 can determine the prerequisite knowledge information between knowledge points by analyzing the content order in the teaching syllabus, the arrangement logic of textbook chapters, and the logical relationship between knowledge points; the knowledge point learning grid module 1 can determine the relevance information between knowledge points by analyzing the content similarity of knowledge points and the co-occurrence of knowledge points in practice questions.

[0046] In the embodiments of this application, attribute information can be a comprehensive description of various features of knowledge points. In addition to including basic learning information, prerequisite knowledge information and relevance information, it can also include related information such as association type and association strength derived from these information, which can comprehensively reflect the features of knowledge points and the association between knowledge points.

[0047] In the embodiments of this application, a knowledge graph can be a graph that displays knowledge points and the relationships between knowledge points in a graphical structure. A knowledge graph can include nodes representing knowledge points and edges representing the relationships between knowledge points. A knowledge graph can present the structure and logical relationships of a knowledge system through a visual structure.

[0048] In this embodiment, the knowledge point learning grid module 1 can generate attribute information of knowledge points based on the acquired basic learning information, prerequisite knowledge information and relevance information. It integrates the difficulty, importance, learning time and other contents in the basic learning information, the specific prerequisite knowledge points corresponding to the prerequisite knowledge information, and the related knowledge points and degree of association corresponding to the relevance information to form unique attribute information for each knowledge point. Based on the generated attribute information, a knowledge graph corresponding to the knowledge point set is constructed.

[0049] In this embodiment of the application, the knowledge point learning grid in the knowledge point learning grid module 1 can be a two-dimensional grid that presents knowledge points. Each cell in the knowledge point learning grid can correspond to a knowledge point, and the knowledge point learning grid can be used to intuitively display the distribution of knowledge points.

[0050] In this embodiment of the application, the target knowledge point learning grid in the knowledge point learning grid module 1 can be a grid formed by mapping the knowledge point nodes and the relationships between nodes in the knowledge graph to the knowledge point learning grid. The target knowledge point learning grid can include the cell corresponding to each knowledge point, the attribute information of the knowledge point, and the relationship information between the knowledge points.

[0051] In the embodiments of this application, the knowledge point learning grid module 1 can map the knowledge graph to the knowledge point learning grid corresponding to the course material information. The basic structure of the knowledge point learning grid can be determined first, and an appropriate number of cells can be divided according to the content volume and number of knowledge points of the course material information, with each cell corresponding to one knowledge point.

[0052] For example, in the process of mapping the knowledge graph in the knowledge point learning grid corresponding to the course material information in the knowledge point learning grid module 1, in order to maintain the topological relationship between knowledge points in the knowledge graph so that the connected nodes in the graph are as adjacent as possible in the grid, a force-directed algorithm can be used. The force-directed algorithm simulates physical forces (such as repulsive and attractive forces) to determine the position of the nodes. Of course, other similar graph layout algorithms can also be used, including but not limited to.

[0053] In some examples, since the layout generated by the force-directed algorithm is a continuous coordinate, the knowledge point learning grid module 1 can discretize the continuous coordinates onto the grid. Specifically, it can divide the two-dimensional space into a predefined grid and then assign each knowledge point node to the nearest grid cell.

[0054] For example, in the process of assigning each knowledge point node to the nearest grid cell, the knowledge point learning grid module 1 can also use a greedy algorithm to sort the nodes in the force-directed layout according to their importance (such as degree, i.e., the number of associated knowledge points corresponding to the node), and place the nodes in the grid in turn to the nearest free cell in the grid until all knowledge point nodes are mapped to the corresponding cells of the grid.

[0055] In some examples, each cell in the target knowledge point learning grid constructed by Knowledge Point Learning Grid Module 1 can be labeled with the attribute information of the corresponding knowledge point, such as difficulty, importance, learning time, etc. At the same time, the relationship information between knowledge points can be displayed in the form of lines, such as directed lines to represent prerequisite relationships and undirected lines to represent correlation relationships. The correlation strength can also be marked on the lines, thus forming a complete learning grid containing knowledge point attribute information and relationship information.

[0056] In the embodiments of this application, a learning plan can be a detailed learning arrangement formulated for students within a target time period. For example, the learning plan in the embodiments of this application may specifically include the knowledge points to be learned, the learning order, the learning duration, the learning content (such as online courses, practice questions, etc.), and the learning objectives.

[0057] In the embodiments of this application, the learning path generated by the learning path generation module 2 can be a visual representation of the learning order of knowledge points in the learning plan. The learning path can be used to display the learning order and path from the starting knowledge point to the target knowledge point in the target knowledge point learning grid through specific markers (such as lines of different colors, arrows, etc.).

[0058] For example, the knowledge point learning grid module 1 can display the learning plan as a learning path in the target knowledge point learning grid. Specifically, the display can use arrows of specific colors to connect the cells corresponding to the knowledge points to be learned, and the direction of the arrows indicates the learning order. At the same time, the learning time period and learning content prompts for each knowledge point can be marked in the grid. Students can intuitively see their learning path and specific arrangements within the target time period through the target knowledge point learning grid displayed by the knowledge point learning grid module 1.

[0059] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0060] Example 11: The knowledge point learning grid module 1 is used to determine the frequency data of knowledge points appearing in the same historical learning sessions based on attribute information, and generate the first association strength corresponding to the knowledge points in the knowledge point set based on the frequency data; determine the mastery level data of knowledge points based on attribute information, and generate the second association strength corresponding to the knowledge points in the knowledge point set based on the mastery level data; determine the proximity of the learning order of knowledge points based on attribute information, and generate the third association strength corresponding to the knowledge points in the knowledge point set based on the proximity of the learning order; determine the probability data of incorrect answers to knowledge points based on attribute information, and generate the fourth association strength corresponding to the knowledge points in the knowledge point set based on the probability data of incorrect answers; and generate the target association strength corresponding to the knowledge points in the knowledge point set based on the first association strength, second association strength, third association strength, and fourth association strength.

[0061] Example 12: The knowledge point learning grid module 1 is used to determine the first association type between knowledge points based on basic learning information, the second association type between knowledge points based on prerequisite knowledge information, and the third association type between knowledge points based on relevance information; it generates directed edges corresponding to the knowledge point set based on the first association type between knowledge points corresponding to basic learning information and the second association type between knowledge points corresponding to prerequisite knowledge information, and generates undirected edges corresponding to the knowledge point set based on the first association type between knowledge points corresponding to the third association type between knowledge points corresponding to relevance information; it determines the target association strength corresponding to the knowledge points in the knowledge point set based on attribute information, and generates an association matrix based on the knowledge point set, directed edges, undirected edges, and association strength; it constructs graph edges based on the association matrix, and constructs graph nodes based on the knowledge point set and attribute information, and combines graph nodes and graph edges to generate a knowledge graph.

[0062] Example 13: The knowledge point learning grid module 1 is used to perform quality assessment on the knowledge graph. When there are isolated nodes in the knowledge graph, the knowledge point set is refined, and the knowledge graph is adjusted based on the refined knowledge point set. When there are nodes in the knowledge graph with a density greater than the density threshold, the knowledge point set is merged, and the knowledge graph is adjusted based on the merged knowledge point set.

[0063] Example 14: The knowledge point learning grid module 1 is used to respond to the acquisition of learning behavior data of students learning based on the learning plan. Based on the learning behavior data, it determines the students' question information and note information during the learning process; identifies implicit knowledge points in the question information and note information, and determines the implicit attribute information of the implicit knowledge points. The implicit attribute information includes implicit prerequisite knowledge information and implicit relevance information; when the implicit attribute information meets the knowledge graph update conditions, it updates the knowledge graph based on the implicit knowledge points and implicit attribute information to obtain the target knowledge graph. The target knowledge graph is used to generate a learning grid that includes implicit knowledge points and implicit knowledge point attribute information.

[0064] Example 15: The knowledge point learning grid module 1 is used to determine the prerequisite knowledge points corresponding to the implicit knowledge points based on implicit prerequisite knowledge information; determine the students' mastery of the implicit knowledge points and prerequisite knowledge points based on the question information, as well as the answer results data of the questions containing the implicit knowledge points and prerequisite knowledge points; determine the confidence level of the implicit prerequisite knowledge information based on the mastery level and answer results data; and update the graph nodes in the knowledge graph based on the implicit knowledge points and update the directed edges in the knowledge graph based on the implicit prerequisite knowledge information when the confidence level of the implicit prerequisite knowledge information is greater than the confidence level threshold and the number of times the implicit knowledge points are identified is greater than the number of times the implicit knowledge points are identified.

[0065] Example 16: The knowledge point learning grid module 1 is used to determine the related knowledge points corresponding to implicit knowledge points based on implicit relevance information; to determine the student's mastery of implicit knowledge points and related knowledge points based on note information, as well as the information contribution data of note information to implicit relevance information; to determine the confidence level of implicit relevance information based on the mastery level and information contribution data; and to update the graph nodes in the knowledge graph based on implicit knowledge points and update the undirected edges in the knowledge graph based on implicit prerequisite knowledge information when the confidence level of implicit relevance information is greater than the confidence level threshold and the number of times implicit knowledge points are identified is greater than the number of times the threshold is reached.

[0066] Compared with existing technologies, this embodiment, through the knowledge point learning grid module in the learning companion system, can acquire course knowledge points and related information within the student's target time period. Combining basic learning, prerequisites, and relevance information, a knowledge graph is constructed, transforming scattered knowledge points into a structured knowledge network and clearly presenting the inherent connections between knowledge. Furthermore, by mapping the knowledge graph into an intuitive target knowledge point learning grid, and sending the obtained knowledge graph to the learning path generation module, the learning path generation module can generate a learning plan based on the grid. The learning path is then displayed through the target knowledge point learning grid in the knowledge point learning grid module. This allows the learning companion system in this embodiment to accurately and clearly present the relationships between knowledge points to students through the learning path, enabling students to effectively understand the knowledge structure and achieve deep learning and transfer through the relationships between knowledge points represented by the learning path. Ultimately, this embodiment's learning companion system can help students improve their learning efficiency.

[0067] Optionally, it also includes a learning behavior collection module 3; the learning behavior collection module 3 is connected to the knowledge point learning grid module 1; the learning behavior collection module 3 is used to respond to the acquisition of the first learning behavior data of the student learning questions based on the learning plan, determine the first question information and the first note information of the student's learning target questions based on the first learning behavior data, and send the first question information and the first note information to the knowledge point learning grid module 1; the knowledge point learning grid module 1 is used to determine the target implicit knowledge point set corresponding to the learning plan from the implicit knowledge point set based on the implicit knowledge point set corresponding to the first question information and the first note information, according to the prerequisite relationship and correlation information between the implicit knowledge point set and the first knowledge point set; update the target implicit knowledge point set in the target knowledge point learning grid, and send the updated target knowledge point learning grid to the learning path generation module 2; the learning path generation module 2 is used to update the learning plan to include the target implicit knowledge point set.

[0068] In this embodiment of the application, the learning behavior data collected by the learning behavior collection module 3 can be various operation data generated by students when they are learning questions in the tutoring system. For example, the learning behavior data in this application may specifically include question answering data (such as answer results, answering time, and wrong question markings), note data (such as note text and the corresponding learning position of the notes), and learning interaction data (such as online class dwell time and number of repeated views).

[0069] In this embodiment, the target question can be a specific question that the student is currently studying based on their current learning plan; in this embodiment, the question information can be detailed information related to the target question. Specifically, the question information may include the question ID, question stem text, answer explanation, system-pre-annotated knowledge points, and the student's answer result (…). (1 indicates correct, 0 indicates incorrect), answer timestamp, and other information.

[0070] In this embodiment of the application, the note information can be the notes recorded by the student during the learning of the target questions. Specifically, in this embodiment, the note information can be... This can be represented as note information, which may include note text (Text), note location (Loc), and the contextual knowledge points (kcontext) corresponding to the note.

[0071] In this embodiment of the application, the learning behavior collection module 3 can monitor the operation behavior of the learning companion system on the learning tablet in real time. When it detects that a student has entered the question learning module based on the current learning plan and started answering the target question, it can automatically trigger the collection of learning behavior data. During the mechanical learning behavior data collection process by the learning behavior collection module 3, it can first record the student's answering operation, generating answer data including the question ID, question stem, student answer, and answering time. Simultaneously, it retrieves the preset answer analysis and explicit knowledge point annotations for the question. If the student triggers the note-taking function (such as handwriting or inputting notes) during the answering process, the learning behavior collection module 3 can simultaneously record the note text, the corresponding learning location of the note, and the contextual knowledge points. The learning behavior collection module 3 can perform structured processing on the collected learning behavior data, identifying question information directly related to the target question and the student's self-recorded note information from the data.

[0072] In this embodiment, the first knowledge point set can be the explicit knowledge point set that marks the target question in the knowledge point learning grid module 1. For example, the first knowledge point set in this embodiment can be specifically represented by Kexplicit.

[0073] In this embodiment, the set of knowledge points corresponding to the question information can be the set of all knowledge points extracted by the knowledge point learning grid module 1 from the question information (especially the answer analysis) of the target question. The set of knowledge points corresponding to the question information can include explicit knowledge points and knowledge points indirectly involved in the question. For example, the set of knowledge points corresponding to the question information in this embodiment can be specifically represented by Kanalysis.

[0074] In this embodiment, the set of knowledge points corresponding to the note information can be the set of all knowledge points extracted by the knowledge point learning grid module 1 from the student's recorded notes. This set of knowledge points can reflect the knowledge points the student focuses on when learning the target questions. The set of knowledge points can also include additional knowledge points not labeled by the system. For example, the set of knowledge points corresponding to the note information in this embodiment can be specifically represented by Knote.

[0075] In this embodiment, the implicit knowledge point set can be a set of knowledge points not included in the first knowledge point set, which are from the knowledge point set corresponding to the question information and the knowledge point set corresponding to the note information. For example, the implicit knowledge point set in this embodiment can be specifically represented by Khidden.

[0076] In this embodiment of the application, the knowledge point learning grid module 1 can extract knowledge points from the question information and the note information to obtain the corresponding knowledge point set. Specifically, for the question information, the knowledge point learning grid module 1 can use natural language processing (NLP) technology to extract knowledge points, including but not limited to using a BERT-based subject knowledge point recognition model to perform entity linking and semantic analysis on the question answer parsing. For the note information, the system can combine a subject-specific dictionary and the TF-IDF text feature extraction algorithm to perform word segmentation and semantic matching on the note text, extracting the knowledge point set corresponding to the note information.

[0077] In this embodiment of the application, the knowledge point learning grid module 1 can also compare the knowledge point set corresponding to the question information and the knowledge point set corresponding to the note information with the first knowledge point set to filter out implicit knowledge points. Specifically, this can include: the knowledge point learning grid module 1 first filters out the knowledge points not included in the first knowledge point set Kexplicit in the knowledge point set Kanalysis corresponding to the question information to obtain the implicit knowledge points of the question source; it then filters out the knowledge points not included in the first knowledge point set Kexplicit in the knowledge point set Knote corresponding to the note information to obtain the implicit knowledge points of the note source; finally, it merges these two implicit knowledge points, removes duplicates, and obtains the implicit knowledge point set Khidden.

[0078] In the embodiments of this application, the prerequisite relationship can be the dependency relationship between knowledge points in the knowledge point learning grid module 1. The prerequisite relationship can be expressed as mastering one knowledge point (prerequisite knowledge point) is a prerequisite for understanding or mastering another knowledge point (subsequent knowledge point).

[0079] For the embodiments of this application, the relevance information may be the association information between knowledge points in the knowledge point learning grid module 1. The relevance information may indicate that two knowledge points are related in semantic description, application scenario or learning logic, but there is no strict order of mastery.

[0080] In this embodiment of the application, the target implicit knowledge point set can be the implicit knowledge point set selected by the knowledge point learning grid module 1 from the implicit knowledge point set that has a high confidence prior relationship or correlation relationship with the first knowledge point set.

[0081] In this embodiment, the knowledge point learning grid module 1 can establish prerequisite relationships and relevance relationships based on the implicit knowledge point set and the first knowledge point set, respectively; the knowledge point learning grid module 1 can determine prerequisite relationships based on the implicit knowledge points extracted from the question information and the first knowledge point set, referring to the teaching syllabus, subject expert experience, and historical student learning data; the knowledge point learning grid module 1 can determine relevance relationships based on the implicit knowledge points extracted from the note information and the first knowledge point set, through text similarity calculation (TF-IDF vectorization technology can be used to convert knowledge point descriptions into vectors and calculate cosine similarity) and knowledge point co-occurrence frequency statistics.

[0082] In this embodiment of the application, the knowledge point learning grid module 1 can calculate the confidence of the prior relationship and the confidence of the relevance relationship, and filter the target implicit knowledge points based on the confidence of the prior relationship and the confidence of the relevance relationship. If the confidence of the prior relationship between the implicit knowledge point and the first knowledge point set is greater than the prior confidence threshold, or the confidence of the relevance relationship between the implicit knowledge point and the first knowledge point set is greater than the relevance confidence threshold, then the implicit knowledge point is included in the target implicit knowledge point set.

[0083] In this embodiment of the application, the knowledge point learning grid can be a two-dimensional grid formed by the knowledge point learning grid module 1 mapping the learning course content of the student's current semester, such as... Figure 2 As shown, in Figure 2 Each grid cell represents a knowledge point. The level of mastery of different knowledge points can be marked within the cell. For example, different circles can be used to mark the proficiency of knowledge points, different symbols can be used to mark different circles, and different shapes can be used to mark the proficiency of knowledge points. The specific marking form of knowledge point proficiency is not limited in this embodiment.

[0084] As an optional method, when marking the proficiency of knowledge points by filling different circles, red can be used to indicate not mastered, yellow can be used to indicate mastered but not proficient, and green can be used to indicate proficient; when marking the proficiency of knowledge points by filling different shapes, 1 can be used to indicate not mastered, 2 can be used to indicate mastered but not proficient, and 3 can be used to indicate proficient; when marking the proficiency of knowledge points by filling different shapes, circles can be used to indicate not mastered, triangles can be used to indicate mastered but not proficient, squares can be used to indicate proficient, and so on, without further examples.

[0085] In this embodiment, the target learning plan can be the updated learning plan of the learning path generation module 2. For example, in this embodiment, the target learning plan can specifically be the learning path generation module 2 incorporating a set of target implicit knowledge points into the original learning plan, and specifying the learning order and priority of the target implicit knowledge points.

[0086] In the embodiments of this application, the learning path generation module 2 can first determine the position of the target implicit knowledge point in the knowledge point learning grid, and ensure that the connected knowledge points (with prior or related relationships) in the grid are as adjacent as possible. The specific method for determining the position of the target implicit knowledge point in the knowledge point learning grid can be, but is not limited to, the force-directed algorithm.

[0087] In this embodiment of the application, the learning path generation module 2 can mark the target implicit knowledge points with colors based on the students' mastery data of the target implicit knowledge points; the learning path generation module 2 can incorporate the set of target implicit knowledge points into the original learning plan, and generate the target learning plan by combining the priority of knowledge points (priority knowledge points have higher priority than related knowledge points) and mastery (red knowledge points have higher priority than yellow and green knowledge points).

[0088] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0089] Example 21: The knowledge point learning grid module 1 is used to extract knowledge points from the question information and note information respectively, to obtain a second set of knowledge points corresponding to the question information and a third set of knowledge points corresponding to the note information; the knowledge points in the second set of knowledge points that are not included in the first set of knowledge points are determined as the first subset of implicit knowledge points corresponding to the target question; the knowledge points in the third set of knowledge points that are not included in the first set of knowledge points are determined as the second subset of implicit knowledge points corresponding to the target question; and the implicit knowledge point set is determined based on the first subset of implicit knowledge points and the second subset of implicit knowledge points.

[0090] Example 22: The knowledge point learning grid module 1 is used to establish multiple knowledge point prerequisite relationships based on a first subset of implicit knowledge points and a first set of knowledge points, so as to determine the knowledge points in the first subset of implicit knowledge points as prerequisite knowledge points for the knowledge points in the first set of knowledge points; to establish multiple knowledge point correlation relationships based on a second subset of implicit knowledge points and the first set of knowledge points, so as to associate the knowledge points in the second subset of implicit knowledge points with the knowledge points in the first set of knowledge points; to determine the first confidence level of using the multiple knowledge point prerequisite relationships as the target knowledge point prerequisite relationships corresponding to the learning plan and the second confidence level of using the multiple knowledge point correlation relationships as the target knowledge point correlation relationships corresponding to the learning plan; and to determine the target implicit knowledge point set corresponding to the learning plan from the implicit knowledge point set based on the first confidence level and the second confidence level.

[0091] Example 23: The knowledge point learning grid module 1 is used to determine the first mastery data of students on the first implicit knowledge point subset, and to determine the students' answer results on the questions based on the students' answer data on the questions in the question information; based on the first mastery data and the answer results, the first support data of each knowledge point prerequisite relationship in multiple knowledge point prerequisite relationships is determined; and the historical confidence of each knowledge point prerequisite relationship is updated according to the first support data to obtain the first confidence of using multiple knowledge point prerequisite relationships as the target knowledge point prerequisite relationship.

[0092] Example 24: The knowledge point learning grid module 1 is used to determine the second mastery data of students on the second subset of implicit knowledge points, and the contribution data of note information to the correlation relationship of multiple knowledge points; based on the mastery data and contribution data, the second support data of each knowledge point correlation relationship in the multiple knowledge point correlation relationships are determined; the second support data is updated according to the historical confidence of each knowledge point correlation relationship based on the second support data, and the second confidence of the current multiple knowledge point correlation relationships as target knowledge point correlation relationships is obtained.

[0093] Example 25: The knowledge point learning grid module 1 is used to store multiple knowledge point prerequisite relationships and multiple knowledge point correlation relationships in a candidate relation library corresponding to the learning plan, so as to monitor the first confidence level and the second confidence level through the candidate relation library; in response to the first confidence level of the first knowledge point prerequisite relationship being greater than the prerequisite confidence threshold and the number of times the first implicit knowledge point corresponding to the first knowledge point prerequisite relationship is identified being greater than the number of times threshold, the first implicit knowledge point is determined as the first target implicit knowledge point corresponding to the learning plan; in response to the first confidence level of the first knowledge point correlation relationship being greater than the correlation confidence threshold and the number of times the first implicit knowledge point corresponding to the first knowledge point correlation relationship is identified being greater than the number of times threshold, the first implicit knowledge point is determined as the first target implicit knowledge point corresponding to the learning plan; the target implicit knowledge point set corresponding to the learning plan is determined based on the first target implicit knowledge point and the second target implicit knowledge point.

[0094] Example 26: The knowledge point learning grid module 1 is used to determine the monitoring period of the candidate relation library for the first confidence level and the second confidence level; during the monitoring period, in response to the first confidence level of the second knowledge point prerequisite relation among multiple knowledge point prerequisite relations and / or the second confidence level of the second knowledge point prerequisite relation among multiple knowledge point correlation relations being lower than the monitoring threshold, the second knowledge point prerequisite relation and / or the second knowledge point prerequisite relation are removed from the candidate relation library; in response to the end of the monitoring period, multiple knowledge point prerequisite relations and multiple knowledge point correlation relations are removed from the candidate relation library.

[0095] It should be noted that this embodiment provides accurate data for updating the learning plan by collecting students' learning behavior data and extracting key information from questions and notes; it constructs implicit relationships in the knowledge graph by identifying the set of implicit knowledge points; it improves the accuracy of selecting target implicit knowledge points by analyzing the prerequisite and relevance relationships of knowledge points; and it achieves precise matching between the learning plan and the student's cognitive state by updating the knowledge point learning grid and dynamically optimizing the learning plan, thereby improving learning efficiency and the systematic nature of knowledge construction.

[0096] Optionally, it also includes a mastery analysis module 4; the mastery analysis module 4 is connected to the learning behavior collection module 3; the learning behavior collection module 3 is used to determine the target learning course corresponding to the learning position information based on the student's learning position information in the target knowledge point learning grid; it divides the student's second learning behavior data in the target learning course into at least one learning behavior data set, generates at least one behavioral feature set corresponding to at least one learning behavior data set, and sends at least one behavioral feature set to the mastery analysis module 4; the mastery analysis module 4 is used to analyze the student's mastery of the knowledge points in the target learning course based on at least one behavioral feature set, determine the student's unmastered knowledge point set in the target learning course, and send the unmastered knowledge point set to the knowledge point learning grid module; the knowledge point learning grid module 1 is used to match the unmastered knowledge point set with the target knowledge graph corresponding to the target knowledge point learning grid, obtain the target knowledge point network corresponding to the unmastered knowledge point set in the target knowledge graph, and send the target knowledge point network to the learning path generation module 2; the learning path generation module 2 generates the student's target learning path in the target knowledge point learning grid based on the target knowledge point network, and the target learning path is used to assist the student in mastering the unmastered knowledge point set.

[0097] In this embodiment of the application, the learning location information collected by the learning behavior collection module 3 can be the location data corresponding to the cell that the student is currently focusing on learning in the target knowledge point learning grid, such as grid coordinates (xi, yi). The learning location information can be associated with the corresponding knowledge point or course content in the learning grid.

[0098] In this embodiment of the application, the target learning courses collected by the learning behavior collection module 3 can be the subject courses that the student needs to study in the current semester, determined based on the student's learning location information and the semester information pre-filled by the student.

[0099] In this embodiment of the application, the learning behavior collection module 3 can first generate a student identifier ID based on the basic information such as class, grade, name, age, and semester filled in by the student during login. The student identifier ID can be used to associate all the student's learning data. The learning behavior collection module 3 can obtain the full range of courses corresponding to the semester from the resource library based on the semester information entered by the student. Then, it can break down these course contents into knowledge points and map them to the target knowledge point learning grid. Each course's knowledge point corresponds to one or more cells in the grid. The system can determine the student's specific learning location information in the target knowledge point learning grid by recording the student's learning operations on the tablet (such as clicking on the course module to be learned, watching the online course chapter, and answering the exercises to the knowledge point). Then, it can determine the corresponding target learning course based on the location information.

[0100] In this embodiment of the application, the second learning behavior data can be various operation data generated by students when they are learning questions in the learning companion system, collected by the learning behavior collection module 3. For example, the learning behavior data in this application may specifically include question answering data (such as answer results, answering time, and incorrect question markings), note data (such as note text and the corresponding learning position of the notes), and learning interaction data (such as online class dwell time and number of repeated views).

[0101] In this embodiment, the behavioral feature set can be a combination of feature data that reflects the student's learning status, extracted by the learning behavior collection module 3 from each learning behavior data set. Each behavioral feature can be quantified and normalized to ensure data consistency.

[0102] In this embodiment, the learning behavior collection module 3 can first classify all the learning behavior data of the students in the target learning course. The classification dimension can be set as the scenario in which the data is generated (online class learning, doing exercises, note-taking, questioning and interaction), and the learning behavior data in the same scenario can be grouped into a learning behavior data set.

[0103] In this embodiment of the application, the learning behavior collection module 3 can extract features from each learning behavior dataset to generate a corresponding behavior feature set. For example, the video viewing completion rate can be extracted from the online course learning behavior dataset. ), number of times viewed repeatedly ( ), length of stay ( ) as features, forming a set of behavioral features [ =0.8, =2, =45]; the accuracy rate can be extracted from the dataset of problem-solving behavior data ( ), answering speed ( ), Correctness rate of redoing incorrect questions ( ) as features, forming a set of behavioral features [ =0.7, =1.5, =0.6]; the frequency of questions can be extracted from the interactive behavior data set ( ), Number of notes ( ) as features, forming a set of behavioral features [ =0.1, =2].

[0104] In the embodiments of this application, the degree of mastery can be the degree of understanding and application of each knowledge point in the target learning course by the student as determined by the degree of mastery analysis module 4. The degree of mastery can be reflected by scores or probabilities and can be used to reflect the student's mastery of knowledge points.

[0105] In this embodiment of the application, the set of unmastered knowledge points can be a set of knowledge points in the target learning course determined by the mastery analysis module 4 that the students' mastery level has not reached the preset qualification standard. The knowledge points in the set of unmastered knowledge points can be the content that the learning path planning focuses on.

[0106] In this embodiment of the application, the analysis of students' mastery of knowledge points in the target learning course based on at least one set of behavioral features can be achieved by first associating all sets of behavioral features corresponding to each knowledge point in the target learning course with the mastery analysis module 4; then calculating the mastery score for each knowledge point; and then mapping the mastery score to the mastery probability through a function. The mastery probability can be used as a quantitative indicator of the mastery level. The value range of the mastery probability can be [0,1]. The higher the value of the mastery probability, the higher the student's mastery of the knowledge point.

[0107] In this embodiment of the application, the mastery analysis module 4 determines the set of knowledge points that students have not mastered in the target learning course by setting a mastery probability judgment threshold. The mastery probability judgment threshold may include a low mastery probability threshold and a high mastery probability threshold. For example, if the mastery probability of knowledge point k1 is less than the low mastery probability threshold, knowledge point k1 can be determined as a knowledge point that has not been mastered; if the mastery probability of knowledge point k1 is greater than or equal to the low mastery probability threshold and less than the high mastery probability threshold, knowledge point k1 can be determined as a knowledge point that has been mastered but not proficient; if the mastery probability of knowledge point k1 is greater than the high mastery probability threshold, knowledge point k1 can be determined as a knowledge point that has been mastered.

[0108] In this embodiment of the application, the mastery analysis module 4 can filter out all knowledge points in the target learning course that are determined to be unmastered to form a set of unmastered knowledge points.

[0109] In this embodiment of the application, the knowledge point learning grid module 1 can match the set of unmastered knowledge points with the target knowledge graph corresponding to the target knowledge point learning grid. Knowledge point extraction can be performed first, that is, Natural Language Processing (NLP) technology can be used to perform structured analysis on the textbook catalog, syllabus, and curriculum standards of the target learning course to identify core concepts, theorems, and skill points, and establish a hierarchical knowledge structure. For example, in this embodiment of the application, the extracted knowledge points can be specifically represented as knowledge point k1, knowledge point k2, knowledge point k3, and knowledge point k4.

[0110] In the embodiments of this application, the knowledge point learning grid module 1 can construct the relationship between knowledge points based on the acquired knowledge points. Specifically, the relationship can be determined by using the attribute information of the knowledge points. The attribute information can be a comprehensive description of various features of the knowledge points. In addition to including basic learning information, prerequisite knowledge information and relevance information, it can also include related information such as the relationship type and relationship strength derived from these information, which can comprehensively reflect the features of the knowledge points and the relationship between them.

[0111] In this embodiment, the knowledge point learning grid module 1 can generate attribute information of knowledge points based on the acquired basic learning information, prerequisite knowledge information, and relevance information. It integrates the difficulty, importance, and learning time in the basic learning information, the specific prerequisite knowledge points corresponding to the prerequisite knowledge information, and the related knowledge points and degree of association corresponding to the relevance information to form unique attribute information for each knowledge point. Based on the generated attribute information, it constructs a graph model with knowledge points as nodes, relationships as edges, and association strength as edge weights, and calculates the centrality index of the nodes to construct the target knowledge graph.

[0112] In the embodiments of this application, the matching of the set of unmastered knowledge points with the target knowledge graph can be achieved by the knowledge point learning grid module 1 locating the corresponding node in the target knowledge graph for each knowledge point in the set of unmastered knowledge points, extracting all associated nodes (including pre-requisite nodes, subsequent nodes, and related nodes) and associated edges of the node to form a preliminary matching network. The preliminary matching network can be filtered, and the filtering criteria can be an association strength threshold. Specifically, the filtering can be to retain edges whose association strength meets the threshold requirements and to remove edges whose association strength does not meet the threshold conditions. After filtering the preliminary matching network, the target knowledge point grid is generated.

[0113] Optionally, in the embodiments of this application, the directed edges of the knowledge graph can maintain direction information, such as a directed edge knowledge graph. Figure 3 As shown, Figure 3 The numbers (0, 1, 2, etc.) in the graph can represent knowledge point identifiers, and each identifier corresponds to one knowledge point. Arrows can indicate the direction of edges; undirected edges do not need to have a direction set. An undirected edge knowledge graph is shown below. Figure 4 As shown, the corresponding target association strength can be used as the weight of the graph edge and labeled on the graph edge; when constructing graph nodes, each knowledge point corresponds to a graph node, and the attribute information of the knowledge point (including basic learning information, prerequisite knowledge information, relevance information, etc.) can be associated with the corresponding graph node.

[0114] In this embodiment, the knowledge point learning grid module 1 can connect graph nodes according to the relationships between knowledge points through graph edges to form a complete knowledge graph. During the construction process, graph algorithms can be used to calculate the centrality indices of nodes, including degree centrality, betweenness centrality, and proximity centrality. Centrality analysis can be performed as follows: Figure 5 As shown, degree centrality can be measured by the number of direct connections a node has, betweenness centrality can be measured by the degree to which a node acts as a bridge, and proximity centrality can be measured by the reciprocal of the average distance from a node to other nodes. For example, knowledge points with high degree centrality can be basic knowledge points, those with high betweenness centrality can be key transit knowledge points, and those with high proximity centrality can be core knowledge points.

[0115] In the embodiments of this application, the target learning path can be the sequence of learning knowledge points planned by the learning path generation module 2 in the target knowledge point learning grid according to the logical relationship of knowledge points and the student's lack of mastery. The target learning path can be used to guide students to gradually master the knowledge points in the set of unmastered knowledge points. The target learning path can be mapped to a grid coordinate sequence for display.

[0116] In this embodiment, the learning path generation module 2 can generate a student's target learning path in the target knowledge point learning grid based on the target knowledge point network. The priority ranking can be based on the following criteria: mastery status of knowledge points (knowledge points that have not been mastered have higher priority than knowledge points that have been mastered but not yet mastered), prerequisite relationship (prerequisite knowledge points have higher priority than subsequent knowledge points), importance (based on betweenness centrality and degree centrality, knowledge points with higher centrality have higher priority), and time decay (knowledge points that have been studied for a longer period of time have higher priority).

[0117] In this embodiment, the learning path generation module 2 can generate a learning path based on priority ranking and the dependency relationship (prerequisite relationship) of knowledge points. Specifically, the learning path can be generated using a graph traversal algorithm (such as breadth-first search (BFS) or depth-first search (DFS). After generating the learning path, the learning path can also be adjusted according to the student's learning ability. The learning ability can be evaluated by the student's learning speed, knowledge retention, and knowledge application ability.

[0118] In this embodiment, obtaining the target knowledge point network corresponding to the set of unmastered knowledge points in the target knowledge graph can be achieved by the knowledge point learning grid module 1 mapping the target learning path generated by the learning path generation module 2 into the target knowledge point learning grid. The target learning path can then be displayed to the student in the form of a grid coordinate sequence. For example, if knowledge point k2 in the set of unmastered knowledge points corresponds to the target knowledge point learning grid coordinates (1,2), and knowledge point k4 in the set of unmastered knowledge points corresponds to the target knowledge point learning grid coordinates (2,3), then the target learning path can be displayed in the target knowledge point learning grid as (1,2) → (2,3). This can guide the student to learn sequentially according to the target knowledge point learning grid positions, helping the student gradually master k2 and k4 in the set of unmastered knowledge points.

[0119] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0120] Example 31: The learning behavior collection module 3 is used to determine the time information corresponding to each behavior feature in at least one set of behavior features, and evaluate the effectiveness of each behavior feature in at least one set of behavior features based on the time information to obtain the effective value data of each behavior feature in at least one set of behavior features; based on the effective value data, the behavior features in at least one set of behavior features are filtered to obtain the target behavior features that meet the effective conditions in at least one set of behavior features, and the target behavior features are combined into at least one set of target behavior features; based on at least one set of target behavior features, the degree of students' mastery of knowledge points in the target learning course is analyzed to determine the set of knowledge points that students have not mastered in the target learning course.

[0121] Example 32: The learning behavior collection module 3 is used to match at least one set of target behavior features with each knowledge point in the target learning course to determine at least one target behavior feature corresponding to each knowledge point in the target learning course; to identify the importance data of at least one target behavior feature corresponding to each knowledge point in the target learning course to each knowledge point in the target learning course through the target model, which is trained based on the student's historical behavior features and historical knowledge point mastery level; to determine the student's mastery level data for each knowledge point in the target learning course based on the at least one target behavior feature and importance data corresponding to each knowledge point; and to determine the set of unmastered knowledge points in the target learning course based on the mastery level data.

[0122] Example 33: The learning behavior collection module 3 is used to determine the influence coefficient of at least one behavioral feature corresponding to each knowledge point on the mastery of each knowledge point based on the importance data; and to analyze at least one behavioral feature based on the influence coefficient to generate data on the student's mastery of each knowledge point in the target learning course.

[0123] Example 34: The learning behavior collection module 3 is used to map the mastery data of each knowledge point through the objective function to obtain the mastery probability data of each knowledge point of the student; based on the mastery probability data, knowledge points that meet the unmastered conditions are selected from the knowledge corresponding to the target learning course, and the knowledge points selected from the knowledge corresponding to the target learning course are combined into a set of unmastered knowledge points.

[0124] Example 35: The mastery analysis module 4 is used to generate a sequence of unmastered knowledge points based on the set of unmastered knowledge points; the sequence of unmastered knowledge points is marked with unmastered identifiers in the target learning grid, and the unmastered knowledge point paths corresponding to the unmastered knowledge point sequences are extracted from the target learning grid; the unmastered knowledge point paths are matched with the target knowledge graph according to the unmastered identifiers to obtain the target knowledge point network corresponding to the set of unmastered knowledge points in the target knowledge graph.

[0125] Example 36: The mastery analysis module 4 is used to match the paths of unmastered knowledge points with the target knowledge graph based on the unmastered identifier, and obtain the network of knowledge points to be screened corresponding to the set of unmastered knowledge points in the target knowledge graph; based on the prerequisite and relevance information of the paths of unmastered knowledge points in the network of knowledge points to be screened, the target knowledge point network is determined from the network of knowledge points to be screened.

[0126] It should be noted that this embodiment achieves precise positioning of the student's current learning focus by obtaining the student's learning location information in the target knowledge point learning grid from the learning companion system and determining the corresponding target learning course; it achieves structured processing of multi-source heterogeneous learning behavior data by dividing the student's second learning behavior data in the target learning course into at least one learning behavior dataset and merging them to generate at least one corresponding behavior feature set; it improves the accuracy of identifying unmastered knowledge points by analyzing the student's mastery of knowledge points in the target learning course based on at least one behavior feature set and determining the set of unmastered knowledge points; it improves the confidence of knowledge graph association by matching the set of unmastered knowledge points with the target knowledge graph corresponding to the target knowledge point learning grid and obtaining the target knowledge point network; and it improves the reliability of learning path generation and enhances the pertinence of assisting students in mastering unmastered knowledge points by generating the student's target learning path in the target knowledge point learning grid based on the target knowledge point network.

[0127] Optionally, a learning intention analysis module 5 is also included. The learning intention analysis module 5 is connected to the mastery analysis module 4 and the learning behavior collection module 3, respectively. The learning behavior collection module 3 is used to acquire third learning behavior data of students learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid. Based on the third learning behavior data, it determines the second question information and second note information of students learning knowledge points in the set of unmastered knowledge points, and sends the second question information and second note information to the learning intention analysis module 5. The learning intention analysis module 5 is used to evaluate students' learning needs for knowledge points in the set of unmastered knowledge points based on the second question information and second note information, and obtain the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid. Based on the learning intention intensity data, the second question information and the second note information, it identifies the students' target learning intention for knowledge points in the set of unmastered knowledge points, and sends the target learning intention to the mastery analysis module 4. The mastery analysis module 4 is used to update the set of unmastered knowledge points based on the target learning intention and the knowledge point positioning information of the set of unmastered knowledge points in the knowledge point learning grid to obtain the target set of unmastered knowledge points, and recommends the target set of unmastered knowledge points to students.

[0128] In this embodiment, the third learning behavior data can be various operational data generated by students during their learning in the target knowledge point learning grid, collected by the learning behavior collection module 3. This third learning behavior data can be used to reflect the student's learning process and learning status. For example, the third learning behavior data in this embodiment may specifically include, but is not limited to, online course learning data (such as video completion rate, number of repeated views, dwell time, fast forward / rewind operation records), practice question data (such as answer accuracy rate, answer speed, number of incorrect questions, correct answer rate for redoing incorrect questions, number of questions completed, question difficulty level), and interaction data (such as question frequency, question content, number of notes, detail of notes, number of comments, and activity level in discussions).

[0129] In this embodiment of the application, the set of unmastered knowledge points can be a set of knowledge points in the target knowledge point learning grid collected by the learning behavior collection module 3 that the students' mastery level has not reached the qualified standard (e.g., the mastery probability is less than 0.4).

[0130] In this embodiment of the application, the question information may be detailed information about the knowledge point questions in the set of unmastered knowledge points collected by the learning behavior collection module 3. Specifically, the question information may include the question ID, question stem text, answer explanation, system-pre-annotated knowledge points, and student's answer result. (1 indicates correct, 0 indicates incorrect), answer timestamp, and other information.

[0131] In this embodiment of the application, the note information can be the notes recorded by the student during the process of learning knowledge points in the set of knowledge points not yet mastered, collected by the learning behavior collection module 3. Specifically, in this embodiment of the application, the note information can be used as... This can be represented as note information, which may include note text (Text), note location (Loc), and the contextual knowledge points (kcontext) corresponding to the note.

[0132] In this embodiment of the application, the learning needs can be the degree of desire and urgency of a student to learn the knowledge points they have not yet mastered, as determined by the learning intention analysis module 5. The learning needs can be affected by various factors such as learning activity, difficulty of understanding, and urgency of learning. Among them, the student's learning activity can be used to reflect the student's active attention to the knowledge points, the difficulty of understanding can be used to reflect the degree of obstacle to mastering the knowledge points, and the urgency of learning can be used to clarify the time urgency for the student to carry out learning.

[0133] In this embodiment of the application, the learning intention intensity data can be numerical data that quantifies the student's need to learn unmastered knowledge points, as determined by the learning intention analysis module 5. The value range of the learning intention intensity data can be [0,1]. The larger the value of the learning intention intensity data, the stronger and more urgent the student's need to learn the knowledge points. The learning intention intensity data can be used to provide a quantitative basis for subsequent learning intention identification and knowledge point recommendation.

[0134] In this embodiment, the learning intention analysis module 5 can first extract key information related to learning needs from the question information and note information, and combine it with the student's learning behavior trajectory to comprehensively evaluate the student's learning needs for each unmastered knowledge point; by analyzing the frequency of note updates for unmastered knowledge points within a target time range (e.g., the last 7 days) in the note information, the learning activity data can be evaluated. If the frequency of note updates for unmastered knowledge points is higher, it indicates that the student is paying more attention to the knowledge points and has higher learning activity; by statistically analyzing the frequency of questions students have about unmastered knowledge points in the question information and note information (e.g., the number of questions asked, the number of question symbols marked in the notes, and the number of content related to misunderstanding deviations reflected in the wrong questions), the comprehension difficulty data can be evaluated. If the frequency of questions students have about unmastered knowledge points is higher, it indicates that the student encounters more obstacles when mastering the knowledge points and has higher comprehension difficulty; by combining the learning end time and time decay coefficient recorded in the learning behavior data, the decay factor of learning intention intensity over time can be determined to evaluate the learning urgency data. The closer the student's learning end time and the smaller the decay factor, the more urgent the student's need to learn the knowledge points.

[0135] In this embodiment of the application, the learning intention analysis module 5 can perform weighted analysis on the learning activity data, comprehension difficulty data, and learning urgency data (the weight coefficients can be determined based on teaching experience or data training, and the sum of the weight coefficients is 1), and use the weighted result as the student's learning intention intensity data for the knowledge points not yet mastered.

[0136] In this embodiment of the application, the target learning intention can be the learning intention of a student when learning knowledge points that they have not mastered, as determined by the learning intention analysis module 5. The target learning intention can include the intention to deepen understanding, the intention to consolidate basic knowledge, and the intention to clarify conceptual doubts. The intention to deepen understanding can be the student's intention to deeply understand the core logic, internal connections, and application scenarios of the knowledge points. The intention to consolidate basic knowledge can be the student's intention to strengthen the basic concepts and basic usages of the knowledge points, consolidate existing preliminary understanding, and improve mastery and proficiency. The intention to clarify conceptual doubts can be the student's intention to resolve basic doubts before further learning when they are confused about the basic concepts, definitions, theorems, etc. of the knowledge points.

[0137] In this embodiment of the application, the knowledge point location information may be the specific location and relationship of the unmastered knowledge point in the knowledge graph corresponding to the knowledge point learning grid, as determined by the mastery analysis module 4. The knowledge point location information may include the prerequisite knowledge points, subsequent knowledge points, related knowledge points, and centrality indicators in the knowledge network.

[0138] In this embodiment of the application, the set of knowledge points that the target has not mastered can be a set of knowledge points that is more in line with the student's cognitive goals and knowledge system logic, obtained by the mastery analysis module 4 after filtering, supplementing and sorting the initial set of knowledge points that have not been mastered based on the target's learning intention and knowledge point location information.

[0139] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0140] Example 41: Based on note information, determine the update frequency of students' notes within the target time range, and evaluate students' learning activity data within the target time range based on the update frequency; based on note information and question information, determine the question frequency of students' doubts about knowledge points in the set of unmastered knowledge points, and evaluate students' difficulty in understanding knowledge points in the set of unmastered knowledge points based on the question frequency; evaluate students' learning needs for knowledge points in the set of unmastered knowledge points based on learning activity data and difficulty in understanding data, and obtain the learning intention intensity data corresponding to knowledge points in the knowledge point learning grid.

[0141] Example 42: Based on the third learning behavior data, determine the learning end time for students to learn the knowledge points in the set of unmastered knowledge points; determine the decay factor of learning intention intensity over time based on the learning end time and time decay coefficient; evaluate the urgency data of students learning the knowledge points in the set of unmastered knowledge points based on the decay factor; perform weighted analysis on learning activity data, comprehension difficulty data and urgency data to evaluate students' learning needs for the knowledge points in the set of unmastered knowledge points, and obtain the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid.

[0142] Example 43: Generate student learning content data and corresponding behavior sequence data based on question information and note information; evaluate the student's learning intention for the knowledge points in the set of unmastered knowledge points as a first probability data of deep understanding intention, a second probability data of basic consolidation intention, and a third probability data of conceptual inquiry intention based on the learning intention intensity data, learning content data, and behavior sequence data; determine the target learning intention from deep understanding intention, basic consolidation intention, and conceptual inquiry intention based on the first probability data, second probability data, and third probability data.

[0143] Example 44: Evaluate the student's required level of understanding of the knowledge points in the set of unmastered knowledge points based on the first probability data, the second probability data, and the third probability data; if the required level of understanding data is greater than the first required level of understanding threshold, determine the student's intention to deepen understanding as the target learning intention for the knowledge points in the set of unmastered knowledge points; if the required level of understanding data is less than or equal to the first required level of understanding threshold and greater than the second required level of understanding threshold, determine the student's intention to consolidate basic knowledge as the target learning intention for the knowledge points in the set of unmastered knowledge points, wherein the second required level of understanding threshold is less than the first required level of understanding threshold; if the required level of understanding data is less than the second required level of understanding threshold, determine the student's intention to raise conceptual questions as the target learning intention for the knowledge points in the set of unmastered knowledge points.

[0144] Example 45: Generate student learning content data based on question information and note information; map the third learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph; perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information for the set of unmastered knowledge points; update the set of unmastered knowledge points according to the target learning intention and knowledge point location information to obtain the target set of unmastered knowledge points, generate the target set of unmastered knowledge points and the target learning path corresponding to the target set of unmastered knowledge points; generate recommendation information for the target set of unmastered knowledge points and the target learning path so that students can master the knowledge points in the target set of unmastered knowledge points based on the target set of unmastered knowledge points and the target learning path.

[0145] Example 46: Obtain third learning behavior data from the learning support system, showing students learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid; divide the third learning behavior data of students in the target knowledge point learning grid into at least one learning behavior data set, and generate a behavioral feature set corresponding to at least one learning behavior data set; determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information, obtaining the effective value data of each behavioral feature in the behavioral feature set; filter the behavioral features in the behavioral feature set based on the effective value data, obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and form a target behavioral feature set; analyze the students' mastery of knowledge points in the target knowledge point learning grid based on the target behavioral feature set, and determine the set of unmastered knowledge points of students in the target knowledge point learning grid; identify the box-selection behavior from the target behavioral feature set, and classify the learning content selected by the box-selection behavior to obtain the question information and note information of students learning knowledge points in the set of unmastered knowledge points.

[0146] It should be noted that this embodiment obtains third-party learning behavior data from the learning support system, which shows students learning knowledge points in the set of unmastered knowledge points within the knowledge point learning grid, and determines the corresponding question information and note information. This provides data support for accurately evaluating students' learning needs. By evaluating students' learning needs for knowledge points in the set of unmastered knowledge points based on question information and note information, and obtaining learning intention intensity data, a quantitative assessment of students' learning needs is achieved. By identifying students' target learning intentions based on learning intention intensity data, question information, and note information, the accuracy of identifying student behavior is improved. By updating the target set of unmastered knowledge points based on the target learning intentions and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, and recommending them to students, the matching degree between recommended content and students' current psychological and cognitive needs is improved, thereby increasing students' acceptance of the recommended content and the effectiveness of the recommended content.

[0147] Optionally, it also includes a knowledge point location module 6; the knowledge point location module 6 is connected to the mastery analysis module 4 and the learning behavior collection module 3 respectively; the knowledge point location module 6 is used to map the third learning behavior data in the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph; it generates the student's learning content data based on the question information and note information, and performs multi-dimensional information matching between the learning content data and the learning knowledge point data to generate knowledge point location information of the set of unmastered knowledge points, and sends the knowledge point location information to the mastery analysis module 4.

[0148] In this embodiment of the application, the learning knowledge point data can be the knowledge point related information of the student in the knowledge graph determined by the knowledge point positioning module 6. The learning knowledge point data can include the attributes, relationships, and positions of the knowledge points in the graph. The learning knowledge point data can be used to reflect the correspondence of the student's learning trajectory in the overall knowledge system.

[0149] In this embodiment, the knowledge point positioning module 6 can map learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph. First, it can extract relevant information about the knowledge points the student has encountered from the learning behavior data, such as the course chapters studied, the knowledge points involved in answering questions, and the knowledge points recorded in notes, forming corresponding knowledge point information. Then, it can match the knowledge point information with nodes in the knowledge graph. The matching method can be semantic matching based on the knowledge point's name and description text, or it can be assisted by combining contextual information such as the knowledge point's position in the textbook and its chapter. Based on the matching results, it can link the extracted knowledge point information with the corresponding graph nodes in the knowledge graph, establishing a connection between learning behavior and the knowledge graph. Based on the graph nodes linked with knowledge point information, it can extract the corresponding attributes (such as difficulty, importance, and learning time), associated edges (such as prerequisite relationships, relevance relationships, and corresponding weights), centrality indicators, and other graph knowledge point information. After integrating the graph knowledge point information, it can generate the student's learning knowledge point data in the knowledge graph.

[0150] In this embodiment of the application, multi-dimensional information matching can be the matching of learning content data and learning knowledge point data by the knowledge point positioning module 6 from multiple perspectives such as content, context, and location.

[0151] In this embodiment of the application, the knowledge point location information may be the specific location and relationship of the unmastered knowledge point in the knowledge graph corresponding to the knowledge point learning grid, as determined by the knowledge point location module 6. The knowledge point location information may include the prerequisite knowledge points, subsequent knowledge points, related knowledge points, and centrality indicators in the knowledge network.

[0152] In this embodiment of the application, the learning content data can be the specific content that the student encounters when learning knowledge points that they have not mastered, as determined by the knowledge point positioning module 6, such as the application scenarios of knowledge points involved in the questions, the key points of knowledge points recorded in the notes, and the points of doubt.

[0153] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0154] Example 51: The knowledge point location module 6 is used to generate student learning content data based on question information and note information; to perform similarity matching based on the first semantic embedding vector corresponding to the learning content data and the second semantic embedding vector corresponding to the learning knowledge point data, so as to match the content similarity between the learning content data and the learning knowledge point data, and obtain a first similarity matching result; to perform similarity matching based on the context data corresponding to the learning content data and the adjacent knowledge point data corresponding to the learning knowledge point data, so as to match the overall similarity between the learning content data and the learning knowledge point data in the knowledge graph, and obtain a second similarity matching result; to perform similarity matching based on the first position data of the learning content data in the textbook and the second position data of the learning knowledge point data in the textbook, so as to match the position similarity between the learning content data and the learning knowledge point data, and obtain a third similarity matching result; based on the first similarity matching result, the second similarity matching result, and the third similarity matching result, knowledge point location information of the set of unmastered knowledge points is generated.

[0155] Example 52: The knowledge point location module 6 is used to perform fusion analysis based on the first similarity matching result, the second similarity matching result, and the third similarity matching result to evaluate the accuracy of the location of knowledge points in the set of unmastered knowledge points, and obtain the location reliability data of the learning content data and the learning knowledge point data; based on the location reliability data, it selects unmastered knowledge points that meet the confidence conditions from the set of unmastered knowledge points to form a location knowledge point set; and generates the knowledge point location information of the set of unmastered knowledge points based on the prerequisite relationships and correlation relationships of the knowledge points in the location knowledge point set in the knowledge graph.

[0156] Example 53: The knowledge point location module 6 is used to determine, based on the prerequisite relationships of knowledge points in the location knowledge point set in the knowledge graph, a first knowledge point set consisting of prerequisite knowledge points corresponding to the location knowledge point set in the knowledge graph, and a second knowledge point set with knowledge points in the location knowledge point set as prerequisite knowledge points; based on the location knowledge point set, the first knowledge point set, and the second knowledge point set, extract the knowledge point dependency relationship chain corresponding to the unmastered knowledge point set from the knowledge graph; based on the correlation relationship of knowledge points in the location knowledge point set in the knowledge graph, determine a third knowledge point set related to the location knowledge point set in the knowledge graph; based on the location knowledge point set and the third knowledge point set, extract the knowledge point related relationship chain corresponding to the unmastered knowledge point set; and generate knowledge point location information for the unmastered knowledge point set based on the knowledge point dependency relationship chain and the knowledge point related relationship chain.

[0157] It should be noted that this embodiment achieves accurate collection of core data related to student learning by obtaining learning behavior data of students' unmastered knowledge points in the knowledge point learning grid from the learning companion system and determining question information and note information, providing a reliable data foundation for subsequent knowledge point association matching; by mapping the learning behavior data in the knowledge graph corresponding to the knowledge point learning grid, a deep correspondence between the learning behavior data and the knowledge graph structure is achieved, providing graph-level support for knowledge point positioning; by generating learning content data based on question information and note information and performing multi-dimensional information matching with learning knowledge point data, accurate positioning of unmastered knowledge points is achieved, improving the accuracy of knowledge point positioning; by updating and recommending the set of unmastered knowledge points based on students' target learning intentions and knowledge point positioning information, accurate matching between the target set of unmastered knowledge points and students' actual learning needs is achieved.

[0158] Optionally, the learning path generation module 2 is used to determine the knowledge points to be reviewed indicated by the knowledge point review path based on the student's review path of the learned knowledge points in the target knowledge point learning grid, and send the knowledge points to be reviewed to the knowledge point learning grid module 1; the knowledge point learning grid module 1 is used to extract the network of knowledge points to be reviewed corresponding to the knowledge points to be reviewed from the knowledge graph corresponding to the target knowledge point learning grid, the network of knowledge points to be reviewed includes at least one prerequisite knowledge point and at least one related knowledge point corresponding to the knowledge point to be reviewed, and send the knowledge point to be reviewed, at least one prerequisite knowledge point and at least one related knowledge point to the learning path generation module 2; the learning path generation module 2 is used to update the knowledge point review path according to the student's mastery of the knowledge point to be reviewed, at least one prerequisite knowledge point and at least one related knowledge point to obtain the target knowledge point review path corresponding to the knowledge point to be reviewed; based on the target knowledge point review path, the student's target knowledge points to be reviewed are determined, and recommendation information of the target knowledge points to be reviewed is generated to recommend the target knowledge points to be reviewed to the student.

[0159] In this embodiment of the application, the knowledge point review path can be the knowledge point sequence path that the student follows when reviewing the learned knowledge points in the target knowledge point learning grid, as determined by the learning path generation module 2. The knowledge point review path can be pre-generated or dynamically adjusted based on the student's previous learning trajectory, the knowledge logic of the course, the teaching syllabus requirements, etc. The knowledge point review path can be used to guide the student to systematically review the learned content.

[0160] In this embodiment of the application, the knowledge points to be reviewed can be the knowledge points that students need to focus on reviewing, as indicated in the knowledge point review path of the learning path generation module 2. The knowledge points to be reviewed can include knowledge points that students have not mastered to the preset standard, have knowledge gaps, or need to be strengthened and consolidated.

[0161] In this embodiment of the application, the learning path generation module 2 obtains the knowledge point review path in the target knowledge point learning grid where the student reviews the knowledge points that have been learned. The knowledge points to be reviewed indicated by the knowledge point review path can be determined by the learning companion system first retrieving the student's learning records in the target knowledge point learning grid through the student's user ID, including the knowledge points that have been learned, the learning time of each knowledge point, the practice questions (accuracy rate, number of wrong questions, redoing status), the online course learning progress (video viewing completion rate, number of repeated viewings, dwell time), the number of notes, the frequency of asking questions, and other data. Then, the system extracts the knowledge point review path for the student to review the knowledge points that have been learned. Subsequently, the system combines the student's mastery of each knowledge point data to filter out the knowledge points that need to be reviewed and determine them as the knowledge points to be reviewed indicated by the knowledge point review path.

[0162] In the embodiments of this application, the knowledge point network to be reviewed can be a sub-network in the knowledge graph of the knowledge point learning grid module 1 that is directly related to the knowledge point to be reviewed. The knowledge point network to be reviewed can include the knowledge point to be reviewed itself, as well as at least one prerequisite knowledge point that has a prerequisite relationship with the knowledge point to be reviewed and at least one related knowledge point that has a correlation relationship. The knowledge point network to be reviewed can be used to present the knowledge dependency and correlation of the knowledge point to be reviewed.

[0163] In the embodiments of this application, the prerequisite knowledge points can be the knowledge points that need to be mastered in advance before learning the knowledge points to be reviewed, as determined by the knowledge point learning grid module 1. Mastering the prerequisite knowledge points can be the basis for understanding and mastering the knowledge points to be reviewed.

[0164] In this embodiment of the application, the relevant knowledge points can be those that are related or complementary to the knowledge points to be reviewed in terms of content, as determined by the knowledge point learning grid module 1, but do not need to strictly follow the order of learning.

[0165] In this embodiment of the application, the process of extracting the network of knowledge points to be reviewed from the knowledge graph corresponding to the target knowledge point learning grid can be as follows: the knowledge point learning grid module 1 first locates the knowledge graph corresponding to the target knowledge point learning grid. The knowledge graph corresponding to the target knowledge point learning grid is constructed based on the course content of the student's current semester. The knowledge graph corresponding to the target knowledge point learning grid can include all knowledge points in the course and the relationships between knowledge points. Then, the knowledge point learning grid module 1 extracts all nodes and edges related to the knowledge points to be reviewed from the knowledge graph corresponding to the target knowledge point learning grid to form the network of knowledge points to be reviewed.

[0166] For example, extracting all nodes and edges related to the knowledge point to be reviewed from the knowledge graph corresponding to the target knowledge point learning grid can specifically include: the knowledge point learning grid module 1 can search for nodes corresponding to directed edges pointing to the knowledge point to be reviewed in the knowledge graph, and the nodes corresponding to the directed edges of the knowledge point to be reviewed can be the prerequisite knowledge points of the knowledge point to be reviewed; the knowledge point learning grid module 1 can search for nodes connected to the knowledge point to be reviewed through undirected edges, and the nodes connected to the knowledge point to be reviewed through undirected edges can be the related knowledge points of the knowledge point to be reviewed.

[0167] In this embodiment of the application, the degree of mastery can be a quantitative indicator of a student's understanding and application of knowledge points. The degree of mastery can be calculated through students' learning behavior data (such as the accuracy rate of answering questions, the progress of online learning, the number of notes, the frequency of asking questions, etc.).

[0168] For example, in the embodiments of this application, the degree of mastery can be represented by the mastery probability, which can be in the range of [0,1]. The degree of mastery can have different mastery indicators, such as no mastery indicator, mastery but not proficient indicator, and mastery indicator (i.e., proficiency indicator), to provide data support for adjusting the review path.

[0169] In this embodiment, the target knowledge point review path can be a review path that is more in line with the actual learning situation of students, obtained by the learning path generation module 2 after adjusting the initial knowledge point review path based on the students' mastery of relevant knowledge points. The target knowledge point review path can be used to help students make up for knowledge gaps in a targeted manner and improve review efficiency.

[0170] In this embodiment, the student's mastery of the knowledge point to be reviewed, at least one prerequisite knowledge point, and at least one related knowledge point can be determined by the learning path generation module 2 first obtaining the student's mastery data on the unreviewed knowledge point, at least one prerequisite knowledge point, and at least one related knowledge point corresponding to the knowledge point to be reviewed from the mastery analysis module 4. The mastery data can be obtained by analyzing the student's learning behavior data, which may include the accuracy rate of completing practice questions, the accuracy rate of redoing incorrect questions, the completion rate of watching online course videos, the number of times repeated viewing, the number of notes, the frequency of asking questions, etc. The mastery probability of the knowledge point to be reviewed, at least one prerequisite knowledge point, and at least one related knowledge point can be calculated using models such as logistic regression model and softmax regression model, and then the mastery level identifier corresponding to the knowledge point to be reviewed, at least one prerequisite knowledge point, and at least one related knowledge point can be determined.

[0171] In this embodiment of the application, the learning path generation module 2 can adjust and update the initial knowledge point review path based on the mastery level indicators of the knowledge point to be reviewed, at least one prerequisite knowledge point, and at least one related knowledge point. For example, if the mastery level indicator of prerequisite knowledge point A is "not mastered," then prerequisite knowledge point A can be added to the review path and prioritized for review; if the mastery level indicator of related knowledge point B is "mastered," then the review content of related knowledge point B can be appropriately simplified or skipped in the review path; if the mastery level of knowledge point C to be reviewed is low, then the review time and practice intensity of knowledge point C can be increased in the path, and finally, the target knowledge point review path corresponding to the knowledge point to be reviewed can be obtained.

[0172] In this embodiment of the application, the target knowledge point to be reviewed can be the knowledge point that the student currently needs to review most, as indicated in the target knowledge point review path in the learning path generation module 2. For example, in this embodiment of the application, the target knowledge point to be reviewed can specifically be a high-priority knowledge point selected based on factors such as mastery level, importance of knowledge point, and strength of correlation.

[0173] In this embodiment of the application, the recommended information may be information determined by the learning path generation module 2, including learning suggestions, learning resources, learning time planning, testing methods, etc. for the target knowledge points to be reviewed. The recommended information can be used to intuitively guide students to efficiently review the target knowledge points to be reviewed, clarify the review direction and specific requirements.

[0174] In this embodiment of the application, determining the student's target knowledge points to be reviewed based on the target knowledge point review path can be achieved by the learning path generation module 2 prioritizing all knowledge points in the target knowledge point review path. The prioritization criteria can include the degree of mastery of the knowledge points (the lower the degree of mastery, the higher the priority), the importance of the knowledge points (based on the centrality indicators of nodes in the knowledge graph, such as betweenness centrality, degree centrality, proximity centrality, etc.; the higher the centrality, the more critical the knowledge point is in the knowledge network, and the higher the priority), and the strength of the association between the knowledge points and the knowledge points to be reviewed (the stronger the association, the greater the support for mastering the knowledge points to be reviewed, and the higher the priority). The system can select one or more knowledge points with the highest priority as the student's target knowledge points to be reviewed and generate corresponding recommendation information.

[0175] For the embodiments of this application, the recommended information may include the specific learning content of the target knowledge points to be reviewed (such as key concepts, core theorems, and common mistakes), recommended learning resources (such as targeted online course videos, special practice question sets, knowledge point explanation documents, and interactive learning tools), suggested learning time, learning order (such as reviewing basic concepts first, then analyzing example problems, and finally completing practice questions), and testing methods.

[0176] In this embodiment of the application, recommending review targets and knowledge points to be reviewed to students can be achieved by the learning path generation module 2 displaying the recommendation information to students through the learning tablet's learning companion system in the form of pop-ups, message pushes, or path annotations, thereby guiding students to review the target knowledge points according to the recommended content.

[0177] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0178] Example 61: The learning path generation module 2 is used to determine the knowledge point mastery level indicator of the knowledge point to be reviewed from the knowledge point network to be reviewed; when the knowledge point mastery level indicator of the knowledge point to be reviewed is not mastered, it determines the first knowledge point mastery level indicator of at least one prerequisite knowledge point and the second knowledge point mastery level indicator of at least one related knowledge point in the knowledge point network to be reviewed; based on the first knowledge point mastery level indicator and the second knowledge point mastery level indicator, it updates the knowledge point review path to obtain the target knowledge point review path corresponding to the knowledge point to be reviewed.

[0179] Example 62: The learning path generation module 2 is used to determine the set of first knowledge points that the student has mastered from at least one prerequisite knowledge point and at least one related knowledge point based on the mastery level identifier of the first knowledge point and the mastery level identifier of the second knowledge point; remove the set of first knowledge points from the network of knowledge points to be reviewed, and use the knowledge points to be reviewed as the starting point of the review path to update the network of knowledge points to be reviewed, so as to obtain the target knowledge point review path corresponding to the knowledge points to be reviewed.

[0180] Example 63: The learning path generation module 2 is used to determine a set of second knowledge points that the student has not mastered from at least one prerequisite knowledge point and at least one related knowledge point, based on the mastery level identifier of the first knowledge point and the mastery level identifier of the second knowledge point; determine the learning priority information of the knowledge points in the second knowledge point set; select the first target knowledge point that meets the priority condition from the second knowledge point set based on the learning priority information; use the first target knowledge point as the starting point of the review path, update the network of knowledge points to be reviewed, and obtain the review path of the target knowledge point.

[0181] Example 64: The learning path generation module 2 is used to determine the mastery probability data and knowledge point difficulty data of each knowledge point in the second knowledge point set; evaluate the learning priority of each knowledge point in the second knowledge point set based on the mastery probability data and knowledge point difficulty data, and obtain the learning priority information of each knowledge point in the second knowledge point set; and determine the knowledge point with the highest learning priority information in the second knowledge point set as the first target knowledge point.

[0182] Example 65: The knowledge point learning grid module 1 is used to determine the knowledge point traversal range based on the knowledge point to be reviewed when the knowledge point mastery level is marked as mastered; traverse the knowledge points within the knowledge point traversal range to obtain a third set of knowledge points that the student has not mastered; determine the corresponding set of prerequisite knowledge points and related knowledge points in the knowledge graph; determine the second target knowledge point that meets the priority condition from the third knowledge point set, the set of prerequisite knowledge points, and the set of related knowledge points; remove the knowledge point to be reviewed from the knowledge point network, and use the second target knowledge point as the starting point of the review path to update the knowledge point network and obtain the target knowledge point review path.

[0183] It should be noted that this embodiment extracts a network of knowledge points to be reviewed from the knowledge graph, consisting of prerequisite knowledge points and related knowledge points. It then updates the review path based on the student's mastery of these knowledge points, thus adapting the review path to the student's cognitive state. By generating recommendation information based on the updated target knowledge point review path, the accuracy of the review knowledge point recommendations is improved, helping students focus on core review content.

[0184] Optionally, the knowledge point learning grid module 1 is used to update the first mastery level identifier of the target knowledge point in response to the learning behavior collection module obtaining the fourth learning behavior data of the student reviewing the target knowledge point; determine the update influence range of the mastery level of the target knowledge point in the knowledge graph corresponding to the knowledge point learning grid, and form a set of knowledge points to be updated based on the knowledge points covered by the update influence range; update the mastery level data of the knowledge points in the set of knowledge points to be updated, and update the second mastery level identifier of the knowledge points in the set of knowledge points to be updated based on the updated mastery level data; update the knowledge point learning grid to the target knowledge point learning grid based on the second mastery level identifier, and determine the student's target review content based on the target knowledge point learning grid.

[0185] In this embodiment of the application, the set of knowledge points to be reviewed can be the set of all knowledge points that the student has learned and needs to review in the knowledge point learning grid module 1; correspondingly, the target knowledge point can be the knowledge point that the student is currently reviewing in the set of knowledge points to be reviewed in the knowledge point learning grid module 1.

[0186] In the embodiments of this application, the first mastery level identifier can be a mark in the knowledge point learning grid module 1 that represents the student's mastery of the target knowledge point. The first mastery level identifier can be used to reflect the student's knowledge mastery status and can be determined based on the mastery probability of the target knowledge point.

[0187] For example, the first mastery level indicator in the embodiments of this application may include a not mastered indicator, a mastered but not proficient indicator, a mastered indicator, etc. The presentation form of the first mastery level indicator may include color marking (such as red corresponding to not mastering the knowledge point, yellow corresponding to mastering the knowledge point but not proficient, and green corresponding to mastering the knowledge point), text annotation, symbol marking, etc.

[0188] In this embodiment of the application, the fourth learning behavior data may include multi-dimensional data such as the completion rate of online course review for the target knowledge point, the accuracy rate of practice questions, the redoing of wrong questions, the review time, the supplementary content of notes, and the frequency of asking questions.

[0189] In this embodiment, the learning behavior collection module 3 can monitor the students' review operations in the learning companion system in real time. When the system detects that the students are reviewing the target knowledge points in the review knowledge point set, it can obtain the corresponding review behavior data. The knowledge point learning grid module 1 can calculate the mastery probability of the target knowledge points based on the behavior data system through a preset model (including but not limited to logistic regression model and softmax regression model), and then update the first mastery level label of the target knowledge points according to the threshold rule.

[0190] For example, updating the first mastery level indicator of the target knowledge point in the embodiments of this application may specifically include: if the initial first mastery level indicator is a mastery level indicator, and the mastery probability after review reaches a threshold, the first mastery level indicator can be updated to a mastery indicator; if the mastery probability after review does not reach the threshold, the first mastery level indicator can be maintained as a mastery indicator.

[0191] In this embodiment of the application, the second mastery level identifier can be a mastery status marker corresponding to the knowledge point in the knowledge point set to be updated in the knowledge point learning grid module 1 after the mastery level data is updated. For example, the second mastery level identifier in this embodiment of the application may specifically include a not mastered identifier, a mastered but not proficient identifier, a mastered identifier, etc., and the presentation form of the second mastery level identifier may include color markings (such as red corresponding to not mastering the knowledge point, yellow corresponding to mastering the knowledge point but not proficient, and green corresponding to mastering the knowledge point), text annotations, symbol markings, etc.

[0192] In this embodiment, the knowledge point learning grid module 1 can update the original mastery data by combining factors such as changes in the mastery level of the target knowledge point, the association type (prerequisite or related) between the knowledge point to be updated and the target knowledge point, and the association strength weight.

[0193] For example, if the mastery of the target knowledge point is significantly improved and there is a strong prerequisite relationship between the target knowledge point and the knowledge point to be updated, the mastery data of the knowledge point to be updated can be improved accordingly; if there is a weak correlation between the target knowledge point and the knowledge point to be updated, the change in the mastery data of the knowledge point to be updated can be relatively small.

[0194] In this embodiment, the knowledge point learning grid module 1 can determine the second mastery level identifier for each knowledge point based on the updated mastery level data and threshold rules. For example, if the updated mastery probability of knowledge point A is lower than the basic threshold, the second mastery level identifier for knowledge point A can be marked as "not mastered"; if the updated mastery probability of knowledge point A is between the basic threshold and the proficiency threshold, the second mastery level identifier for knowledge point A can be marked as "mastered but not proficient"; if the updated mastery probability of knowledge point A is higher than the proficiency threshold, the second mastery level identifier for knowledge point A can be marked as "mastered". Simultaneously, the system can combine special rules such as key knowledge point protection and basic knowledge point acceleration to optimize and adjust the second mastery level identifier, ensuring that the second mastery level identifier accurately reflects the actual mastery status of the knowledge point.

[0195] In this embodiment of the application, the target knowledge point learning grid can be a knowledge point learning grid that reflects the student's latest knowledge mastery status after the knowledge point learning grid module 1 synchronously updates the second mastery level identifier of the knowledge points in the set of knowledge points to be updated. The target knowledge point learning grid can be used to present the student's current knowledge gaps and mastery status in real time and accurately.

[0196] In this embodiment of the application, the target review content may be the knowledge points that need to be reviewed by the knowledge point learning grid module 1 based on the mastery status of the knowledge points in the target knowledge point learning grid, as well as the corresponding learning resources, learning arrangements, etc.

[0197] In this embodiment, the knowledge point learning grid module 1 can synchronize the second mastery level identifiers of all knowledge points in the set of knowledge points to be updated to the original knowledge point learning grid and replace the original identifiers to complete the update of the target knowledge point learning grid. The knowledge point learning grid module 1 can analyze the second mastery level identifiers of knowledge points in the target knowledge point learning grid, prioritize the selection of knowledge points marked as not mastered and mastered but not proficient, and determine the target review content that needs to be focused on by combining the importance of knowledge points (based on the centrality index of the knowledge graph), correlation, teaching progress, exam focus and other factors.

[0198] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0199] Example 71: The knowledge point learning grid module 1 is used to determine the direct dependencies of target knowledge points based on the target prerequisite relationships and target relevance relationships in the knowledge graph, and to determine the direct impact range based on the direct dependencies; to determine the indirect dependencies of target knowledge points based on the indirect connection relationships between target knowledge points and other knowledge points in the knowledge graph, and to determine the indirect impact range based on the indirect dependencies; to determine the set of directly impacted knowledge points covered by the direct impact range, and the set of indirect impacted knowledge points covered by the indirect impact range; and to generate a set of knowledge points to be updated based on the set of directly impacted knowledge points and the set of indirect impacted knowledge points.

[0200] Example 72: The knowledge point learning grid module 1 is used to determine the first indirect dependency relationship established by a target knowledge point through an indirect knowledge point in the knowledge graph, and the second indirect dependency relationship connected by multiple indirect knowledge points; based on the first influence decay degree corresponding to the first indirect dependency relationship, the first influence range of the target knowledge point based on the first indirect dependency relationship is determined from the knowledge graph; based on the second influence decay degree corresponding to the second indirect dependency relationship, the second influence range of the target knowledge point based on the second indirect dependency relationship is determined from the knowledge graph; and the indirect influence range is determined based on the first influence range and the second influence range.

[0201] Example 73: The knowledge point learning grid module 1 is used to determine the dependency strength data between the knowledge points in the knowledge point set to be updated and the target knowledge points based on direct and indirect dependencies; to identify the importance data of the knowledge points in the knowledge point set to be updated through the target model, which is trained based on students' historical behavioral characteristics and historical knowledge point mastery; to determine the update priority information of the knowledge points in the knowledge point set to be updated based on the dependency strength data, importance data, and mastery level data; to update the mastery level data according to the update priority information; and to update the second mastery level identifier of the knowledge points in the knowledge point set to be updated based on the updated mastery level data.

[0202] Example 74: The knowledge point learning grid module 1 is used to determine the knowledge point update order list corresponding to the knowledge point set to be updated according to the update priority information, so as to determine the update order of knowledge points in the knowledge point set to be updated; for the first target knowledge point in the knowledge point set to be updated, the centrality adjustment coefficient corresponding to the first target knowledge point is determined based on the connection strength data of the first target knowledge point in the knowledge graph, the distance data between the first target knowledge point and other knowledge points, and the degree centrality coefficient. The first target knowledge point is any knowledge point in the knowledge point set to be updated; the mastery level data of the first target knowledge point is updated based on the centrality adjustment coefficient and the change in the mastery level data of the target knowledge point; the second mastery level identifier of the knowledge point in the knowledge point set to be updated is updated based on the updated mastery level data of the knowledge points in the knowledge point set to be updated.

[0203] Example 75: The knowledge point learning grid module 1 is used to determine the first target knowledge point as a key knowledge point and mark the second mastery level identifier of the first target knowledge point as a not mastered identifier when the connection strength data in the centrality adjustment coefficient is greater than the connection strength threshold and the change in the mastery level data is less than the first change threshold; when the degree centrality coefficient in the centrality adjustment coefficient is greater than the degree centrality threshold and the mastery level data is greater than the second mastery level threshold, the first target knowledge point is determined as a basic knowledge point and the second mastery level identifier of the first target knowledge point is marked as a mastered identifier.

[0204] It should be noted that this embodiment updates the first mastery level identifier of students in response to their review behavior data of the target knowledge point, and determines the update influence range of the target knowledge point in the knowledge graph to form a set of knowledge points to be updated, thereby realizing the dynamic linkage update of the mastery status of knowledge points; by updating the mastery level data and the second mastery level identifier of the set of knowledge points to be updated, the knowledge point learning grid is updated and the target review content is determined, thereby improving the matching degree between the review content and the students' actual cognitive state.

[0205] Optionally, it also includes a knowledge point status analysis module 7; the knowledge point status analysis module 7 is connected to the learning behavior collection module 3 and the knowledge point learning grid module 1 respectively; the knowledge point status analysis module 7 is used to obtain the fifth learning behavior data of students learning knowledge points in the knowledge point learning grid from the learning behavior collection module 3, and to obtain the mastery level identifier of knowledge points in the knowledge point learning grid from the knowledge point learning grid module 1, and send the fifth learning behavior data and mastery level identifier to the knowledge point status analysis module; the knowledge point status analysis module 7 is used to determine the second mastery level data of students learning knowledge points in the knowledge point learning grid based on the fifth learning behavior data, and evaluate the second knowledge point status data of knowledge points in the knowledge point learning grid based on the second mastery level data; based on the first knowledge point status data and the second knowledge point status data corresponding to the first mastery level data, it determines the abnormal knowledge points in the knowledge point learning grid, and sends the abnormal knowledge points to the knowledge point learning grid module 1; the knowledge point learning grid module 1 is used to update the knowledge graph corresponding to the knowledge point learning grid based on the abnormal knowledge points, and obtain the updated target knowledge graph, which is used to generate the target knowledge point learning grid.

[0206] In this embodiment of the application, the fifth learning behavior data may include multi-dimensional data such as the student's online course completion rate for the target knowledge point, the accuracy rate of answering questions, the redoing of wrong questions, the learning time, the supplementary content of notes, and the frequency of asking questions.

[0207] In this embodiment of the application, the learning behavior collection module 3 can monitor the learning operations of students in the learning companion system in real time. When the system detects that a student is learning a knowledge point, it can obtain the corresponding learning behavior data.

[0208] In some examples, the knowledge point status data can be the data on the student's mastery of different knowledge points as determined by the learning companion system, as determined by the knowledge point status analysis module 7. It should be noted that there is a mapping relationship between the mastery level identifier and the knowledge point status data in this application embodiment. That is, this application embodiment can determine the mastery level identifier of different knowledge points by the presentation of different knowledge points in the knowledge point learning grid, and can also determine the knowledge point status data of different knowledge points by the mastery level identifier of different knowledge points marked in the knowledge point learning grid.

[0209] In this application embodiment, the second mastery level identifier can be an identifier of the student's actual mastery level of knowledge points obtained based on the analysis of the student's current learning behavior data. For example, in this application embodiment, the second mastery level identifier can reflect the student's mastery of knowledge points as analyzed by the current learning companion system based on the student's learning behavior data.

[0210] For example, the second mastery level indicator in the embodiments of this application may include a not mastered indicator, a mastered but not proficient indicator, a mastered indicator, etc. The presentation form of the second mastery level indicator may include color markings (such as red corresponding to not mastering the knowledge point, yellow corresponding to mastering the knowledge point but not proficient, and green corresponding to mastering the knowledge point), text annotations, symbol markings, etc. The embodiments of this application can determine the mastery level indicator of different knowledge points by presenting different knowledge points in the knowledge point learning grid.

[0211] In some examples, the second knowledge point status data can be the actual mastery status data of students on different knowledge points as determined by the knowledge point status analysis module 7. It should be noted that the learning companion system in this application embodiment has the ability to analyze mastery status data. Specifically, through learning behavior data, the learning companion system can identify the actual mastery of knowledge points in the knowledge point learning grid, and then determine the actual mastery level of knowledge points in the knowledge point learning grid, thereby determining the actual status data of knowledge points in the knowledge point learning grid.

[0212] In this application, the knowledge point learning grid module 1 compares the first knowledge point status data and the second knowledge point status data. That is, the knowledge point status data of different knowledge points are determined by the mastery level of different knowledge point markers through the knowledge point learning grid, and compared with the actual status data of knowledge points in the knowledge point learning grid based on learning behavior data analysis. Abnormal knowledge points with inconsistent status can be identified. Then, the knowledge graph corresponding to the knowledge point learning grid is updated according to the abnormal knowledge points to obtain the updated target knowledge graph, and then the updated target knowledge point learning grid is generated.

[0213] In this embodiment of the application, the target knowledge point learning grid can be a knowledge point learning grid that reflects the student's latest and most accurate knowledge mastery status after updating the mastery level label of abnormal knowledge points. The target knowledge point learning grid can be used to present the student's current knowledge gaps and mastery status in real time and accurately.

[0214] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0215] Example 81: Based on the first knowledge point status data and the second knowledge point status data, a status data difference analysis is performed to evaluate the degree of difference between the knowledge point mastery status displayed in the knowledge point learning grid and the student's mastery status of the knowledge points in the knowledge point learning grid; based on learning behavior data, the question information and note information of the student's learning of the knowledge points in the knowledge point learning grid are determined; based on the question information, note information, and first mastery level data, the student's learning status information of the knowledge points in the knowledge point learning grid is determined; based on the learning status information and the degree of difference, abnormal knowledge points are identified from the knowledge point learning grid; based on the abnormal knowledge points, the knowledge graph corresponding to the knowledge point learning grid is updated to obtain the updated target knowledge graph.

[0216] Example 82: Based on note information, determine the update frequency of students' notes within a target time range, and evaluate the students' learning activity data for knowledge points in the knowledge point learning grid within the target time range based on the update frequency; based on note information and question information, determine the frequency of students' questions about knowledge points in the knowledge point learning grid, and evaluate the students' difficulty in understanding knowledge points in the knowledge point learning grid based on the question frequency; if the learning activity data is greater than the activity threshold and / or the difficulty in understanding data is greater than the difficulty threshold and / or the first mastery level data is less than the mastery level threshold, determine the students' learning status information for knowledge points in the knowledge point learning grid as abnormal learning status information.

[0217] Example 83: When the student's learning status information for knowledge points in the knowledge point learning grid is abnormal, the stability data of knowledge points in the knowledge point learning grid in the knowledge graph is evaluated based on the betweenness centrality data and proximity centrality data of knowledge points in the knowledge point learning grid; the credibility data of abnormal learning status information is determined based on the stability data and the degree of difference; abnormal knowledge points are identified from the knowledge point learning grid based on the credibility data, learning status information, and degree of difference; the knowledge graph corresponding to the knowledge point learning grid is updated based on the abnormal knowledge points to obtain the updated target knowledge graph.

[0218] Example 84: Divide the student's learning behavior data in the target knowledge point learning grid into at least one learning behavior data set, and generate a behavioral feature set corresponding to at least one learning behavior data set; determine the time information corresponding to each behavioral feature in the behavioral feature set, and evaluate the effectiveness of each behavioral feature in the behavioral feature set based on the time information to obtain the effective value data of each behavioral feature in the behavioral feature set; filter the behavioral features in the behavioral feature set based on the effective value data to obtain the target behavioral features that meet the effective conditions in the behavioral feature set, and form a target behavioral feature set from the target behavioral feature set; identify the box-selection behavior from the target behavioral feature set, and classify the learning content selected by the box-selection behavior to obtain the question information and note information of the student learning the knowledge points in the abnormal knowledge point set.

[0219] This embodiment obtains student learning behavior data on knowledge points in the knowledge point learning grid from the learning companion system, as well as the mastery level indicators of the knowledge points in the knowledge point learning grid. It can determine the first mastery level data and the first knowledge point status based on the mastery level indicators. It can also analyze the student's second mastery level data and the second knowledge point status based on the learning behavior. By analyzing the difference between the two, abnormal knowledge points with abnormal knowledge point status markings can be identified. The target knowledge graph is then updated based on the abnormal knowledge points, and the target knowledge point learning grid is updated. This embodiment can actively verify and calibrate the consistency of knowledge point status through two different knowledge point statuses. This allows this embodiment to accurately identify the difference between the mastery status in the knowledge grid and the behavior inference status implicit in the real-time learning behavior data stream, thereby clarifying the student's need for updating the knowledge graph. This allows the student to learn based on the updated knowledge graph, improving the learning effect.

[0220] Optionally, the knowledge point learning grid module 1 is used to determine the state correction content corresponding to the knowledge point with an abnormal state; based on the correction content, the abnormal knowledge point is corrected in the knowledge point learning grid, and the mastery level impact data after the abnormal knowledge point is corrected is determined; based on the mastery level impact data, the influence range of the mastery level impact data in the knowledge graph corresponding to the knowledge point learning grid is determined, and the knowledge graph is updated within the influence range.

[0221] In some examples, for abnormal knowledge points that need correction, the corresponding state correction content for the abnormal knowledge point can be determined, that is, the content that needs to be corrected based on the mastery level of the abnormal knowledge point. For example, if the knowledge point state data of knowledge point 1 is determined to be 0.3 (if the mastery data range is 0-1) based on the mastery level of different knowledge points marked by the knowledge point learning grid, and if the actual state data of knowledge point 1 in the knowledge point learning grid based on the learning behavior data analysis is 0.7 (if the mastery data range is 0-1), then the correction content corresponding to knowledge point 1 can be determined based on the knowledge point state data of 0.3 and the actual state data of 0.7. Then, the state of knowledge point 1 can be corrected based on the correction content, and the influence range of the corrected knowledge point 1 in the knowledge graph can be determined.

[0222] As an alternative approach, if the knowledge point status data of knowledge point 2 is determined to be level 1 (if the mastery data includes levels 1-5) by identifying the mastery level of different knowledge point markers through the knowledge point learning grid, and if the actual status data of knowledge point 2 in the knowledge point learning grid based on the analysis of learning behavior data is level 4 (if the mastery data includes levels 1-5), then the correction content corresponding to knowledge point 2 can be determined based on the knowledge point status data being level 1 and the actual status data being level 4. Furthermore, the status of knowledge point 2 can be corrected based on the correction content, and the influence range of the corrected knowledge point 2 in the knowledge graph can be determined.

[0223] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0224] Example 91: When the first mastery level identifier is a mastery identifier, determine the question information and note information of the student's learning of knowledge points in the knowledge point learning grid based on learning behavior data; evaluate the student's learning needs for knowledge points with abnormal status based on question information and note information, and obtain the learning intention intensity data corresponding to the knowledge points with abnormal status; determine the first mastery level data corresponding to the knowledge points with abnormal status based on the first mastery level identifier; when the learning intention intensity data is greater than the learning intention intensity threshold and the first mastery level data is less than the mastery level threshold, determine the first non-mastery identifier as the second mastery level identifier; determine the first state correction content corresponding to the knowledge points with abnormal status based on the mastery identifier and the first non-mastery identifier.

[0225] Example 92: When the first mastery level identifier is the first non-mastery identifier, the student's question information and note information for learning knowledge points in the knowledge point learning grid are determined based on learning behavior data; the frequency of questions the student has about knowledge points with abnormal status is determined based on the note information and question information, and the student's difficulty in understanding knowledge points with abnormal status is evaluated based on the question frequency; the student's score data for the questions corresponding to the knowledge points with abnormal status is determined; when the difficulty in understanding data is greater than the difficulty in understanding threshold and the score data is less than the score threshold, the second non-mastery identifier is determined as the second mastery level identifier; based on the first non-mastery identifier and the second non-mastery identifier, the second status correction content corresponding to the knowledge points with abnormal status is determined.

[0226] It should be noted that this embodiment determines the student's learning status information for knowledge points in the knowledge point learning grid. When the learning status information is abnormal, it determines the correction content corresponding to the abnormal knowledge point. Then, based on the correction content, it corrects the status of the abnormal knowledge point in the knowledge point learning grid. Based on the mastery level impact data after the abnormal knowledge point's status correction, it updates the knowledge graph, thereby generating an updated target knowledge graph. This embodiment can promptly handle situations where the system-evaluated student mastery level does not match the actual situation, accurately identify the status error of the knowledge point, and update the mastery level of other affected knowledge points in the knowledge graph based on the propagation of the error in the graph. This results in an accurate graph, allowing for the recommendation of accurate learning content to students and improving their learning outcomes.

[0227] Optionally, a learning materials recommendation module 8 is also included. The learning materials recommendation module 8 is connected to the learning behavior collection module 3 and the learning path generation module 2, respectively. The learning materials recommendation module 8 is used to obtain students' historical learning data from the learning behavior collection module 3, determine students' learning ability data and learning status information of students' knowledge points in the knowledge point learning grid based on the students' historical learning data, and send the learning status information to the learning path generation module 2. The learning path generation module 2 is used to determine the type of students' learning plan based on the learning ability data and learning status information, and determine the set of knowledge points to be learned in the knowledge point learning grid according to the type of learning plan. Based on the set of knowledge points to be learned, the learning path to be learned is generated for the students in the knowledge point learning grid, and the learning path to be learned is sent to the learning materials recommendation module 8. The learning materials recommendation module 8 is used to determine the set of learning materials that match the learning path to be learned from the learning materials, so as to recommend students to learn the set of knowledge points to be learned based on the set of learning materials.

[0228] In this embodiment of the application, historical learning data can be various historical records generated by students during their learning process in the learning companion system, which are obtained by the learning materials recommendation module 8 from the learning behavior collection module 3. Historical learning data can be used to reflect students' past learning trajectory and learning performance.

[0229] For example, the historical learning data in this application embodiment may specifically include online course learning data (such as video completion rate, number of repeated viewings, time spent on key chapters, fast forward or rewind operation records, etc.), question-solving data (such as answer accuracy rate, answering speed, number of wrong questions, correct answer rate for wrong questions, difficulty level of questions, etc.), interaction data (such as question frequency, number of notes, detail of notes, activity level in discussions, key content marking records, etc.), and test data (such as stage test scores, knowledge point coverage test results, etc.).

[0230] In the embodiments of this application, learning ability data may include data such as learning speed, knowledge retention rate, and knowledge application ability. The learning speed, knowledge retention rate, and knowledge application ability can together constitute a student's ability vector. The learning ability data can be used to provide an adaptation basis for subsequent learning plan formulation and material recommendation.

[0231] In this embodiment of the application, the learning status information can be a comprehensive set of information determined by the learning material recommendation module 8, including the student's mastery of each knowledge point in the knowledge point learning grid, the degree of importance, and the intensity of the student's learning needs. For example, the learning status information in this embodiment may specifically include knowledge point mastery probability data (quantifying the student's mastery level of the knowledge point, typically ranging from [0,1]), centrality data (reflecting the importance of the knowledge point in the knowledge network, including degree centrality, betweenness centrality, proximity centrality, etc.), and learning intention intensity data (quantifying the urgency and level of attention the student has for learning the knowledge point).

[0232] In this application embodiment, the learning plan type can include various types such as a gap-filling learning plan, a preparatory learning plan, and a sprint learning plan. Among them, a gap-filling learning plan can be used to consolidate weak knowledge points in the recently studied chapters, a preparatory learning plan can be used to learn prerequisite knowledge for subsequent teaching content, and a sprint learning plan can be used to prepare for the core test points of the upcoming exam. Different types of plans can correspond to different learning focuses and time arrangements.

[0233] In this embodiment, the learning path generation module 2 determines the type of learning plan based on learning ability data and learning status information. This can be done by comprehensively judging factors such as the student's ability level, knowledge weaknesses, and learning goals. The set of knowledge points to be learned in the knowledge point learning grid is determined based on the type of learning plan. First, the target range of the learning can be clarified based on the plan type, and the abstract plan goal can be transformed into a specific set of knowledge points in the knowledge graph. The knowledge points within the target range can be prioritized by combining the mastery probability data, centrality data, and learning intention intensity data in the learning status information. Knowledge points that meet the priority conditions can be selected to form a set of knowledge points to be learned. Among them, knowledge points that meet the priority conditions can be selected first because the student has a low level of mastery, high importance, and urgent learning needs.

[0234] In this embodiment, generating a student's learning path in a knowledge point learning grid based on a set of knowledge points to be learned can first involve analyzing the dependencies (including prerequisite and relevance relationships) of knowledge points in the knowledge graph corresponding to the knowledge point learning grid. Based on these dependencies, the knowledge points to be learned are sorted to generate an initial sequence that conforms to the learning logic. The sequence is then adjusted based on the student's learning ability data (such as learning speed). If the student's learning speed is fast, highly relevant knowledge points can be arranged in parallel along the path. If the student's learning speed is slow, a strict sequential order can be used. The learning path can be presented in the knowledge point learning grid as a coordinate sequence or a path connection.

[0235] In this embodiment, the learning materials recommendation module 8 can be used to first extract multi-dimensional features of the learning materials and construct feature vectors. Then, the feature vectors are matched with the students' learning ability data for correlation and similarity to select candidate learning materials that are suitable for the students' ability level. Based on the students' learning ability data and the learning path, the duration of the students' learning can be determined and the learning path can be divided into multiple target learning plans. Finally, the corresponding learning materials can be matched for each target learning plan to form a complete set of learning materials.

[0236] In this embodiment of the application, the set of learning materials recommended by the learning materials recommendation module 8 to students may include various types of learning materials such as online course videos, knowledge point explanation documents, practice question sets, and interactive learning tools. The set of learning materials can be used to help students efficiently master the set of knowledge points to be learned.

[0237] As an alternative approach, this application also provides the following embodiments, but is not limited thereto, including:

[0238] Example 101: The learning material recommendation module 8 is used to extract students' learning characteristics from their historical learning data, and to determine the students' historical learning status for the historical knowledge points corresponding to the historical learning data based on the learning characteristics. The learning characteristics include at least one of learning speed characteristics, learning memory characteristics, and answering characteristics. Based on the historical learning status, the module determines the students' learning ability data; it determines the mastery probability data and centrality data of knowledge points in the knowledge point learning grid, and based on the students' historical learning data, it determines the intensity data of the students' learning intention for the knowledge points in the knowledge point learning grid; based on the mastery probability data, centrality data, and intensity data of learning intention, it constructs a learning status matrix of the students for the knowledge points in the knowledge point learning grid, which is used to represent the students' learning status information for the knowledge points in the knowledge point learning grid.

[0239] Example 102: The learning material recommendation module 8 is used to determine the duration of a student's learning plan based on learning ability data and learning status information, and generate at least one learning task information corresponding to the student based on the learning plan duration; match the at least one learning task information with the knowledge graph corresponding to the knowledge point learning grid to map the at least one learning task information to at least one set of candidate knowledge points in the knowledge point learning grid; determine the priority data of knowledge points in the at least one set of candidate knowledge points based on mastery probability data, centrality data, and learning intention intensity data; and form a set of learning knowledge points based on the priority data and the knowledge points in the at least one set of candidate knowledge points that meet the priority conditions.

[0240] Example 103: The learning path generation module 2 is used to generate a first knowledge point sequence corresponding to the knowledge points in the set of knowledge points to be learned based on the dependency relationships of knowledge points in the knowledge graph corresponding to the knowledge point learning grid. The dependency relationships include prerequisite relationships and relevance relationships. The module determines the learning speed information corresponding to the first knowledge point sequence. If the learning speed is greater than the speed threshold, the module determines the parallel knowledge points corresponding to the first knowledge point sequence and generates a learning path based on the parallel knowledge points and the first knowledge point sequence. If the learning speed is less than or equal to the speed threshold, the module generates a learning path based on the first knowledge point sequence.

[0241] Example 104: The learning path generation module 2 is used to determine the set of prerequisite knowledge points corresponding to the set of knowledge points to be learned based on the prerequisite relationships of knowledge points in the set of knowledge points to be learned in the knowledge graph; it generates an initial knowledge point sequence based on the set of knowledge points to be learned, and inserts the knowledge points in the set of prerequisite knowledge points into the preceding positions of the knowledge points in the set of knowledge points to be learned in the initial knowledge point sequence to obtain the first knowledge point sequence.

[0242] Example 105: The learning material recommendation module 8 is used to construct a feature vector corresponding to the learning material based on at least one first material feature in the content dimension and at least one second material feature in the question dimension; perform relevance matching and similarity matching on the feature vector and student ability data to obtain a comprehensive matching result of the feature vector and student ability data, and select candidate learning materials suitable for the student from the learning materials according to the comprehensive matching result; determine the student's learning duration based on the student ability data, and generate at least one target learning plan corresponding to the student according to the learning duration and the learning path to be learned; determine the set of learning materials to be learned that matches each of the at least one target learning plan from the learning materials.

[0243] Example 106: The learning material recommendation module 8 is used to determine the learning plans of students in at least one target learning plan, and the set of questions that students have learned in the learning plans; based on the students' learning status of the set of questions, it analyzes the students' mastery data of the knowledge points corresponding to the set of questions; and updates the unlearned plans and the set of learning materials corresponding to the unlearned plans of students in at least one target learning plan based on the mastery data.

[0244] It should be noted that this embodiment establishes the foundation for recommendations based on dynamic student learning data by acquiring students' historical learning data and knowledge point learning grids updated based on learning behavior data from the learning companion system; it accurately grasps students' personalized learning foundation by determining students' learning ability data and the learning status information of knowledge points in the knowledge point learning grid based on historical learning data; it improves the accuracy of setting personalized learning goals by determining the type of learning plan based on learning ability data and learning status information and determining the set of knowledge points to be learned in the knowledge point learning grid based on the type; and it achieves collaborative matching of learning materials and learning paths by generating learning paths in the knowledge point learning grid based on the set of knowledge points to be learned and determining the set of learning materials matching the path, thereby improving the relevance and operability of learning material recommendations.

[0245] Compared with existing technologies, this embodiment, through the knowledge point learning grid module in the learning companion system, can acquire course knowledge points and related information within the student's target time period. Combining basic learning, prerequisites, and relevance information, a knowledge graph is constructed, transforming scattered knowledge points into a structured knowledge network and clearly presenting the inherent connections between knowledge. Furthermore, by mapping the knowledge graph into an intuitive target knowledge point learning grid, and sending the obtained knowledge graph to the learning path generation module, the learning path generation module can generate a learning plan based on the grid. The learning path is then displayed through the target knowledge point learning grid in the knowledge point learning grid module. This allows the learning companion system in this embodiment to accurately and clearly present the relationships between knowledge points to students through the learning path, enabling students to effectively understand the knowledge structure and achieve deep learning and transfer through the relationships between knowledge points represented by the learning path. Ultimately, this embodiment's learning companion system can help students improve their learning efficiency.

[0246] Based on this understanding, the technical solution of this application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (such as CD-ROM, USB flash drive, mobile hard drive, etc.) and includes several instructions to cause a computer device (such as personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of this application.

[0247] like Figure 3 The diagram shown is a hardware structure schematic of an electronic device according to the present invention, comprising:

[0248] At least one processor 201; and,

[0249] A memory 202 communicatively connected to at least one of the processors 201; wherein,

[0250] The memory 202 stores instructions that can be executed by at least one of the processors to enable at least one of the processors to perform the control method of the protection device as described above.

[0251] Figure 3 Take a processor 201 as an example.

[0252] The electronic device may also include an input device 203 and a display device 204.

[0253] The processor 201, memory 202, input device 203, and display device 204 can be connected via a bus or other means. Figure 3 Taking the example of a connection between China and Israel via a bus.

[0254] The memory 202, as a non-volatile computer-readable storage medium, can be used to store non-volatile software programs, non-volatile computer-executable programs, and modules, such as the program instructions / modules corresponding to the control method of the protection device in the embodiments of this application, for example, Figure 1 and Figure 2 The method flow is shown. The processor 201 executes various functional applications and data processing by running non-volatile software programs, instructions, and modules stored in the memory 202, thereby implementing the control method of the protection device in the above embodiments.

[0255] The memory 202 may include a program storage area and a data storage area. The program storage area may store the operating system and applications required for at least one function; the data storage area may store data created based on the use of the control method of the protection device. Furthermore, the memory 202 may include high-speed random access memory and may also include non-volatile memory, such as at least one disk storage device, flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 202 may optionally include memory remotely located relative to the processor 201, and these remote memories may be connected via a network to the means of performing the control method of the protection device. Examples of such networks include, but are not limited to, the Internet, corporate intranets, local area networks, mobile communication networks, and combinations thereof.

[0256] The input device 203 can receive user clicks and generate signal inputs related to user settings and function control of the protection device's control method. The display device 204 may include a display screen or other display equipment.

[0257] When one or more modules are stored in the memory 202, and are run by one or more processors 201, the control method of the protection device in any of the above method embodiments is executed.

[0258] Optionally, the aforementioned physical devices may also include a user interface, a network interface, a camera, radio frequency (RF) circuitry, sensors, audio circuitry, a Wi-Fi module, etc. The user interface may include a display screen, input units such as a keyboard, etc., and optional user interfaces may also include USB interfaces, card reader interfaces, etc. The network interface may optionally include standard wired interfaces, wireless interfaces (such as Wi-Fi interfaces), etc.

[0259] Those skilled in the art will understand that the physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or combine certain components, or have different component arrangements.

[0260] The storage medium may also include an operating system and a network communication module. The operating system is a program that manages the hardware and software resources of the aforementioned physical device, supporting the operation of information processing programs and other software and / or programs. The network communication module is used to enable communication between the various components within the storage medium, as well as communication with other hardware and software in the information processing physical device.

[0261] Through the above description of the embodiments, those skilled in the art can clearly understand that this application can be implemented by means of software plus necessary general-purpose hardware platforms, or it can be implemented by hardware. By applying the solution of this embodiment, compared with the existing technology, this embodiment can obtain the course knowledge points and related information within the student's target time period through the knowledge point learning grid module of the learning companion system. Combining basic learning, prerequisites and related information to construct a knowledge graph, it can transform scattered knowledge points into a structured knowledge network and clearly present the internal relationship of knowledge. Then, by mapping the knowledge graph into an intuitive target knowledge point learning grid, and sending the obtained knowledge graph to the learning path generation module, the learning path generation module can generate a learning plan based on the grid. Then, the learning path is displayed through the target knowledge point learning grid in the knowledge point learning grid module. This allows the learning companion system of this embodiment to present the relationship between knowledge points to students accurately and clearly through the learning path. This allows students to effectively understand the knowledge structure and achieve deep learning and transfer through the relationship between knowledge points represented by the learning path. Thus, the learning companion system of this embodiment can help students improve their learning efficiency.

[0262] It should be noted that, in this document, relational terms such as "first" and "second" are used merely to distinguish one entity or operation from another, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Furthermore, the term "comprising" or any other variations thereof is intended to cover non-exclusive inclusion, such that a process, method, article, or apparatus that comprises a list of elements includes not only those elements but also other elements not expressly listed, or elements inherent to such a process, method, article, or apparatus. Without further limitations, an element defined by the phrase "comprising one..." does not exclude the presence of other identical elements in the process, method, article, or apparatus that includes said element.

[0263] The above description is merely a specific embodiment of this disclosure, enabling those skilled in the art to understand or implement it. Various modifications to these embodiments will be readily apparent to those skilled in the art, and the general principles defined herein may be implemented in other embodiments without departing from the spirit or scope of this disclosure. Therefore, this disclosure is not to be limited to the embodiments described herein, but is to be accorded the widest scope consistent with the principles and novel features claimed herein.

[0264] It should be noted that the technical solutions in this disclosure are not limited to use in the control circuit of protection devices, but can also be extended to related applications of the same type that require control. All of these should fall within the protection scope of this disclosure, and no specific limitations are made here for the related applications that require control.

[0265] All articles and references disclosed above, including patent applications and publications, are incorporated herein by reference for various purposes. The term “substantially constitutes…” used to describe a combination should include the identified elements, components, parts, or steps, as well as other elements, components, parts, or steps that do not substantially affect the essential novelty of the combination. The use of the terms “comprising” or “including” to describe combinations of elements, components, parts, or steps herein also contemplates embodiments substantially constituted by such elements, components, parts, or steps. The use of the term “may” herein is intended to indicate that any described attribute included by “may” is optional.

[0266] Multiple elements, components, parts, or steps can be provided by a single integrated element, component, part, or step. Alternatively, a single integrated element, component, part, or step can be divided into multiple separate elements, components, parts, or steps. The use of "a" or "an" to describe an element, component, part, or step does not imply the exclusion of other elements, components, parts, or steps.

[0267] It should be understood that the above description is for illustrative purposes and not for limitation. Many embodiments and applications beyond the provided examples will be apparent to those skilled in the art upon reading the above description. Therefore, the scope of this teaching should not be determined by reference to the above description, but rather by reference to the foregoing claims and the full scope of their equivalents. For purposes of completeness, all articles and references, including patent applications and published disclosures, are incorporated herein by reference. The omission of any aspect of the subject matter disclosed herein in the foregoing claims is not intended as a waiver of that subject matter, nor should it be considered as a failure of the applicant to consider that subject matter as part of the disclosed subject matter. It will be apparent to those skilled in the art that various modifications and variations can be made to this disclosure without departing from its spirit and scope. Thus, this disclosure is also intended to include such modifications and variations if they fall within the scope of the claims of this disclosure and their equivalents.

Claims

1. A learning companion system based on an AI intelligent agent, characterized in that, include: The knowledge point learning grid module and the learning path generation module are connected together. The knowledge point learning grid module is used to determine the basic learning information of the knowledge points in the knowledge point set, as well as the prerequisite knowledge information and correlation information between the knowledge points, based on the knowledge point set corresponding to the course material information. Based on the basic learning information, the prerequisite knowledge information, and the relevance information, attribute information of knowledge points is generated, and a knowledge graph corresponding to the set of knowledge points is constructed based on the attribute information. The knowledge graph is mapped into the knowledge point learning grid corresponding to the course material information to obtain the target knowledge point learning grid. The learning path generation module is used to generate a student's learning plan for a target time period based on the knowledge point learning grid in the knowledge point learning grid module, generate the student's learning path based on the learning plan, and send the learning path to the knowledge point learning grid module. The knowledge point learning grid module is used to display the learning path generated by the learning path generation module to the student terminal through the knowledge point learning grid; wherein, the target knowledge point learning grid is a learning grid that includes the attribute information of knowledge points and the relationship information between knowledge points; This also includes a learning behavior collection module; The learning behavior collection module is connected to the knowledge point learning grid module; The learning behavior collection module is used to respond to the acquisition of first learning behavior data of students learning questions based on the learning plan, determine the first question information and first note information of the student's learning target questions based on the first learning behavior data, and send the first question information and the first note information to the knowledge point learning grid module. The knowledge point learning grid module is used to obtain a set of implicit knowledge points based on the knowledge point sets corresponding to the first question information and the first note information. The set of implicit knowledge points is a set of knowledge points in the knowledge point sets corresponding to the first question information and the first note information that are not included in the first knowledge point set. The first knowledge point set is a set of explicit knowledge points that mark the target question. Based on the prerequisite and relevance information of the knowledge points in the set of implicit knowledge points and the knowledge points in the first knowledge point set, the module determines the target set of implicit knowledge points corresponding to the learning plan from the set of implicit knowledge points. The module updates the target set of implicit knowledge points in the target set of implicit knowledge points by establishing association relationships with the knowledge points in the first set of knowledge points. The module updates the target set of implicit knowledge points in the target set of implicit knowledge points in the target set of implicit knowledge points and sends the updated target set of implicit knowledge points to the learning path generation module. The learning path generation module is used to update the learning plan to include the target implicit knowledge point set.

2. The system according to claim 1, characterized in that, It also includes a mastery analysis module; The mastery level analysis module is connected to the learning behavior collection module; The learning behavior collection module is used to determine the target learning course corresponding to the learning location information based on the student's learning location information in the target knowledge point learning grid; The student's second learning behavior data in the target learning course is divided into at least one learning behavior data set, and at least one behavioral feature set corresponding to the at least one learning behavior data set is generated, and the at least one behavioral feature set is sent to the mastery analysis module. The mastery analysis module is used to analyze the student's mastery of the knowledge points in the target learning course based on the at least one set of behavioral features, determine the set of knowledge points that the student has not mastered in the target learning course, and send the set of knowledge points that have not been mastered to the knowledge point learning grid module. The knowledge point learning grid module is used to match all associated nodes and edges of the nodes extracted from the set of unmastered knowledge points with the target knowledge graph corresponding to the target knowledge point learning grid, so as to obtain the target knowledge point network corresponding to the set of unmastered knowledge points in the target knowledge graph, and send the target knowledge point network to the learning path generation module. The learning path generation module generates a target learning path for the student in the target knowledge point learning grid based on the target knowledge point network. The target learning path is used to assist the student in mastering the set of unmastered knowledge points in the target knowledge point learning grid.

3. The system according to claim 2, characterized in that, It also includes a learning intent analysis module; The learning intention analysis module is connected to the mastery level analysis module and the learning behavior collection module, respectively. The learning behavior collection module is used to acquire third learning behavior data of the student learning knowledge points in the set of unmastered knowledge points in the knowledge point learning grid, determine second question information and second note information of the student learning knowledge points in the set of unmastered knowledge points based on the third learning behavior data, and send the second question information and the second note information to the learning intention analysis module. The learning intention analysis module is used to evaluate the student's learning needs for knowledge points in the set of unmastered knowledge points based on the second question information and the second note information, and to obtain the learning intention intensity data corresponding to the knowledge points in the knowledge point learning grid. Based on the learning intention intensity data, the second question information, and the second note information, the student's target learning intention for the knowledge points in the set of unmastered knowledge points is identified, and the target learning intention is sent to the mastery analysis module; The mastery analysis module is used to update the set of unmastered knowledge points based on the target learning intention and the knowledge point location information of the set of unmastered knowledge points in the knowledge point learning grid, to obtain the target set of unmastered knowledge points, and recommend the target set of unmastered knowledge points to the student.

4. The system according to claim 3, characterized in that, It also includes a knowledge point location module; The knowledge point location module is connected to the mastery level analysis module and the learning behavior collection module, respectively. The knowledge point positioning module is used to map the third learning behavior data into the knowledge graph corresponding to the knowledge point learning grid to obtain the student's learning knowledge point data in the knowledge graph; generate the student's learning content data based on the second question information and the second note information, and perform multi-dimensional information matching between the learning content data and the learning knowledge point data to generate the knowledge point positioning information of the set of unmastered knowledge points, and send the knowledge point positioning information to the mastery analysis module.

5. The system according to claim 1, characterized in that, The learning path generation module is used to determine the knowledge points to be reviewed indicated by the knowledge point review path based on the knowledge point review path in the target knowledge point learning grid where the student reviews the learned knowledge points, and send the knowledge points to be reviewed to the knowledge point learning grid module. The knowledge point learning grid module is used to extract the network of knowledge points to be reviewed corresponding to the knowledge point to be reviewed from the knowledge graph corresponding to the target knowledge point learning grid. The network of knowledge points to be reviewed includes at least one prerequisite knowledge point and at least one related knowledge point corresponding to the knowledge point to be reviewed. The knowledge point to be reviewed, the at least one prerequisite knowledge point and the at least one related knowledge point are sent to the learning path generation module. The learning path generation module is used to update the knowledge point review path based on the student's mastery of the knowledge point to be reviewed, the at least one prerequisite knowledge point, and the at least one related knowledge point, to obtain the target knowledge point review path corresponding to the knowledge point to be reviewed. Based on the review path for the target knowledge points, the student's target knowledge points to be reviewed are determined, and recommendation information for the target knowledge points to be reviewed is generated to recommend the student to review the target knowledge points.

6. The system according to claim 5, characterized in that, The knowledge point learning grid module is used to update the first mastery level indicator of the target knowledge point in response to the learning behavior collection module obtaining the fourth learning behavior data of the student reviewing the target knowledge point to be reviewed. Determine the update influence range of the mastery level of the target knowledge point in the knowledge graph corresponding to the knowledge point learning grid, and form a set of knowledge points to be updated based on the knowledge points covered by the update influence range; The mastery level data of the knowledge points in the set of knowledge points to be updated is updated, and the second mastery level identifier of the knowledge points in the set of knowledge points to be updated is updated based on the updated mastery level data; The knowledge point learning grid is updated to the target knowledge point learning grid based on the second mastery level identifier, and the target review content for the student is determined based on the target knowledge point learning grid.

7. The system according to claim 1, characterized in that, It also includes a knowledge point status analysis module; The knowledge point status analysis module is connected to the learning behavior collection module and the knowledge point learning grid module, respectively. The knowledge point status analysis module is used to obtain the fifth learning behavior data of students learning knowledge points in the knowledge point learning grid from the learning behavior collection module, and to obtain the mastery level identifier of the knowledge points in the knowledge point learning grid from the knowledge point learning grid module, and send the fifth learning behavior data and the mastery level identifier to the knowledge point status analysis module. The knowledge point status analysis module is used to determine the student's second mastery level data of the knowledge points in the knowledge point learning grid based on the fifth learning behavior data, and to evaluate the second knowledge point status data of the knowledge points in the knowledge point learning grid based on the second mastery level data. Based on the first knowledge point status data and the second knowledge point status data corresponding to the first mastery level data, abnormal knowledge points are determined from the knowledge point learning grid, and the abnormal knowledge points are sent to the knowledge point learning grid module; wherein, the first mastery level data is data determined based on the mastery level identifier of the knowledge point obtained from the knowledge point learning grid module; The knowledge point learning grid module is used to update the knowledge graph corresponding to the knowledge point learning grid based on the abnormal state knowledge points, so as to obtain the updated target knowledge graph. The target knowledge graph is used to generate the target knowledge point learning grid.

8. The system according to claim 7, characterized in that, The knowledge point learning grid module is used to determine the state correction content corresponding to the abnormal state knowledge point. Based on the correction content, the abnormal knowledge points in the knowledge point learning grid are corrected to determine the impact of the mastery level of the abnormal knowledge points after the correction on the data. Based on the mastery level influence data, determine the influence range of the mastery level influence data in the knowledge graph corresponding to the knowledge point learning grid, and update the knowledge graph within the influence range.

9. The system according to claim 1, characterized in that, It also includes a learning materials recommendation module; The learning materials recommendation module is connected to the learning behavior collection module and the learning path generation module, respectively. The learning materials recommendation module is used to obtain the student's historical learning data from the learning behavior collection module, determine the student's learning ability data and the student's learning status information for knowledge points in the knowledge point learning grid based on the student's historical learning data, and send the learning status information to the learning path generation module. The learning path generation module is used to determine the student's learning plan type based on the learning ability data and the learning status information, and to determine the set of knowledge points to be learned in the knowledge point learning grid according to the learning plan type. Based on the set of knowledge points to be learned, the student's learning path is generated in the knowledge point learning grid, and the learning path is sent to the learning material recommendation module. The learning material recommendation module is used to determine a set of learning materials that match the learning path from the learning materials, so as to recommend that the student learn the set of knowledge points based on the set of learning materials.

Images