Learning assistance method and device based on question bank knowledge graph and electronic equipment

Abstract

The invention discloses a learning assistance method and device based on a question bank knowledge graph, a storage medium and electronic equipment, and relates to the technical field of data processing, and the method comprises the steps: firstly, carrying out the extraction of knowledge points based on a textbook text, and obtaining a basic knowledge point cluster; performing importance degree evaluation on knowledge points in the basic knowledge point cluster, and performing screening according to an evaluation result to obtain an important knowledge point cluster; determining knowledge point distribution information of a basic knowledge point cluster and an important knowledge point cluster in the textbook, generating a knowledge tree containing the knowledge point distribution information, and determining association strength among knowledge points according to the number of branches of the knowledge tree; constructing a question bank knowledge graph according to the association strength among the knowledge points; and matching the question bank knowledge graph with a learning dialogue record of the user, and monitoring a question brushing condition of the user according to a matching result. An important knowledge point cluster is extracted from a teaching material, and a question bank knowledge graph is constructed, so that personalized learning assistance is realized.

Description

Technical Field

[0001] The present application relates to the field of data processing technology, and in particular to a learning assistance method, device, storage medium and electronic device based on a question bank knowledge graph. Background Art

[0002] When students are doing questions, they usually encounter a large number of knowledge points. With the continuous development of educational technology, how to efficiently extract knowledge points from textbooks, construct knowledge systems, and assist teaching through question banks and visualization tools has become an urgent problem to be solved in the field of education.

[0003] At present, the difficulty level of knowledge points is usually determined by statistically analyzing the frequency of question appearance and the error rate of students. For example, questions that appear frequently and have a high error rate are often considered to correspond to more difficult knowledge points, while questions that appear infrequently and have a low error rate are considered to correspond to easier knowledge points.

[0004] However, the existing question bank knowledge graph fails to effectively distinguish between important knowledge points and basic knowledge points, and it is difficult to accurately reflect the complex relationship between knowledge points, which results in students being unable to accurately practice questions on key knowledge points. Summary of the invention

[0005] In view of this, the present application provides a learning assistance method, device, storage medium and electronic device based on a question bank knowledge graph, the main purpose of which is to improve the technical problem in the current prior art that the question bank knowledge graph is difficult to accurately reflect the complex relationship between knowledge points, which in turn leads to students being unable to accurately practice questions on key knowledge points.

[0006] In a first aspect, the present application provides a learning assistance method based on a question bank knowledge graph, comprising: Extract knowledge points based on textbook texts to obtain basic knowledge point clusters; Evaluate the importance of the knowledge points in the basic knowledge point cluster, and select important knowledge point clusters according to the evaluation results; Determine the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the textbook, generate a knowledge tree containing the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree; According to the correlation strength between the various knowledge points, a question bank knowledge graph is constructed, wherein the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation between different knowledge points; The question bank knowledge graph is matched with the user's learning conversation record, and the user's question-answering status is monitored based on the matching result.

[0007] In a second aspect, the present application provides a learning assistance device based on a question bank knowledge graph, comprising: An extraction module is configured to extract knowledge points based on the textbook text to obtain basic knowledge point clusters; An evaluation module is configured to evaluate the importance of the knowledge points in the basic knowledge point cluster, and screen the important knowledge point cluster according to the evaluation result; A generation module is configured to determine the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the teaching material, generate a knowledge tree containing the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree; A construction module is configured to construct a question bank knowledge graph according to the association strength between the various knowledge points, wherein the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the association relationship between different knowledge points; The monitoring module is configured to match the question bank knowledge graph with the user's learning conversation record, and monitor the user's question-answering situation based on the matching result.

[0008] In a third aspect, the present application provides a computer-readable storage medium having a computer program stored thereon, which, when executed by a processor, implements the learning assistance method based on the question bank knowledge graph described in the first aspect.

[0009] In a fourth aspect, the present application provides an electronic device, comprising a storage medium, a processor, and a computer program stored on the storage medium and executable on the processor, wherein when the processor executes the computer program, the learning assistance method based on the question bank knowledge graph described in the first aspect is implemented.

[0010] By means of the above technical scheme, the present application provides a learning assistance method, device, storage medium and electronic device based on a question bank knowledge graph. Compared with the current existing technology, the present application first extracts knowledge points based on the textbook text to obtain basic knowledge point clusters; evaluates the importance of the knowledge points in the basic knowledge point clusters, and obtains important knowledge point clusters based on the evaluation results; determines the knowledge point distribution information of the basic knowledge point clusters and the important knowledge point clusters in the textbook, generates a knowledge tree containing the knowledge point distribution information, and determines the correlation strength between each knowledge point based on the number of branches of the knowledge tree; constructs a question bank knowledge graph based on the correlation strength between each knowledge point, and the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation between different knowledge points; matches the question bank knowledge graph with the user's learning conversation records, and monitors the user's question-answering situation based on the matching results. By analyzing and processing text information, we can obtain basic knowledge point clusters from textbooks and further extract important knowledge point clusters, thereby effectively distinguishing important knowledge points from basic knowledge points and improving the accuracy of screening important knowledge points. By further constructing a question bank knowledge graph, we can associate knowledge points with questions, and use the graph to monitor and analyze students' question-answering situation, so that students can accurately answer questions on key knowledge points, thereby achieving personalized learning assistance. BRIEF DESCRIPTION OF THE DRAWINGS

[0011] The accompanying drawings, which are incorporated in and constitute a part of this specification, illustrate embodiments consistent with the present application and, together with the description, serve to explain the principles of the present application.

[0012] In order to more clearly illustrate the embodiments of the present application or the technical solutions in the prior art, the drawings required for use in the embodiments or the description of the prior art will be briefly introduced below. Obviously, for ordinary technicians in this field, other drawings can be obtained based on these drawings without paying any creative labor.

[0013] Figure 1 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Figure 2 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Figure 3 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Figure 4 A schematic diagram of an example process provided by an embodiment of the present application is shown; Figure 5A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Figure 6 A schematic diagram of an example process provided by an embodiment of the present application is shown; Figure 7 A schematic diagram of an example process provided by an embodiment of the present application is shown; Figure 8 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Fig. 9 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Fig.10 A flow chart of a learning assistance method based on a question bank knowledge graph provided in an embodiment of the present application is shown; Fig.11 A schematic diagram of an example process provided by an embodiment of the present application is shown; Fig.12 A structural schematic diagram of a learning assistance device based on a question bank knowledge graph provided in an embodiment of the present application is shown; Fig.13 A schematic structural diagram of an electronic device provided in an embodiment of the present application is shown. DETAILED DESCRIPTION

[0014] The embodiments of the present application will be described in more detail below with reference to the accompanying drawings. It should be noted that the embodiments and features in the embodiments of the present application can be combined with each other without conflict.

[0015] In order to improve the technical problem that the question bank knowledge graph in the current existing technology is difficult to accurately reflect the complex relationship between knowledge points, which leads to the inability of students to accurately practice questions on key knowledge points. This embodiment provides a learning assistance method based on the question bank knowledge graph, such as Figure 1 As shown, the method includes: Step 101: Extract knowledge points based on the textbook text to obtain basic knowledge point clusters.

[0016] Exemplarily, the basic knowledge point cluster is a set of knowledge units consisting of all basic concepts, terms, facts, rules, etc. identified after text analysis and processing of teaching materials or learning materials. First, the teaching material content is cleaned and preprocessed, including removing irrelevant characters (such as punctuation marks), converting to lowercase, stemming or word form restoration, etc., to ensure the effectiveness of subsequent analysis. The text is divided into words or phrases, and each word is annotated using text analysis techniques, such as text mining, natural language processing, semantic analysis, etc., and based on the extracted keywords and context information, named entity recognition or other machine learning models are applied to identify specific knowledge points. For each identified knowledge point, models such as Word2Vec, GloVe or BERT can be used to convert it into vector form, which can capture the semantic relationship between words to form an identification vector.

[0017] In some examples, the generated identification vectors are grouped through clustering algorithms (such as K-means, hierarchical clustering, etc.) to construct clusters composed of similar knowledge points, namely basic knowledge point clusters, thereby clarifying the subject structure and association patterns in the textbook content.

[0018] Step 102: Evaluate the importance of the knowledge points in the basic knowledge point cluster, and select important knowledge point clusters based on the evaluation results.

[0019] Exemplarily, by classifying the knowledge points in the basic knowledge point cluster in detail, and determining the difficulty level according to the degree of refinement of the knowledge points, for example, the degree of refinement corresponding to the knowledge points can be determined according to the chapter, section, or unit to which the knowledge points belong in the textbook text; or the degree of refinement corresponding to the knowledge points can be determined according to the form of the identification vector corresponding to the knowledge points (in the form of a single unit or a combination of multiple units); and then the difficulty level is determined according to the degree of refinement of the knowledge points, and the higher the degree of refinement of the knowledge points, the higher the corresponding difficulty level. By applying the method of this embodiment, the systematicness and hierarchy of the knowledge points are ensured, and a basis is provided for the subsequent generation of questions of different difficulty levels.

[0020] In some examples, different difficulty levels correspond to different weights of the importance of indicators of each knowledge point. Based on different difficulty levels and weights, each knowledge point can be evaluated to obtain an importance score. According to the importance score, the important knowledge point cluster can be further screened from the basic knowledge point cluster to form a collection of core knowledge points that are essential for understanding the target subject or completing specific learning goals. By identifying and extracting important knowledge points, students can focus on learning key information and avoid wasting time on minor details. Important knowledge points are often the basis for building complex concepts. Mastering these core points helps to deeply understand the structure and logic of the subject, thereby better solving complex problems.

[0021] Step 103: determine the knowledge point distribution information of the basic knowledge point clusters and the important knowledge point clusters in the textbook, generate a knowledge tree containing the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree.

[0022] In some examples, basic knowledge points are extracted and classified by deeply analyzing the textbook text, and the difficulty level is determined according to its refinement and complexity. The importance of each knowledge point is evaluated using a pre-trained evaluation model to distinguish important knowledge point clusters. Then, nodes are created for each knowledge point, and connections are established based on the logical relationships between knowledge points (such as cause and effect, subordination) to build a knowledge tree. At the same time, the difficulty level and importance score can be marked on the nodes.

[0023] For example, the strength of the association between knowledge points can be measured by analyzing the number of branches of each node. The more branches there are, the more difficult the knowledge point is. If necessary, the strength of the association can be adjusted according to the importance score. By visualizing the knowledge tree with graphical tools, the distribution and interconnection of knowledge points can be intuitively displayed, helping teachers and students better understand the course content and develop effective learning plans. The knowledge tree not only clearly displays the hierarchical structure of knowledge points, but also strengthens students' understanding of key knowledge points and their connections.

[0024] Step 104: construct a question bank knowledge graph based on the correlation strength between each knowledge point. The question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation between different knowledge points.

[0025] Exemplarily, by classifying the knowledge points in the basic knowledge point clusters and the important knowledge point clusters in detail and determining the difficulty level according to the degree of refinement of the knowledge points, the systematic and hierarchical nature of the knowledge points is ensured, providing a basis for subsequent question generation. The question bank contains multiple-choice questions, fill-in-the-blank questions, short-answer questions, and essay questions. The questions in the question bank correspond to the important knowledge points in the textbook content. By using text analysis and data mining technology, important knowledge point clusters are automatically extracted, and the corresponding question bank is generated. Based on the question bank, the corresponding question bank knowledge graph is generated, which avoids the subjectivity and inefficiency of manual screening and improves the accuracy and efficiency of knowledge extraction.

[0026] For example, in the question bank knowledge graph, important knowledge point clusters that are core concepts or principles with wide application can be marked, and different colors or symbols can be used to distinguish between common knowledge points and important knowledge points. In the question bank knowledge graph, the relationship between knowledge points is clearly visible, and important knowledge point clusters are highlighted.

[0027] In some examples, knowledge points can be distributed on a two-dimensional grid, with each knowledge point cluster occupying a cell. The size of the cell can be adjusted according to the complexity and importance of the knowledge point, and the cells where important knowledge point clusters are located are marked with special identifiers (such as color, etc.) to form a key learning grid. Navigation paths can also be added to the learning map to indicate the learning order from basic knowledge points to advanced knowledge points, helping students better plan their learning paths. The setting of the key learning grid not only highlights key knowledge points, but also provides students with a clear learning path, thereby improving learning efficiency and effectiveness.

[0028] Step 105: Match the question bank knowledge graph with the user's learning conversation record, and monitor the user's question-answering status based on the matching results.

[0029] For example, by constructing a detailed question bank knowledge graph, in which each knowledge point node is marked with the corresponding difficulty level and importance, and linked to the relevant questions, while collecting and processing user conversation records, and using natural language processing technology to identify the knowledge points mentioned by users. Then these knowledge points are matched with the nodes in the knowledge graph, and the guardian is helped to monitor the students' practice of questions in a timely manner based on the matching results. If the problem is not solved, it can help students to answer it in time, thereby improving the efficiency of practice.

[0030] For example, on this basis, the system can also record the user's practice data (such as the number of completed questions, accuracy, answering time, etc.), track their learning progress and mark their mastery on the knowledge graph. Provide personalized feedback and suggestions based on the user's practice performance, dynamically adjust the learning path to optimize the recommendation of learning resources, realize effective monitoring and management of the user's practice status, improve learning efficiency and provide a personalized learning experience.

[0031] Compared with the current existing technology, this embodiment first extracts knowledge points based on the textbook text to obtain basic knowledge point clusters; evaluates the importance of the knowledge points in the basic knowledge point clusters, and obtains important knowledge point clusters based on the evaluation results; determines the knowledge point distribution information of the basic knowledge point clusters and the important knowledge point clusters in the textbook, generates a knowledge tree containing the knowledge point distribution information, and determines the correlation strength between each knowledge point based on the number of branches of the knowledge tree; constructs a question bank knowledge graph based on the correlation strength between each knowledge point, and the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation relationship between different knowledge points; matches the question bank knowledge graph with the user's learning conversation records, and monitors the user's question-answering situation based on the matching results. By analyzing and processing text information, we can obtain basic knowledge point clusters from textbooks and further extract important knowledge point clusters, thereby effectively distinguishing important knowledge points from basic knowledge points and improving the accuracy of screening important knowledge points. By further constructing a question bank knowledge graph, we can associate knowledge points with questions, and use the graph to monitor and analyze students' question-answering situation, so that students can accurately answer questions on key knowledge points, thereby achieving personalized learning assistance.

[0032] As a refinement and extension of the above embodiment, when determining the association strength between various knowledge points according to the number of branches of the knowledge tree and constructing the question bank knowledge graph, the following methods may be used but are not limited to: Figure 2 As shown, the method includes: Step 201: Divide the difficulty level of each knowledge point according to the number of branches of the knowledge tree.

[0033] In some examples, we first create a node for each knowledge point and establish connections based on the logical relationship between the knowledge points. Then we calculate the number of directly dependent child nodes (i.e., the number of branches) of each knowledge point node, and divide the knowledge points into three difficulty levels: basic, medium, and high according to the number of branches: basic difficulty knowledge points usually have only a small number of or even no dependent child nodes, which are easy to understand and master; medium difficulty knowledge points have a certain number of dependent child nodes, which require a certain level of understanding and application; high difficulty knowledge points have a large number of dependent child nodes, involving complex concepts and applications, which require in-depth understanding and flexible application.

[0034] For example, other factors such as the depth and breadth of knowledge points and student feedback can also be comprehensively considered and dynamically adjusted to ensure the accuracy and rationality of the difficulty division, thereby helping teachers and students to better plan learning paths and improve learning efficiency.

[0035] Step 202: Determine the strength of association between the first knowledge point and the second knowledge point according to the overlapping of questions between the first knowledge point and the second knowledge point of adjacent difficulty levels.

[0036] Exemplarily, when constructing a knowledge point network, the first-level classification An exists in the form of a single-unit identification vector, and the second-level and third-level classifications exist in the form of a combination of multiple units. The identification vectors are superimposed in sequence, and multiple knowledge point networks form a knowledge point cluster, covering the combination of all knowledge points. The general expression of the knowledge point network is: U=(k, β), where k is the knowledge point set and β is the edge set. Based on the knowledge point set U=(k, β), the knowledge graph G=(k, β, r) in the question bank is constructed, where r is the association strength.

[0037] Specifically, based on the question set corresponding to the first knowledge point and the question set corresponding to the second knowledge point, the correlation strength between the first knowledge point and the second knowledge point is determined. The definition is as follows: (Formula 1) In formula 1, is the set of questions corresponding to the first knowledge point, is the set of questions corresponding to the second knowledge point, is the total number of questions marking the first knowledge point, is the total number of questions marking the second knowledge point, The total number of questions marked with both the first knowledge point and the second knowledge point.

[0038] Step 203: based on the strength of association between the first knowledge point and the second knowledge point, update the questions of the difficulty level corresponding to the first knowledge point and / or the second knowledge point in the question bank knowledge graph.

[0039] For example, if the correlation strength is high (for example, exceeding a preset threshold), it indicates that the two knowledge points often appear together in the questions and are closely related. At this time, the question combination corresponding to the two knowledge points in the question bank can be adjusted: for the first knowledge point and the second knowledge point, add comprehensive questions that cover both at the same time to ensure that students can master the related knowledge points simultaneously; at the same time, dynamically adjust the distribution of question difficulty according to the correlation strength, such as reallocating some questions that originally belonged to high-difficulty knowledge points to low-difficulty knowledge points as advanced exercises, or introducing more basic questions as a prelude to high-difficulty knowledge points. This can not only strengthen the logical connection between knowledge points, but also improve the diversity and adaptability of questions, increase comprehensive questions and optimize the connection between question difficulty levels and knowledge points, and help students learn and master knowledge more systematically.

[0040] For example, questions can also be pushed according to the difficulty level of knowledge points. This push mechanism based on the level and difficulty level of knowledge points can effectively help students gradually master knowledge. First, the difficulty of knowledge points is classified and graded, which can be divided into different levels such as basic, intermediate, and advanced. The basic difficulty corresponds to the first-level knowledge points, which are used to help students consolidate basic knowledge and understand basic concepts; the intermediate difficulty corresponds to the second-level knowledge points, which are used to help students apply basic knowledge to more complex problem solving; the advanced difficulty corresponds to the third-level knowledge points, which are used to help students improve their comprehensive application ability, requiring students to be able to integrate and flexibly apply multiple knowledge points, etc. The relationship and combination between knowledge points can also be considered to ensure that all combinations of knowledge points are covered. For example, if a certain knowledge point A is the basis of another knowledge point B, then when pushing questions, you should first ensure that students have mastered A.

[0041] As a refinement and extension of the above embodiment, when updating the questions of the difficulty level corresponding to the first knowledge point and / or the second knowledge point in the question bank knowledge graph based on the correlation strength between the first knowledge point and the second knowledge point, the following methods may be used but are not limited to: Figure 3 As shown, the method includes: Step 301: adjust the topic update strategy corresponding to the first knowledge point and / or the second knowledge point according to the association strength and a preset association strength threshold.

[0042] For example, according to the strength of association And the structure of the knowledge tree, construct the knowledge graph. Set the association strength threshold E, if >E, the knowledge point is considered to be strongly associated, and is associated with Under the knowledge point, otherwise it is a weak association. Under the knowledge point; according to the structure of the knowledge tree, the knowledge graph G in the question bank is finally obtained.

[0043] Step 302: according to the question update strategy, update the questions of the difficulty level corresponding to the first knowledge point and / or the second knowledge point in the question bank knowledge graph.

[0044] In some examples, the classification node level corresponding to the knowledge point can be obtained according to the identification vector form corresponding to the knowledge point, and then the comprehensive difficulty level of the question can be calculated by combining the degree of refinement of the knowledge point and other factors (such as application frequency, complexity, etc.). Then, questions of different difficulty levels can be appropriately mixed in the same set of questions, and the question bank can be regularly updated to add new knowledge points and question types as educational goals change and technology develops. The question bank includes questions corresponding to the first, second, and third level knowledge points. The question bank is stored in the cloud server for use by the learning tutoring system, such as Figure 4 As shown, the learning tutoring system includes a cloud server and multiple user terminals.

[0045] For example, the configuration of questions in the question bank can be adjusted based on the strength of association, comprehensive questions that cover both knowledge points can be added, and the distribution of question difficulty can be adjusted as needed. For example, more transition questions from basic to advanced can be introduced in low-difficulty levels, while more complex comprehensive questions can be added in high-difficulty levels to ensure that students can gradually master the associated knowledge points. In addition, dynamically updating the question labels and categories in the question bank can reflect the latest knowledge point associations, thereby optimizing the diversity and adaptability of the questions and improving learning outcomes.

[0046] As a refinement and extension of the above embodiment, the importance of knowledge points in the basic knowledge point cluster is evaluated, and when the important knowledge point cluster is obtained by screening according to the evaluation result, the following methods may be used but are not limited to: Figure 5 As shown, the method includes: Step 401: Use a pre-trained evaluation model to evaluate the importance of knowledge points in the basic knowledge point cluster.

[0047] Among them, the evaluation indicators include one or more of the number of identification vectors corresponding to knowledge points at all levels in the knowledge point cluster, the weight scores corresponding to the importance of knowledge points at all levels, the number of times the knowledge points corresponding to the test points appear, and the error frequency of the knowledge points corresponding to the test points.

[0048] In some examples, the teaching material content can be uploaded to the first knowledge point analysis module, and the knowledge points in the text can be extracted through text analysis technology and graded. Graded identification refers to giving specific marks to knowledge points or nodes at each level in a multi-level classification structure for easy distinction and management. Through graded identification, the hierarchical relationship of knowledge points can be clearly displayed, which helps to build the entire knowledge network.

[0049] For example, the first-level classification node, as the main node, can be classified by chapter; the second-level classification node, as the slave node of the first-level classification node, can be classified by section, representing the various subsections in each chapter; the third-level classification node, as the slave node of the second-level classification node, can be classified by unit results, further subdividing the specific knowledge points or units under each section, and so on.

[0050] Among them, the first-level classification node appears in the form of a single unit identification vector, and the multi-level classification node appears in the form of a combination of multiple unit identification vectors.

[0051] For example, the knowledge points in the textbook are extracted and graded. The graded labels are divided into n levels, for example, n=3, then U=[An, Bm, Ck], such as Figure 6As shown, among them: the first-level classification An is taken as the main node, and is classified by chapter, and An=[A1, A2...An] is obtained; the second-level classification Bm is taken as the slave node of An, and is classified by section, and Bm=[A1b1, A1b2, A2b1...Anbm] is obtained; the third-level classification Ck is taken as the slave node of Bm, and is classified by unit results, and Ck=[A1b1c1, A1b2c2, A1b2c3...Anbmck] is obtained.

[0052] In some examples, identification codes are used to reflect the hierarchical structure of knowledge points (such as chapters, sections, and units). Each knowledge point corresponds to a unique identification code. The specific forms of identification code values ​​may include digital numbers, letter numbers, mixed numbers, etc. These identification code values ​​can be designed according to the hierarchical structure of the knowledge points and converted into identification vectors through one-hot encoding or other methods for further processing and analysis.

[0053] In some examples, by encoding the hierarchical identification, a unique identification code is matched for each knowledge point, and a corresponding identification vector is generated according to the identification code. A knowledge point network is constructed based on the identification vector, and the knowledge point network is used to represent the relationship between knowledge points, and then multiple knowledge point networks are combined into a comprehensive identification vector set Uori (i.e., basic knowledge point cluster).

[0054] In some examples, the course video can also be recorded and stored through IoT devices (cameras, smart blackboards, etc.); then the audio is converted into text through a pre-trained speech-to-text model. The speech-to-text model can use the OpenAI open source model Whisper to construct an identification vector set Z corresponding to the knowledge point identification and generate a knowledge point network; based on the identification vector set (Dn, Em, Fk), the basic knowledge point cluster L=[Dn, Em, Fk] is obtained.

[0055] In some examples, knowledge point network coverage refers to grading knowledge points according to their importance and complexity, and ensuring that all possible combinations of knowledge points are covered. Through multi-level classification identification and identification vector construction, the knowledge system of the textbook content can be systematically represented to form a complete knowledge framework.

[0056] Specifically, the importance score of each knowledge point in the basic knowledge point cluster is obtained, wherein the importance score G is calculated by using a pre-trained evaluation model (Formula 2); according to the importance score, the importance of each knowledge point is determined. Formula 2 is specifically as follows: (Formula 2) In Formula 2, Z, X, V, and Y are the number of identification vectors corresponding to the first-level, second-level, third-level, and n-level knowledge points in the basic knowledge point cluster, respectively. , , , are the weight coefficients corresponding to the importance of the first-level, second-level, third-level, and n-level identification vectors, is the weight score corresponding to the importance of the n-level identification vector, and < < , because as the knowledge points become more refined, their importance accounts for a larger proportion.

[0057] In some examples, the weight coefficient should reflect the importance and complexity of each level of knowledge points. For example: the knowledge points corresponding to the first-level classification are usually relatively broad concepts with lower weights, the knowledge points corresponding to the second-level classification further refine the content and have moderate weights, and the knowledge points corresponding to the third-level classification are relatively detailed knowledge points with the highest weights. Adjust the weight coefficient according to the actual situation to ensure that the scoring model can accurately reflect the actual importance of the knowledge points. As time goes by and new knowledge is introduced, the weight coefficient may need to be re-evaluated and adjusted. In addition to the degree of refinement of the knowledge points, other factors (such as the frequency of application of the knowledge points, difficulty, etc.) can also be considered to adjust the weight coefficient.

[0058] For example, a basic knowledge point cluster Zori=[Wn, Rm, Hk] can be generated by obtaining a historical question bank according to the identification vector set (Wn, Rm, Hk); and then the basic knowledge point cluster is screened by a pre-trained key knowledge point evaluation model (Formula 3), wherein Formula 3 is specifically as follows: (Formula 3) in, The number of times the test knowledge point appears; is the frequency of errors in the test knowledge points; Gr is the number of branches of the test knowledge points; α is the weight score of the corresponding indicator. Set the scoring threshold T2, when When >T2, the key knowledge point combination is selected to form the second important knowledge point cluster Znew.

[0059] Step 402: Screening is performed in the basic knowledge point cluster based on the importance of each knowledge point and a preset screening threshold, and the screened knowledge point set is determined as an important knowledge point cluster.

[0060] The preset screening threshold is an initial value set according to the importance of the identification vector.

[0061] Exemplarily, a screening threshold T1 is set, and when G>T1, the screened knowledge point identification vector is used as the important knowledge point cluster Unew, such as Figure 7As shown, the initial threshold can be set by customizing, averaging, median and other methods, which are not limited in this embodiment.

[0062] By applying the method of this embodiment, important knowledge point clusters can be effectively screened out. According to the actual situation, a suitable screening threshold setting method is selected to ensure that the screening result can accurately reflect the importance of the knowledge point.

[0063] Optionally, when adjusting the difficulty level of knowledge points in the question bank knowledge graph, the following methods may be used but are not limited to: Figure 8 As shown, the method includes: Step 501: Based on the learning data features of the user in the question bank knowledge graph, a knowledge base is constructed that is classified according to knowledge points of corresponding difficulty levels. The learning data features are used to analyze the user's learning process and learning effect.

[0064] For example, learning data features may include one or more of the online learning time, number of requests for help, number of effective help, response efficiency, accuracy, learning progress, answering time, and proficiency of a single knowledge point. The answering time is the time that starts in the background after the user enters the answering interface. At this time, there may be idle behavior, no answering for too long or waiting for a long time before starting to answer, or exiting the current question and re-entering the page next time.

[0065] In some examples, knowledge points can be classified according to their difficulty levels, knowledge points of similar difficulty can be grouped together, and their classification can be dynamically adjusted to reflect the user's latest learning progress. For knowledge points of different difficulty levels, corresponding question sets are generated or updated. Through this knowledge point classification method based on user learning data characteristics, the constructed knowledge base can not only accurately match the user's personalized needs, but also help users gradually improve their mastery of knowledge points of each difficulty level, thereby achieving more efficient learning path planning and resource allocation.

[0066] Step 502: Use the knowledge base to evaluate the user's mastery of each knowledge point.

[0067] In some examples, according to the information identification and preset relationship arrangement of the basic knowledge point clusters and the important knowledge point clusters, the learning grids corresponding to all the knowledge point clusters contained in a chapter of the textbook content are arranged to form a learning area. The preset relationship between knowledge points may include hierarchical relationship, causal relationship, etc. Each learning grid contains all relevant information of the knowledge point cluster, such as the knowledge point name, description, difficulty level, etc.

[0068] In some examples, a learning map is generated based on the learning area, and each learning grid in the learning map corresponds to all the questions corresponding to a knowledge point cluster in the question bank. Each learning grid in the learning map corresponds to all the questions corresponding to a knowledge point cluster in the question bank. The learning map can be a graphical representation or a structured list, which can provide personalized learning paths and improve learning efficiency based on the student's learning progress and knowledge mastery.

[0069] For example, the learning map can provide personalized learning paths and improve learning efficiency based on students' learning progress and knowledge mastery. Specifically, the learning map can record students' completion status in each learning grid, evaluate students' mastery of each knowledge point through tests or exercises, and then recommend learning paths and questions suitable for them based on the students' evaluation results. Suppose a student has mastered the knowledge point of "variables and constants" but has encountered difficulties in "expressions and equations", the learning map can suggest that the student review the relevant basic knowledge first, and then practice more complex questions.

[0070] Exemplarily, the area corresponding to the important knowledge point cluster on the learning map is determined as the key monitoring area. The dynamic update mechanism of the key monitoring area realizes intelligent management through multi-source data fusion and machine learning technology. Its core process includes: constructing a multi-dimensional association network of operation behavior and knowledge graph, learning path, and spatial topology, and establishing a dual-mode user profile database containing static attributes and dynamic behavior characteristics based on the question bank knowledge graph or using the improved K-means++ Clustering Algorithm (Improved K-means++ Clustering Algorithm, K-means++) clustering algorithm combined with the long short-term memory neural network (Long Short-Term Memory Neural Network, LSTM) neural network; based on the dual-mode user profile database containing static attributes and dynamic behavior characteristics (Dual-Mode User Profile Database with StaticAttributes and Dynamic Behavioral It uses DBSCAN (Data Base Scan) spatial clustering analysis to identify operation-intensive areas, innovatively introduces a nonlinear evaluation model of the number of terminals and the degree of mastery of knowledge points, and dynamically adjusts the monitoring boundary through an adaptive grid division algorithm to form an intelligent closed-loop system that includes behavioral heat map analysis, intelligent resource allocation, and multi-dimensional evaluation of learning effectiveness. It realizes dynamic matching of knowledge blind spot warning, path optimization, and teacher allocation, and promotes the upgrade of student learning monitoring to cognitive perception-based intelligent monitoring.

[0071] In some examples, cluster analysis is performed on user operation behavior data to form key monitoring area information with multiple different characteristics, and the cluster center point in the required area is used as the key point or key location point. Different area information is set, and the number of user terminals within the area is obtained (the number of terminals can reflect the user's mastery of the knowledge points of the location. If the number of people who master it is large, the number of user terminals in the area is small, and it is assumed that most users can master it) as the basis for setting the key points, so that new key monitoring area information can be constructed or incremented.

[0072] Step 503: Dynamically adjust the difficulty level of the knowledge points in the question bank knowledge graph according to the user's mastery of each knowledge point.

[0073] For example, dynamically adjusting the difficulty level and question configuration of knowledge points based on the user's mastery of the knowledge points can enable the question bank knowledge graph to better adapt to the user's personalized learning needs.

[0074] Optionally, when matching the question bank knowledge graph with the user's learning conversation record and monitoring the user's question-answering situation based on the matching result, the following methods may be used but are not limited to: Fig. 9 As shown, the method includes: Step 601: Identify management detection feature data corresponding to the learning conversation record through a deep learning model.

[0075] For example, the management detection feature data of the chat content can be identified based on a model that combines a pre-trained language model using Bidirectional Encoder Representations from Transformers (BERT) and a Recurrent Neural Network (RNN) model, and the content comparison model can be used to determine whether the chat content belongs to the knowledge base content.

[0076] Step 602: Based on the management detection feature data, the learning conversation record is scored using a learning quality scoring model.

[0077] In some examples, user A asks user B a question / helps and sends information related to the question to the chat box; during the chat, the system monitors the chat box conversation content in real time (learning conversation record); finally, user A gives feedback that the conversation has been resolved / unresolved / ended as an instruction to terminate monitoring; assuming that a single conversation contains N messages, of which K are identified as knowledge base content, the following core indicators are defined: Dependency Index (DI) and Cognitive Leap Span (CLS).

[0078] Exemplarily, the dependency index between the chat content and the knowledge base content within the time window T is determined, and multiple time windows T are statistically analyzed to determine whether the chat content of the user at this stage is related to learning. The calculation formula of the dependency index is shown in Formula 4: (Formula 4) in, is the similarity between the i-th chat content and the knowledge base content, For enhanced items, the higher the similarity, the stronger the dependence.

[0079] For example, the thinking transition degree is used to evaluate the reasoning logic of the chat content context, and the semantic analysis model and word vector embedding model are used to extract the semantic feature vector of the chat content. , based on the DIKWP model, calculate the semantic jump distance of adjacent messages , and then the weighted summation after standardization is obtained to obtain CLS, as shown in Formula 5: (Formula 5) in, , For global conversation data The mean and standard deviation of is the time decay weight, ( , the recency effect is strengthened).

[0080] For example, the learning conversation record is scored, and the chat content quality scoring model is shown in Formula 6: (Formula 6) in, is the dynamic penalty factor, A proportional penalty is imposed for the portion exceeding the threshold. is the indicator function, ,in For content that does not belong to the knowledge base, The message count threshold.

[0081] Step 603: Determine the degree of match between the question bank knowledge graph and the learning conversation record according to the learning quality score corresponding to the learning conversation record.

[0082] For example, after calculating the learning quality score Q, these knowledge points are matched with the knowledge points in the question bank knowledge graph to evaluate their consistency. The degree of match can be determined by comparing the overlap between the knowledge points mentioned in the conversation and the corresponding knowledge points in the question bank and the user's performance on these knowledge points. A high degree of match means that the question bank knowledge graph can well reflect the user's learning content and needs, and the user's learning process is relatively smooth, while a low degree of match may indicate that the user has unresolved problems or is inefficient in answering questions.

[0083] Step 604: If the matching degree is lower than the first warning threshold, the warning mechanism is triggered and warning information is generated based on the user's test-taking situation.

[0084] Exemplarily, a first warning threshold G1 can be set. When Q<G1, a warning is triggered and the warning information is reported to the guardian app. The warning information includes: question / help information, chat start / end time, dialogue feedback results, etc.; it helps the guardian to monitor the students' problem-solving status in a timely manner. If the problem is not solved, it can help the students to answer it in time, thereby improving the efficiency of problem-solving.

[0085] Optionally, when matching the question bank knowledge graph with the user's learning conversation record and monitoring the user's question-answering situation based on the matching result, the following methods may also be used but are not limited to: Fig.10 As shown, the method includes: Step 701: Map the teaching materials and learning conversation records to a unified multimodal space through feature space projection, and calculate the geometric distance and semantic similarity of cross-modal features.

[0086] In some examples, the knowledge base can be constructed by acquiring the knowledge point learning data in the question bank knowledge point map. The knowledge point learning data includes teaching materials, question banks and answers, courseware and other data. The knowledge base classification results are obtained after cluster analysis using the pre-trained classification model. The knowledge base classification results are classified according to the corresponding knowledge points. The classification model is a model that combines the BERT pre-trained language model + RNN model, which can divide the knowledge base and chat content into three categories: text, formula, and chart.

[0087] For example, the textbook text, formulas, charts and learning conversation records are projected into a unified high-dimensional space through heterogeneous encoders to achieve dual alignment of semantics and structure, integrate geometric distance (cosine similarity) and semantic similarity (concept association strength), establish an interpretable measurement system for cross-modal features, dynamically adjust the judgment threshold according to the historical data distribution, balance the precision and recall rate, and solve the distribution shift problem caused by knowledge base updates.

[0088] In some examples, the model training method includes: inputting textbook PDF / text + formula LaTeX + chart image on the textbook side, and inputting chat text + screenshot (including formula / chart) on the user side. The feature encoder is conditionally configured, the functional module of core reasoning), and the text encoding adopts the improved Curriculum-BERT model (knowledge distillation). On the basis of standard BERT, the textbook domain vocabulary (such as mathematical symbols, professional terms) is added to the chapter level position encoding as shown in Formula 7: (Formula 7) Where c is the chapter number, l is the level depth (e.g. chapter is 1, section is 2, subsection is 3), and pos is the position of the character in the paragraph. is the hidden layer dimension of the BERT model, i is the dimension index, The item achieves attenuated attention to deep chapter structure. The deeper the level (such as subsection), the smaller the fluctuation of position encoding.

[0089] In some examples, the process of formula graph convolution encoding includes: Step 1: LaTeX is parsed into a syntax tree → converted into a graph structure G=(V,E), where the node set V is an operator, an operand, a special symbol, and the edge set E is a grammatical dependency; Step 2: Graph convolution is iteratively updated, as shown in Formula 8: (Formula 8) in, is the feature vector of node v at layer k (the number of layers k is usually 3 to balance local and global features), is the neighbor set of node v, is the normalized coefficient of edge (v,u) (usually the node degree), is the learnable weight matrix of the kth layer, is the GELU activation function In some examples, the dynamic threshold decision mechanism first needs to calculate the basic similarity: (Formula 9) in, is the feature vector of student chat content, is the knowledge base feature vector, is the feature space standard deviation Second, calculate the adaptive threshold: (Formula 10) in, is the initial threshold (default 0.85), η is the maximum adjustment range, k is the adjustment rate, t is the current training round, The starting round to trigger the adjustment Then calculate the decision function: (Formula 11) In some examples, the multimodal pre-training steps include: establishing a cross-modal unified representation space. Step 1: Knowledge base parsing: converting text into a hierarchically labeled token sequence, formulas into a grammatical graph structure, and charts into coordinate annotated images; Step 2: Contrastive learning: positive sample pairs: (knowledge base text segment, corresponding formula / chart), negative sample pairs: Type 1: randomly replace the formulas in the textbook, Type 2: shuffle the chart coordinate annotations.

[0090] Calculate the loss function: (Formula 12) in, is the interval parameter (the default is 0.2), (a, p, n) is the anchor point, positive example, and negative example triplet.

[0091] In some examples, the model can also be fine-tuned discriminatively to enhance the ability to distinguish between teaching material features and non-teaching material features. Specifically, the method of hybrid enhanced data generation (using complex samples to improve the accuracy of model recognition), semantic preservation perturbation, and synonym replacement is as follows: (Formula 13) Among them, x is a word, w is a synonym of x, Cos() is the similarity, combined with sentence conversion, active and passive voice conversion, structure destruction operation, and random discard of formula nodes, as shown in the following formula: (Formula 14) In the DropNode random deletion method, the graph offset is as follows: (Formula 15) in, is the offset.

[0092] Exemplarily, the training process can be conducted in three stages: elementary, intermediate, and advanced. The sample complexity can be gradually increased in stages to improve the accuracy of model recognition.

[0093] Step 702: Based on the geometric distance and semantic similarity of cross-modal features, the matching degree between the question bank knowledge graph and the learning dialogue record is determined through a decision function.

[0094] For example, Fig.11As shown in the figure, first the user input is processed to extract multimodal features, which are then fused with the knowledge base features in the pre-computed cache. Through the knowledge distillation technology, the cross-modal fused features are further optimized to finally generate dynamic decision results. This series of steps ensures that the system can efficiently process complex information and make real-time decisions based on comprehensive analysis.

[0095] In some embodiments, the first step is to input the chat content "The Pythagorean theorem formula is ; The second processing step includes the text encoder: extracting the concept features of "Pythagorean Theorem" , Formula Encoder: Parsing Formula Structure Generation , cross-modal fusion is shown in the following formula: (Formula 16) Based on the above embodiment steps, the third step is to search the textbook library: find all Pythagorean theorem related entries in the mathematics textbooks , the fourth step is decision calculation: (Formula 17) For example, if the current threshold θ=0.88, it can be determined that the learning dialogue record matches the standard and belongs to the content of the question bank knowledge graph.

[0096] Step 703: If the matching degree is lower than the second warning threshold, the warning mechanism is triggered and warning information is generated based on the user's test-taking situation.

[0097] Among them, the second warning threshold can be adaptively adjusted based on the historical data distribution.

[0098] Exemplarily, a second warning threshold G2 may be set. When the value is less than G2, an early warning is triggered and the early warning information is reported to the guardian app. The early warning information includes: question / help information, chat start / end time, dialogue feedback results, etc.; it helps the guardian to monitor the students' problem-solving status in a timely manner. If the problem is not solved, it can help students to solve it in time, thereby improving the efficiency of problem-solving.

[0099] Compared with the current existing technology, this embodiment can obtain basic knowledge point clusters from textbooks and further extract important knowledge point clusters through analysis and processing of text information, thereby effectively distinguishing important knowledge points from basic knowledge points and improving the accuracy of important knowledge point screening. By further constructing a question bank knowledge graph, knowledge points are associated with questions, and the graph is used to monitor and analyze students' question-answering situation, students can accurately answer questions on key knowledge points, thereby achieving personalized learning assistance.

[0100] Further, as Figures 1 to 10The specific implementation of the method shown in the embodiment provides a learning assistance device based on the question bank knowledge graph, such as Fig.12 As shown, the device includes: an extraction module 81, an evaluation module 82, a generation module 83, a construction module 84, and a monitoring module 85.

[0101] An extraction module 81 is configured to extract knowledge points based on the textbook text to obtain basic knowledge point clusters; An evaluation module 82 is configured to evaluate the importance of the knowledge points in the basic knowledge point cluster, and filter out important knowledge point clusters according to the evaluation results; A generating module 83 is configured to determine the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the teaching material, generate a knowledge tree including the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree; A construction module 84 is configured to construct a question bank knowledge graph according to the association strength between the various knowledge points, wherein the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the association relationship between different knowledge points; The monitoring module 85 is configured to match the question bank knowledge graph with the user's learning conversation record, and monitor the user's question-answering situation based on the matching result.

[0102] In some examples of the present embodiment, the generation module 83 is specifically configured to divide the difficulty level of each knowledge point according to the number of branches of the knowledge tree; determine the association strength between the first knowledge point and the second knowledge point according to the overlap of questions between the first knowledge point and the second knowledge point of adjacent difficulty levels; accordingly, the construction module 84 is specifically configured to update the questions of the corresponding difficulty levels of the first knowledge point and / or the second knowledge point in the question bank knowledge graph based on the association strength between the first knowledge point and the second knowledge point.

[0103] In some examples of this embodiment, the generation module 83 is further configured to determine the association strength between the first knowledge point and the second knowledge point based on the topic set corresponding to the first knowledge point and the topic set corresponding to the second knowledge point, wherein the association strength is defined as:

[0104] in, is a set of questions corresponding to the first knowledge point, is the set of questions corresponding to the second knowledge point, is the total number of questions marking the first knowledge point, The total number of questions marking the second knowledge point, is the total number of questions that are marked with both the first knowledge point and the second knowledge point.

[0105] In some examples of this embodiment, the generation module 83 is further specifically configured to adjust the question update strategy corresponding to the first knowledge point and / or the second knowledge point according to the association strength and a preset association strength threshold; and update the questions of the difficulty level corresponding to the first knowledge point and / or the second knowledge point in the question bank knowledge graph according to the question update strategy.

[0106] In some examples of the present embodiment, the evaluation module 82 is specifically configured to evaluate the importance of the knowledge points in the basic knowledge point cluster using a pre-trained evaluation model, where the evaluation indicators include one or more of the number of identification vectors corresponding to knowledge points at each level in the knowledge point cluster, the weight scores corresponding to the importance of knowledge points at each level, the number of occurrences of the knowledge points corresponding to the test points, and the number of error frequencies of the knowledge points corresponding to the test points; based on the importance of each knowledge point and a preset screening threshold, the basic knowledge point cluster is screened, and the screened knowledge point set is determined as the important knowledge point cluster, wherein the preset screening threshold is an initial value set for the importance of each knowledge point.

[0107] In some examples of this embodiment, the construction module 84 is further specifically configured to construct a knowledge base that classifies knowledge points according to corresponding difficulty levels based on the learning data features of the user in the question bank knowledge graph, and the learning data features are used to analyze the learning process and learning effect of the user; use the knowledge base to evaluate the user's mastery of each knowledge point; and dynamically adjust the difficulty level of the knowledge points in the question bank knowledge graph according to the user's mastery of each knowledge point.

[0108] In some examples of this embodiment, the monitoring module 85 is specifically configured to identify the management detection feature data corresponding to the learning conversation record through a deep learning model; based on the management detection feature data, score the learning conversation record using a learning quality scoring model; determine the matching degree between the question bank knowledge graph and the learning conversation record according to the learning quality score corresponding to the learning conversation record; if the matching degree is lower than a first warning threshold, trigger the warning mechanism and generate warning information based on the user's question-answering situation.

[0109] In some examples of this embodiment, the monitoring module 85 is further configured to map the teaching materials and the learning conversation records to a unified multimodal space through feature space projection, and calculate the geometric distance and semantic similarity of cross-modal features; based on the geometric distance and semantic similarity of the cross-modal features, determine the matching degree between the question bank knowledge graph and the learning conversation records through a decision function; if the matching degree is lower than a second warning threshold, trigger the warning mechanism and generate warning information based on the user's question-answering situation, and the second warning threshold is adaptively adjusted based on the historical data distribution.

[0110] It should be noted that for other corresponding descriptions of the functional units involved in the learning assistance device based on the question bank knowledge graph provided in this embodiment, please refer to Figures 1 to 10 The corresponding description in will not be repeated here.

[0111] Based on the above Figures 1 to 10 The method shown in the embodiment also provides a computer-readable storage medium on which a computer program is stored. When the computer program is executed by a processor, the above-mentioned Figures 1 to 10 The method shown.

[0112] Based on this understanding, the technical solution of the present application can be embodied in the form of a software product, which can be stored in a non-volatile storage medium (which can be a CD-ROM, USB flash drive, mobile hard disk, etc.), including a number of instructions for enabling a computer device (which can be a personal computer, server, or network device, etc.) to execute the methods of various implementation scenarios of the present application.

[0113] like Fig.13 The figure shows a hardware structure diagram of an electronic device of the present invention, including: at least one processor 901; and, A memory 902 that is communicatively connected to at least one of the processors 901; wherein: The memory 902 stores instructions that can be executed by at least one of the processors, and the instructions are executed by at least one of the processors so that at least one of the processors can execute the learning assistance method based on the question bank knowledge graph as described above.

[0114] Fig.13 A processor 901 is taken as an example.

[0115] The electronic device may further include: an input device 903 and a display device 904 .

[0116] The processor 901, the memory 902, the input device 903 and the display device 904 may be connected via a bus or other means. Fig.13 The example of connecting through bus is taken in the following.

[0117] The memory 902 is a non-volatile computer-readable storage medium that can be used to store non-volatile software programs, non-volatile computer executable programs and modules, such as program instructions / modules corresponding to the learning assistance method based on the question bank knowledge graph in the embodiment of the present application, for example, Figures 1 to 8 The processor 901 executes various functional applications and data processing by running the non-volatile software programs, instructions and modules stored in the memory 902, that is, the learning assistance method based on the question bank knowledge graph in the above embodiment is implemented.

[0118] The memory 902 may include a program storage area and a data storage area, wherein the program storage area may store an operating system, an application required for at least one function; the data storage area may store data created based on the use of a learning assistance method based on a question bank knowledge graph, etc. In addition, the memory 902 may include a high-speed random access memory, and may also include a non-volatile memory, such as at least one disk storage device, a flash memory device, or other non-volatile solid-state storage device. In some embodiments, the memory 902 may optionally include a memory remotely arranged relative to the processor 901, and these remote memories may be connected to a device for executing a learning assistance method based on a question bank knowledge graph via a network. Examples of the above-mentioned network include, but are not limited to, the Internet, an intranet, a local area network, a mobile communication network, and combinations thereof.

[0119] The input device 903 can receive input user clicks and generate signal input related to user settings and function control of the learning assistance method based on the question bank knowledge graph. The display device 904 can include display devices such as a display screen.

[0120] The one or more modules are stored in the memory 902, and when executed by the one or more processors 901, the learning assistance method based on the question bank knowledge graph in any of the above method embodiments is executed.

[0121] Optionally, the above-mentioned physical device may also include a user interface, a network interface, a camera, a radio frequency (RF) circuit, a sensor, an audio circuit, a WI-FI module, etc. The user interface may include a display, an input unit such as a keyboard, etc., and the optional user interface may also include a USB interface, a card reader interface, etc. The network interface may optionally include a standard wired interface, a wireless interface (such as a WI-FI interface), etc.

[0122] Those skilled in the art will appreciate that the above-mentioned physical device structure provided in this embodiment does not constitute a limitation on the physical device, and may include more or fewer components, or a combination of certain components, or different arrangements of components.

[0123] 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 above-mentioned physical device, and supports the operation of the information processing program and other software and / or programs. The network communication module is used to realize the communication between the components inside the storage medium, and the communication with other hardware and software in the information processing physical device.

[0124] Through the description of the above implementation methods, the technical personnel in this field can clearly understand that the present application can be implemented by means of software plus the necessary general hardware platform, or by hardware. By applying the scheme of this embodiment, compared with the current prior art, this embodiment first extracts knowledge points based on the textbook text to obtain a basic knowledge point cluster; evaluates the importance of the knowledge points in the basic knowledge point cluster, and obtains an important knowledge point cluster based on the evaluation results; determines the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the textbook, generates a knowledge tree containing the knowledge point distribution information, and determines the correlation strength between each knowledge point based on the number of branches of the knowledge tree; constructs a question bank knowledge graph based on the correlation strength between each knowledge point, and the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation between different knowledge points; matches the question bank knowledge graph with the user's learning dialogue record, and monitors the user's question-answering situation based on the matching results. By analyzing and processing text information, we can obtain basic knowledge point clusters from textbooks and further extract important knowledge point clusters, thereby effectively distinguishing important knowledge points from basic knowledge points and improving the accuracy of screening important knowledge points. By further constructing a question bank knowledge graph, we can associate knowledge points with questions, and use the graph to monitor and analyze students' question-answering situation, so that students can accurately answer questions on key knowledge points, thereby achieving personalized learning assistance.

[0125] It should be noted that, in this article, relational terms such as "first" and "second" are only used to distinguish one entity or operation from another entity or operation, and do not necessarily require or imply any such actual relationship or order between these entities or operations. Moreover, the terms "include", "comprise" or any other variants thereof are intended to cover non-exclusive inclusion, so that a process, method, article or device including a series of elements includes not only those elements, but also other elements not explicitly listed, or also includes elements inherent to such process, method, article or device. In the absence of further restrictions, the elements defined by the sentence "comprise a ..." do not exclude the existence of other identical elements in the process, method, article or device including the elements.

[0126] The above is only a specific implementation of the present application, so that those skilled in the art can understand or implement the present application. Various modifications to these embodiments will be apparent to those skilled in the art, and the general principles defined herein can be implemented in other embodiments without departing from the spirit or scope of the present application. Therefore, the present application will not be limited to the embodiments described herein, but will conform to the widest scope consistent with the principles and novel features applied for herein.

Claims

1. A learning assistance method based on question bank knowledge graph, characterized in that: include: Extract knowledge points based on textbook texts to obtain basic knowledge point clusters; Evaluate the importance of the knowledge points in the basic knowledge point cluster, and select important knowledge point clusters according to the evaluation results; Determine the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the textbook, generate a knowledge tree containing the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree; According to the correlation strength between the various knowledge points, a question bank knowledge graph is constructed, wherein the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the correlation between different knowledge points; The question bank knowledge graph is matched with the user's learning conversation record, and the user's question-answering status is monitored based on the matching result.

2. The method according to claim 1, characterized in that The determining the association strength between the knowledge points according to the number of branches of the knowledge tree includes: Dividing the difficulty level of each knowledge point according to the number of branches of the knowledge tree; Determining the strength of association between the first knowledge point and the second knowledge point according to the overlapping of questions between the first knowledge point and the second knowledge point of adjacent difficulty levels; The step of constructing a question bank knowledge graph according to the association strength between the various knowledge points includes: Based on the correlation strength between the first knowledge point and the second knowledge point, questions of corresponding difficulty levels of the first knowledge point and / or the second knowledge point are updated in the question bank knowledge graph.

3. The method according to claim 2, characterized in that The determining the association strength between the first knowledge point and the second knowledge point according to the overlapping of questions between the first knowledge point and the second knowledge point of adjacent difficulty levels includes: Based on the topic set corresponding to the first knowledge point and the topic set corresponding to the second knowledge point, the association strength between the first knowledge point and the second knowledge point is determined. is defined as: in, is a set of questions corresponding to the first knowledge point, is the set of questions corresponding to the second knowledge point, is the total number of questions marking the first knowledge point, The total number of questions marking the second knowledge point, is the total number of questions that are marked with both the first knowledge point and the second knowledge point.

4. The method according to claim 2, characterized in that: The updating of questions of difficulty levels corresponding to the first knowledge point and / or the second knowledge point in the question bank knowledge graph based on the association strength between the first knowledge point and the second knowledge point includes: According to the association strength and a preset association strength threshold, adjusting a question update strategy corresponding to the first knowledge point and / or the second knowledge point; According to the question updating strategy, questions of difficulty levels corresponding to the first knowledge point and / or the second knowledge point are updated in the question bank knowledge graph.

5. The method according to claim 1, characterized in that The step of evaluating the importance of the knowledge points in the basic knowledge point cluster and screening the important knowledge point cluster according to the evaluation result includes: Using a pre-trained evaluation model to evaluate the importance of the knowledge points in the basic knowledge point cluster, the evaluation indicators include one or more of the number of identification vectors corresponding to the knowledge points at each level in the knowledge point cluster, the weight scores corresponding to the importance of the knowledge points at each level, the number of occurrences of the knowledge points corresponding to the test points, and the number of error frequencies of the knowledge points corresponding to the test points; The basic knowledge point cluster is screened based on the importance of each knowledge point and a preset screening threshold, and the screened knowledge point set is determined as the important knowledge point cluster, wherein the preset screening threshold is an initial value set for the importance of each knowledge point.

6. The method according to claim 1, characterized in that The method further comprises: Based on the learning data features of the user in the question bank knowledge graph, a knowledge base is constructed that is classified according to knowledge points of corresponding difficulty levels, and the learning data features are used to analyze the learning process and learning effect of the user; Using the knowledge base to evaluate the user's mastery of each knowledge point; The difficulty level of the knowledge points in the question bank knowledge graph is dynamically adjusted according to the user's mastery of each knowledge point.

7. The method according to claim 1, characterized in that The matching of the question bank knowledge graph with the user's learning conversation record and monitoring the user's question-answering situation according to the matching result includes: Identify management detection feature data corresponding to the learning conversation record through a deep learning model; Based on the management detection feature data, scoring the learning conversation record using a learning quality scoring model; Determining the matching degree between the question bank knowledge graph and the learning conversation record according to the learning quality score corresponding to the learning conversation record; If the matching degree is lower than the first warning threshold, the warning mechanism is triggered and warning information is generated based on the user's answering situation.

8. The method according to claim 1, characterized in that The matching of the question bank knowledge graph with the user's learning conversation record and monitoring the user's question-answering situation according to the matching result includes: Mapping the teaching material and the learning dialogue record to a unified multimodal space through feature space projection, and calculating the geometric distance and semantic similarity of cross-modal features; Based on the geometric distance and semantic similarity of the cross-modal features, determining the matching degree between the question bank knowledge graph and the learning dialogue record through a decision function; If the matching degree is lower than a second warning threshold, the warning mechanism is triggered and warning information is generated based on the user's question-solving situation. The second warning threshold is adaptively adjusted based on historical data distribution.

9. A learning assistance device based on a question bank knowledge graph, characterized in that: include: An extraction module is configured to extract knowledge points based on the textbook text to obtain basic knowledge point clusters; An evaluation module is configured to evaluate the importance of the knowledge points in the basic knowledge point cluster, and screen the important knowledge point cluster according to the evaluation result; A generation module is configured to determine the knowledge point distribution information of the basic knowledge point cluster and the important knowledge point cluster in the teaching material, generate a knowledge tree containing the knowledge point distribution information, and determine the association strength between each knowledge point according to the number of branches of the knowledge tree; A construction module is configured to construct a question bank knowledge graph according to the association strength between the various knowledge points, wherein the question bank knowledge graph is used to display the questions corresponding to each knowledge point and the association relationship between different knowledge points; The monitoring module is configured to match the question bank knowledge graph with the user's learning conversation record, and monitor the user's question-answering situation based on the matching result.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that: When the computer program is executed by a processor, the method according to any one of claims 1 to 8 is implemented.

11. An electronic device comprising a storage medium, a processor, and a computer program stored in the storage medium and executable on the processor, characterized in that: When the processor executes the computer program, the method according to any one of claims 1 to 8 is implemented.

Images