Knowledge space control method and system for assisting learning

Abstract

The invention discloses a knowledge space control method and system for assisting learning, and relates to the technical field of knowledge space generation methods, and the method comprises the steps: determining a corresponding problem solving path according to the previous problem solving content of a user; and determining error contents of each problem solving node in the problem solving path based on matching of the problem solving path and the knowledge application space, and marking knowledge nodes associated with the error contents. Determining corresponding correct content according to the error content and knowledge content presented by the knowledge node, determining difference content between the correct content and the error content, determining a correct answering thought according to the difference content and the answering thought of the user relative to the error content, and marking knowledge difficult points of the user; the error factors of the user are determined according to the knowledge difficult points of the user, the corresponding mastering level and the answering accuracy of the user, the corresponding auxiliary learning measures are determined based on the error factors of the user and the current learning process of the user, and the accuracy of the auxiliary learning measures is improved.

Description

Technical Field

[0001] The present invention relates to the technical field of methods for generating knowledge spaces, and in particular to a method and system for controlling a knowledge space for assisting learning. Background Art

[0002] With the development of technology, users, as students, need to be compatible with both learning in class and training in the process of solving problems. Users gradually improve their learning process in class and develop their own problem-solving logic. At the same time, users encounter multiple errors in the process of solving problems and further reflect on the errors. However, the errors are stored along a single knowledge space. Reflection on the errors requires frequent searches for corresponding knowledge nodes, and the accuracy of the knowledge nodes cannot be guaranteed. It is further impossible to grasp the factors that lead to users' errors and the accuracy of auxiliary learning measures cannot be guaranteed. Summary of the Invention

[0003] The purpose of the present invention is to overcome the deficiencies of the prior art. The present invention provides a method and system for controlling a knowledge space for auxiliary learning.

[0004] An embodiment of the present invention provides a method for controlling a knowledge space for auxiliary learning, including: Collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; In the basic knowledge space, mark the user's current learning node, and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; In the knowledge application space, the corresponding problem-solving path is determined based on the user's previous problem-solving content. Based on the matching between the problem-solving path and the knowledge application space, the incorrect content of each problem-solving node in the problem-solving path is determined, and the knowledge nodes associated with the incorrect content are marked. In the problem-solving learning space, the correct content is determined based on the incorrect content and the knowledge content presented by the knowledge node, and the difference between the correct and incorrect content is determined. The correct answer is determined based on the difference and the user's answer to the incorrect content, and the user's knowledge difficulties are marked. Collect the user's mastery level of knowledge difficulties, and determine the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy. Based on the user's error factors and the user's current learning history, determine the corresponding auxiliary learning measures.

[0005] An embodiment of the present invention provides a control system for a knowledge space for assisting learning. The control system for the knowledge space for assisting learning is applied to the above-mentioned control method for the knowledge space for assisting learning. The control system for the knowledge space for assisting learning includes: The basic knowledge space module is used to collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; The knowledge application space module is used to mark the user's current learning node in the basic knowledge space and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; The knowledge node module is used to determine the corresponding problem-solving path in the knowledge application space based on the user's previous problem-solving content, determine the incorrect content of each problem-solving node in the problem-solving path based on the matching of the problem-solving path and the knowledge application space, and mark the knowledge node associated with the incorrect content; The knowledge difficulty point module is used to determine the corresponding correct content based on the incorrect content and the knowledge content presented by the knowledge node in the problem-solving learning space, and determine the difference between the correct content and the incorrect content. Based on the difference and the user's answer idea relative to the incorrect content, the correct answer idea is determined, and the user's knowledge difficulty point is marked; The auxiliary learning measures module is used to collect the user's mastery level of knowledge difficulties, and determine the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, and determine the corresponding auxiliary learning measures based on the user's error factors and the user's current learning process.

[0006] Compared with the prior art, the present invention has the following beneficial effects: In an embodiment of the present invention, through the method in the embodiment of the present invention, the user's personal information is collected, and the basic knowledge space is determined based on the user's personal information, learning history and learning database; in the basic knowledge space, the user's current learning node is marked, and the user's previous problem-solving content is determined by the user's current learning node and the knowledge application space; in the knowledge application space, the corresponding problem-solving path is determined based on the user's previous problem-solving content, and the erroneous content of each problem-solving node in the problem-solving path is determined based on the matching of the problem-solving path and the knowledge application space, and the knowledge nodes associated with the erroneous content are marked, and the basic knowledge space and the knowledge application space are introduced to ensure the accuracy of the erroneous content of each problem-solving node in the problem-solving path, improve the accuracy of the knowledge nodes, and ensure the full utilization of the basic knowledge space and the knowledge application space.

[0007] Therefore, in the problem-solving learning space, the corresponding correct content is determined based on the incorrect content and the knowledge content presented by the knowledge node, and the difference between the correct content and the incorrect content is determined. The correct answer idea is determined based on the difference content and the user's answer idea relative to the incorrect content, and the user's knowledge difficulties are marked; the user's mastery level of knowledge difficulties is collected, and the user's error factors are determined based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy. The corresponding auxiliary learning measures are determined based on the user's error factors and the user's current learning history. The problem-solving learning space is further introduced, which is compatible with the overall consideration of the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, ensuring the accuracy of the user's error factors and improving the accuracy of the auxiliary learning measures. BRIEF DESCRIPTION OF THE DRAWINGS

[0008] Figure 1 is a flow chart of a method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 2 1 is a flow chart of step S11 in the method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 3 1 is a flow chart of step S12 in the method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 4 1 is a flow chart of step S13 in the method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 5 1 is a flow chart of step S14 in the method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 6 1 is a flow chart of step S15 in the method for controlling a knowledge space for auxiliary learning in an embodiment of the present invention; Figure 7 It is a schematic diagram of the structural composition of the control system of the knowledge space for auxiliary learning in an embodiment of the present invention. DETAILED DESCRIPTION

[0009] The technical solutions in the embodiments of the present invention will be described clearly and completely below with reference to the accompanying drawings in the embodiments of the present invention.

[0010] See also Figures 1 to 7 A method for controlling a knowledge space for auxiliary learning is provided, and a control scenario of the knowledge space is applied; the method for controlling a knowledge space for auxiliary learning includes: Step S11: Collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; Step S12: Mark the user's current learning node in the basic knowledge space, and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; Step S13: In the knowledge application space, a corresponding problem-solving path is determined based on the user's previous problem-solving content. Based on the matching between the problem-solving path and the knowledge application space, the incorrect content of each problem-solving node in the problem-solving path is determined, and the knowledge nodes associated with the incorrect content are marked. Step S14: In the problem-solving learning space, the correct content corresponding to the incorrect content and the knowledge content presented by the knowledge node is determined, and the difference between the correct content and the incorrect content is determined. The correct answer is determined based on the difference and the user's answer strategy relative to the incorrect content, and the user's knowledge difficulties are marked. Step S15: Collecting the user's mastery level of knowledge difficulties, and determining the user's error factors based on the user's knowledge difficulties, the corresponding mastery level, and the user's answer accuracy, and determining corresponding auxiliary learning measures based on the user's error factors and the user's current learning process; refer to Figure 2 ,In step S11, the user's personal information is collected, and the basic knowledge space is determined according to the user's personal information, learning history and learning database; In the specific implementation process of the present invention, the specific steps are: S111: Collect the user's enrollment information and determine the user's personal information based on the traversal of the user's enrollment information. At the same time, collect the learning database and determine the user's learning nodes in different courses based on the learning database and the user's personal information. S112: Determine the user's learning history based on tracing back the user's learning nodes in different courses, determine a first space system based on the user's learning history and the user's personal information, and determine a second space system based on the user's learning history and the learning database; S113: Determine the basic knowledge space based on the synthesis of the first space system and the second space system. At this time, the basic knowledge space covers all learning events of the user in the learning process, and marks the learning events with corresponding learning tags.

[0011] In an embodiment of the present application, the user's admission information is collected, and the user's personal information is determined based on the traversal of the user's admission information. At the same time, the learning database is collected, and the user's learning nodes in different courses are determined based on the learning database and the user's personal information. This combines the overall consideration of the learning database and the user's personal information to ensure the accuracy of the user's learning nodes in different courses.

[0012] At this point, the user's basic information and learning background are collected; admission information usually includes the user's name, age, gender, educational background (such as previous school, grades, etc.), interests and hobbies, specialties, and any relevant admission test or interview results; this information is crucial for a preliminary understanding of the user's learning ability and potential.

[0013] The system will go through the admissions information in detail and extract key information to build the user's personal profile; this includes the user's age, gender, educational background, interests, hobbies, specialties, etc., as well as any factors that affect their learning, such as learning style, concentration, etc. (this information is obtained indirectly through admission tests or interviews).

[0014] The learning database is a huge system that contains resources such as knowledge points, learning paths, exercises, etc. for each course. In this step, the system will determine the user's starting learning node in different courses based on the user's personal information and the content of the learning database. This is usually based on factors such as the user's previous learning experience, grades, interests, and course prerequisites. At the same time, for the user, the system first checks his learning database. The database shows that the user has mastered most of the knowledge points in junior high school mathematics and science and has excellent grades. Therefore, when the user starts high school, the system recommends that he start with higher-level courses in mathematics and science courses, such as high school mathematics II and science III. At the same time, since the user has a strong interest in programming, the system also recommends that he start with an introductory programming course.

[0015] Furthermore, the user's learning history is determined by tracing the user's learning nodes in different courses, the first spatial system is determined based on the user's learning history and personal information, and the second spatial system is determined based on the user's learning history and learning database, which is compatible with the overall consideration of the user's learning history and learning database and ensures the accuracy of the second spatial system.

[0016] At this point, the system will trace and organize the user's learning history based on the user's learning nodes in different courses; learning nodes usually represent learning tasks completed or learning milestones reached by the user at a certain point in time, such as completing the study of a chapter, passing a test, obtaining a certificate, etc.; by tracing these nodes, the system constructs the user's learning path and learning progress; at this point, the system traced the user's learning nodes in different courses and found that he had completed the basic learning of algebra and geometry in the mathematics course and was learning calculus; in the science course, he had mastered the basic knowledge of physics and chemistry and was exploring advanced topics in biology; in addition, he had completed introductory learning in the programming course and was learning data structures.

[0017] The first space system is a personalized learning space, which is built based on the user's learning history and personal information; this space reflects the user's learning preferences, interests, ability level and learning progress; through the first space system, the system provides users with personalized learning resources, learning paths and learning suggestions; at this time, based on the user's learning history and personal information, the system builds the user's first space system; this system includes: according to the user's interests and ability level, the system recommends a series of mathematics, science and programming learning resources suitable for him, such as advanced mathematics tutorials, biology experiment guides, programming practice projects, etc.; the system plans a personalized learning path for the user, suggesting that he complete the study of calculus first, then delve into advanced topics in physics, and continue to improve his data structure and algorithm capabilities in programming; the system also provides some learning suggestions, such as participating in mathematics competitions to improve problem-solving skills, joining science laboratories for practical operations, and participating in programming communities to broaden his horizons.

[0018] The second space system is a universal learning space built based on the learning database; it contains knowledge points, learning paths, exercises and other resources of all courses, and is the basis for building basic knowledge space and learning path planning; through the second space system, the system provides users with comprehensive learning resources and learning support; at this time, the system builds the user's second space system based on the user's learning history and learning database; this system includes: the system organizes knowledge points in fields such as mathematics, science and programming, and provides users with comprehensive learning resources; the system provides multiple learning paths for users to choose from, each path contains learning content from basic to advanced and a recommended learning order; the system provides users with a large number of exercises and simulation tests to help them consolidate what they have learned and improve their problem-solving ability.

[0019] Therefore, the basic knowledge space is determined based on the synthesis of the first space system and the second space system. At this time, the basic knowledge space covers all learning events of the user in the learning process, and marks the learning events with corresponding learning tags, which is compatible with the overall consideration of the synthesis of the first space system and the second space system, ensuring the accuracy of the basic knowledge space.

[0020] At this time, the system will synthesize the first space system and the second space system; the first space system is a personalized learning space that reflects the user's learning preferences, interests, ability level and learning progress; and the second space system is a general learning space built based on the learning database, which contains knowledge points, learning paths, exercises and other resources of all courses; by synthesizing these two space systems, the system builds a basic knowledge space for users that is both personalized and comprehensive; at this time, the system first extracts personalized learning resources, learning paths and learning suggestions in the first space system, and then matches and integrates these contents with the knowledge point library, learning path library and exercise library in the second space system; during the integration process, the system will take into account the user's learning preferences and ability level to ensure that the content of the basic knowledge space is both in line with the user's needs and challenging.

[0021] Based on the synthesis of the first spatial system and the second spatial system, the system determines the basic knowledge space; this space covers all important learning events in the user's learning process, such as completed courses, passed tests, certificates obtained, etc.; at the same time, the system will mark these learning events and assign corresponding learning tags to each event, such as the name of the knowledge point, learning difficulty, mastery level, etc.; these tags help users quickly understand their learning progress and mastery; at this time, the system determines the basic knowledge space for the user based on his learning process and the integrated spatial system; this space contains the mathematics, science and programming knowledge points that the user has mastered, as well as the content he is learning and future learning plans; the system also assigns corresponding learning tags to each knowledge point or learning event, such as "Calculus-Basics-Mastered", "Biology-Cell Structure-Learning", etc.

[0022] After determining the basic knowledge space, the system will mark the learning events therein and assign corresponding learning tags to each event; these tags include the name of the knowledge point, the level of learning difficulty (such as elementary, intermediate, advanced), the degree of mastery (such as not mastered, partially mastered, proficiently mastered), etc.; by marking learning tags, the system helps users understand their learning progress and mastery more clearly, so as to formulate more effective learning plans; at the same time, the system assigns corresponding learning tags to each learning event in the user's basic knowledge space; for example, for the basic knowledge points of calculus that the user has mastered, the system marks them as "Calculus-Basics-Mastered"; for the biological cell structure content he is learning, the system marks it as "Biology-Cell Structure-Learning"; for the advanced topics of programming algorithms that he plans to learn in the future, the system marks them as "Programming-Algorithms-To be Learned".

[0023] In some embodiments of the present application, a first spatial system matching table is collected, and the first spatial system matching table is shown in Table 1: Table 1 First Space System Matching Table Collect the second space system matching table, which is shown in Table 2: Table 2 Second space system matching table By synthesizing these two space systems, we can obtain the user's basic knowledge space and collect the basic knowledge space matching table. The basic knowledge space is shown in Table 3: Table 3 Basic knowledge space matching table refer to Figure 3 In step S12, in the basic knowledge space, the user's current learning node is marked, and the user's previous problem-solving content is determined by combining the user's current learning node with the knowledge application space; In the specific implementation process of the present invention, the specific steps are: S121: If the user enters the basic knowledge space, the user's current learning node is determined based on the user's current time, the user's learning progress, and the corresponding subject category, and the user's current learning content is collected in the current learning node; S122: Determine a corresponding target subject based on the analysis of the current learning content, input the target subject into the knowledge application space, and determine the user's previous problem-solving content based on the matching between the target subject and the knowledge application space.

[0024] In an embodiment of the present application, if the user enters the basic knowledge space, the user's current learning node is determined according to the user's current time, the user's learning progress and the corresponding subject category. In the current learning node, the user's current learning content is collected, which is compatible with the overall consideration of the user's current time, the user's learning progress and the corresponding subject category, thereby ensuring the accuracy of the user's current learning node.

[0025] At this time, when the user logs in to the learning platform or application and chooses to enter the basic knowledge space, the system will record the user's behavior; the basic knowledge space is a personalized or general learning space, which contains various knowledge points, learning paths, learning resources, etc. involved in the user's learning process; at this time, assuming that the user logs in to the learning platform and clicks on the entrance to the "Basic Knowledge Space", the system will immediately record the user's behavior of entering the basic knowledge space.

[0026] The system will comprehensively consider the user's current time, learning progress and selected subject categories to determine the user's current learning node in the basic knowledge space; at the same time, the system records the specific time point when the user enters the basic knowledge space, which helps the system understand the user's learning rhythm and habits; the system will evaluate the user's learning progress in each subject category based on the user's previous learning records; this includes the knowledge points that the user has mastered, the content being learned, and the parts that have not yet been learned; when the user enters the basic knowledge space, he or she usually chooses one or more subject categories to study; the system will further determine the user's learning content in the current learning node based on the subject categories selected by the user.

[0027] Furthermore, the corresponding target subject is determined based on the analysis of the current learning content, the target subject is input into the knowledge application space, and the user's previous problem-solving content is determined based on the matching of the target subject and the knowledge application space, which is compatible with the overall consideration of the matching of the target subject and the knowledge application space, and ensures the accuracy of the user's previous problem-solving content.

[0028] At this time, the system will parse the current learning content to determine its corresponding target subject; the parsing process involves analyzing information such as keywords, context, and knowledge point associations in the learning content, so as to accurately identify the subject area to which the learning content belongs; at this time, assuming that the system has collected the content that the user is currently learning, this is a geometry problem about "parallel lines and intersecting lines"; the system will parse this problem and identify the keywords "parallel lines", "intersecting lines" and related geometry knowledge points; through this information, the system determines that the target subject of this problem is mathematics.

[0029] After determining the target subject, the system will input this information into the knowledge application space; the knowledge application space is a database containing various learning resources, exercises, problem-solving strategies and answer analysis; it is designed to help users consolidate the knowledge they have learned and improve their problem-solving ability; at this time, the system has entered the target subject "Mathematics" into the knowledge application space; in the knowledge application space, the system accesses various learning resources related to mathematics, including a question bank, a problem-solving strategy bank, an answer analysis bank, etc.

[0030] The system will search the knowledge application space for previous problem-solving content that matches the target subject; this content includes the user's previous exercises, error records, problem-solving strategies, and answer analysis, etc. By matching the target subject with the content in the knowledge application space, the system provides users with personalized learning resources and feedback. At this point, the system has searched the knowledge application space for previous problem-solving content related to mathematics subjects. For the user, the system has found the exercises he had done before on "parallel lines and intersecting lines", as well as the error records and corresponding answer analysis that he encountered when doing these problems. In addition, the system also recommends some problem-solving strategies and techniques related to the current learning content to the user.

[0031] In some embodiments of the present application, an answer resolution link matching table is collected, and the answer resolution link matching table is shown in Table 4: Table 4 Answer analysis link matching table In the answer analysis link matching table, the system can easily find the exercises that the user has done before that are related to the current learning content, as well as the solution status and answer analysis of these exercises.

[0032] refer to Figure 4 In step S13, in the knowledge application space, the corresponding problem-solving path is determined based on the user's previous problem-solving content. Based on the matching between the problem-solving path and the knowledge application space, the incorrect content of each problem-solving node in the problem-solving path is determined, and the knowledge nodes associated with the incorrect content are marked. In the specific implementation process of the present invention, the specific steps are: S131: Collect the knowledge application space and monitor the knowledge application space in real time, determine multiple sub-problem-solving contents based on the user's previous problem-solving content, determine corresponding problem-solving paths based on the details and order of the multiple sub-problem-solving contents, and mark each problem-solving node of the problem-solving path; S132: Determine the logic of the problem-solving approach based on the identification of the problem-solving path, determine the corresponding logic space of the problem-solving approach based on the matching of the logic of the problem-solving approach and the knowledge application space, and determine the content of the standard answer based on the traversal of the logic space of the problem-solving approach; S133: Determine the abnormal content area based on the match between the standard answer content and the user's previous problem-solving content, determine the erroneous content of each problem-solving node in the problem-solving path based on the identification of the abnormal content area, and determine the knowledge nodes associated with the erroneous content based on the tracing of the erroneous content.

[0033] In an embodiment of the present application, the knowledge application space is collected and monitored in real time. Multiple sub-problem-solving contents are determined based on the user's previous division of problem-solving contents. Corresponding problem-solving paths are determined according to the detailed contents and sorting of the multiple sub-problem-solving contents, and each problem-solving node of the problem-solving path is marked. This is compatible with the overall consideration of the detailed contents and sorting of the multiple sub-problem-solving contents, ensuring the accuracy of the corresponding problem-solving path.

[0034] At this time, the system will first collect all data related to the user's problem-solving from the knowledge application space; these data include the user's previous problem-solving records, practice question bank, problem-solving strategies, answer analysis, etc.; the purpose of collecting this data is to fully understand the user's learning situation and problem-solving habits, and provide a basis for subsequent analysis and processing; at this time, the system will extract the user's historical problem-solving records from the database of the knowledge application space. These records contain all the practice questions the user has done, the problem-solving steps for each question, the user's answer time, whether it is correct or not, and other information; at the same time, the system will also collect question information in the practice question bank, including the type of question, difficulty, and knowledge points involved.

[0035] After collecting data, the system will monitor the knowledge application space in real time; this means that the system will continue to track the user's activities in the knowledge application space, such as the exercises the user is doing, the answer analysis the user is viewing, the problem-solving strategies the user is using, etc.; the purpose of real-time monitoring is to promptly discover the problems and difficulties the user encounters during the learning process so that the system can respond quickly; at this time, the system will set some triggers or monitoring rules. When the user performs certain operations in the knowledge application space (such as starting a new question, viewing the answer analysis, etc.), the system will immediately capture these operations and record them; in this way, the system can understand the user's learning status and progress in real time.

[0036] The system will divide the user's previous problem-solving content into multiple sub-problem-solving contents; these sub-problem-solving contents represent different stages or links in the user's learning process, and each sub-problem-solving content contains specific knowledge points or skills; the purpose of division is to better understand the user's problem-solving process and provide a basis for subsequent determination of the problem-solving path; at this time, the system will use clustering algorithms or classification algorithms to divide the user's previous problem-solving content; for example, the system will classify all the exercises the user has done according to knowledge points, and divide the questions involving the same knowledge points into the same sub-problem-solving content; or, the system will also divide the sub-problem-solving content according to the user's problem-solving steps and strategies, and divide the questions with similar problem-solving steps and strategies into the same sub-problem-solving content.

[0037] After determining multiple sub-problem-solving contents, the system will determine a corresponding problem-solving path based on the detailed content of these sub-problem-solving contents and the logical relationship between them; this problem-solving path describes the entire process from the starting point to the end point (that is, solving the problem), and it contains information about what order the user needs to follow and which knowledge points or skills to use to solve the problem; at this time, the system will use graph theory algorithms or path planning algorithms to determine the problem-solving path; for example, the system regards each sub-problem-solving content as a node in the graph, and the logical relationship between the nodes as the edges in the graph, and then uses the graph theory algorithm to find the shortest path or optimal path from the starting node to the end node; this path is the problem-solving path determined by the system for the user.

[0038] After determining the problem-solving path, the system will mark each problem-solving node on the path; these nodes represent key steps or decision points in the path, and they are areas where users need to pay special attention during the problem-solving process; the purpose of marking the problem-solving nodes is to allow users to understand the problem-solving process more clearly and to accurately locate each step when solving the problem; at this time, the system will display the problem-solving path in a graphical manner on the user interface, and mark each problem-solving node on the path with different colors or icons; in this way, when users view the problem-solving path, they can see at a glance which steps are key steps, so that they can focus more on learning and practicing these steps.

[0039] Furthermore, based on the identification of the problem-solving path, the logic of the problem-solving idea is determined, and according to the matching of the logic of the problem-solving idea and the knowledge application space, the corresponding logic space of the idea is determined, and based on the traversal of the logic space of the idea, the content of the standard answer is determined, which is compatible with the overall consideration of the matching of the logic of the problem-solving idea and the knowledge application space, to ensure the accuracy of the corresponding logic space of the idea.

[0040] At this time, the system will first identify the logical thinking that the user needs to follow when solving the problem based on the previously determined problem-solving path; this logical thinking describes the entire process from understanding the problem, analyzing the problem to solving the problem, and it guides the user on how to find the answer to the problem step by step; the determination of the logical thinking is based on the order of each node in the problem-solving path and the logical relationship between them; at this time, the system will extract the steps and strategies that the user needs to follow when solving the problem by parsing the nodes and edges in the problem-solving path; for example, if the problem-solving path contains a node of "understanding definitions and properties", then the system will extract the logical thinking that the user needs to understand the relevant definitions and properties first; if the problem-solving path contains a node of "applying theorems for calculations", then the system will extract the logical thinking that the user needs to select the appropriate theorem and perform calculations.

[0041] After determining the logic of the problem-solving idea, the system will search for content that matches this logic in the knowledge application space; this matching process is based on a large amount of problem-solving strategies, answer analysis, related knowledge points and other information stored in the knowledge application space; the system will find all information related to the logic of the problem-solving idea and combine this information into a logic space; this space contains all the resources and strategies that users need to refer to when solving problems; at this time, the system will use text matching, semantic analysis and other technologies to search for content that matches the logic of the problem-solving idea in the knowledge application space; for example, if the logic of the problem-solving idea is "understanding the definition and properties of parallel lines and intersecting lines", then the system will search for text or image resources containing the definition and properties of parallel lines and intersecting lines in the knowledge application space; if the logic of the problem-solving idea is "applying geometric theorems for calculations", then the system will search for relevant geometric theorems and calculation formulas in the knowledge application space.

[0042] After determining the logical space of thinking, the system will traverse all resources and strategies in this space, and gradually deduce the standard answer content according to the logic of problem-solving thinking; this deduction process is based on the knowledge points, problem-solving strategies and answer analysis in the logical space of thinking; the system will gradually apply relevant knowledge points and problem-solving strategies in the order of the logic of problem-solving thinking, and finally get the answer to the problem; at this time, the system will use automated reasoning, machine learning and other technologies to traverse the logical space of thinking and deduce the standard answer; for example, if the logic of thinking is "first understand the definition and properties of parallel lines and intersecting lines, then identify the key information in the question and determine the solution, and finally apply geometric theorems to calculate and get the answer", then the system will first extract the definition and properties of parallel lines and intersecting lines, and then identify the key information in the question (such as angles, line segment lengths, etc.), and then select appropriate geometric theorems (such as the congruent angle theorem, the interior alternate angle theorem, etc.), and finally calculate and get the answer.

[0043] Therefore, the abnormal content area is determined based on the matching of the standard answer content and the user's previous problem-solving content, the erroneous content of each problem-solving node in the problem-solving path is determined based on the identification of the abnormal content area, and the knowledge nodes associated with the erroneous content are determined based on the tracing of the erroneous content. This is compatible with the overall consideration of the matching of the standard answer content and the user's previous problem-solving content, ensuring the accuracy of the abnormal content area. At the same time, the basic knowledge space and the knowledge application space are introduced to ensure the accuracy of the erroneous content of each problem-solving node in the problem-solving path, improve the accuracy of the knowledge nodes, and ensure the full utilization of the basic knowledge space and the knowledge application space.

[0044] At this time, the system will compare and match the standard answer content with the user's previous problem-solving content; this process aims to find out the parts of the user's problem-solving process that are inconsistent with or deviate from the standard answer, that is, abnormal content areas; these areas represent the user's errors or deficiencies in understanding the problem, applying knowledge points or problem-solving strategies; at this time, the system will use text comparison, semantic analysis and other technologies to compare the standard answer content with the user's previous problem-solving content; by comparing sentence by sentence or paragraph by paragraph, the system can identify the parts of the user's problem-solving process that are inconsistent with the standard answer and mark them as abnormal content areas; these areas include incorrect problem-solving steps, omitted key information, misunderstood question requirements, etc.

[0045] After determining the abnormal content area, the system will map these abnormal content areas to specific problem-solving nodes based on the order and logical relationship of each problem-solving node in the problem-solving path; this process aims to find out at which node in the problem-solving path the user made an error, so as to locate the problem more accurately; at this time, the system will use node mapping, error location and other technologies to determine the erroneous content of each problem-solving node in the problem-solving path; by comparing and mapping the abnormal content area with the nodes in the problem-solving path, the system can identify which node has an error and mark it as an error node; these error nodes represent the user's errors in understanding the question, applying theorem, performing calculations and other steps.

[0046] After determining the error nodes, the system will further trace the knowledge points or skills associated with these erroneous contents; this process aims to find out the specific knowledge points or skill deficiencies that cause users to make mistakes in solving problems, so as to provide targeted guidance for subsequent learning and improvement; at this time, the system will use knowledge graphs, skill trees and other technologies to trace the knowledge nodes associated with the erroneous content; by analyzing the knowledge points or skills involved in the error nodes, the system can find other related knowledge points or skills in the knowledge graph or skill tree, and mark them as related knowledge nodes; these related knowledge nodes represent the content that users need to strengthen their learning in terms of understanding questions, applying theorems, performing calculations, etc.

[0047] In some embodiments of the present application, the weights are set as follows: understanding the question requirements: 0.2 (relatively simple, low weight); identifying key information: 0.2 (also relatively simple); applying the theorem for calculation: 0.4 (key step, high weight); obtaining the result: 0.2 (depends on the previous steps, but relatively simple in itself); at this time, the user correctly completes the first two steps and scores 0.21 + 0.21 = 0.4; the user chooses the wrong theorem in the third step and scores 0.4 * 0 = 0 (because this step is wrong); although the result of the fourth step is wrong due to the error in the previous step, the system gives a certain "attempt score", for example, 0.2 * 0.5 = 0.1 (assuming the user at least tried to obtain the result); total score: 0.4 + 0 + 0.1 = 0.5.

[0048] Optional, user problem-solving evaluation report: Problem-solving path: understand the question requirements > identify key information > apply theorem to calculate > obtain the result; Score: understand the question requirements: correct, score 0.2; identify key information: correct, score 0.2; apply theorem to calculate: wrong, selected Theorem B (should be Theorem A), score 0; obtain the result: try to obtain the result, but due to the error in the previous step, score 0.1; Total score: 0.5; Error location and suggestions: at the "apply theorem to calculate" node, the user selected the wrong Theorem B; it is recommended to strengthen the study of the relevant knowledge points of "properties of parallel lines" and the correct application of Theorem A; through such output examples, the system clearly shows the user's problem-solving situation, error location and improvement suggestions.

[0049] refer to Figure 5 In step S14, in the problem-solving learning space, the corresponding correct content is determined based on the incorrect content and the knowledge content presented by the knowledge node, and the difference between the correct content and the incorrect content is determined. The correct answer idea is determined based on the difference and the user's answer idea relative to the incorrect content, and the user's knowledge difficulties are marked; In the specific implementation process of the present invention, the specific steps are: S141: Traverse the learning database and collect the problem-solving learning space, monitor the problem-solving learning space in real time, mark the knowledge node associated with the erroneous content, and determine the corresponding problem-solving space based on the tracing of the knowledge node; S142: inputting the incorrect content into the problem-solving space and performing autonomous correction in the problem-solving space to output corresponding correct content; determining the difference between the correct content and the incorrect content based on a comparison between the correct content and the incorrect content; S143: Determine the user's answer ideas relative to the incorrect content based on the tracing back of the incorrect content, determine the correct answer ideas based on the user's answer ideas relative to the incorrect content and the difference content, and mark the user's knowledge difficulties based on the reverse tracing back of the correct answer ideas.

[0050] In an embodiment of the present application, the learning database is traversed, and the problem-solving learning space is collected and monitored in real time. At the same time, the knowledge nodes associated with the erroneous content are marked, and the corresponding problem-solving space is determined based on the tracing of the knowledge nodes, which is compatible with the overall consideration of the tracing of the knowledge nodes and ensures the accuracy of the corresponding problem-solving space.

[0051] At this time, the system will first traverse its built-in learning database; this database is a huge knowledge base that contains a large number of questions, problem-solving steps, knowledge point explanations and answers in various subjects; the system obtains all available learning resources and information by traversing this database; at this time, the system will use indexing technology to speed up the traversal process to ensure that relevant questions and knowledge points can be found quickly; at the same time, the system will also filter and sort the content in the database according to the user's learning progress and interests, so as to provide users with more personalized learning resources.

[0052] Based on traversing the learning database, the system will collect and construct a problem-solving learning space; this space is a dynamic environment that includes the questions the user is currently learning, the relevant problem-solving steps, the knowledge points involved, and the user's problem-solving attempts and feedback; at the same time, the system will select suitable questions and knowledge points from the database according to the user's learning path and question difficulty, and construct a personalized problem-solving learning space; at the same time, the system will also monitor the user's learning behavior in this space in real time, such as problem-solving time, accuracy, etc., in order to provide a basis for subsequent learning analysis and optimization.

[0053] The system will monitor the problem-solving learning space in real time; this monitoring process aims to promptly detect errors or deficiencies that occur in the user's problem-solving process, so as to provide data support for subsequent error analysis and knowledge node marking; at the same time, the system will use machine learning technology to analyze the user's problem-solving behavior and answer quality; by comparing the user's problem-solving attempts with the standard answers, the system identifies the user's errors and deficiencies; at the same time, the system will also record detailed information on these errors and deficiencies, such as error type, error location, etc., for subsequent more in-depth analysis and processing.

[0054] After identifying the user's errors and shortcomings, the system will trace back and mark the knowledge nodes associated with the erroneous content; these nodes represent knowledge points that the user does not understand clearly or has not mastered firmly, and are also the focus of subsequent learning; at the same time, the system will find the corresponding nodes in the knowledge graph or knowledge tree based on the knowledge points involved in the erroneous content, and mark them as error-related nodes; these nodes will be associated with multiple questions and problem-solving steps, so the system needs to ensure the accuracy and completeness of the marking.

[0055] After marking the error-related nodes, the system will trace back and determine a corresponding problem-solving space based on these nodes; this space contains all questions, problem-solving steps and knowledge points related to the erroneous content, aiming to provide users with a more focused and targeted learning environment; at this time, the system will filter out questions and knowledge points related to these nodes from the database based on the information of the error-related nodes, and construct a new problem-solving space; this space will be more compact and concentrated than the previous problem-solving learning space, so that users can learn and correct errors more efficiently.

[0056] Furthermore, the erroneous content is input into the problem-solving space and autonomously corrected in the problem-solving space to output the corresponding correct content; the difference between the correct content and the erroneous content is determined based on the comparison between the correct content and the erroneous content, which is compatible with the overall consideration of the comparison between the correct content and the erroneous content and ensures the accuracy of the difference between the correct content and the erroneous content.

[0057] At this time, the system will input the incorrect content generated by the user during the learning process into the previously determined problem-solving space; this problem-solving space is constructed based on the user's incorrect content and related knowledge nodes, aiming to provide users with a targeted learning environment; at this time, the system will input the user's incorrect answers, incorrect problem-solving steps or misunderstood knowledge points and other information in digital form into the problem-solving space; this space is a virtual learning environment that contains all questions, problem-solving steps and knowledge points related to the incorrect content.

[0058] In the problem-solving space, the system will attempt to autonomously correct the user's incorrect content; this process involves a variety of technical means, such as machine learning algorithms, knowledge graph reasoning, etc., aiming to generate a correct problem-solving process or answer based on the correct problem-solving steps and knowledge points; at this time, the system will use the built-in problem-solving engine or machine learning model to parse and process the user's incorrect content; by comparing the user's incorrect answer with the correct problem-solving steps, the system identifies the error and generates a correct problem-solving process or answer; this process is automated and also requires the assistance of the system or the participation of the user.

[0059] After the self-correction is completed, the system will output the corresponding correct content; this correct content is the correct answer, the correct problem-solving steps or the relevant knowledge point explanation, etc.; at this time, the system will present the generated correct content to the user in a digital form, in the form of text, images, animation or video, etc.; these correct contents are designed to help users understand the errors and learn the correct problem-solving methods and knowledge points.

[0060] After outputting the correct content, the system will compare the correct content with the user's incorrect content to determine the differences between them; these differences include incorrect problem-solving steps, omitted key information, misunderstood knowledge points, etc.; at the same time, the system will use text comparison, semantic analysis and other technical means to compare and analyze the correct content and incorrect content sentence by sentence or paragraph by paragraph; through this process, the system identifies the user's shortcomings in the learning process and generates a difference report.

[0061] Therefore, based on the tracing back of the incorrect content, the user's answer ideas relative to the incorrect content are determined, based on the user's answer ideas relative to the incorrect content and the different content, the correct answer ideas are determined, and based on the reverse tracing back of the correct answer ideas, the user's knowledge difficulties are marked, which is compatible with the overall consideration of the user's answer ideas relative to the incorrect content and the different content, and ensures the accuracy of the correct answer ideas.

[0062] At this point, the system analyzes the user's errors and attempts to trace and understand the user's thoughts and ideas during the problem-solving process. This usually involves analyzing the user's incorrect answers and the problem-solving logic or ideas hidden behind the incorrect answers. At this point, the system uses natural language processing (NLP) technology to analyze the user's incorrect answers and extract key information and problem-solving steps. Then, based on this information and steps, the system attempts to reconstruct the user's answer ideas and identify errors or deficiencies.

[0063] After determining the user's answer ideas, the system will compare them with the correct problem-solving process to find out the differences between the two; these differences include incorrect problem-solving steps, missing key information, incorrect assumptions or reasoning, etc.; then, the system will determine a correct answer idea based on these differences; at this time, the system will build a difference analysis model to compare the user's answer ideas and the correct problem-solving process; this model will identify the differences between the two and generate a difference report; then, the system will determine a correct answer idea based on this report and provide the user with corresponding explanations and instructions.

[0064] After determining the correct answer idea, the system will trace back this idea to find out the key knowledge points and concepts involved; then, the system will mark the user's knowledge difficulties based on the user's mastery of these knowledge points and concepts; these difficulties are knowledge points that the user does not understand clearly, does not have a solid grasp of, or is completely unknown to the user; at this time, the system will use data structures such as knowledge graphs or knowledge trees to represent and store the relationship between knowledge points; then, the system will follow the correct answer idea and traverse these data structures in reverse to find out the key knowledge points and concepts involved; then, the system will mark the user's knowledge difficulties based on the user's performance on these knowledge points (such as error rate, answering time, etc.), and provide the user with corresponding learning suggestions and resources.

[0065] refer to Figure 6 In step S15, the user's mastery level of knowledge difficulties is collected, and the user's error factors are determined based on the user's knowledge difficulties, the corresponding mastery level, and the user's answer accuracy. Based on the user's error factors and the user's current learning process, corresponding auxiliary learning measures are determined; In the specific implementation process of the present invention, the specific steps are: S151: Collecting the user's learning history, determining corresponding learning difficulty events based on the matching of the user's learning history and the user's knowledge difficulties, and determining the user's mastery level of the knowledge difficulties based on the learning difficulty events and the corresponding learning difficulty marks; S152: Determine a first sub-error event based on the user's knowledge difficulty and the corresponding mastery level, and determine a second sub-error event based on the user's knowledge difficulty and the user's answer accuracy; S153: Determine the user's error factor according to the first sub-error event, the second sub-error event and the error factor mapping relationship, and determine corresponding auxiliary learning measures according to the user's error factor, the user's current learning history and the auxiliary learning mapping relationship.

[0066] In an embodiment of the present application, the user's learning history is collected, and the corresponding learning difficulty events are determined based on the matching of the user's learning history and the user's knowledge difficulties, and the user's mastery level of the knowledge difficulties is determined based on the learning difficulty events and the corresponding learning difficulty marks. This is compatible with the overall consideration of the learning difficulty events and the corresponding learning difficulty marks, and ensures the accuracy of the user's mastery level of the knowledge difficulties.

[0067] At this time, the system needs to comprehensively collect the user's learning process data; this data includes but is not limited to the exercises completed by the user, test scores, learning time records, access to learning resources (such as video tutorials, document materials, etc.), the user's interactive behaviors during the learning process (such as asking questions, discussing, likes, etc.) and any information that can reflect the user's learning progress and status; at this time, the system will obtain this data through the user's learning management system (LMS), online course platform, learning application and other channels; this data usually exists in the form of logs, database records or API interfaces, and the system needs to design corresponding data capture, cleaning and integration processes to ensure the accuracy and completeness of the data.

[0068] After collecting the user's learning history data, the system needs to match this data with the user's knowledge difficulties; knowledge difficulties are usually the user's confusion or deficiencies in specific knowledge points or skills that the system has previously identified through the user's learning performance, error analysis, knowledge graphs, etc.; at this time, the system will use natural language processing (NLP) technology to parse the user's learning history data and extract key information and knowledge points; then, the system will compare this information with the knowledge difficulty database to find matching learning difficulty events; these events include users' frequent errors in specific knowledge points, skills that have been unable to be mastered for a long time, misunderstandings of specific concepts, etc.

[0069] By matching the user's learning history and knowledge difficulties, the system determines a series of corresponding learning difficulty events; these events are specific problems or challenges encountered by users in the learning process, and they involve different knowledge points, skills or learning stages; at the same time, the system will assign a unique identifier to each learning difficulty event and record its related detailed information, such as the time of occurrence, the knowledge points involved, the user's error type, error frequency, etc.; this information will help the system to conduct in-depth analysis and processing of learning difficulty events in the future.

[0070] After determining the learning difficulty events, the system needs to determine the user's mastery level of the knowledge points based on these events and the corresponding learning difficulty marks; the learning difficulty marks are pre-set by the system and are used to indicate the difficulty levels of different knowledge points or skills; the mastery level is a quantitative indicator used to reflect the user's proficiency or depth of understanding on specific knowledge points; at the same time, information such as the type, frequency, and difficulty of the knowledge points involved of the learning difficulty events are used as input to output a level indicating the user's mastery of the knowledge points; this level is a numerical value (such as 1-5), percentage, or text description (such as elementary, intermediate, advanced, etc.).

[0071] Specifically, suppose the user encounters difficulties when learning the knowledge point of "linear function graph transformation"; the system collects the user's practice records in the learning management system and finds that the user has made multiple mistakes in the practice question of "linear function graph translation"; the system also records that the user has watched the relevant video tutorial, but raised questions about the translation direction in the comment area; the system compares the user's practice records and questions with the knowledge difficulty database and finds that the user has a misunderstanding of the "linear function graph translation direction". The system identifies a learning difficulty event: "The user cannot correctly understand the translation direction of the linear function graph."

[0072] Based on this learning difficulty event and the difficulty mark of the knowledge point "Linear Function Graph Transformation" (assuming it is of medium difficulty), as well as the user's error frequency and questioning on this knowledge point, the system determines that the user's mastery level of "Linear Function Graph Translation Direction" is "lower elementary"; through this process, the system not only identifies the specific difficulties encountered by the user in learning "Linear Function Graph Transformation", but also quantifies the user's mastery of this knowledge point, providing a basis for providing personalized learning suggestions and auxiliary measures in the future.

[0073] Furthermore, the first sub-error event is determined based on the user's knowledge difficulties and the corresponding mastery level, and the second sub-error event is determined based on the user's knowledge difficulties and the user's answer accuracy. This takes into account the overall consideration of the user's knowledge difficulties and the user's answer accuracy, ensuring the accuracy of the second sub-error event.

[0074] At this point, the system further refines the user's error situation by combining the user's knowledge difficulties and corresponding mastery levels. Knowledge difficulties are the confusion or deficiencies that the system has previously identified in users regarding specific knowledge points or skills, while mastery levels reflect the user's proficiency or depth of understanding of these knowledge points. The system determines the first sub-error event by analyzing the user's knowledge difficulties and mastery levels. These events typically describe the user's error pattern or type on a certain knowledge point in a more specific way, such as "concept confusion," "calculation error," "weak memory," etc. At this point, the system first reviews the user's list of knowledge difficulties, which are obtained through previous error analysis, user feedback, or knowledge graph analysis. Next, the system checks the user's mastery level for each knowledge difficulty, which is a numerical value (such as 1-5 levels), percentage, or text description (such as elementary, intermediate, advanced, etc.). Based on the difficulty and mastery level, the system determines the first sub-error event. For example, if the user has difficulties in understanding a concept and has a low mastery level, the first sub-error event is "concept confusion."

[0075] In this step, the system not only considers the user's knowledge difficulties, but also combines the user's answer accuracy to determine the second sub-error event; the answer accuracy is the proportion of correct answers of the user on specific knowledge points or exercises, which reflects the user's stable performance or fluctuations; by analyzing the user's answer accuracy and knowledge difficulties, the system identifies the user's persistent problems or accidental errors; this information helps the system understand the user's errors more accurately and provide a basis for subsequent learning suggestions and tutoring measures; at this time, the system collects the user's answer records on specific knowledge points, including correct and incorrect answers; calculates the user's answer accuracy, that is, the proportion of correct answers; combining the user's knowledge difficulties and answer accuracy, the system determines the second sub-error event; for example, if the user's answer accuracy on a knowledge point is low, and the knowledge point is a previously identified difficulty, then the second sub-error event is "persistent problem" or "unskilled".

[0076] Specifically, assume that the user encounters difficulties when learning "quadratic function graphs and properties"; at the same time, the first sub-error event is determined based on the user's knowledge difficulties and the corresponding mastery level: the system recognizes that one of the user's knowledge difficulties is "the opening direction of the quadratic function graph"; through previous tests and analysis, the system determines that the user's mastery level of this knowledge point is "elementary", indicating that the user's understanding of the opening direction is not deep enough; therefore, the system determines that the first sub-error event is "concept confusion", that is, the user has a misunderstanding of the concept of the opening direction of the quadratic function graph.

[0077] The second sub-error event is determined based on the user's knowledge difficulties and the user's answer accuracy: the system collects the user's answer records on exercises related to "quadratic function graphs and properties"; calculations show that the user's answer accuracy on questions involving "quadratic function graph opening direction" is 60%, indicating that the user is unstable on this knowledge point.

[0078] Combined with the user's difficulties with this knowledge point and the low accuracy of their answers, the system determined that the second sub-error event was a "persistent problem", that is, the user continued to make mistakes on this knowledge point and needed to further strengthen his learning; through this process, the system not only identified the user's specific error situation on the knowledge point of "quadratic function graph and properties", but also refined the error type, providing a basis for providing targeted learning suggestions and tutoring measures in the future.

[0079] Therefore, the user's error factors are determined based on the first sub-error event, the second sub-error event and the error factor mapping, and the corresponding auxiliary learning measures are determined based on the user's error factors, the user's current learning history and the auxiliary learning mapping relationship. This is compatible with the overall consideration of the user's error factors, the user's current learning history and the auxiliary learning mapping relationship, ensuring the accuracy of the corresponding auxiliary learning measures. At the same time, the problem-solving learning space is further introduced, which is compatible with the overall consideration of the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, ensuring the accuracy of the user's error factors and improving the accuracy of the auxiliary learning measures.

[0080] At this time, the system integrates the information of the first sub-error event (such as "concept confusion", "calculation error", etc.) and the second sub-error event (such as "persistent problem", "accidental error", etc.), and refers to the error factor mapping relationship to determine the user's error factor; the error factor mapping relationship is a pre-established model or table, which links different types of sub-error events with specific error factors (such as "lack of understanding", "weak memory", "distraction", etc.); at this time, the system first reviews the specific content of the first sub-error event and the second sub-error event; then, the system checks the error factor mapping relationship to find the error factors corresponding to these sub-error events; if there are multiple error factors, the system will conduct further analysis and judgment based on the user's answer history, learning behavior or other relevant information to determine the error factors.

[0081] After determining the user's error factors, the system will determine the corresponding auxiliary learning measures based on this information, the user's current learning history (such as completed learning tasks, remaining learning time, etc.) and the auxiliary learning mapping relationship; the auxiliary learning mapping relationship is a pre-established model or table, which recommends specific learning resources, practice questions, tutoring strategies, etc. based on the user's error factors and learning history; at this time, the system first determines the user's error factors, such as "lack of understanding" or "weak memory"; then, the system checks the user's current learning history to understand the user's completed learning tasks, mastered knowledge points and remaining learning content; then, based on the error factors and current learning history, the system searches for recommended auxiliary learning measures in the auxiliary learning mapping relationship; these measures include watching specific teaching videos, completing additional exercises, participating in online tutoring courses, etc.; finally, the system personalizes and optimizes the recommended auxiliary learning measures according to the user's actual situation and learning preferences.

[0082] Specifically, suppose the user encounters difficulties when learning "the application of trigonometric functions"; the system identifies the user's first sub-error event as "concept confusion", that is, the user has misunderstandings about some basic concepts of trigonometric functions (such as sine, cosine, tangent, etc.); the second sub-error event is "persistent problem", indicating that the user continues to make mistakes on this knowledge point, and the error rate is high; the system checks the error factor mapping relationship and determines that the user's error factor is "lack of understanding", that is, the user lacks an in-depth understanding of the basic concepts and application scenarios of trigonometric functions.

[0083] The system checks the user's current learning history and finds that the user has completed the introduction to the basic concepts of trigonometric functions and some basic exercises, but the level of mastery is not solid enough; based on the error factor "lack of understanding" and the current learning history, the system searches for recommended auxiliary learning measures in the auxiliary learning mapping relationship; the system recommends that users watch detailed explanation videos on the concepts of trigonometric functions, which demonstrate the basic concepts and application scenarios of trigonometric functions through vivid examples and graphics; in addition, the system also recommends that users complete a series of exercises on the application of trigonometric functions to deepen their understanding and memory of knowledge points; finally, the system recommends that users participate in online tutoring courses to communicate and discuss with teachers and classmates to further consolidate what they have learned; through this process, the system not only determines the user's error factors, but also provides users with personalized auxiliary learning measures to help users overcome learning difficulties and improve learning effects.

[0084] In some embodiments of the present application, an example error factor mapping table is collected, and the example error factor mapping table is shown in Table 5: Table 5 Example error factor mapping table The auxiliary learning mapping relationship table is collected, and the auxiliary learning mapping relationship table is shown in Table 6: Table 6 Auxiliary learning mapping relationship table The user's error factor is "lack of understanding" and the current learning stage is "beginner stage"; searching in the auxiliary learning mapping relationship, the recommended auxiliary learning measures are "watching basic concept explanation videos and completing basic exercises."

[0085] In some embodiments of the present application, the construction of a real-time knowledge space includes the construction of a basic knowledge space, a knowledge application space, and a problem-solving learning space. The construction of the corresponding knowledge space is uploaded to the National Industrial Internet Identifier Resolution Secondary Node Platform in real time for information retrieval and application of a cross-platform teaching platform. For a certain learner's problem-solving knowledge space, the learner's knowledge space can be retrieved on different learning platforms to analyze and push the knowledge resources and question bank of this platform. For schools or teachers, under the condition of authentication and authorization, the knowledge space information of relevant students can also be obtained to conduct a comprehensive analysis of the students.

[0086] Establish a public basic knowledge space: The construction of the basic knowledge space is based on relatively authoritative basic knowledge spaces generated by national textbooks and relevant official teaching courses. A unique identification code is generated for each knowledge point classified within a specific knowledge domain within a specific discipline. The relationships between knowledge points are captured, including sequential (including causal, progressive, and hierarchical relationships), parallel (in which knowledge points exist side by side, are independent of each other, and have no necessary connection), and comprehensive (in which knowledge points are interconnected and applied in a comprehensive manner). Based on sequential relationships, basic "knowledge point-relationship-knowledge point" triples are established, and a unique identification code is generated for each "entity-relationship-entity" triple. Based on comprehensive relationships, a "multi-entity-multi-relationship-multi-entity" relationship combination is established, generating a unique identification code. Teaching courseware and course content are matched to the entity identification codes corresponding to the knowledge points, as well as the sequential and comprehensive relationship combination identification codes. Knowledge points are then marked as part of the basic knowledge point library.

[0087] Establishing a knowledge application space: Obtain the question bank and corresponding problem-solving steps of the school or various teaching platforms, split the knowledge points and knowledge point reasoning relationship combinations applied in each step of the problem-solving, match the knowledge points and knowledge point reasoning relationship combinations applied in the problem-solving to generate the entity identification code corresponding to the knowledge point and the knowledge point relationship combination. If the knowledge points or knowledge point relationship combinations used in problem solving do not match the identification code, the knowledge points or knowledge point relationship combinations will be pushed to the expert review system of the secondary node for certification by the experts. If the review is passed, the experts will define the disciplines and classifications, and then generate a unique identification code for the knowledge points in this knowledge point or knowledge point relationship combination, and generate an identification code for the knowledge point relationship combination. The problem-solving steps are associated with the knowledge points and knowledge point relationship combinations. At the same time, the corresponding knowledge points and knowledge point relationship combinations are also synchronized to the public basic knowledge space and marked as extended first knowledge point library in the basic knowledge space; if the review fails, the validity of the current problem-solving steps is marked as pending.

[0088] If the knowledge points or knowledge point relationship combinations used in solving the problem match the identification code, the problem-solving steps are associated with the knowledge points and knowledge point relationship combinations. This ultimately forms a knowledge point association path for each problem. If a problem has multiple solution steps, multiple knowledge point association paths can be formed using the above method.

[0089] For each problem, the learner's incorrect answer steps are obtained, along with the knowledge point association path of the learner's answer. The knowledge point and knowledge association combination of each step in the problem and the learner's answer are compared. The number of learner answers that do not match each step, Gn, and the number of learner answers that match each step, Hn, are counted. The accuracy rate for each step, Ln = Hn / (Gn + Hn), is calculated. When Ln < a threshold, the knowledge point and knowledge association combination corresponding to this step is recorded as a difficulty. This identifies the difficulty of each knowledge point and knowledge association combination in solving each problem.

[0090] Establish a problem-solving learning space: Obtain the problem-solving steps of learners in a certain school or teaching platform, split the knowledge points and the reasoning relationship combination of each step in the problem-solving, and match the knowledge points and the reasoning relationship combination of the knowledge points used in the problem-solving to the entity identification code and knowledge point relationship combination corresponding to the knowledge points generated in (1). If the knowledge points or knowledge point relationship combinations used in problem solving cannot match the identification code, the knowledge points or knowledge point relationship combinations will be pushed to the expert review system of the secondary node for certification by the experts. If the review is passed, the experts will define the disciplines and classifications, and then generate a unique identification code for this knowledge point or the knowledge points in the knowledge point relationship combination, and generate an identification code for the knowledge point relationship combination. The problem-solving steps are associated with the knowledge points and knowledge point relationship combinations. At the same time, the corresponding knowledge points and knowledge point relationship combinations are also synchronized to the public basic knowledge space and marked as extended second knowledge point libraries in the basic knowledge space. If the review fails, the learner's current problem-solving steps are marked as incorrect, and the learner is marked as not having mastered the prerequisite knowledge point corresponding to the current problem-solving steps. If the knowledge points or knowledge point relationship combinations used in problem solving can match the identification code, the problem-solving steps are associated with the knowledge points and knowledge point relationship combinations.

[0091] See also Figure 7 , Figure 7 : is a schematic diagram of the structure of a control system for a knowledge space for auxiliary learning in an embodiment of the present invention; the control system for the knowledge space for auxiliary learning includes: The basic knowledge space module 21 is used to collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; The knowledge application space module 22 is used to mark the user's current learning node in the basic knowledge space and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; The knowledge node module 23 is used to determine the corresponding problem-solving path in the knowledge application space based on the user's previous problem-solving content, determine the incorrect content of each problem-solving node in the problem-solving path based on the matching of the problem-solving path and the knowledge application space, and mark the knowledge node associated with the incorrect content; The knowledge difficulty module 24 is used to determine the corresponding correct content based on the incorrect content and the knowledge content presented by the knowledge node in the problem-solving learning space, determine the difference between the correct content and the incorrect content, determine the correct answer based on the difference and the user's answer strategy relative to the incorrect content, and mark the user's knowledge difficulty; The auxiliary learning measures module 25 is used to collect the user's mastery level of knowledge difficulties and determine the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, and determine the corresponding auxiliary learning measures based on the user's error factors and the user's current learning history.

[0092] The technical features of the above embodiments may be combined arbitrarily. To make the description concise, not all combinations of the technical features in the above embodiments are described. However, as long as there is no contradiction in the combination of these technical features, they should be considered to be within the scope of this specification.

Claims

1. A method for controlling a knowledge space for auxiliary learning, characterized in that: include: Collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; In the basic knowledge space, mark the user's current learning node, and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; In the knowledge application space, the corresponding problem-solving path is determined based on the user's previous problem-solving content. Based on the matching between the problem-solving path and the knowledge application space, the incorrect content of each problem-solving node in the problem-solving path is determined, and the knowledge nodes associated with the incorrect content are marked. In the problem-solving learning space, the correct content is determined based on the incorrect content and the knowledge content presented by the knowledge node, and the difference between the correct and incorrect content is determined. The correct answer is determined based on the difference and the user's answer to the incorrect content, and the user's knowledge difficulties are marked. Collect the user's mastery level of knowledge difficulties, and determine the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy. Based on the user's error factors and the user's current learning history, determine the corresponding auxiliary learning measures.

2. The method for controlling a knowledge space for auxiliary learning according to claim 1, characterized in that: The collecting of the user's personal information and determining the basic knowledge space based on the user's personal information, learning history, and learning database include: Collect the user's admission information and determine the user's personal information based on the traversal of the user's admission information. At the same time, collect the learning database and determine the user's learning nodes in different courses based on the learning database and the user's personal information; Determine the user's learning history by tracing back the user's learning nodes in different courses, determine the first space system based on the user's learning history and personal information, and determine the second space system based on the user's learning history and learning database; The basic knowledge space is determined based on the synthesis of the first space system and the second space system. At this time, the basic knowledge space covers all learning events of the user in the learning process and marks the corresponding learning tags for the learning events.

3. The method for controlling a knowledge space for auxiliary learning according to claim 1, characterized in that: The method of marking the user's current learning node in the basic knowledge space and determining the user's previous problem-solving content by combining the user's current learning node with the knowledge application space includes: If the user enters the basic knowledge space, the user's current learning node is determined based on the user's current time, the user's learning progress and the corresponding subject category, and the user's current learning content is collected in the current learning node; The corresponding target subject is determined based on the analysis of the current learning content, the target subject is input into the knowledge application space, and the user's previous problem-solving content is determined based on the matching between the target subject and the knowledge application space.

4. The method for controlling a knowledge space for auxiliary learning according to claim 1, wherein: The method of determining a corresponding problem-solving path in the knowledge application space based on the user's previous problem-solving content, determining the erroneous content of each problem-solving node in the problem-solving path based on the matching between the problem-solving path and the knowledge application space, and marking the knowledge nodes associated with the erroneous content includes: The knowledge application space is collected and monitored in real time. Multiple sub-problem-solving contents are determined based on the user's previous problem-solving content division. The corresponding problem-solving path is determined according to the detailed content and sorting of the multiple sub-problem-solving contents, and each problem-solving node of the problem-solving path is marked.

5. The method for controlling a knowledge space for auxiliary learning according to claim 4, characterized in that: The method further includes determining a corresponding problem-solving path in the knowledge application space based on the user's previous problem-solving content, determining the erroneous content of each problem-solving node in the problem-solving path based on a match between the problem-solving path and the knowledge application space, and marking the knowledge nodes associated with the erroneous content. Based on the identification of the problem-solving path, the logic of the problem-solving idea is determined, and the corresponding logic space of the idea is determined based on the matching of the logic of the problem-solving idea and the knowledge application space. The standard answer content is determined based on the traversal of the logic space of the idea; Based on the matching of the standard answer content and the user's previous problem-solving content, the abnormal content area is determined, and based on the identification of the abnormal content area, the incorrect content of each problem-solving node in the problem-solving path is determined, and based on the tracing of the incorrect content, the knowledge nodes associated with the incorrect content are determined.

6. The method for controlling a knowledge space for auxiliary learning according to claim 1, characterized in that: In the problem-solving learning space, the correct content corresponding to the incorrect content and the knowledge content presented by the knowledge node is determined, and the difference between the correct content and the incorrect content is determined. The correct answer is determined based on the difference and the user's answer to the incorrect content, and the user's knowledge difficulties are marked, including: Traverse the learning database, collect the problem-solving learning space, monitor the problem-solving learning space in real time, and mark the knowledge nodes associated with the erroneous content. Determine the corresponding problem-solving space based on the tracing of the knowledge nodes.

7. The method for controlling a knowledge space for auxiliary learning according to claim 6, characterized in that: The method further includes: determining the corresponding correct content in the problem-solving learning space based on the incorrect content and the knowledge content presented by the knowledge node, determining the difference between the correct content and the incorrect content, determining the correct answer based on the difference and the user's answer strategy relative to the incorrect content, and marking the user's knowledge difficulties; Input the erroneous content into the problem-solving space and perform self-correction in the problem-solving space to output corresponding correct content; determine the difference between the correct content and the erroneous content based on the comparison between the correct content and the erroneous content; Based on the tracing back of the incorrect content, the user's answer ideas relative to the incorrect content are determined; based on the user's answer ideas relative to the incorrect content and the different content, the correct answer ideas are determined; and based on the reverse tracing back of the correct answer ideas, the user's knowledge difficulties are marked.

8. The method for controlling a knowledge space for auxiliary learning according to claim 1, wherein: The method of collecting the user's mastery level of knowledge difficulties and determining the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, and determining corresponding auxiliary learning measures based on the user's error factors and the user's current learning history includes: The user's learning history is collected, and the corresponding learning difficulty events are determined based on the matching of the user's learning history and the user's knowledge difficulties. The user's mastery level of the knowledge difficulties is determined based on the learning difficulty events and the corresponding learning difficulty marks.

9. The method for controlling a knowledge space for auxiliary learning according to claim 8, characterized in that: The collecting of the user's mastery level of knowledge difficulties, determining the user's error factors based on the user's knowledge difficulties, the corresponding mastery level, and the user's answer accuracy, and determining corresponding auxiliary learning measures based on the user's error factors and the user's current learning history, further includes: Determine the first sub-error event based on the user's knowledge difficulty and the corresponding mastery level, and determine the second sub-error event based on the user's knowledge difficulty and the user's answer accuracy; The user's error factor is determined according to the first sub-error event, the second sub-error event and the error factor mapping relationship, and the corresponding auxiliary learning measures are determined according to the user's error factor, the user's current learning history and the auxiliary learning mapping relationship.

10. A control system for a knowledge space used to assist learning, characterized in that: The control system of the knowledge space for assisting learning is applied to the control method of the knowledge space for assisting learning as claimed in any one of claims 1 to 9, and the control system of the knowledge space for assisting learning includes: The basic knowledge space module is used to collect the user's personal information and determine the basic knowledge space based on the user's personal information, learning history and learning database; The knowledge application space module is used to mark the user's current learning node in the basic knowledge space and determine the user's previous problem-solving content based on the user's current learning node and the knowledge application space; The knowledge node module is used to determine the corresponding problem-solving path in the knowledge application space based on the user's previous problem-solving content, determine the incorrect content of each problem-solving node in the problem-solving path based on the matching of the problem-solving path and the knowledge application space, and mark the knowledge node associated with the incorrect content; The knowledge difficulty point module is used to determine the corresponding correct content based on the incorrect content and the knowledge content presented by the knowledge node in the problem-solving learning space, and determine the difference between the correct content and the incorrect content. Based on the difference and the user's answer idea relative to the incorrect content, the correct answer idea is determined, and the user's knowledge difficulty point is marked; The auxiliary learning measures module is used to collect the user's mastery level of knowledge difficulties, and determine the user's error factors based on the user's knowledge difficulties, the corresponding mastery level and the user's answer accuracy, and determine the corresponding auxiliary learning measures based on the user's error factors and the user's current learning process.

Images