Intelligent learning difficulty adjusting device and method

Abstract

The invention relates to the technical field of computers, and discloses a learning difficulty intelligent adjusting device and method, and the method comprises the steps: extracting key knowledge elements from pre-obtained user learning data, and constructing a learning graph; according to the learning map, analyzing the knowledge mastering degree and the learning ability of the user to obtain a user ability evaluation result; generating corresponding learning content in combination with the user capability evaluation result and the node association relationship in the learning map; in the learning process of the user, the updating condition of the knowledge elements and the change condition of the learning ability of the user are analyzed, and the learning graph is dynamically updated to obtain an updated learning graph; according to the updated learning map, the difficulty of the learning content is adjusted in real time, updated learning content is obtained, and intelligent adjustment of the learning difficulty is achieved; the learning content difficulty is intelligently adjusted, the requirements of different users in different learning stages are met, and the learning effect and the knowledge mastering degree are effectively improved.

Description

Technical Field

[0001] The present invention relates to the field of computer technology, and in particular to a device and method for intelligently adjusting learning difficulty. Background Art

[0002] Existing learning systems provide uniform learning content and difficulty, without considering the differences in knowledge mastery and learning abilities among different students. During the user's learning process, the learning content and difficulty cannot be adjusted in a timely manner according to the updating of knowledge elements and changes in learning abilities during the student's learning process. The connection between different subjects and different knowledge points is poor, making it difficult to build a comprehensive and accurate knowledge system. This leads to a lack of systematic and logical arrangement of learning content, making it difficult for students to form a complete knowledge network.

[0003] To solve at least one of the above problems, the present invention proposes a device and method for intelligently adjusting learning difficulty. Summary of the Invention

[0004] In view of the shortcomings of the prior art, the main purpose of the present invention is to provide a device and method for intelligently adjusting learning difficulty, which can effectively solve the problems in the background technology. The specific technical solutions of the present invention are as follows:

[0005] A method for intelligently adjusting learning difficulty, comprising:

[0006] Extract key knowledge elements from pre-acquired user learning data and construct a learning graph;

[0007] Analyze the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability assessment result;

[0008] Combining the user capability assessment results with the node association relationship in the learning graph to generate corresponding learning content, wherein the nodes include knowledge nodes and capability nodes;

[0009] During the user's learning process, the update of knowledge elements and the change of the user's learning ability are analyzed, and the learning map is dynamically updated to obtain an updated learning map;

[0010] According to the updated learning map, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to realize intelligent adjustment of learning difficulty.

[0011] Specifically, extracting key knowledge elements from pre-acquired user learning data and constructing a learning graph includes:

[0012] Based on the pre-acquired user learning data, the corresponding knowledge points are extracted to obtain the key knowledge elements;

[0013] The key knowledge elements are used as knowledge nodes, and the corresponding knowledge nodes are connected by analyzing the association relationship between the key knowledge elements to obtain an initial learning graph;

[0014] The user learning data is fused and mapped to the initial learning graph to obtain a corresponding learning graph.

[0015] Specifically, based on the learning graph, the user's knowledge mastery and learning ability are analyzed to obtain user ability assessment results, including:

[0016] Based on the correlation between knowledge nodes in the learning graph, the user's answer situation at each knowledge node is analyzed to obtain the user's knowledge mastery level;

[0017] Aggregate the knowledge nodes reflecting different subject knowledge points in the learning graph to obtain multiple types of subject nodes;

[0018] For each subject node, the user's knowledge mastery level is evaluated separately to obtain the knowledge mastery level of each subject;

[0019] According to the mastery level of each subject knowledge, add corresponding ability nodes to each subject node and connect them;

[0020] During the user's learning process, the attributes of the capability node are dynamically updated according to the changes in the user's mastery of each subject knowledge to obtain an updated capability node;

[0021] Combined with the update capability nodes corresponding to each subject, the user's learning ability is evaluated to obtain the user's ability evaluation results.

[0022] Specifically, combining the user capability assessment results and the node association relationship in the learning graph to generate corresponding learning content includes:

[0023] According to the user's ability assessment results, the target template library of corresponding difficulty is matched in the preset question template library;

[0024] By analyzing the node association relationship in the learning graph, corresponding weights are assigned to each node;

[0025] In combination with the target template library and weights, corresponding learning content is generated through a preset content generation model.

[0026] Specifically, during the user's learning process, the update of knowledge elements and changes in the user's learning ability are analyzed, and the learning graph is dynamically updated to obtain an updated learning graph, including:

[0027] During the user's learning process, the update of knowledge elements and changes in user learning ability are analyzed to obtain updated learning status;

[0028] According to the updated learning state, updating the nodes and node connection relationships in the learning graph to obtain a first updated learning graph;

[0029] By analyzing the learning ability levels of different users, the structure of the first updated learning graph is updated to obtain an updated learning graph.

[0030] Specifically, according to the updated learning state, updating the nodes and node connection relationships in the learning graph to obtain a first updated learning graph includes:

[0031] According to the updated learning status, when a new knowledge point is added, the corresponding knowledge node is added to the learning map, and the connection relationship between the subject to which the new knowledge point belongs and the existing knowledge nodes is established to obtain the first updated node;

[0032] When the user's knowledge mastery level improves, the corresponding knowledge node attributes and connection relationships are updated to obtain a second updated node;

[0033] According to the second update node, the corresponding capability node attributes and connection relationships are updated to obtain a third update node;

[0034] In combination with the first update node, the second update node and the third update node, the nodes and node connection relationships in the learning graph are updated to obtain a first updated learning graph.

[0035] Specifically, the structure of the first updated learning graph is updated by analyzing the learning ability levels of different users to obtain an updated learning graph, including:

[0036] According to the user's learning ability, the user is graded by a preset learning ability evaluation model to obtain multiple levels of users, wherein the multiple levels of users include primary users, intermediate users and advanced users;

[0037] For the primary user, the structure of the first update learning graph is simplified to obtain the update learning graph of the primary user;

[0038] For intermediate users, an updated learning graph for intermediate users is obtained by improving the node association relationship between knowledge nodes in the first updated learning graph;

[0039] For advanced users, knowledge nodes are expanded in the first updated learning graph to obtain an updated learning graph for advanced users.

[0040] Specifically, according to the updated learning graph, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to achieve intelligent adjustment of learning difficulty, including:

[0041] According to the updated learning graph, the user's knowledge mastery of each knowledge node is analyzed to obtain the updated knowledge mastery level;

[0042] Based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path;

[0043] Matching the update node path in a preset question template library to obtain an update template;

[0044] Based on the update template, corresponding updated learning content is generated through a preset content update model to achieve intelligent adjustment of learning difficulty.

[0045] Specifically, based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path, including:

[0046] Based on the updated knowledge mastery level, extracting nodes corresponding to knowledge mastery level changes greater than a preset threshold value from the updated learning graph to obtain a plurality of knowledge nodes to be updated;

[0047] By analyzing the association relationship between the knowledge nodes, the multiple knowledge nodes to be updated are connected to obtain an update node path.

[0048] A device for intelligently adjusting learning difficulty, for implementing the aforementioned method for intelligently adjusting learning difficulty, comprising:

[0049] The learning graph construction module extracts key knowledge elements from pre-acquired user learning data and constructs a learning graph;

[0050] A user evaluation module analyzes the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability evaluation result;

[0051] A learning content generation module generates corresponding learning content based on the user capability assessment results and the node association relationship in the learning graph, wherein the nodes include knowledge nodes and capability nodes;

[0052] A learning graph update module analyzes the update of knowledge elements and changes in user learning ability during the user's learning process, and dynamically updates the learning graph to obtain an updated learning graph;

[0053] The learning difficulty adjustment module adjusts the difficulty of the learning content in real time according to the updated learning map to obtain updated learning content, so as to realize intelligent adjustment of learning difficulty.

[0054] Compared with the prior art, this application has the following beneficial effects:

[0055] This application extracts key knowledge elements from user learning data and constructs a learning map. Based on the learning map, it dynamically analyzes and evaluates the user's knowledge mastery and learning ability, and updates the ability evaluation results in real time. In combination with changes in the user's learning ability, the learning map is dynamically updated, and the difficulty of the learning content is adjusted in real time based on the updated learning map, realizing intelligent adjustment of learning difficulty, meeting the needs of different users at different learning stages, and improving the user's knowledge mastery and learning ability. BRIEF DESCRIPTION OF THE DRAWINGS

[0056] Figure 1 This is a workflow diagram of a method for intelligently adjusting learning difficulty in Example 1 of the present invention;

[0057] Figure 2 This is a schematic diagram of updating a learning graph node in Example 1 of the present invention;

[0058] Figure 3 A schematic diagram of updating a learning graph for a primary user in Example 1 of the present invention;

[0059] Figure 4 A schematic diagram of updating the learning graph for an intermediate user in Example 1 of the present invention;

[0060] Figure 5 A schematic diagram of updating a learning graph for an advanced user in Example 1 of the present invention;

[0061] Figure 6 This is a structural diagram of an intelligent adjustment device for learning difficulty in Example 2 of the present invention. DETAILED DESCRIPTION

[0062] In order to make the above-mentioned objects, features and advantages of the present invention more obvious and easy to understand, the specific embodiments of the present invention are described in detail below with reference to the accompanying drawings.

[0063] In the following description, many specific details are set forth to facilitate a full understanding of the present invention. However, the present invention may also be implemented in other ways different from those described herein. Those skilled in the art may make similar generalizations without violating the connotation of the present invention. Therefore, the present invention is not limited to the specific embodiments disclosed below.

[0064] Secondly, the term "one embodiment" or "embodiment" herein refers to a specific feature, structure, or characteristic that may be included in at least one implementation of the present invention. The phrase "in one embodiment" appearing in various places throughout this specification does not necessarily refer to the same embodiment, nor does it refer to a separate or selective embodiment that is mutually exclusive of other embodiments.

[0065] Example 1

[0066] This embodiment provides a method for intelligently adjusting learning difficulty. Figure 1 As shown, the method for intelligently adjusting learning difficulty includes:

[0067] S101. Extract key knowledge elements from pre-acquired user learning data and construct a learning graph;

[0068] S102: Analyze the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability assessment result;

[0069] S103: Generate corresponding learning content based on the user capability assessment result and the node association relationship in the learning graph, wherein the nodes include knowledge nodes and capability nodes;

[0070] S104: During the user's learning process, the update of knowledge elements and changes in the user's learning ability are analyzed, and the learning graph is dynamically updated to obtain an updated learning graph;

[0071] S105. According to the updated learning graph, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to achieve intelligent adjustment of learning difficulty.

[0072] This embodiment constructs a learning map based on user learning data, and during the user's learning process, conducts real-time evaluation of the user's knowledge mastery and learning ability, and adjusts the difficulty of the learning content in real time, so that the learning content always matches the user's ability, avoiding learning difficulties or low learning efficiency due to inappropriate difficulty, and improving learning effects; it solves the problem in traditional learning systems that the single learning content makes it impossible for users to adapt to the learning difficulty, resulting in poor learning effects.

[0073] In this embodiment, first, during the user's learning process, the user's learning data is collected, including online course viewing records, homework completion status, test scores, etc., and the collected data is cleaned to remove redundant or erroneous data; secondly, key knowledge elements are extracted from the preprocessed data. The key knowledge elements can reflect the core knowledge points in the learning process. Based on the key knowledge elements, the logical relationship between the knowledge elements is analyzed to construct a corresponding learning map; by constructing a learning map, it is helpful for users to establish a systematic knowledge system, and according to the connection between the knowledge points, the user's mastery of knowledge is analyzed, so that the learning content can be dynamically adjusted.

[0074] Specifically, according to the learning map, the user's learning data at each knowledge node is analyzed, the user's mastery of each knowledge point is calculated, and the user's learning ability is analyzed based on the user's mastery of each knowledge point to obtain the user's ability assessment result; by obtaining accurate user ability assessment results, the user's learning status can be accurately understood, providing a basis for the generation of learning content; according to the user ability assessment results, the appropriate learning content difficulty level is determined for the user, for example, novice users are suitable for content of basic difficulty, intermediate users can choose content of medium difficulty, and advanced users can challenge content of high difficulty; according to the corresponding learning content difficulty level, corresponding learning content suitable for the user's current learning ability is generated; by generating learning content of corresponding difficulty levels for users with different learning abilities, the learning needs of different users can be met, and the pertinence and effectiveness of learning can be improved.

[0075] During the user's learning process, the user's learning ability and knowledge point mastery are updated in real time. According to the changes in the user's learning ability, the learning of new knowledge and the mastery of old knowledge, the node attributes and connection relationships of the learning map are dynamically updated, so that the learning map can always reflect the user's real-time learning status, timely adapt to the update of knowledge and the development of the user's learning ability, and ensure the continuous effectiveness of learning; according to the updated learning map, the difficulty of the learning content is adjusted in real time to ensure that the learning content always matches the user's ability. When the user's ability improves, the difficulty of the learning content is increased; when the user encounters difficulties on certain knowledge nodes, the difficulty of the relevant content is reduced; the corresponding learning content is updated to obtain updated learning content, and at the same time, the order of the learning content is rearranged to adapt to changes in difficulty; by updating the difficulty of the learning content in real time, it can be ensured that the difficulty of the learning content always matches the user's ability, improve the efficiency and effectiveness of learning, avoid users losing interest in learning due to the learning content being too difficult or too easy, and enhance the motivation and enthusiasm for learning.

[0076] This application extracts key knowledge elements from user learning data and constructs a learning map. Based on the learning map, it dynamically analyzes and evaluates the user's knowledge mastery and learning ability, and updates the ability evaluation results in real time. In combination with changes in the user's learning ability, the learning map is dynamically updated, and the difficulty of the learning content is adjusted in real time based on the updated learning map, realizing intelligent adjustment of learning difficulty, meeting the needs of different users at different learning stages, and improving the user's knowledge mastery and learning ability.

[0077] Furthermore, extracting key knowledge elements from the pre-acquired user learning data and constructing a learning graph includes:

[0078] S201. Extract corresponding knowledge points based on pre-acquired user learning data to obtain key knowledge elements;

[0079] S202: Taking the key knowledge elements as knowledge nodes, and connecting the corresponding knowledge nodes by analyzing the association relationships between the key knowledge elements to obtain an initial learning graph;

[0080] S203: Fusing the user learning data and mapping it to the initial learning graph to obtain a corresponding learning graph.

[0081] In this embodiment, based on the collected user learning data, after data cleaning, the text learning data is analyzed through natural language processing technology to identify the knowledge points therein; for structured data, relevant knowledge points are extracted according to the fields and meanings of the data; for example, in mathematics test score data, knowledge points such as functions, geometry, and probability are extracted according to the chapters and types to which the questions belong; multiple knowledge points are extracted as key knowledge elements. By extracting key knowledge elements, core knowledge content can be obtained from massive learning data, thereby improving the targeted learning and the quality of the learning map.

[0082] Specifically, after extracting the key knowledge elements, the correlation between the knowledge elements is analyzed, and the key knowledge elements are used as knowledge nodes. By analyzing the correlation between the knowledge elements, connections are established to construct an initial learning map; the correlation type is set according to the characteristics of the subject knowledge and the rules of learning; for example, in mathematics, there are "prerequisite relationships" (such as the need to master basic algebraic operations before learning functions), "application relationships" (such as the application of geometric knowledge in actual measurement), etc.; in Chinese learning, there are "topic associations" (such as different articles revolving around the same topic), "grammatical associations" (such as the association between words and sentence structures), etc.; by analyzing the contextual information in the learning data, the frequency and order of knowledge use, etc., the correlation between the knowledge elements is analyzed, and the key knowledge elements are used as knowledge nodes. Connections are established between nodes based on the correlation relationships to construct an initial learning map. By constructing the initial learning map, the correlation between knowledge points is quickly established, which provides a structural basis for analyzing the user's knowledge mastery and generating personalized learning paths.

[0083] Specifically, the pre-processed user learning data is matched with the knowledge nodes in the initial learning graph; for example, the user's accuracy in answering questions on a certain knowledge point, learning time and other data are associated with the corresponding knowledge nodes in the learning graph; user learning data is added as an attribute for each knowledge node, for example, a "mastery score" attribute is added to the knowledge node, and the score is calculated based on the user's answer situation on the knowledge point; based on the results of data mapping, the initial learning graph is updated to obtain a learning graph containing user learning information; by adding personalized features to the learning graph, the learning status of each user can be accurately reflected, providing a basis for generating corresponding learning content.

[0084] Furthermore, based on the learning graph, the user's knowledge mastery and learning ability are analyzed to obtain user ability assessment results, including:

[0085] S301. Analyze the user's answers to questions at each knowledge node based on the association between knowledge nodes in the learning graph to obtain the user's knowledge mastery level.

[0086] S302, aggregating knowledge nodes reflecting knowledge points of different subjects in the learning graph to obtain multiple types of subject nodes;

[0087] S303: For each subject node, evaluate the user's knowledge mastery level to obtain the knowledge mastery level of each subject;

[0088] S304: Add corresponding capability nodes to each subject node and connect them according to the mastery level of each subject knowledge;

[0089] S305. During the user's learning process, dynamically update the attributes of the capability node according to the changes in the user's mastery of each subject knowledge to obtain an updated capability node;

[0090] S306. Evaluate the user's learning ability based on the updated ability nodes corresponding to each subject category to obtain a user ability evaluation result.

[0091] In this embodiment, the user's answer data on each knowledge node is obtained from the learning system, including the accuracy of the answers, the answering time, the error type, etc., and the importance of each knowledge node is analyzed based on the correlation between the knowledge nodes in the learning graph. For example, when a knowledge node is the prerequisite knowledge of multiple other knowledge nodes, the importance of the knowledge node is relatively high; combining the answer data and the correlation information of the knowledge nodes, the knowledge mastery score is calculated for each knowledge node, and the weighted average method is adopted. For knowledge nodes with high importance, the answer situation has a greater weight in the calculation; for example, the answer accuracy of a knowledge node is 80%, and the weight of the node is 0.6, then the knowledge mastery score of the knowledge node is 80%×0.6=0.48 points; by calculating the knowledge mastery score, the user's mastery of each knowledge node can be accurately evaluated.

[0092] Specifically, the knowledge nodes in the learning map are classified according to the subject attributes of the knowledge points. For example, mathematics, physics, chemistry and other knowledge nodes are classified separately; a subject node is created for each subject, and the knowledge nodes belonging to the subject are associated with the subject nodes; for each type of subject node, the knowledge mastery scores of all knowledge nodes under each type of subject node are summarized, and a weighted average is taken according to the importance of the knowledge nodes to calculate the knowledge mastery level of each type of subject; by analyzing the user's subject learning level, corresponding learning plans can be formulated for different subjects and corresponding learning content can be generated.

[0093] Specifically, such as Figure 2As shown in the figure, based on the calculated knowledge mastery level of each subject, the user's learning ability for each subject is evaluated. A corresponding ability node is added to each subject node, and a connection is established between the subject node and the ability node. The ability node is assigned a value based on the knowledge mastery level. During the user's learning process, the user's knowledge mastery level in each subject is continuously monitored, and new answer data and learning records are regularly collected. Based on the changes in knowledge mastery level, the user's learning ability in each subject is re-evaluated. For example, when the user's knowledge mastery level in a certain subject improves significantly, it indicates that the user's learning ability in that subject has increased. The attribute value of the corresponding ability node is increased, and an updated ability node is obtained. The updated ability node can reflect the changes in the user's learning ability in real time, ensuring the accuracy and timeliness of the evaluation results. The attribute data of the updated ability node corresponding to each subject is combined and calculated through weighted summation to obtain the user's learning ability evaluation result. This can comprehensively and objectively evaluate the user's learning ability and provide data support for the formulation of personalized learning plans and development plans.

[0094] Furthermore, the corresponding learning content is generated by combining the user capability assessment results and the node association relationship in the learning graph, including:

[0095] S401. Match a target template library of corresponding difficulty in a preset question template library based on the user ability assessment result;

[0096] S402, by analyzing the node association relationship in the learning graph, assigning a corresponding weight to each node;

[0097] S403: Generate corresponding learning content by combining the target template library and weights through a preset content generation model.

[0098] In this embodiment, users are analyzed based on the results of user ability assessment, including elementary, intermediate, and advanced levels, and each level corresponds to different learning abilities; questions are marked with corresponding difficulty levels in a preset question template library, and the difficulty level is determined by factors such as the number of knowledge points involved in the question, the complexity, and the thinking ability required to solve the question, including simple, medium, and difficult; based on the level corresponding to the user ability assessment result, question templates of corresponding difficulty levels are screened out from the preset question template library to form a target template library; for example, when the user ability is assessed as intermediate, a question template of medium difficulty is selected and put into the target template library; by selecting a target template library of corresponding difficulty, it can be ensured that the difficulty of the learning content is adapted to the user's ability, thereby improving the pertinence and effectiveness of learning and avoiding users from wasting time on questions of inappropriate difficulty.

[0099] Specifically, according to the corresponding node association relationship in the learning graph, the importance of each node is analyzed and weights are assigned to the nodes; by analyzing the association relationship between the nodes in the learning graph, including sequence, cause and effect, inclusion relationship, etc., corresponding weight distribution principles are formulated. For example, nodes that are at the core of the knowledge system and have an important impact on subsequent learning have higher weights; while nodes that are auxiliary and have weaker association have lower weights; this embodiment specifically adopts the hierarchical analysis method to assign weights to each node according to the weight distribution principle; by assigning weights, the generated learning content is more in line with the structure and focus of the knowledge system, and key knowledge will be more reflected and strengthened in the learning content, which will help users better master key knowledge points.

[0100] Specifically, based on the calculated node weights and the corresponding target template library, question templates related to each node are screened out from the target template library. The number of question templates corresponding to knowledge nodes with higher weights can be relatively large to ensure that key knowledge is fully practiced. The screened question templates are combined according to the association relationship and logical order of the nodes in the learning graph. For example, the questions corresponding to the preceding knowledge nodes are arranged first, and then the questions for subsequent related knowledge nodes are arranged to make the learning content coherent; the preset content generation model is used to further process the combined question templates, such as adding necessary instructions and prompts, etc., to finally generate complete learning content; the learning content generated according to the target template library and the corresponding knowledge node weights takes into account the user's ability level, and highlights the key points and logical structure of the knowledge system, thereby improving the efficiency and quality of learning content generation.

[0101] Furthermore, during the user's learning process, the updating of knowledge elements and the changes in the user's learning ability are analyzed, and the learning graph is dynamically updated to obtain an updated learning graph, including:

[0102] S501. During the user's learning process, the update of knowledge elements and the change of the user's learning ability are analyzed to obtain an updated learning status;

[0103] S502: updating the nodes and node connection relationships in the learning graph according to the updated learning state to obtain a first updated learning graph;

[0104] S503: By analyzing the learning ability levels of different users, the structure of the first updated learning graph is updated to obtain an updated learning graph.

[0105] During the user's learning process, this embodiment dynamically updates the nodes and node connection relationships in the learning graph according to changes in the user's learning status, and optimizes the structure of the learning graph according to the learning ability levels of different users, providing each user with a learning path and knowledge system that suits their own characteristics, enhancing the pertinence and effectiveness of learning, and improving the user's learning experience.

[0106] In this embodiment, the learning data of the user's learning process is collected and analyzed in real time to identify newly learned knowledge elements. For example, the course chapters studied by the user, the topics of the materials read, etc. are analyzed to determine whether new knowledge points are introduced. At the same time, the learning time, number of learning times, and other information of each knowledge element are recorded to obtain the frequency and degree of updating of new knowledge points. The changes in the user's learning ability are evaluated from multiple aspects. By comparing the changes in the correct answer rate and answer time of the user for the same knowledge point in different time periods, it is judged whether the user's mastery of knowledge has improved and whether the speed of mastering knowledge has accelerated. Combining these factors, the improvement or change of the user's learning ability is analyzed. The update of knowledge elements and the change of learning ability are integrated to obtain an updated learning status. By analyzing the user's updated learning status, the user's learning progress and ability changes can be timely understood, thereby updating the learning map.

[0107] Specifically, according to the user's updated learning status, the nodes and node connection relationships in the learning map are updated. Specifically, the learning map is updated by adding new knowledge nodes, updating node attributes, and updating node connection relationships. By updating nodes and connection relationships, newly learned knowledge elements and new associations between knowledge can be reflected in a timely manner, ensuring that the learning map is always consistent with the user's learning progress and knowledge mastery, and providing accurate learning navigation.

[0108] Specifically, by analyzing the user's learning ability level, the structure of the learning map is further updated, and users are graded according to their learning ability. For users of different levels, the structure of the learning map is optimized to make it more in line with the learning needs of users of different levels; for example, for users with strong learning ability, a more challenging and in-depth knowledge structure can be provided; for users with weaker learning ability, the map structure can be simplified, highlighting basic knowledge and key content to help them better understand and master knowledge; by optimizing the structure of the learning map, the personalized needs of users with different learning abilities can be met, and the adaptability and effectiveness of learning can be improved.

[0109] Furthermore, according to the updated learning state, the nodes and node connection relationships in the learning graph are updated to obtain a first updated learning graph, including:

[0110] S601: When a new knowledge point is added according to the updated learning state, a corresponding knowledge node is added to the learning graph, and a connection relationship is established between the subject to which the new knowledge point belongs and the existing knowledge nodes to obtain a first updated node;

[0111] S602: When the user's knowledge mastery level improves, the corresponding knowledge node attributes and connection relationships are updated to obtain a second updated node;

[0112] S603: Update the corresponding capability node attributes and connection relationships according to the second update node to obtain a third update node;

[0113] S604: Combine the first update node, the second update node, and the third update node to update the nodes and node connection relationships in the learning graph to obtain a first updated learning graph.

[0114] In this embodiment, according to the user's updated learning status, when the user learns a new knowledge point, a new knowledge node is created based on the newly added knowledge point, and the attributes of the new knowledge point are configured, including the name of the knowledge point, the subject to which it belongs, etc. By analyzing the subject to which the newly added knowledge point belongs and its relationship with the existing knowledge nodes in the learning graph, a connection relationship is established between the newly added knowledge node and the related existing knowledge nodes; the learning graph is updated according to the newly added knowledge node to obtain the first updated node. By timely updating the learning graph, the learning graph is kept consistent with the user's learning progress, thereby updating the learning content accordingly.

[0115] Specifically, according to the user's mastery of the knowledge point, the corresponding knowledge node attributes and connection relationships are updated to obtain the second updated node. According to the user's learning data, including the accuracy of answering questions, homework completion status, test scores, etc., it is evaluated whether the user's mastery of each knowledge node has improved. For example, in a series of tests on the "function" knowledge node, the user's accuracy rate increased from the original 60% to 80%, indicating that the user's mastery of the "function" knowledge has improved. For the knowledge nodes with improved knowledge mastery, their attributes are updated and their mastery values ​​are increased accordingly. According to the association between knowledge nodes, considering that the improvement of the mastery of a knowledge node will enhance the association strength with other related knowledge nodes, the node connection relationship is updated. For example, the improvement of the mastery of "function" knowledge will make the connection between the knowledge node and the "derivative" knowledge node closer, because function is the basis of derivative, and a high mastery of function knowledge helps to understand derivative. At this time, the weight of the connecting edge between the two nodes can be increased to update the connection relationship; thereby accurately reflecting the changes in the user's knowledge mastery.

[0116] Specifically, according to the changes in the user's mastery of the knowledge node in the second update node, the corresponding capability node is updated to obtain the third update node; first, the capability node related to the second update node is determined; according to the update of the knowledge node, the attributes of the relevant capability node are updated, the attribute value of the corresponding capability node is improved, and the connection relationship between the capability node and the knowledge node is updated. By updating the capability node, the changes in user learning can be reflected from the perspective of capability, providing a more accurate capability-level basis for the formulation of personalized learning plans, making the learning plan more targeted.

[0117] At the same time, all new nodes and updated nodes in the first update node, the second update node and the third update node are merged into the learning graph, the learning graph is updated to obtain the first updated learning graph, and the connection relationship between the updated nodes is checked and adjusted to ensure the accuracy and logic of the connection relationship and avoid isolated nodes or unreasonable connections. By updating the learning graph, the user's knowledge growth and ability improvement in the learning process can be reflected in real time and dynamically, so as to formulate more targeted learning plans and learning content for users and improve learning effects.

[0118] Furthermore, the structure of the first updated learning graph is updated by analyzing the learning ability levels of different users to obtain an updated learning graph, including:

[0119] S701: Classify users according to their learning abilities using a preset learning ability evaluation model to obtain multiple levels of users, wherein the multiple levels of users include primary users, intermediate users, and advanced users;

[0120] S702: For the primary user, simplify the structure of the first updated learning graph to obtain an updated learning graph for the primary user;

[0121] S703: For the intermediate user, an updated learning graph for the intermediate user is obtained by improving the node association relationship between the knowledge nodes in the first updated learning graph;

[0122] S704: For advanced users, expand knowledge nodes in the first updated learning graph to obtain an updated learning graph for the advanced users.

[0123] In this embodiment, users are graded according to their learning abilities, taking into account factors such as the degree of knowledge mastery, learning speed, problem-solving ability, and learning initiative, and the user's learning ability is evaluated through a preset learning ability evaluation model. The learning ability evaluation model can be a statistical analysis model, a machine learning model, etc. The learning ability evaluation model in this embodiment is specifically a decision tree model. The decision tree model is trained using a large amount of historical data to obtain a pre-trained learning ability evaluation model. The user's learning ability evaluation factors are input into the pre-trained learning ability evaluation model, and the model outputs the user's grade division results, including primary, intermediate, and advanced users; users are graded according to their learning abilities, and different structural optimizations can be performed on the learning map for users of different levels, thereby formulating corresponding personalized learning plans; by performing targeted learning map updates for users of different learning ability levels, personalized learning support is provided for each user, meeting the needs of users at different learning stages.

[0124] like Figure 3 As shown, for novice users, the first updated learning graph is structurally simplified and the learning graph is updated. According to the characteristics of novice users, corresponding simplified learning graph strategies are formulated, for example, the number of knowledge nodes is reduced, the core knowledge points are retained, and the connection relationships between knowledge points are updated; by screening out the core knowledge nodes, simplifying the connection relationships between knowledge nodes, and retaining the most direct and important associations, an updated learning graph for novice users is obtained; by simplifying the structure, the learning difficulty can be reduced, making it easier for novice users to start learning, and helping novice users concentrate on learning core knowledge.

[0125] like Figure 4 As shown, for intermediate users, by improving the correlation between knowledge nodes between the first updated learning graph and updating the learning graph, intermediate users can better understand the systematic and logical nature of knowledge and promote the integration of knowledge; according to the learning needs and knowledge system of intermediate users, the knowledge nodes that need to enhance the correlation are determined, including the knowledge nodes that need to be mastered in the intermediate learning stage and the knowledge nodes that are closely related to other important knowledge points; by shortening the length of the connecting edge and increasing the weight of the connecting edge, the correlation between the selected knowledge nodes is enhanced, and after the correlation is enhanced, an updated learning graph for the intermediate user is obtained; by enhancing the correlation between knowledge nodes, intermediate users can deepen their understanding of knowledge, improve their ability to apply knowledge, promote the improvement and systematization of the intermediate user's knowledge system, and cultivate their logical thinking ability.

[0126] like Figure 5As shown in the figure, for advanced users, by expanding knowledge nodes in the first updated learning graph, the learning graph is updated to meet the learning needs of advanced users and further improve their learning ability and knowledge level; according to the learning goals and subject areas of advanced users, the direction of knowledge node expansion is determined. For example, in the computer science learning graph, knowledge nodes are expanded to cutting-edge fields such as artificial intelligence, big data, and cloud computing; in the first updated learning graph, knowledge nodes related to the expansion direction are added. Knowledge nodes include more in-depth professional knowledge, the latest research results, interdisciplinary knowledge integration, etc., and corresponding node attributes are given to each expanded knowledge node, including node name, field, difficulty level, etc.; a connection relationship is established between the newly added expanded knowledge node and the relevant knowledge node in the original learning graph, and the corresponding connection relationship is determined and connected by analyzing the logical connection between the knowledge nodes. After completing the knowledge node expansion and the establishment of the connection relationship, an updated learning graph for advanced users is obtained; by expanding the knowledge nodes, the needs of advanced users for in-depth exploration of knowledge can be met, and advanced users can be helped to broaden their knowledge and cultivate interdisciplinary thinking ability and comprehensive literacy.

[0127] Furthermore, according to the updated learning graph, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to achieve intelligent adjustment of learning difficulty, including:

[0128] S801. Analyze the user's knowledge mastery of each knowledge node based on the updated learning graph to obtain an updated knowledge mastery level.

[0129] S802: Based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path;

[0130] S803: Match the update node path in a preset question template library to obtain an update template;

[0131] S804: Based on the update template, corresponding updated learning content is generated through a preset content update model to achieve intelligent adjustment of learning difficulty.

[0132] In this embodiment, based on the updated learning graph, the user's knowledge mastery level is analyzed for each knowledge node, the learning status of the user in the learning process is updated to obtain the updated knowledge mastery level, the learning data corresponding to each knowledge node is extracted from the updated learning graph, and the corresponding knowledge mastery level score is calculated based on the learning data to obtain the updated knowledge mastery level of each knowledge node; based on the calculated updated knowledge mastery level, the knowledge nodes that need to be focused on or further studied are screened out in the updated learning graph, and based on the correlation between the nodes, the learning path is determined to obtain the updated node path; by screening out the updated node path, users can learn weak knowledge in a targeted manner, gradually improve the knowledge system, and improve learning effects.

[0133] Specifically, according to the update node path, matching is performed in the preset question template library. By analyzing the knowledge nodes in the update node path and the learning order and focus of the knowledge, the corresponding question templates are screened out in the preset question template library. According to the order of the update node path, the screened question templates are combined to obtain the updated template. By screening the question combination suitable for the user's learning path in the question template library, it can be ensured that the learning content is closely matched with the user's current learning needs and knowledge mastery, thereby improving the pertinence and effectiveness of learning.

[0134] Specifically, according to the screened update templates, the corresponding learning content is updated through the preset content update model; according to the user's learning ability assessment results and the updated knowledge mastery level, relevant parameters are set for the content update model, and the update template is input into the preset content update model. The model processes the question template according to the set parameters and built-in rules, including modifying and supplementing the questions, adjusting the order of questions, adding auxiliary content such as problem-solving ideas and knowledge point explanations. After processing by the content update model, the complete updated learning content is output to achieve intelligent adjustment of learning difficulty to meet the user's current learning needs; by updating the learning content, highly personalized learning content can be generated to accurately match the user's learning ability and knowledge mastery level, and intelligently adjust the difficulty of the learning content, which can stimulate the user's interest in learning, avoid the decline in learning motivation due to inappropriate difficulty, and effectively improve learning effects.

[0135] Furthermore, based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path, including:

[0136] S901: Based on the updated knowledge mastery level, extract nodes whose corresponding knowledge mastery level changes are greater than a preset threshold value from the updated learning graph to obtain a plurality of knowledge nodes to be updated;

[0137] S902: Analyze the association relationship between knowledge nodes, connect the multiple knowledge nodes to be updated, and obtain an update node path.

[0138] In this embodiment, a threshold value for the change in knowledge mastery is pre-set based on the characteristics of the learning content and the learning objectives. For example, for basic knowledge points, the threshold value is set to 15%; for more difficult knowledge points, the threshold value is set to 10%; the currently updated knowledge mastery level is compared with the previously recorded knowledge mastery level, and the change in the mastery level of each knowledge node is calculated. For example, the last mastery level of a knowledge node was 60%, and the current updated mastery level is 75%, then its change is 15%; all knowledge nodes in the updated learning graph are traversed, and the calculated change in mastery level is compared with the preset threshold value. When the change is greater than the preset threshold value, the knowledge node is extracted as the knowledge node to be updated; for example, if the preset threshold value is 10%, and the calculated change in the mastery level of the knowledge node is 15%, it is included in the set of knowledge nodes to be updated. By quickly screening out knowledge nodes that have changed significantly during the user's learning process, blind searching among a large number of knowledge nodes is avoided, thereby improving the efficiency of learning planning.

[0139] Specifically, based on the screened knowledge nodes to be updated, for each knowledge node to be updated, the association relationship between it and other knowledge nodes to be updated is searched in the update learning map, and the starting node of the path is determined from the knowledge nodes to be updated according to the logical order of knowledge and the learning rules, and the basic knowledge node is selected as the starting node; according to the association relationship between knowledge nodes, starting from the starting node, other knowledge nodes to be updated are connected in sequence to form an update node path. During the connection process, the continuity and logic of the path are ensured. When there are multiple knowledge nodes to be updated and the associations between them are more complex, multiple paths can be constructed to meet different learning needs. For example, starting from the "quadratic equation" node, connect to the "quadratic function" node, and then connect to the "using quadratic function to solve practical problems" node to form a complete update node path; by connecting knowledge nodes, users can learn knowledge systematically, avoid knowledge fragmentation, and improve learning effects.

[0140] Example 2

[0141] In this embodiment, if Figure 6 , provides a device for intelligently adjusting learning difficulty, for implementing the aforementioned method for intelligently adjusting learning difficulty, comprising:

[0142] The learning graph construction module extracts key knowledge elements from pre-acquired user learning data and constructs a learning graph;

[0143] A user evaluation module analyzes the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability evaluation result;

[0144] A learning content generation module generates corresponding learning content based on the user capability assessment results and the node association relationship in the learning graph, wherein the nodes include knowledge nodes and capability nodes;

[0145] A learning graph update module analyzes the update of knowledge elements and changes in user learning ability during the user's learning process, and dynamically updates the learning graph to obtain an updated learning graph;

[0146] The learning difficulty adjustment module adjusts the difficulty of the learning content in real time according to the updated learning map to obtain updated learning content, so as to realize intelligent adjustment of learning difficulty.

[0147] In this embodiment, the learning graph construction module is responsible for extracting key knowledge elements from the pre-acquired user learning data and constructing a learning graph. By mining and organizing the learning data, the knowledge is presented in the form of a graph, which clearly shows the relationship between each knowledge element, so as to facilitate the system to fully understand the knowledge system and the user's learning content; the user evaluation module analyzes the user's knowledge mastery and learning ability based on the learning graph, and obtains the user ability assessment results. By analyzing the user's performance at each knowledge node and ability node in the learning graph, including the understanding, mastery and application of knowledge points, as well as the comprehensive performance in different learning tasks, the user's level and ability characteristics in knowledge learning are evaluated.

[0148] Specifically, the learning content generation module combines the user's ability assessment results and the relationship between knowledge nodes and ability nodes in the learning map to generate learning content suitable for the user. According to the user's ability level, knowledge nodes of corresponding difficulty and correlation are selected from the learning map, and organized into targeted learning materials, including exercises, explanation documents, video tutorials, etc., to ensure that the generated learning content is in line with the user's existing knowledge level and can help users gradually improve their abilities, achieve effective knowledge accumulation and gradual improvement of abilities; the learning map update module continuously pays attention to the update of knowledge elements and changes in user learning abilities during the user's learning process, and dynamically updates the learning map. When users learn new knowledge, master new skills, or understand existing knowledge, When deepening, the nodes and connection relationships in the learning map are adjusted in time to adapt to changes in the user's learning progress and knowledge structure; by continuously updating the learning map, the system can always analyze and make decisions based on the user's latest status to ensure the adaptability and effectiveness of the learning content; the learning difficulty adjustment module adjusts the difficulty of the learning content in real time according to the updated learning map, and generates updated learning content to achieve intelligent adjustment of learning difficulty. By analyzing the user's mastery of each knowledge node in the updated learning map, the user's learning progress and ability improvement are determined, and a suitable question template is selected from the preset question template library. The content that meets the user's current learning difficulty is generated through the content update model, realizing intelligent adjustment of the difficulty of the learning content and improving learning effect and efficiency.

[0149] The basic principles, main features, and advantages of the present invention are shown and described above. Those skilled in the art should understand that the present invention is not limited to the above embodiments. The above embodiments and descriptions are merely illustrative of the principles of the present invention. Various changes and modifications may be made to the present invention without departing from the spirit and scope of the present invention. Such changes and modifications are intended to fall within the scope of the present invention. The scope of protection claimed in the present invention is defined by the appended claims and their equivalents.

Claims

1. A method for intelligently adjusting learning difficulty, characterized in that: include: Extract key knowledge elements from pre-acquired user learning data and construct a learning graph; Analyze the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability assessment result; Combining the user capability assessment results with the node association relationship in the learning graph to generate corresponding learning content, wherein the nodes include knowledge nodes and capability nodes; During the user's learning process, the update of knowledge elements and the change of the user's learning ability are analyzed, and the learning map is dynamically updated to obtain an updated learning map; According to the updated learning map, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to realize intelligent adjustment of learning difficulty.

2. The method for intelligently adjusting learning difficulty according to claim 1, characterized in that: Extracting key knowledge elements from pre-acquired user learning data and constructing a learning graph includes: Based on the pre-acquired user learning data, the corresponding knowledge points are extracted to obtain the key knowledge elements; The key knowledge elements are used as knowledge nodes, and the corresponding knowledge nodes are connected by analyzing the association relationship between the key knowledge elements to obtain an initial learning graph; The user learning data is fused and mapped to the initial learning graph to obtain a corresponding learning graph.

3. The method for intelligently adjusting learning difficulty according to claim 1, characterized in that: Based on the learning graph, the user's knowledge mastery and learning ability are analyzed to obtain user ability assessment results, including: Based on the correlation between knowledge nodes in the learning graph, the user's answer situation at each knowledge node is analyzed to obtain the user's knowledge mastery level; Aggregate the knowledge nodes reflecting different subject knowledge points in the learning graph to obtain multiple types of subject nodes; For each subject node, the user's knowledge mastery level is evaluated separately to obtain the knowledge mastery level of each subject; According to the mastery level of each subject knowledge, add corresponding ability nodes to each subject node and connect them; During the user's learning process, the attributes of the capability node are dynamically updated according to the changes in the user's mastery of each subject knowledge to obtain an updated capability node; Combined with the update capability nodes corresponding to each subject, the user's learning ability is evaluated to obtain the user's ability evaluation results.

4. The method for intelligently adjusting learning difficulty according to claim 1, wherein: Combining the user capability assessment results with the node association relationships in the learning graph, corresponding learning content is generated, including: According to the user's ability assessment results, the target template library of corresponding difficulty is matched in the preset question template library; By analyzing the node association relationship in the learning graph, corresponding weights are assigned to each node; In combination with the target template library and weights, corresponding learning content is generated through a preset content generation model.

5. The method for intelligently adjusting learning difficulty according to claim 1, characterized in that: During the user's learning process, the update of knowledge elements and changes in the user's learning ability are analyzed, and the learning graph is dynamically updated to obtain an updated learning graph, including: During the user's learning process, the update of knowledge elements and changes in user learning ability are analyzed to obtain updated learning status; According to the updated learning state, updating the nodes and node connection relationships in the learning graph to obtain a first updated learning graph; By analyzing the learning ability levels of different users, the structure of the first updated learning graph is updated to obtain an updated learning graph.

6. The method for intelligently adjusting learning difficulty according to claim 5, characterized in that: According to the updated learning state, updating the nodes and node connection relationships in the learning graph to obtain a first updated learning graph includes: According to the updated learning status, when a new knowledge point is added, the corresponding knowledge node is added to the learning map, and the connection relationship between the subject to which the new knowledge point belongs and the existing knowledge nodes is established to obtain the first updated node; When the user's knowledge mastery level improves, the corresponding knowledge node attributes and connection relationships are updated to obtain a second updated node; According to the second update node, the corresponding capability node attributes and connection relationships are updated to obtain a third update node; In combination with the first update node, the second update node and the third update node, the nodes and node connection relationships in the learning graph are updated to obtain a first updated learning graph.

7. The method for intelligently adjusting learning difficulty according to claim 5, characterized in that: The updating of the structure of the first updated learning graph by analyzing the learning ability levels of different users to obtain an updated learning graph includes: According to the user's learning ability, the user is graded by a preset learning ability evaluation model to obtain multiple levels of users, wherein the multiple levels of users include primary users, intermediate users and advanced users; For the primary user, the structure of the first update learning graph is simplified to obtain the update learning graph of the primary user; For intermediate users, an updated learning graph for intermediate users is obtained by improving the node association relationship between knowledge nodes in the first updated learning graph; For advanced users, knowledge nodes are expanded in the first updated learning graph to obtain an updated learning graph for advanced users.

8. The method for intelligently adjusting learning difficulty according to claim 1, characterized in that: According to the updated learning graph, the difficulty of the learning content is adjusted in real time to obtain updated learning content, so as to achieve intelligent adjustment of learning difficulty, including: According to the updated learning graph, the user's knowledge mastery of each knowledge node is analyzed to obtain the updated knowledge mastery level; Based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path; Matching the update node path in a preset question template library to obtain an update template; Based on the update template, corresponding updated learning content is generated through a preset content update model to achieve intelligent adjustment of learning difficulty.

9. The method for intelligently adjusting learning difficulty according to claim 8, characterized in that: Based on the mastery level of the updated knowledge, matching is performed in the updated learning graph to obtain an updated node path, including: Based on the updated knowledge mastery level, extracting nodes corresponding to knowledge mastery level changes greater than a preset threshold value from the updated learning graph to obtain a plurality of knowledge nodes to be updated; By analyzing the association relationship between the knowledge nodes, the multiple knowledge nodes to be updated are connected to obtain an update node path.

10. A device for intelligently adjusting learning difficulty, characterized in that: A method for intelligently adjusting learning difficulty according to any one of claims 1 to 9, comprising: The learning graph construction module extracts key knowledge elements from pre-acquired user learning data and constructs a learning graph; A user evaluation module analyzes the user's knowledge mastery and learning ability based on the learning graph to obtain a user ability evaluation result; A learning content generation module generates corresponding learning content based on the user capability assessment results and the node association relationship in the learning graph, wherein the nodes include knowledge nodes and capability nodes; A learning graph update module analyzes the update of knowledge elements and changes in user learning ability during the user's learning process, and dynamically updates the learning graph to obtain an updated learning graph; The learning difficulty adjustment module adjusts the difficulty of the learning content in real time according to the updated learning map to obtain updated learning content, so as to realize intelligent adjustment of learning difficulty.

Images